diff options
| author | Dave Airlie <airlied@redhat.com> | 2023-10-03 06:02:29 +1000 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2023-10-03 06:02:30 +1000 |
| commit | caacbdc28f545744770fb2caf347b3c4be9a6299 (patch) | |
| tree | 4f6f46bf09daa991b5b8d8ff72d35e9cbc85b5d9 /drivers/gpu | |
| parent | 79fb229b8810071648b65c37382aea7819a5f935 (diff) | |
| parent | 03d681412b38558aefe4fb0f46e36efa94bb21ef (diff) | |
Merge tag 'drm-intel-gt-next-2023-09-28' of git://anongit.freedesktop.org/drm/drm-intel into drm-next
Driver Changes:
Fixes/improvements/new stuff:
- Fix TLB-Invalidation seqno store [mtl] (Alan Previn)
- Force a reset on internal GuC error [guc] (John Harrison)
- Define GSC fw [gsc] (Daniele Ceraolo Spurio)
- Update workaround 14016712196 [dg2/mtl] (Tejas Upadhyay)
- Mark requests for GuC virtual engines to avoid use-after-free (Andrzej Hajda)
- Add Wa_14015150844 [dg2/mtl] (Shekhar Chauhan)
- Prevent error pointer dereference (Dan Carpenter)
- Add Wa_18022495364 [tgl,adl,rpl] (Dnyaneshwar Bhadane)
- Fix GuC PMU by moving execlist stats initialization to execlist specific setup (Umesh Nerlige Ramappa)
- Fix PXP firmware load [pxp/mtl] (Alan Previn)
- Fix execution/context state of PXP contexts (Alan Previn)
- Limit the length of an sg list to the requested length (Matthew Wilcox)
- Fix reservation address in ggtt_reserve_guc_top [guc] (Javier Pello)
- Add Wa_18028616096 [dg2] (Shekhar Chauhan)
- Get runtime pm in busyness worker only if already active [guc/pmu] (Umesh Nerlige Ramappa)
- Don't set PIPE_CONTROL_FLUSH_L3 for aux inval (Nirmoy Das)
Future platform enablement:
- Fix and consolidate some workaround checks, make others IP version based [mtl] (Matt Roper)
- Replace Meteorlake subplatforms with IP version checks (Matt Roper)
- Adding DeviceID for Arrowlake-S under MTL [mtl] (Nemesa Garg)
- Run relevant bits of debugfs drop_caches per GT (Tvrtko Ursulin)
Miscellaneous:
- Remove Wa_15010599737 [dg2] (Shekhar Chauhan)
- Align igt_spinner_create_request with hangcheck [selftests] (Jonathan Cavitt)
- Remove pre-production workarounds [dg2] (Matt Roper)
- Tidy some workaround definitions (Matt Roper)
- Wait longer for tasks in migrate selftest [gt] (Jonathan Cavitt)
- Skip WA verification for GEN7_MISCCPCTL on DG2 [gt] (Andrzej Hajda)
- Silence injected failure in the load via GSC path [huc] (Daniele Ceraolo Spurio)
- Refactor deprecated strncpy (Justin Stitt)
- Update RC6 mask for mtl_drpc [debugfs/mtl] (Badal Nilawar)
- Remove a static inline that requires including i915_drv.h [gt] (Jani Nikula)
- Remove inlines from i915_gem_execbuffer.c [gem] (Jani Nikula)
- Remove gtt_offset from stream->oa_buffer.head/.tail [perf] (Ashutosh Dixit)
- Do not disable preemption for resets (Tvrtko Ursulin)
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/ZRVzL02VFuwIkcGl@tursulin-desk
Diffstat (limited to 'drivers/gpu')
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; regs[CTX_TIMESTAMP] = ce->stats.runtime.last; @@ -1094,6 +1117,9 @@ __lrc_alloc_state(struct intel_context *ce, struct intel_engine_cs *engine) I915_BO_ALLOC_PM_VOLATILE); if (IS_ERR(obj)) { obj = i915_gem_object_create_shmem(engine->i915, context_size); + if (IS_ERR(obj)) + return ERR_CAST(obj); + /* * Wa_22016122933: For Media version 13.0, all Media GT shared * memory needs to be mapped as WC on CPU side and UC (PAT @@ -1102,8 +1128,6 @@ __lrc_alloc_state(struct intel_context *ce, struct intel_engine_cs *engine) if (intel_gt_needs_wa_22016122933(engine->gt)) i915_gem_object_set_cache_coherency(obj, I915_CACHE_NONE); } - if (IS_ERR(obj)) - return ERR_CAST(obj); vma = i915_vma_instance(obj, &engine->gt->ggtt->vm, NULL); if (IS_ERR(vma)) { @@ -1316,29 +1340,6 @@ gen12_emit_cmd_buf_wa(const struct intel_context *ce, u32 *cs) } /* - * On DG2 during context restore of a preempted context in GPGPU mode, - * RCS restore hang is detected. This is extremely timing dependent. - * To address this below sw wabb is implemented for DG2 A steppings. - */ -static u32 * -dg2_emit_rcs_hang_wabb(const struct intel_context *ce, u32 *cs) -{ - *cs++ = MI_LOAD_REGISTER_IMM(1); - *cs++ = i915_mmio_reg_offset(GEN12_STATE_ACK_DEBUG(ce->engine->mmio_base)); - *cs++ = 0x21; - - *cs++ = MI_LOAD_REGISTER_REG; - *cs++ = i915_mmio_reg_offset(RING_NOPID(ce->engine->mmio_base)); - *cs++ = i915_mmio_reg_offset(XEHP_CULLBIT1); - - *cs++ = MI_LOAD_REGISTER_REG; - *cs++ = i915_mmio_reg_offset(RING_NOPID(ce->engine->mmio_base)); - *cs++ = i915_mmio_reg_offset(XEHP_CULLBIT2); - - return cs; -} - -/* * The bspec's tuning guide asks us to program a vertical watermark value of * 0x3FF. However this register is not saved/restored properly by the * hardware, so we're required to apply the desired value via INDIRECT_CTX @@ -1356,27 +1357,34 @@ dg2_emit_draw_watermark_setting(u32 *cs) } static u32 * +gen12_invalidate_state_cache(u32 *cs) +{ + *cs++ = MI_LOAD_REGISTER_IMM(1); + *cs++ = i915_mmio_reg_offset(GEN12_CS_DEBUG_MODE2); + *cs++ = _MASKED_BIT_ENABLE(INSTRUCTION_STATE_CACHE_INVALIDATE); + return cs; +} + +static u32 * gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs) { cs = gen12_emit_timestamp_wa(ce, cs); cs = gen12_emit_cmd_buf_wa(ce, cs); cs = gen12_emit_restore_scratch(ce, cs); - /* Wa_22011450934:dg2 */ - if (IS_DG2_GRAPHICS_STEP(ce->engine->i915, G10, STEP_A0, STEP_B0) || - IS_DG2_GRAPHICS_STEP(ce->engine->i915, G11, STEP_A0, STEP_B0)) - cs = dg2_emit_rcs_hang_wabb(ce, cs); - /* Wa_16013000631:dg2 */ - if (IS_DG2_GRAPHICS_STEP(ce->engine->i915, G10, STEP_B0, STEP_C0) || - IS_DG2_G11(ce->engine->i915)) + if (IS_DG2_G11(ce->engine->i915)) cs = gen8_emit_pipe_control(cs, PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE, 0); cs = gen12_emit_aux_table_inv(ce->engine, cs); + /* Wa_18022495364 */ + if (IS_GFX_GT_IP_RANGE(ce->engine->gt, IP_VER(12, 0), IP_VER(12, 10))) + cs = gen12_invalidate_state_cache(cs); + /* Wa_16014892111 */ - if (IS_MTL_GRAPHICS_STEP(ce->engine->i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(ce->engine->i915, P, STEP_A0, STEP_B0) || + if (IS_GFX_GT_IP_STEP(ce->engine->gt, IP_VER(12, 70), STEP_A0, STEP_B0) || + IS_GFX_GT_IP_STEP(ce->engine->gt, IP_VER(12, 71), STEP_A0, STEP_B0) || IS_DG2(ce->engine->i915)) cs = dg2_emit_draw_watermark_setting(cs); @@ -1390,8 +1398,7 @@ gen12_emit_indirect_ctx_xcs(const struct intel_context *ce, u32 *cs) cs = gen12_emit_restore_scratch(ce, cs); /* Wa_16013000631:dg2 */ - if (IS_DG2_GRAPHICS_STEP(ce->engine->i915, G10, STEP_B0, STEP_C0) || - IS_DG2_G11(ce->engine->i915)) + if (IS_DG2_G11(ce->engine->i915)) if (ce->engine->class == COMPUTE_CLASS) cs = gen8_emit_pipe_control(cs, PIPE_CONTROL_INSTRUCTION_CACHE_INVALIDATE, diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c index 2c014407225c..07269ff3be13 100644 --- a/drivers/gpu/drm/i915/gt/intel_mocs.c +++ b/drivers/gpu/drm/i915/gt/intel_mocs.c @@ -404,18 +404,6 @@ static const struct drm_i915_mocs_entry dg2_mocs_table[] = { MOCS_ENTRY(3, 0, L3_3_WB | L3_LKUP(1)), }; -static const struct drm_i915_mocs_entry dg2_mocs_table_g10_ax[] = { - /* Wa_14011441408: Set Go to Memory for MOCS#0 */ - MOCS_ENTRY(0, 0, L3_1_UC | L3_GLBGO(1) | L3_LKUP(1)), - /* UC - Coherent; GO:Memory */ - MOCS_ENTRY(1, 0, L3_1_UC | L3_GLBGO(1) | L3_LKUP(1)), - /* UC - Non-Coherent; GO:Memory */ - MOCS_ENTRY(2, 0, L3_1_UC | L3_GLBGO(1)), - - /* WB - LC */ - MOCS_ENTRY(3, 0, L3_3_WB | L3_LKUP(1)), -}; - static const struct drm_i915_mocs_entry pvc_mocs_table[] = { /* Error */ MOCS_ENTRY(0, 0, L3_3_WB), @@ -507,7 +495,7 @@ static unsigned int get_mocs_settings(const struct drm_i915_private *i915, memset(table, 0, sizeof(struct drm_i915_mocs_table)); table->unused_entries_index = I915_MOCS_PTE; - if (IS_METEORLAKE(i915)) { + if (IS_GFX_GT_IP_RANGE(&i915->gt0, IP_VER(12, 70), IP_VER(12, 71))) { table->size = ARRAY_SIZE(mtl_mocs_table); table->table = mtl_mocs_table; table->n_entries = MTL_NUM_MOCS_ENTRIES; @@ -521,13 +509,8 @@ static unsigned int get_mocs_settings(const struct drm_i915_private *i915, table->wb_index = 2; table->unused_entries_index = 2; } else if (IS_DG2(i915)) { - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) { - table->size = ARRAY_SIZE(dg2_mocs_table_g10_ax); - table->table = dg2_mocs_table_g10_ax; - } else { - table->size = ARRAY_SIZE(dg2_mocs_table); - table->table = dg2_mocs_table; - } + table->size = ARRAY_SIZE(dg2_mocs_table); + table->table = dg2_mocs_table; table->uc_index = 1; table->n_entries = GEN9_NUM_MOCS_ENTRIES; table->unused_entries_index = 3; diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c index 58bb1c55294c..8b67abd720be 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6.c +++ b/drivers/gpu/drm/i915/gt/intel_rc6.c @@ -118,14 +118,12 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6) GEN6_RC_CTL_EI_MODE(1); /* - * Wa_16011777198 and BSpec 52698 - Render powergating must be off. + * BSpec 52698 - Render powergating must be off. * FIXME BSpec is outdated, disabling powergating for MTL is just * temporary wa and should be removed after fixing real cause * of forcewake timeouts. */ - if (IS_METEORLAKE(gt->i915) || - IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_C0) || - IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_B0)) + if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71))) pg_enable = GEN9_MEDIA_PG_ENABLE | GEN11_MEDIA_SAMPLER_PG_ENABLE; @@ -526,8 +524,7 @@ static bool rc6_supported(struct intel_rc6 *rc6) return false; } - if (IS_MTL_MEDIA_STEP(gt->i915, STEP_A0, STEP_B0) && - gt->type == GT_MEDIA) { + if (IS_MEDIA_GT_IP_STEP(gt, IP_VER(13, 0), STEP_A0, STEP_B0)) { drm_notice(&i915->drm, "Media RC6 disabled on A step\n"); return false; diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index cc6bd21a3e51..a21e939fdbf6 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -161,16 +161,16 @@ static int i915_do_reset(struct intel_gt *gt, struct pci_dev *pdev = to_pci_dev(gt->i915->drm.dev); int err; - /* Assert reset for at least 20 usec, and wait for acknowledgement. */ + /* Assert reset for at least 50 usec, and wait for acknowledgement. */ pci_write_config_byte(pdev, I915_GDRST, GRDOM_RESET_ENABLE); udelay(50); - err = wait_for_atomic(i915_in_reset(pdev), 50); + err = _wait_for_atomic(i915_in_reset(pdev), 50000, 0); /* Clear the reset request. */ pci_write_config_byte(pdev, I915_GDRST, 0); udelay(50); if (!err) - err = wait_for_atomic(!i915_in_reset(pdev), 50); + err = _wait_for_atomic(!i915_in_reset(pdev), 50000, 0); return err; } @@ -190,7 +190,7 @@ static int g33_do_reset(struct intel_gt *gt, struct pci_dev *pdev = to_pci_dev(gt->i915->drm.dev); pci_write_config_byte(pdev, I915_GDRST, GRDOM_RESET_ENABLE); - return wait_for_atomic(g4x_reset_complete(pdev), 50); + return _wait_for_atomic(g4x_reset_complete(pdev), 50000, 0); } static int g4x_do_reset(struct intel_gt *gt, @@ -207,7 +207,7 @@ static int g4x_do_reset(struct intel_gt *gt, pci_write_config_byte(pdev, I915_GDRST, GRDOM_MEDIA | GRDOM_RESET_ENABLE); - ret = wait_for_atomic(g4x_reset_complete(pdev), 50); + ret = _wait_for_atomic(g4x_reset_complete(pdev), 50000, 0); if (ret) { GT_TRACE(gt, "Wait for media reset failed\n"); goto out; @@ -215,7 +215,7 @@ static int g4x_do_reset(struct intel_gt *gt, pci_write_config_byte(pdev, I915_GDRST, GRDOM_RENDER | GRDOM_RESET_ENABLE); - ret = wait_for_atomic(g4x_reset_complete(pdev), 50); + ret = _wait_for_atomic(g4x_reset_complete(pdev), 50000, 0); if (ret) { GT_TRACE(gt, "Wait for render reset failed\n"); goto out; @@ -705,7 +705,7 @@ static int __reset_guc(struct intel_gt *gt) static bool needs_wa_14015076503(struct intel_gt *gt, intel_engine_mask_t engine_mask) { - if (!IS_METEORLAKE(gt->i915) || !HAS_ENGINE(gt, GSC0)) + if (MEDIA_VER_FULL(gt->i915) != IP_VER(13, 0) || !HAS_ENGINE(gt, GSC0)) return false; if (!__HAS_ENGINE(engine_mask, GSC0)) @@ -785,9 +785,7 @@ int __intel_gt_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask) reset_mask = wa_14015076503_start(gt, engine_mask, !retry); GT_TRACE(gt, "engine_mask=%x\n", reset_mask); - preempt_disable(); ret = reset(gt, reset_mask, retry); - preempt_enable(); wa_14015076503_end(gt, reset_mask); } @@ -1632,6 +1630,24 @@ void __intel_fini_wedge(struct intel_wedge_me *w) w->gt = NULL; } +/* + * Wa_22011802037 requires that we (or the GuC) ensure that no command + * streamers are executing MI_FORCE_WAKE while an engine reset is initiated. + */ +bool intel_engine_reset_needs_wa_22011802037(struct intel_gt *gt) +{ + if (GRAPHICS_VER(gt->i915) < 11) + return false; + + if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_A0, STEP_B0)) + return true; + + if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 70)) + return false; + + return true; +} + #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftest_reset.c" #include "selftest_hangcheck.c" diff --git a/drivers/gpu/drm/i915/gt/intel_reset.h b/drivers/gpu/drm/i915/gt/intel_reset.h index 25c975b6e8fc..f615b30b81c5 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.h +++ b/drivers/gpu/drm/i915/gt/intel_reset.h @@ -78,4 +78,6 @@ void __intel_fini_wedge(struct intel_wedge_me *w); bool intel_has_gpu_reset(const struct intel_gt *gt); bool intel_has_reset_engine(const struct intel_gt *gt); +bool intel_engine_reset_needs_wa_22011802037(struct intel_gt *gt); + #endif /* I915_RESET_H */ diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index 092542f53aad..4feef874e6d6 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -1161,7 +1161,7 @@ void gen6_rps_get_freq_caps(struct intel_rps *rps, struct intel_rps_freq_caps *c { struct drm_i915_private *i915 = rps_to_i915(rps); - if (IS_METEORLAKE(i915)) + if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) return mtl_get_freq_caps(rps, caps); else return __gen6_rps_get_freq_caps(rps, caps); diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 3ae0dbd39eaa..b86a10b1f534 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -764,68 +764,41 @@ static void dg2_ctx_workarounds_init(struct intel_engine_cs *engine, { dg2_ctx_gt_tuning_init(engine, wal); - /* Wa_16011186671:dg2_g11 */ - if (IS_DG2_GRAPHICS_STEP(engine->i915, G11, STEP_A0, STEP_B0)) { - wa_mcr_masked_dis(wal, VFLSKPD, DIS_MULT_MISS_RD_SQUASH); - wa_mcr_masked_en(wal, VFLSKPD, DIS_OVER_FETCH_CACHE); - } - - if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0)) { - /* Wa_14010469329:dg2_g10 */ - wa_mcr_masked_en(wal, XEHP_COMMON_SLICE_CHICKEN3, - XEHP_DUAL_SIMD8_SEQ_MERGE_DISABLE); - - /* - * Wa_22010465075:dg2_g10 - * Wa_22010613112:dg2_g10 - * Wa_14010698770:dg2_g10 - */ - wa_mcr_masked_en(wal, XEHP_COMMON_SLICE_CHICKEN3, - GEN12_DISABLE_CPS_AWARE_COLOR_PIPE); - } - /* Wa_16013271637:dg2 */ wa_mcr_masked_en(wal, XEHP_SLICE_COMMON_ECO_CHICKEN1, MSC_MSAA_REODER_BUF_BYPASS_DISABLE); /* Wa_14014947963:dg2 */ - if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_B0, STEP_FOREVER) || - IS_DG2_G11(engine->i915) || IS_DG2_G12(engine->i915)) - wa_masked_field_set(wal, VF_PREEMPTION, PREEMPTION_VERTEX_COUNT, 0x4000); + wa_masked_field_set(wal, VF_PREEMPTION, PREEMPTION_VERTEX_COUNT, 0x4000); /* Wa_18018764978:dg2 */ - if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_C0, STEP_FOREVER) || - IS_DG2_G11(engine->i915) || IS_DG2_G12(engine->i915)) - wa_mcr_masked_en(wal, XEHP_PSS_MODE2, SCOREBOARD_STALL_FLUSH_CONTROL); - - /* Wa_15010599737:dg2 */ - wa_mcr_masked_en(wal, CHICKEN_RASTER_1, DIS_SF_ROUND_NEAREST_EVEN); + wa_mcr_masked_en(wal, XEHP_PSS_MODE2, SCOREBOARD_STALL_FLUSH_CONTROL); /* Wa_18019271663:dg2 */ wa_masked_en(wal, CACHE_MODE_1, MSAA_OPTIMIZATION_REDUC_DISABLE); } -static void mtl_ctx_gt_tuning_init(struct intel_engine_cs *engine, - struct i915_wa_list *wal) +static void xelpg_ctx_gt_tuning_init(struct intel_engine_cs *engine, + struct i915_wa_list *wal) { - struct drm_i915_private *i915 = engine->i915; + struct intel_gt *gt = engine->gt; dg2_ctx_gt_tuning_init(engine, wal); - if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_B0, STEP_FOREVER) || - IS_MTL_GRAPHICS_STEP(i915, P, STEP_B0, STEP_FOREVER)) + if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_B0, STEP_FOREVER) || + IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_B0, STEP_FOREVER)) wa_add(wal, DRAW_WATERMARK, VERT_WM_VAL, 0x3FF, 0, false); } -static void mtl_ctx_workarounds_init(struct intel_engine_cs *engine, - struct i915_wa_list *wal) +static void xelpg_ctx_workarounds_init(struct intel_engine_cs *engine, + struct i915_wa_list *wal) { - struct drm_i915_private *i915 = engine->i915; + struct intel_gt *gt = engine->gt; - mtl_ctx_gt_tuning_init(engine, wal); + xelpg_ctx_gt_tuning_init(engine, wal); - 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)) { /* Wa_14014947963 */ wa_masked_field_set(wal, VF_PREEMPTION, PREEMPTION_VERTEX_COUNT, 0x4000); @@ -931,8 +904,8 @@ __intel_engine_init_ctx_wa(struct intel_engine_cs *engine, if (engine->class != RENDER_CLASS) goto done; - if (IS_METEORLAKE(i915)) - mtl_ctx_workarounds_init(engine, wal); + if (IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 70), IP_VER(12, 71))) + xelpg_ctx_workarounds_init(engine, wal); else if (IS_PONTEVECCHIO(i915)) ; /* noop; none at this time */ else if (IS_DG2(i915)) @@ -1606,31 +1579,11 @@ xehpsdv_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) static void dg2_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) { - struct intel_engine_cs *engine; - int id; - xehp_init_mcr(gt, wal); /* Wa_14011060649:dg2 */ wa_14011060649(gt, wal); - /* - * Although there are per-engine instances of these registers, - * they technically exist outside the engine itself and are not - * impacted by engine resets. Furthermore, they're part of the - * GuC blacklist so trying to treat them as engine workarounds - * will result in GuC initialization failure and a wedged GPU. - */ - for_each_engine(engine, gt, id) { - if (engine->class != VIDEO_DECODE_CLASS) - continue; - - /* Wa_16010515920:dg2_g10 */ - if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_B0)) - wa_write_or(wal, VDBOX_CGCTL3F18(engine->mmio_base), - ALNUNIT_CLKGATE_DIS); - } - if (IS_DG2_G10(gt->i915)) { /* Wa_22010523718:dg2 */ wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE, @@ -1641,70 +1594,15 @@ dg2_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) DSS_ROUTER_CLKGATE_DIS); } - if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_B0) || - IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_B0)) { - /* Wa_14012362059:dg2 */ - wa_mcr_write_or(wal, XEHP_MERT_MOD_CTRL, FORCE_MISS_FTLB); - } - - if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_B0)) { - /* Wa_14010948348:dg2_g10 */ - wa_write_or(wal, UNSLCGCTL9430, MSQDUNIT_CLKGATE_DIS); - - /* Wa_14011037102:dg2_g10 */ - wa_write_or(wal, UNSLCGCTL9444, LTCDD_CLKGATE_DIS); - - /* Wa_14011371254:dg2_g10 */ - wa_mcr_write_or(wal, XEHP_SLICE_UNIT_LEVEL_CLKGATE, NODEDSS_CLKGATE_DIS); - - /* Wa_14011431319:dg2_g10 */ - wa_write_or(wal, UNSLCGCTL9440, GAMTLBOACS_CLKGATE_DIS | - GAMTLBVDBOX7_CLKGATE_DIS | - GAMTLBVDBOX6_CLKGATE_DIS | - GAMTLBVDBOX5_CLKGATE_DIS | - GAMTLBVDBOX4_CLKGATE_DIS | - GAMTLBVDBOX3_CLKGATE_DIS | - GAMTLBVDBOX2_CLKGATE_DIS | - GAMTLBVDBOX1_CLKGATE_DIS | - GAMTLBVDBOX0_CLKGATE_DIS | - GAMTLBKCR_CLKGATE_DIS | - GAMTLBGUC_CLKGATE_DIS | - GAMTLBBLT_CLKGATE_DIS); - wa_write_or(wal, UNSLCGCTL9444, GAMTLBGFXA0_CLKGATE_DIS | - GAMTLBGFXA1_CLKGATE_DIS | - GAMTLBCOMPA0_CLKGATE_DIS | - GAMTLBCOMPA1_CLKGATE_DIS | - GAMTLBCOMPB0_CLKGATE_DIS | - GAMTLBCOMPB1_CLKGATE_DIS | - GAMTLBCOMPC0_CLKGATE_DIS | - GAMTLBCOMPC1_CLKGATE_DIS | - GAMTLBCOMPD0_CLKGATE_DIS | - GAMTLBCOMPD1_CLKGATE_DIS | - GAMTLBMERT_CLKGATE_DIS | - GAMTLBVEBOX3_CLKGATE_DIS | - GAMTLBVEBOX2_CLKGATE_DIS | - GAMTLBVEBOX1_CLKGATE_DIS | - GAMTLBVEBOX0_CLKGATE_DIS); - - /* Wa_14010569222:dg2_g10 */ - wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE, - GAMEDIA_CLKGATE_DIS); - - /* Wa_14011028019:dg2_g10 */ - wa_mcr_write_or(wal, SSMCGCTL9530, RTFUNIT_CLKGATE_DIS); - - /* Wa_14010680813:dg2_g10 */ - wa_mcr_write_or(wal, XEHP_GAMSTLB_CTRL, - CONTROL_BLOCK_CLKGATE_DIS | - EGRESS_BLOCK_CLKGATE_DIS | - TAG_BLOCK_CLKGATE_DIS); - } - /* Wa_14014830051:dg2 */ wa_mcr_write_clr(wal, SARB_CHICKEN1, COMP_CKN_IN); - /* Wa_14015795083 */ - wa_write_clr(wal, GEN7_MISCCPCTL, GEN12_DOP_CLOCK_GATE_RENDER_ENABLE); + /* + * Wa_14015795083 + * Skip verification for possibly locked register. + */ + wa_add(wal, GEN7_MISCCPCTL, GEN12_DOP_CLOCK_GATE_RENDER_ENABLE, + 0, 0, false); /* Wa_18018781329 */ wa_mcr_write_or(wal, RENDER_MOD_CTRL, FORCE_MISS_FTLB); @@ -1747,8 +1645,8 @@ xelpg_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) /* Wa_22016670082 */ wa_write_or(wal, GEN12_SQCNT1, GEN12_STRICT_RAR_ENABLE); - if (IS_MTL_GRAPHICS_STEP(gt->i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(gt->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)) { /* Wa_14014830051 */ wa_mcr_write_clr(wal, SARB_CHICKEN1, COMP_CKN_IN); @@ -1791,10 +1689,8 @@ xelpmp_gt_workarounds_init(struct intel_gt *gt, struct i915_wa_list *wal) */ static void gt_tuning_settings(struct intel_gt *gt, struct i915_wa_list *wal) { - if (IS_METEORLAKE(gt->i915)) { - if (gt->type != GT_MEDIA) - wa_mcr_write_or(wal, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS); - + if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71))) { + wa_mcr_write_or(wal, XEHP_L3SCQREG7, BLEND_FILL_CACHING_OPT_DIS); wa_mcr_write_or(wal, XEHP_SQCM, EN_32B_ACCESS); } @@ -1818,15 +1714,15 @@ gt_init_workarounds(struct intel_gt *gt, struct i915_wa_list *wal) gt_tuning_settings(gt, wal); if (gt->type == GT_MEDIA) { - if (MEDIA_VER(i915) >= 13) + if (MEDIA_VER_FULL(i915) == IP_VER(13, 0)) xelpmp_gt_workarounds_init(gt, wal); else - MISSING_CASE(MEDIA_VER(i915)); + MISSING_CASE(MEDIA_VER_FULL(i915)); return; } - if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 70)) + if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71))) xelpg_gt_workarounds_init(gt, wal); else if (IS_PONTEVECCHIO(i915)) pvc_gt_workarounds_init(gt, wal); @@ -2242,29 +2138,10 @@ static void dg2_whitelist_build(struct intel_engine_cs *engine) switch (engine->class) { case RENDER_CLASS: - /* - * Wa_1507100340:dg2_g10 - * - * This covers 4 registers which are next to one another : - * - PS_INVOCATION_COUNT - * - PS_INVOCATION_COUNT_UDW - * - PS_DEPTH_COUNT - * - PS_DEPTH_COUNT_UDW - */ - if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0)) - whitelist_reg_ext(w, PS_INVOCATION_COUNT, - RING_FORCE_TO_NONPRIV_ACCESS_RD | - RING_FORCE_TO_NONPRIV_RANGE_4); - /* Required by recommended tuning setting (not a workaround) */ whitelist_mcr_reg(w, XEHP_COMMON_SLICE_CHICKEN3); break; - case COMPUTE_CLASS: - /* Wa_16011157294:dg2_g10 */ - if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_B0)) - whitelist_reg(w, GEN9_CTX_PREEMPT_REG); - break; default: break; } @@ -2294,7 +2171,7 @@ static void pvc_whitelist_build(struct intel_engine_cs *engine) blacklist_trtt(engine); } -static void mtl_whitelist_build(struct intel_engine_cs *engine) +static void xelpg_whitelist_build(struct intel_engine_cs *engine) { struct i915_wa_list *w = &engine->whitelist; @@ -2316,8 +2193,10 @@ void intel_engine_init_whitelist(struct intel_engine_cs *engine) wa_init_start(w, engine->gt, "whitelist", engine->name); - if (IS_METEORLAKE(i915)) - mtl_whitelist_build(engine); + if (engine->gt->type == GT_MEDIA) + ; /* none yet */ + else if (IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 70), IP_VER(12, 71))) + xelpg_whitelist_build(engine); else if (IS_PONTEVECCHIO(i915)) pvc_whitelist_build(engine); else if (IS_DG2(i915)) @@ -2415,62 +2294,35 @@ engine_fake_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) } } -static bool needs_wa_1308578152(struct intel_engine_cs *engine) -{ - return intel_sseu_find_first_xehp_dss(&engine->gt->info.sseu, 0, 0) >= - GEN_DSS_PER_GSLICE; -} - static void rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) { struct drm_i915_private *i915 = engine->i915; + struct intel_gt *gt = engine->gt; - 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)) { /* Wa_22014600077 */ wa_mcr_masked_en(wal, GEN10_CACHE_MODE_SS, ENABLE_EU_COUNT_FOR_TDL_FLUSH); } - if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0) || - IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_FOREVER) || - IS_DG2_G11(i915) || IS_DG2_G12(i915)) { + 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) || + IS_DG2(i915)) { /* Wa_1509727124 */ wa_mcr_masked_en(wal, GEN10_SAMPLER_MODE, SC_DISABLE_POWER_OPTIMIZATION_EBB); } - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_FOREVER) || - IS_DG2_G11(i915) || IS_DG2_G12(i915) || - IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0)) { + if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_A0, STEP_B0) || + IS_DG2(i915)) { /* Wa_22012856258 */ wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN2, GEN12_DISABLE_READ_SUPPRESSION); } - if (IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) { - /* Wa_14013392000:dg2_g11 */ - wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN2, GEN12_ENABLE_LARGE_GRF_MODE); - } - - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0) || - IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) { - /* Wa_14012419201:dg2 */ - wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN4, - GEN12_DISABLE_HDR_PAST_PAYLOAD_HOLD_FIX); - } - - /* Wa_1308578152:dg2_g10 when first gslice is fused off */ - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_C0) && - needs_wa_1308578152(engine)) { - wa_masked_dis(wal, GEN12_CS_DEBUG_MODE1_CCCSUNIT_BE_COMMON, - GEN12_REPLAY_MODE_GRANULARITY); - } - - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_FOREVER) || - IS_DG2_G11(i915) || IS_DG2_G12(i915)) { + if (IS_DG2(i915)) { /* * Wa_22010960976:dg2 * Wa_14013347512:dg2 @@ -2479,34 +2331,15 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) LSC_L1_FLUSH_CTL_3D_DATAPORT_FLUSH_EVENTS_MASK); } - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) { - /* - * Wa_1608949956:dg2_g10 - * Wa_14010198302:dg2_g10 - */ - wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN, - MDQ_ARBITRATION_MODE | UGM_BACKUP_MODE); + if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71)) || + IS_DG2(i915)) { + /* Wa_14015150844 */ + wa_mcr_add(wal, XEHP_HDC_CHICKEN0, 0, + _MASKED_BIT_ENABLE(DIS_ATOMIC_CHAINING_TYPED_WRITES), + 0, true); } - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) - /* Wa_22010430635:dg2 */ - wa_mcr_masked_en(wal, - GEN9_ROW_CHICKEN4, - GEN12_DISABLE_GRF_CLEAR); - - /* Wa_14013202645:dg2 */ - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_C0) || - IS_DG2_GRAPHICS_STEP(i915, G11, STEP_A0, STEP_B0)) - wa_mcr_write_or(wal, RT_CTRL, DIS_NULL_QUERY); - - /* Wa_22012532006:dg2 */ - if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_A0, STEP_C0) || - IS_DG2_GRAPHICS_STEP(engine->i915, G11, STEP_A0, STEP_B0)) - wa_mcr_masked_en(wal, GEN9_HALF_SLICE_CHICKEN7, - DG2_DISABLE_ROUND_ENABLE_ALLOW_FOR_SSLA); - - if (IS_DG2_GRAPHICS_STEP(i915, G11, STEP_B0, STEP_FOREVER) || - IS_DG2_G10(i915)) { + if (IS_DG2_G11(i915) || IS_DG2_G10(i915)) { /* Wa_22014600077:dg2 */ wa_mcr_add(wal, GEN10_CACHE_MODE_SS, 0, _MASKED_BIT_ENABLE(ENABLE_EU_COUNT_FOR_TDL_FLUSH), @@ -2514,6 +2347,19 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) true); } + if (IS_DG2(i915) || IS_ALDERLAKE_P(i915) || IS_ALDERLAKE_S(i915) || + IS_DG1(i915) || IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) { + /* + * Wa_1606700617:tgl,dg1,adl-p + * Wa_22010271021:tgl,rkl,dg1,adl-s,adl-p + * Wa_14010826681:tgl,dg1,rkl,adl-p + * Wa_18019627453:dg2 + */ + wa_masked_en(wal, + GEN9_CS_DEBUG_MODE1, + FF_DOP_CLOCK_GATE_DISABLE); + } + if (IS_ALDERLAKE_P(i915) || IS_ALDERLAKE_S(i915) || IS_DG1(i915) || IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) { /* Wa_1606931601:tgl,rkl,dg1,adl-s,adl-p */ @@ -2527,19 +2373,11 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) */ wa_write_or(wal, GEN7_FF_THREAD_MODE, GEN12_FF_TESSELATION_DOP_GATE_DISABLE); - } - if (IS_ALDERLAKE_P(i915) || IS_DG2(i915) || IS_ALDERLAKE_S(i915) || - IS_DG1(i915) || IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) { - /* - * Wa_1606700617:tgl,dg1,adl-p - * Wa_22010271021:tgl,rkl,dg1,adl-s,adl-p - * Wa_14010826681:tgl,dg1,rkl,adl-p - * Wa_18019627453:dg2 - */ - wa_masked_en(wal, - GEN9_CS_DEBUG_MODE1, - FF_DOP_CLOCK_GATE_DISABLE); + /* Wa_1406941453:tgl,rkl,dg1,adl-s,adl-p */ + wa_mcr_masked_en(wal, + GEN10_SAMPLER_MODE, + ENABLE_SMALLPL); } if (IS_ALDERLAKE_P(i915) || IS_ALDERLAKE_S(i915) || @@ -2566,14 +2404,6 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) GEN8_RC_SEMA_IDLE_MSG_DISABLE); } - if (IS_DG1(i915) || IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915) || - IS_ALDERLAKE_S(i915) || IS_ALDERLAKE_P(i915)) { - /* Wa_1406941453:tgl,rkl,dg1,adl-s,adl-p */ - wa_mcr_masked_en(wal, - GEN10_SAMPLER_MODE, - ENABLE_SMALLPL); - } - if (GRAPHICS_VER(i915) == 11) { /* This is not an Wa. Enable for better image quality */ wa_masked_en(wal, @@ -2975,10 +2805,12 @@ ccs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) * function invoked by __intel_engine_init_ctx_wa(). */ static void -add_render_compute_tuning_settings(struct drm_i915_private *i915, +add_render_compute_tuning_settings(struct intel_gt *gt, struct i915_wa_list *wal) { - if (IS_METEORLAKE(i915) || IS_DG2(i915)) + struct drm_i915_private *i915 = gt->i915; + + if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71)) || IS_DG2(i915)) wa_mcr_write_clr_set(wal, RT_CTRL, STACKID_CTRL, STACKID_CTRL_512); /* @@ -3007,8 +2839,9 @@ static void general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) { struct drm_i915_private *i915 = engine->i915; + struct intel_gt *gt = engine->gt; - add_render_compute_tuning_settings(i915, wal); + add_render_compute_tuning_settings(gt, wal); if (GRAPHICS_VER(i915) >= 11) { /* This is not a Wa (although referred to as @@ -3029,13 +2862,13 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li GEN11_INDIRECT_STATE_BASE_ADDR_OVERRIDE); } - if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_B0, STEP_FOREVER) || - IS_MTL_GRAPHICS_STEP(i915, P, STEP_B0, STEP_FOREVER)) + if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_B0, STEP_FOREVER) || + IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_B0, STEP_FOREVER)) /* Wa_14017856879 */ wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN3, MTL_DISABLE_FIX_FOR_EOT_FLUSH); - 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)) /* * Wa_14017066071 * Wa_14017654203 @@ -3043,37 +2876,47 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li wa_mcr_masked_en(wal, GEN10_SAMPLER_MODE, MTL_DISABLE_SAMPLER_SC_OOO); - if (IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0)) + if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 71), STEP_A0, STEP_B0)) /* Wa_22015279794 */ wa_mcr_masked_en(wal, GEN10_CACHE_MODE_SS, DISABLE_PREFETCH_INTO_IC); - if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0) || - IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_FOREVER) || - IS_DG2_G11(i915) || IS_DG2_G12(i915)) { + 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) || + IS_DG2(i915)) { /* Wa_22013037850 */ wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0_UDW, DISABLE_128B_EVICTION_COMMAND_UDW); + + /* Wa_18017747507 */ + wa_masked_en(wal, VFG_PREEMPTION_CHICKEN, POLYGON_TRIFAN_LINELOOP_DISABLE); } - 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) || IS_PONTEVECCHIO(i915) || IS_DG2(i915)) { /* Wa_22014226127 */ wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0, DISABLE_D8_D16_COASLESCE); } - if (IS_MTL_GRAPHICS_STEP(i915, M, STEP_A0, STEP_B0) || - IS_MTL_GRAPHICS_STEP(i915, P, STEP_A0, STEP_B0) || - IS_DG2(i915)) { - /* Wa_18017747507 */ - wa_masked_en(wal, VFG_PREEMPTION_CHICKEN, POLYGON_TRIFAN_LINELOOP_DISABLE); + if (IS_PONTEVECCHIO(i915) || IS_DG2(i915)) { + /* Wa_14015227452:dg2,pvc */ + wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN4, XEHP_DIS_BBL_SYSPIPE); + + /* Wa_16015675438:dg2,pvc */ + wa_masked_en(wal, FF_SLICE_CS_CHICKEN2, GEN12_PERF_FIX_BALANCING_CFE_DISABLE); } - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_B0, STEP_C0) || - IS_DG2_G11(i915)) { + if (IS_DG2(i915)) { + /* + * Wa_16011620976:dg2_g11 + * Wa_22015475538:dg2 + */ + wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0_UDW, DIS_CHAIN_2XSIMD8); + } + + if (IS_DG2_G11(i915)) { /* * Wa_22012826095:dg2 * Wa_22013059131:dg2 @@ -3085,18 +2928,23 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li /* Wa_22013059131:dg2 */ wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0, FORCE_1_SUB_MESSAGE_PER_FRAGMENT); - } - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) { /* - * Wa_14010918519:dg2_g10 + * Wa_22012654132 * - * LSC_CHICKEN_BIT_0 always reads back as 0 is this stepping, - * so ignoring verification. + * Note that register 0xE420 is write-only and cannot be read + * back for verification on DG2 (due to Wa_14012342262), so + * we need to explicitly skip the readback. */ - wa_mcr_add(wal, LSC_CHICKEN_BIT_0_UDW, 0, - FORCE_SLM_FENCE_SCOPE_TO_TILE | FORCE_UGM_FENCE_SCOPE_TO_TILE, - 0, false); + wa_mcr_add(wal, GEN10_CACHE_MODE_SS, 0, + _MASKED_BIT_ENABLE(ENABLE_PREFETCH_INTO_IC), + 0 /* write-only, so skip validation */, + true); + } + + if (IS_DG2_G10(i915) || IS_DG2_G12(i915)) { + /* Wa_18028616096 */ + wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0_UDW, UGM_FRAGMENT_THRESHOLD_TO_3); } if (IS_XEHPSDV(i915)) { @@ -3114,35 +2962,6 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li wa_mcr_masked_en(wal, GEN8_HALF_SLICE_CHICKEN1, GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE); } - - if (IS_DG2(i915) || IS_PONTEVECCHIO(i915)) { - /* Wa_14015227452:dg2,pvc */ - wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN4, XEHP_DIS_BBL_SYSPIPE); - - /* Wa_16015675438:dg2,pvc */ - wa_masked_en(wal, FF_SLICE_CS_CHICKEN2, GEN12_PERF_FIX_BALANCING_CFE_DISABLE); - } - - if (IS_DG2(i915)) { - /* - * Wa_16011620976:dg2_g11 - * Wa_22015475538:dg2 - */ - wa_mcr_write_or(wal, LSC_CHICKEN_BIT_0_UDW, DIS_CHAIN_2XSIMD8); - } - - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_C0) || IS_DG2_G11(i915)) - /* - * Wa_22012654132 - * - * Note that register 0xE420 is write-only and cannot be read - * back for verification on DG2 (due to Wa_14012342262), so - * we need to explicitly skip the readback. - */ - wa_mcr_add(wal, GEN10_CACHE_MODE_SS, 0, - _MASKED_BIT_ENABLE(ENABLE_PREFETCH_INTO_IC), - 0 /* write-only, so skip validation */, - true); } static void diff --git a/drivers/gpu/drm/i915/gt/selftest_migrate.c b/drivers/gpu/drm/i915/gt/selftest_migrate.c index 3def5ca72dec..1a34cbe04fb6 100644 --- a/drivers/gpu/drm/i915/gt/selftest_migrate.c +++ b/drivers/gpu/drm/i915/gt/selftest_migrate.c @@ -710,7 +710,7 @@ static int threaded_migrate(struct intel_migrate *migrate, thread[i].tsk = tsk; } - msleep(10); /* start all threads before we kthread_stop() */ + msleep(10 * n_cpus); /* start all threads before we kthread_stop() */ for (i = 0; i < n_cpus; ++i) { struct task_struct *tsk = thread[i].tsk; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc_heci_cmd_submit.c b/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc_heci_cmd_submit.c index 89ed5ee9cded..2fde5c360cff 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc_heci_cmd_submit.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc_heci_cmd_submit.c @@ -81,8 +81,17 @@ out_rq: i915_request_add(rq); - if (!err && i915_request_wait(rq, 0, msecs_to_jiffies(500)) < 0) - err = -ETIME; + if (!err) { + /* + * Start timeout for i915_request_wait only after considering one possible + * pending GSC-HECI submission cycle on the other (non-privileged) path. + */ + if (wait_for(i915_request_started(rq), GSC_HECI_REPLY_LATENCY_MS)) + drm_dbg(&gsc_uc_to_gt(gsc)->i915->drm, + "Delay in gsc-heci-priv submission to gsccs-hw"); + if (i915_request_wait(rq, 0, msecs_to_jiffies(GSC_HECI_REPLY_LATENCY_MS)) < 0) + err = -ETIME; + } i915_request_put(rq); @@ -186,6 +195,13 @@ out_rq: i915_request_add(rq); if (!err) { + /* + * Start timeout for i915_request_wait only after considering one possible + * pending GSC-HECI submission cycle on the other (privileged) path. + */ + if (wait_for(i915_request_started(rq), GSC_HECI_REPLY_LATENCY_MS)) + drm_dbg(&gsc_uc_to_gt(gsc)->i915->drm, + "Delay in gsc-heci-non-priv submission to gsccs-hw"); if (i915_request_wait(rq, I915_WAIT_INTERRUPTIBLE, msecs_to_jiffies(timeout_ms)) < 0) err = -ETIME; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc_heci_cmd_submit.h b/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc_heci_cmd_submit.h index 09d3fbdad05a..c4308291c003 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc_heci_cmd_submit.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc_heci_cmd_submit.h @@ -12,6 +12,12 @@ struct i915_vma; struct intel_context; struct intel_gsc_uc; +#define GSC_HECI_REPLY_LATENCY_MS 500 +/* + * Max FW response time is 500ms, but this should be counted from the time the + * command has hit the GSC-CS hardware, not the preceding handoff to GuC CTB. + */ + struct intel_gsc_mtl_header { u32 validity_marker; #define GSC_HECI_VALIDITY_MARKER 0xA578875A diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c index 569b5fe94c41..27df41c53b89 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c @@ -159,6 +159,21 @@ static void gen11_disable_guc_interrupts(struct intel_guc *guc) gen11_reset_guc_interrupts(guc); } +static void guc_dead_worker_func(struct work_struct *w) +{ + struct intel_guc *guc = container_of(w, struct intel_guc, dead_guc_worker); + struct intel_gt *gt = guc_to_gt(guc); + unsigned long last = guc->last_dead_guc_jiffies; + unsigned long delta = jiffies_to_msecs(jiffies - last); + + if (delta < 500) { + intel_gt_set_wedged(gt); + } else { + intel_gt_handle_error(gt, ALL_ENGINES, I915_ERROR_CAPTURE, "dead GuC"); + guc->last_dead_guc_jiffies = jiffies; + } +} + void intel_guc_init_early(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); @@ -171,6 +186,8 @@ void intel_guc_init_early(struct intel_guc *guc) intel_guc_slpc_init_early(&guc->slpc); intel_guc_rc_init_early(guc); + INIT_WORK(&guc->dead_guc_worker, guc_dead_worker_func); + mutex_init(&guc->send_mutex); spin_lock_init(&guc->irq_lock); if (GRAPHICS_VER(i915) >= 11) { @@ -272,18 +289,14 @@ static u32 guc_ctl_wa_flags(struct intel_guc *guc) GRAPHICS_VER_FULL(gt->i915) < IP_VER(12, 50)) flags |= GUC_WA_POLLCS; - /* Wa_16011759253:dg2_g10:a0 */ - if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_B0)) - flags |= GUC_WA_GAM_CREDITS; - /* Wa_14014475959 */ - if (IS_MTL_GRAPHICS_STEP(gt->i915, M, STEP_A0, STEP_B0) || + if (IS_GFX_GT_IP_STEP(gt, IP_VER(12, 70), STEP_A0, STEP_B0) || IS_DG2(gt->i915)) flags |= GUC_WA_HOLD_CCS_SWITCHOUT; /* - * Wa_14012197797:dg2_g10:a0,dg2_g11:a0 - * Wa_22011391025:dg2_g10,dg2_g11,dg2_g12 + * Wa_14012197797 + * Wa_22011391025 * * The same WA bit is used for both and 22011391025 is applicable to * all DG2. @@ -292,22 +305,14 @@ static u32 guc_ctl_wa_flags(struct intel_guc *guc) flags |= GUC_WA_DUAL_QUEUE; /* Wa_22011802037: graphics version 11/12 */ - if (IS_MTL_GRAPHICS_STEP(gt->i915, M, STEP_A0, STEP_B0) || - (GRAPHICS_VER(gt->i915) >= 11 && - GRAPHICS_VER_FULL(gt->i915) < IP_VER(12, 70))) + if (intel_engine_reset_needs_wa_22011802037(gt)) flags |= GUC_WA_PRE_PARSER; - /* Wa_16011777198:dg2 */ - if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_C0) || - IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_B0)) - flags |= GUC_WA_RCS_RESET_BEFORE_RC6; - /* - * Wa_22012727170:dg2_g10[a0-c0), dg2_g11[a0..) - * Wa_22012727685:dg2_g11[a0..) + * Wa_22012727170 + * Wa_22012727685 */ - if (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_C0) || - IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_FOREVER)) + if (IS_DG2_G11(gt->i915)) flags |= GUC_WA_CONTEXT_ISOLATION; /* Wa_16015675438 */ @@ -461,6 +466,8 @@ void intel_guc_fini(struct intel_guc *guc) if (!intel_uc_fw_is_loadable(&guc->fw)) return; + flush_work(&guc->dead_guc_worker); + if (intel_guc_slpc_is_used(guc)) intel_guc_slpc_fini(&guc->slpc); @@ -585,6 +592,20 @@ out: return ret; } +int intel_guc_crash_process_msg(struct intel_guc *guc, u32 action) +{ + if (action == INTEL_GUC_ACTION_NOTIFY_CRASH_DUMP_POSTED) + guc_err(guc, "Crash dump notification\n"); + else if (action == INTEL_GUC_ACTION_NOTIFY_EXCEPTION) + guc_err(guc, "Exception notification\n"); + else + guc_err(guc, "Unknown crash notification: 0x%04X\n", action); + + queue_work(system_unbound_wq, &guc->dead_guc_worker); + + return 0; +} + int intel_guc_to_host_process_recv_msg(struct intel_guc *guc, const u32 *payload, u32 len) { @@ -601,6 +622,9 @@ int intel_guc_to_host_process_recv_msg(struct intel_guc *guc, if (msg & INTEL_GUC_RECV_MSG_EXCEPTION) guc_err(guc, "Received early exception notification!\n"); + if (msg & (INTEL_GUC_RECV_MSG_CRASH_DUMP_POSTED | INTEL_GUC_RECV_MSG_EXCEPTION)) + queue_work(system_unbound_wq, &guc->dead_guc_worker); + return 0; } @@ -640,6 +664,8 @@ int intel_guc_suspend(struct intel_guc *guc) return 0; if (intel_guc_submission_is_used(guc)) { + flush_work(&guc->dead_guc_worker); + /* * This H2G MMIO command tears down the GuC in two steps. First it will * generate a G2H CTB for every active context indicating a reset. In diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index 8dc291ff0093..6c392bad29c1 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -266,6 +266,20 @@ struct intel_guc { unsigned long last_stat_jiffies; } timestamp; + /** + * @dead_guc_worker: Asynchronous worker thread for forcing a GuC reset. + * Specifically used when the G2H handler wants to issue a reset. Resets + * require flushing the G2H queue. So, the G2H processing itself must not + * trigger a reset directly. Instead, go via this worker. + */ + struct work_struct dead_guc_worker; + /** + * @last_dead_guc_jiffies: timestamp of previous 'dead guc' occurrance + * used to prevent a fundamentally broken system from continuously + * reloading the GuC. + */ + unsigned long last_dead_guc_jiffies; + #ifdef CONFIG_DRM_I915_SELFTEST /** * @number_guc_id_stolen: The number of guc_ids that have been stolen @@ -476,6 +490,7 @@ int intel_guc_engine_failure_process_msg(struct intel_guc *guc, const u32 *msg, u32 len); int intel_guc_error_capture_process_msg(struct intel_guc *guc, const u32 *msg, u32 len); +int intel_guc_crash_process_msg(struct intel_guc *guc, u32 action); struct intel_engine_cs * intel_guc_lookup_engine(struct intel_guc *guc, u8 guc_class, u8 instance); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c index 97eadd08181d..6e22af31513a 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c @@ -1112,12 +1112,8 @@ static int ct_process_request(struct intel_guc_ct *ct, struct ct_incoming_msg *r ret = 0; break; case INTEL_GUC_ACTION_NOTIFY_CRASH_DUMP_POSTED: - CT_ERROR(ct, "Received GuC crash dump notification!\n"); - ret = 0; - break; case INTEL_GUC_ACTION_NOTIFY_EXCEPTION: - CT_ERROR(ct, "Received GuC exception notification!\n"); - ret = 0; + ret = intel_guc_crash_process_msg(guc, action); break; default: ret = -EOPNOTSUPP; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c index 477df260ae3a..2dfb07cc4b33 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c @@ -138,17 +138,6 @@ static int guc_action_slpc_set_param(struct intel_guc *guc, u8 id, u32 value) return ret > 0 ? -EPROTO : ret; } -static int guc_action_slpc_unset_param(struct intel_guc *guc, u8 id) -{ - u32 request[] = { - GUC_ACTION_HOST2GUC_PC_SLPC_REQUEST, - SLPC_EVENT(SLPC_EVENT_PARAMETER_UNSET, 1), - id, - }; - - return intel_guc_send(guc, request, ARRAY_SIZE(request)); -} - static bool slpc_is_running(struct intel_guc_slpc *slpc) { return slpc_get_state(slpc) == SLPC_GLOBAL_STATE_RUNNING; @@ -199,15 +188,6 @@ static int slpc_set_param(struct intel_guc_slpc *slpc, u8 id, u32 value) return ret; } -static int slpc_unset_param(struct intel_guc_slpc *slpc, u8 id) -{ - struct intel_guc *guc = slpc_to_guc(slpc); - - GEM_BUG_ON(id >= SLPC_MAX_PARAM); - - return guc_action_slpc_unset_param(guc, id); -} - static int slpc_force_min_freq(struct intel_guc_slpc *slpc, u32 freq) { struct intel_guc *guc = slpc_to_guc(slpc); @@ -672,49 +652,6 @@ static void slpc_get_rp_values(struct intel_guc_slpc *slpc) slpc->boost_freq = slpc->rp0_freq; } -/** - * intel_guc_slpc_override_gucrc_mode() - override GUCRC mode - * @slpc: pointer to intel_guc_slpc. - * @mode: new value of the mode. - * - * This function will override the GUCRC mode. - * - * Return: 0 on success, non-zero error code on failure. - */ -int intel_guc_slpc_override_gucrc_mode(struct intel_guc_slpc *slpc, u32 mode) -{ - int ret; - struct drm_i915_private *i915 = slpc_to_i915(slpc); - intel_wakeref_t wakeref; - - if (mode >= SLPC_GUCRC_MODE_MAX) - return -EINVAL; - - with_intel_runtime_pm(&i915->runtime_pm, wakeref) { - ret = slpc_set_param(slpc, SLPC_PARAM_PWRGATE_RC_MODE, mode); - if (ret) - guc_err(slpc_to_guc(slpc), "Override RC mode %d failed: %pe\n", - mode, ERR_PTR(ret)); - } - - return ret; -} - -int intel_guc_slpc_unset_gucrc_mode(struct intel_guc_slpc *slpc) -{ - struct drm_i915_private *i915 = slpc_to_i915(slpc); - intel_wakeref_t wakeref; - int ret = 0; - - with_intel_runtime_pm(&i915->runtime_pm, wakeref) { - ret = slpc_unset_param(slpc, SLPC_PARAM_PWRGATE_RC_MODE); - if (ret) - guc_err(slpc_to_guc(slpc), "Unsetting RC mode failed: %pe\n", ERR_PTR(ret)); - } - - return ret; -} - /* * intel_guc_slpc_enable() - Start SLPC * @slpc: pointer to intel_guc_slpc. diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h index 597eb5413ddf..6ac6503c39d4 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h @@ -44,8 +44,6 @@ int intel_guc_slpc_set_media_ratio_mode(struct intel_guc_slpc *slpc, u32 val); void intel_guc_pm_intrmsk_enable(struct intel_gt *gt); void intel_guc_slpc_boost(struct intel_guc_slpc *slpc); void intel_guc_slpc_dec_waiters(struct intel_guc_slpc *slpc); -int intel_guc_slpc_unset_gucrc_mode(struct intel_guc_slpc *slpc); -int intel_guc_slpc_override_gucrc_mode(struct intel_guc_slpc *slpc, u32 mode); int intel_guc_slpc_set_ignore_eff_freq(struct intel_guc_slpc *slpc, bool val); #endif diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index b5b7f2fe8c78..ae3495a9c814 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1433,6 +1433,36 @@ static void guc_timestamp_ping(struct work_struct *wrk) int srcu, ret; /* + * Ideally the busyness worker should take a gt pm wakeref because the + * worker only needs to be active while gt is awake. However, the + * gt_park path cancels the worker synchronously and this complicates + * the flow if the worker is also running at the same time. The cancel + * waits for the worker and when the worker releases the wakeref, that + * would call gt_park and would lead to a deadlock. + * + * The resolution is to take the global pm wakeref if runtime pm is + * already active. If not, we don't need to update the busyness stats as + * the stats would already be updated when the gt was parked. + * + * Note: + * - We do not requeue the worker if we cannot take a reference to runtime + * pm since intel_guc_busyness_unpark would requeue the worker in the + * resume path. + * + * - If the gt was parked longer than time taken for GT timestamp to roll + * over, we ignore those rollovers since we don't care about tracking + * the exact GT time. We only care about roll overs when the gt is + * active and running workloads. + * + * - There is a window of time between gt_park and runtime suspend, + * where the worker may run. This is acceptable since the worker will + * not find any new data to update busyness. + */ + wakeref = intel_runtime_pm_get_if_active(>->i915->runtime_pm); + if (!wakeref) + return; + + /* * Synchronize with gt reset to make sure the worker does not * corrupt the engine/guc stats. NB: can't actually block waiting * for a reset to complete as the reset requires flushing out @@ -1440,10 +1470,9 @@ static void guc_timestamp_ping(struct work_struct *wrk) */ ret = intel_gt_reset_trylock(gt, &srcu); if (ret) - return; + goto err_trylock; - with_intel_runtime_pm(>->i915->runtime_pm, wakeref) - __update_guc_busyness_stats(guc); + __update_guc_busyness_stats(guc); /* adjust context stats for overflow */ xa_for_each(&guc->context_lookup, index, ce) @@ -1452,6 +1481,9 @@ static void guc_timestamp_ping(struct work_struct *wrk) intel_gt_reset_unlock(gt, srcu); guc_enable_busyness_worker(guc); + +err_trylock: + intel_runtime_pm_put(>->i915->runtime_pm, wakeref); } static int guc_action_enable_usage_stats(struct intel_guc *guc) @@ -1658,9 +1690,7 @@ static void guc_engine_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_stop_cs(engine); intel_engine_wait_for_pending_mi_fw(engine); } @@ -4267,7 +4297,7 @@ static void guc_default_vfuncs(struct intel_engine_cs *engine) /* Wa_14014475959:dg2 */ if (engine->class == COMPUTE_CLASS) - if (IS_MTL_GRAPHICS_STEP(engine->i915, M, STEP_A0, STEP_B0) || + if (IS_GFX_GT_IP_STEP(engine->gt, IP_VER(12, 70), STEP_A0, STEP_B0) || IS_DG2(engine->i915)) engine->flags |= I915_ENGINE_USES_WA_HOLD_CCS_SWITCHOUT; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c index 8be005de1d28..32e27e9a2490 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c @@ -132,6 +132,17 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw, fw_def(SKYLAKE, 0, huc_mmp(skl, 2, 0, 0)) /* + * The GSC FW has multiple version (see intel_gsc_uc.h for details); since what + * we care about is the interface, we use the compatibility version in the + * binary names. + * Same as with the GuC, a major version bump indicate a + * backward-incompatible change, while a minor version bump indicates a + * backward-compatible one, so we use only the former in the file name. + */ +#define INTEL_GSC_FIRMWARE_DEFS(fw_def, gsc_def) \ + fw_def(METEORLAKE, 0, gsc_def(mtl, 1, 0)) + +/* * Set of macros for producing a list of filenames from the above table. */ #define __MAKE_UC_FW_PATH_BLANK(prefix_, name_) \ @@ -166,6 +177,9 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw, #define MAKE_HUC_FW_PATH_MMP(prefix_, major_, minor_, patch_) \ __MAKE_UC_FW_PATH_MMP(prefix_, "huc", major_, minor_, patch_) +#define MAKE_GSC_FW_PATH(prefix_, major_, minor_) \ + __MAKE_UC_FW_PATH_MAJOR(prefix_, "gsc", major_) + /* * All blobs need to be declared via MODULE_FIRMWARE(). * This first expansion of the table macros is solely to provide @@ -176,6 +190,7 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw, INTEL_GUC_FIRMWARE_DEFS(INTEL_UC_MODULE_FW, MAKE_GUC_FW_PATH_MAJOR, MAKE_GUC_FW_PATH_MMP) INTEL_HUC_FIRMWARE_DEFS(INTEL_UC_MODULE_FW, MAKE_HUC_FW_PATH_BLANK, MAKE_HUC_FW_PATH_MMP, MAKE_HUC_FW_PATH_GSC) +INTEL_GSC_FIRMWARE_DEFS(INTEL_UC_MODULE_FW, MAKE_GSC_FW_PATH) /* * The next expansion of the table macros (in __uc_fw_auto_select below) provides @@ -225,6 +240,10 @@ struct __packed uc_fw_blob { #define HUC_FW_BLOB_GSC(prefix_) \ UC_FW_BLOB_NEW(0, 0, 0, true, MAKE_HUC_FW_PATH_GSC(prefix_)) +#define GSC_FW_BLOB(prefix_, major_, minor_) \ + UC_FW_BLOB_NEW(major_, minor_, 0, true, \ + MAKE_GSC_FW_PATH(prefix_, major_, minor_)) + struct __packed uc_fw_platform_requirement { enum intel_platform p; u8 rev; /* first platform rev using this FW */ @@ -251,9 +270,14 @@ static const struct uc_fw_platform_requirement blobs_huc[] = { INTEL_HUC_FIRMWARE_DEFS(MAKE_FW_LIST, HUC_FW_BLOB, HUC_FW_BLOB_MMP, HUC_FW_BLOB_GSC) }; +static const struct uc_fw_platform_requirement blobs_gsc[] = { + INTEL_GSC_FIRMWARE_DEFS(MAKE_FW_LIST, GSC_FW_BLOB) +}; + static const struct fw_blobs_by_type blobs_all[INTEL_UC_FW_NUM_TYPES] = { [INTEL_UC_FW_TYPE_GUC] = { blobs_guc, ARRAY_SIZE(blobs_guc) }, [INTEL_UC_FW_TYPE_HUC] = { blobs_huc, ARRAY_SIZE(blobs_huc) }, + [INTEL_UC_FW_TYPE_GSC] = { blobs_gsc, ARRAY_SIZE(blobs_gsc) }, }; static void @@ -267,14 +291,6 @@ __uc_fw_auto_select(struct drm_i915_private *i915, struct intel_uc_fw *uc_fw) bool found; /* - * GSC FW support is still not fully in place, so we're not defining - * the FW blob yet because we don't want the driver to attempt to load - * it until we're ready for it. - */ - if (uc_fw->type == INTEL_UC_FW_TYPE_GSC) - return; - - /* * The only difference between the ADL GuC FWs is the HWConfig support. * ADL-N does not support HWConfig, so we should use the same binary as * ADL-S, otherwise the GuC might attempt to fetch a config table that diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 4de44cf1026d..e9b79c2c37d8 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -144,7 +144,7 @@ static const char *i915_cache_level_str(struct drm_i915_gem_object *obj) { struct drm_i915_private *i915 = obj_to_i915(obj); - if (IS_METEORLAKE(i915)) { + if (IS_GFX_GT_IP_RANGE(to_gt(i915), IP_VER(12, 70), IP_VER(12, 71))) { switch (obj->pat_index) { case 0: return " WB"; case 1: return " WT"; @@ -740,15 +740,19 @@ static int i915_drop_caches_set(void *data, u64 val) { struct drm_i915_private *i915 = data; + struct intel_gt *gt; unsigned int flags; + unsigned int i; int ret; drm_dbg(&i915->drm, "Dropping caches: 0x%08llx [0x%08llx]\n", val, val & DROP_ALL); - ret = gt_drop_caches(to_gt(i915), val); - if (ret) - return ret; + for_each_gt(gt, i915, i) { + ret = gt_drop_caches(gt, val); + if (ret) + return ret; + } fs_reclaim_acquire(GFP_KERNEL); flags = memalloc_noreclaim_save(); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 7a8ce7239bc9..ea92a00353da 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -573,10 +573,6 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define IS_PONTEVECCHIO(i915) IS_PLATFORM(i915, INTEL_PONTEVECCHIO) #define IS_METEORLAKE(i915) IS_PLATFORM(i915, INTEL_METEORLAKE) -#define IS_METEORLAKE_M(i915) \ - IS_SUBPLATFORM(i915, INTEL_METEORLAKE, INTEL_SUBPLATFORM_M) -#define IS_METEORLAKE_P(i915) \ - IS_SUBPLATFORM(i915, INTEL_METEORLAKE, INTEL_SUBPLATFORM_P) #define IS_DG2_G10(i915) \ IS_SUBPLATFORM(i915, INTEL_DG2, INTEL_SUBPLATFORM_G10) #define IS_DG2_G11(i915) \ @@ -658,37 +654,10 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define IS_XEHPSDV_GRAPHICS_STEP(__i915, since, until) \ (IS_XEHPSDV(__i915) && IS_GRAPHICS_STEP(__i915, since, until)) -#define IS_MTL_GRAPHICS_STEP(__i915, variant, since, until) \ - (IS_SUBPLATFORM(__i915, INTEL_METEORLAKE, INTEL_SUBPLATFORM_##variant) && \ - IS_GRAPHICS_STEP(__i915, since, until)) - #define IS_MTL_DISPLAY_STEP(__i915, since, until) \ (IS_METEORLAKE(__i915) && \ IS_DISPLAY_STEP(__i915, since, until)) -#define IS_MTL_MEDIA_STEP(__i915, since, until) \ - (IS_METEORLAKE(__i915) && \ - IS_MEDIA_STEP(__i915, since, until)) - -/* - * DG2 hardware steppings are a bit unusual. The hardware design was forked to - * create three variants (G10, G11, and G12) which each have distinct - * workaround sets. The G11 and G12 forks of the DG2 design reset the GT - * stepping back to "A0" for their first iterations, even though they're more - * similar to a G10 B0 stepping and G10 C0 stepping respectively in terms of - * functionality and workarounds. However the display stepping does not reset - * in the same manner --- a specific stepping like "B0" has a consistent - * meaning regardless of whether it belongs to a G10, G11, or G12 DG2. - * - * TLDR: All GT workarounds and stepping-specific logic must be applied in - * relation to a specific subplatform (G10/G11/G12), whereas display workarounds - * and stepping-specific logic will be applied with a general DG2-wide stepping - * number. - */ -#define IS_DG2_GRAPHICS_STEP(__i915, variant, since, until) \ - (IS_SUBPLATFORM(__i915, INTEL_DG2, INTEL_SUBPLATFORM_##variant) && \ - IS_GRAPHICS_STEP(__i915, since, until)) - #define IS_DG2_DISPLAY_STEP(__i915, since, until) \ (IS_DG2(__i915) && \ IS_DISPLAY_STEP(__i915, since, until)) diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 04bc1f4a1115..1347e4ec9dd5 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -543,10 +543,9 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream) { u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma); int report_size = stream->oa_buffer.format->size; - u32 head, tail, read_tail; + u32 tail, hw_tail; unsigned long flags; bool pollin; - u32 hw_tail; u32 partial_report_size; /* We have to consider the (unlikely) possibility that read() errors @@ -556,6 +555,7 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream) spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags); hw_tail = stream->perf->ops.oa_hw_tail_read(stream); + hw_tail -= gtt_offset; /* The tail pointer increases in 64 byte increments, not in report_size * steps. Also the report size may not be a power of 2. Compute @@ -567,13 +567,6 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream) /* Subtract partial amount off the tail */ hw_tail = OA_TAKEN(hw_tail, partial_report_size); - /* NB: The head we observe here might effectively be a little - * out of date. If a read() is in progress, the head could be - * anywhere between this head and stream->oa_buffer.tail. - */ - head = stream->oa_buffer.head - gtt_offset; - read_tail = stream->oa_buffer.tail - gtt_offset; - tail = hw_tail; /* Walk the stream backward until we find a report with report @@ -587,7 +580,7 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream) * memory in the order they were written to. * If not : (╯°□°）╯︵ ┻━┻ */ - while (OA_TAKEN(tail, read_tail) >= report_size) { + while (OA_TAKEN(tail, stream->oa_buffer.tail) >= report_size) { void *report = stream->oa_buffer.vaddr + tail; if (oa_report_id(stream, report) || @@ -601,9 +594,9 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream) __ratelimit(&stream->perf->tail_pointer_race)) drm_notice(&stream->uncore->i915->drm, "unlanded report(s) head=0x%x tail=0x%x hw_tail=0x%x\n", - head, tail, hw_tail); + stream->oa_buffer.head, tail, hw_tail); - stream->oa_buffer.tail = gtt_offset + tail; + stream->oa_buffer.tail = tail; pollin = OA_TAKEN(stream->oa_buffer.tail, stream->oa_buffer.head) >= report_size; @@ -754,13 +747,6 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags); /* - * NB: oa_buffer.head/tail include the gtt_offset which we don't want - * while indexing relative to oa_buf_base. - */ - head -= gtt_offset; - tail -= gtt_offset; - - /* * An out of bounds or misaligned head or tail pointer implies a driver * bug since we validate + align the tail pointers we read from the * hardware and we are in full control of the head pointer which should @@ -895,9 +881,8 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, * We removed the gtt_offset for the copy loop above, indexing * relative to oa_buf_base so put back here... */ - head += gtt_offset; intel_uncore_write(uncore, oaheadptr, - head & GEN12_OAG_OAHEADPTR_MASK); + (head + gtt_offset) & GEN12_OAG_OAHEADPTR_MASK); stream->oa_buffer.head = head; spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags); @@ -1042,12 +1027,6 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream, spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags); - /* NB: oa_buffer.head/tail include the gtt_offset which we don't want - * while indexing relative to oa_buf_base. - */ - head -= gtt_offset; - tail -= gtt_offset; - /* An out of bounds or misaligned head or tail pointer implies a driver * bug since we validate + align the tail pointers we read from the * hardware and we are in full control of the head pointer which should @@ -1110,13 +1089,8 @@ static int gen7_append_oa_reports(struct i915_perf_stream *stream, if (start_offset != *offset) { spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags); - /* We removed the gtt_offset for the copy loop above, indexing - * relative to oa_buf_base so put back here... - */ - head += gtt_offset; - intel_uncore_write(uncore, GEN7_OASTATUS2, - (head & GEN7_OASTATUS2_HEAD_MASK) | + ((head + gtt_offset) & GEN7_OASTATUS2_HEAD_MASK) | GEN7_OASTATUS2_MEM_SELECT_GGTT); stream->oa_buffer.head = head; @@ -1675,13 +1649,6 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream) free_oa_buffer(stream); - /* - * Wa_16011777198:dg2: Unset the override of GUCRC mode to enable rc6. - */ - if (stream->override_gucrc) - drm_WARN_ON(>->i915->drm, - intel_guc_slpc_unset_gucrc_mode(>->uc.guc.slpc)); - intel_uncore_forcewake_put(stream->uncore, FORCEWAKE_ALL); intel_engine_pm_put(stream->engine); @@ -1711,7 +1678,7 @@ static void gen7_init_oa_buffer(struct i915_perf_stream *stream) */ intel_uncore_write(uncore, GEN7_OASTATUS2, /* head */ gtt_offset | GEN7_OASTATUS2_MEM_SELECT_GGTT); - stream->oa_buffer.head = gtt_offset; + stream->oa_buffer.head = 0; intel_uncore_write(uncore, GEN7_OABUFFER, gtt_offset); @@ -1719,7 +1686,7 @@ static void gen7_init_oa_buffer(struct i915_perf_stream *stream) gtt_offset | OABUFFER_SIZE_16M); /* Mark that we need updated tail pointers to read from... */ - stream->oa_buffer.tail = gtt_offset; + stream->oa_buffer.tail = 0; spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags); @@ -1753,7 +1720,7 @@ static void gen8_init_oa_buffer(struct i915_perf_stream *stream) intel_uncore_write(uncore, GEN8_OASTATUS, 0); intel_uncore_write(uncore, GEN8_OAHEADPTR, gtt_offset); - stream->oa_buffer.head = gtt_offset; + stream->oa_buffer.head = 0; intel_uncore_write(uncore, GEN8_OABUFFER_UDW, 0); @@ -1770,7 +1737,7 @@ static void gen8_init_oa_buffer(struct i915_perf_stream *stream) intel_uncore_write(uncore, GEN8_OATAILPTR, gtt_offset & GEN8_OATAILPTR_MASK); /* Mark that we need updated tail pointers to read from... */ - stream->oa_buffer.tail = gtt_offset; + stream->oa_buffer.tail = 0; /* * Reset state used to recognise context switches, affecting which @@ -1807,7 +1774,7 @@ static void gen12_init_oa_buffer(struct i915_perf_stream *stream) intel_uncore_write(uncore, __oa_regs(stream)->oa_status, 0); intel_uncore_write(uncore, __oa_regs(stream)->oa_head_ptr, gtt_offset & GEN12_OAG_OAHEADPTR_MASK); - stream->oa_buffer.head = gtt_offset; + stream->oa_buffer.head = 0; /* * PRM says: @@ -1823,7 +1790,7 @@ static void gen12_init_oa_buffer(struct i915_perf_stream *stream) gtt_offset & GEN12_OAG_OATAILPTR_MASK); /* Mark that we need updated tail pointers to read from... */ - stream->oa_buffer.tail = gtt_offset; + stream->oa_buffer.tail = 0; /* * Reset state used to recognise context switches, affecting which @@ -3227,11 +3194,10 @@ get_sseu_config(struct intel_sseu *out_sseu, */ u32 i915_perf_oa_timestamp_frequency(struct drm_i915_private *i915) { - /* - * Wa_18013179988:dg2 - * Wa_14015846243:mtl - */ - if (IS_DG2(i915) || IS_METEORLAKE(i915)) { + struct intel_gt *gt = to_gt(i915); + + /* Wa_18013179988 */ + if (IS_DG2(i915) || IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71))) { intel_wakeref_t wakeref; u32 reg, shift; @@ -3272,7 +3238,6 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, struct drm_i915_private *i915 = stream->perf->i915; struct i915_perf *perf = stream->perf; struct i915_perf_group *g; - struct intel_gt *gt; int ret; if (!props->engine) { @@ -3280,7 +3245,6 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, "OA engine not specified\n"); return -EINVAL; } - gt = props->engine->gt; g = props->engine->oa_group; /* @@ -3381,25 +3345,6 @@ static int i915_oa_stream_init(struct i915_perf_stream *stream, intel_engine_pm_get(stream->engine); intel_uncore_forcewake_get(stream->uncore, FORCEWAKE_ALL); - /* - * Wa_16011777198:dg2: GuC resets render as part of the Wa. This causes - * OA to lose the configuration state. Prevent this by overriding GUCRC - * mode. - */ - if (intel_uc_uses_guc_rc(>->uc) && - (IS_DG2_GRAPHICS_STEP(gt->i915, G10, STEP_A0, STEP_C0) || - IS_DG2_GRAPHICS_STEP(gt->i915, G11, STEP_A0, STEP_B0))) { - ret = intel_guc_slpc_override_gucrc_mode(>->uc.guc.slpc, - SLPC_GUCRC_MODE_GUCRC_NO_RC6); - if (ret) { - drm_dbg(&stream->perf->i915->drm, - "Unable to override gucrc mode\n"); - goto err_gucrc; - } - - stream->override_gucrc = true; - } - ret = alloc_oa_buffer(stream); if (ret) goto err_oa_buf_alloc; @@ -3436,10 +3381,6 @@ err_enable: free_oa_buffer(stream); err_oa_buf_alloc: - if (stream->override_gucrc) - intel_guc_slpc_unset_gucrc_mode(>->uc.guc.slpc); - -err_gucrc: intel_uncore_forcewake_put(stream->uncore, FORCEWAKE_ALL); intel_engine_pm_put(stream->engine); @@ -4223,7 +4164,7 @@ static int read_properties_unlocked(struct i915_perf *perf, * C6 disable in BIOS. Fail if Media C6 is enabled on steppings where OAM * does not work as expected. */ - if (IS_MTL_MEDIA_STEP(props->engine->i915, STEP_A0, STEP_C0) && + if (IS_MEDIA_GT_IP_STEP(props->engine->gt, IP_VER(13, 0), STEP_A0, STEP_C0) && props->engine->oa_group->type == TYPE_OAM && intel_check_bios_c6_setup(&props->engine->gt->rc6)) { drm_dbg(&perf->i915->drm, @@ -4539,7 +4480,7 @@ static bool xehp_is_valid_b_counter_addr(struct i915_perf *perf, u32 addr) static bool gen12_is_valid_mux_addr(struct i915_perf *perf, u32 addr) { - if (IS_METEORLAKE(perf->i915)) + if (GRAPHICS_VER_FULL(perf->i915) >= IP_VER(12, 70)) return reg_in_range_table(addr, mtl_oa_mux_regs); else return reg_in_range_table(addr, gen12_oa_mux_regs); @@ -5332,16 +5273,9 @@ int i915_perf_ioctl_version(struct drm_i915_private *i915) * C6 disable in BIOS. If Media C6 is enabled in BIOS, return version 6 * to indicate that OA media is not supported. */ - if (IS_MTL_MEDIA_STEP(i915, STEP_A0, STEP_C0)) { - struct intel_gt *gt; - int i; - - for_each_gt(gt, i915, i) { - if (gt->type == GT_MEDIA && - intel_check_bios_c6_setup(>->rc6)) - return 6; - } - } + if (IS_MEDIA_GT_IP_STEP(i915->media_gt, IP_VER(13, 0), STEP_A0, STEP_C0) && + intel_check_bios_c6_setup(&i915->media_gt->rc6)) + return 6; return 7; } diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h index fe3a5dae8c22..13b1ae9b96c7 100644 --- a/drivers/gpu/drm/i915/i915_perf_types.h +++ b/drivers/gpu/drm/i915/i915_perf_types.h @@ -338,12 +338,6 @@ struct i915_perf_stream { * buffer should be checked for available data. */ u64 poll_oa_period; - - /** - * @override_gucrc: GuC RC has been overridden for the perf stream, - * and we need to restore the default configuration on release. - */ - bool override_gucrc; }; /** diff --git a/drivers/gpu/drm/i915/intel_clock_gating.c b/drivers/gpu/drm/i915/intel_clock_gating.c index 81a4d32734e9..c66eb6abd4a2 100644 --- a/drivers/gpu/drm/i915/intel_clock_gating.c +++ b/drivers/gpu/drm/i915/intel_clock_gating.c @@ -396,14 +396,6 @@ static void dg2_init_clock_gating(struct drm_i915_private *i915) /* Wa_22010954014:dg2 */ intel_uncore_rmw(&i915->uncore, XEHP_CLOCK_GATE_DIS, 0, SGSI_SIDECLK_DIS); - - /* - * Wa_14010733611:dg2_g10 - * Wa_22010146351:dg2_g10 - */ - if (IS_DG2_GRAPHICS_STEP(i915, G10, STEP_A0, STEP_B0)) - intel_uncore_rmw(&i915->uncore, XEHP_CLOCK_GATE_DIS, 0, - SGR_DIS | SGGI_DIS); } static void pvc_init_clock_gating(struct drm_i915_private *i915) diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c index ea0ec6174ce5..9dfa680a4c62 100644 --- a/drivers/gpu/drm/i915/intel_device_info.c +++ b/drivers/gpu/drm/i915/intel_device_info.c @@ -206,14 +206,6 @@ static const u16 subplatform_g12_ids[] = { INTEL_DG2_G12_IDS(0), }; -static const u16 subplatform_m_ids[] = { - INTEL_MTL_M_IDS(0), -}; - -static const u16 subplatform_p_ids[] = { - INTEL_MTL_P_IDS(0), -}; - static bool find_devid(u16 id, const u16 *p, unsigned int num) { for (; num; num--, p++) { @@ -275,12 +267,6 @@ static void intel_device_info_subplatform_init(struct drm_i915_private *i915) } else if (find_devid(devid, subplatform_g12_ids, ARRAY_SIZE(subplatform_g12_ids))) { mask = BIT(INTEL_SUBPLATFORM_G12); - } else if (find_devid(devid, subplatform_m_ids, - ARRAY_SIZE(subplatform_m_ids))) { - mask = BIT(INTEL_SUBPLATFORM_M); - } else if (find_devid(devid, subplatform_p_ids, - ARRAY_SIZE(subplatform_p_ids))) { - mask = BIT(INTEL_SUBPLATFORM_P); } GEM_BUG_ON(mask & ~INTEL_SUBPLATFORM_MASK); diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h index dbfe6443457b..2ca54417d19b 100644 --- a/drivers/gpu/drm/i915/intel_device_info.h +++ b/drivers/gpu/drm/i915/intel_device_info.h @@ -129,10 +129,6 @@ enum intel_platform { #define INTEL_SUBPLATFORM_N 1 #define INTEL_SUBPLATFORM_RPLU 2 -/* MTL */ -#define INTEL_SUBPLATFORM_M 0 -#define INTEL_SUBPLATFORM_P 1 - enum intel_ppgtt_type { INTEL_PPGTT_NONE = I915_GEM_PPGTT_NONE, INTEL_PPGTT_ALIASING = I915_GEM_PPGTT_ALIASING, diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_43.h b/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_43.h index 0165d38fbead..329b4fcdc040 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_43.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_cmd_interface_43.h @@ -14,8 +14,8 @@ #define PXP43_CMDID_NEW_HUC_AUTH 0x0000003F /* MTL+ */ #define PXP43_CMDID_INIT_SESSION 0x00000036 -/* PXP-Packet sizes for MTL's GSCCS-HECI instruction */ -#define PXP43_MAX_HECI_INOUT_SIZE (SZ_32K) +/* PXP-Packet sizes for MTL's GSCCS-HECI instruction is spec'd at 65K before page alignment*/ +#define PXP43_MAX_HECI_INOUT_SIZE (PAGE_ALIGN(SZ_64K + SZ_1K)) /* PXP-Packet size for MTL's NEW_HUC_AUTH instruction */ #define PXP43_HUC_AUTH_INOUT_SIZE (SZ_4K) diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.c b/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.c index 2a600184a077..9b2cc0db2f55 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.c @@ -111,7 +111,7 @@ gsccs_send_message(struct intel_pxp *pxp, ret = intel_gsc_uc_heci_cmd_submit_nonpriv(>->uc.gsc, exec_res->ce, &pkt, exec_res->bb_vaddr, - GSC_REPLY_LATENCY_MS); + GSC_HECI_REPLY_LATENCY_MS); if (ret) { drm_err(&i915->drm, "failed to send gsc PXP msg (%d)\n", ret); goto unlock; diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h b/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h index 298ad38e6c7d..9aae779c4da3 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_gsccs.h @@ -8,16 +8,14 @@ #include <linux/types.h> +#include "gt/uc/intel_gsc_uc_heci_cmd_submit.h" + struct intel_pxp; -#define GSC_REPLY_LATENCY_MS 210 -/* - * Max FW response time is 200ms, to which we add 10ms to account for overhead - * such as request preparation, GuC submission to hw and pipeline completion times. - */ #define GSC_PENDING_RETRY_MAXCOUNT 40 #define GSC_PENDING_RETRY_PAUSE_MS 50 -#define GSCFW_MAX_ROUND_TRIP_LATENCY_MS (GSC_PENDING_RETRY_MAXCOUNT * GSC_PENDING_RETRY_PAUSE_MS) +#define GSCFW_MAX_ROUND_TRIP_LATENCY_MS (GSC_HECI_REPLY_LATENCY_MS + \ + (GSC_PENDING_RETRY_MAXCOUNT * GSC_PENDING_RETRY_PAUSE_MS)) #ifdef CONFIG_DRM_I915_PXP void intel_pxp_gsccs_fini(struct intel_pxp *pxp); diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c index 80bb00189865..e50112645950 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_tee.c @@ -9,6 +9,7 @@ #include <drm/i915_component.h> #include "gem/i915_gem_lmem.h" +#include "gt/intel_gt_print.h" #include "i915_drv.h" #include "gt/intel_gt.h" @@ -155,7 +156,8 @@ static int i915_pxp_tee_component_bind(struct device *i915_kdev, { struct drm_i915_private *i915 = kdev_to_i915(i915_kdev); struct intel_pxp *pxp = i915->pxp; - struct intel_uc *uc = &pxp->ctrl_gt->uc; + struct intel_gt *gt = pxp->ctrl_gt; + struct intel_uc *uc = >->uc; intel_wakeref_t wakeref; int ret = 0; @@ -175,7 +177,7 @@ static int i915_pxp_tee_component_bind(struct device *i915_kdev, /* load huc via pxp */ ret = intel_huc_fw_load_and_auth_via_gsc(&uc->huc); if (ret < 0) - drm_err(&i915->drm, "failed to load huc via gsc %d\n", ret); + gt_probe_error(gt, "failed to load huc via gsc %d\n", ret); } } diff --git a/drivers/gpu/drm/i915/selftests/igt_spinner.c b/drivers/gpu/drm/i915/selftests/igt_spinner.c index 0f064930ef11..8c3e1f20e5a1 100644 --- a/drivers/gpu/drm/i915/selftests/igt_spinner.c +++ b/drivers/gpu/drm/i915/selftests/igt_spinner.c @@ -179,6 +179,9 @@ igt_spinner_create_request(struct igt_spinner *spin, *batch++ = arbitration_command; + memset32(batch, MI_NOOP, 128); + batch += 128; + if (GRAPHICS_VER(rq->i915) >= 8) *batch++ = MI_BATCH_BUFFER_START | BIT(8) | 1; else if (IS_HASWELL(rq->i915)) |