diff options
author | Dave Airlie <airlied@redhat.com> | 2024-04-30 07:20:31 +0300 |
---|---|---|
committer | Dave Airlie <airlied@redhat.com> | 2024-04-30 07:40:43 +0300 |
commit | 68b89e23c2282877b0d411e07a3ef90490d6fe30 (patch) | |
tree | b9be4b583185edfdb72255819ae8c3680166fb67 /drivers/gpu | |
parent | b84bc948528e6474ba48596144e9c17466a98448 (diff) | |
parent | 4d3421e04c5dc38baf15224c051256204f223c15 (diff) | |
download | linux-68b89e23c2282877b0d411e07a3ef90490d6fe30.tar.xz |
Merge tag 'drm-intel-gt-next-2024-04-26' of https://anongit.freedesktop.org/git/drm/drm-intel into drm-next
UAPI Changes:
- drm/i915/guc: Use context hints for GT frequency
Allow user to provide a low latency context hint. When set, KMD
sends a hint to GuC which results in special handling for this
context. SLPC will ramp the GT frequency aggressively every time
it switches to this context. The down freq threshold will also be
lower so GuC will ramp down the GT freq for this context more slowly.
We also disable waitboost for this context as that will interfere with
the strategy.
We need to enable the use of SLPC Compute strategy during init, but
it will apply only to contexts that set this bit during context
creation.
Userland can check whether this feature is supported using a new param-
I915_PARAM_HAS_CONTEXT_FREQ_HINT. This flag is true for all guc submission
enabled platforms as they use SLPC for frequency management.
The Mesa usage model for this flag is here -
https://gitlab.freedesktop.org/sushmave/mesa/-/commits/compute_hint
- drm/i915/gt: Enable only one CCS for compute workload
Enable only one CCS engine by default with all the compute sices
allocated to it.
While generating the list of UABI engines to be exposed to the
user, exclude any additional CCS engines beyond the first
instance
***
NOTE: This W/A will make all DG2 SKUs appear like single CCS SKUs by
default to mitigate a hardware bug. All the EUs will still remain
usable, and all the userspace drivers have been confirmed to be able
to dynamically detect the change in number of CCS engines and adjust.
For the smaller percent of applications that get perf benefit from
letting the userspace driver dispatch across all 4 CCS engines we will
be introducing a sysfs control as a later patch to choose 4 CCS each
with 25% EUs (or 50% if 2 CCS).
NOTE: A regression has been reported at
https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/10895
However Andi has been triaging the issue and we're closing in a fix
to the gap in the W/A implementation:
https://lists.freedesktop.org/archives/intel-gfx/2024-April/348747.html
Driver Changes:
- Add new and fix to existing workarounds: Wa_14018575942 (MTL),
Wa_16019325821 (Gen12.70), Wa_14019159160 (MTL), Wa_16015675438,
Wa_14020495402 (Gen12.70) (Tejas, John, Lucas)
- Fix UAF on destroy against retire race and remove two earlier
partial fixes (Janusz)
- Limit the reserved VM space to only the platforms that need it (Andi)
- Reset queue_priority_hint on parking for execlist platforms (Chris)
- Fix gt reset with GuC submission is disabled (Nirmoy)
- Correct capture of EIR register on hang (John)
- Remove usage of the deprecated ida_simple_xx() API
- Refactor confusing __intel_gt_reset() (Nirmoy)
- Fix the fix for GuC reset lock confusion (John)
- Simplify/extend platform check for Wa_14018913170 (John)
- Replace dev_priv with i915 (Andi)
- Add and use gt_to_guc() wrapper (Andi)
- Remove bogus null check (Rodrigo, Dan)
. Selftest improvements (Janusz, Nirmoy, Daniele)
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/ZitVBTvZmityDi7D@jlahtine-mobl.ger.corp.intel.com
Diffstat (limited to 'drivers/gpu')
53 files changed, 399 insertions, 156 deletions
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index dcbfe32fd30c..81f65cab1330 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -879,6 +879,7 @@ static int set_proto_ctx_param(struct drm_i915_file_private *fpriv, struct i915_gem_proto_context *pc, struct drm_i915_gem_context_param *args) { + struct drm_i915_private *i915 = fpriv->i915; int ret = 0; switch (args->param) { @@ -904,6 +905,13 @@ static int set_proto_ctx_param(struct drm_i915_file_private *fpriv, pc->user_flags &= ~BIT(UCONTEXT_BANNABLE); break; + case I915_CONTEXT_PARAM_LOW_LATENCY: + if (intel_uc_uses_guc_submission(&to_gt(i915)->uc)) + pc->user_flags |= BIT(UCONTEXT_LOW_LATENCY); + else + ret = -EINVAL; + break; + case I915_CONTEXT_PARAM_RECOVERABLE: if (args->size) ret = -EINVAL; @@ -992,6 +1000,9 @@ static int intel_context_set_gem(struct intel_context *ce, if (sseu.slice_mask && !WARN_ON(ce->engine->class != RENDER_CLASS)) ret = intel_context_reconfigure_sseu(ce, sseu); + if (test_bit(UCONTEXT_LOW_LATENCY, &ctx->user_flags)) + __set_bit(CONTEXT_LOW_LATENCY, &ce->flags); + return ret; } @@ -1630,6 +1641,9 @@ i915_gem_create_context(struct drm_i915_private *i915, if (vm) ctx->vm = vm; + /* Assign early so intel_context_set_gem can access these flags */ + ctx->user_flags = pc->user_flags; + mutex_init(&ctx->engines_mutex); if (pc->num_user_engines >= 0) { i915_gem_context_set_user_engines(ctx); @@ -1652,8 +1666,6 @@ i915_gem_create_context(struct drm_i915_private *i915, * is no remap info, it will be a NOP. */ ctx->remap_slice = ALL_L3_SLICES(i915); - ctx->user_flags = pc->user_flags; - for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++) ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h index 03bc7f9d191b..b6d97da63d1f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h @@ -338,6 +338,7 @@ struct i915_gem_context { #define UCONTEXT_BANNABLE 2 #define UCONTEXT_RECOVERABLE 3 #define UCONTEXT_PERSISTENCE 4 +#define UCONTEXT_LOW_LATENCY 5 /** * @flags: small set of booleans diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index d3a771afb083..42619fc05de4 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -255,7 +255,6 @@ struct i915_execbuffer { struct intel_context *context; /* logical state for the request */ struct i915_gem_context *gem_context; /** caller's context */ intel_wakeref_t wakeref; - intel_wakeref_t wakeref_gt0; /** our requests to build */ struct i915_request *requests[MAX_ENGINE_INSTANCE + 1]; @@ -2457,7 +2456,7 @@ static int eb_submit(struct i915_execbuffer *eb) * The engine index is returned. */ static unsigned int -gen8_dispatch_bsd_engine(struct drm_i915_private *dev_priv, +gen8_dispatch_bsd_engine(struct drm_i915_private *i915, struct drm_file *file) { struct drm_i915_file_private *file_priv = file->driver_priv; @@ -2465,7 +2464,7 @@ gen8_dispatch_bsd_engine(struct drm_i915_private *dev_priv, /* Check whether the file_priv has already selected one ring. */ if ((int)file_priv->bsd_engine < 0) file_priv->bsd_engine = - get_random_u32_below(dev_priv->engine_uabi_class_count[I915_ENGINE_CLASS_VIDEO]); + get_random_u32_below(i915->engine_uabi_class_count[I915_ENGINE_CLASS_VIDEO]); return file_priv->bsd_engine; } @@ -2686,7 +2685,6 @@ static int eb_select_engine(struct i915_execbuffer *eb) { struct intel_context *ce, *child; - struct intel_gt *gt; unsigned int idx; int err; @@ -2710,17 +2708,10 @@ eb_select_engine(struct i915_execbuffer *eb) } } eb->num_batches = ce->parallel.number_children + 1; - gt = ce->engine->gt; for_each_child(ce, child) intel_context_get(child); eb->wakeref = intel_gt_pm_get(ce->engine->gt); - /* - * Keep GT0 active on MTL so that i915_vma_parked() doesn't - * free VMAs while execbuf ioctl is validating VMAs. - */ - if (gt->info.id) - eb->wakeref_gt0 = intel_gt_pm_get(to_gt(gt->i915)); if (!test_bit(CONTEXT_ALLOC_BIT, &ce->flags)) { err = intel_context_alloc_state(ce); @@ -2759,9 +2750,6 @@ eb_select_engine(struct i915_execbuffer *eb) return err; err: - if (gt->info.id) - intel_gt_pm_put(to_gt(gt->i915), eb->wakeref_gt0); - intel_gt_pm_put(ce->engine->gt, eb->wakeref); for_each_child(ce, child) intel_context_put(child); @@ -2775,12 +2763,6 @@ eb_put_engine(struct i915_execbuffer *eb) struct intel_context *child; i915_vm_put(eb->context->vm); - /* - * This works in conjunction with eb_select_engine() to prevent - * i915_vma_parked() from interfering while execbuf validates vmas. - */ - if (eb->gt->info.id) - intel_gt_pm_put(to_gt(eb->gt->i915), eb->wakeref_gt0); intel_gt_pm_put(eb->context->engine->gt, eb->wakeref); for_each_child(eb->context, child) intel_context_put(child); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index 38b72d86560f..c5e1c718a6d2 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -654,7 +654,7 @@ i915_gem_object_create_shmem(struct drm_i915_private *i915, /* Allocate a new GEM object and fill it with the supplied data */ struct drm_i915_gem_object * -i915_gem_object_create_shmem_from_data(struct drm_i915_private *dev_priv, +i915_gem_object_create_shmem_from_data(struct drm_i915_private *i915, const void *data, resource_size_t size) { struct drm_i915_gem_object *obj; @@ -663,8 +663,8 @@ i915_gem_object_create_shmem_from_data(struct drm_i915_private *dev_priv, resource_size_t offset; int err; - GEM_WARN_ON(IS_DGFX(dev_priv)); - obj = i915_gem_object_create_shmem(dev_priv, round_up(size, PAGE_SIZE)); + GEM_WARN_ON(IS_DGFX(i915)); + obj = i915_gem_object_create_shmem(i915, round_up(size, PAGE_SIZE)); if (IS_ERR(obj)) return obj; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.h b/drivers/gpu/drm/i915/gem/i915_gem_stolen.h index 258381d1c054..dfe0db8bb1b9 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.h @@ -14,14 +14,14 @@ struct drm_i915_gem_object; #define i915_stolen_fb drm_mm_node -int i915_gem_stolen_insert_node(struct drm_i915_private *dev_priv, +int i915_gem_stolen_insert_node(struct drm_i915_private *i915, struct drm_mm_node *node, u64 size, unsigned alignment); -int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *dev_priv, +int i915_gem_stolen_insert_node_in_range(struct drm_i915_private *i915, struct drm_mm_node *node, u64 size, unsigned alignment, u64 start, u64 end); -void i915_gem_stolen_remove_node(struct drm_i915_private *dev_priv, +void i915_gem_stolen_remove_node(struct drm_i915_private *i915, struct drm_mm_node *node); struct intel_memory_region * i915_gem_stolen_smem_setup(struct drm_i915_private *i915, u16 type, @@ -31,7 +31,7 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type, u16 instance); struct drm_i915_gem_object * -i915_gem_object_create_stolen(struct drm_i915_private *dev_priv, +i915_gem_object_create_stolen(struct drm_i915_private *i915, resource_size_t size); bool i915_gem_object_is_stolen(const struct drm_i915_gem_object *obj); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c index a049ca0b7980..d9eb84c1d2f1 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c @@ -343,12 +343,12 @@ int i915_gem_set_tiling_ioctl(struct drm_device *dev, void *data, struct drm_file *file) { - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *i915 = to_i915(dev); struct drm_i915_gem_set_tiling *args = data; struct drm_i915_gem_object *obj; int err; - if (!to_gt(dev_priv)->ggtt->num_fences) + if (!to_gt(i915)->ggtt->num_fences) return -EOPNOTSUPP; obj = i915_gem_object_lookup(file, args->handle); @@ -374,9 +374,9 @@ i915_gem_set_tiling_ioctl(struct drm_device *dev, void *data, args->stride = 0; } else { if (args->tiling_mode == I915_TILING_X) - args->swizzle_mode = to_gt(dev_priv)->ggtt->bit_6_swizzle_x; + args->swizzle_mode = to_gt(i915)->ggtt->bit_6_swizzle_x; else - args->swizzle_mode = to_gt(dev_priv)->ggtt->bit_6_swizzle_y; + args->swizzle_mode = to_gt(i915)->ggtt->bit_6_swizzle_y; /* Hide bit 17 swizzling from the user. This prevents old Mesa * from aborting the application on sw fallbacks to bit 17, @@ -427,11 +427,11 @@ i915_gem_get_tiling_ioctl(struct drm_device *dev, void *data, struct drm_file *file) { struct drm_i915_gem_get_tiling *args = data; - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *i915 = to_i915(dev); struct drm_i915_gem_object *obj; int err = -ENOENT; - if (!to_gt(dev_priv)->ggtt->num_fences) + if (!to_gt(i915)->ggtt->num_fences) return -EOPNOTSUPP; rcu_read_lock(); @@ -447,10 +447,10 @@ i915_gem_get_tiling_ioctl(struct drm_device *dev, void *data, switch (args->tiling_mode) { case I915_TILING_X: - args->swizzle_mode = to_gt(dev_priv)->ggtt->bit_6_swizzle_x; + args->swizzle_mode = to_gt(i915)->ggtt->bit_6_swizzle_x; break; case I915_TILING_Y: - args->swizzle_mode = to_gt(dev_priv)->ggtt->bit_6_swizzle_y; + args->swizzle_mode = to_gt(i915)->ggtt->bit_6_swizzle_y; break; default: case I915_TILING_NONE: @@ -459,7 +459,7 @@ i915_gem_get_tiling_ioctl(struct drm_device *dev, void *data, } /* Hide bit 17 from the user -- see comment in i915_gem_set_tiling */ - if (dev_priv->gem_quirks & GEM_QUIRK_PIN_SWIZZLED_PAGES) + if (i915->gem_quirks & GEM_QUIRK_PIN_SWIZZLED_PAGES) args->phys_swizzle_mode = I915_BIT_6_SWIZZLE_UNKNOWN; else args->phys_swizzle_mode = args->swizzle_mode; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 61abfb505766..09b68713ab32 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -463,13 +463,13 @@ i915_gem_userptr_ioctl(struct drm_device *dev, struct drm_file *file) { static struct lock_class_key __maybe_unused lock_class; - struct drm_i915_private *dev_priv = to_i915(dev); + struct drm_i915_private *i915 = to_i915(dev); struct drm_i915_gem_userptr *args = data; struct drm_i915_gem_object __maybe_unused *obj; int __maybe_unused ret; u32 __maybe_unused handle; - if (!HAS_LLC(dev_priv) && !HAS_SNOOP(dev_priv)) { + if (!HAS_LLC(i915) && !HAS_SNOOP(i915)) { /* We cannot support coherent userptr objects on hw without * LLC and broken snooping. */ @@ -501,7 +501,7 @@ i915_gem_userptr_ioctl(struct drm_device *dev, * On almost all of the older hw, we cannot tell the GPU that * a page is readonly. */ - if (!to_gt(dev_priv)->vm->has_read_only) + if (!to_gt(i915)->vm->has_read_only) return -ENODEV; } diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c index edb54903be0a..84d41e6ccf05 100644 --- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c +++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c @@ -1969,19 +1969,19 @@ int i915_gem_huge_page_mock_selftests(void) SUBTEST(igt_mock_memory_region_huge_pages), SUBTEST(igt_mock_ppgtt_misaligned_dma), }; - struct drm_i915_private *dev_priv; + struct drm_i915_private *i915; struct i915_ppgtt *ppgtt; int err; - dev_priv = mock_gem_device(); - if (!dev_priv) + i915 = mock_gem_device(); + if (!i915) return -ENOMEM; /* Pretend to be a device which supports the 48b PPGTT */ - RUNTIME_INFO(dev_priv)->ppgtt_type = INTEL_PPGTT_FULL; - RUNTIME_INFO(dev_priv)->ppgtt_size = 48; + RUNTIME_INFO(i915)->ppgtt_type = INTEL_PPGTT_FULL; + RUNTIME_INFO(i915)->ppgtt_size = 48; - ppgtt = i915_ppgtt_create(to_gt(dev_priv), 0); + ppgtt = i915_ppgtt_create(to_gt(i915), 0); if (IS_ERR(ppgtt)) { err = PTR_ERR(ppgtt); goto out_unlock; @@ -2005,7 +2005,7 @@ int i915_gem_huge_page_mock_selftests(void) out_put: i915_vm_put(&ppgtt->vm); out_unlock: - mock_destroy_device(dev_priv); + mock_destroy_device(i915); return err; } diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c index d684a70f2c04..65a931ea80e9 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_dmabuf.c @@ -7,6 +7,7 @@ #include "i915_drv.h" #include "i915_selftest.h" #include "gem/i915_gem_context.h" +#include "gt/intel_gt.h" #include "mock_context.h" #include "mock_dmabuf.h" @@ -155,6 +156,7 @@ static int verify_access(struct drm_i915_private *i915, struct file *file; u32 *vaddr; int err = 0, i; + unsigned int mode; file = mock_file(i915); if (IS_ERR(file)) @@ -194,7 +196,8 @@ static int verify_access(struct drm_i915_private *i915, if (err) goto out_file; - vaddr = i915_gem_object_pin_map_unlocked(native_obj, I915_MAP_WB); + mode = intel_gt_coherent_map_type(to_gt(i915), native_obj, true); + vaddr = i915_gem_object_pin_map_unlocked(native_obj, mode); if (IS_ERR(vaddr)) { err = PTR_ERR(vaddr); goto out_file; diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index 2e27bcb52e0d..e9f65f27b53f 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -740,21 +740,25 @@ static u32 *gen12_emit_preempt_busywait(struct i915_request *rq, u32 *cs) } /* Wa_14014475959:dg2 */ -#define CCS_SEMAPHORE_PPHWSP_OFFSET 0x540 -static u32 ccs_semaphore_offset(struct i915_request *rq) +/* Wa_16019325821 */ +/* Wa_14019159160 */ +#define HOLD_SWITCHOUT_SEMAPHORE_PPHWSP_OFFSET 0x540 +static u32 hold_switchout_semaphore_offset(struct i915_request *rq) { return i915_ggtt_offset(rq->context->state) + - (LRC_PPHWSP_PN * PAGE_SIZE) + CCS_SEMAPHORE_PPHWSP_OFFSET; + (LRC_PPHWSP_PN * PAGE_SIZE) + HOLD_SWITCHOUT_SEMAPHORE_PPHWSP_OFFSET; } /* Wa_14014475959:dg2 */ -static u32 *ccs_emit_wa_busywait(struct i915_request *rq, u32 *cs) +/* Wa_16019325821 */ +/* Wa_14019159160 */ +static u32 *hold_switchout_emit_wa_busywait(struct i915_request *rq, u32 *cs) { int i; *cs++ = MI_ATOMIC_INLINE | MI_ATOMIC_GLOBAL_GTT | MI_ATOMIC_CS_STALL | MI_ATOMIC_MOVE; - *cs++ = ccs_semaphore_offset(rq); + *cs++ = hold_switchout_semaphore_offset(rq); *cs++ = 0; *cs++ = 1; @@ -770,7 +774,7 @@ static u32 *ccs_emit_wa_busywait(struct i915_request *rq, u32 *cs) MI_SEMAPHORE_POLL | MI_SEMAPHORE_SAD_EQ_SDD; *cs++ = 0; - *cs++ = ccs_semaphore_offset(rq); + *cs++ = hold_switchout_semaphore_offset(rq); *cs++ = 0; return cs; @@ -787,8 +791,10 @@ gen12_emit_fini_breadcrumb_tail(struct i915_request *rq, u32 *cs) cs = gen12_emit_preempt_busywait(rq, cs); /* Wa_14014475959:dg2 */ - if (intel_engine_uses_wa_hold_ccs_switchout(rq->engine)) - cs = ccs_emit_wa_busywait(rq, cs); + /* Wa_16019325821 */ + /* Wa_14019159160 */ + if (intel_engine_uses_wa_hold_switchout(rq->engine)) + cs = hold_switchout_emit_wa_busywait(rq, cs); rq->tail = intel_ring_offset(rq, cs); assert_ring_tail_valid(rq->ring, rq->tail); diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index 7eccbd70d89f..ed95a7b57cbb 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -130,6 +130,7 @@ struct intel_context { #define CONTEXT_PERMA_PIN 11 #define CONTEXT_IS_PARKING 12 #define CONTEXT_EXITING 13 +#define CONTEXT_LOW_LATENCY 14 struct { u64 timeout_us; diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 6bee0c6026ab..5c8e9ee3b008 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -588,7 +588,7 @@ u64 intel_clamp_preempt_timeout_ms(struct intel_engine_cs *engine, u64 value) * NB: The GuC API only supports 32bit values. However, the limit is further * reduced due to internal calculations which would otherwise overflow. */ - if (intel_guc_submission_is_wanted(&engine->gt->uc.guc)) + if (intel_guc_submission_is_wanted(gt_to_guc(engine->gt))) value = min_t(u64, value, guc_policy_max_preempt_timeout_ms()); value = min_t(u64, value, jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT)); @@ -609,7 +609,7 @@ u64 intel_clamp_timeslice_duration_ms(struct intel_engine_cs *engine, u64 value) * NB: The GuC API only supports 32bit values. However, the limit is further * reduced due to internal calculations which would otherwise overflow. */ - if (intel_guc_submission_is_wanted(&engine->gt->uc.guc)) + if (intel_guc_submission_is_wanted(gt_to_guc(engine->gt))) value = min_t(u64, value, guc_policy_max_exec_quantum_ms()); value = min_t(u64, value, jiffies_to_msecs(MAX_SCHEDULE_TIMEOUT)); @@ -678,7 +678,7 @@ void intel_engines_release(struct intel_gt *gt) */ GEM_BUG_ON(intel_gt_pm_is_awake(gt)); if (!INTEL_INFO(gt->i915)->gpu_reset_clobbers_display) - __intel_gt_reset(gt, ALL_ENGINES); + intel_gt_reset_all_engines(gt); /* Decouple the backend; but keep the layout for late GPU resets */ for_each_engine(engine, gt, id) { diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index 960e6be2042f..ba55c059063d 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -586,7 +586,7 @@ struct intel_engine_cs { #define I915_ENGINE_HAS_RCS_REG_STATE BIT(9) #define I915_ENGINE_HAS_EU_PRIORITY BIT(10) #define I915_ENGINE_FIRST_RENDER_COMPUTE BIT(11) -#define I915_ENGINE_USES_WA_HOLD_CCS_SWITCHOUT BIT(12) +#define I915_ENGINE_USES_WA_HOLD_SWITCHOUT BIT(12) unsigned int flags; /* @@ -696,10 +696,12 @@ intel_engine_has_relative_mmio(const struct intel_engine_cs * const engine) } /* Wa_14014475959:dg2 */ +/* Wa_16019325821 */ +/* Wa_14019159160 */ static inline bool -intel_engine_uses_wa_hold_ccs_switchout(struct intel_engine_cs *engine) +intel_engine_uses_wa_hold_switchout(struct intel_engine_cs *engine) { - return engine->flags & I915_ENGINE_USES_WA_HOLD_CCS_SWITCHOUT; + return engine->flags & I915_ENGINE_USES_WA_HOLD_SWITCHOUT; } #endif /* __INTEL_ENGINE_TYPES_H__ */ diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 355aab5b38ba..21829439e686 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -2898,7 +2898,7 @@ static void enable_error_interrupt(struct intel_engine_cs *engine) drm_err(&engine->i915->drm, "engine '%s' resumed still in error: %08x\n", engine->name, status); - __intel_gt_reset(engine->gt, engine->mask); + intel_gt_reset_engine(engine); } /* diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index ec1cbe229f0e..0d0a0dc9f610 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -231,11 +231,8 @@ static void guc_ggtt_ct_invalidate(struct intel_gt *gt) struct intel_uncore *uncore = gt->uncore; intel_wakeref_t wakeref; - with_intel_runtime_pm_if_active(uncore->rpm, wakeref) { - struct intel_guc *guc = >->uc.guc; - - intel_guc_invalidate_tlb_guc(guc); - } + with_intel_runtime_pm_if_active(uncore->rpm, wakeref) + intel_guc_invalidate_tlb_guc(gt_to_guc(gt)); } static void guc_ggtt_invalidate(struct i915_ggtt *ggtt) @@ -246,7 +243,7 @@ static void guc_ggtt_invalidate(struct i915_ggtt *ggtt) gen8_ggtt_invalidate(ggtt); list_for_each_entry(gt, &ggtt->gt_list, ggtt_link) { - if (intel_guc_tlb_invalidation_is_available(>->uc.guc)) + if (intel_guc_tlb_invalidation_is_available(gt_to_guc(gt))) guc_ggtt_ct_invalidate(gt); else if (GRAPHICS_VER(i915) >= 12) intel_uncore_write_fw(gt->uncore, diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index 580b5141ce1e..626b166e67ef 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -832,7 +832,7 @@ void intel_gt_driver_unregister(struct intel_gt *gt) /* Scrub all HW state upon release */ with_intel_runtime_pm(gt->uncore->rpm, wakeref) - __intel_gt_reset(gt, ALL_ENGINES); + intel_gt_reset_all_engines(gt); } void intel_gt_driver_release(struct intel_gt *gt) diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h index 003eb93b826f..b5e114d284ad 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.h +++ b/drivers/gpu/drm/i915/gt/intel_gt.h @@ -124,6 +124,11 @@ static inline struct drm_i915_private *guc_to_i915(struct intel_guc *guc) return guc_to_gt(guc)->i915; } +static inline struct intel_guc *gt_to_guc(struct intel_gt *gt) +{ + return >->uc.guc; +} + void intel_gt_common_init_early(struct intel_gt *gt); int intel_root_gt_init_early(struct drm_i915_private *i915); int intel_gt_assign_ggtt(struct intel_gt *gt); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c index 77fb57223465..ad4c51f18d3a 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c @@ -68,9 +68,9 @@ gen11_other_irq_handler(struct intel_gt *gt, const u8 instance, struct intel_gt *media_gt = gt->i915->media_gt; if (instance == OTHER_GUC_INSTANCE) - return guc_irq_handler(>->uc.guc, iir); + return guc_irq_handler(gt_to_guc(gt), iir); if (instance == OTHER_MEDIA_GUC_INSTANCE && media_gt) - return guc_irq_handler(&media_gt->uc.guc, iir); + return guc_irq_handler(gt_to_guc(media_gt), iir); if (instance == OTHER_GTPM_INSTANCE) return gen11_rps_irq_handler(>->rps, iir); @@ -442,7 +442,7 @@ void gen8_gt_irq_handler(struct intel_gt *gt, u32 master_ctl) iir = raw_reg_read(regs, GEN8_GT_IIR(2)); if (likely(iir)) { gen6_rps_irq_handler(>->rps, iir); - guc_irq_handler(>->uc.guc, iir >> 16); + guc_irq_handler(gt_to_guc(gt), iir >> 16); raw_reg_write(regs, GEN8_GT_IIR(2), iir); } } diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c index 220ac4f92edf..c08fdb65cc69 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c @@ -159,7 +159,7 @@ static bool reset_engines(struct intel_gt *gt) if (INTEL_INFO(gt->i915)->gpu_reset_clobbers_display) return false; - return __intel_gt_reset(gt, ALL_ENGINES) == 0; + return intel_gt_reset_all_engines(gt) == 0; } static void gt_sanitize(struct intel_gt *gt, bool force) 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 2c7afd472959..4fcba42cfe34 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c @@ -534,7 +534,7 @@ static bool rps_eval(void *data) { struct intel_gt *gt = data; - if (intel_guc_slpc_is_used(>->uc.guc)) + if (intel_guc_slpc_is_used(gt_to_guc(gt))) return false; else return HAS_RPS(gt->i915); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h index 95ce267f3ee9..e42b3a5d4e63 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h @@ -1161,6 +1161,7 @@ #define GEN12_DISABLE_EARLY_READ REG_BIT(14) #define GEN12_ENABLE_LARGE_GRF_MODE REG_BIT(12) #define GEN12_PUSH_CONST_DEREF_HOLD_DIS REG_BIT(8) +#define XELPG_DISABLE_TDL_SVHS_GATING REG_BIT(1) #define GEN12_DISABLE_DOP_GATING REG_BIT(0) #define RT_CTRL MCR_REG(0xe530) diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c index f4a5bef246c3..d7784650e4d9 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c @@ -442,7 +442,7 @@ static ssize_t slpc_ignore_eff_freq_show(struct kobject *kobj, char *buff) { struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name); - struct intel_guc_slpc *slpc = >->uc.guc.slpc; + struct intel_guc_slpc *slpc = >_to_guc(gt)->slpc; return sysfs_emit(buff, "%u\n", slpc->ignore_eff_freq); } @@ -452,7 +452,7 @@ static ssize_t slpc_ignore_eff_freq_store(struct kobject *kobj, const char *buff, size_t count) { struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name); - struct intel_guc_slpc *slpc = >->uc.guc.slpc; + struct intel_guc_slpc *slpc = >_to_guc(gt)->slpc; int err; u32 val; @@ -595,7 +595,7 @@ static ssize_t media_freq_factor_store(struct kobject *kobj, const char *buff, size_t count) { struct intel_gt *gt = intel_gt_sysfs_get_drvdata(kobj, attr->attr.name); - struct intel_guc_slpc *slpc = >->uc.guc.slpc; + struct intel_guc_slpc *slpc = >_to_guc(gt)->slpc; u32 factor, mode; int err; diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c index 8f4b3c8af09c..c864d101faf9 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6.c +++ b/drivers/gpu/drm/i915/gt/intel_rc6.c @@ -109,7 +109,7 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6) * thus allowing GuC to control RC6 entry/exit fully instead. * We will not set the HW ENABLE and EI bits */ - if (!intel_guc_rc_enable(>->uc.guc)) + if (!intel_guc_rc_enable(gt_to_guc(gt))) rc6->ctl_enable = GEN6_RC_CTL_RC6_ENABLE; else rc6->ctl_enable = @@ -569,7 +569,7 @@ static void __intel_rc6_disable(struct intel_rc6 *rc6) struct intel_gt *gt = rc6_to_gt(rc6); /* Take control of RC6 back from GuC */ - intel_guc_rc_disable(>->uc.guc); + intel_guc_rc_disable(gt_to_guc(gt)); intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL); if (GRAPHICS_VER(i915) >= 9) diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index c8e9aa41fdea..6161f7a3ff70 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -764,7 +764,7 @@ wa_14015076503_end(struct intel_gt *gt, intel_engine_mask_t engine_mask) HECI_H_GS1_ER_PREP, 0); } -int __intel_gt_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask) +static int __intel_gt_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask) { const int retries = engine_mask == ALL_ENGINES ? RESET_MAX_RETRIES : 1; reset_func reset; @@ -879,8 +879,17 @@ static intel_engine_mask_t reset_prepare(struct intel_gt *gt) intel_engine_mask_t awake = 0; enum intel_engine_id id; - /* For GuC mode, ensure submission is disabled before stopping ring */ - intel_uc_reset_prepare(>->uc); + /** + * For GuC mode with submission enabled, ensure submission + * is disabled before stopping ring. + * + * For GuC mode with submission disabled, ensure that GuC is not + * sanitized, do that after engine reset. reset_prepare() + * is followed by engine reset which in this mode requires GuC to + * process any CSB FIFO entries generated by the resets. + */ + if (intel_uc_uses_guc_submission(>->uc)) + intel_uc_reset_prepare(>->uc); for_each_engine(engine, gt, id) { if (intel_engine_pm_get_if_awake(engine)) @@ -978,7 +987,7 @@ static void __intel_gt_set_wedged(struct intel_gt *gt) /* Even if the GPU reset fails, it should still stop the engines */ if (!INTEL_INFO(gt->i915)->gpu_reset_clobbers_display) - __intel_gt_reset(gt, ALL_ENGINES); + intel_gt_reset_all_engines(gt); for_each_engine(engine, gt, id) engine->submit_request = nop_submit_request; @@ -1089,7 +1098,7 @@ static bool __intel_gt_unset_wedged(struct intel_gt *gt) /* We must reset pending GPU events before restoring our submission */ ok = !HAS_EXECLISTS(gt->i915); /* XXX better agnosticism desired */ if (!INTEL_INFO(gt->i915)->gpu_reset_clobbers_display) - ok = __intel_gt_reset(gt, ALL_ENGINES) == 0; + ok = intel_gt_reset_all_engines(gt) == 0; if (!ok) { /* * Warn CI about the unrecoverable wedged condition. @@ -1133,10 +1142,10 @@ static int do_reset(struct intel_gt *gt, intel_engine_mask_t stalled_mask) { int err, i; - err = __intel_gt_reset(gt, ALL_ENGINES); + err = intel_gt_reset_all_engines(gt); for (i = 0; err && i < RESET_MAX_RETRIES; i++) { msleep(10 * (i + 1)); - err = __intel_gt_reset(gt, ALL_ENGINES); + err = intel_gt_reset_all_engines(gt); } if (err) return err; @@ -1227,6 +1236,9 @@ void intel_gt_reset(struct intel_gt *gt, intel_overlay_reset(gt->i915); + /* sanitize uC after engine reset */ + if (!intel_uc_uses_guc_submission(>->uc)) + intel_uc_reset_prepare(>->uc); /* * Next we need to restore the context, but we don't use those * yet either... @@ -1270,7 +1282,30 @@ error: goto finish; } -static int intel_gt_reset_engine(struct intel_engine_cs *engine) +/** + * intel_gt_reset_all_engines() - Reset all engines in the given gt. + * @gt: the GT to reset all engines for. + * + * This function resets all engines within the given gt. + * + * Returns: + * Zero on success, negative error code on failure. + */ +int intel_gt_reset_all_engines(struct intel_gt *gt) +{ + return __intel_gt_reset(gt, ALL_ENGINES); +} + +/** + * intel_gt_reset_engine() - Reset a specific engine within a gt. + * @engine: engine to be reset. + * + * This function resets the specified engine within a gt. + * + * Returns: + * Zero on success, negative error code on failure. + */ +int intel_gt_reset_engine(struct intel_engine_cs *engine) { return __intel_gt_reset(engine->gt, engine->mask); } diff --git a/drivers/gpu/drm/i915/gt/intel_reset.h b/drivers/gpu/drm/i915/gt/intel_reset.h index f615b30b81c5..c00de353075c 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.h +++ b/drivers/gpu/drm/i915/gt/intel_reset.h @@ -54,7 +54,8 @@ int intel_gt_terminally_wedged(struct intel_gt *gt); void intel_gt_set_wedged_on_init(struct intel_gt *gt); void intel_gt_set_wedged_on_fini(struct intel_gt *gt); -int __intel_gt_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask); +int intel_gt_reset_engine(struct intel_engine_cs *engine); +int intel_gt_reset_all_engines(struct intel_gt *gt); int intel_reset_guc(struct intel_gt *gt); diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index 005942b145aa..c9cb2a391942 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -52,7 +52,7 @@ static struct intel_guc_slpc *rps_to_slpc(struct intel_rps *rps) { struct intel_gt *gt = rps_to_gt(rps); - return >->uc.guc.slpc; + return >_to_guc(gt)->slpc; } static bool rps_uses_slpc(struct intel_rps *rps) @@ -1013,6 +1013,10 @@ void intel_rps_boost(struct i915_request *rq) if (i915_request_signaled(rq) || i915_request_has_waitboost(rq)) return; + /* Waitboost is not needed for contexts marked with a Freq hint */ + if (test_bit(CONTEXT_LOW_LATENCY, &rq->context->flags)) + return; + /* Serializes with i915_request_retire() */ if (!test_and_set_bit(I915_FENCE_FLAG_BOOST, &rq->fence.flags)) { struct intel_rps *rps = &READ_ONCE(rq->engine)->gt->rps; diff --git a/drivers/gpu/drm/i915/gt/intel_tlb.c b/drivers/gpu/drm/i915/gt/intel_tlb.c index 4bb13d1890e3..756e9ebbc725 100644 --- a/drivers/gpu/drm/i915/gt/intel_tlb.c +++ b/drivers/gpu/drm/i915/gt/intel_tlb.c @@ -132,7 +132,7 @@ void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno) return; with_intel_gt_pm_if_awake(gt, wakeref) { - struct intel_guc *guc = >->uc.guc; + struct intel_guc *guc = gt_to_guc(gt); mutex_lock(>->tlb.invalidate_lock); if (tlb_seqno_passed(gt, seqno)) diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index d4e8daf9e6a9..68b6aa11bcf7 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -2760,10 +2760,14 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li 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) || - IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 74), IP_VER(12, 74))) + IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 74), IP_VER(12, 74))) { /* Wa_14017856879 */ wa_mcr_masked_en(wal, GEN9_ROW_CHICKEN3, MTL_DISABLE_FIX_FOR_EOT_FLUSH); + /* Wa_14020495402 */ + wa_mcr_masked_en(wal, GEN8_ROW_CHICKEN2, XELPG_DISABLE_TDL_SVHS_GATING); + } + 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)) /* @@ -2800,9 +2804,6 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li /* 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); - /* * Wa_16011620976:dg2_g11 * Wa_22015475538:dg2 diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c index 0dd4d00ee894..9ce8ff1c04fe 100644 --- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c +++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c @@ -319,7 +319,7 @@ static int igt_hang_sanitycheck(void *arg) i915_request_add(rq); timeout = 0; - intel_wedge_on_timeout(&w, gt, HZ / 10 /* 100ms */) + intel_wedge_on_timeout(&w, gt, HZ / 5 /* 200ms */) timeout = i915_request_wait(rq, 0, MAX_SCHEDULE_TIMEOUT); if (intel_gt_is_wedged(gt)) diff --git a/drivers/gpu/drm/i915/gt/selftest_reset.c b/drivers/gpu/drm/i915/gt/selftest_reset.c index f40de408cd3a..2cfc23c58e90 100644 --- a/drivers/gpu/drm/i915/gt/selftest_reset.c +++ b/drivers/gpu/drm/i915/gt/selftest_reset.c @@ -281,7 +281,7 @@ static int igt_atomic_reset(void *arg) awake = reset_prepare(gt); p->critical_section_begin(); - err = __intel_gt_reset(gt, ALL_ENGINES); + err = intel_gt_reset_all_engines(gt); p->critical_section_end(); reset_finish(gt, awake); diff --git a/drivers/gpu/drm/i915/gt/selftest_slpc.c b/drivers/gpu/drm/i915/gt/selftest_slpc.c index 302d0540295d..4ecc4ae74a54 100644 --- a/drivers/gpu/drm/i915/gt/selftest_slpc.c +++ b/drivers/gpu/drm/i915/gt/selftest_slpc.c @@ -53,7 +53,7 @@ static int slpc_set_max_freq(struct intel_guc_slpc *slpc, u32 freq) static int slpc_set_freq(struct intel_gt *gt, u32 freq) { int err; - struct intel_guc_slpc *slpc = >->uc.guc.slpc; + struct intel_guc_slpc *slpc = >_to_guc(gt)->slpc; err = slpc_set_max_freq(slpc, freq); if (err) { @@ -182,7 +182,7 @@ static int vary_min_freq(struct intel_guc_slpc *slpc, struct intel_rps *rps, static int slpc_power(struct intel_gt *gt, struct intel_engine_cs *engine) { - struct intel_guc_slpc *slpc = >->uc.guc.slpc; + struct intel_guc_slpc *slpc = >_to_guc(gt)->slpc; struct { u64 power; int freq; @@ -262,7 +262,7 @@ static int max_granted_freq(struct intel_guc_slpc *slpc, struct intel_rps *rps, static int run_test(struct intel_gt *gt, int test_type) { - struct intel_guc_slpc *slpc = >->uc.guc.slpc; + struct intel_guc_slpc *slpc = >_to_guc(gt)->slpc; struct intel_rps *rps = >->rps; struct intel_engine_cs *engine; enum intel_engine_id id; diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h index 811add10c30d..c34674e797c6 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_actions_slpc_abi.h @@ -207,6 +207,27 @@ struct slpc_shared_data { u8 reserved_mode_definition[4096]; } __packed; +struct slpc_context_frequency_request { + u32 frequency_request:16; + u32 reserved:12; + u32 is_compute:1; + u32 ignore_busyness:1; + u32 is_minimum:1; + u32 is_predefined:1; +} __packed; + +#define SLPC_CTX_FREQ_REQ_IS_COMPUTE REG_BIT(28) + +struct slpc_optimized_strategies { + u32 compute:1; + u32 async_flip:1; + u32 media:1; + u32 vsync_flip:1; + u32 reserved:28; +} __packed; + +#define SLPC_OPTIMIZED_STRATEGY_COMPUTE REG_BIT(0) + /** * DOC: SLPC H2G MESSAGE FORMAT * diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_errors_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_errors_abi.h index dabeaf4f245f..00d6402333f8 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_errors_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_errors_abi.h @@ -36,6 +36,7 @@ enum intel_guc_load_status { INTEL_GUC_LOAD_STATUS_INVALID_INIT_DATA_RANGE_START, INTEL_GUC_LOAD_STATUS_MPU_DATA_INVALID = 0x73, INTEL_GUC_LOAD_STATUS_INIT_MMIO_SAVE_RESTORE_INVALID = 0x74, + INTEL_GUC_LOAD_STATUS_KLV_WORKAROUND_INIT_ERROR = 0x75, INTEL_GUC_LOAD_STATUS_INVALID_INIT_DATA_RANGE_END, INTEL_GUC_LOAD_STATUS_READY = 0xF0, diff --git a/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h b/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h index 58012edd4eb0..bebf28e3c479 100644 --- a/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h +++ b/drivers/gpu/drm/i915/gt/uc/abi/guc_klvs_abi.h @@ -101,4 +101,11 @@ enum { GUC_CONTEXT_POLICIES_KLV_NUM_IDS = 5, }; +/* + * Workaround keys: + */ +enum { + GUC_WORKAROUND_KLV_SERIALIZED_RA_MODE = 0x9001, +}; + #endif /* _ABI_GUC_KLVS_ABI_H */ diff --git a/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c index e2e42b3e0d5d..3b69bc6616bd 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c @@ -298,7 +298,7 @@ static int gsc_fw_load_prepare(struct intel_gsc_uc *gsc) memcpy_toio(gsc->local_vaddr, src, gsc->fw.size); memset_io(gsc->local_vaddr + gsc->fw.size, 0, gsc->local->size - gsc->fw.size); - intel_guc_write_barrier(>->uc.guc); + intel_guc_write_barrier(gt_to_guc(gt)); i915_gem_object_unpin_map(gsc->fw.obj); @@ -351,7 +351,7 @@ static int gsc_fw_query_compatibility_version(struct intel_gsc_uc *gsc) void *vaddr; int err; - err = intel_guc_allocate_and_map_vma(>->uc.guc, GSC_VER_PKT_SZ * 2, + err = intel_guc_allocate_and_map_vma(gt_to_guc(gt), GSC_VER_PKT_SZ * 2, &vma, &vaddr); if (err) { gt_err(gt, "failed to allocate vma for GSC version query\n"); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_gsc_proxy.c b/drivers/gpu/drm/i915/gt/uc/intel_gsc_proxy.c index 40817ebcca71..a7d5465655f9 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_gsc_proxy.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_gsc_proxy.c @@ -358,7 +358,8 @@ static int proxy_channel_alloc(struct intel_gsc_uc *gsc) void *vaddr; int err; - err = intel_guc_allocate_and_map_vma(>->uc.guc, GSC_PROXY_CHANNEL_SIZE, + err = intel_guc_allocate_and_map_vma(gt_to_guc(gt), + GSC_PROXY_CHANNEL_SIZE, &vma, &vaddr); if (err) return err; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c index b85706aa4aff..5e60a34692af 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c @@ -294,6 +294,11 @@ static u32 guc_ctl_wa_flags(struct intel_guc *guc) IS_DG2(gt->i915)) flags |= GUC_WA_HOLD_CCS_SWITCHOUT; + /* Wa_16019325821 */ + /* Wa_14019159160 */ + if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71))) + flags |= GUC_WA_RCS_CCS_SWITCHOUT; + /* * Wa_14012197797 * Wa_22011391025 @@ -315,11 +320,12 @@ static u32 guc_ctl_wa_flags(struct intel_guc *guc) if (IS_DG2_G11(gt->i915)) flags |= GUC_WA_CONTEXT_ISOLATION; - /* Wa_14018913170 */ - if (GUC_FIRMWARE_VER(guc) >= MAKE_GUC_VER(70, 7, 0)) { - if (IS_DG2(gt->i915) || IS_METEORLAKE(gt->i915)) - flags |= GUC_WA_ENABLE_TSC_CHECK_ON_RC6; - } + /* + * Wa_14018913170: Applicable to all platforms supported by i915 so + * don't bother testing for all X/Y/Z platforms explicitly. + */ + if (GUC_FIRMWARE_VER(guc) >= MAKE_GUC_VER(70, 7, 0)) + flags |= GUC_WA_ENABLE_TSC_CHECK_ON_RC6; return flags; } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index be70c46604b4..57b903132776 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -204,6 +204,8 @@ struct intel_guc { struct guc_mmio_reg *ads_regset; /** @ads_golden_ctxt_size: size of the golden contexts in the ADS */ u32 ads_golden_ctxt_size; + /** @ads_waklv_size: size of workaround KLVs */ + u32 ads_waklv_size; /** @ads_capture_size: size of register lists in the ADS used for error capture */ u32 ads_capture_size; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c index 3345aed2f88a..c606bb5e3b7b 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ads.c @@ -46,6 +46,10 @@ * +---------------------------------------+ * | padding | * +---------------------------------------+ <== 4K aligned + * | w/a KLVs | + * +---------------------------------------+ + * | padding | + * +---------------------------------------+ <== 4K aligned * | capture lists | * +---------------------------------------+ * | padding | @@ -88,6 +92,11 @@ static u32 guc_ads_golden_ctxt_size(struct intel_guc *guc) return PAGE_ALIGN(guc->ads_golden_ctxt_size); } +static u32 guc_ads_waklv_size(struct intel_guc *guc) +{ + return PAGE_ALIGN(guc->ads_waklv_size); +} + static u32 guc_ads_capture_size(struct intel_guc *guc) { return PAGE_ALIGN(guc->ads_capture_size); @@ -113,7 +122,7 @@ static u32 guc_ads_golden_ctxt_offset(struct intel_guc *guc) return PAGE_ALIGN(offset); } -static u32 guc_ads_capture_offset(struct intel_guc *guc) +static u32 guc_ads_waklv_offset(struct intel_guc *guc) { u32 offset; @@ -123,6 +132,16 @@ static u32 guc_ads_capture_offset(struct intel_guc *guc) return PAGE_ALIGN(offset); } +static u32 guc_ads_capture_offset(struct intel_guc *guc) +{ + u32 offset; + + offset = guc_ads_waklv_offset(guc) + + guc_ads_waklv_size(guc); + + return PAGE_ALIGN(offset); +} + static u32 guc_ads_private_data_offset(struct intel_guc *guc) { u32 offset; @@ -796,6 +815,65 @@ engine_instance_list: return PAGE_ALIGN(total_size); } +/* Wa_14019159160 */ +static u32 guc_waklv_ra_mode(struct intel_guc *guc, u32 offset, u32 remain) +{ + u32 size; + u32 klv_entry[] = { + /* 16:16 key/length */ + FIELD_PREP(GUC_KLV_0_KEY, GUC_WORKAROUND_KLV_SERIALIZED_RA_MODE) | + FIELD_PREP(GUC_KLV_0_LEN, 0), + /* 0 dwords data */ + }; + + size = sizeof(klv_entry); + GEM_BUG_ON(remain < size); + + iosys_map_memcpy_to(&guc->ads_map, offset, klv_entry, size); + + return size; +} + +static void guc_waklv_init(struct intel_guc *guc) +{ + struct intel_gt *gt = guc_to_gt(guc); + u32 offset, addr_ggtt, remain, size; + + if (!intel_uc_uses_guc_submission(>->uc)) + return; + + if (GUC_FIRMWARE_VER(guc) < MAKE_GUC_VER(70, 10, 0)) + return; + + GEM_BUG_ON(iosys_map_is_null(&guc->ads_map)); + offset = guc_ads_waklv_offset(guc); + remain = guc_ads_waklv_size(guc); + + /* Wa_14019159160 */ + if (IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 70), IP_VER(12, 71))) { + size = guc_waklv_ra_mode(guc, offset, remain); + offset += size; + remain -= size; + } + + size = guc_ads_waklv_size(guc) - remain; + if (!size) + return; + + offset = guc_ads_waklv_offset(guc); + addr_ggtt = intel_guc_ggtt_offset(guc, guc->ads_vma) + offset; + + ads_blob_write(guc, ads.wa_klv_addr_lo, addr_ggtt); + ads_blob_write(guc, ads.wa_klv_addr_hi, 0); + ads_blob_write(guc, ads.wa_klv_size, size); +} + +static int guc_prep_waklv(struct intel_guc *guc) +{ + /* Fudge something chunky for now: */ + return PAGE_SIZE; +} + static void __guc_ads_init(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); @@ -843,6 +921,9 @@ static void __guc_ads_init(struct intel_guc *guc) /* MMIO save/restore list */ guc_mmio_reg_state_init(guc); + /* Workaround KLV list */ + guc_waklv_init(guc); + /* Private Data */ ads_blob_write(guc, ads.private_data, base + guc_ads_private_data_offset(guc)); @@ -886,6 +967,12 @@ int intel_guc_ads_create(struct intel_guc *guc) return ret; guc->ads_capture_size = ret; + /* And don't forget the workaround KLVs: */ + ret = guc_prep_waklv(guc); + if (ret < 0) + return ret; + guc->ads_waklv_size = ret; + /* Now the total size can be determined: */ size = guc_ads_blob_size(guc); @@ -961,7 +1048,7 @@ u32 intel_guc_engine_usage_offset(struct intel_guc *guc) struct iosys_map intel_guc_engine_usage_record_map(struct intel_engine_cs *engine) { - struct intel_guc *guc = &engine->gt->uc.guc; + struct intel_guc *guc = gt_to_guc(engine->gt); u8 guc_class = engine_class_to_guc_class(engine->class); size_t offset = offsetof(struct __guc_ads_blob, engine_usage.engines[guc_class][ilog2(engine->logical_mask)]); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c index a1cd40d80517..9547fff672bd 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c @@ -51,6 +51,7 @@ { RING_ESR(0), 0, 0, "ESR" }, \ { RING_DMA_FADD(0), 0, 0, "RING_DMA_FADD_LDW" }, \ { RING_DMA_FADD_UDW(0), 0, 0, "RING_DMA_FADD_UDW" }, \ + { RING_EIR(0), 0, 0, "EIR" }, \ { RING_IPEIR(0), 0, 0, "IPEIR" }, \ { RING_IPEHR(0), 0, 0, "IPEHR" }, \ { RING_INSTPS(0), 0, 0, "INSTPS" }, \ @@ -80,9 +81,6 @@ { GEN8_RING_PDP_LDW(0, 3), 0, 0, "PDP3_LDW" }, \ { GEN8_RING_PDP_UDW(0, 3), 0, 0, "PDP3_UDW" } -#define COMMON_BASE_HAS_EU \ - { EIR, 0, 0, "EIR" } - #define COMMON_BASE_RENDER \ { GEN7_SC_INSTDONE, 0, 0, "GEN7_SC_INSTDONE" } @@ -105,7 +103,6 @@ static const struct __guc_mmio_reg_descr xe_lp_global_regs[] = { /* XE_LP Render / Compute Per-Class */ static const struct __guc_mmio_reg_descr xe_lp_rc_class_regs[] = { - COMMON_BASE_HAS_EU, COMMON_BASE_RENDER, COMMON_GEN12BASE_RENDER, }; @@ -148,7 +145,6 @@ static const struct __guc_mmio_reg_descr gen8_global_regs[] = { }; static const struct __guc_mmio_reg_descr gen8_rc_class_regs[] = { - COMMON_BASE_HAS_EU, COMMON_BASE_RENDER, }; @@ -1441,7 +1437,7 @@ int intel_guc_capture_print_engine_node(struct drm_i915_error_state_buf *ebuf, if (!cap || !ee->engine) return -ENODEV; - guc = &ee->engine->gt->uc.guc; + guc = gt_to_guc(ee->engine->gt); i915_error_printf(ebuf, "global --- GuC Error Capture on %s command stream:\n", ee->engine->name); @@ -1543,7 +1539,7 @@ bool intel_guc_capture_is_matching_engine(struct intel_gt *gt, if (!gt || !ce || !engine) return false; - guc = >->uc.guc; + guc = gt_to_guc(gt); if (!guc->capture) return false; @@ -1573,7 +1569,7 @@ void intel_guc_capture_get_matching_node(struct intel_gt *gt, if (!gt || !ee || !ce) return; - guc = >->uc.guc; + guc = gt_to_guc(gt); if (!guc->capture) return; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c index a35e32695e1b..23f54c84cbab 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fw.c @@ -115,6 +115,7 @@ static inline bool guc_load_done(struct intel_uncore *uncore, u32 *status, bool case INTEL_GUC_LOAD_STATUS_INIT_DATA_INVALID: case INTEL_GUC_LOAD_STATUS_MPU_DATA_INVALID: case INTEL_GUC_LOAD_STATUS_INIT_MMIO_SAVE_RESTORE_INVALID: + case INTEL_GUC_LOAD_STATUS_KLV_WORKAROUND_INIT_ERROR: *success = false; return true; } @@ -241,6 +242,11 @@ static int guc_wait_ucode(struct intel_guc *guc) ret = -EPERM; break; + case INTEL_GUC_LOAD_STATUS_KLV_WORKAROUND_INIT_ERROR: + guc_info(guc, "invalid w/a KLV entry\n"); + ret = -EINVAL; + break; + case INTEL_GUC_LOAD_STATUS_HWCONFIG_START: guc_info(guc, "still extracting hwconfig table.\n"); ret = -ETIMEDOUT; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h index 8ae1846431da..14797e80bc92 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h @@ -96,8 +96,9 @@ #define GUC_WA_GAM_CREDITS BIT(10) #define GUC_WA_DUAL_QUEUE BIT(11) #define GUC_WA_RCS_RESET_BEFORE_RC6 BIT(13) -#define GUC_WA_CONTEXT_ISOLATION BIT(15) #define GUC_WA_PRE_PARSER BIT(14) +#define GUC_WA_CONTEXT_ISOLATION BIT(15) +#define GUC_WA_RCS_CCS_SWITCHOUT BIT(16) #define GUC_WA_HOLD_CCS_SWITCHOUT BIT(17) #define GUC_WA_POLLCS BIT(18) #define GUC_WA_RCS_REGS_IN_CCS_REGS_LIST BIT(21) @@ -430,7 +431,10 @@ struct guc_ads { u32 capture_instance[GUC_CAPTURE_LIST_INDEX_MAX][GUC_MAX_ENGINE_CLASSES]; u32 capture_class[GUC_CAPTURE_LIST_INDEX_MAX][GUC_MAX_ENGINE_CLASSES]; u32 capture_global[GUC_CAPTURE_LIST_INDEX_MAX]; - u32 reserved[14]; + u32 wa_klv_addr_lo; + u32 wa_klv_addr_hi; + u32 wa_klv_size; + u32 reserved[11]; } __packed; /* Engine usage stats */ diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_hwconfig.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_hwconfig.c index cc9569af7f0c..b67a15f74276 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_hwconfig.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_hwconfig.c @@ -111,7 +111,7 @@ static bool has_table(struct drm_i915_private *i915) static int guc_hwconfig_init(struct intel_gt *gt) { struct intel_hwconfig *hwconfig = >->info.hwconfig; - struct intel_guc *guc = >->uc.guc; + struct intel_guc *guc = gt_to_guc(gt); int ret; if (!has_table(gt->i915)) 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 3e681ab6fbf9..706fffca698b 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c @@ -537,6 +537,20 @@ int intel_guc_slpc_get_min_freq(struct intel_guc_slpc *slpc, u32 *val) return ret; } +int intel_guc_slpc_set_strategy(struct intel_guc_slpc *slpc, u32 val) +{ + 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_set_param(slpc, + SLPC_PARAM_STRATEGIES, + val); + + return ret; +} + int intel_guc_slpc_set_media_ratio_mode(struct intel_guc_slpc *slpc, u32 val) { struct drm_i915_private *i915 = slpc_to_i915(slpc); @@ -711,6 +725,9 @@ int intel_guc_slpc_enable(struct intel_guc_slpc *slpc) /* Set cached media freq ratio mode */ intel_guc_slpc_set_media_ratio_mode(slpc, slpc->media_ratio_mode); + /* Enable SLPC Optimized Strategy for compute */ + intel_guc_slpc_set_strategy(slpc, SLPC_OPTIMIZED_STRATEGY_COMPUTE); + return 0; } 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 6ac6503c39d4..1cb5fd44f05c 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.h @@ -45,5 +45,6 @@ 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_set_ignore_eff_freq(struct intel_guc_slpc *slpc, bool val); +int intel_guc_slpc_set_strategy(struct intel_guc_slpc *slpc, u32 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 58f2dea46395..0eaa1064242c 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -398,7 +398,7 @@ static inline void set_context_guc_id_invalid(struct intel_context *ce) static inline struct intel_guc *ce_to_guc(struct intel_context *ce) { - return &ce->engine->gt->uc.guc; + return gt_to_guc(ce->engine->gt); } static inline struct i915_priolist *to_priolist(struct rb_node *rb) @@ -1246,7 +1246,7 @@ static void __get_engine_usage_record(struct intel_engine_cs *engine, static void guc_update_engine_gt_clks(struct intel_engine_cs *engine) { struct intel_engine_guc_stats *stats = &engine->stats.guc; - struct intel_guc *guc = &engine->gt->uc.guc; + struct intel_guc *guc = gt_to_guc(engine->gt); u32 last_switch, ctx_id, total; lockdep_assert_held(&guc->timestamp.lock); @@ -1311,7 +1311,7 @@ static ktime_t guc_engine_busyness(struct intel_engine_cs *engine, ktime_t *now) struct intel_engine_guc_stats stats_saved, *stats = &engine->stats.guc; struct i915_gpu_error *gpu_error = &engine->i915->gpu_error; struct intel_gt *gt = engine->gt; - struct intel_guc *guc = >->uc.guc; + struct intel_guc *guc = gt_to_guc(gt); u64 total, gt_stamp_saved; unsigned long flags; u32 reset_count; @@ -1577,7 +1577,7 @@ static void guc_fini_engine_stats(struct intel_guc *guc) void intel_guc_busyness_park(struct intel_gt *gt) { - struct intel_guc *guc = >->uc.guc; + struct intel_guc *guc = gt_to_guc(gt); if (!guc_submission_initialized(guc)) return; @@ -1604,7 +1604,7 @@ void intel_guc_busyness_park(struct intel_gt *gt) void intel_guc_busyness_unpark(struct intel_gt *gt) { - struct intel_guc *guc = >->uc.guc; + struct intel_guc *guc = gt_to_guc(gt); unsigned long flags; ktime_t unused; @@ -2189,7 +2189,7 @@ static bool need_tasklet(struct intel_guc *guc, struct i915_request *rq) static void guc_submit_request(struct i915_request *rq) { struct i915_sched_engine *sched_engine = rq->engine->sched_engine; - struct intel_guc *guc = &rq->engine->gt->uc.guc; + struct intel_guc *guc = gt_to_guc(rq->engine->gt); unsigned long flags; /* Will be called from irq-context when using foreign fences. */ @@ -2215,11 +2215,10 @@ static int new_guc_id(struct intel_guc *guc, struct intel_context *ce) order_base_2(ce->parallel.number_children + 1)); else - ret = ida_simple_get(&guc->submission_state.guc_ids, - NUMBER_MULTI_LRC_GUC_ID(guc), - guc->submission_state.num_guc_ids, - GFP_KERNEL | __GFP_RETRY_MAYFAIL | - __GFP_NOWARN); + ret = ida_alloc_range(&guc->submission_state.guc_ids, + NUMBER_MULTI_LRC_GUC_ID(guc), + guc->submission_state.num_guc_ids - 1, + GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN); if (unlikely(ret < 0)) return ret; @@ -2242,8 +2241,8 @@ static void __release_guc_id(struct intel_guc *guc, struct intel_context *ce) + 1)); } else { --guc->submission_state.guc_ids_in_use; - ida_simple_remove(&guc->submission_state.guc_ids, - ce->guc_id.id); + ida_free(&guc->submission_state.guc_ids, + ce->guc_id.id); } clr_ctx_id_mapping(guc, ce->guc_id.id); set_context_guc_id_invalid(ce); @@ -2640,6 +2639,7 @@ MAKE_CONTEXT_POLICY_ADD(execution_quantum, EXECUTION_QUANTUM) MAKE_CONTEXT_POLICY_ADD(preemption_timeout, PREEMPTION_TIMEOUT) MAKE_CONTEXT_POLICY_ADD(priority, SCHEDULING_PRIORITY) MAKE_CONTEXT_POLICY_ADD(preempt_to_idle, PREEMPT_TO_IDLE_ON_QUANTUM_EXPIRY) +MAKE_CONTEXT_POLICY_ADD(slpc_ctx_freq_req, SLPM_GT_FREQUENCY) #undef MAKE_CONTEXT_POLICY_ADD @@ -2655,10 +2655,11 @@ static int __guc_context_set_context_policies(struct intel_guc *guc, static int guc_context_policy_init_v70(struct intel_context *ce, bool loop) { struct intel_engine_cs *engine = ce->engine; - struct intel_guc *guc = &engine->gt->uc.guc; + struct intel_guc *guc = gt_to_guc(engine->gt); struct context_policy policy; u32 execution_quantum; u32 preemption_timeout; + u32 slpc_ctx_freq_req = 0; unsigned long flags; int ret; @@ -2670,11 +2671,15 @@ static int guc_context_policy_init_v70(struct intel_context *ce, bool loop) execution_quantum = engine->props.timeslice_duration_ms * 1000; preemption_timeout = engine->props.preempt_timeout_ms * 1000; + if (ce->flags & BIT(CONTEXT_LOW_LATENCY)) + slpc_ctx_freq_req |= SLPC_CTX_FREQ_REQ_IS_COMPUTE; + __guc_context_policy_start_klv(&policy, ce->guc_id.id); __guc_context_policy_add_priority(&policy, ce->guc_state.prio); __guc_context_policy_add_execution_quantum(&policy, execution_quantum); __guc_context_policy_add_preemption_timeout(&policy, preemption_timeout); + __guc_context_policy_add_slpc_ctx_freq_req(&policy, slpc_ctx_freq_req); if (engine->flags & I915_ENGINE_WANT_FORCED_PREEMPTION) __guc_context_policy_add_preempt_to_idle(&policy, 1); @@ -2731,7 +2736,7 @@ static u32 map_guc_prio_to_lrc_desc_prio(u8 prio) static void prepare_context_registration_info_v69(struct intel_context *ce) { struct intel_engine_cs *engine = ce->engine; - struct intel_guc *guc = &engine->gt->uc.guc; + struct intel_guc *guc = gt_to_guc(engine->gt); u32 ctx_id = ce->guc_id.id; struct guc_lrc_desc_v69 *desc; struct intel_context *child; @@ -2800,7 +2805,7 @@ static void prepare_context_registration_info_v70(struct intel_context *ce, struct guc_ctxt_registration_info *info) { struct intel_engine_cs *engine = ce->engine; - struct intel_guc *guc = &engine->gt->uc.guc; + struct intel_guc *guc = gt_to_guc(engine->gt); u32 ctx_id = ce->guc_id.id; GEM_BUG_ON(!engine->mask); @@ -2863,7 +2868,7 @@ static int try_context_registration(struct intel_context *ce, bool loop) { struct intel_engine_cs *engine = ce->engine; struct intel_runtime_pm *runtime_pm = engine->uncore->rpm; - struct intel_guc *guc = &engine->gt->uc.guc; + struct intel_guc *guc = gt_to_guc(engine->gt); intel_wakeref_t wakeref; u32 ctx_id = ce->guc_id.id; bool context_registered; @@ -4491,7 +4496,13 @@ static void guc_default_vfuncs(struct intel_engine_cs *engine) if (engine->class == COMPUTE_CLASS) 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; + engine->flags |= I915_ENGINE_USES_WA_HOLD_SWITCHOUT; + + /* Wa_16019325821 */ + /* Wa_14019159160 */ + if ((engine->class == COMPUTE_CLASS || engine->class == RENDER_CLASS) && + IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 70), IP_VER(12, 71))) + engine->flags |= I915_ENGINE_USES_WA_HOLD_SWITCHOUT; /* * TODO: GuC supports timeslicing and semaphores as well, but they're @@ -4544,7 +4555,7 @@ static void guc_sched_engine_destroy(struct kref *kref) int intel_guc_submission_setup(struct intel_engine_cs *engine) { struct drm_i915_private *i915 = engine->i915; - struct intel_guc *guc = &engine->gt->uc.guc; + struct intel_guc *guc = gt_to_guc(engine->gt); /* * The setup relies on several assumptions (e.g. irqs always enabled) @@ -5303,7 +5314,7 @@ int intel_guc_engine_failure_process_msg(struct intel_guc *guc, void intel_guc_find_hung_context(struct intel_engine_cs *engine) { - struct intel_guc *guc = &engine->gt->uc.guc; + struct intel_guc *guc = gt_to_guc(engine->gt); struct intel_context *ce; struct i915_request *rq; unsigned long index; @@ -5365,7 +5376,7 @@ void intel_guc_dump_active_requests(struct intel_engine_cs *engine, struct i915_request *hung_rq, struct drm_printer *m) { - struct intel_guc *guc = &engine->gt->uc.guc; + struct intel_guc *guc = gt_to_guc(engine->gt); struct intel_context *ce; unsigned long index; unsigned long flags; @@ -5817,7 +5828,7 @@ guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count, if (!ve) return ERR_PTR(-ENOMEM); - guc = &siblings[0]->gt->uc.guc; + guc = gt_to_guc(siblings[0]->gt); ve->base.i915 = siblings[0]->i915; ve->base.gt = siblings[0]->gt; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c index 0945b177d5f9..2d9152eb7282 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c @@ -385,7 +385,7 @@ int intel_huc_init(struct intel_huc *huc) if (HAS_ENGINE(gt, GSC0)) { struct i915_vma *vma; - vma = intel_guc_allocate_vma(>->uc.guc, PXP43_HUC_AUTH_INOUT_SIZE * 2); + vma = intel_guc_allocate_vma(gt_to_guc(gt), PXP43_HUC_AUTH_INOUT_SIZE * 2); if (IS_ERR(vma)) { err = PTR_ERR(vma); huc_info(huc, "Failed to allocate heci pkt\n"); @@ -540,7 +540,7 @@ int intel_huc_wait_for_auth_complete(struct intel_huc *huc, int intel_huc_auth(struct intel_huc *huc, enum intel_huc_authentication_type type) { struct intel_gt *gt = huc_to_gt(huc); - struct intel_guc *guc = >->uc.guc; + struct intel_guc *guc = gt_to_guc(gt); int ret; if (!intel_uc_fw_is_loaded(&huc->fw)) 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 756093eaf2ad..d80278eb45d7 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c @@ -807,7 +807,7 @@ static int try_firmware_load(struct intel_uc_fw *uc_fw, const struct firmware ** static int check_mtl_huc_guc_compatibility(struct intel_gt *gt, struct intel_uc_fw_file *huc_selected) { - struct intel_uc_fw_file *guc_selected = >->uc.guc.fw.file_selected; + struct intel_uc_fw_file *guc_selected = >_to_guc(gt)->fw.file_selected; struct intel_uc_fw_ver *huc_ver = &huc_selected->ver; struct intel_uc_fw_ver *guc_ver = &guc_selected->ver; bool new_huc, new_guc; @@ -1209,7 +1209,7 @@ static int uc_fw_rsa_data_create(struct intel_uc_fw *uc_fw) * since its GGTT offset will be GuC accessible. */ GEM_BUG_ON(uc_fw->rsa_size > PAGE_SIZE); - vma = intel_guc_allocate_vma(>->uc.guc, PAGE_SIZE); + vma = intel_guc_allocate_vma(gt_to_guc(gt), PAGE_SIZE); if (IS_ERR(vma)) return PTR_ERR(vma); diff --git a/drivers/gpu/drm/i915/gt/uc/selftest_guc.c b/drivers/gpu/drm/i915/gt/uc/selftest_guc.c index c900aac85adb..68feb55654f7 100644 --- a/drivers/gpu/drm/i915/gt/uc/selftest_guc.c +++ b/drivers/gpu/drm/i915/gt/uc/selftest_guc.c @@ -144,7 +144,7 @@ err: static int intel_guc_steal_guc_ids(void *arg) { struct intel_gt *gt = arg; - struct intel_guc *guc = >->uc.guc; + struct intel_guc *guc = gt_to_guc(gt); int ret, sv, context_index = 0; intel_wakeref_t wakeref; struct intel_engine_cs *engine; diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c index 4b9233c07a22..622a24305bc2 100644 --- a/drivers/gpu/drm/i915/i915_driver.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -202,7 +202,7 @@ static void sanitize_gpu(struct drm_i915_private *i915) unsigned int i; for_each_gt(gt, i915, i) - __intel_gt_reset(gt, ALL_ENGINES); + intel_gt_reset_all_engines(gt); } } diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c index fc4c3d4e2b40..a62405787e77 100644 --- a/drivers/gpu/drm/i915/i915_getparam.c +++ b/drivers/gpu/drm/i915/i915_getparam.c @@ -155,6 +155,12 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data, */ value = 1; break; + case I915_PARAM_HAS_CONTEXT_FREQ_HINT: + if (intel_uc_uses_guc_submission(&to_gt(i915)->uc)) + value = 1; + else + value = -EINVAL; + break; case I915_PARAM_HAS_CONTEXT_ISOLATION: value = intel_engines_has_context_isolation(i915); break; diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index b70715b1411d..d2f064d2525c 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -1776,8 +1776,6 @@ static void release_references(struct i915_vma *vma, struct intel_gt *gt, if (vm_ddestroy) i915_vm_resv_put(vma->vm); - /* Wait for async active retire */ - i915_active_wait(&vma->active); i915_active_fini(&vma->active); GEM_WARN_ON(vma->resource); i915_vma_free(vma); diff --git a/drivers/gpu/drm/i915/selftests/i915_selftest.c b/drivers/gpu/drm/i915/selftests/i915_selftest.c index ee79e0809a6d..fee76c1d2f45 100644 --- a/drivers/gpu/drm/i915/selftests/i915_selftest.c +++ b/drivers/gpu/drm/i915/selftests/i915_selftest.c @@ -154,6 +154,30 @@ __wait_gsc_proxy_completed(struct drm_i915_private *i915) pr_warn(DRIVER_NAME "Timed out waiting for gsc_proxy_completion!\n"); } +static void +__wait_gsc_huc_load_completed(struct drm_i915_private *i915) +{ + /* this only applies to DG2, so we only care about GT0 */ + struct intel_huc *huc = &to_gt(i915)->uc.huc; + bool need_to_wait = (IS_ENABLED(CONFIG_INTEL_MEI_PXP) && + intel_huc_wait_required(huc)); + /* + * The GSC and PXP mei bringup depends on the kernel boot ordering, so + * to account for the worst case scenario the HuC code waits for up to + * 10s for the GSC driver to load and then another 5s for the PXP + * component to bind before giving up, even though those steps normally + * complete in less than a second from the i915 load. We match that + * timeout here, but we expect to bail early due to the fence being + * signalled even in a failure case, as it is extremely unlikely that + * both components will use their full timeout. + */ + unsigned long timeout_ms = 15000; + + if (need_to_wait && + wait_for(i915_sw_fence_done(&huc->delayed_load.fence), timeout_ms)) + pr_warn(DRIVER_NAME "Timed out waiting for huc load via GSC!\n"); +} + static int __run_selftests(const char *name, struct selftest *st, unsigned int count, @@ -228,14 +252,16 @@ int i915_mock_selftests(void) int i915_live_selftests(struct pci_dev *pdev) { + struct drm_i915_private *i915 = pdev_to_i915(pdev); int err; if (!i915_selftest.live) return 0; - __wait_gsc_proxy_completed(pdev_to_i915(pdev)); + __wait_gsc_proxy_completed(i915); + __wait_gsc_huc_load_completed(i915); - err = run_selftests(live, pdev_to_i915(pdev)); + err = run_selftests(live, i915); if (err) { i915_selftest.live = err; return err; @@ -251,14 +277,16 @@ int i915_live_selftests(struct pci_dev *pdev) int i915_perf_selftests(struct pci_dev *pdev) { + struct drm_i915_private *i915 = pdev_to_i915(pdev); int err; if (!i915_selftest.perf) return 0; - __wait_gsc_proxy_completed(pdev_to_i915(pdev)); + __wait_gsc_proxy_completed(i915); + __wait_gsc_huc_load_completed(i915); - err = run_selftests(perf, pdev_to_i915(pdev)); + err = run_selftests(perf, i915); if (err) { i915_selftest.perf = err; return err; |