diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c index d3887c27c3ba..2d3e1ce9cc76 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.c +++ b/drivers/gpu/drm/i915/i915_gem_context.c @@ -89,6 +89,7 @@ #include #include "i915_drv.h" #include "i915_trace.h" +#include "intel_lrc_reg.h" #include "intel_workarounds.h" #define ALL_L3_SLICES(dev) (1 << NUM_L3_SLICES(dev)) - 1 @@ -321,6 +322,15 @@ static u32 default_desc_template(const struct drm_i915_private *i915, return desc; } +static void intel_context_retire(struct i915_gem_active *active, + struct i915_request *rq) +{ + struct intel_context *ce = + container_of(active, typeof(*ce), active_tracker); + + intel_context_unpin(ce); +} + void intel_context_init(struct intel_context *ce, struct i915_gem_context *ctx, @@ -333,6 +343,8 @@ intel_context_init(struct intel_context *ce, /* Use the whole device by default */ ce->sseu = intel_device_default_sseu(ctx->i915); + + init_request_active(&ce->active_tracker, intel_context_retire); } static struct i915_gem_context * @@ -850,6 +862,56 @@ int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data, return 0; } +static int get_sseu(struct i915_gem_context *ctx, + struct drm_i915_gem_context_param *args) +{ + struct drm_i915_gem_context_param_sseu user_sseu; + struct intel_engine_cs *engine; + struct intel_context *ce; + int ret; + + if (args->size == 0) + goto out; + else if (args->size < sizeof(user_sseu)) + return -EINVAL; + + if (copy_from_user(&user_sseu, u64_to_user_ptr(args->value), + sizeof(user_sseu))) + return -EFAULT; + + if (user_sseu.flags || user_sseu.rsvd) + return -EINVAL; + + engine = intel_engine_lookup_user(ctx->i915, + user_sseu.engine_class, + user_sseu.engine_instance); + if (!engine) + return -EINVAL; + + /* Only use for mutex here is to serialize get_param and set_param. */ + ret = mutex_lock_interruptible(&ctx->i915->drm.struct_mutex); + if (ret) + return ret; + + ce = to_intel_context(ctx, engine); + + user_sseu.slice_mask = ce->sseu.slice_mask; + user_sseu.subslice_mask = ce->sseu.subslice_mask; + user_sseu.min_eus_per_subslice = ce->sseu.min_eus_per_subslice; + user_sseu.max_eus_per_subslice = ce->sseu.max_eus_per_subslice; + + mutex_unlock(&ctx->i915->drm.struct_mutex); + + if (copy_to_user(u64_to_user_ptr(args->value), &user_sseu, + sizeof(user_sseu))) + return -EFAULT; + +out: + args->size = sizeof(user_sseu); + + return 0; +} + int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data, struct drm_file *file) { @@ -862,15 +924,17 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data, if (!ctx) return -ENOENT; - args->size = 0; switch (args->param) { case I915_CONTEXT_PARAM_BAN_PERIOD: ret = -EINVAL; break; case I915_CONTEXT_PARAM_NO_ZEROMAP: + args->size = 0; args->value = test_bit(UCONTEXT_NO_ZEROMAP, &ctx->user_flags); break; case I915_CONTEXT_PARAM_GTT_SIZE: + args->size = 0; + if (ctx->ppgtt) args->value = ctx->ppgtt->vm.total; else if (to_i915(dev)->mm.aliasing_ppgtt) @@ -879,14 +943,20 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data, args->value = to_i915(dev)->ggtt.vm.total; break; case I915_CONTEXT_PARAM_NO_ERROR_CAPTURE: + args->size = 0; args->value = i915_gem_context_no_error_capture(ctx); break; case I915_CONTEXT_PARAM_BANNABLE: + args->size = 0; args->value = i915_gem_context_is_bannable(ctx); break; case I915_CONTEXT_PARAM_PRIORITY: + args->size = 0; args->value = ctx->sched.priority >> I915_USER_PRIORITY_SHIFT; break; + case I915_CONTEXT_PARAM_SSEU: + ret = get_sseu(ctx, args); + break; default: ret = -EINVAL; break; @@ -896,6 +966,270 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data, return ret; } +static int gen8_emit_rpcs_config(struct i915_request *rq, + struct intel_context *ce, + struct intel_sseu sseu) +{ + u64 offset; + u32 *cs; + + cs = intel_ring_begin(rq, 4); + if (IS_ERR(cs)) + return PTR_ERR(cs); + + offset = i915_ggtt_offset(ce->state) + + LRC_STATE_PN * PAGE_SIZE + + (CTX_R_PWR_CLK_STATE + 1) * 4; + + *cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT; + *cs++ = lower_32_bits(offset); + *cs++ = upper_32_bits(offset); + *cs++ = gen8_make_rpcs(rq->i915, &sseu); + + intel_ring_advance(rq, cs); + + return 0; +} + +static int +gen8_modify_rpcs_gpu(struct intel_context *ce, + struct intel_engine_cs *engine, + struct intel_sseu sseu) +{ + struct drm_i915_private *i915 = engine->i915; + struct i915_request *rq, *prev; + intel_wakeref_t wakeref; + int ret; + + GEM_BUG_ON(!ce->pin_count); + + lockdep_assert_held(&i915->drm.struct_mutex); + + /* Submitting requests etc needs the hw awake. */ + wakeref = intel_runtime_pm_get(i915); + + rq = i915_request_alloc(engine, i915->kernel_context); + if (IS_ERR(rq)) { + ret = PTR_ERR(rq); + goto out_put; + } + + /* Queue this switch after all other activity by this context. */ + prev = i915_gem_active_raw(&ce->ring->timeline->last_request, + &i915->drm.struct_mutex); + if (prev && !i915_request_completed(prev)) { + ret = i915_request_await_dma_fence(rq, &prev->fence); + if (ret < 0) + goto out_add; + } + + /* Order all following requests to be after. */ + ret = i915_timeline_set_barrier(ce->ring->timeline, rq); + if (ret) + goto out_add; + + ret = gen8_emit_rpcs_config(rq, ce, sseu); + if (ret) + goto out_add; + + /* + * Guarantee context image and the timeline remains pinned until the + * modifying request is retired by setting the ce activity tracker. + * + * But we only need to take one pin on the account of it. Or in other + * words transfer the pinned ce object to tracked active request. + */ + if (!i915_gem_active_isset(&ce->active_tracker)) + __intel_context_pin(ce); + i915_gem_active_set(&ce->active_tracker, rq); + +out_add: + i915_request_add(rq); +out_put: + intel_runtime_pm_put(i915, wakeref); + + return ret; +} + +static int +i915_gem_context_reconfigure_sseu(struct i915_gem_context *ctx, + struct intel_engine_cs *engine, + struct intel_sseu sseu) +{ + struct intel_context *ce = to_intel_context(ctx, engine); + int ret; + + GEM_BUG_ON(INTEL_GEN(ctx->i915) < 8); + GEM_BUG_ON(engine->id != RCS); + + ret = mutex_lock_interruptible(&ctx->i915->drm.struct_mutex); + if (ret) + return ret; + + /* Nothing to do if unmodified. */ + if (!memcmp(&ce->sseu, &sseu, sizeof(sseu))) + goto out; + + /* + * If context is not idle we have to submit an ordered request to modify + * its context image via the kernel context. Pristine and idle contexts + * will be configured on pinning. + */ + if (ce->pin_count) + ret = gen8_modify_rpcs_gpu(ce, engine, sseu); + + if (!ret) + ce->sseu = sseu; + +out: + mutex_unlock(&ctx->i915->drm.struct_mutex); + + return ret; +} + +static int +user_to_context_sseu(struct drm_i915_private *i915, + const struct drm_i915_gem_context_param_sseu *user, + struct intel_sseu *context) +{ + const struct sseu_dev_info *device = &RUNTIME_INFO(i915)->sseu; + + /* No zeros in any field. */ + if (!user->slice_mask || !user->subslice_mask || + !user->min_eus_per_subslice || !user->max_eus_per_subslice) + return -EINVAL; + + /* Max > min. */ + if (user->max_eus_per_subslice < user->min_eus_per_subslice) + return -EINVAL; + + /* + * Some future proofing on the types since the uAPI is wider than the + * current internal implementation. + */ + if (overflows_type(user->slice_mask, context->slice_mask) || + overflows_type(user->subslice_mask, context->subslice_mask) || + overflows_type(user->min_eus_per_subslice, + context->min_eus_per_subslice) || + overflows_type(user->max_eus_per_subslice, + context->max_eus_per_subslice)) + return -EINVAL; + + /* Check validity against hardware. */ + if (user->slice_mask & ~device->slice_mask) + return -EINVAL; + + if (user->subslice_mask & ~device->subslice_mask[0]) + return -EINVAL; + + if (user->max_eus_per_subslice > device->max_eus_per_subslice) + return -EINVAL; + + context->slice_mask = user->slice_mask; + context->subslice_mask = user->subslice_mask; + context->min_eus_per_subslice = user->min_eus_per_subslice; + context->max_eus_per_subslice = user->max_eus_per_subslice; + + /* Part specific restrictions. */ + if (IS_GEN(i915, 11)) { + unsigned int hw_s = hweight8(device->slice_mask); + unsigned int hw_ss_per_s = hweight8(device->subslice_mask[0]); + unsigned int req_s = hweight8(context->slice_mask); + unsigned int req_ss = hweight8(context->subslice_mask); + + /* + * Only full subslice enablement is possible if more than one + * slice is turned on. + */ + if (req_s > 1 && req_ss != hw_ss_per_s) + return -EINVAL; + + /* + * If more than four (SScount bitfield limit) subslices are + * requested then the number has to be even. + */ + if (req_ss > 4 && (req_ss & 1)) + return -EINVAL; + + /* + * If only one slice is enabled and subslice count is below the + * device full enablement, it must be at most half of the all + * available subslices. + */ + if (req_s == 1 && req_ss < hw_ss_per_s && + req_ss > (hw_ss_per_s / 2)) + return -EINVAL; + + /* ABI restriction - VME use case only. */ + + /* All slices or one slice only. */ + if (req_s != 1 && req_s != hw_s) + return -EINVAL; + + /* + * Half subslices or full enablement only when one slice is + * enabled. + */ + if (req_s == 1 && + (req_ss != hw_ss_per_s && req_ss != (hw_ss_per_s / 2))) + return -EINVAL; + + /* No EU configuration changes. */ + if ((user->min_eus_per_subslice != + device->max_eus_per_subslice) || + (user->max_eus_per_subslice != + device->max_eus_per_subslice)) + return -EINVAL; + } + + return 0; +} + +static int set_sseu(struct i915_gem_context *ctx, + struct drm_i915_gem_context_param *args) +{ + struct drm_i915_private *i915 = ctx->i915; + struct drm_i915_gem_context_param_sseu user_sseu; + struct intel_engine_cs *engine; + struct intel_sseu sseu; + int ret; + + if (args->size < sizeof(user_sseu)) + return -EINVAL; + + if (!IS_GEN(i915, 11)) + return -ENODEV; + + if (copy_from_user(&user_sseu, u64_to_user_ptr(args->value), + sizeof(user_sseu))) + return -EFAULT; + + if (user_sseu.flags || user_sseu.rsvd) + return -EINVAL; + + engine = intel_engine_lookup_user(i915, + user_sseu.engine_class, + user_sseu.engine_instance); + if (!engine) + return -EINVAL; + + /* Only render engine supports RPCS configuration. */ + if (engine->class != RENDER_CLASS) + return -ENODEV; + + ret = user_to_context_sseu(i915, &user_sseu, &sseu); + if (ret) + return ret; + + ret = i915_gem_context_reconfigure_sseu(ctx, engine, sseu); + if (ret) + return ret; + + args->size = sizeof(user_sseu); + + return 0; +} + int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data, struct drm_file *file) { @@ -958,7 +1292,9 @@ int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data, I915_USER_PRIORITY(priority); } break; - + case I915_CONTEXT_PARAM_SSEU: + ret = set_sseu(ctx, args); + break; default: ret = -EINVAL; break; diff --git a/drivers/gpu/drm/i915/i915_gem_context.h b/drivers/gpu/drm/i915/i915_gem_context.h index 919f6f0a0f7a..92ad5272e57f 100644 --- a/drivers/gpu/drm/i915/i915_gem_context.h +++ b/drivers/gpu/drm/i915/i915_gem_context.h @@ -183,6 +183,12 @@ struct i915_gem_context { u64 lrc_desc; int pin_count; + /** + * active_tracker: Active tracker for the external rq activity + * on this intel_context object. + */ + struct i915_gem_active active_tracker; + const struct intel_context_ops *ops; /** sseu: Control eu/slice partitioning */ diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index d99c462e2c09..5e98fd79bd9d 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -2498,7 +2498,9 @@ u32 gen8_make_rpcs(struct drm_i915_private *i915, struct intel_sseu *req_sseu) * subslices are enabled, or a count between one and four on the first * slice. */ - if (IS_GEN(i915, 11) && slices == 1 && subslices >= 4) { + if (IS_GEN(i915, 11) && + slices == 1 && + subslices > min_t(u8, 4, hweight8(sseu->subslice_mask[0]) / 2)) { GEM_BUG_ON(subslices & 1); subslice_pg = false; diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h index 298b2e197744..397810fa2d33 100644 --- a/include/uapi/drm/i915_drm.h +++ b/include/uapi/drm/i915_drm.h @@ -1486,9 +1486,73 @@ struct drm_i915_gem_context_param { #define I915_CONTEXT_MAX_USER_PRIORITY 1023 /* inclusive */ #define I915_CONTEXT_DEFAULT_PRIORITY 0 #define I915_CONTEXT_MIN_USER_PRIORITY -1023 /* inclusive */ + /* + * When using the following param, value should be a pointer to + * drm_i915_gem_context_param_sseu. + */ +#define I915_CONTEXT_PARAM_SSEU 0x7 __u64 value; }; +/** + * Context SSEU programming + * + * It may be necessary for either functional or performance reason to configure + * a context to run with a reduced number of SSEU (where SSEU stands for Slice/ + * Sub-slice/EU). + * + * This is done by configuring SSEU configuration using the below + * @struct drm_i915_gem_context_param_sseu for every supported engine which + * userspace intends to use. + * + * Not all GPUs or engines support this functionality in which case an error + * code -ENODEV will be returned. + * + * Also, flexibility of possible SSEU configuration permutations varies between + * GPU generations and software imposed limitations. Requesting such a + * combination will return an error code of -EINVAL. + * + * NOTE: When perf/OA is active the context's SSEU configuration is ignored in + * favour of a single global setting. + */ +struct drm_i915_gem_context_param_sseu { + /* + * Engine class & instance to be configured or queried. + */ + __u16 engine_class; + __u16 engine_instance; + + /* + * Unused for now. Must be cleared to zero. + */ + __u32 flags; + + /* + * Mask of slices to enable for the context. Valid values are a subset + * of the bitmask value returned for I915_PARAM_SLICE_MASK. + */ + __u64 slice_mask; + + /* + * Mask of subslices to enable for the context. Valid values are a + * subset of the bitmask value return by I915_PARAM_SUBSLICE_MASK. + */ + __u64 subslice_mask; + + /* + * Minimum/Maximum number of EUs to enable per subslice for the + * context. min_eus_per_subslice must be inferior or equal to + * max_eus_per_subslice. + */ + __u16 min_eus_per_subslice; + __u16 max_eus_per_subslice; + + /* + * Unused for now. Must be cleared to zero. + */ + __u32 rsvd; +}; + enum drm_i915_oa_format { I915_OA_FORMAT_A13 = 1, /* HSW only */ I915_OA_FORMAT_A29, /* HSW only */