| Message ID | 20210722235426.31831-2-matthew.brost@intel.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | Remaining patches for basic GuC submission | expand |
On 7/22/2021 4:53 PM, Matthew Brost wrote: > Implement GuC virtual engines. Rather simple implementation, basically > just allocate an engine, setup context enter / exit function to virtual > engine specific functions, set all other variables / functions to guc > versions, and set the engine mask to that of all the siblings. > > v2: Update to work with proto-ctx > v3: > (Daniele) > - Drop include, add comment to intel_virtual_engine_has_heartbeat > > Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> > Signed-off-by: Matthew Brost <matthew.brost@intel.com> > --- > drivers/gpu/drm/i915/gem/i915_gem_context.c | 8 +- > drivers/gpu/drm/i915/gt/intel_context_types.h | 6 + > drivers/gpu/drm/i915/gt/intel_engine.h | 30 ++- > drivers/gpu/drm/i915/gt/intel_engine_cs.c | 14 + > .../drm/i915/gt/intel_execlists_submission.c | 29 ++- > .../drm/i915/gt/intel_execlists_submission.h | 4 - > drivers/gpu/drm/i915/gt/selftest_execlists.c | 12 +- > .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 244 +++++++++++++++++- > .../gpu/drm/i915/gt/uc/intel_guc_submission.h | 2 + > 9 files changed, 313 insertions(+), 36 deletions(-) > > diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c > index 89ca401bf9ae..bc52eeed782a 100644 > --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c > +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c > @@ -74,7 +74,6 @@ > #include "gt/intel_context_param.h" > #include "gt/intel_engine_heartbeat.h" > #include "gt/intel_engine_user.h" > -#include "gt/intel_execlists_submission.h" /* virtual_engine */ > #include "gt/intel_gpu_commands.h" > #include "gt/intel_ring.h" > > @@ -363,9 +362,6 @@ set_proto_ctx_engines_balance(struct i915_user_extension __user *base, > if (!HAS_EXECLISTS(i915)) > return -ENODEV; > > - if (intel_uc_uses_guc_submission(&i915->gt.uc)) > - return -ENODEV; /* not implement yet */ > - > if (get_user(idx, &ext->engine_index)) > return -EFAULT; > > @@ -950,8 +946,8 @@ static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx, > break; > > case I915_GEM_ENGINE_TYPE_BALANCED: > - ce = intel_execlists_create_virtual(pe[n].siblings, > - pe[n].num_siblings); > + ce = intel_engine_create_virtual(pe[n].siblings, > + pe[n].num_siblings); > break; > > case I915_GEM_ENGINE_TYPE_INVALID: > diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h > index 4a5518d295c2..542c98418771 100644 > --- a/drivers/gpu/drm/i915/gt/intel_context_types.h > +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h > @@ -47,6 +47,12 @@ struct intel_context_ops { > > void (*reset)(struct intel_context *ce); > void (*destroy)(struct kref *kref); > + > + /* virtual engine/context interface */ > + struct intel_context *(*create_virtual)(struct intel_engine_cs **engine, > + unsigned int count); > + struct intel_engine_cs *(*get_sibling)(struct intel_engine_cs *engine, > + unsigned int sibling); > }; > > struct intel_context { > diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h > index f911c1224ab2..13bfb7ec33b2 100644 > --- a/drivers/gpu/drm/i915/gt/intel_engine.h > +++ b/drivers/gpu/drm/i915/gt/intel_engine.h > @@ -273,13 +273,41 @@ intel_engine_has_preempt_reset(const struct intel_engine_cs *engine) > return intel_engine_has_preemption(engine); > } > > +struct intel_context * > +intel_engine_create_virtual(struct intel_engine_cs **siblings, > + unsigned int count); looks like I missed this earlier, but this forward decl seems unneeded. > + > +static inline bool > +intel_virtual_engine_has_heartbeat(const struct intel_engine_cs *engine) > +{ > + /* > + * For non-GuC submission we expect the back-end to look at the > + * heartbeat status of the actual physical engine that the work > + * has been (or is being) scheduled on, so we should only reach > + * here with GuC submission enabled. > + */ > + GEM_BUG_ON(!intel_engine_uses_guc(engine)); > + > + return intel_guc_virtual_engine_has_heartbeat(engine); > +} > + > static inline bool > intel_engine_has_heartbeat(const struct intel_engine_cs *engine) > { > if (!IS_ACTIVE(CONFIG_DRM_I915_HEARTBEAT_INTERVAL)) > return false; > > - return READ_ONCE(engine->props.heartbeat_interval_ms); > + if (intel_engine_is_virtual(engine)) > + return intel_virtual_engine_has_heartbeat(engine); > + else > + return READ_ONCE(engine->props.heartbeat_interval_ms); > +} > + > +static inline struct intel_engine_cs * > +intel_engine_get_sibling(struct intel_engine_cs *engine, unsigned int sibling) > +{ > + GEM_BUG_ON(!intel_engine_is_virtual(engine)); > + return engine->cops->get_sibling(engine, sibling); > } > > #endif /* _INTEL_RINGBUFFER_H_ */ > diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c > index c1c96ced2a4b..7dee9a1209bc 100644 > --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c > +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c > @@ -1755,6 +1755,20 @@ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine, ktime_t *now) > return total; > } > > +struct intel_context * > +intel_engine_create_virtual(struct intel_engine_cs **siblings, > + unsigned int count) > +{ > + if (count == 0) > + return ERR_PTR(-EINVAL); > + > + if (count == 1) > + return intel_context_create(siblings[0]); > + > + GEM_BUG_ON(!siblings[0]->cops->create_virtual); > + return siblings[0]->cops->create_virtual(siblings, count); > +} > + > static bool match_ring(struct i915_request *rq) > { > u32 ring = ENGINE_READ(rq->engine, RING_START); > diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c > index 87cedaeb4bf8..b2580cd2ce51 100644 > --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c > +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c > @@ -199,6 +199,9 @@ static struct virtual_engine *to_virtual_engine(struct intel_engine_cs *engine) > return container_of(engine, struct virtual_engine, base); > } > > +static struct intel_context * > +execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count); > + > static struct i915_request * > __active_request(const struct intel_timeline * const tl, > struct i915_request *rq, > @@ -2599,6 +2602,8 @@ static const struct intel_context_ops execlists_context_ops = { > > .reset = lrc_reset, > .destroy = lrc_destroy, > + > + .create_virtual = execlists_create_virtual, > }; > > static int emit_pdps(struct i915_request *rq) > @@ -3545,6 +3550,17 @@ static void virtual_context_exit(struct intel_context *ce) > intel_engine_pm_put(ve->siblings[n]); > } > > +static struct intel_engine_cs * > +virtual_get_sibling(struct intel_engine_cs *engine, unsigned int sibling) > +{ > + struct virtual_engine *ve = to_virtual_engine(engine); > + > + if (sibling >= ve->num_siblings) > + return NULL; > + > + return ve->siblings[sibling]; > +} > + > static const struct intel_context_ops virtual_context_ops = { > .flags = COPS_HAS_INFLIGHT, > > @@ -3559,6 +3575,8 @@ static const struct intel_context_ops virtual_context_ops = { > .exit = virtual_context_exit, > > .destroy = virtual_context_destroy, > + > + .get_sibling = virtual_get_sibling, > }; > > static intel_engine_mask_t virtual_submission_mask(struct virtual_engine *ve) > @@ -3707,20 +3725,13 @@ static void virtual_submit_request(struct i915_request *rq) > spin_unlock_irqrestore(&ve->base.sched_engine->lock, flags); > } > > -struct intel_context * > -intel_execlists_create_virtual(struct intel_engine_cs **siblings, > - unsigned int count) > +static struct intel_context * > +execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count) > { > struct virtual_engine *ve; > unsigned int n; > int err; > > - if (count == 0) > - return ERR_PTR(-EINVAL); > - > - if (count == 1) > - return intel_context_create(siblings[0]); > - > ve = kzalloc(struct_size(ve, siblings, count), GFP_KERNEL); > if (!ve) > return ERR_PTR(-ENOMEM); > diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h > index ad4f3e1a0fde..a1aa92c983a5 100644 > --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h > +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h > @@ -32,10 +32,6 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine, > int indent), > unsigned int max); > > -struct intel_context * > -intel_execlists_create_virtual(struct intel_engine_cs **siblings, > - unsigned int count); > - > bool > intel_engine_in_execlists_submission_mode(const struct intel_engine_cs *engine); > > diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c > index 22a124b134b6..f12ffe797639 100644 > --- a/drivers/gpu/drm/i915/gt/selftest_execlists.c > +++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c > @@ -3733,7 +3733,7 @@ static int nop_virtual_engine(struct intel_gt *gt, > GEM_BUG_ON(!nctx || nctx > ARRAY_SIZE(ve)); > > for (n = 0; n < nctx; n++) { > - ve[n] = intel_execlists_create_virtual(siblings, nsibling); > + ve[n] = intel_engine_create_virtual(siblings, nsibling); > if (IS_ERR(ve[n])) { > err = PTR_ERR(ve[n]); > nctx = n; > @@ -3929,7 +3929,7 @@ static int mask_virtual_engine(struct intel_gt *gt, > * restrict it to our desired engine within the virtual engine. > */ > > - ve = intel_execlists_create_virtual(siblings, nsibling); > + ve = intel_engine_create_virtual(siblings, nsibling); > if (IS_ERR(ve)) { > err = PTR_ERR(ve); > goto out_close; > @@ -4060,7 +4060,7 @@ static int slicein_virtual_engine(struct intel_gt *gt, > i915_request_add(rq); > } > > - ce = intel_execlists_create_virtual(siblings, nsibling); > + ce = intel_engine_create_virtual(siblings, nsibling); > if (IS_ERR(ce)) { > err = PTR_ERR(ce); > goto out; > @@ -4112,7 +4112,7 @@ static int sliceout_virtual_engine(struct intel_gt *gt, > > /* XXX We do not handle oversubscription and fairness with normal rq */ > for (n = 0; n < nsibling; n++) { > - ce = intel_execlists_create_virtual(siblings, nsibling); > + ce = intel_engine_create_virtual(siblings, nsibling); > if (IS_ERR(ce)) { > err = PTR_ERR(ce); > goto out; > @@ -4214,7 +4214,7 @@ static int preserved_virtual_engine(struct intel_gt *gt, > if (err) > goto out_scratch; > > - ve = intel_execlists_create_virtual(siblings, nsibling); > + ve = intel_engine_create_virtual(siblings, nsibling); > if (IS_ERR(ve)) { > err = PTR_ERR(ve); > goto out_scratch; > @@ -4354,7 +4354,7 @@ static int reset_virtual_engine(struct intel_gt *gt, > if (igt_spinner_init(&spin, gt)) > return -ENOMEM; > > - ve = intel_execlists_create_virtual(siblings, nsibling); > + ve = intel_engine_create_virtual(siblings, nsibling); > if (IS_ERR(ve)) { > err = PTR_ERR(ve); > goto out_spin; > 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 26aadad10b12..28404454a97a 100644 > --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c > +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c > @@ -60,6 +60,15 @@ > * > */ > > +/* GuC Virtual Engine */ > +struct guc_virtual_engine { > + struct intel_engine_cs base; > + struct intel_context context; > +}; > + > +static struct intel_context * > +guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count); > + > #define GUC_REQUEST_SIZE 64 /* bytes */ > > /* > @@ -931,14 +940,17 @@ static int guc_lrc_desc_pin(struct intel_context *ce) > return ret; > } > > -static int guc_context_pre_pin(struct intel_context *ce, > - struct i915_gem_ww_ctx *ww, > - void **vaddr) > +static int __guc_context_pre_pin(struct intel_context *ce, > + struct intel_engine_cs *engine, > + struct i915_gem_ww_ctx *ww, > + void **vaddr) > { > - return lrc_pre_pin(ce, ce->engine, ww, vaddr); > + return lrc_pre_pin(ce, engine, ww, vaddr); > } > > -static int guc_context_pin(struct intel_context *ce, void *vaddr) > +static int __guc_context_pin(struct intel_context *ce, > + struct intel_engine_cs *engine, > + void *vaddr) > { > if (i915_ggtt_offset(ce->state) != > (ce->lrc.lrca & CTX_GTT_ADDRESS_MASK)) > @@ -949,7 +961,19 @@ static int guc_context_pin(struct intel_context *ce, void *vaddr) > * explaination of why. > */ > > - return lrc_pin(ce, ce->engine, vaddr); > + return lrc_pin(ce, engine, vaddr); > +} > + > +static int guc_context_pre_pin(struct intel_context *ce, > + struct i915_gem_ww_ctx *ww, > + void **vaddr) > +{ > + return __guc_context_pre_pin(ce, ce->engine, ww, vaddr); > +} > + > +static int guc_context_pin(struct intel_context *ce, void *vaddr) > +{ > + return __guc_context_pin(ce, ce->engine, vaddr); > } > > static void guc_context_unpin(struct intel_context *ce) > @@ -1054,6 +1078,21 @@ static inline void guc_lrc_desc_unpin(struct intel_context *ce) > deregister_context(ce, ce->guc_id); > } > > +static void __guc_context_destroy(struct intel_context *ce) > +{ > + lrc_fini(ce); > + intel_context_fini(ce); > + > + if (intel_engine_is_virtual(ce->engine)) { > + struct guc_virtual_engine *ve = > + container_of(ce, typeof(*ve), context); > + > + kfree(ve); > + } else { > + intel_context_free(ce); > + } > +} > + > static void guc_context_destroy(struct kref *kref) > { > struct intel_context *ce = container_of(kref, typeof(*ce), ref); > @@ -1068,11 +1107,11 @@ static void guc_context_destroy(struct kref *kref) > * registered with the GuC. > */ > if (context_guc_id_invalid(ce)) { > - lrc_destroy(kref); > + __guc_context_destroy(ce); > return; > } else if (!lrc_desc_registered(guc, ce->guc_id)) { > release_guc_id(guc, ce); > - lrc_destroy(kref); > + __guc_context_destroy(ce); > return; > } > > @@ -1087,7 +1126,7 @@ static void guc_context_destroy(struct kref *kref) > spin_lock_irqsave(&guc->contexts_lock, flags); > if (context_guc_id_invalid(ce)) { > spin_unlock_irqrestore(&guc->contexts_lock, flags); > - lrc_destroy(kref); > + __guc_context_destroy(ce); > return; > } > > @@ -1132,6 +1171,8 @@ static const struct intel_context_ops guc_context_ops = { > > .reset = lrc_reset, > .destroy = guc_context_destroy, > + > + .create_virtual = guc_create_virtual, > }; > > static void __guc_signal_context_fence(struct intel_context *ce) > @@ -1260,6 +1301,83 @@ static int guc_request_alloc(struct i915_request *rq) > return 0; > } > > +static struct intel_engine_cs * > +guc_virtual_get_sibling(struct intel_engine_cs *ve, unsigned int sibling) > +{ > + struct intel_engine_cs *engine; > + intel_engine_mask_t tmp, mask = ve->mask; > + unsigned int num_siblings = 0; > + > + for_each_engine_masked(engine, ve->gt, mask, tmp) > + if (num_siblings++ == sibling) > + return engine; > + > + return NULL; > +} > + > +static int guc_virtual_context_pre_pin(struct intel_context *ce, > + struct i915_gem_ww_ctx *ww, > + void **vaddr) > +{ > + struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0); > + > + return __guc_context_pre_pin(ce, engine, ww, vaddr); > +} > + > +static int guc_virtual_context_pin(struct intel_context *ce, void *vaddr) > +{ > + struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0); > + > + return __guc_context_pin(ce, engine, vaddr); > +} > + > +static void guc_virtual_context_enter(struct intel_context *ce) > +{ > + intel_engine_mask_t tmp, mask = ce->engine->mask; > + struct intel_engine_cs *engine; > + > + for_each_engine_masked(engine, ce->engine->gt, mask, tmp) > + intel_engine_pm_get(engine); > + > + intel_timeline_enter(ce->timeline); > +} > + > +static void guc_virtual_context_exit(struct intel_context *ce) > +{ > + intel_engine_mask_t tmp, mask = ce->engine->mask; > + struct intel_engine_cs *engine; > + > + for_each_engine_masked(engine, ce->engine->gt, mask, tmp) > + intel_engine_pm_put(engine); > + > + intel_timeline_exit(ce->timeline); > +} > + > +static int guc_virtual_context_alloc(struct intel_context *ce) > +{ > + struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0); > + > + return lrc_alloc(ce, engine); > +} > + > +static const struct intel_context_ops virtual_guc_context_ops = { > + .alloc = guc_virtual_context_alloc, > + > + .pre_pin = guc_virtual_context_pre_pin, > + .pin = guc_virtual_context_pin, > + .unpin = guc_context_unpin, > + .post_unpin = guc_context_post_unpin, > + > + .enter = guc_virtual_context_enter, > + .exit = guc_virtual_context_exit, > + > + .sched_disable = guc_context_sched_disable, > + > + .destroy = guc_context_destroy, > + > + .get_sibling = guc_virtual_get_sibling, > +}; > + > static void sanitize_hwsp(struct intel_engine_cs *engine) > { > struct intel_timeline *tl; > @@ -1566,7 +1684,7 @@ int intel_guc_deregister_done_process_msg(struct intel_guc *guc, > } else if (context_destroyed(ce)) { > /* Context has been destroyed */ > release_guc_id(guc, ce); > - lrc_destroy(&ce->ref); > + __guc_context_destroy(ce); > } > > decr_outstanding_submission_g2h(guc); > @@ -1681,3 +1799,109 @@ void intel_guc_submission_print_context_info(struct intel_guc *guc, > atomic_read(&ce->guc_sched_state_no_lock)); > } > } > + > +static struct intel_context * > +guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count) > +{ > + struct guc_virtual_engine *ve; > + struct intel_guc *guc; > + unsigned int n; > + int err; > + > + ve = kzalloc(sizeof(*ve), GFP_KERNEL); > + if (!ve) > + return ERR_PTR(-ENOMEM); > + > + guc = &siblings[0]->gt->uc.guc; > + > + ve->base.i915 = siblings[0]->i915; > + ve->base.gt = siblings[0]->gt; > + ve->base.uncore = siblings[0]->uncore; > + ve->base.id = -1; > + > + ve->base.uabi_class = I915_ENGINE_CLASS_INVALID; > + ve->base.instance = I915_ENGINE_CLASS_INVALID_VIRTUAL; > + ve->base.uabi_instance = I915_ENGINE_CLASS_INVALID_VIRTUAL; > + ve->base.saturated = ALL_ENGINES; > + ve->base.breadcrumbs = intel_breadcrumbs_create(&ve->base); > + if (!ve->base.breadcrumbs) { > + kfree(ve); > + return ERR_PTR(-ENOMEM); > + } > + > + snprintf(ve->base.name, sizeof(ve->base.name), "virtual"); > + > + ve->base.sched_engine = i915_sched_engine_get(guc->sched_engine); > + > + ve->base.cops = &virtual_guc_context_ops; > + ve->base.request_alloc = guc_request_alloc; > + > + ve->base.submit_request = guc_submit_request; > + > + ve->base.flags = I915_ENGINE_IS_VIRTUAL; > + > + intel_context_init(&ve->context, &ve->base); > + > + for (n = 0; n < count; n++) { > + struct intel_engine_cs *sibling = siblings[n]; > + > + GEM_BUG_ON(!is_power_of_2(sibling->mask)); > + if (sibling->mask & ve->base.mask) { > + DRM_DEBUG("duplicate %s entry in load balancer\n", > + sibling->name); > + err = -EINVAL; > + goto err_put; > + } > + > + ve->base.mask |= sibling->mask; > + > + if (n != 0 && ve->base.class != sibling->class) { > + DRM_DEBUG("invalid mixing of engine class, sibling %d, already %d\n", > + sibling->class, ve->base.class); > + err = -EINVAL; > + goto err_put; > + } else if (n == 0) { > + ve->base.class = sibling->class; > + ve->base.uabi_class = sibling->uabi_class; > + snprintf(ve->base.name, sizeof(ve->base.name), > + "v%dx%d", ve->base.class, count); > + ve->base.context_size = sibling->context_size; > + > + ve->base.emit_bb_start = sibling->emit_bb_start; > + ve->base.emit_flush = sibling->emit_flush; > + ve->base.emit_init_breadcrumb = > + sibling->emit_init_breadcrumb; > + ve->base.emit_fini_breadcrumb = > + sibling->emit_fini_breadcrumb; > + ve->base.emit_fini_breadcrumb_dw = > + sibling->emit_fini_breadcrumb_dw; > + > + ve->base.flags |= sibling->flags; > + > + ve->base.props.timeslice_duration_ms = > + sibling->props.timeslice_duration_ms; > + ve->base.props.preempt_timeout_ms = > + sibling->props.preempt_timeout_ms; > + } > + } > + > + return &ve->context; > + > +err_put: > + intel_context_put(&ve->context); > + return ERR_PTR(err); > +} > + > + > + Too many new lines. with the 2 nits addressed: Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Daniele > +bool intel_guc_virtual_engine_has_heartbeat(const struct intel_engine_cs *ve) > +{ > + struct intel_engine_cs *engine; > + intel_engine_mask_t tmp, mask = ve->mask; > + > + for_each_engine_masked(engine, ve->gt, mask, tmp) > + if (READ_ONCE(engine->props.heartbeat_interval_ms)) > + return true; > + > + return false; > +} > diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h > index 2b9470c90558..5f263ac4f46a 100644 > --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h > +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h > @@ -26,6 +26,8 @@ void intel_guc_submission_print_info(struct intel_guc *guc, > void intel_guc_submission_print_context_info(struct intel_guc *guc, > struct drm_printer *p); > > +bool intel_guc_virtual_engine_has_heartbeat(const struct intel_engine_cs *ve); > + > static inline bool intel_guc_submission_is_supported(struct intel_guc *guc) > { > /* XXX: GuC submission is unavailable for now */
On Fri, Jul 23, 2021 at 05:47:45PM -0700, Daniele Ceraolo Spurio wrote: > > > On 7/22/2021 4:53 PM, Matthew Brost wrote: > > Implement GuC virtual engines. Rather simple implementation, basically > > just allocate an engine, setup context enter / exit function to virtual > > engine specific functions, set all other variables / functions to guc > > versions, and set the engine mask to that of all the siblings. > > > > v2: Update to work with proto-ctx > > v3: > > (Daniele) > > - Drop include, add comment to intel_virtual_engine_has_heartbeat > > > > Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> > > Signed-off-by: Matthew Brost <matthew.brost@intel.com> > > --- > > drivers/gpu/drm/i915/gem/i915_gem_context.c | 8 +- > > drivers/gpu/drm/i915/gt/intel_context_types.h | 6 + > > drivers/gpu/drm/i915/gt/intel_engine.h | 30 ++- > > drivers/gpu/drm/i915/gt/intel_engine_cs.c | 14 + > > .../drm/i915/gt/intel_execlists_submission.c | 29 ++- > > .../drm/i915/gt/intel_execlists_submission.h | 4 - > > drivers/gpu/drm/i915/gt/selftest_execlists.c | 12 +- > > .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 244 +++++++++++++++++- > > .../gpu/drm/i915/gt/uc/intel_guc_submission.h | 2 + > > 9 files changed, 313 insertions(+), 36 deletions(-) > > > > diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c > > index 89ca401bf9ae..bc52eeed782a 100644 > > --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c > > +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c > > @@ -74,7 +74,6 @@ > > #include "gt/intel_context_param.h" > > #include "gt/intel_engine_heartbeat.h" > > #include "gt/intel_engine_user.h" > > -#include "gt/intel_execlists_submission.h" /* virtual_engine */ > > #include "gt/intel_gpu_commands.h" > > #include "gt/intel_ring.h" > > @@ -363,9 +362,6 @@ set_proto_ctx_engines_balance(struct i915_user_extension __user *base, > > if (!HAS_EXECLISTS(i915)) > > return -ENODEV; > > - if (intel_uc_uses_guc_submission(&i915->gt.uc)) > > - return -ENODEV; /* not implement yet */ > > - > > if (get_user(idx, &ext->engine_index)) > > return -EFAULT; > > @@ -950,8 +946,8 @@ static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx, > > break; > > case I915_GEM_ENGINE_TYPE_BALANCED: > > - ce = intel_execlists_create_virtual(pe[n].siblings, > > - pe[n].num_siblings); > > + ce = intel_engine_create_virtual(pe[n].siblings, > > + pe[n].num_siblings); > > break; > > case I915_GEM_ENGINE_TYPE_INVALID: > > diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h > > index 4a5518d295c2..542c98418771 100644 > > --- a/drivers/gpu/drm/i915/gt/intel_context_types.h > > +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h > > @@ -47,6 +47,12 @@ struct intel_context_ops { > > void (*reset)(struct intel_context *ce); > > void (*destroy)(struct kref *kref); > > + > > + /* virtual engine/context interface */ > > + struct intel_context *(*create_virtual)(struct intel_engine_cs **engine, > > + unsigned int count); > > + struct intel_engine_cs *(*get_sibling)(struct intel_engine_cs *engine, > > + unsigned int sibling); > > }; > > struct intel_context { > > diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h > > index f911c1224ab2..13bfb7ec33b2 100644 > > --- a/drivers/gpu/drm/i915/gt/intel_engine.h > > +++ b/drivers/gpu/drm/i915/gt/intel_engine.h > > @@ -273,13 +273,41 @@ intel_engine_has_preempt_reset(const struct intel_engine_cs *engine) > > return intel_engine_has_preemption(engine); > > } > > +struct intel_context * > > +intel_engine_create_virtual(struct intel_engine_cs **siblings, > > + unsigned int count); > > looks like I missed this earlier, but this forward decl seems unneeded. > Not a forward decl, this is a header file which defines a function implmented in gt/intel_engine_cs.c and used in gem/i915_gem_contexts.c. It is absolutely needed. > > + > > +static inline bool > > +intel_virtual_engine_has_heartbeat(const struct intel_engine_cs *engine) > > +{ > > + /* > > + * For non-GuC submission we expect the back-end to look at the > > + * heartbeat status of the actual physical engine that the work > > + * has been (or is being) scheduled on, so we should only reach > > + * here with GuC submission enabled. > > + */ > > + GEM_BUG_ON(!intel_engine_uses_guc(engine)); > > + > > + return intel_guc_virtual_engine_has_heartbeat(engine); > > +} > > + > > static inline bool > > intel_engine_has_heartbeat(const struct intel_engine_cs *engine) > > { > > if (!IS_ACTIVE(CONFIG_DRM_I915_HEARTBEAT_INTERVAL)) > > return false; > > - return READ_ONCE(engine->props.heartbeat_interval_ms); > > + if (intel_engine_is_virtual(engine)) > > + return intel_virtual_engine_has_heartbeat(engine); > > + else > > + return READ_ONCE(engine->props.heartbeat_interval_ms); > > +} > > + > > +static inline struct intel_engine_cs * > > +intel_engine_get_sibling(struct intel_engine_cs *engine, unsigned int sibling) > > +{ > > + GEM_BUG_ON(!intel_engine_is_virtual(engine)); > > + return engine->cops->get_sibling(engine, sibling); > > } > > #endif /* _INTEL_RINGBUFFER_H_ */ > > diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c > > index c1c96ced2a4b..7dee9a1209bc 100644 > > --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c > > +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c > > @@ -1755,6 +1755,20 @@ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine, ktime_t *now) > > return total; > > } > > +struct intel_context * > > +intel_engine_create_virtual(struct intel_engine_cs **siblings, > > + unsigned int count) > > +{ > > + if (count == 0) > > + return ERR_PTR(-EINVAL); > > + > > + if (count == 1) > > + return intel_context_create(siblings[0]); > > + > > + GEM_BUG_ON(!siblings[0]->cops->create_virtual); > > + return siblings[0]->cops->create_virtual(siblings, count); > > +} > > + > > static bool match_ring(struct i915_request *rq) > > { > > u32 ring = ENGINE_READ(rq->engine, RING_START); > > diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c > > index 87cedaeb4bf8..b2580cd2ce51 100644 > > --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c > > +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c > > @@ -199,6 +199,9 @@ static struct virtual_engine *to_virtual_engine(struct intel_engine_cs *engine) > > return container_of(engine, struct virtual_engine, base); > > } > > +static struct intel_context * > > +execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count); > > + > > static struct i915_request * > > __active_request(const struct intel_timeline * const tl, > > struct i915_request *rq, > > @@ -2599,6 +2602,8 @@ static const struct intel_context_ops execlists_context_ops = { > > .reset = lrc_reset, > > .destroy = lrc_destroy, > > + > > + .create_virtual = execlists_create_virtual, > > }; > > static int emit_pdps(struct i915_request *rq) > > @@ -3545,6 +3550,17 @@ static void virtual_context_exit(struct intel_context *ce) > > intel_engine_pm_put(ve->siblings[n]); > > } > > +static struct intel_engine_cs * > > +virtual_get_sibling(struct intel_engine_cs *engine, unsigned int sibling) > > +{ > > + struct virtual_engine *ve = to_virtual_engine(engine); > > + > > + if (sibling >= ve->num_siblings) > > + return NULL; > > + > > + return ve->siblings[sibling]; > > +} > > + > > static const struct intel_context_ops virtual_context_ops = { > > .flags = COPS_HAS_INFLIGHT, > > @@ -3559,6 +3575,8 @@ static const struct intel_context_ops virtual_context_ops = { > > .exit = virtual_context_exit, > > .destroy = virtual_context_destroy, > > + > > + .get_sibling = virtual_get_sibling, > > }; > > static intel_engine_mask_t virtual_submission_mask(struct virtual_engine *ve) > > @@ -3707,20 +3725,13 @@ static void virtual_submit_request(struct i915_request *rq) > > spin_unlock_irqrestore(&ve->base.sched_engine->lock, flags); > > } > > -struct intel_context * > > -intel_execlists_create_virtual(struct intel_engine_cs **siblings, > > - unsigned int count) > > +static struct intel_context * > > +execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count) > > { > > struct virtual_engine *ve; > > unsigned int n; > > int err; > > - if (count == 0) > > - return ERR_PTR(-EINVAL); > > - > > - if (count == 1) > > - return intel_context_create(siblings[0]); > > - > > ve = kzalloc(struct_size(ve, siblings, count), GFP_KERNEL); > > if (!ve) > > return ERR_PTR(-ENOMEM); > > diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h > > index ad4f3e1a0fde..a1aa92c983a5 100644 > > --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h > > +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h > > @@ -32,10 +32,6 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine, > > int indent), > > unsigned int max); > > -struct intel_context * > > -intel_execlists_create_virtual(struct intel_engine_cs **siblings, > > - unsigned int count); > > - > > bool > > intel_engine_in_execlists_submission_mode(const struct intel_engine_cs *engine); > > diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c > > index 22a124b134b6..f12ffe797639 100644 > > --- a/drivers/gpu/drm/i915/gt/selftest_execlists.c > > +++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c > > @@ -3733,7 +3733,7 @@ static int nop_virtual_engine(struct intel_gt *gt, > > GEM_BUG_ON(!nctx || nctx > ARRAY_SIZE(ve)); > > for (n = 0; n < nctx; n++) { > > - ve[n] = intel_execlists_create_virtual(siblings, nsibling); > > + ve[n] = intel_engine_create_virtual(siblings, nsibling); > > if (IS_ERR(ve[n])) { > > err = PTR_ERR(ve[n]); > > nctx = n; > > @@ -3929,7 +3929,7 @@ static int mask_virtual_engine(struct intel_gt *gt, > > * restrict it to our desired engine within the virtual engine. > > */ > > - ve = intel_execlists_create_virtual(siblings, nsibling); > > + ve = intel_engine_create_virtual(siblings, nsibling); > > if (IS_ERR(ve)) { > > err = PTR_ERR(ve); > > goto out_close; > > @@ -4060,7 +4060,7 @@ static int slicein_virtual_engine(struct intel_gt *gt, > > i915_request_add(rq); > > } > > - ce = intel_execlists_create_virtual(siblings, nsibling); > > + ce = intel_engine_create_virtual(siblings, nsibling); > > if (IS_ERR(ce)) { > > err = PTR_ERR(ce); > > goto out; > > @@ -4112,7 +4112,7 @@ static int sliceout_virtual_engine(struct intel_gt *gt, > > /* XXX We do not handle oversubscription and fairness with normal rq */ > > for (n = 0; n < nsibling; n++) { > > - ce = intel_execlists_create_virtual(siblings, nsibling); > > + ce = intel_engine_create_virtual(siblings, nsibling); > > if (IS_ERR(ce)) { > > err = PTR_ERR(ce); > > goto out; > > @@ -4214,7 +4214,7 @@ static int preserved_virtual_engine(struct intel_gt *gt, > > if (err) > > goto out_scratch; > > - ve = intel_execlists_create_virtual(siblings, nsibling); > > + ve = intel_engine_create_virtual(siblings, nsibling); > > if (IS_ERR(ve)) { > > err = PTR_ERR(ve); > > goto out_scratch; > > @@ -4354,7 +4354,7 @@ static int reset_virtual_engine(struct intel_gt *gt, > > if (igt_spinner_init(&spin, gt)) > > return -ENOMEM; > > - ve = intel_execlists_create_virtual(siblings, nsibling); > > + ve = intel_engine_create_virtual(siblings, nsibling); > > if (IS_ERR(ve)) { > > err = PTR_ERR(ve); > > goto out_spin; > > 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 26aadad10b12..28404454a97a 100644 > > --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c > > +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c > > @@ -60,6 +60,15 @@ > > * > > */ > > +/* GuC Virtual Engine */ > > +struct guc_virtual_engine { > > + struct intel_engine_cs base; > > + struct intel_context context; > > +}; > > + > > +static struct intel_context * > > +guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count); > > + > > #define GUC_REQUEST_SIZE 64 /* bytes */ > > /* > > @@ -931,14 +940,17 @@ static int guc_lrc_desc_pin(struct intel_context *ce) > > return ret; > > } > > -static int guc_context_pre_pin(struct intel_context *ce, > > - struct i915_gem_ww_ctx *ww, > > - void **vaddr) > > +static int __guc_context_pre_pin(struct intel_context *ce, > > + struct intel_engine_cs *engine, > > + struct i915_gem_ww_ctx *ww, > > + void **vaddr) > > { > > - return lrc_pre_pin(ce, ce->engine, ww, vaddr); > > + return lrc_pre_pin(ce, engine, ww, vaddr); > > } > > -static int guc_context_pin(struct intel_context *ce, void *vaddr) > > +static int __guc_context_pin(struct intel_context *ce, > > + struct intel_engine_cs *engine, > > + void *vaddr) > > { > > if (i915_ggtt_offset(ce->state) != > > (ce->lrc.lrca & CTX_GTT_ADDRESS_MASK)) > > @@ -949,7 +961,19 @@ static int guc_context_pin(struct intel_context *ce, void *vaddr) > > * explaination of why. > > */ > > - return lrc_pin(ce, ce->engine, vaddr); > > + return lrc_pin(ce, engine, vaddr); > > +} > > + > > +static int guc_context_pre_pin(struct intel_context *ce, > > + struct i915_gem_ww_ctx *ww, > > + void **vaddr) > > +{ > > + return __guc_context_pre_pin(ce, ce->engine, ww, vaddr); > > +} > > + > > +static int guc_context_pin(struct intel_context *ce, void *vaddr) > > +{ > > + return __guc_context_pin(ce, ce->engine, vaddr); > > } > > static void guc_context_unpin(struct intel_context *ce) > > @@ -1054,6 +1078,21 @@ static inline void guc_lrc_desc_unpin(struct intel_context *ce) > > deregister_context(ce, ce->guc_id); > > } > > +static void __guc_context_destroy(struct intel_context *ce) > > +{ > > + lrc_fini(ce); > > + intel_context_fini(ce); > > + > > + if (intel_engine_is_virtual(ce->engine)) { > > + struct guc_virtual_engine *ve = > > + container_of(ce, typeof(*ve), context); > > + > > + kfree(ve); > > + } else { > > + intel_context_free(ce); > > + } > > +} > > + > > static void guc_context_destroy(struct kref *kref) > > { > > struct intel_context *ce = container_of(kref, typeof(*ce), ref); > > @@ -1068,11 +1107,11 @@ static void guc_context_destroy(struct kref *kref) > > * registered with the GuC. > > */ > > if (context_guc_id_invalid(ce)) { > > - lrc_destroy(kref); > > + __guc_context_destroy(ce); > > return; > > } else if (!lrc_desc_registered(guc, ce->guc_id)) { > > release_guc_id(guc, ce); > > - lrc_destroy(kref); > > + __guc_context_destroy(ce); > > return; > > } > > @@ -1087,7 +1126,7 @@ static void guc_context_destroy(struct kref *kref) > > spin_lock_irqsave(&guc->contexts_lock, flags); > > if (context_guc_id_invalid(ce)) { > > spin_unlock_irqrestore(&guc->contexts_lock, flags); > > - lrc_destroy(kref); > > + __guc_context_destroy(ce); > > return; > > } > > @@ -1132,6 +1171,8 @@ static const struct intel_context_ops guc_context_ops = { > > .reset = lrc_reset, > > .destroy = guc_context_destroy, > > + > > + .create_virtual = guc_create_virtual, > > }; > > static void __guc_signal_context_fence(struct intel_context *ce) > > @@ -1260,6 +1301,83 @@ static int guc_request_alloc(struct i915_request *rq) > > return 0; > > } > > +static struct intel_engine_cs * > > +guc_virtual_get_sibling(struct intel_engine_cs *ve, unsigned int sibling) > > +{ > > + struct intel_engine_cs *engine; > > + intel_engine_mask_t tmp, mask = ve->mask; > > + unsigned int num_siblings = 0; > > + > > + for_each_engine_masked(engine, ve->gt, mask, tmp) > > + if (num_siblings++ == sibling) > > + return engine; > > + > > + return NULL; > > +} > > + > > +static int guc_virtual_context_pre_pin(struct intel_context *ce, > > + struct i915_gem_ww_ctx *ww, > > + void **vaddr) > > +{ > > + struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0); > > + > > + return __guc_context_pre_pin(ce, engine, ww, vaddr); > > +} > > + > > +static int guc_virtual_context_pin(struct intel_context *ce, void *vaddr) > > +{ > > + struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0); > > + > > + return __guc_context_pin(ce, engine, vaddr); > > +} > > + > > +static void guc_virtual_context_enter(struct intel_context *ce) > > +{ > > + intel_engine_mask_t tmp, mask = ce->engine->mask; > > + struct intel_engine_cs *engine; > > + > > + for_each_engine_masked(engine, ce->engine->gt, mask, tmp) > > + intel_engine_pm_get(engine); > > + > > + intel_timeline_enter(ce->timeline); > > +} > > + > > +static void guc_virtual_context_exit(struct intel_context *ce) > > +{ > > + intel_engine_mask_t tmp, mask = ce->engine->mask; > > + struct intel_engine_cs *engine; > > + > > + for_each_engine_masked(engine, ce->engine->gt, mask, tmp) > > + intel_engine_pm_put(engine); > > + > > + intel_timeline_exit(ce->timeline); > > +} > > + > > +static int guc_virtual_context_alloc(struct intel_context *ce) > > +{ > > + struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0); > > + > > + return lrc_alloc(ce, engine); > > +} > > + > > +static const struct intel_context_ops virtual_guc_context_ops = { > > + .alloc = guc_virtual_context_alloc, > > + > > + .pre_pin = guc_virtual_context_pre_pin, > > + .pin = guc_virtual_context_pin, > > + .unpin = guc_context_unpin, > > + .post_unpin = guc_context_post_unpin, > > + > > + .enter = guc_virtual_context_enter, > > + .exit = guc_virtual_context_exit, > > + > > + .sched_disable = guc_context_sched_disable, > > + > > + .destroy = guc_context_destroy, > > + > > + .get_sibling = guc_virtual_get_sibling, > > +}; > > + > > static void sanitize_hwsp(struct intel_engine_cs *engine) > > { > > struct intel_timeline *tl; > > @@ -1566,7 +1684,7 @@ int intel_guc_deregister_done_process_msg(struct intel_guc *guc, > > } else if (context_destroyed(ce)) { > > /* Context has been destroyed */ > > release_guc_id(guc, ce); > > - lrc_destroy(&ce->ref); > > + __guc_context_destroy(ce); > > } > > decr_outstanding_submission_g2h(guc); > > @@ -1681,3 +1799,109 @@ void intel_guc_submission_print_context_info(struct intel_guc *guc, > > atomic_read(&ce->guc_sched_state_no_lock)); > > } > > } > > + > > +static struct intel_context * > > +guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count) > > +{ > > + struct guc_virtual_engine *ve; > > + struct intel_guc *guc; > > + unsigned int n; > > + int err; > > + > > + ve = kzalloc(sizeof(*ve), GFP_KERNEL); > > + if (!ve) > > + return ERR_PTR(-ENOMEM); > > + > > + guc = &siblings[0]->gt->uc.guc; > > + > > + ve->base.i915 = siblings[0]->i915; > > + ve->base.gt = siblings[0]->gt; > > + ve->base.uncore = siblings[0]->uncore; > > + ve->base.id = -1; > > + > > + ve->base.uabi_class = I915_ENGINE_CLASS_INVALID; > > + ve->base.instance = I915_ENGINE_CLASS_INVALID_VIRTUAL; > > + ve->base.uabi_instance = I915_ENGINE_CLASS_INVALID_VIRTUAL; > > + ve->base.saturated = ALL_ENGINES; > > + ve->base.breadcrumbs = intel_breadcrumbs_create(&ve->base); > > + if (!ve->base.breadcrumbs) { > > + kfree(ve); > > + return ERR_PTR(-ENOMEM); > > + } > > + > > + snprintf(ve->base.name, sizeof(ve->base.name), "virtual"); > > + > > + ve->base.sched_engine = i915_sched_engine_get(guc->sched_engine); > > + > > + ve->base.cops = &virtual_guc_context_ops; > > + ve->base.request_alloc = guc_request_alloc; > > + > > + ve->base.submit_request = guc_submit_request; > > + > > + ve->base.flags = I915_ENGINE_IS_VIRTUAL; > > + > > + intel_context_init(&ve->context, &ve->base); > > + > > + for (n = 0; n < count; n++) { > > + struct intel_engine_cs *sibling = siblings[n]; > > + > > + GEM_BUG_ON(!is_power_of_2(sibling->mask)); > > + if (sibling->mask & ve->base.mask) { > > + DRM_DEBUG("duplicate %s entry in load balancer\n", > > + sibling->name); > > + err = -EINVAL; > > + goto err_put; > > + } > > + > > + ve->base.mask |= sibling->mask; > > + > > + if (n != 0 && ve->base.class != sibling->class) { > > + DRM_DEBUG("invalid mixing of engine class, sibling %d, already %d\n", > > + sibling->class, ve->base.class); > > + err = -EINVAL; > > + goto err_put; > > + } else if (n == 0) { > > + ve->base.class = sibling->class; > > + ve->base.uabi_class = sibling->uabi_class; > > + snprintf(ve->base.name, sizeof(ve->base.name), > > + "v%dx%d", ve->base.class, count); > > + ve->base.context_size = sibling->context_size; > > + > > + ve->base.emit_bb_start = sibling->emit_bb_start; > > + ve->base.emit_flush = sibling->emit_flush; > > + ve->base.emit_init_breadcrumb = > > + sibling->emit_init_breadcrumb; > > + ve->base.emit_fini_breadcrumb = > > + sibling->emit_fini_breadcrumb; > > + ve->base.emit_fini_breadcrumb_dw = > > + sibling->emit_fini_breadcrumb_dw; > > + > > + ve->base.flags |= sibling->flags; > > + > > + ve->base.props.timeslice_duration_ms = > > + sibling->props.timeslice_duration_ms; > > + ve->base.props.preempt_timeout_ms = > > + sibling->props.preempt_timeout_ms; > > + } > > + } > > + > > + return &ve->context; > > + > > +err_put: > > + intel_context_put(&ve->context); > > + return ERR_PTR(err); > > +} > > + > > + > > + > > Too many new lines. > Yep, running dim checkpatch caught this for me. Already fixed. Matt > with the 2 nits addressed: > > Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> > > Daniele > > > +bool intel_guc_virtual_engine_has_heartbeat(const struct intel_engine_cs *ve) > > +{ > > + struct intel_engine_cs *engine; > > + intel_engine_mask_t tmp, mask = ve->mask; > > + > > + for_each_engine_masked(engine, ve->gt, mask, tmp) > > + if (READ_ONCE(engine->props.heartbeat_interval_ms)) > > + return true; > > + > > + return false; > > +} > > diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h > > index 2b9470c90558..5f263ac4f46a 100644 > > --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h > > +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h > > @@ -26,6 +26,8 @@ void intel_guc_submission_print_info(struct intel_guc *guc, > > void intel_guc_submission_print_context_info(struct intel_guc *guc, > > struct drm_printer *p); > > +bool intel_guc_virtual_engine_has_heartbeat(const struct intel_engine_cs *ve); > > + > > static inline bool intel_guc_submission_is_supported(struct intel_guc *guc) > > { > > /* XXX: GuC submission is unavailable for now */ >
On 7/24/2021 4:13 PM, Matthew Brost wrote: > On Fri, Jul 23, 2021 at 05:47:45PM -0700, Daniele Ceraolo Spurio wrote: >> >> On 7/22/2021 4:53 PM, Matthew Brost wrote: >>> Implement GuC virtual engines. Rather simple implementation, basically >>> just allocate an engine, setup context enter / exit function to virtual >>> engine specific functions, set all other variables / functions to guc >>> versions, and set the engine mask to that of all the siblings. >>> >>> v2: Update to work with proto-ctx >>> v3: >>> (Daniele) >>> - Drop include, add comment to intel_virtual_engine_has_heartbeat >>> >>> Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> >>> Signed-off-by: Matthew Brost <matthew.brost@intel.com> >>> --- >>> drivers/gpu/drm/i915/gem/i915_gem_context.c | 8 +- >>> drivers/gpu/drm/i915/gt/intel_context_types.h | 6 + >>> drivers/gpu/drm/i915/gt/intel_engine.h | 30 ++- >>> drivers/gpu/drm/i915/gt/intel_engine_cs.c | 14 + >>> .../drm/i915/gt/intel_execlists_submission.c | 29 ++- >>> .../drm/i915/gt/intel_execlists_submission.h | 4 - >>> drivers/gpu/drm/i915/gt/selftest_execlists.c | 12 +- >>> .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 244 +++++++++++++++++- >>> .../gpu/drm/i915/gt/uc/intel_guc_submission.h | 2 + >>> 9 files changed, 313 insertions(+), 36 deletions(-) >>> >>> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c >>> index 89ca401bf9ae..bc52eeed782a 100644 >>> --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c >>> +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c >>> @@ -74,7 +74,6 @@ >>> #include "gt/intel_context_param.h" >>> #include "gt/intel_engine_heartbeat.h" >>> #include "gt/intel_engine_user.h" >>> -#include "gt/intel_execlists_submission.h" /* virtual_engine */ >>> #include "gt/intel_gpu_commands.h" >>> #include "gt/intel_ring.h" >>> @@ -363,9 +362,6 @@ set_proto_ctx_engines_balance(struct i915_user_extension __user *base, >>> if (!HAS_EXECLISTS(i915)) >>> return -ENODEV; >>> - if (intel_uc_uses_guc_submission(&i915->gt.uc)) >>> - return -ENODEV; /* not implement yet */ >>> - >>> if (get_user(idx, &ext->engine_index)) >>> return -EFAULT; >>> @@ -950,8 +946,8 @@ static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx, >>> break; >>> case I915_GEM_ENGINE_TYPE_BALANCED: >>> - ce = intel_execlists_create_virtual(pe[n].siblings, >>> - pe[n].num_siblings); >>> + ce = intel_engine_create_virtual(pe[n].siblings, >>> + pe[n].num_siblings); >>> break; >>> case I915_GEM_ENGINE_TYPE_INVALID: >>> diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h >>> index 4a5518d295c2..542c98418771 100644 >>> --- a/drivers/gpu/drm/i915/gt/intel_context_types.h >>> +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h >>> @@ -47,6 +47,12 @@ struct intel_context_ops { >>> void (*reset)(struct intel_context *ce); >>> void (*destroy)(struct kref *kref); >>> + >>> + /* virtual engine/context interface */ >>> + struct intel_context *(*create_virtual)(struct intel_engine_cs **engine, >>> + unsigned int count); >>> + struct intel_engine_cs *(*get_sibling)(struct intel_engine_cs *engine, >>> + unsigned int sibling); >>> }; >>> struct intel_context { >>> diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h >>> index f911c1224ab2..13bfb7ec33b2 100644 >>> --- a/drivers/gpu/drm/i915/gt/intel_engine.h >>> +++ b/drivers/gpu/drm/i915/gt/intel_engine.h >>> @@ -273,13 +273,41 @@ intel_engine_has_preempt_reset(const struct intel_engine_cs *engine) >>> return intel_engine_has_preemption(engine); >>> } >>> +struct intel_context * >>> +intel_engine_create_virtual(struct intel_engine_cs **siblings, >>> + unsigned int count); >> looks like I missed this earlier, but this forward decl seems unneeded. >> > Not a forward decl, this is a header file which defines a function > implmented in gt/intel_engine_cs.c and used in gem/i915_gem_contexts.c. > It is absolutely needed. D'oh! My mistake, my mind read this as a .c file because the functions below are implemented in here. Now I get why it didn't bother me the first time I reviewed this... The r-b obviously stands. Daniele > >>> + >>> +static inline bool >>> +intel_virtual_engine_has_heartbeat(const struct intel_engine_cs *engine) >>> +{ >>> + /* >>> + * For non-GuC submission we expect the back-end to look at the >>> + * heartbeat status of the actual physical engine that the work >>> + * has been (or is being) scheduled on, so we should only reach >>> + * here with GuC submission enabled. >>> + */ >>> + GEM_BUG_ON(!intel_engine_uses_guc(engine)); >>> + >>> + return intel_guc_virtual_engine_has_heartbeat(engine); >>> +} >>> + >>> static inline bool >>> intel_engine_has_heartbeat(const struct intel_engine_cs *engine) >>> { >>> if (!IS_ACTIVE(CONFIG_DRM_I915_HEARTBEAT_INTERVAL)) >>> return false; >>> - return READ_ONCE(engine->props.heartbeat_interval_ms); >>> + if (intel_engine_is_virtual(engine)) >>> + return intel_virtual_engine_has_heartbeat(engine); >>> + else >>> + return READ_ONCE(engine->props.heartbeat_interval_ms); >>> +} >>> + >>> +static inline struct intel_engine_cs * >>> +intel_engine_get_sibling(struct intel_engine_cs *engine, unsigned int sibling) >>> +{ >>> + GEM_BUG_ON(!intel_engine_is_virtual(engine)); >>> + return engine->cops->get_sibling(engine, sibling); >>> } >>> #endif /* _INTEL_RINGBUFFER_H_ */ >>> diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c >>> index c1c96ced2a4b..7dee9a1209bc 100644 >>> --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c >>> +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c >>> @@ -1755,6 +1755,20 @@ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine, ktime_t *now) >>> return total; >>> } >>> +struct intel_context * >>> +intel_engine_create_virtual(struct intel_engine_cs **siblings, >>> + unsigned int count) >>> +{ >>> + if (count == 0) >>> + return ERR_PTR(-EINVAL); >>> + >>> + if (count == 1) >>> + return intel_context_create(siblings[0]); >>> + >>> + GEM_BUG_ON(!siblings[0]->cops->create_virtual); >>> + return siblings[0]->cops->create_virtual(siblings, count); >>> +} >>> + >>> static bool match_ring(struct i915_request *rq) >>> { >>> u32 ring = ENGINE_READ(rq->engine, RING_START); >>> diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c >>> index 87cedaeb4bf8..b2580cd2ce51 100644 >>> --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c >>> +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c >>> @@ -199,6 +199,9 @@ static struct virtual_engine *to_virtual_engine(struct intel_engine_cs *engine) >>> return container_of(engine, struct virtual_engine, base); >>> } >>> +static struct intel_context * >>> +execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count); >>> + >>> static struct i915_request * >>> __active_request(const struct intel_timeline * const tl, >>> struct i915_request *rq, >>> @@ -2599,6 +2602,8 @@ static const struct intel_context_ops execlists_context_ops = { >>> .reset = lrc_reset, >>> .destroy = lrc_destroy, >>> + >>> + .create_virtual = execlists_create_virtual, >>> }; >>> static int emit_pdps(struct i915_request *rq) >>> @@ -3545,6 +3550,17 @@ static void virtual_context_exit(struct intel_context *ce) >>> intel_engine_pm_put(ve->siblings[n]); >>> } >>> +static struct intel_engine_cs * >>> +virtual_get_sibling(struct intel_engine_cs *engine, unsigned int sibling) >>> +{ >>> + struct virtual_engine *ve = to_virtual_engine(engine); >>> + >>> + if (sibling >= ve->num_siblings) >>> + return NULL; >>> + >>> + return ve->siblings[sibling]; >>> +} >>> + >>> static const struct intel_context_ops virtual_context_ops = { >>> .flags = COPS_HAS_INFLIGHT, >>> @@ -3559,6 +3575,8 @@ static const struct intel_context_ops virtual_context_ops = { >>> .exit = virtual_context_exit, >>> .destroy = virtual_context_destroy, >>> + >>> + .get_sibling = virtual_get_sibling, >>> }; >>> static intel_engine_mask_t virtual_submission_mask(struct virtual_engine *ve) >>> @@ -3707,20 +3725,13 @@ static void virtual_submit_request(struct i915_request *rq) >>> spin_unlock_irqrestore(&ve->base.sched_engine->lock, flags); >>> } >>> -struct intel_context * >>> -intel_execlists_create_virtual(struct intel_engine_cs **siblings, >>> - unsigned int count) >>> +static struct intel_context * >>> +execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count) >>> { >>> struct virtual_engine *ve; >>> unsigned int n; >>> int err; >>> - if (count == 0) >>> - return ERR_PTR(-EINVAL); >>> - >>> - if (count == 1) >>> - return intel_context_create(siblings[0]); >>> - >>> ve = kzalloc(struct_size(ve, siblings, count), GFP_KERNEL); >>> if (!ve) >>> return ERR_PTR(-ENOMEM); >>> diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h >>> index ad4f3e1a0fde..a1aa92c983a5 100644 >>> --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h >>> +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h >>> @@ -32,10 +32,6 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine, >>> int indent), >>> unsigned int max); >>> -struct intel_context * >>> -intel_execlists_create_virtual(struct intel_engine_cs **siblings, >>> - unsigned int count); >>> - >>> bool >>> intel_engine_in_execlists_submission_mode(const struct intel_engine_cs *engine); >>> diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c >>> index 22a124b134b6..f12ffe797639 100644 >>> --- a/drivers/gpu/drm/i915/gt/selftest_execlists.c >>> +++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c >>> @@ -3733,7 +3733,7 @@ static int nop_virtual_engine(struct intel_gt *gt, >>> GEM_BUG_ON(!nctx || nctx > ARRAY_SIZE(ve)); >>> for (n = 0; n < nctx; n++) { >>> - ve[n] = intel_execlists_create_virtual(siblings, nsibling); >>> + ve[n] = intel_engine_create_virtual(siblings, nsibling); >>> if (IS_ERR(ve[n])) { >>> err = PTR_ERR(ve[n]); >>> nctx = n; >>> @@ -3929,7 +3929,7 @@ static int mask_virtual_engine(struct intel_gt *gt, >>> * restrict it to our desired engine within the virtual engine. >>> */ >>> - ve = intel_execlists_create_virtual(siblings, nsibling); >>> + ve = intel_engine_create_virtual(siblings, nsibling); >>> if (IS_ERR(ve)) { >>> err = PTR_ERR(ve); >>> goto out_close; >>> @@ -4060,7 +4060,7 @@ static int slicein_virtual_engine(struct intel_gt *gt, >>> i915_request_add(rq); >>> } >>> - ce = intel_execlists_create_virtual(siblings, nsibling); >>> + ce = intel_engine_create_virtual(siblings, nsibling); >>> if (IS_ERR(ce)) { >>> err = PTR_ERR(ce); >>> goto out; >>> @@ -4112,7 +4112,7 @@ static int sliceout_virtual_engine(struct intel_gt *gt, >>> /* XXX We do not handle oversubscription and fairness with normal rq */ >>> for (n = 0; n < nsibling; n++) { >>> - ce = intel_execlists_create_virtual(siblings, nsibling); >>> + ce = intel_engine_create_virtual(siblings, nsibling); >>> if (IS_ERR(ce)) { >>> err = PTR_ERR(ce); >>> goto out; >>> @@ -4214,7 +4214,7 @@ static int preserved_virtual_engine(struct intel_gt *gt, >>> if (err) >>> goto out_scratch; >>> - ve = intel_execlists_create_virtual(siblings, nsibling); >>> + ve = intel_engine_create_virtual(siblings, nsibling); >>> if (IS_ERR(ve)) { >>> err = PTR_ERR(ve); >>> goto out_scratch; >>> @@ -4354,7 +4354,7 @@ static int reset_virtual_engine(struct intel_gt *gt, >>> if (igt_spinner_init(&spin, gt)) >>> return -ENOMEM; >>> - ve = intel_execlists_create_virtual(siblings, nsibling); >>> + ve = intel_engine_create_virtual(siblings, nsibling); >>> if (IS_ERR(ve)) { >>> err = PTR_ERR(ve); >>> goto out_spin; >>> 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 26aadad10b12..28404454a97a 100644 >>> --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c >>> +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c >>> @@ -60,6 +60,15 @@ >>> * >>> */ >>> +/* GuC Virtual Engine */ >>> +struct guc_virtual_engine { >>> + struct intel_engine_cs base; >>> + struct intel_context context; >>> +}; >>> + >>> +static struct intel_context * >>> +guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count); >>> + >>> #define GUC_REQUEST_SIZE 64 /* bytes */ >>> /* >>> @@ -931,14 +940,17 @@ static int guc_lrc_desc_pin(struct intel_context *ce) >>> return ret; >>> } >>> -static int guc_context_pre_pin(struct intel_context *ce, >>> - struct i915_gem_ww_ctx *ww, >>> - void **vaddr) >>> +static int __guc_context_pre_pin(struct intel_context *ce, >>> + struct intel_engine_cs *engine, >>> + struct i915_gem_ww_ctx *ww, >>> + void **vaddr) >>> { >>> - return lrc_pre_pin(ce, ce->engine, ww, vaddr); >>> + return lrc_pre_pin(ce, engine, ww, vaddr); >>> } >>> -static int guc_context_pin(struct intel_context *ce, void *vaddr) >>> +static int __guc_context_pin(struct intel_context *ce, >>> + struct intel_engine_cs *engine, >>> + void *vaddr) >>> { >>> if (i915_ggtt_offset(ce->state) != >>> (ce->lrc.lrca & CTX_GTT_ADDRESS_MASK)) >>> @@ -949,7 +961,19 @@ static int guc_context_pin(struct intel_context *ce, void *vaddr) >>> * explaination of why. >>> */ >>> - return lrc_pin(ce, ce->engine, vaddr); >>> + return lrc_pin(ce, engine, vaddr); >>> +} >>> + >>> +static int guc_context_pre_pin(struct intel_context *ce, >>> + struct i915_gem_ww_ctx *ww, >>> + void **vaddr) >>> +{ >>> + return __guc_context_pre_pin(ce, ce->engine, ww, vaddr); >>> +} >>> + >>> +static int guc_context_pin(struct intel_context *ce, void *vaddr) >>> +{ >>> + return __guc_context_pin(ce, ce->engine, vaddr); >>> } >>> static void guc_context_unpin(struct intel_context *ce) >>> @@ -1054,6 +1078,21 @@ static inline void guc_lrc_desc_unpin(struct intel_context *ce) >>> deregister_context(ce, ce->guc_id); >>> } >>> +static void __guc_context_destroy(struct intel_context *ce) >>> +{ >>> + lrc_fini(ce); >>> + intel_context_fini(ce); >>> + >>> + if (intel_engine_is_virtual(ce->engine)) { >>> + struct guc_virtual_engine *ve = >>> + container_of(ce, typeof(*ve), context); >>> + >>> + kfree(ve); >>> + } else { >>> + intel_context_free(ce); >>> + } >>> +} >>> + >>> static void guc_context_destroy(struct kref *kref) >>> { >>> struct intel_context *ce = container_of(kref, typeof(*ce), ref); >>> @@ -1068,11 +1107,11 @@ static void guc_context_destroy(struct kref *kref) >>> * registered with the GuC. >>> */ >>> if (context_guc_id_invalid(ce)) { >>> - lrc_destroy(kref); >>> + __guc_context_destroy(ce); >>> return; >>> } else if (!lrc_desc_registered(guc, ce->guc_id)) { >>> release_guc_id(guc, ce); >>> - lrc_destroy(kref); >>> + __guc_context_destroy(ce); >>> return; >>> } >>> @@ -1087,7 +1126,7 @@ static void guc_context_destroy(struct kref *kref) >>> spin_lock_irqsave(&guc->contexts_lock, flags); >>> if (context_guc_id_invalid(ce)) { >>> spin_unlock_irqrestore(&guc->contexts_lock, flags); >>> - lrc_destroy(kref); >>> + __guc_context_destroy(ce); >>> return; >>> } >>> @@ -1132,6 +1171,8 @@ static const struct intel_context_ops guc_context_ops = { >>> .reset = lrc_reset, >>> .destroy = guc_context_destroy, >>> + >>> + .create_virtual = guc_create_virtual, >>> }; >>> static void __guc_signal_context_fence(struct intel_context *ce) >>> @@ -1260,6 +1301,83 @@ static int guc_request_alloc(struct i915_request *rq) >>> return 0; >>> } >>> +static struct intel_engine_cs * >>> +guc_virtual_get_sibling(struct intel_engine_cs *ve, unsigned int sibling) >>> +{ >>> + struct intel_engine_cs *engine; >>> + intel_engine_mask_t tmp, mask = ve->mask; >>> + unsigned int num_siblings = 0; >>> + >>> + for_each_engine_masked(engine, ve->gt, mask, tmp) >>> + if (num_siblings++ == sibling) >>> + return engine; >>> + >>> + return NULL; >>> +} >>> + >>> +static int guc_virtual_context_pre_pin(struct intel_context *ce, >>> + struct i915_gem_ww_ctx *ww, >>> + void **vaddr) >>> +{ >>> + struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0); >>> + >>> + return __guc_context_pre_pin(ce, engine, ww, vaddr); >>> +} >>> + >>> +static int guc_virtual_context_pin(struct intel_context *ce, void *vaddr) >>> +{ >>> + struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0); >>> + >>> + return __guc_context_pin(ce, engine, vaddr); >>> +} >>> + >>> +static void guc_virtual_context_enter(struct intel_context *ce) >>> +{ >>> + intel_engine_mask_t tmp, mask = ce->engine->mask; >>> + struct intel_engine_cs *engine; >>> + >>> + for_each_engine_masked(engine, ce->engine->gt, mask, tmp) >>> + intel_engine_pm_get(engine); >>> + >>> + intel_timeline_enter(ce->timeline); >>> +} >>> + >>> +static void guc_virtual_context_exit(struct intel_context *ce) >>> +{ >>> + intel_engine_mask_t tmp, mask = ce->engine->mask; >>> + struct intel_engine_cs *engine; >>> + >>> + for_each_engine_masked(engine, ce->engine->gt, mask, tmp) >>> + intel_engine_pm_put(engine); >>> + >>> + intel_timeline_exit(ce->timeline); >>> +} >>> + >>> +static int guc_virtual_context_alloc(struct intel_context *ce) >>> +{ >>> + struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0); >>> + >>> + return lrc_alloc(ce, engine); >>> +} >>> + >>> +static const struct intel_context_ops virtual_guc_context_ops = { >>> + .alloc = guc_virtual_context_alloc, >>> + >>> + .pre_pin = guc_virtual_context_pre_pin, >>> + .pin = guc_virtual_context_pin, >>> + .unpin = guc_context_unpin, >>> + .post_unpin = guc_context_post_unpin, >>> + >>> + .enter = guc_virtual_context_enter, >>> + .exit = guc_virtual_context_exit, >>> + >>> + .sched_disable = guc_context_sched_disable, >>> + >>> + .destroy = guc_context_destroy, >>> + >>> + .get_sibling = guc_virtual_get_sibling, >>> +}; >>> + >>> static void sanitize_hwsp(struct intel_engine_cs *engine) >>> { >>> struct intel_timeline *tl; >>> @@ -1566,7 +1684,7 @@ int intel_guc_deregister_done_process_msg(struct intel_guc *guc, >>> } else if (context_destroyed(ce)) { >>> /* Context has been destroyed */ >>> release_guc_id(guc, ce); >>> - lrc_destroy(&ce->ref); >>> + __guc_context_destroy(ce); >>> } >>> decr_outstanding_submission_g2h(guc); >>> @@ -1681,3 +1799,109 @@ void intel_guc_submission_print_context_info(struct intel_guc *guc, >>> atomic_read(&ce->guc_sched_state_no_lock)); >>> } >>> } >>> + >>> +static struct intel_context * >>> +guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count) >>> +{ >>> + struct guc_virtual_engine *ve; >>> + struct intel_guc *guc; >>> + unsigned int n; >>> + int err; >>> + >>> + ve = kzalloc(sizeof(*ve), GFP_KERNEL); >>> + if (!ve) >>> + return ERR_PTR(-ENOMEM); >>> + >>> + guc = &siblings[0]->gt->uc.guc; >>> + >>> + ve->base.i915 = siblings[0]->i915; >>> + ve->base.gt = siblings[0]->gt; >>> + ve->base.uncore = siblings[0]->uncore; >>> + ve->base.id = -1; >>> + >>> + ve->base.uabi_class = I915_ENGINE_CLASS_INVALID; >>> + ve->base.instance = I915_ENGINE_CLASS_INVALID_VIRTUAL; >>> + ve->base.uabi_instance = I915_ENGINE_CLASS_INVALID_VIRTUAL; >>> + ve->base.saturated = ALL_ENGINES; >>> + ve->base.breadcrumbs = intel_breadcrumbs_create(&ve->base); >>> + if (!ve->base.breadcrumbs) { >>> + kfree(ve); >>> + return ERR_PTR(-ENOMEM); >>> + } >>> + >>> + snprintf(ve->base.name, sizeof(ve->base.name), "virtual"); >>> + >>> + ve->base.sched_engine = i915_sched_engine_get(guc->sched_engine); >>> + >>> + ve->base.cops = &virtual_guc_context_ops; >>> + ve->base.request_alloc = guc_request_alloc; >>> + >>> + ve->base.submit_request = guc_submit_request; >>> + >>> + ve->base.flags = I915_ENGINE_IS_VIRTUAL; >>> + >>> + intel_context_init(&ve->context, &ve->base); >>> + >>> + for (n = 0; n < count; n++) { >>> + struct intel_engine_cs *sibling = siblings[n]; >>> + >>> + GEM_BUG_ON(!is_power_of_2(sibling->mask)); >>> + if (sibling->mask & ve->base.mask) { >>> + DRM_DEBUG("duplicate %s entry in load balancer\n", >>> + sibling->name); >>> + err = -EINVAL; >>> + goto err_put; >>> + } >>> + >>> + ve->base.mask |= sibling->mask; >>> + >>> + if (n != 0 && ve->base.class != sibling->class) { >>> + DRM_DEBUG("invalid mixing of engine class, sibling %d, already %d\n", >>> + sibling->class, ve->base.class); >>> + err = -EINVAL; >>> + goto err_put; >>> + } else if (n == 0) { >>> + ve->base.class = sibling->class; >>> + ve->base.uabi_class = sibling->uabi_class; >>> + snprintf(ve->base.name, sizeof(ve->base.name), >>> + "v%dx%d", ve->base.class, count); >>> + ve->base.context_size = sibling->context_size; >>> + >>> + ve->base.emit_bb_start = sibling->emit_bb_start; >>> + ve->base.emit_flush = sibling->emit_flush; >>> + ve->base.emit_init_breadcrumb = >>> + sibling->emit_init_breadcrumb; >>> + ve->base.emit_fini_breadcrumb = >>> + sibling->emit_fini_breadcrumb; >>> + ve->base.emit_fini_breadcrumb_dw = >>> + sibling->emit_fini_breadcrumb_dw; >>> + >>> + ve->base.flags |= sibling->flags; >>> + >>> + ve->base.props.timeslice_duration_ms = >>> + sibling->props.timeslice_duration_ms; >>> + ve->base.props.preempt_timeout_ms = >>> + sibling->props.preempt_timeout_ms; >>> + } >>> + } >>> + >>> + return &ve->context; >>> + >>> +err_put: >>> + intel_context_put(&ve->context); >>> + return ERR_PTR(err); >>> +} >>> + >>> + >>> + >> Too many new lines. >> > Yep, running dim checkpatch caught this for me. Already fixed. > > Matt > >> with the 2 nits addressed: >> >> Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> >> >> Daniele >> >>> +bool intel_guc_virtual_engine_has_heartbeat(const struct intel_engine_cs *ve) >>> +{ >>> + struct intel_engine_cs *engine; >>> + intel_engine_mask_t tmp, mask = ve->mask; >>> + >>> + for_each_engine_masked(engine, ve->gt, mask, tmp) >>> + if (READ_ONCE(engine->props.heartbeat_interval_ms)) >>> + return true; >>> + >>> + return false; >>> +} >>> diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h >>> index 2b9470c90558..5f263ac4f46a 100644 >>> --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h >>> +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h >>> @@ -26,6 +26,8 @@ void intel_guc_submission_print_info(struct intel_guc *guc, >>> void intel_guc_submission_print_context_info(struct intel_guc *guc, >>> struct drm_printer *p); >>> +bool intel_guc_virtual_engine_has_heartbeat(const struct intel_engine_cs *ve); >>> + >>> static inline bool intel_guc_submission_is_supported(struct intel_guc *guc) >>> { >>> /* XXX: GuC submission is unavailable for now */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index 89ca401bf9ae..bc52eeed782a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -74,7 +74,6 @@ #include "gt/intel_context_param.h" #include "gt/intel_engine_heartbeat.h" #include "gt/intel_engine_user.h" -#include "gt/intel_execlists_submission.h" /* virtual_engine */ #include "gt/intel_gpu_commands.h" #include "gt/intel_ring.h" @@ -363,9 +362,6 @@ set_proto_ctx_engines_balance(struct i915_user_extension __user *base, if (!HAS_EXECLISTS(i915)) return -ENODEV; - if (intel_uc_uses_guc_submission(&i915->gt.uc)) - return -ENODEV; /* not implement yet */ - if (get_user(idx, &ext->engine_index)) return -EFAULT; @@ -950,8 +946,8 @@ static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx, break; case I915_GEM_ENGINE_TYPE_BALANCED: - ce = intel_execlists_create_virtual(pe[n].siblings, - pe[n].num_siblings); + ce = intel_engine_create_virtual(pe[n].siblings, + pe[n].num_siblings); break; case I915_GEM_ENGINE_TYPE_INVALID: diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index 4a5518d295c2..542c98418771 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -47,6 +47,12 @@ struct intel_context_ops { void (*reset)(struct intel_context *ce); void (*destroy)(struct kref *kref); + + /* virtual engine/context interface */ + struct intel_context *(*create_virtual)(struct intel_engine_cs **engine, + unsigned int count); + struct intel_engine_cs *(*get_sibling)(struct intel_engine_cs *engine, + unsigned int sibling); }; struct intel_context { diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h index f911c1224ab2..13bfb7ec33b2 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine.h +++ b/drivers/gpu/drm/i915/gt/intel_engine.h @@ -273,13 +273,41 @@ intel_engine_has_preempt_reset(const struct intel_engine_cs *engine) return intel_engine_has_preemption(engine); } +struct intel_context * +intel_engine_create_virtual(struct intel_engine_cs **siblings, + unsigned int count); + +static inline bool +intel_virtual_engine_has_heartbeat(const struct intel_engine_cs *engine) +{ + /* + * For non-GuC submission we expect the back-end to look at the + * heartbeat status of the actual physical engine that the work + * has been (or is being) scheduled on, so we should only reach + * here with GuC submission enabled. + */ + GEM_BUG_ON(!intel_engine_uses_guc(engine)); + + return intel_guc_virtual_engine_has_heartbeat(engine); +} + static inline bool intel_engine_has_heartbeat(const struct intel_engine_cs *engine) { if (!IS_ACTIVE(CONFIG_DRM_I915_HEARTBEAT_INTERVAL)) return false; - return READ_ONCE(engine->props.heartbeat_interval_ms); + if (intel_engine_is_virtual(engine)) + return intel_virtual_engine_has_heartbeat(engine); + else + return READ_ONCE(engine->props.heartbeat_interval_ms); +} + +static inline struct intel_engine_cs * +intel_engine_get_sibling(struct intel_engine_cs *engine, unsigned int sibling) +{ + GEM_BUG_ON(!intel_engine_is_virtual(engine)); + return engine->cops->get_sibling(engine, sibling); } #endif /* _INTEL_RINGBUFFER_H_ */ diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index c1c96ced2a4b..7dee9a1209bc 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -1755,6 +1755,20 @@ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine, ktime_t *now) return total; } +struct intel_context * +intel_engine_create_virtual(struct intel_engine_cs **siblings, + unsigned int count) +{ + if (count == 0) + return ERR_PTR(-EINVAL); + + if (count == 1) + return intel_context_create(siblings[0]); + + GEM_BUG_ON(!siblings[0]->cops->create_virtual); + return siblings[0]->cops->create_virtual(siblings, count); +} + static bool match_ring(struct i915_request *rq) { u32 ring = ENGINE_READ(rq->engine, RING_START); diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 87cedaeb4bf8..b2580cd2ce51 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -199,6 +199,9 @@ static struct virtual_engine *to_virtual_engine(struct intel_engine_cs *engine) return container_of(engine, struct virtual_engine, base); } +static struct intel_context * +execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count); + static struct i915_request * __active_request(const struct intel_timeline * const tl, struct i915_request *rq, @@ -2599,6 +2602,8 @@ static const struct intel_context_ops execlists_context_ops = { .reset = lrc_reset, .destroy = lrc_destroy, + + .create_virtual = execlists_create_virtual, }; static int emit_pdps(struct i915_request *rq) @@ -3545,6 +3550,17 @@ static void virtual_context_exit(struct intel_context *ce) intel_engine_pm_put(ve->siblings[n]); } +static struct intel_engine_cs * +virtual_get_sibling(struct intel_engine_cs *engine, unsigned int sibling) +{ + struct virtual_engine *ve = to_virtual_engine(engine); + + if (sibling >= ve->num_siblings) + return NULL; + + return ve->siblings[sibling]; +} + static const struct intel_context_ops virtual_context_ops = { .flags = COPS_HAS_INFLIGHT, @@ -3559,6 +3575,8 @@ static const struct intel_context_ops virtual_context_ops = { .exit = virtual_context_exit, .destroy = virtual_context_destroy, + + .get_sibling = virtual_get_sibling, }; static intel_engine_mask_t virtual_submission_mask(struct virtual_engine *ve) @@ -3707,20 +3725,13 @@ static void virtual_submit_request(struct i915_request *rq) spin_unlock_irqrestore(&ve->base.sched_engine->lock, flags); } -struct intel_context * -intel_execlists_create_virtual(struct intel_engine_cs **siblings, - unsigned int count) +static struct intel_context * +execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count) { struct virtual_engine *ve; unsigned int n; int err; - if (count == 0) - return ERR_PTR(-EINVAL); - - if (count == 1) - return intel_context_create(siblings[0]); - ve = kzalloc(struct_size(ve, siblings, count), GFP_KERNEL); if (!ve) return ERR_PTR(-ENOMEM); diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h index ad4f3e1a0fde..a1aa92c983a5 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h @@ -32,10 +32,6 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine, int indent), unsigned int max); -struct intel_context * -intel_execlists_create_virtual(struct intel_engine_cs **siblings, - unsigned int count); - bool intel_engine_in_execlists_submission_mode(const struct intel_engine_cs *engine); diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c index 22a124b134b6..f12ffe797639 100644 --- a/drivers/gpu/drm/i915/gt/selftest_execlists.c +++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c @@ -3733,7 +3733,7 @@ static int nop_virtual_engine(struct intel_gt *gt, GEM_BUG_ON(!nctx || nctx > ARRAY_SIZE(ve)); for (n = 0; n < nctx; n++) { - ve[n] = intel_execlists_create_virtual(siblings, nsibling); + ve[n] = intel_engine_create_virtual(siblings, nsibling); if (IS_ERR(ve[n])) { err = PTR_ERR(ve[n]); nctx = n; @@ -3929,7 +3929,7 @@ static int mask_virtual_engine(struct intel_gt *gt, * restrict it to our desired engine within the virtual engine. */ - ve = intel_execlists_create_virtual(siblings, nsibling); + ve = intel_engine_create_virtual(siblings, nsibling); if (IS_ERR(ve)) { err = PTR_ERR(ve); goto out_close; @@ -4060,7 +4060,7 @@ static int slicein_virtual_engine(struct intel_gt *gt, i915_request_add(rq); } - ce = intel_execlists_create_virtual(siblings, nsibling); + ce = intel_engine_create_virtual(siblings, nsibling); if (IS_ERR(ce)) { err = PTR_ERR(ce); goto out; @@ -4112,7 +4112,7 @@ static int sliceout_virtual_engine(struct intel_gt *gt, /* XXX We do not handle oversubscription and fairness with normal rq */ for (n = 0; n < nsibling; n++) { - ce = intel_execlists_create_virtual(siblings, nsibling); + ce = intel_engine_create_virtual(siblings, nsibling); if (IS_ERR(ce)) { err = PTR_ERR(ce); goto out; @@ -4214,7 +4214,7 @@ static int preserved_virtual_engine(struct intel_gt *gt, if (err) goto out_scratch; - ve = intel_execlists_create_virtual(siblings, nsibling); + ve = intel_engine_create_virtual(siblings, nsibling); if (IS_ERR(ve)) { err = PTR_ERR(ve); goto out_scratch; @@ -4354,7 +4354,7 @@ static int reset_virtual_engine(struct intel_gt *gt, if (igt_spinner_init(&spin, gt)) return -ENOMEM; - ve = intel_execlists_create_virtual(siblings, nsibling); + ve = intel_engine_create_virtual(siblings, nsibling); if (IS_ERR(ve)) { err = PTR_ERR(ve); goto out_spin; 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 26aadad10b12..28404454a97a 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -60,6 +60,15 @@ * */ +/* GuC Virtual Engine */ +struct guc_virtual_engine { + struct intel_engine_cs base; + struct intel_context context; +}; + +static struct intel_context * +guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count); + #define GUC_REQUEST_SIZE 64 /* bytes */ /* @@ -931,14 +940,17 @@ static int guc_lrc_desc_pin(struct intel_context *ce) return ret; } -static int guc_context_pre_pin(struct intel_context *ce, - struct i915_gem_ww_ctx *ww, - void **vaddr) +static int __guc_context_pre_pin(struct intel_context *ce, + struct intel_engine_cs *engine, + struct i915_gem_ww_ctx *ww, + void **vaddr) { - return lrc_pre_pin(ce, ce->engine, ww, vaddr); + return lrc_pre_pin(ce, engine, ww, vaddr); } -static int guc_context_pin(struct intel_context *ce, void *vaddr) +static int __guc_context_pin(struct intel_context *ce, + struct intel_engine_cs *engine, + void *vaddr) { if (i915_ggtt_offset(ce->state) != (ce->lrc.lrca & CTX_GTT_ADDRESS_MASK)) @@ -949,7 +961,19 @@ static int guc_context_pin(struct intel_context *ce, void *vaddr) * explaination of why. */ - return lrc_pin(ce, ce->engine, vaddr); + return lrc_pin(ce, engine, vaddr); +} + +static int guc_context_pre_pin(struct intel_context *ce, + struct i915_gem_ww_ctx *ww, + void **vaddr) +{ + return __guc_context_pre_pin(ce, ce->engine, ww, vaddr); +} + +static int guc_context_pin(struct intel_context *ce, void *vaddr) +{ + return __guc_context_pin(ce, ce->engine, vaddr); } static void guc_context_unpin(struct intel_context *ce) @@ -1054,6 +1078,21 @@ static inline void guc_lrc_desc_unpin(struct intel_context *ce) deregister_context(ce, ce->guc_id); } +static void __guc_context_destroy(struct intel_context *ce) +{ + lrc_fini(ce); + intel_context_fini(ce); + + if (intel_engine_is_virtual(ce->engine)) { + struct guc_virtual_engine *ve = + container_of(ce, typeof(*ve), context); + + kfree(ve); + } else { + intel_context_free(ce); + } +} + static void guc_context_destroy(struct kref *kref) { struct intel_context *ce = container_of(kref, typeof(*ce), ref); @@ -1068,11 +1107,11 @@ static void guc_context_destroy(struct kref *kref) * registered with the GuC. */ if (context_guc_id_invalid(ce)) { - lrc_destroy(kref); + __guc_context_destroy(ce); return; } else if (!lrc_desc_registered(guc, ce->guc_id)) { release_guc_id(guc, ce); - lrc_destroy(kref); + __guc_context_destroy(ce); return; } @@ -1087,7 +1126,7 @@ static void guc_context_destroy(struct kref *kref) spin_lock_irqsave(&guc->contexts_lock, flags); if (context_guc_id_invalid(ce)) { spin_unlock_irqrestore(&guc->contexts_lock, flags); - lrc_destroy(kref); + __guc_context_destroy(ce); return; } @@ -1132,6 +1171,8 @@ static const struct intel_context_ops guc_context_ops = { .reset = lrc_reset, .destroy = guc_context_destroy, + + .create_virtual = guc_create_virtual, }; static void __guc_signal_context_fence(struct intel_context *ce) @@ -1260,6 +1301,83 @@ static int guc_request_alloc(struct i915_request *rq) return 0; } +static struct intel_engine_cs * +guc_virtual_get_sibling(struct intel_engine_cs *ve, unsigned int sibling) +{ + struct intel_engine_cs *engine; + intel_engine_mask_t tmp, mask = ve->mask; + unsigned int num_siblings = 0; + + for_each_engine_masked(engine, ve->gt, mask, tmp) + if (num_siblings++ == sibling) + return engine; + + return NULL; +} + +static int guc_virtual_context_pre_pin(struct intel_context *ce, + struct i915_gem_ww_ctx *ww, + void **vaddr) +{ + struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0); + + return __guc_context_pre_pin(ce, engine, ww, vaddr); +} + +static int guc_virtual_context_pin(struct intel_context *ce, void *vaddr) +{ + struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0); + + return __guc_context_pin(ce, engine, vaddr); +} + +static void guc_virtual_context_enter(struct intel_context *ce) +{ + intel_engine_mask_t tmp, mask = ce->engine->mask; + struct intel_engine_cs *engine; + + for_each_engine_masked(engine, ce->engine->gt, mask, tmp) + intel_engine_pm_get(engine); + + intel_timeline_enter(ce->timeline); +} + +static void guc_virtual_context_exit(struct intel_context *ce) +{ + intel_engine_mask_t tmp, mask = ce->engine->mask; + struct intel_engine_cs *engine; + + for_each_engine_masked(engine, ce->engine->gt, mask, tmp) + intel_engine_pm_put(engine); + + intel_timeline_exit(ce->timeline); +} + +static int guc_virtual_context_alloc(struct intel_context *ce) +{ + struct intel_engine_cs *engine = guc_virtual_get_sibling(ce->engine, 0); + + return lrc_alloc(ce, engine); +} + +static const struct intel_context_ops virtual_guc_context_ops = { + .alloc = guc_virtual_context_alloc, + + .pre_pin = guc_virtual_context_pre_pin, + .pin = guc_virtual_context_pin, + .unpin = guc_context_unpin, + .post_unpin = guc_context_post_unpin, + + .enter = guc_virtual_context_enter, + .exit = guc_virtual_context_exit, + + .sched_disable = guc_context_sched_disable, + + .destroy = guc_context_destroy, + + .get_sibling = guc_virtual_get_sibling, +}; + static void sanitize_hwsp(struct intel_engine_cs *engine) { struct intel_timeline *tl; @@ -1566,7 +1684,7 @@ int intel_guc_deregister_done_process_msg(struct intel_guc *guc, } else if (context_destroyed(ce)) { /* Context has been destroyed */ release_guc_id(guc, ce); - lrc_destroy(&ce->ref); + __guc_context_destroy(ce); } decr_outstanding_submission_g2h(guc); @@ -1681,3 +1799,109 @@ void intel_guc_submission_print_context_info(struct intel_guc *guc, atomic_read(&ce->guc_sched_state_no_lock)); } } + +static struct intel_context * +guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count) +{ + struct guc_virtual_engine *ve; + struct intel_guc *guc; + unsigned int n; + int err; + + ve = kzalloc(sizeof(*ve), GFP_KERNEL); + if (!ve) + return ERR_PTR(-ENOMEM); + + guc = &siblings[0]->gt->uc.guc; + + ve->base.i915 = siblings[0]->i915; + ve->base.gt = siblings[0]->gt; + ve->base.uncore = siblings[0]->uncore; + ve->base.id = -1; + + ve->base.uabi_class = I915_ENGINE_CLASS_INVALID; + ve->base.instance = I915_ENGINE_CLASS_INVALID_VIRTUAL; + ve->base.uabi_instance = I915_ENGINE_CLASS_INVALID_VIRTUAL; + ve->base.saturated = ALL_ENGINES; + ve->base.breadcrumbs = intel_breadcrumbs_create(&ve->base); + if (!ve->base.breadcrumbs) { + kfree(ve); + return ERR_PTR(-ENOMEM); + } + + snprintf(ve->base.name, sizeof(ve->base.name), "virtual"); + + ve->base.sched_engine = i915_sched_engine_get(guc->sched_engine); + + ve->base.cops = &virtual_guc_context_ops; + ve->base.request_alloc = guc_request_alloc; + + ve->base.submit_request = guc_submit_request; + + ve->base.flags = I915_ENGINE_IS_VIRTUAL; + + intel_context_init(&ve->context, &ve->base); + + for (n = 0; n < count; n++) { + struct intel_engine_cs *sibling = siblings[n]; + + GEM_BUG_ON(!is_power_of_2(sibling->mask)); + if (sibling->mask & ve->base.mask) { + DRM_DEBUG("duplicate %s entry in load balancer\n", + sibling->name); + err = -EINVAL; + goto err_put; + } + + ve->base.mask |= sibling->mask; + + if (n != 0 && ve->base.class != sibling->class) { + DRM_DEBUG("invalid mixing of engine class, sibling %d, already %d\n", + sibling->class, ve->base.class); + err = -EINVAL; + goto err_put; + } else if (n == 0) { + ve->base.class = sibling->class; + ve->base.uabi_class = sibling->uabi_class; + snprintf(ve->base.name, sizeof(ve->base.name), + "v%dx%d", ve->base.class, count); + ve->base.context_size = sibling->context_size; + + ve->base.emit_bb_start = sibling->emit_bb_start; + ve->base.emit_flush = sibling->emit_flush; + ve->base.emit_init_breadcrumb = + sibling->emit_init_breadcrumb; + ve->base.emit_fini_breadcrumb = + sibling->emit_fini_breadcrumb; + ve->base.emit_fini_breadcrumb_dw = + sibling->emit_fini_breadcrumb_dw; + + ve->base.flags |= sibling->flags; + + ve->base.props.timeslice_duration_ms = + sibling->props.timeslice_duration_ms; + ve->base.props.preempt_timeout_ms = + sibling->props.preempt_timeout_ms; + } + } + + return &ve->context; + +err_put: + intel_context_put(&ve->context); + return ERR_PTR(err); +} + + + +bool intel_guc_virtual_engine_has_heartbeat(const struct intel_engine_cs *ve) +{ + struct intel_engine_cs *engine; + intel_engine_mask_t tmp, mask = ve->mask; + + for_each_engine_masked(engine, ve->gt, mask, tmp) + if (READ_ONCE(engine->props.heartbeat_interval_ms)) + return true; + + return false; +} diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h index 2b9470c90558..5f263ac4f46a 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h @@ -26,6 +26,8 @@ void intel_guc_submission_print_info(struct intel_guc *guc, void intel_guc_submission_print_context_info(struct intel_guc *guc, struct drm_printer *p); +bool intel_guc_virtual_engine_has_heartbeat(const struct intel_engine_cs *ve); + static inline bool intel_guc_submission_is_supported(struct intel_guc *guc) { /* XXX: GuC submission is unavailable for now */
Implement GuC virtual engines. Rather simple implementation, basically just allocate an engine, setup context enter / exit function to virtual engine specific functions, set all other variables / functions to guc versions, and set the engine mask to that of all the siblings. v2: Update to work with proto-ctx v3: (Daniele) - Drop include, add comment to intel_virtual_engine_has_heartbeat Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Signed-off-by: Matthew Brost <matthew.brost@intel.com> --- drivers/gpu/drm/i915/gem/i915_gem_context.c | 8 +- drivers/gpu/drm/i915/gt/intel_context_types.h | 6 + drivers/gpu/drm/i915/gt/intel_engine.h | 30 ++- drivers/gpu/drm/i915/gt/intel_engine_cs.c | 14 + .../drm/i915/gt/intel_execlists_submission.c | 29 ++- .../drm/i915/gt/intel_execlists_submission.h | 4 - drivers/gpu/drm/i915/gt/selftest_execlists.c | 12 +- .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 244 +++++++++++++++++- .../gpu/drm/i915/gt/uc/intel_guc_submission.h | 2 + 9 files changed, 313 insertions(+), 36 deletions(-)