From: Daniel Vetter <daniel@ffwll.ch>
To: Matthew Brost <matthew.brost@intel.com>
Cc: intel-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org
Subject: Re: [Intel-gfx] [PATCH 26/46] drm/i915: Connect UAPI to GuC multi-lrc interface
Date: Mon, 9 Aug 2021 18:37:20 +0200 [thread overview]
Message-ID: <YRFZwPSkrGqh4hpJ@phenom.ffwll.local> (raw)
In-Reply-To: <20210803222943.27686-27-matthew.brost@intel.com>
On Tue, Aug 03, 2021 at 03:29:23PM -0700, Matthew Brost wrote:
> Introduce 'set parallel submit' extension to connect UAPI to GuC
> multi-lrc interface. Kernel doc in new uAPI should explain it all.
>
> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
> Signed-off-by: Matthew Brost <matthew.brost@intel.com>
UMD merge request link + igt patchwork link because this is uapi please.
-Daniel
> ---
> drivers/gpu/drm/i915/gem/i915_gem_context.c | 157 +++++++++++++++++-
> .../gpu/drm/i915/gem/i915_gem_context_types.h | 6 +
> drivers/gpu/drm/i915/gt/intel_context_types.h | 8 +-
> drivers/gpu/drm/i915/gt/intel_engine.h | 12 +-
> drivers/gpu/drm/i915/gt/intel_engine_cs.c | 6 +-
> .../drm/i915/gt/intel_execlists_submission.c | 6 +-
> drivers/gpu/drm/i915/gt/selftest_execlists.c | 12 +-
> .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 111 +++++++++++--
> include/uapi/drm/i915_drm.h | 128 ++++++++++++++
> 9 files changed, 417 insertions(+), 29 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
> index cff72679ad7c..2b0dd3ff4db8 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
> @@ -515,9 +515,149 @@ set_proto_ctx_engines_bond(struct i915_user_extension __user *base, void *data)
> return 0;
> }
>
> +static int
> +set_proto_ctx_engines_parallel_submit(struct i915_user_extension __user *base,
> + void *data)
> +{
> + struct i915_context_engines_parallel_submit __user *ext =
> + container_of_user(base, typeof(*ext), base);
> + const struct set_proto_ctx_engines *set = data;
> + struct drm_i915_private *i915 = set->i915;
> + u64 flags;
> + int err = 0, n, i, j;
> + u16 slot, width, num_siblings;
> + struct intel_engine_cs **siblings = NULL;
> + intel_engine_mask_t prev_mask;
> +
> + /* Disabling for now */
> + return -ENODEV;
> +
> + if (!(intel_uc_uses_guc_submission(&i915->gt.uc)))
> + return -ENODEV;
> +
> + if (get_user(slot, &ext->engine_index))
> + return -EFAULT;
> +
> + if (get_user(width, &ext->width))
> + return -EFAULT;
> +
> + if (get_user(num_siblings, &ext->num_siblings))
> + return -EFAULT;
> +
> + if (slot >= set->num_engines) {
> + drm_dbg(&i915->drm, "Invalid placement value, %d >= %d\n",
> + slot, set->num_engines);
> + return -EINVAL;
> + }
> +
> + if (set->engines[slot].type != I915_GEM_ENGINE_TYPE_INVALID) {
> + drm_dbg(&i915->drm,
> + "Invalid placement[%d], already occupied\n", slot);
> + return -EINVAL;
> + }
> +
> + if (get_user(flags, &ext->flags))
> + return -EFAULT;
> +
> + if (flags) {
> + drm_dbg(&i915->drm, "Unknown flags 0x%02llx", flags);
> + return -EINVAL;
> + }
> +
> + for (n = 0; n < ARRAY_SIZE(ext->mbz64); n++) {
> + err = check_user_mbz(&ext->mbz64[n]);
> + if (err)
> + return err;
> + }
> +
> + if (width < 2) {
> + drm_dbg(&i915->drm, "Width (%d) < 2\n", width);
> + return -EINVAL;
> + }
> +
> + if (num_siblings < 1) {
> + drm_dbg(&i915->drm, "Number siblings (%d) < 1\n",
> + num_siblings);
> + return -EINVAL;
> + }
> +
> + siblings = kmalloc_array(num_siblings * width,
> + sizeof(*siblings),
> + GFP_KERNEL);
> + if (!siblings)
> + return -ENOMEM;
> +
> + /* Create contexts / engines */
> + for (i = 0; i < width; ++i) {
> + intel_engine_mask_t current_mask = 0;
> + struct i915_engine_class_instance prev_engine;
> +
> + for (j = 0; j < num_siblings; ++j) {
> + struct i915_engine_class_instance ci;
> +
> + n = i * num_siblings + j;
> + if (copy_from_user(&ci, &ext->engines[n], sizeof(ci))) {
> + err = -EFAULT;
> + goto out_err;
> + }
> +
> + siblings[n] =
> + intel_engine_lookup_user(i915, ci.engine_class,
> + ci.engine_instance);
> + if (!siblings[n]) {
> + drm_dbg(&i915->drm,
> + "Invalid sibling[%d]: { class:%d, inst:%d }\n",
> + n, ci.engine_class, ci.engine_instance);
> + err = -EINVAL;
> + goto out_err;
> + }
> +
> + if (n) {
> + if (prev_engine.engine_class !=
> + ci.engine_class) {
> + drm_dbg(&i915->drm,
> + "Mismatched class %d, %d\n",
> + prev_engine.engine_class,
> + ci.engine_class);
> + err = -EINVAL;
> + goto out_err;
> + }
> + }
> +
> + prev_engine = ci;
> + current_mask |= siblings[n]->logical_mask;
> + }
> +
> + if (i > 0) {
> + if (current_mask != prev_mask << 1) {
> + drm_dbg(&i915->drm,
> + "Non contiguous logical mask 0x%x, 0x%x\n",
> + prev_mask, current_mask);
> + err = -EINVAL;
> + goto out_err;
> + }
> + }
> + prev_mask = current_mask;
> + }
> +
> + set->engines[slot].type = I915_GEM_ENGINE_TYPE_PARALLEL;
> + set->engines[slot].num_siblings = num_siblings;
> + set->engines[slot].width = width;
> + set->engines[slot].siblings = siblings;
> +
> + return 0;
> +
> +out_err:
> + kfree(siblings);
> +
> + return err;
> +}
> +
> static const i915_user_extension_fn set_proto_ctx_engines_extensions[] = {
> [I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE] = set_proto_ctx_engines_balance,
> [I915_CONTEXT_ENGINES_EXT_BOND] = set_proto_ctx_engines_bond,
> + [I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT] =
> + set_proto_ctx_engines_parallel_submit,
> };
>
> static int set_proto_ctx_engines(struct drm_i915_file_private *fpriv,
> @@ -938,7 +1078,7 @@ static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx,
>
> e = alloc_engines(num_engines);
> for (n = 0; n < num_engines; n++) {
> - struct intel_context *ce;
> + struct intel_context *ce, *child;
> int ret;
>
> switch (pe[n].type) {
> @@ -948,7 +1088,13 @@ static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx,
>
> case I915_GEM_ENGINE_TYPE_BALANCED:
> ce = intel_engine_create_virtual(pe[n].siblings,
> - pe[n].num_siblings);
> + pe[n].num_siblings, 0);
> + break;
> +
> + case I915_GEM_ENGINE_TYPE_PARALLEL:
> + ce = intel_engine_create_parallel(pe[n].siblings,
> + pe[n].num_siblings,
> + pe[n].width);
> break;
>
> case I915_GEM_ENGINE_TYPE_INVALID:
> @@ -969,6 +1115,13 @@ static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx,
> err = ERR_PTR(ret);
> goto free_engines;
> }
> + for_each_child(ce, child) {
> + ret = intel_context_set_gem(child, ctx, pe->sseu);
> + if (ret) {
> + err = ERR_PTR(ret);
> + goto free_engines;
> + }
> + }
> }
> e->num_engines = num_engines;
>
> diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
> index 94c03a97cb77..7b096d83bca1 100644
> --- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
> +++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
> @@ -78,6 +78,9 @@ enum i915_gem_engine_type {
>
> /** @I915_GEM_ENGINE_TYPE_BALANCED: A load-balanced engine set */
> I915_GEM_ENGINE_TYPE_BALANCED,
> +
> + /** @I915_GEM_ENGINE_TYPE_PARALLEL: A parallel engine set */
> + I915_GEM_ENGINE_TYPE_PARALLEL,
> };
>
> /**
> @@ -108,6 +111,9 @@ struct i915_gem_proto_engine {
> /** @num_siblings: Number of balanced siblings */
> unsigned int num_siblings;
>
> + /** @width: Width of each sibling */
> + unsigned int width;
> +
> /** @siblings: Balanced siblings */
> struct intel_engine_cs **siblings;
>
> diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h
> index f4fc81f64921..9cdbea752014 100644
> --- a/drivers/gpu/drm/i915/gt/intel_context_types.h
> +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h
> @@ -55,9 +55,13 @@ struct intel_context_ops {
> void (*reset)(struct intel_context *ce);
> void (*destroy)(struct kref *kref);
>
> - /* virtual engine/context interface */
> + /* virtual/parallel engine/context interface */
> struct intel_context *(*create_virtual)(struct intel_engine_cs **engine,
> - unsigned int count);
> + unsigned int count,
> + unsigned long flags);
> + struct intel_context *(*create_parallel)(struct intel_engine_cs **engines,
> + unsigned int num_siblings,
> + unsigned int width);
> struct intel_engine_cs *(*get_sibling)(struct intel_engine_cs *engine,
> unsigned int sibling);
> };
> diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
> index 87579affb952..43f16a8347ee 100644
> --- a/drivers/gpu/drm/i915/gt/intel_engine.h
> +++ b/drivers/gpu/drm/i915/gt/intel_engine.h
> @@ -279,9 +279,19 @@ intel_engine_has_preempt_reset(const struct intel_engine_cs *engine)
> return intel_engine_has_preemption(engine);
> }
>
> +#define FORCE_VIRTUAL BIT(0)
> struct intel_context *
> intel_engine_create_virtual(struct intel_engine_cs **siblings,
> - unsigned int count);
> + unsigned int count, unsigned long flags);
> +
> +static inline struct intel_context *
> +intel_engine_create_parallel(struct intel_engine_cs **engines,
> + unsigned int num_engines,
> + unsigned int width)
> +{
> + GEM_BUG_ON(!engines[0]->cops->create_parallel);
> + return engines[0]->cops->create_parallel(engines, num_engines, width);
> +}
>
> static inline bool
> intel_virtual_engine_has_heartbeat(const struct intel_engine_cs *engine)
> diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
> index 4d790f9a65dd..f66c75c77584 100644
> --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
> +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
> @@ -1923,16 +1923,16 @@ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine, ktime_t *now)
>
> struct intel_context *
> intel_engine_create_virtual(struct intel_engine_cs **siblings,
> - unsigned int count)
> + unsigned int count, unsigned long flags)
> {
> if (count == 0)
> return ERR_PTR(-EINVAL);
>
> - if (count == 1)
> + if (count == 1 && !(flags & FORCE_VIRTUAL))
> return intel_context_create(siblings[0]);
>
> GEM_BUG_ON(!siblings[0]->cops->create_virtual);
> - return siblings[0]->cops->create_virtual(siblings, count);
> + return siblings[0]->cops->create_virtual(siblings, count, flags);
> }
>
> struct i915_request *
> diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
> index fc74ca28f245..769480e026bb 100644
> --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
> +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
> @@ -201,7 +201,8 @@ static struct virtual_engine *to_virtual_engine(struct intel_engine_cs *engine)
> }
>
> static struct intel_context *
> -execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count);
> +execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count,
> + unsigned long flags);
>
> static struct i915_request *
> __active_request(const struct intel_timeline * const tl,
> @@ -3785,7 +3786,8 @@ static void virtual_submit_request(struct i915_request *rq)
> }
>
> static struct intel_context *
> -execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count)
> +execlists_create_virtual(struct intel_engine_cs **siblings, unsigned int count,
> + unsigned long flags)
> {
> struct virtual_engine *ve;
> unsigned int n;
> diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c
> index f12ffe797639..e876a9d88a5c 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_engine_create_virtual(siblings, nsibling);
> + ve[n] = intel_engine_create_virtual(siblings, nsibling, 0);
> 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_engine_create_virtual(siblings, nsibling);
> + ve = intel_engine_create_virtual(siblings, nsibling, 0);
> 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_engine_create_virtual(siblings, nsibling);
> + ce = intel_engine_create_virtual(siblings, nsibling, 0);
> 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_engine_create_virtual(siblings, nsibling);
> + ce = intel_engine_create_virtual(siblings, nsibling, 0);
> 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_engine_create_virtual(siblings, nsibling);
> + ve = intel_engine_create_virtual(siblings, nsibling, 0);
> 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_engine_create_virtual(siblings, nsibling);
> + ve = intel_engine_create_virtual(siblings, nsibling, 0);
> 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 44a7582c9aed..89528624710a 100644
> --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> @@ -82,7 +82,8 @@
> */
>
> static struct intel_context *
> -guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count);
> +guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count,
> + unsigned long flags);
>
> #define GUC_REQUEST_SIZE 64 /* bytes */
>
> @@ -2514,8 +2515,6 @@ static void guc_context_post_unpin(struct intel_context *ce)
> __guc_context_post_unpin(ce);
> }
>
> -/* Future patches will use this function */
> -__maybe_unused
> static int guc_parent_context_pre_pin(struct intel_context *ce,
> struct i915_gem_ww_ctx *ww)
> {
> @@ -2559,8 +2558,6 @@ static int guc_parent_context_pre_pin(struct intel_context *ce,
> return err;
> }
>
> -/* Future patches will use this function */
> -__maybe_unused
> static void guc_parent_context_post_unpin(struct intel_context *ce)
> {
> struct intel_context *child;
> @@ -2576,8 +2573,6 @@ static void guc_parent_context_post_unpin(struct intel_context *ce)
> }
> }
>
> -/* Future patches will use this function */
> -__maybe_unused
> static int guc_parent_context_pin(struct intel_context *ce)
> {
> int ret, i = 0, j = 0;
> @@ -2623,8 +2618,6 @@ static int guc_parent_context_pin(struct intel_context *ce)
> return ret;
> }
>
> -/* Future patches will use this function */
> -__maybe_unused
> static void guc_parent_context_unpin(struct intel_context *ce)
> {
> struct intel_context *child;
> @@ -3048,8 +3041,6 @@ static void destroy_worker_func(struct work_struct *w)
> intel_gt_pm_unpark_work_add(gt, destroy_worker);
> }
>
> -/* Future patches will use this function */
> -__maybe_unused
> static void guc_child_context_destroy(struct kref *kref)
> {
> __guc_context_destroy(container_of(kref, struct intel_context, ref));
> @@ -3272,6 +3263,11 @@ static void remove_from_context(struct i915_request *rq)
> i915_request_notify_execute_cb_imm(rq);
> }
>
> +static struct intel_context *
> +guc_create_parallel(struct intel_engine_cs **engines,
> + unsigned int num_siblings,
> + unsigned int width);
> +
> static const struct intel_context_ops guc_context_ops = {
> .alloc = guc_context_alloc,
>
> @@ -3293,6 +3289,7 @@ static const struct intel_context_ops guc_context_ops = {
> .destroy = guc_context_destroy,
>
> .create_virtual = guc_create_virtual,
> + .create_parallel = guc_create_parallel,
> };
>
> static void __guc_signal_context_fence(struct intel_context *ce)
> @@ -3782,6 +3779,91 @@ static void guc_retire_inflight_request_prio(struct i915_request *rq)
> spin_unlock(&ce->guc_active.lock);
> }
>
> +static const struct intel_context_ops virtual_parent_context_ops = {
> + .alloc = guc_virtual_context_alloc,
> +
> + .pre_pin = guc_parent_context_pre_pin,
> + .pin = guc_parent_context_pin,
> + .unpin = guc_parent_context_unpin,
> + .post_unpin = guc_parent_context_post_unpin,
> +
> + .ban = guc_context_ban,
> +
> + .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 const struct intel_context_ops virtual_child_context_ops = {
> + .alloc = guc_virtual_context_alloc,
> +
> + .enter = guc_virtual_context_enter,
> + .exit = guc_virtual_context_exit,
> +
> + .destroy = guc_child_context_destroy,
> +};
> +
> +static struct intel_context *
> +guc_create_parallel(struct intel_engine_cs **engines,
> + unsigned int num_siblings,
> + unsigned int width)
> +{
> + struct intel_engine_cs **siblings = NULL;
> + struct intel_context *parent = NULL, *ce, *err;
> + int i, j;
> + int ret;
> +
> + siblings = kmalloc_array(num_siblings,
> + sizeof(*siblings),
> + GFP_KERNEL);
> + if (!siblings)
> + return ERR_PTR(-ENOMEM);
> +
> + for (i = 0; i < width; ++i) {
> + for (j = 0; j < num_siblings; ++j)
> + siblings[j] = engines[i * num_siblings + j];
> +
> + ce = intel_engine_create_virtual(siblings, num_siblings,
> + FORCE_VIRTUAL);
> + if (!ce) {
> + err = ERR_PTR(-ENOMEM);
> + goto unwind;
> + }
> +
> + if (i == 0) {
> + parent = ce;
> + } else {
> + intel_context_bind_parent_child(parent, ce);
> + ret = intel_context_alloc_state(ce);
> + if (ret) {
> + err = ERR_PTR(ret);
> + goto unwind;
> + }
> + }
> + }
> +
> + parent->ops = &virtual_parent_context_ops;
> + for_each_child(parent, ce)
> + ce->ops = &virtual_child_context_ops;
> +
> + kfree(siblings);
> + return parent;
> +
> +unwind:
> + if (parent) {
> + for_each_child(parent, ce)
> + intel_context_put(ce);
> + intel_context_put(parent);
> + }
> + kfree(siblings);
> + return err;
> +}
> +
> static void sanitize_hwsp(struct intel_engine_cs *engine)
> {
> struct intel_timeline *tl;
> @@ -4578,7 +4660,8 @@ void intel_guc_submission_print_context_info(struct intel_guc *guc,
> }
>
> static struct intel_context *
> -guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count)
> +guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count,
> + unsigned long flags)
> {
> struct guc_virtual_engine *ve;
> struct intel_guc *guc;
> @@ -4591,7 +4674,9 @@ guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count)
> return ERR_PTR(-ENOMEM);
>
> guc = &siblings[0]->gt->uc.guc;
> - sched_engine = guc_to_sched_engine(guc, GUC_SUBMIT_ENGINE_SINGLE_LRC);
> + sched_engine = guc_to_sched_engine(guc, (flags & FORCE_VIRTUAL) ?
> + GUC_SUBMIT_ENGINE_MULTI_LRC :
> + GUC_SUBMIT_ENGINE_SINGLE_LRC);
>
> ve->base.i915 = siblings[0]->i915;
> ve->base.gt = siblings[0]->gt;
> diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
> index ef72e07fe08c..a16f0f8908de 100644
> --- a/include/uapi/drm/i915_drm.h
> +++ b/include/uapi/drm/i915_drm.h
> @@ -1821,6 +1821,7 @@ struct drm_i915_gem_context_param {
> * Extensions:
> * i915_context_engines_load_balance (I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE)
> * i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND)
> + * i915_context_engines_parallel_submit (I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT)
> */
> #define I915_CONTEXT_PARAM_ENGINES 0xa
>
> @@ -2046,6 +2047,132 @@ struct i915_context_engines_bond {
> struct i915_engine_class_instance engines[N__]; \
> } __attribute__((packed)) name__
>
> +/**
> + * struct i915_context_engines_parallel_submit - Configure engine for
> + * parallel submission.
> + *
> + * Setup a slot in the context engine map to allow multiple BBs to be submitted
> + * in a single execbuf IOCTL. Those BBs will then be scheduled to run on the GPU
> + * in parallel. Multiple hardware contexts are created internally in the i915
> + * run these BBs. Once a slot is configured for N BBs only N BBs can be
> + * submitted in each execbuf IOCTL and this is implicit behavior e.g. The user
> + * doesn't tell the execbuf IOCTL there are N BBs, the execbuf IOCTL knows how
> + * many BBs there are based on the slot's configuration. The N BBs are the last
> + * N buffer objects or first N if I915_EXEC_BATCH_FIRST is set.
> + *
> + * The default placement behavior is to create implicit bonds between each
> + * context if each context maps to more than 1 physical engine (e.g. context is
> + * a virtual engine). Also we only allow contexts of same engine class and these
> + * contexts must be in logically contiguous order. Examples of the placement
> + * behavior described below. Lastly, the default is to not allow BBs to
> + * preempted mid BB rather insert coordinated preemption on all hardware
> + * contexts between each set of BBs. Flags may be added in the future to change
> + * both of these default behaviors.
> + *
> + * Returns -EINVAL if hardware context placement configuration is invalid or if
> + * the placement configuration isn't supported on the platform / submission
> + * interface.
> + * Returns -ENODEV if extension isn't supported on the platform / submission
> + * interface.
> + *
> + * .. code-block:: none
> + *
> + * Example 1 pseudo code:
> + * CS[X] = generic engine of same class, logical instance X
> + * INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE
> + * set_engines(INVALID)
> + * set_parallel(engine_index=0, width=2, num_siblings=1,
> + * engines=CS[0],CS[1])
> + *
> + * Results in the following valid placement:
> + * CS[0], CS[1]
> + *
> + * Example 2 pseudo code:
> + * CS[X] = generic engine of same class, logical instance X
> + * INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE
> + * set_engines(INVALID)
> + * set_parallel(engine_index=0, width=2, num_siblings=2,
> + * engines=CS[0],CS[2],CS[1],CS[3])
> + *
> + * Results in the following valid placements:
> + * CS[0], CS[1]
> + * CS[2], CS[3]
> + *
> + * This can also be thought of as 2 virtual engines described by 2-D array
> + * in the engines the field with bonds placed between each index of the
> + * virtual engines. e.g. CS[0] is bonded to CS[1], CS[2] is bonded to
> + * CS[3].
> + * VE[0] = CS[0], CS[2]
> + * VE[1] = CS[1], CS[3]
> + *
> + * Example 3 pseudo code:
> + * CS[X] = generic engine of same class, logical instance X
> + * INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE
> + * set_engines(INVALID)
> + * set_parallel(engine_index=0, width=2, num_siblings=2,
> + * engines=CS[0],CS[1],CS[1],CS[3])
> + *
> + * Results in the following valid and invalid placements:
> + * CS[0], CS[1]
> + * CS[1], CS[3] - Not logical contiguous, return -EINVAL
> + */
> +struct i915_context_engines_parallel_submit {
> + /**
> + * @base: base user extension.
> + */
> + struct i915_user_extension base;
> +
> + /**
> + * @engine_index: slot for parallel engine
> + */
> + __u16 engine_index;
> +
> + /**
> + * @width: number of contexts per parallel engine
> + */
> + __u16 width;
> +
> + /**
> + * @num_siblings: number of siblings per context
> + */
> + __u16 num_siblings;
> +
> + /**
> + * @mbz16: reserved for future use; must be zero
> + */
> + __u16 mbz16;
> +
> + /**
> + * @flags: all undefined flags must be zero, currently not defined flags
> + */
> + __u64 flags;
> +
> + /**
> + * @mbz64: reserved for future use; must be zero
> + */
> + __u64 mbz64[3];
> +
> + /**
> + * @engines: 2-d array of engine instances to configure parallel engine
> + *
> + * length = width (i) * num_siblings (j)
> + * index = j + i * num_siblings
> + */
> + struct i915_engine_class_instance engines[0];
> +
> +} __packed;
> +
> +#define I915_DEFINE_CONTEXT_ENGINES_PARALLEL_SUBMIT(name__, N__) struct { \
> + struct i915_user_extension base; \
> + __u16 engine_index; \
> + __u16 width; \
> + __u16 num_siblings; \
> + __u16 mbz16; \
> + __u64 flags; \
> + __u64 mbz64[3]; \
> + struct i915_engine_class_instance engines[N__]; \
> +} __attribute__((packed)) name__
> +
> /**
> * DOC: Context Engine Map uAPI
> *
> @@ -2105,6 +2232,7 @@ struct i915_context_param_engines {
> __u64 extensions; /* linked chain of extension blocks, 0 terminates */
> #define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */
> #define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */
> +#define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */
> struct i915_engine_class_instance engines[0];
> } __attribute__((packed));
>
> --
> 2.28.0
>
--
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch
next prev parent reply other threads:[~2021-08-09 16:37 UTC|newest]
Thread overview: 111+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-03 22:28 [Intel-gfx] [PATCH 00/46] Parallel submission aka multi-bb execbuf Matthew Brost
2021-08-03 22:28 ` [Intel-gfx] [PATCH 01/46] drm/i915/guc: Allow flexible number of context ids Matthew Brost
2021-08-03 22:28 ` [Intel-gfx] [PATCH 02/46] drm/i915/guc: Connect the number of guc_ids to debugfs Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 03/46] drm/i915/guc: Don't return -EAGAIN to user when guc_ids exhausted Matthew Brost
2021-08-05 8:27 ` Daniel Vetter
2021-08-03 22:29 ` [Intel-gfx] [PATCH 04/46] drm/i915/guc: Don't allow requests not ready to consume all guc_ids Matthew Brost
2021-08-05 8:29 ` Daniel Vetter
2021-08-03 22:29 ` [Intel-gfx] [PATCH 05/46] drm/i915/guc: Introduce guc_submit_engine object Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 06/46] drm/i915/guc: Check return of __xa_store when registering a context Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 07/46] drm/i915/guc: Non-static lrc descriptor registration buffer Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 08/46] drm/i915/guc: Take GT PM ref when deregistering context Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 09/46] drm/i915: Add GT PM unpark worker Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 10/46] drm/i915/guc: Take engine PM when a context is pinned with GuC submission Matthew Brost
2021-08-09 14:23 ` Daniel Vetter
2021-08-09 18:11 ` Matthew Brost
2021-08-10 6:43 ` Daniel Vetter
2021-08-10 21:29 ` Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 11/46] drm/i915/guc: Don't call switch_to_kernel_context " Matthew Brost
2021-08-09 14:27 ` Daniel Vetter
2021-08-09 18:20 ` Matthew Brost
2021-08-10 6:47 ` Daniel Vetter
2021-08-11 17:47 ` Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 12/46] drm/i915/guc: Selftest for GuC flow control Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 13/46] drm/i915: Add logical engine mapping Matthew Brost
2021-08-09 14:28 ` Daniel Vetter
2021-08-09 18:28 ` Matthew Brost
2021-08-10 6:49 ` Daniel Vetter
2021-08-03 22:29 ` [Intel-gfx] [PATCH 14/46] drm/i915: Expose logical engine instance to user Matthew Brost
2021-08-09 14:30 ` Daniel Vetter
2021-08-09 18:37 ` Matthew Brost
2021-08-10 6:53 ` Daniel Vetter
2021-08-11 17:55 ` Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 15/46] drm/i915/guc: Introduce context parent-child relationship Matthew Brost
2021-08-09 14:37 ` Daniel Vetter
2021-08-09 14:40 ` Daniel Vetter
2021-08-09 18:45 ` Matthew Brost
2021-08-09 18:44 ` Matthew Brost
2021-08-10 8:45 ` Daniel Vetter
2021-08-03 22:29 ` [Intel-gfx] [PATCH 16/46] drm/i915/guc: Implement GuC parent-child context pin / unpin functions Matthew Brost
2021-08-09 15:17 ` Daniel Vetter
2021-08-09 18:58 ` Matthew Brost
2021-08-10 8:53 ` Daniel Vetter
2021-08-10 9:07 ` Daniel Vetter
2021-08-11 18:06 ` Matthew Brost
2021-08-12 14:45 ` Daniel Vetter
2021-08-12 14:52 ` Daniel Vetter
2021-08-11 18:23 ` Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 17/46] drm/i915/guc: Add multi-lrc context registration Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 18/46] drm/i915/guc: Ensure GuC schedule operations do not operate on child contexts Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 19/46] drm/i915/guc: Assign contexts in parent-child relationship consecutive guc_ids Matthew Brost
2021-08-09 15:31 ` Daniel Vetter
2021-08-09 19:03 ` Matthew Brost
2021-08-10 9:12 ` Daniel Vetter
2021-08-03 22:29 ` [Intel-gfx] [PATCH 20/46] drm/i915/guc: Add hang check to GuC submit engine Matthew Brost
2021-08-09 15:35 ` Daniel Vetter
2021-08-09 19:05 ` Matthew Brost
2021-08-10 9:18 ` Daniel Vetter
2021-08-03 22:29 ` [Intel-gfx] [PATCH 21/46] drm/i915/guc: Add guc_child_context_destroy Matthew Brost
2021-08-09 15:36 ` Daniel Vetter
2021-08-09 19:06 ` Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 22/46] drm/i915/guc: Implement multi-lrc submission Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 23/46] drm/i915/guc: Insert submit fences between requests in parent-child relationship Matthew Brost
2021-08-09 16:32 ` Daniel Vetter
2021-08-09 16:39 ` Matthew Brost
2021-08-09 17:03 ` Daniel Vetter
2021-08-03 22:29 ` [Intel-gfx] [PATCH 24/46] drm/i915/guc: Implement multi-lrc reset Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 25/46] drm/i915/guc: Update debugfs for GuC multi-lrc Matthew Brost
2021-08-09 16:36 ` Daniel Vetter
2021-08-09 19:13 ` Matthew Brost
2021-08-10 9:23 ` Daniel Vetter
2021-08-10 9:27 ` Daniel Vetter
2021-08-10 17:29 ` Matthew Brost
2021-08-11 10:04 ` Daniel Vetter
2021-08-11 17:35 ` Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 26/46] drm/i915: Connect UAPI to GuC multi-lrc interface Matthew Brost
2021-08-09 16:37 ` Daniel Vetter [this message]
2021-08-03 22:29 ` [Intel-gfx] [PATCH 27/46] drm/i915/doc: Update parallel submit doc to point to i915_drm.h Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 28/46] drm/i915/guc: Add basic GuC multi-lrc selftest Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 29/46] drm/i915/guc: Extend GuC flow control selftest for multi-lrc Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 30/46] drm/i915/guc: Implement no mid batch preemption " Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 31/46] drm/i915: Move secure execbuf check to execbuf2 Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 32/46] drm/i915: Move input/exec fence handling to i915_gem_execbuffer2 Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 33/46] drm/i915: Move output " Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 34/46] drm/i915: Return output fence from i915_gem_do_execbuffer Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 35/46] drm/i915: Store batch index in struct i915_execbuffer Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 36/46] drm/i915: Allow callers of i915_gem_do_execbuffer to override the batch index Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 37/46] drm/i915: Teach execbuf there can be more than one batch in the objects list Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 38/46] drm/i915: Only track object dependencies on first request Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 39/46] drm/i915: Force parallel contexts to use copy engine for reloc Matthew Brost
2021-08-09 16:39 ` Daniel Vetter
2021-08-03 22:29 ` [Intel-gfx] [PATCH 40/46] drm/i915: Multi-batch execbuffer2 Matthew Brost
2021-08-09 17:02 ` Daniel Vetter
2021-08-03 22:29 ` [Intel-gfx] [PATCH 41/46] drm/i915: Eliminate unnecessary VMA calls for multi-BB submission Matthew Brost
2021-08-09 17:07 ` Daniel Vetter
2021-08-09 17:12 ` Daniel Vetter
2021-08-03 22:29 ` [Intel-gfx] [PATCH 42/46] drm/i915: Hold all parallel requests until last request, properly handle error Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 43/46] drm/i915/guc: Handle errors in multi-lrc requests Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 44/46] drm/i915: Enable multi-bb execbuf Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 45/46] drm/i915/execlists: Weak parallel submission support for execlists Matthew Brost
2021-08-03 22:29 ` [Intel-gfx] [PATCH 46/46] drm/i915/guc: Add delay before disabling scheduling on contexts Matthew Brost
2021-08-09 17:17 ` Daniel Vetter
2021-08-09 19:32 ` Matthew Brost
2021-08-11 9:55 ` Daniel Vetter
2021-08-11 17:43 ` Matthew Brost
2021-08-12 14:04 ` Daniel Vetter
2021-08-12 19:26 ` Daniel Vetter
2021-08-03 22:51 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for Parallel submission aka multi-bb execbuf (rev2) Patchwork
2021-08-03 22:53 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2021-08-03 22:57 ` [Intel-gfx] ✗ Fi.CI.DOCS: " Patchwork
2021-08-03 23:19 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2021-08-05 3:53 ` [Intel-gfx] ✓ Fi.CI.IGT: " Patchwork
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=YRFZwPSkrGqh4hpJ@phenom.ffwll.local \
--to=daniel@ffwll.ch \
--cc=dri-devel@lists.freedesktop.org \
--cc=intel-gfx@lists.freedesktop.org \
--cc=matthew.brost@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox