Remove old GuC stage descriptor, add LRC descriptor which will be used by the new GuC interface implemented in this patch series.

v2: (John Harrison) - s/lrc/LRC/g

Cc: John Harrison john.c.harrison@intel.com Signed-off-by: Matthew Brost matthew.brost@intel.com Reviewed-by: John Harrison John.C.Harrison@Intel.com --- drivers/gpu/drm/i915/gt/uc/intel_guc.h | 4 +- drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h | 65 ----------------- .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 72 ++++++------------- 3 files changed, 25 insertions(+), 116 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index 72e4653222e2..2625d2d5959f 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -43,8 +43,8 @@ struct intel_guc { struct i915_vma *ads_vma; struct __guc_ads_blob *ads_blob;

- struct i915_vma *stage_desc_pool; - void *stage_desc_pool_vaddr; + struct i915_vma *lrc_desc_pool; + void *lrc_desc_pool_vaddr;

/* Control params for fw initialization */ u32 params[GUC_CTL_MAX_DWORDS]; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h index 3e060d5958cc..3489b390ae77 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h @@ -26,9 +26,6 @@ #define GUC_CLIENT_PRIORITY_NORMAL 3 #define GUC_CLIENT_PRIORITY_NUM 4

-#define GUC_MAX_STAGE_DESCRIPTORS 1024 -#define GUC_INVALID_STAGE_ID GUC_MAX_STAGE_DESCRIPTORS - #define GUC_MAX_LRC_DESCRIPTORS 65535 #define GUC_INVALID_LRC_ID GUC_MAX_LRC_DESCRIPTORS

@@ -181,68 +178,6 @@ struct guc_process_desc { u32 reserved[30]; } __packed;

-/* engine id and context id is packed into guc_execlist_context.context_id*/ -#define GUC_ELC_CTXID_OFFSET 0 -#define GUC_ELC_ENGINE_OFFSET 29 - -/* The execlist context including software and HW information */ -struct guc_execlist_context { - u32 context_desc; - u32 context_id; - u32 ring_status; - u32 ring_lrca; - u32 ring_begin; - u32 ring_end; - u32 ring_next_free_location; - u32 ring_current_tail_pointer_value; - u8 engine_state_submit_value; - u8 engine_state_wait_value; - u16 pagefault_count; - u16 engine_submit_queue_count; -} __packed; - -/* - * This structure describes a stage set arranged for a particular communication - * between uKernel (GuC) and Driver (KMD). Technically, this is known as a - * "GuC Context descriptor" in the specs, but we use the term "stage descriptor" - * to avoid confusion with all the other things already named "context" in the - * driver. A static pool of these descriptors are stored inside a GEM object - * (stage_desc_pool) which is held for the entire lifetime of our interaction - * with the GuC, being allocated before the GuC is loaded with its firmware. - */ -struct guc_stage_desc { - u32 sched_common_area; - u32 stage_id; - u32 pas_id; - u8 engines_used; - u64 db_trigger_cpu; - u32 db_trigger_uk; - u64 db_trigger_phy; - u16 db_id; - - struct guc_execlist_context lrc[GUC_MAX_ENGINES_NUM]; - - u8 attribute; - - u32 priority; - - u32 wq_sampled_tail_offset; - u32 wq_total_submit_enqueues; - - u32 process_desc; - u32 wq_addr; - u32 wq_size; - - u32 engine_presence; - - u8 engine_suspended; - - u8 reserved0[3]; - u64 reserved1[1]; - - u64 desc_private; -} __packed; - #define CONTEXT_REGISTRATION_FLAG_KMD BIT(0)

#define CONTEXT_POLICY_DEFAULT_EXECUTION_QUANTUM_US 1000000 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 e9c237b18692..ed5d8ab3624f 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -65,57 +65,35 @@ static inline struct i915_priolist *to_priolist(struct rb_node *rb) return rb_entry(rb, struct i915_priolist, node); }

-static struct guc_stage_desc *__get_stage_desc(struct intel_guc *guc, u32 id) +/* Future patches will use this function */ +__maybe_unused +static struct guc_lrc_desc *__get_lrc_desc(struct intel_guc *guc, u32 index) { - struct guc_stage_desc *base = guc->stage_desc_pool_vaddr; + struct guc_lrc_desc *base = guc->lrc_desc_pool_vaddr;

- return &base[id]; -} - -static int guc_stage_desc_pool_create(struct intel_guc *guc) -{ - u32 size = PAGE_ALIGN(sizeof(struct guc_stage_desc) * - GUC_MAX_STAGE_DESCRIPTORS); + GEM_BUG_ON(index >= GUC_MAX_LRC_DESCRIPTORS);

- return intel_guc_allocate_and_map_vma(guc, size, &guc->stage_desc_pool, - &guc->stage_desc_pool_vaddr); + return &base[index]; }

-static void guc_stage_desc_pool_destroy(struct intel_guc *guc) -{ - i915_vma_unpin_and_release(&guc->stage_desc_pool, I915_VMA_RELEASE_MAP); -} - -/* - * Initialise/clear the stage descriptor shared with the GuC firmware. - * - * This descriptor tells the GuC where (in GGTT space) to find the important - * data structures related to work submission (process descriptor, write queue, - * etc). - */ -static void guc_stage_desc_init(struct intel_guc *guc) +static int guc_lrc_desc_pool_create(struct intel_guc *guc) { - struct guc_stage_desc *desc; - - /* we only use 1 stage desc, so hardcode it to 0 */ - desc = __get_stage_desc(guc, 0); - memset(desc, 0, sizeof(*desc)); - - desc->attribute = GUC_STAGE_DESC_ATTR_ACTIVE | - GUC_STAGE_DESC_ATTR_KERNEL; + u32 size; + int ret;

- desc->stage_id = 0; - desc->priority = GUC_CLIENT_PRIORITY_KMD_NORMAL; + size = PAGE_ALIGN(sizeof(struct guc_lrc_desc) * + GUC_MAX_LRC_DESCRIPTORS); + ret = intel_guc_allocate_and_map_vma(guc, size, &guc->lrc_desc_pool, + (void **)&guc->lrc_desc_pool_vaddr); + if (ret) + return ret;

- desc->wq_size = GUC_WQ_SIZE; + return 0; }

-static void guc_stage_desc_fini(struct intel_guc *guc) +static void guc_lrc_desc_pool_destroy(struct intel_guc *guc) { - struct guc_stage_desc *desc; - - desc = __get_stage_desc(guc, 0); - memset(desc, 0, sizeof(*desc)); + i915_vma_unpin_and_release(&guc->lrc_desc_pool, I915_VMA_RELEASE_MAP); }

static void guc_add_request(struct intel_guc *guc, struct i915_request *rq) @@ -410,26 +388,25 @@ int intel_guc_submission_init(struct intel_guc *guc) { int ret;

- if (guc->stage_desc_pool) + if (guc->lrc_desc_pool) return 0;

- ret = guc_stage_desc_pool_create(guc); + ret = guc_lrc_desc_pool_create(guc); if (ret) return ret; /* * Keep static analysers happy, let them know that we allocated the * vma after testing that it didn't exist earlier. */ - GEM_BUG_ON(!guc->stage_desc_pool); + GEM_BUG_ON(!guc->lrc_desc_pool);

return 0; }

void intel_guc_submission_fini(struct intel_guc *guc) { - if (guc->stage_desc_pool) { - guc_stage_desc_pool_destroy(guc); - } + if (guc->lrc_desc_pool) + guc_lrc_desc_pool_destroy(guc); }

static int guc_context_alloc(struct intel_context *ce) @@ -695,7 +672,6 @@ int intel_guc_submission_setup(struct intel_engine_cs *engine)

void intel_guc_submission_enable(struct intel_guc *guc) { - guc_stage_desc_init(guc); }

void intel_guc_submission_disable(struct intel_guc *guc) @@ -705,8 +681,6 @@ void intel_guc_submission_disable(struct intel_guc *guc) GEM_BUG_ON(gt->awake); /* GT should be parked first */

/* Note: By the time we're here, GuC may have already been reset */ - - guc_stage_desc_fini(guc); }

static bool __guc_submission_selected(struct intel_guc *guc)

Implement GuC submission tasklet for new interface. The new GuC interface uses H2G to submit contexts to the GuC. Since H2G use a single channel, a single tasklet is used for the submission path.

Also the per engine interrupt handler has been updated to disable the rescheduling of the physical engine tasklet, when using GuC scheduling, as the physical engine tasklet is no longer used.

In this patch the field, guc_id, has been added to intel_context and is not assigned. Patches later in the series will assign this value.

v2: (John Harrison) - Clean up some comments v3: (John Harrison) - More comment cleanups

Cc: John Harrison john.c.harrison@intel.com Signed-off-by: Matthew Brost matthew.brost@intel.com Reviewed-by: John Harrison John.C.Harrison@Intel.com --- drivers/gpu/drm/i915/gt/intel_context_types.h | 9 + drivers/gpu/drm/i915/gt/uc/intel_guc.h | 4 + .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 231 +++++++++--------- 3 files changed, 127 insertions(+), 117 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index 90026c177105..6d99631d19b9 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -137,6 +137,15 @@ struct intel_context { struct intel_sseu sseu;

u8 wa_bb_page; /* if set, page num reserved for context workarounds */ + + /* GuC scheduling state flags that do not require a lock. */ + atomic_t guc_sched_state_no_lock; + + /* + * GuC LRC descriptor ID - Not assigned in this patch but future patches + * in the series will. + */ + u16 guc_id; };

#endif /* __INTEL_CONTEXT_TYPES__ */ diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index 35783558d261..8c7b92f699f1 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -30,6 +30,10 @@ struct intel_guc { struct intel_guc_log log; struct intel_guc_ct ct;

+ /* Global engine used to submit requests to GuC */ + struct i915_sched_engine *sched_engine; + struct i915_request *stalled_request; + /* intel_guc_recv interrupt related state */ spinlock_t irq_lock; unsigned int msg_enabled_mask; 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 23a94a896a0b..ca0717166a27 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 +60,31 @@

#define GUC_REQUEST_SIZE 64 /* bytes */

+/* + * Below is a set of functions which control the GuC scheduling state which do + * not require a lock as all state transitions are mutually exclusive. i.e. It + * is not possible for the context pinning code and submission, for the same + * context, to be executing simultaneously. We still need an atomic as it is + * possible for some of the bits to changing at the same time though. + */ +#define SCHED_STATE_NO_LOCK_ENABLED BIT(0) +static inline bool context_enabled(struct intel_context *ce) +{ + return (atomic_read(&ce->guc_sched_state_no_lock) & + SCHED_STATE_NO_LOCK_ENABLED); +} + +static inline void set_context_enabled(struct intel_context *ce) +{ + atomic_or(SCHED_STATE_NO_LOCK_ENABLED, &ce->guc_sched_state_no_lock); +} + +static inline void clr_context_enabled(struct intel_context *ce) +{ + atomic_and((u32)~SCHED_STATE_NO_LOCK_ENABLED, + &ce->guc_sched_state_no_lock); +} + static inline struct i915_priolist *to_priolist(struct rb_node *rb) { return rb_entry(rb, struct i915_priolist, node); @@ -122,37 +147,29 @@ static inline void set_lrc_desc_registered(struct intel_guc *guc, u32 id, xa_store_irq(&guc->context_lookup, id, ce, GFP_ATOMIC); }

-static void guc_add_request(struct intel_guc *guc, struct i915_request *rq) +static int guc_add_request(struct intel_guc *guc, struct i915_request *rq) { - /* Leaving stub as this function will be used in future patches */ -} + int err; + struct intel_context *ce = rq->context; + u32 action[3]; + int len = 0; + bool enabled = context_enabled(ce);

-/* - * When we're doing submissions using regular execlists backend, writing to - * ELSP from CPU side is enough to make sure that writes to ringbuffer pages - * pinned in mappable aperture portion of GGTT are visible to command streamer. - * Writes done by GuC on our behalf are not guaranteeing such ordering, - * therefore, to ensure the flush, we're issuing a POSTING READ. - */ -static void flush_ggtt_writes(struct i915_vma *vma) -{ - if (i915_vma_is_map_and_fenceable(vma)) - intel_uncore_posting_read_fw(vma->vm->gt->uncore, - GUC_STATUS); -} + if (!enabled) { + action[len++] = INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_SET; + action[len++] = ce->guc_id; + action[len++] = GUC_CONTEXT_ENABLE; + } else { + action[len++] = INTEL_GUC_ACTION_SCHED_CONTEXT; + action[len++] = ce->guc_id; + }

-static void guc_submit(struct intel_engine_cs *engine, - struct i915_request **out, - struct i915_request **end) -{ - struct intel_guc *guc = &engine->gt->uc.guc; + err = intel_guc_send_nb(guc, action, len);

- do { - struct i915_request *rq = *out++; + if (!enabled && !err) + set_context_enabled(ce);

- flush_ggtt_writes(rq->ring->vma); - guc_add_request(guc, rq); - } while (out != end); + return err; }

static inline int rq_prio(const struct i915_request *rq) @@ -160,125 +177,88 @@ static inline int rq_prio(const struct i915_request *rq) return rq->sched.attr.priority; }

-static struct i915_request *schedule_in(struct i915_request *rq, int idx) +static int guc_dequeue_one_context(struct intel_guc *guc) { - trace_i915_request_in(rq, idx); - - /* - * Currently we are not tracking the rq->context being inflight - * (ce->inflight = rq->engine). It is only used by the execlists - * backend at the moment, a similar counting strategy would be - * required if we generalise the inflight tracking. - */ - - __intel_gt_pm_get(rq->engine->gt); - return i915_request_get(rq); -} - -static void schedule_out(struct i915_request *rq) -{ - trace_i915_request_out(rq); - - intel_gt_pm_put_async(rq->engine->gt); - i915_request_put(rq); -} - -static void __guc_dequeue(struct intel_engine_cs *engine) -{ - struct intel_engine_execlists * const execlists = &engine->execlists; - struct i915_sched_engine * const sched_engine = engine->sched_engine; - struct i915_request **first = execlists->inflight; - struct i915_request ** const last_port = first + execlists->port_mask; - struct i915_request *last = first[0]; - struct i915_request **port; + struct i915_sched_engine * const sched_engine = guc->sched_engine; + struct i915_request *last = NULL; bool submit = false; struct rb_node *rb; + int ret;

lockdep_assert_held(&sched_engine->lock);

- if (last) { - if (*++first) - return; - - last = NULL; + if (guc->stalled_request) { + submit = true; + last = guc->stalled_request; + goto resubmit; }

- /* - * We write directly into the execlists->inflight queue and don't use - * the execlists->pending queue, as we don't have a distinct switch - * event. - */ - port = first; while ((rb = rb_first_cached(&sched_engine->queue))) { struct i915_priolist *p = to_priolist(rb); struct i915_request *rq, *rn;

priolist_for_each_request_consume(rq, rn, p) { - if (last && rq->context != last->context) { - if (port == last_port) - goto done; - - *port = schedule_in(last, - port - execlists->inflight); - port++; - } + if (last && rq->context != last->context) + goto done;

list_del_init(&rq->sched.link); + __i915_request_submit(rq); - submit = true; + + trace_i915_request_in(rq, 0); last = rq; + submit = true; }

rb_erase_cached(&p->node, &sched_engine->queue); i915_priolist_free(p); } done: - sched_engine->queue_priority_hint = - rb ? to_priolist(rb)->priority : INT_MIN; if (submit) { - *port = schedule_in(last, port - execlists->inflight); - *++port = NULL; - guc_submit(engine, first, port); + last->context->lrc_reg_state[CTX_RING_TAIL] = + intel_ring_set_tail(last->ring, last->tail); +resubmit: + /* + * We only check for -EBUSY here even though it is possible for + * -EDEADLK to be returned. If -EDEADLK is returned, the GuC has + * died and a full GT reset needs to be done. The hangcheck will + * eventually detect that the GuC has died and trigger this + * reset so no need to handle -EDEADLK here. + */ + ret = guc_add_request(guc, last); + if (ret == -EBUSY) { + tasklet_schedule(&sched_engine->tasklet); + guc->stalled_request = last; + return false; + } } - execlists->active = execlists->inflight; + + guc->stalled_request = NULL; + return submit; }

static void guc_submission_tasklet(struct tasklet_struct *t) { struct i915_sched_engine *sched_engine = from_tasklet(sched_engine, t, tasklet); - struct intel_engine_cs * const engine = sched_engine->private_data; - struct intel_engine_execlists * const execlists = &engine->execlists; - struct i915_request **port, *rq; unsigned long flags; + bool loop;

- spin_lock_irqsave(&engine->sched_engine->lock, flags); - - for (port = execlists->inflight; (rq = *port); port++) { - if (!i915_request_completed(rq)) - break; - - schedule_out(rq); - } - if (port != execlists->inflight) { - int idx = port - execlists->inflight; - int rem = ARRAY_SIZE(execlists->inflight) - idx; - memmove(execlists->inflight, port, rem * sizeof(*port)); - } + spin_lock_irqsave(&sched_engine->lock, flags);

- __guc_dequeue(engine); + do { + loop = guc_dequeue_one_context(sched_engine->private_data); + } while (loop);

- i915_sched_engine_reset_on_empty(engine->sched_engine); + i915_sched_engine_reset_on_empty(sched_engine);

- spin_unlock_irqrestore(&engine->sched_engine->lock, flags); + spin_unlock_irqrestore(&sched_engine->lock, flags); }

static void cs_irq_handler(struct intel_engine_cs *engine, u16 iir) { - if (iir & GT_RENDER_USER_INTERRUPT) { + if (iir & GT_RENDER_USER_INTERRUPT) intel_engine_signal_breadcrumbs(engine); - tasklet_hi_schedule(&engine->sched_engine->tasklet); - } }

static void guc_reset_prepare(struct intel_engine_cs *engine) @@ -349,6 +329,10 @@ static void guc_reset_cancel(struct intel_engine_cs *engine) struct rb_node *rb; unsigned long flags;

+ /* Can be called during boot if GuC fails to load */ + if (!engine->gt) + return; + ENGINE_TRACE(engine, "\n");

/* @@ -433,8 +417,11 @@ int intel_guc_submission_init(struct intel_guc *guc)

void intel_guc_submission_fini(struct intel_guc *guc) { - if (guc->lrc_desc_pool) - guc_lrc_desc_pool_destroy(guc); + if (!guc->lrc_desc_pool) + return; + + guc_lrc_desc_pool_destroy(guc); + i915_sched_engine_put(guc->sched_engine); }

static int guc_context_alloc(struct intel_context *ce) @@ -499,32 +486,32 @@ static int guc_request_alloc(struct i915_request *request) return 0; }

-static inline void queue_request(struct intel_engine_cs *engine, +static inline void queue_request(struct i915_sched_engine *sched_engine, struct i915_request *rq, int prio) { GEM_BUG_ON(!list_empty(&rq->sched.link)); list_add_tail(&rq->sched.link, - i915_sched_lookup_priolist(engine->sched_engine, prio)); + i915_sched_lookup_priolist(sched_engine, prio)); set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags); }

static void guc_submit_request(struct i915_request *rq) { - struct intel_engine_cs *engine = rq->engine; + struct i915_sched_engine *sched_engine = rq->engine->sched_engine; unsigned long flags;

/* Will be called from irq-context when using foreign fences. */ - spin_lock_irqsave(&engine->sched_engine->lock, flags); + spin_lock_irqsave(&sched_engine->lock, flags);

- queue_request(engine, rq, rq_prio(rq)); + queue_request(sched_engine, rq, rq_prio(rq));

- GEM_BUG_ON(i915_sched_engine_is_empty(engine->sched_engine)); + GEM_BUG_ON(i915_sched_engine_is_empty(sched_engine)); GEM_BUG_ON(list_empty(&rq->sched.link));

- tasklet_hi_schedule(&engine->sched_engine->tasklet); + tasklet_hi_schedule(&sched_engine->tasklet);

- spin_unlock_irqrestore(&engine->sched_engine->lock, flags); + spin_unlock_irqrestore(&sched_engine->lock, flags); }

static void sanitize_hwsp(struct intel_engine_cs *engine) @@ -602,8 +589,6 @@ static void guc_release(struct intel_engine_cs *engine) { engine->sanitize = NULL; /* no longer in control, nothing to sanitize */

- tasklet_kill(&engine->sched_engine->tasklet); - intel_engine_cleanup_common(engine); lrc_fini_wa_ctx(engine); } @@ -674,6 +659,7 @@ static inline void guc_default_irqs(struct intel_engine_cs *engine) int intel_guc_submission_setup(struct intel_engine_cs *engine) { struct drm_i915_private *i915 = engine->i915; + struct intel_guc *guc = &engine->gt->uc.guc;

/* * The setup relies on several assumptions (e.g. irqs always enabled) @@ -681,7 +667,18 @@ int intel_guc_submission_setup(struct intel_engine_cs *engine) */ GEM_BUG_ON(GRAPHICS_VER(i915) < 11);

- tasklet_setup(&engine->sched_engine->tasklet, guc_submission_tasklet); + if (!guc->sched_engine) { + guc->sched_engine = i915_sched_engine_create(ENGINE_VIRTUAL); + if (!guc->sched_engine) + return -ENOMEM; + + guc->sched_engine->schedule = i915_schedule; + guc->sched_engine->private_data = guc; + tasklet_setup(&guc->sched_engine->tasklet, + guc_submission_tasklet); + } + i915_sched_engine_put(engine->sched_engine); + engine->sched_engine = i915_sched_engine_get(guc->sched_engine);

guc_default_vfuncs(engine); guc_default_irqs(engine);

Implement GuC context operations which includes GuC specific operations alloc, pin, unpin, and destroy.

v2: (Daniel Vetter) - Use msleep_interruptible rather than cond_resched in busy loop (Michal) - Remove C++ style comment v3: (Matthew Brost) - Drop GUC_ID_START (John Harrison) - Fix a bunch of typos - Use drm_err rather than drm_dbg for G2H errors (Daniele) - Fix ;; typo - Clean up sched state functions - Add lockdep for guc_id functions - Don't call __release_guc_id when guc_id is invalid - Use MISSING_CASE - Add comment in guc_context_pin - Use shorter path to rpm (Daniele / CI) - Don't call release_guc_id on an invalid guc_id in destroy v4: (Daniel Vetter) - Add FIXME comment

Signed-off-by: John Harrison John.C.Harrison@Intel.com Signed-off-by: Matthew Brost matthew.brost@intel.com Reviewed-by: John Harrison John.C.Harrison@Intel.com --- drivers/gpu/drm/i915/gt/intel_context.c | 5 + drivers/gpu/drm/i915/gt/intel_context_types.h | 22 +- drivers/gpu/drm/i915/gt/intel_lrc_reg.h | 1 - drivers/gpu/drm/i915/gt/uc/intel_guc.h | 47 ++ drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c | 4 + .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 670 ++++++++++++++++-- drivers/gpu/drm/i915/i915_reg.h | 1 + drivers/gpu/drm/i915/i915_request.c | 1 + 8 files changed, 696 insertions(+), 55 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index bd63813c8a80..32fd6647154b 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -384,6 +384,11 @@ intel_context_init(struct intel_context *ce, struct intel_engine_cs *engine)

mutex_init(&ce->pin_mutex);

+ spin_lock_init(&ce->guc_state.lock); + + ce->guc_id = GUC_INVALID_LRC_ID; + INIT_LIST_HEAD(&ce->guc_id_link); + i915_active_init(&ce->active, __intel_context_active, __intel_context_retire, 0); } diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index 6d99631d19b9..606c480aec26 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -96,6 +96,7 @@ struct intel_context { #define CONTEXT_BANNED 6 #define CONTEXT_FORCE_SINGLE_SUBMISSION 7 #define CONTEXT_NOPREEMPT 8 +#define CONTEXT_LRCA_DIRTY 9

struct { u64 timeout_us; @@ -138,14 +139,29 @@ struct intel_context {

u8 wa_bb_page; /* if set, page num reserved for context workarounds */

+ struct { + /** lock: protects everything in guc_state */ + spinlock_t lock; + /** + * sched_state: scheduling state of this context using GuC + * submission + */ + u8 sched_state; + } guc_state; + /* GuC scheduling state flags that do not require a lock. */ atomic_t guc_sched_state_no_lock;

+ /* GuC LRC descriptor ID */ + u16 guc_id; + + /* GuC LRC descriptor reference count */ + atomic_t guc_id_ref; + /* - * GuC LRC descriptor ID - Not assigned in this patch but future patches - * in the series will. + * GuC ID link - in list when unpinned but guc_id still valid in GuC */ - u16 guc_id; + struct list_head guc_id_link; };

#endif /* __INTEL_CONTEXT_TYPES__ */ diff --git a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h index 41e5350a7a05..49d4857ad9b7 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h +++ b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h @@ -87,7 +87,6 @@ #define GEN11_CSB_WRITE_PTR_MASK (GEN11_CSB_PTR_MASK << 0)

#define MAX_CONTEXT_HW_ID (1 << 21) /* exclusive */ -#define MAX_GUC_CONTEXT_HW_ID (1 << 20) /* exclusive */ #define GEN11_MAX_CONTEXT_HW_ID (1 << 11) /* exclusive */ /* in Gen12 ID 0x7FF is reserved to indicate idle */ #define GEN12_MAX_CONTEXT_HW_ID (GEN11_MAX_CONTEXT_HW_ID - 1) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index 8c7b92f699f1..7fd6c3e343e4 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -7,6 +7,7 @@ #define _INTEL_GUC_H_

#include <linux/xarray.h> +#include <linux/delay.h>

#include "intel_uncore.h" #include "intel_guc_fw.h" @@ -44,6 +45,14 @@ struct intel_guc { void (*disable)(struct intel_guc *guc); } interrupts;

+ /* + * contexts_lock protects the pool of free guc ids and a linked list of + * guc ids available to be stolen + */ + spinlock_t contexts_lock; + struct ida guc_ids; + struct list_head guc_id_list; + bool submission_selected;

struct i915_vma *ads_vma; @@ -101,6 +110,41 @@ intel_guc_send_and_receive(struct intel_guc *guc, const u32 *action, u32 len, response_buf, response_buf_size, 0); }

+static inline int intel_guc_send_busy_loop(struct intel_guc *guc, + const u32 *action, + u32 len, + bool loop) +{ + int err; + unsigned int sleep_period_ms = 1; + bool not_atomic = !in_atomic() && !irqs_disabled(); + + /* + * FIXME: Have caller pass in if we are in an atomic context to avoid + * using in_atomic(). It is likely safe here as we check for irqs + * disabled which basically all the spin locks in the i915 do but + * regardless this should be cleaned up. + */ + + /* No sleeping with spin locks, just busy loop */ + might_sleep_if(loop && not_atomic); + +retry: + err = intel_guc_send_nb(guc, action, len); + if (unlikely(err == -EBUSY && loop)) { + if (likely(not_atomic)) { + if (msleep_interruptible(sleep_period_ms)) + return -EINTR; + sleep_period_ms = sleep_period_ms << 1; + } else { + cpu_relax(); + } + goto retry; + } + + return err; +} + static inline void intel_guc_to_host_event_handler(struct intel_guc *guc) { intel_guc_ct_event_handler(&guc->ct); @@ -202,6 +246,9 @@ static inline void intel_guc_disable_msg(struct intel_guc *guc, u32 mask) int intel_guc_reset_engine(struct intel_guc *guc, struct intel_engine_cs *engine);

+int intel_guc_deregister_done_process_msg(struct intel_guc *guc, + const u32 *msg, u32 len); + void intel_guc_load_status(struct intel_guc *guc, struct drm_printer *p);

#endif diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c index 83ec60ea3f89..28ff82c5be45 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c @@ -928,6 +928,10 @@ static int ct_process_request(struct intel_guc_ct *ct, struct ct_incoming_msg *r case INTEL_GUC_ACTION_DEFAULT: ret = intel_guc_to_host_process_recv_msg(guc, payload, len); break; + case INTEL_GUC_ACTION_DEREGISTER_CONTEXT_DONE: + ret = intel_guc_deregister_done_process_msg(guc, payload, + len); + break; default: ret = -EOPNOTSUPP; break; 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 53b4a5eb4a85..463613a414d2 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -13,7 +13,9 @@ #include "gt/intel_gt.h" #include "gt/intel_gt_irq.h" #include "gt/intel_gt_pm.h" +#include "gt/intel_gt_requests.h" #include "gt/intel_lrc.h" +#include "gt/intel_lrc_reg.h" #include "gt/intel_mocs.h" #include "gt/intel_ring.h"

@@ -85,6 +87,72 @@ static inline void clr_context_enabled(struct intel_context *ce) &ce->guc_sched_state_no_lock); }

+/* + * Below is a set of functions which control the GuC scheduling state which + * require a lock, aside from the special case where the functions are called + * from guc_lrc_desc_pin(). In that case it isn't possible for any other code + * path to be executing on the context. + */ +#define SCHED_STATE_WAIT_FOR_DEREGISTER_TO_REGISTER BIT(0) +#define SCHED_STATE_DESTROYED BIT(1) +static inline void init_sched_state(struct intel_context *ce) +{ + /* Only should be called from guc_lrc_desc_pin() */ + atomic_set(&ce->guc_sched_state_no_lock, 0); + ce->guc_state.sched_state = 0; +} + +static inline bool +context_wait_for_deregister_to_register(struct intel_context *ce) +{ + return ce->guc_state.sched_state & + SCHED_STATE_WAIT_FOR_DEREGISTER_TO_REGISTER; +} + +static inline void +set_context_wait_for_deregister_to_register(struct intel_context *ce) +{ + /* Only should be called from guc_lrc_desc_pin() */ + ce->guc_state.sched_state |= + SCHED_STATE_WAIT_FOR_DEREGISTER_TO_REGISTER; +} + +static inline void +clr_context_wait_for_deregister_to_register(struct intel_context *ce) +{ + lockdep_assert_held(&ce->guc_state.lock); + ce->guc_state.sched_state &= + ~SCHED_STATE_WAIT_FOR_DEREGISTER_TO_REGISTER; +} + +static inline bool +context_destroyed(struct intel_context *ce) +{ + return ce->guc_state.sched_state & SCHED_STATE_DESTROYED; +} + +static inline void +set_context_destroyed(struct intel_context *ce) +{ + lockdep_assert_held(&ce->guc_state.lock); + ce->guc_state.sched_state |= SCHED_STATE_DESTROYED; +} + +static inline bool context_guc_id_invalid(struct intel_context *ce) +{ + return ce->guc_id == GUC_INVALID_LRC_ID; +} + +static inline void set_context_guc_id_invalid(struct intel_context *ce) +{ + ce->guc_id = GUC_INVALID_LRC_ID; +} + +static inline struct intel_guc *ce_to_guc(struct intel_context *ce) +{ + return &ce->engine->gt->uc.guc; +} + static inline struct i915_priolist *to_priolist(struct rb_node *rb) { return rb_entry(rb, struct i915_priolist, node); @@ -155,6 +223,9 @@ static int guc_add_request(struct intel_guc *guc, struct i915_request *rq) int len = 0; bool enabled = context_enabled(ce);

+ GEM_BUG_ON(!atomic_read(&ce->guc_id_ref)); + GEM_BUG_ON(context_guc_id_invalid(ce)); + if (!enabled) { action[len++] = INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_SET; action[len++] = ce->guc_id; @@ -417,6 +488,10 @@ int intel_guc_submission_init(struct intel_guc *guc)

xa_init_flags(&guc->context_lookup, XA_FLAGS_LOCK_IRQ);

+ spin_lock_init(&guc->contexts_lock); + INIT_LIST_HEAD(&guc->guc_id_list); + ida_init(&guc->guc_ids); + return 0; }

@@ -429,9 +504,308 @@ void intel_guc_submission_fini(struct intel_guc *guc) i915_sched_engine_put(guc->sched_engine); }

-static int guc_context_alloc(struct intel_context *ce) +static inline void queue_request(struct i915_sched_engine *sched_engine, + struct i915_request *rq, + int prio) { - return lrc_alloc(ce, ce->engine); + GEM_BUG_ON(!list_empty(&rq->sched.link)); + list_add_tail(&rq->sched.link, + i915_sched_lookup_priolist(sched_engine, prio)); + set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags); +} + +static int guc_bypass_tasklet_submit(struct intel_guc *guc, + struct i915_request *rq) +{ + int ret; + + __i915_request_submit(rq); + + trace_i915_request_in(rq, 0); + + guc_set_lrc_tail(rq); + ret = guc_add_request(guc, rq); + if (ret == -EBUSY) + guc->stalled_request = rq; + + return ret; +} + +static void guc_submit_request(struct i915_request *rq) +{ + struct i915_sched_engine *sched_engine = rq->engine->sched_engine; + struct intel_guc *guc = &rq->engine->gt->uc.guc; + unsigned long flags; + + /* Will be called from irq-context when using foreign fences. */ + spin_lock_irqsave(&sched_engine->lock, flags); + + if (guc->stalled_request || !i915_sched_engine_is_empty(sched_engine)) + queue_request(sched_engine, rq, rq_prio(rq)); + else if (guc_bypass_tasklet_submit(guc, rq) == -EBUSY) + tasklet_hi_schedule(&sched_engine->tasklet); + + spin_unlock_irqrestore(&sched_engine->lock, flags); +} + +static int new_guc_id(struct intel_guc *guc) +{ + return ida_simple_get(&guc->guc_ids, 0, + GUC_MAX_LRC_DESCRIPTORS, GFP_KERNEL | + __GFP_RETRY_MAYFAIL | __GFP_NOWARN); +} + +static void __release_guc_id(struct intel_guc *guc, struct intel_context *ce) +{ + if (!context_guc_id_invalid(ce)) { + ida_simple_remove(&guc->guc_ids, ce->guc_id); + reset_lrc_desc(guc, ce->guc_id); + set_context_guc_id_invalid(ce); + } + if (!list_empty(&ce->guc_id_link)) + list_del_init(&ce->guc_id_link); +} + +static void release_guc_id(struct intel_guc *guc, struct intel_context *ce) +{ + unsigned long flags; + + spin_lock_irqsave(&guc->contexts_lock, flags); + __release_guc_id(guc, ce); + spin_unlock_irqrestore(&guc->contexts_lock, flags); +} + +static int steal_guc_id(struct intel_guc *guc) +{ + struct intel_context *ce; + int guc_id; + + lockdep_assert_held(&guc->contexts_lock); + + if (!list_empty(&guc->guc_id_list)) { + ce = list_first_entry(&guc->guc_id_list, + struct intel_context, + guc_id_link); + + GEM_BUG_ON(atomic_read(&ce->guc_id_ref)); + GEM_BUG_ON(context_guc_id_invalid(ce)); + + list_del_init(&ce->guc_id_link); + guc_id = ce->guc_id; + set_context_guc_id_invalid(ce); + return guc_id; + } else { + return -EAGAIN; + } +} + +static int assign_guc_id(struct intel_guc *guc, u16 *out) +{ + int ret; + + lockdep_assert_held(&guc->contexts_lock); + + ret = new_guc_id(guc); + if (unlikely(ret < 0)) { + ret = steal_guc_id(guc); + if (ret < 0) + return ret; + } + + *out = ret; + return 0; +} + +#define PIN_GUC_ID_TRIES 4 +static int pin_guc_id(struct intel_guc *guc, struct intel_context *ce) +{ + int ret = 0; + unsigned long flags, tries = PIN_GUC_ID_TRIES; + + GEM_BUG_ON(atomic_read(&ce->guc_id_ref)); + +try_again: + spin_lock_irqsave(&guc->contexts_lock, flags); + + if (context_guc_id_invalid(ce)) { + ret = assign_guc_id(guc, &ce->guc_id); + if (ret) + goto out_unlock; + ret = 1; /* Indidcates newly assigned guc_id */ + } + if (!list_empty(&ce->guc_id_link)) + list_del_init(&ce->guc_id_link); + atomic_inc(&ce->guc_id_ref); + +out_unlock: + spin_unlock_irqrestore(&guc->contexts_lock, flags); + + /* + * -EAGAIN indicates no guc_ids are available, let's retire any + * outstanding requests to see if that frees up a guc_id. If the first + * retire didn't help, insert a sleep with the timeslice duration before + * attempting to retire more requests. Double the sleep period each + * subsequent pass before finally giving up. The sleep period has max of + * 100ms and minimum of 1ms. + */ + if (ret == -EAGAIN && --tries) { + if (PIN_GUC_ID_TRIES - tries > 1) { + unsigned int timeslice_shifted = + ce->engine->props.timeslice_duration_ms << + (PIN_GUC_ID_TRIES - tries - 2); + unsigned int max = min_t(unsigned int, 100, + timeslice_shifted); + + msleep(max_t(unsigned int, max, 1)); + } + intel_gt_retire_requests(guc_to_gt(guc)); + goto try_again; + } + + return ret; +} + +static void unpin_guc_id(struct intel_guc *guc, struct intel_context *ce) +{ + unsigned long flags; + + GEM_BUG_ON(atomic_read(&ce->guc_id_ref) < 0); + + if (unlikely(context_guc_id_invalid(ce))) + return; + + spin_lock_irqsave(&guc->contexts_lock, flags); + if (!context_guc_id_invalid(ce) && list_empty(&ce->guc_id_link) && + !atomic_read(&ce->guc_id_ref)) + list_add_tail(&ce->guc_id_link, &guc->guc_id_list); + spin_unlock_irqrestore(&guc->contexts_lock, flags); +} + +static int __guc_action_register_context(struct intel_guc *guc, + u32 guc_id, + u32 offset) +{ + u32 action[] = { + INTEL_GUC_ACTION_REGISTER_CONTEXT, + guc_id, + offset, + }; + + return intel_guc_send_busy_loop(guc, action, ARRAY_SIZE(action), true); +} + +static int register_context(struct intel_context *ce) +{ + struct intel_guc *guc = ce_to_guc(ce); + u32 offset = intel_guc_ggtt_offset(guc, guc->lrc_desc_pool) + + ce->guc_id * sizeof(struct guc_lrc_desc); + + return __guc_action_register_context(guc, ce->guc_id, offset); +} + +static int __guc_action_deregister_context(struct intel_guc *guc, + u32 guc_id) +{ + u32 action[] = { + INTEL_GUC_ACTION_DEREGISTER_CONTEXT, + guc_id, + }; + + return intel_guc_send_busy_loop(guc, action, ARRAY_SIZE(action), true); +} + +static int deregister_context(struct intel_context *ce, u32 guc_id) +{ + struct intel_guc *guc = ce_to_guc(ce); + + return __guc_action_deregister_context(guc, guc_id); +} + +static intel_engine_mask_t adjust_engine_mask(u8 class, intel_engine_mask_t mask) +{ + switch (class) { + case RENDER_CLASS: + return mask >> RCS0; + case VIDEO_ENHANCEMENT_CLASS: + return mask >> VECS0; + case VIDEO_DECODE_CLASS: + return mask >> VCS0; + case COPY_ENGINE_CLASS: + return mask >> BCS0; + default: + MISSING_CASE(class); + return 0; + } +} + +static void guc_context_policy_init(struct intel_engine_cs *engine, + struct guc_lrc_desc *desc) +{ + desc->policy_flags = 0; + + desc->execution_quantum = CONTEXT_POLICY_DEFAULT_EXECUTION_QUANTUM_US; + desc->preemption_timeout = CONTEXT_POLICY_DEFAULT_PREEMPTION_TIME_US; +} + +static int guc_lrc_desc_pin(struct intel_context *ce) +{ + struct intel_engine_cs *engine = ce->engine; + struct intel_runtime_pm *runtime_pm = engine->uncore->rpm; + struct intel_guc *guc = &engine->gt->uc.guc; + u32 desc_idx = ce->guc_id; + struct guc_lrc_desc *desc; + bool context_registered; + intel_wakeref_t wakeref; + int ret = 0; + + GEM_BUG_ON(!engine->mask); + + /* + * Ensure LRC + CT vmas are is same region as write barrier is done + * based on CT vma region. + */ + GEM_BUG_ON(i915_gem_object_is_lmem(guc->ct.vma->obj) != + i915_gem_object_is_lmem(ce->ring->vma->obj)); + + context_registered = lrc_desc_registered(guc, desc_idx); + + reset_lrc_desc(guc, desc_idx); + set_lrc_desc_registered(guc, desc_idx, ce); + + desc = __get_lrc_desc(guc, desc_idx); + desc->engine_class = engine_class_to_guc_class(engine->class); + desc->engine_submit_mask = adjust_engine_mask(engine->class, + engine->mask); + desc->hw_context_desc = ce->lrc.lrca; + desc->priority = GUC_CLIENT_PRIORITY_KMD_NORMAL; + desc->context_flags = CONTEXT_REGISTRATION_FLAG_KMD; + guc_context_policy_init(engine, desc); + init_sched_state(ce); + + /* + * The context_lookup xarray is used to determine if the hardware + * context is currently registered. There are two cases in which it + * could be registered either the guc_id has been stolen from another + * context or the lrc descriptor address of this context has changed. In + * either case the context needs to be deregistered with the GuC before + * registering this context. + */ + if (context_registered) { + set_context_wait_for_deregister_to_register(ce); + intel_context_get(ce); + + /* + * If stealing the guc_id, this ce has the same guc_id as the + * context whose guc_id was stolen. + */ + with_intel_runtime_pm(runtime_pm, wakeref) + ret = deregister_context(ce, ce->guc_id); + } else { + with_intel_runtime_pm(runtime_pm, wakeref) + ret = register_context(ce); + } + + return ret; }

static int guc_context_pre_pin(struct intel_context *ce, @@ -443,36 +817,144 @@ static int guc_context_pre_pin(struct intel_context *ce,

static int guc_context_pin(struct intel_context *ce, void *vaddr) { + if (i915_ggtt_offset(ce->state) != + (ce->lrc.lrca & CTX_GTT_ADDRESS_MASK)) + set_bit(CONTEXT_LRCA_DIRTY, &ce->flags); + + /* + * GuC context gets pinned in guc_request_alloc. See that function for + * explaination of why. + */ + return lrc_pin(ce, ce->engine, vaddr); }

+static void guc_context_unpin(struct intel_context *ce) +{ + struct intel_guc *guc = ce_to_guc(ce); + + unpin_guc_id(guc, ce); + lrc_unpin(ce); +} + +static void guc_context_post_unpin(struct intel_context *ce) +{ + lrc_post_unpin(ce); +} + +static inline void guc_lrc_desc_unpin(struct intel_context *ce) +{ + struct intel_guc *guc = ce_to_guc(ce); + unsigned long flags; + + GEM_BUG_ON(!lrc_desc_registered(guc, ce->guc_id)); + GEM_BUG_ON(ce != __get_context(guc, ce->guc_id)); + + spin_lock_irqsave(&ce->guc_state.lock, flags); + set_context_destroyed(ce); + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + + deregister_context(ce, ce->guc_id); +} + +static void guc_context_destroy(struct kref *kref) +{ + struct intel_context *ce = container_of(kref, typeof(*ce), ref); + struct intel_runtime_pm *runtime_pm = ce->engine->uncore->rpm; + struct intel_guc *guc = ce_to_guc(ce); + intel_wakeref_t wakeref; + unsigned long flags; + + /* + * If the guc_id is invalid this context has been stolen and we can free + * it immediately. Also can be freed immediately if the context is not + * registered with the GuC. + */ + if (context_guc_id_invalid(ce)) { + lrc_destroy(kref); + return; + } else if (!lrc_desc_registered(guc, ce->guc_id)) { + release_guc_id(guc, ce); + lrc_destroy(kref); + return; + } + + /* + * We have to acquire the context spinlock and check guc_id again, if it + * is valid it hasn't been stolen and needs to be deregistered. We + * delete this context from the list of unpinned guc_ids available to + * steal to seal a race with guc_lrc_desc_pin(). When the G2H CTB + * returns indicating this context has been deregistered the guc_id is + * returned to the pool of available guc_ids. + */ + spin_lock_irqsave(&guc->contexts_lock, flags); + if (context_guc_id_invalid(ce)) { + spin_unlock_irqrestore(&guc->contexts_lock, flags); + lrc_destroy(kref); + return; + } + + if (!list_empty(&ce->guc_id_link)) + list_del_init(&ce->guc_id_link); + spin_unlock_irqrestore(&guc->contexts_lock, flags); + + /* + * We defer GuC context deregistration until the context is destroyed + * in order to save on CTBs. With this optimization ideally we only need + * 1 CTB to register the context during the first pin and 1 CTB to + * deregister the context when the context is destroyed. Without this + * optimization, a CTB would be needed every pin & unpin. + * + * XXX: Need to acqiure the runtime wakeref as this can be triggered + * from context_free_worker when runtime wakeref is not held. + * guc_lrc_desc_unpin requires the runtime as a GuC register is written + * in H2G CTB to deregister the context. A future patch may defer this + * H2G CTB if the runtime wakeref is zero. + */ + with_intel_runtime_pm(runtime_pm, wakeref) + guc_lrc_desc_unpin(ce); +} + +static int guc_context_alloc(struct intel_context *ce) +{ + return lrc_alloc(ce, ce->engine); +} + static const struct intel_context_ops guc_context_ops = { .alloc = guc_context_alloc,

.pre_pin = guc_context_pre_pin, .pin = guc_context_pin, - .unpin = lrc_unpin, - .post_unpin = lrc_post_unpin, + .unpin = guc_context_unpin, + .post_unpin = guc_context_post_unpin,

.enter = intel_context_enter_engine, .exit = intel_context_exit_engine,

.reset = lrc_reset, - .destroy = lrc_destroy, + .destroy = guc_context_destroy, };

-static int guc_request_alloc(struct i915_request *request) +static bool context_needs_register(struct intel_context *ce, bool new_guc_id) +{ + return new_guc_id || test_bit(CONTEXT_LRCA_DIRTY, &ce->flags) || + !lrc_desc_registered(ce_to_guc(ce), ce->guc_id); +} + +static int guc_request_alloc(struct i915_request *rq) { + struct intel_context *ce = rq->context; + struct intel_guc *guc = ce_to_guc(ce); int ret;

- GEM_BUG_ON(!intel_context_is_pinned(request->context)); + GEM_BUG_ON(!intel_context_is_pinned(rq->context));

/* * Flush enough space to reduce the likelihood of waiting after * we start building the request - in which case we will just * have to repeat work. */ - request->reserved_space += GUC_REQUEST_SIZE; + rq->reserved_space += GUC_REQUEST_SIZE;

/* * Note that after this point, we have committed to using @@ -483,56 +965,47 @@ static int guc_request_alloc(struct i915_request *request) */

/* Unconditionally invalidate GPU caches and TLBs. */ - ret = request->engine->emit_flush(request, EMIT_INVALIDATE); + ret = rq->engine->emit_flush(rq, EMIT_INVALIDATE); if (ret) return ret;

- request->reserved_space -= GUC_REQUEST_SIZE; - return 0; -} + rq->reserved_space -= GUC_REQUEST_SIZE;

-static inline void queue_request(struct i915_sched_engine *sched_engine, - struct i915_request *rq, - int prio) -{ - GEM_BUG_ON(!list_empty(&rq->sched.link)); - list_add_tail(&rq->sched.link, - i915_sched_lookup_priolist(sched_engine, prio)); - set_bit(I915_FENCE_FLAG_PQUEUE, &rq->fence.flags); -} - -static int guc_bypass_tasklet_submit(struct intel_guc *guc, - struct i915_request *rq) -{ - int ret; - - __i915_request_submit(rq); - - trace_i915_request_in(rq, 0); - - guc_set_lrc_tail(rq); - ret = guc_add_request(guc, rq); - if (ret == -EBUSY) - guc->stalled_request = rq; - - return ret; -} - -static void guc_submit_request(struct i915_request *rq) -{ - struct i915_sched_engine *sched_engine = rq->engine->sched_engine; - struct intel_guc *guc = &rq->engine->gt->uc.guc; - unsigned long flags; + /* + * Call pin_guc_id here rather than in the pinning step as with + * dma_resv, contexts can be repeatedly pinned / unpinned trashing the + * guc_ids and creating horrible race conditions. This is especially bad + * when guc_ids are being stolen due to over subscription. By the time + * this function is reached, it is guaranteed that the guc_id will be + * persistent until the generated request is retired. Thus, sealing these + * race conditions. It is still safe to fail here if guc_ids are + * exhausted and return -EAGAIN to the user indicating that they can try + * again in the future. + * + * There is no need for a lock here as the timeline mutex ensures at + * most one context can be executing this code path at once. The + * guc_id_ref is incremented once for every request in flight and + * decremented on each retire. When it is zero, a lock around the + * increment (in pin_guc_id) is needed to seal a race with unpin_guc_id. + */ + if (atomic_add_unless(&ce->guc_id_ref, 1, 0)) + return 0;

- /* Will be called from irq-context when using foreign fences. */ - spin_lock_irqsave(&sched_engine->lock, flags); + ret = pin_guc_id(guc, ce); /* returns 1 if new guc_id assigned */ + if (unlikely(ret < 0)) + return ret; + if (context_needs_register(ce, !!ret)) { + ret = guc_lrc_desc_pin(ce); + if (unlikely(ret)) { /* unwind */ + atomic_dec(&ce->guc_id_ref); + unpin_guc_id(guc, ce); + return ret; + } + }

- if (guc->stalled_request || !i915_sched_engine_is_empty(sched_engine)) - queue_request(sched_engine, rq, rq_prio(rq)); - else if (guc_bypass_tasklet_submit(guc, rq) == -EBUSY) - tasklet_hi_schedule(&sched_engine->tasklet); + clear_bit(CONTEXT_LRCA_DIRTY, &ce->flags);

- spin_unlock_irqrestore(&sched_engine->lock, flags); + return 0; }

static void sanitize_hwsp(struct intel_engine_cs *engine) @@ -606,6 +1079,41 @@ static void guc_set_default_submission(struct intel_engine_cs *engine) engine->submit_request = guc_submit_request; }

+static inline void guc_kernel_context_pin(struct intel_guc *guc, + struct intel_context *ce) +{ + if (context_guc_id_invalid(ce)) + pin_guc_id(guc, ce); + guc_lrc_desc_pin(ce); +} + +static inline void guc_init_lrc_mapping(struct intel_guc *guc) +{ + struct intel_gt *gt = guc_to_gt(guc); + struct intel_engine_cs *engine; + enum intel_engine_id id; + + /* make sure all descriptors are clean... */ + xa_destroy(&guc->context_lookup); + + /* + * Some contexts might have been pinned before we enabled GuC + * submission, so we need to add them to the GuC bookeeping. + * Also, after a reset the of the GuC we want to make sure that the + * information shared with GuC is properly reset. The kernel LRCs are + * not attached to the gem_context, so they need to be added separately. + * + * Note: we purposefully do not check the return of guc_lrc_desc_pin, + * because that function can only fail if a reset is just starting. This + * is at the end of reset so presumably another reset isn't happening + * and even it did this code would be run again. + */ + + for_each_engine(engine, gt, id) + if (engine->kernel_context) + guc_kernel_context_pin(guc, engine->kernel_context); +} + static void guc_release(struct intel_engine_cs *engine) { engine->sanitize = NULL; /* no longer in control, nothing to sanitize */ @@ -718,6 +1226,7 @@ int intel_guc_submission_setup(struct intel_engine_cs *engine)

void intel_guc_submission_enable(struct intel_guc *guc) { + guc_init_lrc_mapping(guc); }

void intel_guc_submission_disable(struct intel_guc *guc) @@ -743,3 +1252,62 @@ void intel_guc_submission_init_early(struct intel_guc *guc) { guc->submission_selected = __guc_submission_selected(guc); } + +static inline struct intel_context * +g2h_context_lookup(struct intel_guc *guc, u32 desc_idx) +{ + struct intel_context *ce; + + if (unlikely(desc_idx >= GUC_MAX_LRC_DESCRIPTORS)) { + drm_err(&guc_to_gt(guc)->i915->drm, + "Invalid desc_idx %u", desc_idx); + return NULL; + } + + ce = __get_context(guc, desc_idx); + if (unlikely(!ce)) { + drm_err(&guc_to_gt(guc)->i915->drm, + "Context is NULL, desc_idx %u", desc_idx); + return NULL; + } + + return ce; +} + +int intel_guc_deregister_done_process_msg(struct intel_guc *guc, + const u32 *msg, + u32 len) +{ + struct intel_context *ce; + u32 desc_idx = msg[0]; + + if (unlikely(len < 1)) { + drm_err(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len); + return -EPROTO; + } + + ce = g2h_context_lookup(guc, desc_idx); + if (unlikely(!ce)) + return -EPROTO; + + if (context_wait_for_deregister_to_register(ce)) { + struct intel_runtime_pm *runtime_pm = + &ce->engine->gt->i915->runtime_pm; + intel_wakeref_t wakeref; + + /* + * Previous owner of this guc_id has been deregistered, now safe + * register this context. + */ + with_intel_runtime_pm(runtime_pm, wakeref) + register_context(ce); + clr_context_wait_for_deregister_to_register(ce); + intel_context_put(ce); + } else if (context_destroyed(ce)) { + /* Context has been destroyed */ + release_guc_id(guc, ce); + lrc_destroy(&ce->ref); + } + + return 0; +} diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 9d501b86c0c9..2157cf65e472 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -4142,6 +4142,7 @@ enum { FAULT_AND_CONTINUE /* Unsupported */ };

+#define CTX_GTT_ADDRESS_MASK GENMASK(31, 12) #define GEN8_CTX_VALID (1 << 0) #define GEN8_CTX_FORCE_PD_RESTORE (1 << 1) #define GEN8_CTX_FORCE_RESTORE (1 << 2) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 09ebea9a0090..ef26724fe980 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -407,6 +407,7 @@ bool i915_request_retire(struct i915_request *rq) */ if (!list_empty(&rq->sched.link)) remove_from_engine(rq); + atomic_dec(&rq->context->guc_id_ref); GEM_BUG_ON(!llist_empty(&rq->execute_cb));

__list_del_entry(&rq->link); /* poison neither prev/next (RCU walks) */

With GuC scheduling, it isn't safe to unpin a context while scheduling is enabled for that context as the GuC may touch some of the pinned state (e.g. LRC). To ensure scheduling isn't enabled when an unpin is done, a call back is added to intel_context_unpin when pin count == 1 to disable scheduling for that context. When the response CTB is received it is safe to do the final unpin.

Future patches may add a heuristic / delay to schedule the disable call back to avoid thrashing on schedule enable / disable.

v2: (John H) - s/drm_dbg/drm_err (Daneiel) - Clean up sched state function

Cc: John Harrison john.c.harrison@intel.com Signed-off-by: Matthew Brost matthew.brost@intel.com Reviewed-by: John Harrison John.C.Harrison@Intel.com --- drivers/gpu/drm/i915/gt/intel_context.c | 4 +- drivers/gpu/drm/i915/gt/intel_context.h | 27 +++- drivers/gpu/drm/i915/gt/intel_context_types.h | 2 + drivers/gpu/drm/i915/gt/uc/intel_guc.h | 2 + drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c | 3 + .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 146 +++++++++++++++++- 6 files changed, 180 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index ad7197c5910f..3d5b4116617f 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -306,9 +306,9 @@ int __intel_context_do_pin(struct intel_context *ce) return err; }

-void intel_context_unpin(struct intel_context *ce) +void __intel_context_do_unpin(struct intel_context *ce, int sub) { - if (!atomic_dec_and_test(&ce->pin_count)) + if (!atomic_sub_and_test(sub, &ce->pin_count)) return;

CE_TRACE(ce, "unpin\n"); diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h index b10cbe8fee99..974ef85320c2 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.h +++ b/drivers/gpu/drm/i915/gt/intel_context.h @@ -113,7 +113,32 @@ static inline void __intel_context_pin(struct intel_context *ce) atomic_inc(&ce->pin_count); }

-void intel_context_unpin(struct intel_context *ce); +void __intel_context_do_unpin(struct intel_context *ce, int sub); + +static inline void intel_context_sched_disable_unpin(struct intel_context *ce) +{ + __intel_context_do_unpin(ce, 2); +} + +static inline void intel_context_unpin(struct intel_context *ce) +{ + if (!ce->ops->sched_disable) { + __intel_context_do_unpin(ce, 1); + } else { + /* + * Move ownership of this pin to the scheduling disable which is + * an async operation. When that operation completes the above + * intel_context_sched_disable_unpin is called potentially + * unpinning the context. + */ + while (!atomic_add_unless(&ce->pin_count, -1, 1)) { + if (atomic_cmpxchg(&ce->pin_count, 1, 2) == 1) { + ce->ops->sched_disable(ce); + break; + } + } + } +}

void intel_context_enter_engine(struct intel_context *ce); void intel_context_exit_engine(struct intel_context *ce); diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index e0e3a937f709..4a5518d295c2 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -43,6 +43,8 @@ struct intel_context_ops { void (*enter)(struct intel_context *ce); void (*exit)(struct intel_context *ce);

+ void (*sched_disable)(struct intel_context *ce); + void (*reset)(struct intel_context *ce); void (*destroy)(struct kref *kref); }; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index 7fd6c3e343e4..4d470ebeda95 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -248,6 +248,8 @@ int intel_guc_reset_engine(struct intel_guc *guc,

int intel_guc_deregister_done_process_msg(struct intel_guc *guc, const u32 *msg, u32 len); +int intel_guc_sched_done_process_msg(struct intel_guc *guc, + const u32 *msg, u32 len);

void intel_guc_load_status(struct intel_guc *guc, struct drm_printer *p);

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c index 28ff82c5be45..019b25ff1888 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c @@ -932,6 +932,9 @@ static int ct_process_request(struct intel_guc_ct *ct, struct ct_incoming_msg *r ret = intel_guc_deregister_done_process_msg(guc, payload, len); break; + case INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_DONE: + ret = intel_guc_sched_done_process_msg(guc, payload, len); + break; default: ret = -EOPNOTSUPP; break; 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 a0871b800153..2f393d9dba0d 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -70,6 +70,7 @@ * possible for some of the bits to changing at the same time though. */ #define SCHED_STATE_NO_LOCK_ENABLED BIT(0) +#define SCHED_STATE_NO_LOCK_PENDING_ENABLE BIT(1) static inline bool context_enabled(struct intel_context *ce) { return (atomic_read(&ce->guc_sched_state_no_lock) & @@ -87,6 +88,24 @@ static inline void clr_context_enabled(struct intel_context *ce) &ce->guc_sched_state_no_lock); }

+static inline bool context_pending_enable(struct intel_context *ce) +{ + return (atomic_read(&ce->guc_sched_state_no_lock) & + SCHED_STATE_NO_LOCK_PENDING_ENABLE); +} + +static inline void set_context_pending_enable(struct intel_context *ce) +{ + atomic_or(SCHED_STATE_NO_LOCK_PENDING_ENABLE, + &ce->guc_sched_state_no_lock); +} + +static inline void clr_context_pending_enable(struct intel_context *ce) +{ + atomic_and((u32)~SCHED_STATE_NO_LOCK_PENDING_ENABLE, + &ce->guc_sched_state_no_lock); +} + /* * Below is a set of functions which control the GuC scheduling state which * require a lock, aside from the special case where the functions are called @@ -95,6 +114,7 @@ static inline void clr_context_enabled(struct intel_context *ce) */ #define SCHED_STATE_WAIT_FOR_DEREGISTER_TO_REGISTER BIT(0) #define SCHED_STATE_DESTROYED BIT(1) +#define SCHED_STATE_PENDING_DISABLE BIT(2) static inline void init_sched_state(struct intel_context *ce) { /* Only should be called from guc_lrc_desc_pin() */ @@ -138,6 +158,23 @@ set_context_destroyed(struct intel_context *ce) ce->guc_state.sched_state |= SCHED_STATE_DESTROYED; }

+static inline bool context_pending_disable(struct intel_context *ce) +{ + return ce->guc_state.sched_state & SCHED_STATE_PENDING_DISABLE; +} + +static inline void set_context_pending_disable(struct intel_context *ce) +{ + lockdep_assert_held(&ce->guc_state.lock); + ce->guc_state.sched_state |= SCHED_STATE_PENDING_DISABLE; +} + +static inline void clr_context_pending_disable(struct intel_context *ce) +{ + lockdep_assert_held(&ce->guc_state.lock); + ce->guc_state.sched_state &= ~SCHED_STATE_PENDING_DISABLE; +} + static inline bool context_guc_id_invalid(struct intel_context *ce) { return ce->guc_id == GUC_INVALID_LRC_ID; @@ -230,6 +267,8 @@ static int guc_add_request(struct intel_guc *guc, struct i915_request *rq) action[len++] = INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_SET; action[len++] = ce->guc_id; action[len++] = GUC_CONTEXT_ENABLE; + set_context_pending_enable(ce); + intel_context_get(ce); } else { action[len++] = INTEL_GUC_ACTION_SCHED_CONTEXT; action[len++] = ce->guc_id; @@ -237,8 +276,12 @@ static int guc_add_request(struct intel_guc *guc, struct i915_request *rq)

err = intel_guc_send_nb(guc, action, len);

- if (!enabled && !err) + if (!enabled && !err) { set_context_enabled(ce); + } else if (!enabled) { + clr_context_pending_enable(ce); + intel_context_put(ce); + }

return err; } @@ -842,6 +885,62 @@ static void guc_context_post_unpin(struct intel_context *ce) lrc_post_unpin(ce); }

+static void __guc_context_sched_disable(struct intel_guc *guc, + struct intel_context *ce, + u16 guc_id) +{ + u32 action[] = { + INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_SET, + guc_id, /* ce->guc_id not stable */ + GUC_CONTEXT_DISABLE + }; + + GEM_BUG_ON(guc_id == GUC_INVALID_LRC_ID); + + intel_context_get(ce); + + intel_guc_send_busy_loop(guc, action, ARRAY_SIZE(action), true); +} + +static u16 prep_context_pending_disable(struct intel_context *ce) +{ + lockdep_assert_held(&ce->guc_state.lock); + + set_context_pending_disable(ce); + clr_context_enabled(ce); + + return ce->guc_id; +} + +static void guc_context_sched_disable(struct intel_context *ce) +{ + struct intel_guc *guc = ce_to_guc(ce); + struct intel_runtime_pm *runtime_pm = &ce->engine->gt->i915->runtime_pm; + unsigned long flags; + u16 guc_id; + intel_wakeref_t wakeref; + + if (context_guc_id_invalid(ce) || + !lrc_desc_registered(guc, ce->guc_id)) { + clr_context_enabled(ce); + goto unpin; + } + + if (!context_enabled(ce)) + goto unpin; + + spin_lock_irqsave(&ce->guc_state.lock, flags); + guc_id = prep_context_pending_disable(ce); + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + + with_intel_runtime_pm(runtime_pm, wakeref) + __guc_context_sched_disable(guc, ce, guc_id); + + return; +unpin: + intel_context_sched_disable_unpin(ce); +} + static inline void guc_lrc_desc_unpin(struct intel_context *ce) { struct intel_guc *guc = ce_to_guc(ce); @@ -849,6 +948,7 @@ static inline void guc_lrc_desc_unpin(struct intel_context *ce)

GEM_BUG_ON(!lrc_desc_registered(guc, ce->guc_id)); GEM_BUG_ON(ce != __get_context(guc, ce->guc_id)); + GEM_BUG_ON(context_enabled(ce));

spin_lock_irqsave(&ce->guc_state.lock, flags); set_context_destroyed(ce); @@ -931,6 +1031,8 @@ static const struct intel_context_ops guc_context_ops = { .enter = intel_context_enter_engine, .exit = intel_context_exit_engine,

+ .sched_disable = guc_context_sched_disable, + .reset = lrc_reset, .destroy = guc_context_destroy, }; @@ -1358,3 +1460,45 @@ int intel_guc_deregister_done_process_msg(struct intel_guc *guc,

return 0; } + +int intel_guc_sched_done_process_msg(struct intel_guc *guc, + const u32 *msg, + u32 len) +{ + struct intel_context *ce; + unsigned long flags; + u32 desc_idx = msg[0]; + + if (unlikely(len < 2)) { + drm_err(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len); + return -EPROTO; + } + + ce = g2h_context_lookup(guc, desc_idx); + if (unlikely(!ce)) + return -EPROTO; + + if (unlikely(context_destroyed(ce) || + (!context_pending_enable(ce) && + !context_pending_disable(ce)))) { + drm_err(&guc_to_gt(guc)->i915->drm, + "Bad context sched_state 0x%x, 0x%x, desc_idx %u", + atomic_read(&ce->guc_sched_state_no_lock), + ce->guc_state.sched_state, desc_idx); + return -EPROTO; + } + + if (context_pending_enable(ce)) { + clr_context_pending_enable(ce); + } else if (context_pending_disable(ce)) { + intel_context_sched_disable_unpin(ce); + + spin_lock_irqsave(&ce->guc_state.lock, flags); + clr_context_pending_disable(ce); + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + } + + intel_context_put(ce); + + return 0; +}

Extend the deregistration context fence to fence whne a GuC context has scheduling disable pending.

v2: (John H) - Update comment why we check the pin count within spin lock

Cc: John Harrison john.c.harrison@intel.com Signed-off-by: Matthew Brost matthew.brost@intel.com Reviewed-by: John Harrison john.c.harrison@intel.com --- .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 40 +++++++++++++++---- 1 file changed, 33 insertions(+), 7 deletions(-)

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 2f393d9dba0d..fc0b36ab1e68 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -930,7 +930,22 @@ static void guc_context_sched_disable(struct intel_context *ce) goto unpin;

spin_lock_irqsave(&ce->guc_state.lock, flags); + + /* + * We have to check if the context has been pinned again as another pin + * operation is allowed to pass this function. Checking the pin count, + * within ce->guc_state.lock, synchronizes this function with + * guc_request_alloc ensuring a request doesn't slip through the + * 'context_pending_disable' fence. Checking within the spin lock (can't + * sleep) ensures another process doesn't pin this context and generate + * a request before we set the 'context_pending_disable' flag here. + */ + if (unlikely(atomic_add_unless(&ce->pin_count, -2, 2))) { + spin_unlock_irqrestore(&ce->guc_state.lock, flags); + return; + } guc_id = prep_context_pending_disable(ce); + spin_unlock_irqrestore(&ce->guc_state.lock, flags);

with_intel_runtime_pm(runtime_pm, wakeref) @@ -1135,19 +1150,22 @@ static int guc_request_alloc(struct i915_request *rq) out: /* * We block all requests on this context if a G2H is pending for a - * context deregistration as the GuC will fail a context registration - * while this G2H is pending. Once a G2H returns, the fence is released - * that is blocking these requests (see guc_signal_context_fence). + * schedule disable or context deregistration as the GuC will fail a + * schedule enable or context registration if either G2H is pending + * respectfully. Once a G2H returns, the fence is released that is + * blocking these requests (see guc_signal_context_fence). * - * We can safely check the below field outside of the lock as it isn't - * possible for this field to transition from being clear to set but + * We can safely check the below fields outside of the lock as it isn't + * possible for these fields to transition from being clear to set but * converse is possible, hence the need for the check within the lock. */ - if (likely(!context_wait_for_deregister_to_register(ce))) + if (likely(!context_wait_for_deregister_to_register(ce) && + !context_pending_disable(ce))) return 0;

spin_lock_irqsave(&ce->guc_state.lock, flags); - if (context_wait_for_deregister_to_register(ce)) { + if (context_wait_for_deregister_to_register(ce) || + context_pending_disable(ce)) { i915_sw_fence_await(&rq->submit);

list_add_tail(&rq->guc_fence_link, &ce->guc_state.fences); @@ -1491,10 +1509,18 @@ int intel_guc_sched_done_process_msg(struct intel_guc *guc, if (context_pending_enable(ce)) { clr_context_pending_enable(ce); } else if (context_pending_disable(ce)) { + /* + * Unpin must be done before __guc_signal_context_fence, + * otherwise a race exists between the requests getting + * submitted + retired before this unpin completes resulting in + * the pin_count going to zero and the context still being + * enabled. + */ intel_context_sched_disable_unpin(ce);

spin_lock_irqsave(&ce->guc_state.lock, flags); clr_context_pending_disable(ce); + __guc_signal_context_fence(ce); spin_unlock_irqrestore(&ce->guc_state.lock, flags); }

If two requests are on the same ring, they are explicitly ordered by the HW. So, a submission fence is sufficient to ensure ordering when using the new GuC submission interface. Conversely, if two requests share a timeline and are on the same physical engine but different context this doesn't ensure ordering on the new GuC submission interface. So, a completion fence needs to be used to ensure ordering.

v2: (Daniele) - Don't delete spin lock v3: (Daniele) - Delete forward dec

Signed-off-by: John Harrison John.C.Harrison@Intel.com Signed-off-by: Matthew Brost matthew.brost@intel.com Reviewed-by: Daniele Ceraolo Spurio daniele.ceraolospurio@intel.com --- drivers/gpu/drm/i915/i915_request.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index ef26724fe980..c55dea0edb09 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -432,6 +432,7 @@ void i915_request_retire_upto(struct i915_request *rq)

do { tmp = list_first_entry(&tl->requests, typeof(*tmp), link); + GEM_BUG_ON(!i915_request_completed(tmp)); } while (i915_request_retire(tmp) && tmp != rq); }

@@ -1463,7 +1464,8 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from) return ret; }

- if (is_power_of_2(to->execution_mask | READ_ONCE(from->execution_mask))) + if (!intel_engine_uses_guc(to->engine) && + is_power_of_2(to->execution_mask | READ_ONCE(from->execution_mask))) ret = await_request_submit(to, from); else ret = emit_semaphore_wait(to, from, I915_FENCE_GFP); @@ -1622,6 +1624,8 @@ __i915_request_add_to_timeline(struct i915_request *rq) prev = to_request(__i915_active_fence_set(&timeline->last_request, &rq->fence)); if (prev && !__i915_request_is_complete(prev)) { + bool uses_guc = intel_engine_uses_guc(rq->engine); + /* * The requests are supposed to be kept in order. However, * we need to be wary in case the timeline->last_request @@ -1632,7 +1636,9 @@ __i915_request_add_to_timeline(struct i915_request *rq) i915_seqno_passed(prev->fence.seqno, rq->fence.seqno));

- if (is_power_of_2(READ_ONCE(prev->engine)->mask | rq->engine->mask)) + if ((!uses_guc && + is_power_of_2(READ_ONCE(prev->engine)->mask | rq->engine->mask)) || + (uses_guc && prev->context == rq->context)) i915_sw_fence_await_sw_fence(&rq->submit, &prev->submit, &rq->submitq);

Ensure G2H response has space in the buffer before sending H2G CTB as the GuC can't handle any backpressure on the G2H interface.

v2: (Matthew) - s/INTEL_GUC_SEND/INTEL_GUC_CT_SEND v3: (Matthew) - Add G2H credit accounting to blocking path, add g2h_release_space helper (John H) - CTB_G2H_BUFFER_SIZE / 4 == G2H_ROOM_BUFFER_SIZE

Signed-off-by: John Harrison John.C.Harrison@Intel.com Signed-off-by: Matthew Brost matthew.brost@intel.com Reviewed-by: John Harrison John.C.Harrison@Intel.com --- drivers/gpu/drm/i915/gt/uc/intel_guc.h | 8 +- drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c | 94 +++++++++++++++---- drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h | 11 ++- drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h | 4 + .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 13 ++- 5 files changed, 104 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index 4d470ebeda95..451797c62b41 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -96,10 +96,11 @@ inline int intel_guc_send(struct intel_guc *guc, const u32 *action, u32 len) }

static -inline int intel_guc_send_nb(struct intel_guc *guc, const u32 *action, u32 len) +inline int intel_guc_send_nb(struct intel_guc *guc, const u32 *action, u32 len, + u32 g2h_len_dw) { return intel_guc_ct_send(&guc->ct, action, len, NULL, 0, - INTEL_GUC_CT_SEND_NB); + MAKE_SEND_FLAGS(g2h_len_dw)); }

static inline int @@ -113,6 +114,7 @@ intel_guc_send_and_receive(struct intel_guc *guc, const u32 *action, u32 len, static inline int intel_guc_send_busy_loop(struct intel_guc *guc, const u32 *action, u32 len, + u32 g2h_len_dw, bool loop) { int err; @@ -130,7 +132,7 @@ static inline int intel_guc_send_busy_loop(struct intel_guc *guc, might_sleep_if(loop && not_atomic);

retry: - err = intel_guc_send_nb(guc, action, len); + err = intel_guc_send_nb(guc, action, len, g2h_len_dw); if (unlikely(err == -EBUSY && loop)) { if (likely(not_atomic)) { if (msleep_interruptible(sleep_period_ms)) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c index 019b25ff1888..75f69c28056e 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c @@ -73,6 +73,7 @@ static inline struct drm_device *ct_to_drm(struct intel_guc_ct *ct) #define CTB_DESC_SIZE ALIGN(sizeof(struct guc_ct_buffer_desc), SZ_2K) #define CTB_H2G_BUFFER_SIZE (SZ_4K) #define CTB_G2H_BUFFER_SIZE (4 * CTB_H2G_BUFFER_SIZE) +#define G2H_ROOM_BUFFER_SIZE (CTB_G2H_BUFFER_SIZE / 4)

struct ct_request { struct list_head link; @@ -129,23 +130,27 @@ static void guc_ct_buffer_desc_init(struct guc_ct_buffer_desc *desc)

static void guc_ct_buffer_reset(struct intel_guc_ct_buffer *ctb) { + u32 space; + ctb->broken = false; ctb->tail = 0; ctb->head = 0; - ctb->space = CIRC_SPACE(ctb->tail, ctb->head, ctb->size); + space = CIRC_SPACE(ctb->tail, ctb->head, ctb->size) - ctb->resv_space; + atomic_set(&ctb->space, space);

guc_ct_buffer_desc_init(ctb->desc); }

static void guc_ct_buffer_init(struct intel_guc_ct_buffer *ctb, struct guc_ct_buffer_desc *desc, - u32 *cmds, u32 size_in_bytes) + u32 *cmds, u32 size_in_bytes, u32 resv_space) { GEM_BUG_ON(size_in_bytes % 4);

ctb->desc = desc; ctb->cmds = cmds; ctb->size = size_in_bytes / 4; + ctb->resv_space = resv_space / 4;

guc_ct_buffer_reset(ctb); } @@ -226,6 +231,7 @@ int intel_guc_ct_init(struct intel_guc_ct *ct) struct guc_ct_buffer_desc *desc; u32 blob_size; u32 cmds_size; + u32 resv_space; void *blob; u32 *cmds; int err; @@ -250,19 +256,23 @@ int intel_guc_ct_init(struct intel_guc_ct *ct) desc = blob; cmds = blob + 2 * CTB_DESC_SIZE; cmds_size = CTB_H2G_BUFFER_SIZE; - CT_DEBUG(ct, "%s desc %#tx cmds %#tx size %u\n", "send", - ptrdiff(desc, blob), ptrdiff(cmds, blob), cmds_size); + resv_space = 0; + CT_DEBUG(ct, "%s desc %#tx cmds %#tx size %u/%u\n", "send", + ptrdiff(desc, blob), ptrdiff(cmds, blob), cmds_size, + resv_space);

- guc_ct_buffer_init(&ct->ctbs.send, desc, cmds, cmds_size); + guc_ct_buffer_init(&ct->ctbs.send, desc, cmds, cmds_size, resv_space);

/* store pointers to desc and cmds for recv ctb */ desc = blob + CTB_DESC_SIZE; cmds = blob + 2 * CTB_DESC_SIZE + CTB_H2G_BUFFER_SIZE; cmds_size = CTB_G2H_BUFFER_SIZE; - CT_DEBUG(ct, "%s desc %#tx cmds %#tx size %u\n", "recv", - ptrdiff(desc, blob), ptrdiff(cmds, blob), cmds_size); + resv_space = G2H_ROOM_BUFFER_SIZE; + CT_DEBUG(ct, "%s desc %#tx cmds %#tx size %u/%u\n", "recv", + ptrdiff(desc, blob), ptrdiff(cmds, blob), cmds_size, + resv_space);

- guc_ct_buffer_init(&ct->ctbs.recv, desc, cmds, cmds_size); + guc_ct_buffer_init(&ct->ctbs.recv, desc, cmds, cmds_size, resv_space);

return 0; } @@ -461,8 +471,8 @@ static int ct_write(struct intel_guc_ct *ct,

/* update local copies */ ctb->tail = tail; - GEM_BUG_ON(ctb->space < len + GUC_CTB_HDR_LEN); - ctb->space -= len + GUC_CTB_HDR_LEN; + GEM_BUG_ON(atomic_read(&ctb->space) < len + GUC_CTB_HDR_LEN); + atomic_sub(len + GUC_CTB_HDR_LEN, &ctb->space);

/* now update descriptor */ WRITE_ONCE(desc->tail, tail); @@ -537,6 +547,32 @@ static inline bool ct_deadlocked(struct intel_guc_ct *ct) return ret; }

+static inline bool g2h_has_room(struct intel_guc_ct *ct, u32 g2h_len_dw) +{ + struct intel_guc_ct_buffer *ctb = &ct->ctbs.recv; + + /* + * We leave a certain amount of space in the G2H CTB buffer for + * unexpected G2H CTBs (e.g. logging, engine hang, etc...) + */ + return !g2h_len_dw || atomic_read(&ctb->space) >= g2h_len_dw; +} + +static inline void g2h_reserve_space(struct intel_guc_ct *ct, u32 g2h_len_dw) +{ + lockdep_assert_held(&ct->ctbs.send.lock); + + GEM_BUG_ON(!g2h_has_room(ct, g2h_len_dw)); + + if (g2h_len_dw) + atomic_sub(g2h_len_dw, &ct->ctbs.recv.space); +} + +static inline void g2h_release_space(struct intel_guc_ct *ct, u32 g2h_len_dw) +{ + atomic_add(g2h_len_dw, &ct->ctbs.recv.space); +} + static inline bool h2g_has_room(struct intel_guc_ct *ct, u32 len_dw) { struct intel_guc_ct_buffer *ctb = &ct->ctbs.send; @@ -544,7 +580,7 @@ static inline bool h2g_has_room(struct intel_guc_ct *ct, u32 len_dw) u32 head; u32 space;

- if (ctb->space >= len_dw) + if (atomic_read(&ctb->space) >= len_dw) return true;

head = READ_ONCE(desc->head); @@ -557,16 +593,16 @@ static inline bool h2g_has_room(struct intel_guc_ct *ct, u32 len_dw) }

space = CIRC_SPACE(ctb->tail, head, ctb->size); - ctb->space = space; + atomic_set(&ctb->space, space);

return space >= len_dw; }

-static int has_room_nb(struct intel_guc_ct *ct, u32 len_dw) +static int has_room_nb(struct intel_guc_ct *ct, u32 h2g_dw, u32 g2h_dw) { lockdep_assert_held(&ct->ctbs.send.lock);

- if (unlikely(!h2g_has_room(ct, len_dw))) { + if (unlikely(!h2g_has_room(ct, h2g_dw) || !g2h_has_room(ct, g2h_dw))) { if (ct->stall_time == KTIME_MAX) ct->stall_time = ktime_get();

@@ -580,6 +616,12 @@ static int has_room_nb(struct intel_guc_ct *ct, u32 len_dw) return 0; }

+#define G2H_LEN_DW(f) ({ \ + typeof(f) f_ = (f); \ + FIELD_GET(INTEL_GUC_CT_SEND_G2H_DW_MASK, f_) ? \ + FIELD_GET(INTEL_GUC_CT_SEND_G2H_DW_MASK, f_) + \ + GUC_CTB_HXG_MSG_MIN_LEN : 0; \ +}) static int ct_send_nb(struct intel_guc_ct *ct, const u32 *action, u32 len, @@ -587,12 +629,13 @@ static int ct_send_nb(struct intel_guc_ct *ct, { struct intel_guc_ct_buffer *ctb = &ct->ctbs.send; unsigned long spin_flags; + u32 g2h_len_dw = G2H_LEN_DW(flags); u32 fence; int ret;

spin_lock_irqsave(&ctb->lock, spin_flags);

- ret = has_room_nb(ct, len + GUC_CTB_HDR_LEN); + ret = has_room_nb(ct, len + GUC_CTB_HDR_LEN, g2h_len_dw); if (unlikely(ret)) goto out;

@@ -601,6 +644,7 @@ static int ct_send_nb(struct intel_guc_ct *ct, if (unlikely(ret)) goto out;

+ g2h_reserve_space(ct, g2h_len_dw); intel_guc_notify(ct_to_guc(ct));

out: @@ -632,11 +676,13 @@ static int ct_send(struct intel_guc_ct *ct, /* * We use a lazy spin wait loop here as we believe that if the CT * buffers are sized correctly the flow control condition should be - * rare. + * rare. Reserving the maximum size in the G2H credits as we don't know + * how big the response is going to be. */ retry: spin_lock_irqsave(&ctb->lock, flags); - if (unlikely(!h2g_has_room(ct, len + GUC_CTB_HDR_LEN))) { + if (unlikely(!h2g_has_room(ct, len + GUC_CTB_HDR_LEN) || + !g2h_has_room(ct, GUC_CTB_HXG_MSG_MAX_LEN))) { if (ct->stall_time == KTIME_MAX) ct->stall_time = ktime_get(); spin_unlock_irqrestore(&ctb->lock, flags); @@ -664,6 +710,7 @@ static int ct_send(struct intel_guc_ct *ct, spin_unlock(&ct->requests.lock);

err = ct_write(ct, action, len, fence, 0); + g2h_reserve_space(ct, GUC_CTB_HXG_MSG_MAX_LEN);

spin_unlock_irqrestore(&ctb->lock, flags);

@@ -673,6 +720,7 @@ static int ct_send(struct intel_guc_ct *ct, intel_guc_notify(ct_to_guc(ct));

err = wait_for_ct_request_update(&request, status); + g2h_release_space(ct, GUC_CTB_HXG_MSG_MAX_LEN); if (unlikely(err)) goto unlink;

@@ -992,10 +1040,22 @@ static void ct_incoming_request_worker_func(struct work_struct *w) static int ct_handle_event(struct intel_guc_ct *ct, struct ct_incoming_msg *request) { const u32 *hxg = &request->msg[GUC_CTB_MSG_MIN_LEN]; + u32 action = FIELD_GET(GUC_HXG_EVENT_MSG_0_ACTION, hxg[0]); unsigned long flags;

GEM_BUG_ON(FIELD_GET(GUC_HXG_MSG_0_TYPE, hxg[0]) != GUC_HXG_TYPE_EVENT);

+ /* + * Adjusting the space must be done in IRQ or deadlock can occur as the + * CTB processing in the below workqueue can send CTBs which creates a + * circular dependency if the space was returned there. + */ + switch (action) { + case INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_DONE: + case INTEL_GUC_ACTION_DEREGISTER_CONTEXT_DONE: + g2h_release_space(ct, request->size); + } + spin_lock_irqsave(&ct->requests.lock, flags); list_add_tail(&request->link, &ct->requests.incoming); spin_unlock_irqrestore(&ct->requests.lock, flags); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h index edd1bba0445d..dda2d6a75392 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h @@ -33,6 +33,7 @@ struct intel_guc; * @desc: pointer to the buffer descriptor * @cmds: pointer to the commands buffer * @size: size of the commands buffer in dwords + * @resv_space: reserved space in buffer in dwords * @head: local shadow copy of head in dwords * @tail: local shadow copy of tail in dwords * @space: local shadow copy of space in dwords @@ -43,9 +44,10 @@ struct intel_guc_ct_buffer { struct guc_ct_buffer_desc *desc; u32 *cmds; u32 size; + u32 resv_space; u32 tail; u32 head; - u32 space; + atomic_t space; bool broken; };

@@ -97,6 +99,13 @@ static inline bool intel_guc_ct_enabled(struct intel_guc_ct *ct) }

#define INTEL_GUC_CT_SEND_NB BIT(31) +#define INTEL_GUC_CT_SEND_G2H_DW_SHIFT 0 +#define INTEL_GUC_CT_SEND_G2H_DW_MASK (0xff << INTEL_GUC_CT_SEND_G2H_DW_SHIFT) +#define MAKE_SEND_FLAGS(len) ({ \ + typeof(len) len_ = (len); \ + GEM_BUG_ON(!FIELD_FIT(INTEL_GUC_CT_SEND_G2H_DW_MASK, len_)); \ + (FIELD_PREP(INTEL_GUC_CT_SEND_G2H_DW_MASK, len_) | INTEL_GUC_CT_SEND_NB); \ +}) int intel_guc_ct_send(struct intel_guc_ct *ct, const u32 *action, u32 len, u32 *response_buf, u32 response_buf_size, u32 flags); void intel_guc_ct_event_handler(struct intel_guc_ct *ct); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h index 3489b390ae77..82534259b7ad 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h @@ -17,6 +17,10 @@ #include "abi/guc_communication_ctb_abi.h" #include "abi/guc_messages_abi.h"

+/* Payload length only i.e. don't include G2H header length */ +#define G2H_LEN_DW_SCHED_CONTEXT_MODE_SET 2 +#define G2H_LEN_DW_DEREGISTER_CONTEXT 1 + #define GUC_CONTEXT_DISABLE 0 #define GUC_CONTEXT_ENABLE 1

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 fc0b36ab1e68..cba38f05e44d 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -258,6 +258,7 @@ static int guc_add_request(struct intel_guc *guc, struct i915_request *rq) struct intel_context *ce = rq->context; u32 action[3]; int len = 0; + u32 g2h_len_dw = 0; bool enabled = context_enabled(ce);

GEM_BUG_ON(!atomic_read(&ce->guc_id_ref)); @@ -269,13 +270,13 @@ static int guc_add_request(struct intel_guc *guc, struct i915_request *rq) action[len++] = GUC_CONTEXT_ENABLE; set_context_pending_enable(ce); intel_context_get(ce); + g2h_len_dw = G2H_LEN_DW_SCHED_CONTEXT_MODE_SET; } else { action[len++] = INTEL_GUC_ACTION_SCHED_CONTEXT; action[len++] = ce->guc_id; }

- err = intel_guc_send_nb(guc, action, len); - + err = intel_guc_send_nb(guc, action, len, g2h_len_dw); if (!enabled && !err) { set_context_enabled(ce); } else if (!enabled) { @@ -734,7 +735,7 @@ static int __guc_action_register_context(struct intel_guc *guc, offset, };

- return intel_guc_send_busy_loop(guc, action, ARRAY_SIZE(action), true); + return intel_guc_send_busy_loop(guc, action, ARRAY_SIZE(action), 0, true); }

static int register_context(struct intel_context *ce) @@ -754,7 +755,8 @@ static int __guc_action_deregister_context(struct intel_guc *guc, guc_id, };

- return intel_guc_send_busy_loop(guc, action, ARRAY_SIZE(action), true); + return intel_guc_send_busy_loop(guc, action, ARRAY_SIZE(action), + G2H_LEN_DW_DEREGISTER_CONTEXT, true); }

static int deregister_context(struct intel_context *ce, u32 guc_id) @@ -899,7 +901,8 @@ static void __guc_context_sched_disable(struct intel_guc *guc,

intel_context_get(ce);

- intel_guc_send_busy_loop(guc, action, ARRAY_SIZE(action), true); + intel_guc_send_busy_loop(guc, action, ARRAY_SIZE(action), + G2H_LEN_DW_SCHED_CONTEXT_MODE_SET, true); }

static u16 prep_context_pending_disable(struct intel_context *ce)

Update GuC debugfs to support the new GuC structures.

v2: (John Harrison) - Remove intel_lrc_reg.h include from i915_debugfs.c (Michal) - Rename GuC debugfs functions

Signed-off-by: John Harrison John.C.Harrison@Intel.com Signed-off-by: Matthew Brost matthew.brost@intel.com Reviewed-by: John Harrison John.C.Harrison@Intel.com --- drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c | 22 ++++++++ drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h | 3 + .../gpu/drm/i915/gt/uc/intel_guc_debugfs.c | 23 +++++++- .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 55 +++++++++++++++++++ .../gpu/drm/i915/gt/uc/intel_guc_submission.h | 5 ++ 5 files changed, 107 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c index b6bbbdb4c689..8bb6b1bbcea1 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c @@ -1174,3 +1174,25 @@ void intel_guc_ct_event_handler(struct intel_guc_ct *ct)

ct_try_receive_message(ct); } + +void intel_guc_ct_print_info(struct intel_guc_ct *ct, + struct drm_printer *p) +{ + drm_printf(p, "CT %s\n", enableddisabled(ct->enabled)); + + if (!ct->enabled) + return; + + drm_printf(p, "H2G Space: %u\n", + atomic_read(&ct->ctbs.send.space) * 4); + drm_printf(p, "Head: %u\n", + ct->ctbs.send.desc->head); + drm_printf(p, "Tail: %u\n", + ct->ctbs.send.desc->tail); + drm_printf(p, "G2H Space: %u\n", + atomic_read(&ct->ctbs.recv.space) * 4); + drm_printf(p, "Head: %u\n", + ct->ctbs.recv.desc->head); + drm_printf(p, "Tail: %u\n", + ct->ctbs.recv.desc->tail); +} diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h index 2758ee849a59..f709a19c7e21 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h @@ -16,6 +16,7 @@

struct i915_vma; struct intel_guc; +struct drm_printer;

/** * DOC: Command Transport (CT). @@ -114,4 +115,6 @@ int intel_guc_ct_send(struct intel_guc_ct *ct, const u32 *action, u32 len, u32 *response_buf, u32 response_buf_size, u32 flags); void intel_guc_ct_event_handler(struct intel_guc_ct *ct);

+void intel_guc_ct_print_info(struct intel_guc_ct *ct, struct drm_printer *p); + #endif /* _INTEL_GUC_CT_H_ */ diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c index fe7cb7b29a1e..7a454c91a736 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_debugfs.c @@ -9,6 +9,8 @@ #include "intel_guc.h" #include "intel_guc_debugfs.h" #include "intel_guc_log_debugfs.h" +#include "gt/uc/intel_guc_ct.h" +#include "gt/uc/intel_guc_submission.h"

static int guc_info_show(struct seq_file *m, void *data) { @@ -22,16 +24,35 @@ static int guc_info_show(struct seq_file *m, void *data) drm_puts(&p, "\n"); intel_guc_log_info(&guc->log, &p);

- /* Add more as required ... */ + if (!intel_guc_submission_is_used(guc)) + return 0; + + intel_guc_ct_print_info(&guc->ct, &p); + intel_guc_submission_print_info(guc, &p);

return 0; } DEFINE_GT_DEBUGFS_ATTRIBUTE(guc_info);

+static int guc_registered_contexts_show(struct seq_file *m, void *data) +{ + struct intel_guc *guc = m->private; + struct drm_printer p = drm_seq_file_printer(m); + + if (!intel_guc_submission_is_used(guc)) + return -ENODEV; + + intel_guc_submission_print_context_info(guc, &p); + + return 0; +} +DEFINE_GT_DEBUGFS_ATTRIBUTE(guc_registered_contexts); + void intel_guc_debugfs_register(struct intel_guc *guc, struct dentry *root) { static const struct debugfs_gt_file files[] = { { "guc_info", &guc_info_fops, NULL }, + { "guc_registered_contexts", &guc_registered_contexts_fops, NULL }, };

if (!intel_guc_is_supported(guc)) 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 e4ce21c9b7ef..e6e5364beb1c 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1609,3 +1609,58 @@ int intel_guc_sched_done_process_msg(struct intel_guc *guc,

return 0; } + +void intel_guc_submission_print_info(struct intel_guc *guc, + struct drm_printer *p) +{ + struct i915_sched_engine *sched_engine = guc->sched_engine; + struct rb_node *rb; + unsigned long flags; + + if (!sched_engine) + return; + + drm_printf(p, "GuC Number Outstanding Submission G2H: %u\n", + atomic_read(&guc->outstanding_submission_g2h)); + drm_printf(p, "GuC tasklet count: %u\n\n", + atomic_read(&sched_engine->tasklet.count)); + + spin_lock_irqsave(&sched_engine->lock, flags); + drm_printf(p, "Requests in GuC submit tasklet:\n"); + for (rb = rb_first_cached(&sched_engine->queue); rb; rb = rb_next(rb)) { + struct i915_priolist *pl = to_priolist(rb); + struct i915_request *rq; + + priolist_for_each_request(rq, pl) + drm_printf(p, "guc_id=%u, seqno=%llu\n", + rq->context->guc_id, + rq->fence.seqno); + } + spin_unlock_irqrestore(&sched_engine->lock, flags); + drm_printf(p, "\n"); +} + +void intel_guc_submission_print_context_info(struct intel_guc *guc, + struct drm_printer *p) +{ + struct intel_context *ce; + unsigned long index; + + xa_for_each(&guc->context_lookup, index, ce) { + drm_printf(p, "GuC lrc descriptor %u:\n", ce->guc_id); + drm_printf(p, "\tHW Context Desc: 0x%08x\n", ce->lrc.lrca); + drm_printf(p, "\t\tLRC Head: Internal %u, Memory %u\n", + ce->ring->head, + ce->lrc_reg_state[CTX_RING_HEAD]); + drm_printf(p, "\t\tLRC Tail: Internal %u, Memory %u\n", + ce->ring->tail, + ce->lrc_reg_state[CTX_RING_TAIL]); + drm_printf(p, "\t\tContext Pin Count: %u\n", + atomic_read(&ce->pin_count)); + drm_printf(p, "\t\tGuC ID Ref Count: %u\n", + atomic_read(&ce->guc_id_ref)); + drm_printf(p, "\t\tSchedule State: 0x%x, 0x%x\n\n", + ce->guc_state.sched_state, + atomic_read(&ce->guc_sched_state_no_lock)); + } +} 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 3f7005018939..2b9470c90558 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.h @@ -10,6 +10,7 @@

#include "intel_guc.h"

+struct drm_printer; struct intel_engine_cs;

void intel_guc_submission_init_early(struct intel_guc *guc); @@ -20,6 +21,10 @@ void intel_guc_submission_fini(struct intel_guc *guc); int intel_guc_preempt_work_create(struct intel_guc *guc); void intel_guc_preempt_work_destroy(struct intel_guc *guc); int intel_guc_submission_setup(struct intel_engine_cs *engine); +void intel_guc_submission_print_info(struct intel_guc *guc, + struct drm_printer *p); +void intel_guc_submission_print_context_info(struct intel_guc *guc, + struct drm_printer *p);

static inline bool intel_guc_submission_is_supported(struct intel_guc *guc) {

Add intel_context tracing. These trace points are particular helpful when debugging the GuC firmware and can be enabled via CONFIG_DRM_I915_LOW_LEVEL_TRACEPOINTS kernel config option.

Cc: John Harrison john.c.harrison@intel.com Signed-off-by: Matthew Brost matthew.brost@intel.com Reviewed-by: John Harrison John.C.Harrison@Intel.com --- drivers/gpu/drm/i915/gt/intel_context.c | 6 + .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 14 ++ drivers/gpu/drm/i915/i915_trace.h | 145 ++++++++++++++++++ 3 files changed, 165 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index 91349d071e0e..251ff7eea22d 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -8,6 +8,7 @@

#include "i915_drv.h" #include "i915_globals.h" +#include "i915_trace.h"

#include "intel_context.h" #include "intel_engine.h" @@ -28,6 +29,7 @@ static void rcu_context_free(struct rcu_head *rcu) { struct intel_context *ce = container_of(rcu, typeof(*ce), rcu);

+ trace_intel_context_free(ce); kmem_cache_free(global.slab_ce, ce); }

@@ -46,6 +48,7 @@ intel_context_create(struct intel_engine_cs *engine) return ERR_PTR(-ENOMEM);

intel_context_init(ce, engine); + trace_intel_context_create(ce); return ce; }

@@ -268,6 +271,8 @@ int __intel_context_do_pin_ww(struct intel_context *ce,

GEM_BUG_ON(!intel_context_is_pinned(ce)); /* no overflow! */

+ trace_intel_context_do_pin(ce); + err_unlock: mutex_unlock(&ce->pin_mutex); err_post_unpin: @@ -323,6 +328,7 @@ void __intel_context_do_unpin(struct intel_context *ce, int sub) */ intel_context_get(ce); intel_context_active_release(ce); + trace_intel_context_do_unpin(ce); intel_context_put(ce); }

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 d47a8358c831..26aadad10b12 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -344,6 +344,7 @@ static int guc_add_request(struct intel_guc *guc, struct i915_request *rq)

err = intel_guc_send_nb(guc, action, len, g2h_len_dw); if (!enabled && !err) { + trace_intel_context_sched_enable(ce); atomic_inc(&guc->outstanding_submission_g2h); set_context_enabled(ce); } else if (!enabled) { @@ -815,6 +816,8 @@ static int register_context(struct intel_context *ce) u32 offset = intel_guc_ggtt_offset(guc, guc->lrc_desc_pool) + ce->guc_id * sizeof(struct guc_lrc_desc);

+ trace_intel_context_register(ce); + return __guc_action_register_context(guc, ce->guc_id, offset); }

@@ -835,6 +838,8 @@ static int deregister_context(struct intel_context *ce, u32 guc_id) { struct intel_guc *guc = ce_to_guc(ce);

+ trace_intel_context_deregister(ce); + return __guc_action_deregister_context(guc, guc_id); }

@@ -908,6 +913,7 @@ static int guc_lrc_desc_pin(struct intel_context *ce) * registering this context. */ if (context_registered) { + trace_intel_context_steal_guc_id(ce); set_context_wait_for_deregister_to_register(ce); intel_context_get(ce);

@@ -971,6 +977,7 @@ static void __guc_context_sched_disable(struct intel_guc *guc,

GEM_BUG_ON(guc_id == GUC_INVALID_LRC_ID);

+ trace_intel_context_sched_disable(ce); intel_context_get(ce);

guc_submission_send_busy_loop(guc, action, ARRAY_SIZE(action), @@ -1133,6 +1140,9 @@ static void __guc_signal_context_fence(struct intel_context *ce)

lockdep_assert_held(&ce->guc_state.lock);

+ if (!list_empty(&ce->guc_state.fences)) + trace_intel_context_fence_release(ce); + list_for_each_entry(rq, &ce->guc_state.fences, guc_fence_link) i915_sw_fence_complete(&rq->submit);

@@ -1538,6 +1548,8 @@ int intel_guc_deregister_done_process_msg(struct intel_guc *guc, if (unlikely(!ce)) return -EPROTO;

+ trace_intel_context_deregister_done(ce); + if (context_wait_for_deregister_to_register(ce)) { struct intel_runtime_pm *runtime_pm = &ce->engine->gt->i915->runtime_pm; @@ -1589,6 +1601,8 @@ int intel_guc_sched_done_process_msg(struct intel_guc *guc, return -EPROTO; }

+ trace_intel_context_sched_done(ce); + if (context_pending_enable(ce)) { clr_context_pending_enable(ce); } else if (context_pending_disable(ce)) { diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index 478f5427531d..68b70626c3e2 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -895,6 +895,91 @@ TRACE_EVENT(i915_request_out, __entry->ctx, __entry->seqno, __entry->completed) );

+DECLARE_EVENT_CLASS(intel_context, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce), + + TP_STRUCT__entry( + __field(u32, guc_id) + __field(int, pin_count) + __field(u32, sched_state) + __field(u32, guc_sched_state_no_lock) + ), + + TP_fast_assign( + __entry->guc_id = ce->guc_id; + __entry->pin_count = atomic_read(&ce->pin_count); + __entry->sched_state = ce->guc_state.sched_state; + __entry->guc_sched_state_no_lock = + atomic_read(&ce->guc_sched_state_no_lock); + ), + + TP_printk("guc_id=%d, pin_count=%d sched_state=0x%x,0x%x", + __entry->guc_id, __entry->pin_count, + __entry->sched_state, + __entry->guc_sched_state_no_lock) +); + +DEFINE_EVENT(intel_context, intel_context_register, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + +DEFINE_EVENT(intel_context, intel_context_deregister, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + +DEFINE_EVENT(intel_context, intel_context_deregister_done, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + +DEFINE_EVENT(intel_context, intel_context_sched_enable, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + +DEFINE_EVENT(intel_context, intel_context_sched_disable, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + +DEFINE_EVENT(intel_context, intel_context_sched_done, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + +DEFINE_EVENT(intel_context, intel_context_create, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + +DEFINE_EVENT(intel_context, intel_context_fence_release, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + +DEFINE_EVENT(intel_context, intel_context_free, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + +DEFINE_EVENT(intel_context, intel_context_steal_guc_id, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + +DEFINE_EVENT(intel_context, intel_context_do_pin, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + +DEFINE_EVENT(intel_context, intel_context_do_unpin, + TP_PROTO(struct intel_context *ce), + TP_ARGS(ce) +); + #else #if !defined(TRACE_HEADER_MULTI_READ) static inline void @@ -921,6 +1006,66 @@ static inline void trace_i915_request_out(struct i915_request *rq) { } + +static inline void +trace_intel_context_register(struct intel_context *ce) +{ +} + +static inline void +trace_intel_context_deregister(struct intel_context *ce) +{ +} + +static inline void +trace_intel_context_deregister_done(struct intel_context *ce) +{ +} + +static inline void +trace_intel_context_sched_enable(struct intel_context *ce) +{ +} + +static inline void +trace_intel_context_sched_disable(struct intel_context *ce) +{ +} + +static inline void +trace_intel_context_sched_done(struct intel_context *ce) +{ +} + +static inline void +trace_intel_context_create(struct intel_context *ce) +{ +} + +static inline void +trace_intel_context_fence_release(struct intel_context *ce) +{ +} + +static inline void +trace_intel_context_free(struct intel_context *ce) +{ +} + +static inline void +trace_intel_context_steal_guc_id(struct intel_context *ce) +{ +} + +static inline void +trace_intel_context_do_pin(struct intel_context *ce) +{ +} + +static inline void +trace_intel_context_do_unpin(struct intel_context *ce) +{ +} #endif #endif