diff options
Diffstat (limited to 'drivers/gpu')
-rw-r--r-- | drivers/gpu/drm/i915/display/intel_fbc.c | 3 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gem/i915_gem_domain.c | 7 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gt/intel_context_types.h | 8 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gt/intel_engine.h | 9 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gt/intel_engine_cs.c | 6 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gt/intel_engine_types.h | 35 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gt/intel_gt_irq.c | 15 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gt/intel_lrc.c | 117 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gt/selftest_lrc.c | 34 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c | 2 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/gvt/scheduler.c | 4 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/i915_gpu_error.c | 12 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/i915_irq.c | 16 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/i915_perf.c | 6 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/i915_reg.h | 1 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/i915_vma.c | 25 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/intel_pm.c | 2 | ||||
-rw-r--r-- | drivers/gpu/drm/i915/selftests/i915_vma.c | 2 | ||||
-rw-r--r-- | drivers/gpu/drm/tegra/drm.c | 3 | ||||
-rw-r--r-- | drivers/gpu/host1x/dev.c | 59 |
20 files changed, 237 insertions, 129 deletions
diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c index 2e5d835a9eaa..c125ca9ab9b3 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.c +++ b/drivers/gpu/drm/i915/display/intel_fbc.c @@ -485,8 +485,7 @@ static int intel_fbc_alloc_cfb(struct drm_i915_private *dev_priv, if (!ret) goto err_llb; else if (ret > 1) { - DRM_INFO("Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n"); - + DRM_INFO_ONCE("Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n"); } fbc->threshold = ret; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c index 0cc40e77bbd2..4f96c8788a2e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c @@ -368,7 +368,6 @@ static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj) struct drm_i915_private *i915 = to_i915(obj->base.dev); struct i915_vma *vma; - GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj)); if (!atomic_read(&obj->bind_count)) return; @@ -400,12 +399,8 @@ static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj) void i915_gem_object_unpin_from_display_plane(struct i915_vma *vma) { - struct drm_i915_gem_object *obj = vma->obj; - - assert_object_held(obj); - /* Bump the LRU to try and avoid premature eviction whilst flipping */ - i915_gem_object_bump_inactive_ggtt(obj); + i915_gem_object_bump_inactive_ggtt(vma->obj); i915_vma_unpin(vma); } diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index 07cb83a0d017..ca0d4f4f3615 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -69,7 +69,13 @@ struct intel_context { #define CONTEXT_NOPREEMPT 7 u32 *lrc_reg_state; - u64 lrc_desc; + union { + struct { + u32 lrca; + u32 ccid; + }; + u64 desc; + } lrc; u32 tag; /* cookie passed to HW to track this context on submission */ /* Time on GPU as tracked by the hw. */ diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h index b469de0dd9b6..a1aa0d3e8be1 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine.h +++ b/drivers/gpu/drm/i915/gt/intel_engine.h @@ -333,13 +333,4 @@ intel_engine_has_preempt_reset(const struct intel_engine_cs *engine) return intel_engine_has_preemption(engine); } -static inline bool -intel_engine_has_timeslices(const struct intel_engine_cs *engine) -{ - if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION)) - return false; - - return intel_engine_has_semaphores(engine); -} - #endif /* _INTEL_RINGBUFFER_H_ */ diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 3aa8a652c16d..883a9b7fe88d 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -1295,6 +1295,12 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine, if (engine->id == RENDER_CLASS && IS_GEN_RANGE(dev_priv, 4, 7)) drm_printf(m, "\tCCID: 0x%08x\n", ENGINE_READ(engine, CCID)); + if (HAS_EXECLISTS(dev_priv)) { + drm_printf(m, "\tEL_STAT_HI: 0x%08x\n", + ENGINE_READ(engine, RING_EXECLIST_STATUS_HI)); + drm_printf(m, "\tEL_STAT_LO: 0x%08x\n", + ENGINE_READ(engine, RING_EXECLIST_STATUS_LO)); + } drm_printf(m, "\tRING_START: 0x%08x\n", ENGINE_READ(engine, RING_START)); drm_printf(m, "\tRING_HEAD: 0x%08x\n", diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index 80cdde712842..0be674ae1cf6 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -157,6 +157,20 @@ struct intel_engine_execlists { struct i915_priolist default_priolist; /** + * @ccid: identifier for contexts submitted to this engine + */ + u32 ccid; + + /** + * @yield: CCID at the time of the last semaphore-wait interrupt. + * + * Instead of leaving a semaphore busy-spinning on an engine, we would + * like to switch to another ready context, i.e. yielding the semaphore + * timeslice. + */ + u32 yield; + + /** * @error_interrupt: CS Master EIR * * The CS generates an interrupt when it detects an error. We capture @@ -295,8 +309,7 @@ struct intel_engine_cs { u32 context_size; u32 mmio_base; - unsigned int context_tag; -#define NUM_CONTEXT_TAG roundup_pow_of_two(2 * EXECLIST_MAX_PORTS) + unsigned long context_tag; struct rb_node uabi_node; @@ -483,10 +496,11 @@ struct intel_engine_cs { #define I915_ENGINE_SUPPORTS_STATS BIT(1) #define I915_ENGINE_HAS_PREEMPTION BIT(2) #define I915_ENGINE_HAS_SEMAPHORES BIT(3) -#define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(4) -#define I915_ENGINE_IS_VIRTUAL BIT(5) -#define I915_ENGINE_HAS_RELATIVE_MMIO BIT(6) -#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(7) +#define I915_ENGINE_HAS_TIMESLICES BIT(4) +#define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(5) +#define I915_ENGINE_IS_VIRTUAL BIT(6) +#define I915_ENGINE_HAS_RELATIVE_MMIO BIT(7) +#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(8) unsigned int flags; /* @@ -585,6 +599,15 @@ intel_engine_has_semaphores(const struct intel_engine_cs *engine) } static inline bool +intel_engine_has_timeslices(const struct intel_engine_cs *engine) +{ + if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION)) + return false; + + return engine->flags & I915_ENGINE_HAS_TIMESLICES; +} + +static inline bool intel_engine_needs_breadcrumb_tasklet(const struct intel_engine_cs *engine) { return engine->flags & I915_ENGINE_NEEDS_BREADCRUMB_TASKLET; diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c index f0e7fd95165a..0cc7dd54f4f9 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c @@ -39,6 +39,15 @@ cs_irq_handler(struct intel_engine_cs *engine, u32 iir) } } + if (iir & GT_WAIT_SEMAPHORE_INTERRUPT) { + WRITE_ONCE(engine->execlists.yield, + ENGINE_READ_FW(engine, RING_EXECLIST_STATUS_HI)); + ENGINE_TRACE(engine, "semaphore yield: %08x\n", + engine->execlists.yield); + if (del_timer(&engine->execlists.timer)) + tasklet = true; + } + if (iir & GT_CONTEXT_SWITCH_INTERRUPT) tasklet = true; @@ -228,7 +237,8 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt) const u32 irqs = GT_CS_MASTER_ERROR_INTERRUPT | GT_RENDER_USER_INTERRUPT | - GT_CONTEXT_SWITCH_INTERRUPT; + GT_CONTEXT_SWITCH_INTERRUPT | + GT_WAIT_SEMAPHORE_INTERRUPT; struct intel_uncore *uncore = gt->uncore; const u32 dmask = irqs << 16 | irqs; const u32 smask = irqs << 16; @@ -366,7 +376,8 @@ void gen8_gt_irq_postinstall(struct intel_gt *gt) const u32 irqs = GT_CS_MASTER_ERROR_INTERRUPT | GT_RENDER_USER_INTERRUPT | - GT_CONTEXT_SWITCH_INTERRUPT; + GT_CONTEXT_SWITCH_INTERRUPT | + GT_WAIT_SEMAPHORE_INTERRUPT; const u32 gt_interrupts[] = { irqs << GEN8_RCS_IRQ_SHIFT | irqs << GEN8_BCS_IRQ_SHIFT, irqs << GEN8_VCS0_IRQ_SHIFT | irqs << GEN8_VCS1_IRQ_SHIFT, diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 683014e7bc51..77420372d813 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -456,10 +456,10 @@ assert_priority_queue(const struct i915_request *prev, * engine info, SW context ID and SW counter need to form a unique number * (Context ID) per lrc. */ -static u64 +static u32 lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine) { - u64 desc; + u32 desc; desc = INTEL_LEGACY_32B_CONTEXT; if (i915_vm_is_4lvl(ce->vm)) @@ -470,21 +470,7 @@ lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine) if (IS_GEN(engine->i915, 8)) desc |= GEN8_CTX_L3LLC_COHERENT; - desc |= i915_ggtt_offset(ce->state); /* bits 12-31 */ - /* - * The following 32bits are copied into the OA reports (dword 2). - * Consider updating oa_get_render_ctx_id in i915_perf.c when changing - * anything below. - */ - if (INTEL_GEN(engine->i915) >= 11) { - desc |= (u64)engine->instance << GEN11_ENGINE_INSTANCE_SHIFT; - /* bits 48-53 */ - - desc |= (u64)engine->class << GEN11_ENGINE_CLASS_SHIFT; - /* bits 61-63 */ - } - - return desc; + return i915_ggtt_offset(ce->state) | desc; } static inline unsigned int dword_in_page(void *addr) @@ -1192,7 +1178,7 @@ static void reset_active(struct i915_request *rq, __execlists_update_reg_state(ce, engine, head); /* We've switched away, so this should be a no-op, but intent matters */ - ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; + ce->lrc.desc |= CTX_DESC_FORCE_RESTORE; } static u32 intel_context_get_runtime(const struct intel_context *ce) @@ -1251,18 +1237,23 @@ __execlists_schedule_in(struct i915_request *rq) if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)) execlists_check_context(ce, engine); - ce->lrc_desc &= ~GENMASK_ULL(47, 37); if (ce->tag) { /* Use a fixed tag for OA and friends */ - ce->lrc_desc |= (u64)ce->tag << 32; + GEM_BUG_ON(ce->tag <= BITS_PER_LONG); + ce->lrc.ccid = ce->tag; } else { /* We don't need a strict matching tag, just different values */ - ce->lrc_desc |= - (u64)(++engine->context_tag % NUM_CONTEXT_TAG) << - GEN11_SW_CTX_ID_SHIFT; - BUILD_BUG_ON(NUM_CONTEXT_TAG > GEN12_MAX_CONTEXT_HW_ID); + unsigned int tag = ffs(engine->context_tag); + + GEM_BUG_ON(tag == 0 || tag >= BITS_PER_LONG); + clear_bit(tag - 1, &engine->context_tag); + ce->lrc.ccid = tag << (GEN11_SW_CTX_ID_SHIFT - 32); + + BUILD_BUG_ON(BITS_PER_LONG > GEN12_MAX_CONTEXT_HW_ID); } + ce->lrc.ccid |= engine->execlists.ccid; + __intel_gt_pm_get(engine->gt); execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_IN); intel_engine_context_in(engine); @@ -1302,7 +1293,8 @@ static void kick_siblings(struct i915_request *rq, struct intel_context *ce) static inline void __execlists_schedule_out(struct i915_request *rq, - struct intel_engine_cs * const engine) + struct intel_engine_cs * const engine, + unsigned int ccid) { struct intel_context * const ce = rq->context; @@ -1320,6 +1312,14 @@ __execlists_schedule_out(struct i915_request *rq, i915_request_completed(rq)) intel_engine_add_retire(engine, ce->timeline); + ccid >>= GEN11_SW_CTX_ID_SHIFT - 32; + ccid &= GEN12_MAX_CONTEXT_HW_ID; + if (ccid < BITS_PER_LONG) { + GEM_BUG_ON(ccid == 0); + GEM_BUG_ON(test_bit(ccid - 1, &engine->context_tag)); + set_bit(ccid - 1, &engine->context_tag); + } + intel_context_update_runtime(ce); intel_engine_context_out(engine); execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT); @@ -1345,15 +1345,17 @@ execlists_schedule_out(struct i915_request *rq) { struct intel_context * const ce = rq->context; struct intel_engine_cs *cur, *old; + u32 ccid; trace_i915_request_out(rq); + ccid = rq->context->lrc.ccid; old = READ_ONCE(ce->inflight); do cur = ptr_unmask_bits(old, 2) ? ptr_dec(old) : NULL; while (!try_cmpxchg(&ce->inflight, &old, cur)); if (!cur) - __execlists_schedule_out(rq, old); + __execlists_schedule_out(rq, old, ccid); i915_request_put(rq); } @@ -1361,7 +1363,7 @@ execlists_schedule_out(struct i915_request *rq) static u64 execlists_update_context(struct i915_request *rq) { struct intel_context *ce = rq->context; - u64 desc = ce->lrc_desc; + u64 desc = ce->lrc.desc; u32 tail, prev; /* @@ -1400,7 +1402,7 @@ static u64 execlists_update_context(struct i915_request *rq) */ wmb(); - ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE; + ce->lrc.desc &= ~CTX_DESC_FORCE_RESTORE; return desc; } @@ -1754,7 +1756,8 @@ static void defer_active(struct intel_engine_cs *engine) } static bool -need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq) +need_timeslice(const struct intel_engine_cs *engine, + const struct i915_request *rq) { int hint; @@ -1768,6 +1771,32 @@ need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq) return hint >= effective_prio(rq); } +static bool +timeslice_yield(const struct intel_engine_execlists *el, + const struct i915_request *rq) +{ + /* + * Once bitten, forever smitten! + * + * If the active context ever busy-waited on a semaphore, + * it will be treated as a hog until the end of its timeslice (i.e. + * until it is scheduled out and replaced by a new submission, + * possibly even its own lite-restore). The HW only sends an interrupt + * on the first miss, and we do know if that semaphore has been + * signaled, or even if it is now stuck on another semaphore. Play + * safe, yield if it might be stuck -- it will be given a fresh + * timeslice in the near future. + */ + return rq->context->lrc.ccid == READ_ONCE(el->yield); +} + +static bool +timeslice_expired(const struct intel_engine_execlists *el, + const struct i915_request *rq) +{ + return timer_expired(&el->timer) || timeslice_yield(el, rq); +} + static int switch_prio(struct intel_engine_cs *engine, const struct i915_request *rq) { @@ -1783,8 +1812,7 @@ timeslice(const struct intel_engine_cs *engine) return READ_ONCE(engine->props.timeslice_duration_ms); } -static unsigned long -active_timeslice(const struct intel_engine_cs *engine) +static unsigned long active_timeslice(const struct intel_engine_cs *engine) { const struct intel_engine_execlists *execlists = &engine->execlists; const struct i915_request *rq = *execlists->active; @@ -1946,13 +1974,14 @@ static void execlists_dequeue(struct intel_engine_cs *engine) last = NULL; } else if (need_timeslice(engine, last) && - timer_expired(&engine->execlists.timer)) { + timeslice_expired(execlists, last)) { ENGINE_TRACE(engine, - "expired last=%llx:%lld, prio=%d, hint=%d\n", + "expired last=%llx:%lld, prio=%d, hint=%d, yield?=%s\n", last->fence.context, last->fence.seqno, last->sched.attr.priority, - execlists->queue_priority_hint); + execlists->queue_priority_hint, + yesno(timeslice_yield(execlists, last))); ring_set_paused(engine, 1); defer_active(engine); @@ -2213,6 +2242,7 @@ done: } clear_ports(port + 1, last_port - port); + WRITE_ONCE(execlists->yield, -1); execlists_submit_ports(engine); set_preempt_timeout(engine, *active); } else { @@ -3043,7 +3073,7 @@ __execlists_context_pin(struct intel_context *ce, if (IS_ERR(vaddr)) return PTR_ERR(vaddr); - ce->lrc_desc = lrc_descriptor(ce, engine) | CTX_DESC_FORCE_RESTORE; + ce->lrc.lrca = lrc_descriptor(ce, engine) | CTX_DESC_FORCE_RESTORE; ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE; __execlists_update_reg_state(ce, engine, ce->ring->tail); @@ -3072,7 +3102,7 @@ static void execlists_context_reset(struct intel_context *ce) ce, ce->engine, ce->ring, true); __execlists_update_reg_state(ce, ce->engine, ce->ring->tail); - ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; + ce->lrc.desc |= CTX_DESC_FORCE_RESTORE; } static const struct intel_context_ops execlists_context_ops = { @@ -3541,7 +3571,7 @@ static void enable_execlists(struct intel_engine_cs *engine) enable_error_interrupt(engine); - engine->context_tag = 0; + engine->context_tag = GENMASK(BITS_PER_LONG - 2, 0); } static bool unexpected_starting_state(struct intel_engine_cs *engine) @@ -3753,7 +3783,7 @@ out_replay: head, ce->ring->tail); __execlists_reset_reg_state(ce, engine); __execlists_update_reg_state(ce, engine, head); - ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; /* paranoid: GPU was reset! */ + ce->lrc.desc |= CTX_DESC_FORCE_RESTORE; /* paranoid: GPU was reset! */ unwind: /* Push back any incomplete requests for replay after the reset. */ @@ -4369,8 +4399,11 @@ void intel_execlists_set_default_submission(struct intel_engine_cs *engine) engine->flags |= I915_ENGINE_SUPPORTS_STATS; if (!intel_vgpu_active(engine->i915)) { engine->flags |= I915_ENGINE_HAS_SEMAPHORES; - if (HAS_LOGICAL_RING_PREEMPTION(engine->i915)) + if (HAS_LOGICAL_RING_PREEMPTION(engine->i915)) { engine->flags |= I915_ENGINE_HAS_PREEMPTION; + if (IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION)) + engine->flags |= I915_ENGINE_HAS_TIMESLICES; + } } if (INTEL_GEN(engine->i915) >= 12) @@ -4449,6 +4482,7 @@ logical_ring_default_irqs(struct intel_engine_cs *engine) engine->irq_enable_mask = GT_RENDER_USER_INTERRUPT << shift; engine->irq_keep_mask = GT_CONTEXT_SWITCH_INTERRUPT << shift; engine->irq_keep_mask |= GT_CS_MASTER_ERROR_INTERRUPT << shift; + engine->irq_keep_mask |= GT_WAIT_SEMAPHORE_INTERRUPT << shift; } static void rcs_submission_override(struct intel_engine_cs *engine) @@ -4516,6 +4550,11 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine) else execlists->csb_size = GEN11_CSB_ENTRIES; + if (INTEL_GEN(engine->i915) >= 11) { + execlists->ccid |= engine->instance << (GEN11_ENGINE_INSTANCE_SHIFT - 32); + execlists->ccid |= engine->class << (GEN11_ENGINE_CLASS_SHIFT - 32); + } + reset_csb_pointers(engine); /* Finally, take ownership and responsibility for cleanup! */ diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c index 6f06ba750a0a..f95ae15ce865 100644 --- a/drivers/gpu/drm/i915/gt/selftest_lrc.c +++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c @@ -929,7 +929,7 @@ create_rewinder(struct intel_context *ce, goto err; } - cs = intel_ring_begin(rq, 10); + cs = intel_ring_begin(rq, 14); if (IS_ERR(cs)) { err = PTR_ERR(cs); goto err; @@ -941,8 +941,8 @@ create_rewinder(struct intel_context *ce, *cs++ = MI_SEMAPHORE_WAIT | MI_SEMAPHORE_GLOBAL_GTT | MI_SEMAPHORE_POLL | - MI_SEMAPHORE_SAD_NEQ_SDD; - *cs++ = 0; + MI_SEMAPHORE_SAD_GTE_SDD; + *cs++ = idx; *cs++ = offset; *cs++ = 0; @@ -951,6 +951,11 @@ create_rewinder(struct intel_context *ce, *cs++ = offset + idx * sizeof(u32); *cs++ = 0; + *cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT; + *cs++ = offset; + *cs++ = 0; + *cs++ = idx + 1; + intel_ring_advance(rq, cs); rq->sched.attr.priority = I915_PRIORITY_MASK; @@ -984,7 +989,7 @@ static int live_timeslice_rewind(void *arg) for_each_engine(engine, gt, id) { enum { A1, A2, B1 }; - enum { X = 1, Y, Z }; + enum { X = 1, Z, Y }; struct i915_request *rq[3] = {}; struct intel_context *ce; unsigned long heartbeat; @@ -1017,13 +1022,13 @@ static int live_timeslice_rewind(void *arg) goto err; } - rq[0] = create_rewinder(ce, NULL, slot, 1); + rq[0] = create_rewinder(ce, NULL, slot, X); if (IS_ERR(rq[0])) { intel_context_put(ce); goto err; } - rq[1] = create_rewinder(ce, NULL, slot, 2); + rq[1] = create_rewinder(ce, NULL, slot, Y); intel_context_put(ce); if (IS_ERR(rq[1])) goto err; @@ -1041,7 +1046,7 @@ static int live_timeslice_rewind(void *arg) goto err; } - rq[2] = create_rewinder(ce, rq[0], slot, 3); + rq[2] = create_rewinder(ce, rq[0], slot, Z); intel_context_put(ce); if (IS_ERR(rq[2])) goto err; @@ -1055,15 +1060,12 @@ static int live_timeslice_rewind(void *arg) GEM_BUG_ON(!timer_pending(&engine->execlists.timer)); /* ELSP[] = { { A:rq1, A:rq2 }, { B:rq1 } } */ - GEM_BUG_ON(!i915_request_is_active(rq[A1])); - GEM_BUG_ON(!i915_request_is_active(rq[A2])); - GEM_BUG_ON(!i915_request_is_active(rq[B1])); - - /* Wait for the timeslice to kick in */ - del_timer(&engine->execlists.timer); - tasklet_hi_schedule(&engine->execlists.tasklet); - intel_engine_flush_submission(engine); - + if (i915_request_is_active(rq[A2])) { /* semaphore yielded! */ + /* Wait for the timeslice to kick in */ + del_timer(&engine->execlists.timer); + tasklet_hi_schedule(&engine->execlists.tasklet); + intel_engine_flush_submission(engine); + } /* -> ELSP[] = { { A:rq1 }, { B:rq1 } } */ GEM_BUG_ON(!i915_request_is_active(rq[A1])); GEM_BUG_ON(!i915_request_is_active(rq[B1])); 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 fe7778c28d2d..aa6d56e25a10 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -217,7 +217,7 @@ static void guc_wq_item_append(struct intel_guc *guc, static void guc_add_request(struct intel_guc *guc, struct i915_request *rq) { struct intel_engine_cs *engine = rq->engine; - u32 ctx_desc = lower_32_bits(rq->context->lrc_desc); + u32 ctx_desc = rq->context->lrc.ccid; u32 ring_tail = intel_ring_set_tail(rq->ring, rq->tail) / sizeof(u64); guc_wq_item_append(guc, engine->guc_id, ctx_desc, diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index cb11c3184085..6eb6710b35e9 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -290,7 +290,7 @@ static void shadow_context_descriptor_update(struct intel_context *ce, struct intel_vgpu_workload *workload) { - u64 desc = ce->lrc_desc; + u64 desc = ce->lrc.desc; /* * Update bits 0-11 of the context descriptor which includes flags @@ -300,7 +300,7 @@ shadow_context_descriptor_update(struct intel_context *ce, desc |= (u64)workload->ctx_desc.addressing_mode << GEN8_CTX_ADDRESSING_MODE_SHIFT; - ce->lrc_desc = desc; + ce->lrc.desc = desc; } static int copy_workload_to_ring_buffer(struct intel_vgpu_workload *workload) diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 2a4cd0ba5464..5c8e51d2ba5b 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1207,8 +1207,6 @@ static void engine_record_registers(struct intel_engine_coredump *ee) static void record_request(const struct i915_request *request, struct i915_request_coredump *erq) { - const struct i915_gem_context *ctx; - erq->flags = request->fence.flags; erq->context = request->fence.context; erq->seqno = request->fence.seqno; @@ -1219,9 +1217,13 @@ static void record_request(const struct i915_request *request, erq->pid = 0; rcu_read_lock(); - ctx = rcu_dereference(request->context->gem_context); - if (ctx) - erq->pid = pid_nr(ctx->pid); + if (!intel_context_is_closed(request->context)) { + const struct i915_gem_context *ctx; + + ctx = rcu_dereference(request->context->gem_context); + if (ctx) + erq->pid = pid_nr(ctx->pid); + } rcu_read_unlock(); } diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index d91557d842dc..8a2b83807ffc 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -3361,7 +3361,7 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) u32 de_pipe_masked = gen8_de_pipe_fault_mask(dev_priv) | GEN8_PIPE_CDCLK_CRC_DONE; u32 de_pipe_enables; - u32 de_port_masked = GEN8_AUX_CHANNEL_A; + u32 de_port_masked = gen8_de_port_aux_mask(dev_priv); u32 de_port_enables; u32 de_misc_masked = GEN8_DE_EDP_PSR; enum pipe pipe; @@ -3369,18 +3369,8 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) if (INTEL_GEN(dev_priv) <= 10) de_misc_masked |= GEN8_DE_MISC_GSE; - if (INTEL_GEN(dev_priv) >= 9) { - de_port_masked |= GEN9_AUX_CHANNEL_B | GEN9_AUX_CHANNEL_C | - GEN9_AUX_CHANNEL_D; - if (IS_GEN9_LP(dev_priv)) - de_port_masked |= BXT_DE_PORT_GMBUS; - } - - if (INTEL_GEN(dev_priv) >= 11) - de_port_masked |= ICL_AUX_CHANNEL_E; - - if (IS_CNL_WITH_PORT_F(dev_priv) || INTEL_GEN(dev_priv) >= 11) - de_port_masked |= CNL_AUX_CHANNEL_F; + if (IS_GEN9_LP(dev_priv)) + de_port_masked |= BXT_DE_PORT_GMBUS; de_pipe_enables = de_pipe_masked | GEN8_PIPE_VBLANK | GEN8_PIPE_FIFO_UNDERRUN; diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 66a46e41d5ef..cf2c01f17da8 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -1310,8 +1310,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream) * dropped by GuC. They won't be part of the context * ID in the OA reports, so squash those lower bits. */ - stream->specific_ctx_id = - lower_32_bits(ce->lrc_desc) >> 12; + stream->specific_ctx_id = ce->lrc.lrca >> 12; /* * GuC uses the top bit to signal proxy submission, so @@ -1328,11 +1327,10 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream) ((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32); /* * Pick an unused context id - * 0 - (NUM_CONTEXT_TAG - 1) are used by other contexts + * 0 - BITS_PER_LONG are used by other contexts * GEN12_MAX_CONTEXT_HW_ID (0x7ff) is used by idle context */ stream->specific_ctx_id = (GEN12_MAX_CONTEXT_HW_ID - 1) << (GEN11_SW_CTX_ID_SHIFT - 32); - BUILD_BUG_ON((GEN12_MAX_CONTEXT_HW_ID - 1) < NUM_CONTEXT_TAG); break; } diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index e0c6021fdaf9..6e12000c4b6b 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -3094,6 +3094,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GT_BSD_CS_ERROR_INTERRUPT (1 << 15) #define GT_BSD_USER_INTERRUPT (1 << 12) #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1 (1 << 11) /* hsw+; rsvd on snb, ivb, vlv */ +#define GT_WAIT_SEMAPHORE_INTERRUPT REG_BIT(11) /* bdw+ */ #define GT_CONTEXT_SWITCH_INTERRUPT (1 << 8) #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT (1 << 5) /* !snb */ #define GT_RENDER_PIPECTL_NOTIFY_INTERRUPT (1 << 4) diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 82e3bc280622..2cd7a7e87c0a 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -1228,18 +1228,6 @@ int __i915_vma_unbind(struct i915_vma *vma) lockdep_assert_held(&vma->vm->mutex); - /* - * First wait upon any activity as retiring the request may - * have side-effects such as unpinning or even unbinding this vma. - * - * XXX Actually waiting under the vm->mutex is a hinderance and - * should be pipelined wherever possible. In cases where that is - * unavoidable, we should lift the wait to before the mutex. - */ - ret = i915_vma_sync(vma); - if (ret) - return ret; - if (i915_vma_is_pinned(vma)) { vma_print_allocator(vma, "is pinned"); return -EAGAIN; @@ -1313,15 +1301,20 @@ int i915_vma_unbind(struct i915_vma *vma) if (!drm_mm_node_allocated(&vma->node)) return 0; - if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND)) - /* XXX not always required: nop_clear_range */ - wakeref = intel_runtime_pm_get(&vm->i915->runtime_pm); - /* Optimistic wait before taking the mutex */ err = i915_vma_sync(vma); if (err) goto out_rpm; + if (i915_vma_is_pinned(vma)) { + vma_print_allocator(vma, "is pinned"); + return -EAGAIN; + } + + if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND)) + /* XXX not always required: nop_clear_range */ + wakeref = intel_runtime_pm_get(&vm->i915->runtime_pm); + err = mutex_lock_interruptible(&vm->mutex); if (err) goto out_rpm; diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 8375054ba27d..a52986a9e7a6 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4992,7 +4992,7 @@ static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state, * WaIncreaseLatencyIPCEnabled: kbl,cfl * Display WA #1141: kbl,cfl */ - if ((IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv)) || + if ((IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv)) && dev_priv->ipc_enabled) latency += 4; diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c index 58b5f40a07dd..af89c7fc8f59 100644 --- a/drivers/gpu/drm/i915/selftests/i915_vma.c +++ b/drivers/gpu/drm/i915/selftests/i915_vma.c @@ -173,7 +173,7 @@ static int igt_vma_create(void *arg) } nc = 0; - for_each_prime_number(num_ctx, 2 * NUM_CONTEXT_TAG) { + for_each_prime_number(num_ctx, 2 * BITS_PER_LONG) { for (; nc < num_ctx; nc++) { ctx = mock_context(i915, "mock"); if (!ctx) diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index bd268028fb3d..583cd6e0ae27 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -1039,6 +1039,7 @@ void tegra_drm_free(struct tegra_drm *tegra, size_t size, void *virt, static bool host1x_drm_wants_iommu(struct host1x_device *dev) { + struct host1x *host1x = dev_get_drvdata(dev->dev.parent); struct iommu_domain *domain; /* @@ -1076,7 +1077,7 @@ static bool host1x_drm_wants_iommu(struct host1x_device *dev) * sufficient and whether or not the host1x is attached to an IOMMU * doesn't matter. */ - if (!domain && dma_get_mask(dev->dev.parent) <= DMA_BIT_MASK(32)) + if (!domain && host1x_get_dma_mask(host1x) <= DMA_BIT_MASK(32)) return true; return domain != NULL; diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c index 388bcc2889aa..d24344e91922 100644 --- a/drivers/gpu/host1x/dev.c +++ b/drivers/gpu/host1x/dev.c @@ -192,17 +192,55 @@ static void host1x_setup_sid_table(struct host1x *host) } } +static bool host1x_wants_iommu(struct host1x *host1x) +{ + /* + * If we support addressing a maximum of 32 bits of physical memory + * and if the host1x firewall is enabled, there's no need to enable + * IOMMU support. This can happen for example on Tegra20, Tegra30 + * and Tegra114. + * + * Tegra124 and later can address up to 34 bits of physical memory and + * many platforms come equipped with more than 2 GiB of system memory, + * which requires crossing the 4 GiB boundary. But there's a catch: on + * SoCs before Tegra186 (i.e. Tegra124 and Tegra210), the host1x can + * only address up to 32 bits of memory in GATHER opcodes, which means + * that command buffers need to either be in the first 2 GiB of system + * memory (which could quickly lead to memory exhaustion), or command + * buffers need to be treated differently from other buffers (which is + * not possible with the current ABI). + * + * A third option is to use the IOMMU in these cases to make sure all + * buffers will be mapped into a 32-bit IOVA space that host1x can + * address. This allows all of the system memory to be used and works + * within the limitations of the host1x on these SoCs. + * + * In summary, default to enable IOMMU on Tegra124 and later. For any + * of the earlier SoCs, only use the IOMMU for additional safety when + * the host1x firewall is disabled. + */ + if (host1x->info->dma_mask <= DMA_BIT_MASK(32)) { + if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL)) + return false; + } + + return true; +} + static struct iommu_domain *host1x_iommu_attach(struct host1x *host) { struct iommu_domain *domain = iommu_get_domain_for_dev(host->dev); int err; /* - * If the host1x firewall is enabled, there's no need to enable IOMMU - * support. Similarly, if host1x is already attached to an IOMMU (via - * the DMA API), don't try to attach again. + * We may not always want to enable IOMMU support (for example if the + * host1x firewall is already enabled and we don't support addressing + * more than 32 bits of physical memory), so check for that first. + * + * Similarly, if host1x is already attached to an IOMMU (via the DMA + * API), don't try to attach again. */ - if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL) || domain) + if (!host1x_wants_iommu(host) || domain) return domain; host->group = iommu_group_get(host->dev); @@ -502,6 +540,19 @@ static void __exit tegra_host1x_exit(void) } module_exit(tegra_host1x_exit); +/** + * host1x_get_dma_mask() - query the supported DMA mask for host1x + * @host1x: host1x instance + * + * Note that this returns the supported DMA mask for host1x, which can be + * different from the applicable DMA mask under certain circumstances. + */ +u64 host1x_get_dma_mask(struct host1x *host1x) +{ + return host1x->info->dma_mask; +} +EXPORT_SYMBOL(host1x_get_dma_mask); + MODULE_AUTHOR("Thierry Reding <thierry.reding@avionic-design.de>"); MODULE_AUTHOR("Terje Bergstrom <tbergstrom@nvidia.com>"); MODULE_DESCRIPTION("Host1x driver for Tegra products"); |