diff options
Diffstat (limited to 'drivers/gpu/drm/i915/gt')
105 files changed, 1306 insertions, 1421 deletions
diff --git a/drivers/gpu/drm/i915/gt/debugfs_gt.c b/drivers/gpu/drm/i915/gt/debugfs_gt.c index 3a21cf63b3f0..591eb60785db 100644 --- a/drivers/gpu/drm/i915/gt/debugfs_gt.c +++ b/drivers/gpu/drm/i915/gt/debugfs_gt.c @@ -1,5 +1,4 @@ // SPDX-License-Identifier: MIT - /* * Copyright © 2019 Intel Corporation */ @@ -37,6 +36,7 @@ void intel_gt_debugfs_register_files(struct dentry *root, { while (count--) { umode_t mode = files->fops->write ? 0644 : 0444; + if (!files->eval || files->eval(data)) debugfs_create_file(files->name, mode, root, data, diff --git a/drivers/gpu/drm/i915/gt/gen2_engine_cs.c b/drivers/gpu/drm/i915/gt/gen2_engine_cs.c index b491a64919c8..9646200d2792 100644 --- a/drivers/gpu/drm/i915/gt/gen2_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen2_engine_cs.c @@ -143,7 +143,7 @@ static u32 *__gen2_emit_breadcrumb(struct i915_request *rq, u32 *cs, int flush, int post) { GEM_BUG_ON(i915_request_active_timeline(rq)->hwsp_ggtt != rq->engine->status_page.vma); - GEM_BUG_ON(offset_in_page(i915_request_active_timeline(rq)->hwsp_offset) != I915_GEM_HWS_SEQNO_ADDR); + GEM_BUG_ON(offset_in_page(rq->hwsp_seqno) != I915_GEM_HWS_SEQNO_ADDR); *cs++ = MI_FLUSH; diff --git a/drivers/gpu/drm/i915/gt/gen6_engine_cs.c b/drivers/gpu/drm/i915/gt/gen6_engine_cs.c index ce38d1bcaba3..b388ceeeb1c9 100644 --- a/drivers/gpu/drm/i915/gt/gen6_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen6_engine_cs.c @@ -161,7 +161,7 @@ u32 *gen6_emit_breadcrumb_rcs(struct i915_request *rq, u32 *cs) PIPE_CONTROL_DC_FLUSH_ENABLE | PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_CS_STALL); - *cs++ = i915_request_active_timeline(rq)->hwsp_offset | + *cs++ = i915_request_active_seqno(rq) | PIPE_CONTROL_GLOBAL_GTT; *cs++ = rq->fence.seqno; @@ -359,7 +359,7 @@ u32 *gen7_emit_breadcrumb_rcs(struct i915_request *rq, u32 *cs) PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_GLOBAL_GTT_IVB | PIPE_CONTROL_CS_STALL); - *cs++ = i915_request_active_timeline(rq)->hwsp_offset; + *cs++ = i915_request_active_seqno(rq); *cs++ = rq->fence.seqno; *cs++ = MI_USER_INTERRUPT; @@ -374,7 +374,7 @@ u32 *gen7_emit_breadcrumb_rcs(struct i915_request *rq, u32 *cs) u32 *gen6_emit_breadcrumb_xcs(struct i915_request *rq, u32 *cs) { GEM_BUG_ON(i915_request_active_timeline(rq)->hwsp_ggtt != rq->engine->status_page.vma); - GEM_BUG_ON(offset_in_page(i915_request_active_timeline(rq)->hwsp_offset) != I915_GEM_HWS_SEQNO_ADDR); + GEM_BUG_ON(offset_in_page(rq->hwsp_seqno) != I915_GEM_HWS_SEQNO_ADDR); *cs++ = MI_FLUSH_DW | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_DW_STORE_INDEX; *cs++ = I915_GEM_HWS_SEQNO_ADDR | MI_FLUSH_DW_USE_GTT; @@ -394,7 +394,7 @@ u32 *gen7_emit_breadcrumb_xcs(struct i915_request *rq, u32 *cs) int i; GEM_BUG_ON(i915_request_active_timeline(rq)->hwsp_ggtt != rq->engine->status_page.vma); - GEM_BUG_ON(offset_in_page(i915_request_active_timeline(rq)->hwsp_offset) != I915_GEM_HWS_SEQNO_ADDR); + GEM_BUG_ON(offset_in_page(rq->hwsp_seqno) != I915_GEM_HWS_SEQNO_ADDR); *cs++ = MI_FLUSH_DW | MI_INVALIDATE_TLB | MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_DW_STORE_INDEX; diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.h b/drivers/gpu/drm/i915/gt/gen6_ppgtt.h index 3357228f3304..6a61a5c3a85a 100644 --- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.h +++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.h @@ -59,9 +59,9 @@ static inline struct gen6_ppgtt *to_gen6_ppgtt(struct i915_ppgtt *base) for (iter = gen6_pde_index(start); \ length > 0 && iter < I915_PDES && \ (pt = i915_pt_entry(pd, iter), true); \ - ({ u32 temp = ALIGN(start+1, 1 << GEN6_PDE_SHIFT); \ + ({ u32 temp = ALIGN(start + 1, 1 << GEN6_PDE_SHIFT); \ temp = min(temp - start, length); \ - start += temp, length -= temp; }), ++iter) + start += temp; length -= temp; }), ++iter) #define gen6_for_all_pdes(pt, pd, iter) \ for (iter = 0; \ diff --git a/drivers/gpu/drm/i915/gt/gen6_renderstate.c b/drivers/gpu/drm/i915/gt/gen6_renderstate.c index 11c8e7b3dd7c..555e83f3a93a 100644 --- a/drivers/gpu/drm/i915/gt/gen6_renderstate.c +++ b/drivers/gpu/drm/i915/gt/gen6_renderstate.c @@ -1,25 +1,7 @@ +// SPDX-License-Identifier: MIT /* * Copyright © 2014 Intel Corporation * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice (including the next - * paragraph) shall be included in all copies or substantial portions of the - * Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * * Generated by: intel-gpu-tools-1.8-220-g01153e7 */ diff --git a/drivers/gpu/drm/i915/gt/gen7_renderstate.c b/drivers/gpu/drm/i915/gt/gen7_renderstate.c index 655180646152..c36e84d30d24 100644 --- a/drivers/gpu/drm/i915/gt/gen7_renderstate.c +++ b/drivers/gpu/drm/i915/gt/gen7_renderstate.c @@ -1,25 +1,7 @@ +// SPDX-License-Identifier: MIT /* * Copyright © 2014 Intel Corporation * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice (including the next - * paragraph) shall be included in all copies or substantial portions of the - * Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * * Generated by: intel-gpu-tools-1.8-220-g01153e7 */ diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index 07ba524da90b..732c2ed1d933 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -42,7 +42,7 @@ int gen8_emit_flush_rcs(struct i915_request *rq, u32 mode) vf_flush_wa = true; /* WaForGAMHang:kbl */ - if (IS_KBL_GT_REVID(rq->engine->i915, 0, KBL_REVID_B0)) + if (IS_KBL_GT_STEP(rq->engine->i915, 0, STEP_B0)) dc_flush_wa = true; } @@ -338,15 +338,14 @@ static u32 preempt_address(struct intel_engine_cs *engine) static u32 hwsp_offset(const struct i915_request *rq) { - const struct intel_timeline_cacheline *cl; + const struct intel_timeline *tl; - /* Before the request is executed, the timeline/cachline is fixed */ + /* Before the request is executed, the timeline is fixed */ + tl = rcu_dereference_protected(rq->timeline, + !i915_request_signaled(rq)); - cl = rcu_dereference_protected(rq->hwsp_cacheline, 1); - if (cl) - return cl->ggtt_offset; - - return rcu_dereference_protected(rq->timeline, 1)->hwsp_offset; + /* See the comment in i915_request_active_seqno(). */ + return page_mask_bits(tl->hwsp_offset) + offset_in_page(rq->hwsp_seqno); } int gen8_emit_init_breadcrumb(struct i915_request *rq) diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c index 755522ced60d..176c19633412 100644 --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c @@ -5,6 +5,8 @@ #include <linux/log2.h> +#include "gem/i915_gem_lmem.h" + #include "gen8_ppgtt.h" #include "i915_scatterlist.h" #include "i915_trace.h" @@ -35,6 +37,9 @@ static u64 gen8_pte_encode(dma_addr_t addr, if (unlikely(flags & PTE_READ_ONLY)) pte &= ~_PAGE_RW; + if (flags & PTE_LM) + pte |= GEN12_PPGTT_PTE_LM; + switch (level) { case I915_CACHE_NONE: pte |= PPAT_UNCACHED; @@ -145,6 +150,7 @@ static unsigned int gen8_pt_count(u64 start, u64 end) static unsigned int gen8_pd_top_count(const struct i915_address_space *vm) { unsigned int shift = __gen8_pte_shift(vm->top); + return (vm->total + (1ull << shift) - 1) >> shift; } @@ -557,6 +563,7 @@ static void gen8_ppgtt_insert(struct i915_address_space *vm, static int gen8_init_scratch(struct i915_address_space *vm) { + u32 pte_flags; int ret; int i; @@ -580,9 +587,13 @@ static int gen8_init_scratch(struct i915_address_space *vm) if (ret) return ret; + pte_flags = vm->has_read_only; + if (i915_gem_object_is_lmem(vm->scratch[0])) + pte_flags |= PTE_LM; + vm->scratch[0]->encode = gen8_pte_encode(px_dma(vm->scratch[0]), - I915_CACHE_LLC, vm->has_read_only); + I915_CACHE_LLC, pte_flags); for (i = 1; i <= vm->top; i++) { struct drm_i915_gem_object *obj; diff --git a/drivers/gpu/drm/i915/gt/gen8_renderstate.c b/drivers/gpu/drm/i915/gt/gen8_renderstate.c index 95288a34c15d..ef9d7b0dd2da 100644 --- a/drivers/gpu/drm/i915/gt/gen8_renderstate.c +++ b/drivers/gpu/drm/i915/gt/gen8_renderstate.c @@ -1,25 +1,7 @@ +// SPDX-License-Identifier: MIT /* * Copyright © 2014 Intel Corporation * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice (including the next - * paragraph) shall be included in all copies or substantial portions of the - * Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * * Generated by: intel-gpu-tools-1.8-220-g01153e7 */ diff --git a/drivers/gpu/drm/i915/gt/gen9_renderstate.c b/drivers/gpu/drm/i915/gt/gen9_renderstate.c index 7d3ac02f0177..428b724ded3e 100644 --- a/drivers/gpu/drm/i915/gt/gen9_renderstate.c +++ b/drivers/gpu/drm/i915/gt/gen9_renderstate.c @@ -1,25 +1,7 @@ +// SPDX-License-Identifier: MIT /* * Copyright © 2014 Intel Corporation * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice (including the next - * paragraph) shall be included in all copies or substantial portions of the - * Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * * Generated by: intel-gpu-tools-1.19-177-g68e2eab2 */ diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c index 34a645d6babd..38cc42783dfb 100644 --- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c +++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c @@ -1,25 +1,6 @@ +// SPDX-License-Identifier: MIT /* - * Copyright © 2015 Intel Corporation - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice (including the next - * paragraph) shall be included in all copies or substantial portions of the - * Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - * + * Copyright © 2015-2021 Intel Corporation */ #include <linux/kthread.h> diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index 349e7fa1488d..17cf2640b082 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h index d24ab6fa0ee5..f83a73a2b39f 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.h +++ b/drivers/gpu/drm/i915/gt/intel_context.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_context_param.h b/drivers/gpu/drm/i915/gt/intel_context_param.h index f053d8633fe2..3ecacc675f41 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_param.h +++ b/drivers/gpu/drm/i915/gt/intel_context_param.h @@ -6,9 +6,18 @@ #ifndef INTEL_CONTEXT_PARAM_H #define INTEL_CONTEXT_PARAM_H -struct intel_context; +#include <linux/types.h> + +#include "intel_context.h" int intel_context_set_ring_size(struct intel_context *ce, long sz); long intel_context_get_ring_size(struct intel_context *ce); +static inline int +intel_context_set_watchdog_us(struct intel_context *ce, u64 timeout_us) +{ + ce->watchdog.timeout_us = timeout_us; + return 0; +} + #endif /* INTEL_CONTEXT_PARAM_H */ diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index e10d78601bbd..ed8c447a7346 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ @@ -97,6 +96,10 @@ struct intel_context { #define CONTEXT_FORCE_SINGLE_SUBMISSION 7 #define CONTEXT_NOPREEMPT 8 + struct { + u64 timeout_us; + } watchdog; + u32 *lrc_reg_state; union { struct { diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 9cf555d6842b..efe935f80c1a 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -1,25 +1,6 @@ +// SPDX-License-Identifier: MIT /* * Copyright © 2016 Intel Corporation - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice (including the next - * paragraph) shall be included in all copies or substantial portions of the - * Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - * */ #include <drm/drm_print.h> @@ -619,6 +600,7 @@ static void cleanup_status_page(struct intel_engine_cs *engine) } static int pin_ggtt_status_page(struct intel_engine_cs *engine, + struct i915_gem_ww_ctx *ww, struct i915_vma *vma) { unsigned int flags; @@ -639,12 +621,13 @@ static int pin_ggtt_status_page(struct intel_engine_cs *engine, else flags = PIN_HIGH; - return i915_ggtt_pin(vma, NULL, 0, flags); + return i915_ggtt_pin(vma, ww, 0, flags); } static int init_status_page(struct intel_engine_cs *engine) { struct drm_i915_gem_object *obj; + struct i915_gem_ww_ctx ww; struct i915_vma *vma; void *vaddr; int ret; @@ -670,30 +653,39 @@ static int init_status_page(struct intel_engine_cs *engine) vma = i915_vma_instance(obj, &engine->gt->ggtt->vm, NULL); if (IS_ERR(vma)) { ret = PTR_ERR(vma); - goto err; + goto err_put; } + i915_gem_ww_ctx_init(&ww, true); +retry: + ret = i915_gem_object_lock(obj, &ww); + if (!ret && !HWS_NEEDS_PHYSICAL(engine->i915)) + ret = pin_ggtt_status_page(engine, &ww, vma); + if (ret) + goto err; + vaddr = i915_gem_object_pin_map(obj, I915_MAP_WB); if (IS_ERR(vaddr)) { ret = PTR_ERR(vaddr); - goto err; + goto err_unpin; } engine->status_page.addr = memset(vaddr, 0, PAGE_SIZE); engine->status_page.vma = vma; - if (!HWS_NEEDS_PHYSICAL(engine->i915)) { - ret = pin_ggtt_status_page(engine, vma); - if (ret) - goto err_unpin; - } - - return 0; - err_unpin: - i915_gem_object_unpin_map(obj); + if (ret) + i915_vma_unpin(vma); err: - i915_gem_object_put(obj); + if (ret == -EDEADLK) { + ret = i915_gem_ww_ctx_backoff(&ww); + if (!ret) + goto retry; + } + i915_gem_ww_ctx_fini(&ww); +err_put: + if (ret) + i915_gem_object_put(obj); return ret; } @@ -763,6 +755,7 @@ static int measure_breadcrumb_dw(struct intel_context *ce) frame->rq.engine = engine; frame->rq.context = ce; rcu_assign_pointer(frame->rq.timeline, ce->timeline); + frame->rq.hwsp_seqno = ce->timeline->hwsp_seqno; frame->ring.vaddr = frame->cs; frame->ring.size = sizeof(frame->cs); @@ -1239,14 +1232,14 @@ void __intel_engine_flush_submission(struct intel_engine_cs *engine, bool sync) { struct tasklet_struct *t = &engine->execlists.tasklet; - if (!t->func) + if (!t->callback) return; local_bh_disable(); if (tasklet_trylock(t)) { /* Must wait for any GPU reset in progress. */ if (__tasklet_is_enabled(t)) - t->func(t->data); + t->callback(t); tasklet_unlock(t); } local_bh_enable(); @@ -1273,14 +1266,8 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine) return true; /* Waiting to drain ELSP? */ - if (execlists_active(&engine->execlists)) { - synchronize_hardirq(engine->i915->drm.pdev->irq); - - intel_engine_flush_submission(engine); - - if (execlists_active(&engine->execlists)) - return false; - } + synchronize_hardirq(to_pci_dev(engine->i915->drm.dev)->irq); + intel_engine_flush_submission(engine); /* ELSP is empty, but there are ready requests? E.g. after reset */ if (!RB_EMPTY_ROOT(&engine->execlists.queue.rb_root)) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c index d7be2b9339f9..b99ac41695f3 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ @@ -32,7 +31,7 @@ static bool next_heartbeat(struct intel_engine_cs *engine) delay = msecs_to_jiffies_timeout(delay); if (delay >= HZ) delay = round_jiffies_up_relative(delay); - mod_delayed_work(system_highpri_wq, &engine->heartbeat.work, delay); + mod_delayed_work(system_highpri_wq, &engine->heartbeat.work, delay + 1); return true; } @@ -81,9 +80,7 @@ static void show_heartbeat(const struct i915_request *rq, static void heartbeat(struct work_struct *wrk) { - struct i915_sched_attr attr = { - .priority = I915_USER_PRIORITY(I915_PRIORITY_MIN), - }; + struct i915_sched_attr attr = { .priority = I915_PRIORITY_MIN }; struct intel_engine_cs *engine = container_of(wrk, typeof(*engine), heartbeat.work.work); struct intel_context *ce = engine->kernel_context; @@ -106,6 +103,13 @@ static void heartbeat(struct work_struct *wrk) goto out; if (engine->heartbeat.systole) { + long delay = READ_ONCE(engine->props.heartbeat_interval_ms); + + /* Safeguard against too-fast worker invocations */ + if (!time_after(jiffies, + rq->emitted_jiffies + msecs_to_jiffies(delay))) + goto out; + if (!i915_sw_fence_signaled(&rq->submit)) { /* * Not yet submitted, system is stalled. @@ -125,9 +129,9 @@ static void heartbeat(struct work_struct *wrk) * low latency and no jitter] the chance to naturally * complete before being preempted. */ - attr.priority = I915_PRIORITY_MASK; + attr.priority = 0; if (rq->sched.attr.priority >= attr.priority) - attr.priority |= I915_USER_PRIORITY(I915_PRIORITY_HEARTBEAT); + attr.priority = I915_PRIORITY_HEARTBEAT; if (rq->sched.attr.priority >= attr.priority) attr.priority = I915_PRIORITY_BARRIER; @@ -143,6 +147,8 @@ static void heartbeat(struct work_struct *wrk) "stopped heartbeat on %s", engine->name); } + + rq->emitted_jiffies = jiffies; goto out; } @@ -279,15 +285,14 @@ int intel_engine_pulse(struct intel_engine_cs *engine) mutex_unlock(&ce->timeline->mutex); } + intel_engine_flush_submission(engine); intel_engine_pm_put(engine); return err; } int intel_engine_flush_barriers(struct intel_engine_cs *engine) { - struct i915_sched_attr attr = { - .priority = I915_USER_PRIORITY(I915_PRIORITY_MIN), - }; + struct i915_sched_attr attr = { .priority = I915_PRIORITY_MIN }; struct intel_context *ce = engine->kernel_context; struct i915_request *rq; int err; diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.h b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.h index a7b8c0f9e005..a488ea3e84a3 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c index e67d09259dd0..7c9af86fdb1e 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ @@ -27,12 +26,16 @@ static void dbg_poison_ce(struct intel_context *ce) int type = i915_coherent_map_type(ce->engine->i915); void *map; + if (!i915_gem_object_trylock(obj)) + return; + map = i915_gem_object_pin_map(obj, type); if (!IS_ERR(map)) { memset(map, CONTEXT_REDZONE, obj->base.size); i915_gem_object_flush_map(obj); i915_gem_object_unpin_map(obj); } + i915_gem_object_unlock(obj); } } diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.h b/drivers/gpu/drm/i915/gt/intel_engine_pm.h index 418df0a13145..70ea46d6cfb0 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_pm.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index d2346b425547..883bafc44902 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_engine_user.c b/drivers/gpu/drm/i915/gt/intel_engine_user.c index 34e6096f196e..3cca7ea2d6ea 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_user.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_user.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ @@ -49,7 +48,8 @@ static const u8 uabi_classes[] = { [VIDEO_ENHANCEMENT_CLASS] = I915_ENGINE_CLASS_VIDEO_ENHANCE, }; -static int engine_cmp(void *priv, struct list_head *A, struct list_head *B) +static int engine_cmp(void *priv, const struct list_head *A, + const struct list_head *B) { const struct intel_engine_cs *a = container_of((struct rb_node *)A, typeof(*a), uabi_node); diff --git a/drivers/gpu/drm/i915/gt/intel_engine_user.h b/drivers/gpu/drm/i915/gt/intel_engine_user.h index f845ea1cbfaa..3dc7e8ab9fbc 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_user.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_user.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index ac1be7a632d3..de124870af44 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -274,22 +274,13 @@ static int effective_prio(const struct i915_request *rq) static int queue_prio(const struct intel_engine_execlists *execlists) { - struct i915_priolist *p; struct rb_node *rb; rb = rb_first_cached(&execlists->queue); if (!rb) return INT_MIN; - /* - * As the priolist[] are inverted, with the highest priority in [0], - * we have to flip the index value to become priority. - */ - p = to_priolist(rb); - if (!I915_USER_PRIORITY_SHIFT) - return p->priority; - - return ((p->priority + 1) << I915_USER_PRIORITY_SHIFT) - ffs(p->used); + return to_priolist(rb)->priority; } static int virtual_prio(const struct intel_engine_execlists *el) @@ -470,6 +461,11 @@ static void reset_active(struct i915_request *rq, ce->lrc.lrca = lrc_update_regs(ce, engine, head); } +static bool bad_request(const struct i915_request *rq) +{ + return rq->fence.error && i915_request_started(rq); +} + static struct intel_engine_cs * __execlists_schedule_in(struct i915_request *rq) { @@ -482,7 +478,7 @@ __execlists_schedule_in(struct i915_request *rq) !intel_engine_has_heartbeat(engine))) intel_context_set_banned(ce); - if (unlikely(intel_context_is_banned(ce))) + if (unlikely(intel_context_is_banned(ce) || bad_request(rq))) reset_active(rq, engine); if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)) @@ -752,9 +748,8 @@ assert_pending_valid(const struct intel_engine_execlists *execlists, { struct intel_engine_cs *engine = container_of(execlists, typeof(*engine), execlists); - struct i915_request * const *port, *rq; + struct i915_request * const *port, *rq, *prev = NULL; struct intel_context *ce = NULL; - bool sentinel = false; u32 ccid = -1; trace_ports(execlists, msg, execlists->pending); @@ -804,15 +799,20 @@ assert_pending_valid(const struct intel_engine_execlists *execlists, * Sentinels are supposed to be the last request so they flush * the current execution off the HW. Check that they are the only * request in the pending submission. + * + * NB: Due to the async nature of preempt-to-busy and request + * cancellation we need to handle the case where request + * becomes a sentinel in parallel to CSB processing. */ - if (sentinel) { + if (prev && i915_request_has_sentinel(prev) && + !READ_ONCE(prev->fence.error)) { GEM_TRACE_ERR("%s: context:%llx after sentinel in pending[%zd]\n", engine->name, ce->timeline->fence_context, port - execlists->pending); return false; } - sentinel = i915_request_has_sentinel(rq); + prev = rq; /* * We want virtual requests to only be in the first slot so @@ -948,7 +948,7 @@ static bool can_merge_rq(const struct i915_request *prev, if (__i915_request_is_complete(next)) return true; - if (unlikely((i915_request_flags(prev) ^ i915_request_flags(next)) & + if (unlikely((i915_request_flags(prev) | i915_request_flags(next)) & (BIT(I915_FENCE_FLAG_NOPREEMPT) | BIT(I915_FENCE_FLAG_SENTINEL)))) return false; @@ -1072,7 +1072,6 @@ static void defer_request(struct i915_request *rq, struct list_head * const pl) __i915_request_has_started(w) && !__i915_request_is_complete(rq)); - GEM_BUG_ON(i915_request_is_active(w)); if (!i915_request_is_ready(w)) continue; @@ -1080,6 +1079,7 @@ static void defer_request(struct i915_request *rq, struct list_head * const pl) continue; GEM_BUG_ON(rq_prio(w) > rq_prio(rq)); + GEM_BUG_ON(i915_request_is_active(w)); list_move_tail(&w->sched.link, &list); } @@ -1208,7 +1208,7 @@ static unsigned long active_preempt_timeout(struct intel_engine_cs *engine, return 0; /* Force a fast reset for terminated contexts (ignoring sysfs!) */ - if (unlikely(intel_context_is_banned(rq->context))) + if (unlikely(intel_context_is_banned(rq->context) || bad_request(rq))) return 1; return READ_ONCE(engine->props.preempt_timeout_ms); @@ -1452,9 +1452,8 @@ unlock: while ((rb = rb_first_cached(&execlists->queue))) { struct i915_priolist *p = to_priolist(rb); struct i915_request *rq, *rn; - int i; - priolist_for_each_request_consume(rq, rn, p, i) { + priolist_for_each_request_consume(rq, rn, p) { bool merge = true; /* @@ -2344,9 +2343,10 @@ static bool preempt_timeout(const struct intel_engine_cs *const engine) * Check the unread Context Status Buffers and manage the submission of new * contexts to the ELSP accordingly. */ -static void execlists_submission_tasklet(unsigned long data) +static void execlists_submission_tasklet(struct tasklet_struct *t) { - struct intel_engine_cs * const engine = (struct intel_engine_cs *)data; + struct intel_engine_cs * const engine = + from_tasklet(engine, t, execlists.tasklet); struct i915_request *post[2 * EXECLIST_MAX_PORTS]; struct i915_request **inactive; @@ -2457,11 +2457,31 @@ static void execlists_submit_request(struct i915_request *request) spin_unlock_irqrestore(&engine->active.lock, flags); } +static int +__execlists_context_pre_pin(struct intel_context *ce, + struct intel_engine_cs *engine, + struct i915_gem_ww_ctx *ww, void **vaddr) +{ + int err; + + err = lrc_pre_pin(ce, engine, ww, vaddr); + if (err) + return err; + + if (!__test_and_set_bit(CONTEXT_INIT_BIT, &ce->flags)) { + lrc_init_state(ce, engine, *vaddr); + + __i915_gem_object_flush_map(ce->state->obj, 0, engine->context_size); + } + + return 0; +} + static int execlists_context_pre_pin(struct intel_context *ce, struct i915_gem_ww_ctx *ww, void **vaddr) { - return lrc_pre_pin(ce, ce->engine, ww, vaddr); + return __execlists_context_pre_pin(ce, ce->engine, ww, vaddr); } static int execlists_context_pin(struct intel_context *ce, void *vaddr) @@ -2729,31 +2749,11 @@ static void enable_execlists(struct intel_engine_cs *engine) enable_error_interrupt(engine); } -static bool unexpected_starting_state(struct intel_engine_cs *engine) -{ - bool unexpected = false; - - if (ENGINE_READ_FW(engine, RING_MI_MODE) & STOP_RING) { - drm_dbg(&engine->i915->drm, - "STOP_RING still set in RING_MI_MODE\n"); - unexpected = true; - } - - return unexpected; -} - static int execlists_resume(struct intel_engine_cs *engine) { intel_mocs_init_engine(engine); - intel_breadcrumbs_reset(engine->breadcrumbs); - if (GEM_SHOW_DEBUG() && unexpected_starting_state(engine)) { - struct drm_printer p = drm_debug_printer(__func__); - - intel_engine_dump(engine, &p, NULL); - } - enable_execlists(engine); return 0; @@ -2924,9 +2924,10 @@ static void execlists_reset_rewind(struct intel_engine_cs *engine, bool stalled) rcu_read_unlock(); } -static void nop_submission_tasklet(unsigned long data) +static void nop_submission_tasklet(struct tasklet_struct *t) { - struct intel_engine_cs * const engine = (struct intel_engine_cs *)data; + struct intel_engine_cs * const engine = + from_tasklet(engine, t, execlists.tasklet); /* The driver is wedged; don't process any more events. */ WRITE_ONCE(engine->execlists.queue_priority_hint, INT_MIN); @@ -2962,17 +2963,18 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine) /* Mark all executing requests as skipped. */ list_for_each_entry(rq, &engine->active.requests, sched.link) - i915_request_mark_eio(rq); + i915_request_put(i915_request_mark_eio(rq)); intel_engine_signal_breadcrumbs(engine); /* Flush the queued requests to the timeline list (for retiring). */ while ((rb = rb_first_cached(&execlists->queue))) { struct i915_priolist *p = to_priolist(rb); - int i; - priolist_for_each_request_consume(rq, rn, p, i) { - i915_request_mark_eio(rq); - __i915_request_submit(rq); + priolist_for_each_request_consume(rq, rn, p) { + if (i915_request_mark_eio(rq)) { + __i915_request_submit(rq); + i915_request_put(rq); + } } rb_erase_cached(&p->node, &execlists->queue); @@ -2981,7 +2983,7 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine) /* On-hold requests will be flushed to timeline upon their release */ list_for_each_entry(rq, &engine->active.hold, sched.link) - i915_request_mark_eio(rq); + i915_request_put(i915_request_mark_eio(rq)); /* Cancel all attached virtual engines */ while ((rb = rb_first_cached(&execlists->virtual))) { @@ -2994,10 +2996,11 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine) spin_lock(&ve->base.active.lock); rq = fetch_and_zero(&ve->request); if (rq) { - i915_request_mark_eio(rq); - - rq->engine = engine; - __i915_request_submit(rq); + if (i915_request_mark_eio(rq)) { + rq->engine = engine; + __i915_request_submit(rq); + i915_request_put(rq); + } i915_request_put(rq); ve->base.execlists.queue_priority_hint = INT_MIN; @@ -3011,7 +3014,7 @@ static void execlists_reset_cancel(struct intel_engine_cs *engine) execlists->queue = RB_ROOT_CACHED; GEM_BUG_ON(__tasklet_is_enabled(&execlists->tasklet)); - execlists->tasklet.func = nop_submission_tasklet; + execlists->tasklet.callback = nop_submission_tasklet; spin_unlock_irqrestore(&engine->active.lock, flags); rcu_read_unlock(); @@ -3072,7 +3075,7 @@ static void execlists_set_default_submission(struct intel_engine_cs *engine) { engine->submit_request = execlists_submit_request; engine->schedule = i915_schedule; - engine->execlists.tasklet.func = execlists_submission_tasklet; + engine->execlists.tasklet.callback = execlists_submission_tasklet; engine->reset.prepare = execlists_reset_prepare; engine->reset.rewind = execlists_reset_rewind; @@ -3119,7 +3122,7 @@ static void execlists_release(struct intel_engine_cs *engine) static void logical_ring_default_vfuncs(struct intel_engine_cs *engine) { - /* Default vfuncs which can be overriden by each engine. */ + /* Default vfuncs which can be overridden by each engine. */ engine->resume = execlists_resume; @@ -3195,8 +3198,7 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine) struct intel_uncore *uncore = engine->uncore; u32 base = engine->mmio_base; - tasklet_init(&engine->execlists.tasklet, - execlists_submission_tasklet, (unsigned long)engine); + tasklet_setup(&engine->execlists.tasklet, execlists_submission_tasklet); timer_setup(&engine->execlists.timer, execlists_timeslice, 0); timer_setup(&engine->execlists.preempt, execlists_preempt, 0); @@ -3244,7 +3246,7 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine) static struct list_head *virtual_queue(struct virtual_engine *ve) { - return &ve->base.execlists.default_priolist.requests[0]; + return &ve->base.execlists.default_priolist.requests; } static void rcu_virtual_context_destroy(struct work_struct *wrk) @@ -3360,13 +3362,13 @@ static int virtual_context_alloc(struct intel_context *ce) } static int virtual_context_pre_pin(struct intel_context *ce, - struct i915_gem_ww_ctx *ww, - void **vaddr) + struct i915_gem_ww_ctx *ww, + void **vaddr) { struct virtual_engine *ve = container_of(ce, typeof(*ve), context); - /* Note: we must use a real engine class for setting up reg state */ - return lrc_pre_pin(ce, ve->siblings[0], ww, vaddr); + /* Note: we must use a real engine class for setting up reg state */ + return __execlists_context_pre_pin(ce, ve->siblings[0], ww, vaddr); } static int virtual_context_pin(struct intel_context *ce, void *vaddr) @@ -3438,9 +3440,10 @@ static intel_engine_mask_t virtual_submission_mask(struct virtual_engine *ve) return mask; } -static void virtual_submission_tasklet(unsigned long data) +static void virtual_submission_tasklet(struct tasklet_struct *t) { - struct virtual_engine * const ve = (struct virtual_engine *)data; + struct virtual_engine * const ve = + from_tasklet(ve, t, base.execlists.tasklet); const int prio = READ_ONCE(ve->base.execlists.queue_priority_hint); intel_engine_mask_t mask; unsigned int n; @@ -3650,9 +3653,7 @@ intel_execlists_create_virtual(struct intel_engine_cs **siblings, INIT_LIST_HEAD(virtual_queue(ve)); ve->base.execlists.queue_priority_hint = INT_MIN; - tasklet_init(&ve->base.execlists.tasklet, - virtual_submission_tasklet, - (unsigned long)ve); + tasklet_setup(&ve->base.execlists.tasklet, virtual_submission_tasklet); intel_context_init(&ve->context, &ve->base); @@ -3680,7 +3681,7 @@ intel_execlists_create_virtual(struct intel_engine_cs **siblings, * layering if we handle cloning of the requests and * submitting a copy into each backend. */ - if (sibling->execlists.tasklet.func != + if (sibling->execlists.tasklet.callback != execlists_submission_tasklet) { err = -ENODEV; goto err_put; @@ -3840,9 +3841,8 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine, count = 0; for (rb = rb_first_cached(&execlists->queue); rb; rb = rb_next(rb)) { struct i915_priolist *p = rb_entry(rb, typeof(*p), node); - int i; - priolist_for_each_request(rq, p, i) { + priolist_for_each_request(rq, p) { if (count++ < max - 1) show_request(m, rq, "\t\t", 0); else diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h index a8fd7adefd82..fd61dae820e9 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h @@ -6,6 +6,7 @@ #ifndef __INTEL_EXECLISTS_SUBMISSION_H__ #define __INTEL_EXECLISTS_SUBMISSION_H__ +#include <linux/llist.h> #include <linux/types.h> struct drm_printer; @@ -13,6 +14,7 @@ struct drm_printer; struct i915_request; struct intel_context; struct intel_engine_cs; +struct intel_gt; enum { INTEL_CONTEXT_SCHEDULE_IN = 0, diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index 700588bc9d57..670c1271e7d5 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -10,6 +10,8 @@ #include <drm/i915_drm.h> +#include "gem/i915_gem_lmem.h" + #include "intel_gt.h" #include "i915_drv.h" #include "i915_scatterlist.h" @@ -92,7 +94,7 @@ int i915_ggtt_init_hw(struct drm_i915_private *i915) } /* - * Certain Gen5 chipsets require require idling the GPU before + * Certain Gen5 chipsets require idling the GPU before * unmapping anything from the GTT when VT-d is enabled. */ static bool needs_idle_maps(struct drm_i915_private *i915) @@ -189,7 +191,12 @@ static u64 gen8_ggtt_pte_encode(dma_addr_t addr, enum i915_cache_level level, u32 flags) { - return addr | _PAGE_PRESENT; + gen8_pte_t pte = addr | _PAGE_PRESENT; + + if (flags & PTE_LM) + pte |= GEN12_GGTT_PTE_LM; + + return pte; } static void gen8_set_pte(void __iomem *addr, gen8_pte_t pte) @@ -201,13 +208,13 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm, dma_addr_t addr, u64 offset, enum i915_cache_level level, - u32 unused) + u32 flags) { struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm); gen8_pte_t __iomem *pte = (gen8_pte_t __iomem *)ggtt->gsm + offset / I915_GTT_PAGE_SIZE; - gen8_set_pte(pte, gen8_ggtt_pte_encode(addr, level, 0)); + gen8_set_pte(pte, gen8_ggtt_pte_encode(addr, level, flags)); ggtt->invalidate(ggtt); } @@ -217,7 +224,7 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm, enum i915_cache_level level, u32 flags) { - const gen8_pte_t pte_encode = gen8_ggtt_pte_encode(0, level, 0); + const gen8_pte_t pte_encode = gen8_ggtt_pte_encode(0, level, flags); struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm); gen8_pte_t __iomem *gte; gen8_pte_t __iomem *end; @@ -459,6 +466,8 @@ static void ggtt_bind_vma(struct i915_address_space *vm, pte_flags = 0; if (i915_gem_object_is_readonly(obj)) pte_flags |= PTE_READ_ONLY; + if (i915_gem_object_is_lmem(obj)) + pte_flags |= PTE_LM; vm->insert_entries(vm, vma, cache_level, pte_flags); vma->page_sizes.gtt = I915_GTT_PAGE_SIZE; @@ -647,7 +656,9 @@ static int init_aliasing_ppgtt(struct i915_ggtt *ggtt) if (err) goto err_ppgtt; + i915_gem_object_lock(ppgtt->vm.scratch[0], NULL); err = i915_vm_pin_pt_stash(&ppgtt->vm, &stash); + i915_gem_object_unlock(ppgtt->vm.scratch[0]); if (err) goto err_stash; @@ -734,6 +745,7 @@ static void ggtt_cleanup_hw(struct i915_ggtt *ggtt) mutex_unlock(&ggtt->vm.mutex); i915_address_space_fini(&ggtt->vm); + dma_resv_fini(&ggtt->vm.resv); arch_phys_wc_del(ggtt->mtrr); @@ -792,8 +804,9 @@ static unsigned int chv_get_total_gtt_size(u16 gmch_ctrl) static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size) { struct drm_i915_private *i915 = ggtt->vm.i915; - struct pci_dev *pdev = i915->drm.pdev; + struct pci_dev *pdev = to_pci_dev(i915->drm.dev); phys_addr_t phys_addr; + u32 pte_flags; int ret; /* For Modern GENs the PTEs and register space are split in the BAR */ @@ -823,9 +836,13 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size) return ret; } + pte_flags = 0; + if (i915_gem_object_is_lmem(ggtt->vm.scratch[0])) + pte_flags |= PTE_LM; + ggtt->vm.scratch[0]->encode = ggtt->vm.pte_encode(px_dma(ggtt->vm.scratch[0]), - I915_CACHE_NONE, 0); + I915_CACHE_NONE, pte_flags); return 0; } @@ -862,7 +879,7 @@ static struct resource pci_resource(struct pci_dev *pdev, int bar) static int gen8_gmch_probe(struct i915_ggtt *ggtt) { struct drm_i915_private *i915 = ggtt->vm.i915; - struct pci_dev *pdev = i915->drm.pdev; + struct pci_dev *pdev = to_pci_dev(i915->drm.dev); unsigned int size; u16 snb_gmch_ctl; @@ -1006,7 +1023,7 @@ static u64 iris_pte_encode(dma_addr_t addr, static int gen6_gmch_probe(struct i915_ggtt *ggtt) { struct drm_i915_private *i915 = ggtt->vm.i915; - struct pci_dev *pdev = i915->drm.pdev; + struct pci_dev *pdev = to_pci_dev(i915->drm.dev); unsigned int size; u16 snb_gmch_ctl; @@ -1069,7 +1086,7 @@ static int i915_gmch_probe(struct i915_ggtt *ggtt) phys_addr_t gmadr_base; int ret; - ret = intel_gmch_probe(i915->bridge_dev, i915->drm.pdev, NULL); + ret = intel_gmch_probe(i915->bridge_dev, to_pci_dev(i915->drm.dev), NULL); if (!ret) { drm_err(&i915->drm, "failed to set up gmch\n"); return -EIO; @@ -1114,7 +1131,8 @@ static int ggtt_probe_hw(struct i915_ggtt *ggtt, struct intel_gt *gt) ggtt->vm.gt = gt; ggtt->vm.i915 = i915; - ggtt->vm.dma = &i915->drm.pdev->dev; + ggtt->vm.dma = i915->drm.dev; + dma_resv_init(&ggtt->vm.resv); if (INTEL_GEN(i915) <= 5) ret = i915_gmch_probe(ggtt); @@ -1122,8 +1140,10 @@ static int ggtt_probe_hw(struct i915_ggtt *ggtt, struct intel_gt *gt) ret = gen6_gmch_probe(ggtt); else ret = gen8_gmch_probe(ggtt); - if (ret) + if (ret) { + dma_resv_fini(&ggtt->vm.resv); return ret; + } if ((ggtt->vm.total - 1) >> 32) { drm_err(&i915->drm, @@ -1247,14 +1267,16 @@ void i915_ggtt_resume(struct i915_ggtt *ggtt) static struct scatterlist * rotate_pages(struct drm_i915_gem_object *obj, unsigned int offset, unsigned int width, unsigned int height, - unsigned int stride, + unsigned int src_stride, unsigned int dst_stride, struct sg_table *st, struct scatterlist *sg) { unsigned int column, row; unsigned int src_idx; for (column = 0; column < width; column++) { - src_idx = stride * (height - 1) + column + offset; + unsigned int left; + + src_idx = src_stride * (height - 1) + column + offset; for (row = 0; row < height; row++) { st->nents++; /* @@ -1267,8 +1289,25 @@ rotate_pages(struct drm_i915_gem_object *obj, unsigned int offset, i915_gem_object_get_dma_address(obj, src_idx); sg_dma_len(sg) = I915_GTT_PAGE_SIZE; sg = sg_next(sg); - src_idx -= stride; + src_idx -= src_stride; } + + left = (dst_stride - height) * I915_GTT_PAGE_SIZE; + + if (!left) + continue; + + st->nents++; + + /* + * The DE ignores the PTEs for the padding tiles, the sg entry + * here is just a conenience to indicate how many padding PTEs + * to insert at this spot. + */ + sg_set_page(sg, NULL, left, 0); + sg_dma_address(sg) = 0; + sg_dma_len(sg) = left; + sg = sg_next(sg); } return sg; @@ -1297,11 +1336,12 @@ intel_rotate_pages(struct intel_rotation_info *rot_info, st->nents = 0; sg = st->sgl; - for (i = 0 ; i < ARRAY_SIZE(rot_info->plane); i++) { + for (i = 0 ; i < ARRAY_SIZE(rot_info->plane); i++) sg = rotate_pages(obj, rot_info->plane[i].offset, rot_info->plane[i].width, rot_info->plane[i].height, - rot_info->plane[i].stride, st, sg); - } + rot_info->plane[i].src_stride, + rot_info->plane[i].dst_stride, + st, sg); return st; @@ -1319,7 +1359,7 @@ err_st_alloc: static struct scatterlist * remap_pages(struct drm_i915_gem_object *obj, unsigned int offset, unsigned int width, unsigned int height, - unsigned int stride, + unsigned int src_stride, unsigned int dst_stride, struct sg_table *st, struct scatterlist *sg) { unsigned int row; @@ -1352,7 +1392,24 @@ remap_pages(struct drm_i915_gem_object *obj, unsigned int offset, left -= length; } - offset += stride - width; + offset += src_stride - width; + + left = (dst_stride - width) * I915_GTT_PAGE_SIZE; + + if (!left) + continue; + + st->nents++; + + /* + * The DE ignores the PTEs for the padding tiles, the sg entry + * here is just a conenience to indicate how many padding PTEs + * to insert at this spot. + */ + sg_set_page(sg, NULL, left, 0); + sg_dma_address(sg) = 0; + sg_dma_len(sg) = left; + sg = sg_next(sg); } return sg; @@ -1384,7 +1441,8 @@ intel_remap_pages(struct intel_remapped_info *rem_info, for (i = 0 ; i < ARRAY_SIZE(rem_info->plane); i++) { sg = remap_pages(obj, rem_info->plane[i].offset, rem_info->plane[i].width, rem_info->plane[i].height, - rem_info->plane[i].stride, st, sg); + rem_info->plane[i].src_stride, rem_info->plane[i].dst_stride, + st, sg); } i915_sg_trim(st); @@ -1420,7 +1478,7 @@ intel_partial_pages(const struct i915_ggtt_view *view, if (ret) goto err_sg_alloc; - iter = i915_gem_object_get_sg_dma(obj, view->partial.offset, &offset); + iter = i915_gem_object_get_sg_dma(obj, view->partial.offset, &offset, true); GEM_BUG_ON(!iter); sg = st->sgl; diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c index 67de2b189598..e72b7a0dc316 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c @@ -1,24 +1,6 @@ +// SPDX-License-Identifier: MIT /* * Copyright © 2008-2015 Intel Corporation - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice (including the next - * paragraph) shall be included in all copies or substantial portions of the - * Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. */ #include "i915_drv.h" @@ -609,6 +591,7 @@ static void detect_bit_6_swizzle(struct i915_ggtt *ggtt) } } else { u32 dimm_c0, dimm_c1; + dimm_c0 = intel_uncore_read(uncore, MAD_DIMM_C0); dimm_c1 = intel_uncore_read(uncore, MAD_DIMM_C1); dimm_c0 &= MAD_DIMM_A_SIZE_MASK | MAD_DIMM_B_SIZE_MASK; @@ -798,10 +781,12 @@ i915_gem_object_do_bit_17_swizzle(struct drm_i915_gem_object *obj, i = 0; for_each_sgt_page(page, sgt_iter, pages) { char new_bit_17 = page_to_phys(page) >> 17; + if ((new_bit_17 & 0x1) != (test_bit(i, obj->bit_17) != 0)) { swizzle_page(page); set_page_dirty(page); } + i++; } } diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.h b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.h index 9eef679e1311..25340be5ecf0 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.h +++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.h @@ -1,25 +1,6 @@ +/* SPDX-License-Identifier: MIT */ /* * Copyright © 2016 Intel Corporation - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice (including the next - * paragraph) shall be included in all copies or substantial portions of the - * Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - * */ #ifndef __INTEL_GGTT_FENCING_H__ diff --git a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h index 534e435f20bc..14e2ffb6c0e5 100644 --- a/drivers/gpu/drm/i915/gt/intel_gpu_commands.h +++ b/drivers/gpu/drm/i915/gt/intel_gpu_commands.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT*/ /* - * SPDX-License-Identifier: MIT - * * Copyright � 2003-2018 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index d8e1ab412634..8d77dcbad059 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -4,6 +4,8 @@ */ #include "debugfs_gt.h" + +#include "gem/i915_gem_lmem.h" #include "i915_drv.h" #include "intel_context.h" #include "intel_gt.h" @@ -29,6 +31,9 @@ void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915) INIT_LIST_HEAD(>->closed_vma); spin_lock_init(>->closed_lock); + init_llist_head(>->watchdog.list); + INIT_WORK(>->watchdog.work, intel_gt_watchdog_work); + intel_gt_init_buffer_pool(gt); intel_gt_init_reset(gt); intel_gt_init_requests(gt); @@ -39,6 +44,42 @@ void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915) intel_uc_init_early(>->uc); } +int intel_gt_probe_lmem(struct intel_gt *gt) +{ + struct drm_i915_private *i915 = gt->i915; + struct intel_memory_region *mem; + int id; + int err; + + mem = intel_gt_setup_lmem(gt); + if (mem == ERR_PTR(-ENODEV)) + mem = intel_gt_setup_fake_lmem(gt); + if (IS_ERR(mem)) { + err = PTR_ERR(mem); + if (err == -ENODEV) + return 0; + + drm_err(&i915->drm, + "Failed to setup region(%d) type=%d\n", + err, INTEL_MEMORY_LOCAL); + return err; + } + + id = INTEL_REGION_LMEM; + + mem->id = id; + mem->type = INTEL_MEMORY_LOCAL; + mem->instance = 0; + + intel_memory_region_set_name(mem, "local%u", mem->instance); + + GEM_BUG_ON(!HAS_REGION(i915, id)); + GEM_BUG_ON(i915->mm.regions[id]); + i915->mm.regions[id] = mem; + + return 0; +} + void intel_gt_init_hw_early(struct intel_gt *gt, struct i915_ggtt *ggtt) { gt->ggtt = ggtt; @@ -344,11 +385,13 @@ static int intel_gt_init_scratch(struct intel_gt *gt, unsigned int size) struct i915_vma *vma; int ret; - obj = i915_gem_object_create_stolen(i915, size); + obj = i915_gem_object_create_lmem(i915, size, I915_BO_ALLOC_VOLATILE); + if (IS_ERR(obj)) + obj = i915_gem_object_create_stolen(i915, size); if (IS_ERR(obj)) obj = i915_gem_object_create_internal(i915, size); if (IS_ERR(obj)) { - DRM_ERROR("Failed to allocate scratch page\n"); + drm_err(&i915->drm, "Failed to allocate scratch page\n"); return PTR_ERR(obj); } diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h index 9157c7411f60..7ec395cace69 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.h +++ b/drivers/gpu/drm/i915/gt/intel_gt.h @@ -36,6 +36,7 @@ static inline struct intel_gt *huc_to_gt(struct intel_huc *huc) void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915); void intel_gt_init_hw_early(struct intel_gt *gt, struct i915_ggtt *ggtt); +int intel_gt_probe_lmem(struct intel_gt *gt); int intel_gt_init_mmio(struct intel_gt *gt); int __must_check intel_gt_init_hw(struct intel_gt *gt); int intel_gt_init(struct intel_gt *gt); @@ -77,4 +78,6 @@ static inline bool intel_gt_is_wedged(const struct intel_gt *gt) void intel_gt_info_print(const struct intel_gt_info *info, struct drm_printer *p); +void intel_gt_watchdog_work(struct work_struct *work); + #endif /* __INTEL_GT_H__ */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c index 06d84cf09570..c59468107598 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.c @@ -98,28 +98,6 @@ static void pool_free_work(struct work_struct *wrk) round_jiffies_up_relative(HZ)); } -static int pool_active(struct i915_active *ref) -{ - struct intel_gt_buffer_pool_node *node = - container_of(ref, typeof(*node), active); - struct dma_resv *resv = node->obj->base.resv; - int err; - - if (dma_resv_trylock(resv)) { - dma_resv_add_excl_fence(resv, NULL); - dma_resv_unlock(resv); - } - - err = i915_gem_object_pin_pages(node->obj); - if (err) - return err; - - /* Hide this pinned object from the shrinker until retired */ - i915_gem_object_make_unshrinkable(node->obj); - - return 0; -} - __i915_active_call static void pool_retire(struct i915_active *ref) { @@ -129,10 +107,13 @@ static void pool_retire(struct i915_active *ref) struct list_head *list = bucket_for_size(pool, node->obj->base.size); unsigned long flags; - i915_gem_object_unpin_pages(node->obj); + if (node->pinned) { + i915_gem_object_unpin_pages(node->obj); - /* Return this object to the shrinker pool */ - i915_gem_object_make_purgeable(node->obj); + /* Return this object to the shrinker pool */ + i915_gem_object_make_purgeable(node->obj); + node->pinned = false; + } GEM_BUG_ON(node->age); spin_lock_irqsave(&pool->lock, flags); @@ -144,6 +125,19 @@ static void pool_retire(struct i915_active *ref) round_jiffies_up_relative(HZ)); } +void intel_gt_buffer_pool_mark_used(struct intel_gt_buffer_pool_node *node) +{ + assert_object_held(node->obj); + + if (node->pinned) + return; + + __i915_gem_object_pin_pages(node->obj); + /* Hide this pinned object from the shrinker until retired */ + i915_gem_object_make_unshrinkable(node->obj); + node->pinned = true; +} + static struct intel_gt_buffer_pool_node * node_create(struct intel_gt_buffer_pool *pool, size_t sz, enum i915_map_type type) @@ -159,7 +153,8 @@ node_create(struct intel_gt_buffer_pool *pool, size_t sz, node->age = 0; node->pool = pool; - i915_active_init(&node->active, pool_active, pool_retire); + node->pinned = false; + i915_active_init(&node->active, NULL, pool_retire); obj = i915_gem_object_create_internal(gt->i915, sz); if (IS_ERR(obj)) { diff --git a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.h b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.h index 6068f8f1762e..487b8a5520f1 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool.h @@ -18,10 +18,15 @@ struct intel_gt_buffer_pool_node * intel_gt_get_buffer_pool(struct intel_gt *gt, size_t size, enum i915_map_type type); +void intel_gt_buffer_pool_mark_used(struct intel_gt_buffer_pool_node *node); + static inline int intel_gt_buffer_pool_mark_active(struct intel_gt_buffer_pool_node *node, struct i915_request *rq) { + /* did we call mark_used? */ + GEM_WARN_ON(!node->pinned); + return i915_active_add_request(&node->active, rq); } diff --git a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool_types.h b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool_types.h index d8d82c890da8..df1d75d08cd2 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool_types.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_buffer_pool_types.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2014-2018 Intel Corporation */ @@ -31,6 +30,7 @@ struct intel_gt_buffer_pool_node { }; unsigned long age; enum i915_map_type type; + u32 pinned; }; #endif /* INTEL_GT_BUFFER_POOL_TYPES_H */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c index a4242ca8dcd7..582fcaee11aa 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c @@ -165,7 +165,6 @@ void intel_gt_init_clock_frequency(struct intel_gt *gt) gt->clock_period_ns, div_u64(mul_u32_u32(gt->clock_period_ns, S32_MAX), USEC_PER_SEC)); - } #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM) diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c index 9830342aa6f4..9fc6c912a4e5 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.h b/drivers/gpu/drm/i915/gt/intel_gt_irq.h index 886c5cf408a2..f667e976fb2b 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_irq.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c index c94e8ac884eb..aef3084e8b16 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.h b/drivers/gpu/drm/i915/gt/intel_gt_pm.h index 63846a856e7e..d0588d8aaa44 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_pm_irq.c index babe866126d7..811a11ed181c 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm_irq.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm_irq.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm_irq.h b/drivers/gpu/drm/i915/gt/intel_gt_pm_irq.h index b29816a04809..ff766966d6fc 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm_irq.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm_irq.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c index dc06c78c9eeb..647eca9d867a 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ @@ -9,6 +8,7 @@ #include "i915_drv.h" /* for_each_engine() */ #include "i915_request.h" #include "intel_engine_heartbeat.h" +#include "intel_execlists_submission.h" #include "intel_gt.h" #include "intel_gt_pm.h" #include "intel_gt_requests.h" @@ -243,4 +243,31 @@ void intel_gt_fini_requests(struct intel_gt *gt) { /* Wait until the work is marked as finished before unloading! */ cancel_delayed_work_sync(>->requests.retire_work); + + flush_work(>->watchdog.work); +} + +void intel_gt_watchdog_work(struct work_struct *work) +{ + struct intel_gt *gt = + container_of(work, typeof(*gt), watchdog.work); + struct i915_request *rq, *rn; + struct llist_node *first; + + first = llist_del_all(>->watchdog.list); + if (!first) + return; + + llist_for_each_entry_safe(rq, rn, first, watchdog.link) { + if (!i915_request_completed(rq)) { + struct dma_fence *f = &rq->fence; + + pr_notice("Fence expiration time out i915-%s:%s:%llx!\n", + f->ops->get_driver_name(f), + f->ops->get_timeline_name(f), + f->seqno); + i915_request_cancel(rq, -EINTR); + } + i915_request_put(rq); + } } diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.h b/drivers/gpu/drm/i915/gt/intel_gt_requests.h index dbac53baf1cb..fcc30a6e4fe9 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_requests.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h index a83d3e18254d..0caf6ca0a784 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_types.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h @@ -8,10 +8,12 @@ #include <linux/ktime.h> #include <linux/list.h> +#include <linux/llist.h> #include <linux/mutex.h> #include <linux/notifier.h> #include <linux/spinlock.h> #include <linux/types.h> +#include <linux/workqueue.h> #include "uc/intel_uc.h" @@ -39,10 +41,6 @@ struct intel_gt { struct intel_gt_timelines { spinlock_t lock; /* protects active_list */ struct list_head active_list; - - /* Pack multiple timelines' seqnos into the same page */ - spinlock_t hwsp_lock; - struct list_head hwsp_free_list; } timelines; struct intel_gt_requests { @@ -56,6 +54,11 @@ struct intel_gt { struct delayed_work retire_work; } requests; + struct { + struct llist_head list; + struct work_struct work; + } watchdog; + struct intel_wakeref wakeref; atomic_t user_wakeref; diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c index 04aa6601e984..941f8af016d6 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.c +++ b/drivers/gpu/drm/i915/gt/intel_gtt.c @@ -13,16 +13,36 @@ struct drm_i915_gem_object *alloc_pt_dma(struct i915_address_space *vm, int sz) { + struct drm_i915_gem_object *obj; + if (I915_SELFTEST_ONLY(should_fail(&vm->fault_attr, 1))) i915_gem_shrink_all(vm->i915); - return i915_gem_object_create_internal(vm->i915, sz); + obj = i915_gem_object_create_internal(vm->i915, sz); + /* ensure all dma objects have the same reservation class */ + if (!IS_ERR(obj)) + obj->base.resv = &vm->resv; + return obj; } int pin_pt_dma(struct i915_address_space *vm, struct drm_i915_gem_object *obj) { int err; + i915_gem_object_lock(obj, NULL); + err = i915_gem_object_pin_pages(obj); + i915_gem_object_unlock(obj); + if (err) + return err; + + i915_gem_object_make_unshrinkable(obj); + return 0; +} + +int pin_pt_dma_locked(struct i915_address_space *vm, struct drm_i915_gem_object *obj) +{ + int err; + err = i915_gem_object_pin_pages(obj); if (err) return err; @@ -56,6 +76,20 @@ void __i915_vm_close(struct i915_address_space *vm) mutex_unlock(&vm->mutex); } +/* lock the vm into the current ww, if we lock one, we lock all */ +int i915_vm_lock_objects(struct i915_address_space *vm, + struct i915_gem_ww_ctx *ww) +{ + if (vm->scratch[0]->base.resv == &vm->resv) { + return i915_gem_object_lock(vm->scratch[0], ww); + } else { + struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(vm); + + /* We borrowed the scratch page from ggtt, take the top level object */ + return i915_gem_object_lock(ppgtt->pd->pt.base, ww); + } +} + void i915_address_space_fini(struct i915_address_space *vm) { drm_mm_takedown(&vm->mm); @@ -69,6 +103,7 @@ static void __i915_vm_release(struct work_struct *work) vm->cleanup(vm); i915_address_space_fini(vm); + dma_resv_fini(&vm->resv); kfree(vm); } @@ -98,6 +133,7 @@ void i915_address_space_init(struct i915_address_space *vm, int subclass) mutex_init(&vm->mutex); lockdep_set_subclass(&vm->mutex, subclass); i915_gem_shrinker_taints_mutex(vm->i915, &vm->mutex); + dma_resv_init(&vm->resv); GEM_BUG_ON(!vm->total); drm_mm_init(&vm->mm, 0, vm->total); @@ -427,7 +463,6 @@ __vm_create_scratch_for_read(struct i915_address_space *vm, unsigned long size) { struct drm_i915_gem_object *obj; struct i915_vma *vma; - int err; obj = i915_gem_object_create_internal(vm->i915, PAGE_ALIGN(size)); if (IS_ERR(obj)) @@ -441,6 +476,19 @@ __vm_create_scratch_for_read(struct i915_address_space *vm, unsigned long size) return vma; } + return vma; +} + +struct i915_vma * +__vm_create_scratch_for_read_pinned(struct i915_address_space *vm, unsigned long size) +{ + struct i915_vma *vma; + int err; + + vma = __vm_create_scratch_for_read(vm, size); + if (IS_ERR(vma)) + return vma; + err = i915_vma_pin(vma, 0, 0, i915_vma_is_ggtt(vma) ? PIN_GLOBAL : PIN_USER); if (err) { diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h index 29c10fde8ce3..e67e34e17913 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.h +++ b/drivers/gpu/drm/i915/gt/intel_gtt.h @@ -85,6 +85,10 @@ typedef u64 gen8_pte_t; #define BYT_PTE_SNOOPED_BY_CPU_CACHES REG_BIT(2) #define BYT_PTE_WRITEABLE REG_BIT(1) +#define GEN12_PPGTT_PTE_LM BIT_ULL(11) + +#define GEN12_GGTT_PTE_LM BIT_ULL(1) + /* * Cacheability Control is a 4-bit value. The low three bits are stored in bits * 3:1 of the PTE, while the fourth bit is stored in bit 11 of the PTE. @@ -238,6 +242,7 @@ struct i915_address_space { atomic_t open; struct mutex mutex; /* protects vma and our lists */ + struct dma_resv resv; /* reservation lock for all pd objects, and buffer pool */ #define VM_CLASS_GGTT 0 #define VM_CLASS_PPGTT 1 @@ -264,6 +269,7 @@ struct i915_address_space { enum i915_cache_level level, u32 flags); /* Create a valid PTE */ #define PTE_READ_ONLY BIT(0) +#define PTE_LM BIT(1) void (*allocate_va_range)(struct i915_address_space *vm, struct i915_vm_pt_stash *stash, @@ -346,6 +352,9 @@ struct i915_ppgtt { #define i915_is_ggtt(vm) ((vm)->is_ggtt) +int __must_check +i915_vm_lock_objects(struct i915_address_space *vm, struct i915_gem_ww_ctx *ww); + static inline bool i915_vm_is_4lvl(const struct i915_address_space *vm) { @@ -522,6 +531,7 @@ struct i915_page_directory *alloc_pd(struct i915_address_space *vm); struct i915_page_directory *__alloc_pd(int npde); int pin_pt_dma(struct i915_address_space *vm, struct drm_i915_gem_object *obj); +int pin_pt_dma_locked(struct i915_address_space *vm, struct drm_i915_gem_object *obj); void free_px(struct i915_address_space *vm, struct i915_page_table *pt, int lvl); @@ -576,6 +586,9 @@ void i915_vm_free_pt_stash(struct i915_address_space *vm, struct i915_vma * __vm_create_scratch_for_read(struct i915_address_space *vm, unsigned long size); +struct i915_vma * +__vm_create_scratch_for_read_pinned(struct i915_address_space *vm, unsigned long size); + static inline struct sgt_dma { struct scatterlist *sg; dma_addr_t dma, max; diff --git a/drivers/gpu/drm/i915/gt/intel_llc.c b/drivers/gpu/drm/i915/gt/intel_llc.c index e3f637b3650e..075d741644ae 100644 --- a/drivers/gpu/drm/i915/gt/intel_llc.c +++ b/drivers/gpu/drm/i915/gt/intel_llc.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_llc.h b/drivers/gpu/drm/i915/gt/intel_llc.h index ef09a890d2b7..0e2e3871c919 100644 --- a/drivers/gpu/drm/i915/gt/intel_llc.h +++ b/drivers/gpu/drm/i915/gt/intel_llc.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_llc_types.h b/drivers/gpu/drm/i915/gt/intel_llc_types.h index ecad4687b930..ca5bdf166a23 100644 --- a/drivers/gpu/drm/i915/gt/intel_llc_types.h +++ b/drivers/gpu/drm/i915/gt/intel_llc_types.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 94f485b591af..e86897cde984 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -3,6 +3,8 @@ * Copyright © 2014 Intel Corporation */ +#include "gem/i915_gem_lmem.h" + #include "gen8_engine_cs.h" #include "i915_drv.h" #include "i915_perf.h" @@ -808,7 +810,9 @@ __lrc_alloc_state(struct intel_context *ce, struct intel_engine_cs *engine) context_size += PAGE_SIZE; } - obj = i915_gem_object_create_shmem(engine->i915, context_size); + obj = i915_gem_object_create_lmem(engine->i915, context_size, 0); + if (IS_ERR(obj)) + obj = i915_gem_object_create_shmem(engine->i915, context_size); if (IS_ERR(obj)) return ERR_CAST(obj); @@ -1417,7 +1421,7 @@ gen10_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch) #define CTX_WA_BB_SIZE (PAGE_SIZE) -static int lrc_setup_wa_ctx(struct intel_engine_cs *engine) +static int lrc_create_wa_ctx(struct intel_engine_cs *engine) { struct drm_i915_gem_object *obj; struct i915_vma *vma; @@ -1433,10 +1437,6 @@ static int lrc_setup_wa_ctx(struct intel_engine_cs *engine) goto err; } - err = i915_ggtt_pin(vma, NULL, 0, PIN_HIGH); - if (err) - goto err; - engine->wa_ctx.vma = vma; return 0; @@ -1448,9 +1448,6 @@ err: void lrc_fini_wa_ctx(struct intel_engine_cs *engine) { i915_vma_unpin_and_release(&engine->wa_ctx.vma, 0); - - /* Called on error unwind, clear all flags to prevent further use */ - memset(&engine->wa_ctx, 0, sizeof(engine->wa_ctx)); } typedef u32 *(*wa_bb_func_t)(struct intel_engine_cs *engine, u32 *batch); @@ -1462,6 +1459,7 @@ void lrc_init_wa_ctx(struct intel_engine_cs *engine) &wa_ctx->indirect_ctx, &wa_ctx->per_ctx }; wa_bb_func_t wa_bb_fn[ARRAY_SIZE(wa_bb)]; + struct i915_gem_ww_ctx ww; void *batch, *batch_ptr; unsigned int i; int err; @@ -1490,7 +1488,7 @@ void lrc_init_wa_ctx(struct intel_engine_cs *engine) return; } - err = lrc_setup_wa_ctx(engine); + err = lrc_create_wa_ctx(engine); if (err) { /* * We continue even if we fail to initialize WA batch @@ -1503,7 +1501,22 @@ void lrc_init_wa_ctx(struct intel_engine_cs *engine) return; } + if (!engine->wa_ctx.vma) + return; + + i915_gem_ww_ctx_init(&ww, true); +retry: + err = i915_gem_object_lock(wa_ctx->vma->obj, &ww); + if (!err) + err = i915_ggtt_pin(wa_ctx->vma, &ww, 0, PIN_HIGH); + if (err) + goto err; + batch = i915_gem_object_pin_map(wa_ctx->vma->obj, I915_MAP_WB); + if (IS_ERR(batch)) { + err = PTR_ERR(batch); + goto err_unpin; + } /* * Emit the two workaround batch buffers, recording the offset from the @@ -1528,8 +1541,26 @@ void lrc_init_wa_ctx(struct intel_engine_cs *engine) __i915_gem_object_release_map(wa_ctx->vma->obj); /* Verify that we can handle failure to setup the wa_ctx */ - if (err || i915_inject_probe_error(engine->i915, -ENODEV)) - lrc_fini_wa_ctx(engine); + if (!err) + err = i915_inject_probe_error(engine->i915, -ENODEV); + +err_unpin: + if (err) + i915_vma_unpin(wa_ctx->vma); +err: + if (err == -EDEADLK) { + err = i915_gem_ww_ctx_backoff(&ww); + if (!err) + goto retry; + } + i915_gem_ww_ctx_fini(&ww); + + if (err) { + i915_vma_put(engine->wa_ctx.vma); + + /* Clear all flags to prevent further use */ + memset(wa_ctx, 0, sizeof(*wa_ctx)); + } } static void st_update_runtime_underflow(struct intel_context *ce, s32 dt) diff --git a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h index 65fe76738335..41e5350a7a05 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc_reg.h +++ b/drivers/gpu/drm/i915/gt/intel_lrc_reg.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2014-2018 Intel Corporation */ @@ -40,7 +39,7 @@ #define ASSIGN_CTX_PML4(ppgtt, reg_state) do { \ u32 *reg_state__ = (reg_state); \ - const u64 addr__ = px_dma(ppgtt->pd); \ + const u64 addr__ = px_dma((ppgtt)->pd); \ (reg_state__)[CTX_PDP0_UDW] = upper_32_bits(addr__); \ (reg_state__)[CTX_PDP0_LDW] = lower_32_bits(addr__); \ } while (0) diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c index 8acb84960cd0..b14138fd505c 100644 --- a/drivers/gpu/drm/i915/gt/intel_mocs.c +++ b/drivers/gpu/drm/i915/gt/intel_mocs.c @@ -1,23 +1,6 @@ +// SPDX-License-Identifier: MIT /* - * Copyright (c) 2015 Intel Corporation - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: * - * The above copyright notice and this permission notice (including the next - * paragraph) shall be included in all copies or substantial portions of the - * Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, - * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. + * Copyright © 2015 Intel Corporation */ #include "i915_drv.h" diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.h b/drivers/gpu/drm/i915/gt/intel_mocs.h index 83371f3e6ba1..d83274f5163b 100644 --- a/drivers/gpu/drm/i915/gt/intel_mocs.h +++ b/drivers/gpu/drm/i915/gt/intel_mocs.h @@ -1,24 +1,6 @@ +/* SPDX-License-Identifier: MIT */ /* - * Copyright (c) 2015 Intel Corporation - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice (including the next - * paragraph) shall be included in all copies or substantial portions of the - * Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, - * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. + * Copyright © 2015 Intel Corporation */ #ifndef INTEL_MOCS_H diff --git a/drivers/gpu/drm/i915/gt/intel_ppgtt.c b/drivers/gpu/drm/i915/gt/intel_ppgtt.c index 96b85a10ef33..014ae8ac4480 100644 --- a/drivers/gpu/drm/i915/gt/intel_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ppgtt.c @@ -5,6 +5,8 @@ #include <linux/slab.h> +#include "gem/i915_gem_lmem.h" + #include "i915_trace.h" #include "intel_gtt.h" #include "gen6_ppgtt.h" @@ -192,6 +194,8 @@ void ppgtt_bind_vma(struct i915_address_space *vm, pte_flags = 0; if (i915_gem_object_is_readonly(vma->obj)) pte_flags |= PTE_READ_ONLY; + if (i915_gem_object_is_lmem(vma->obj)) + pte_flags |= PTE_LM; vm->insert_entries(vm, vma, cache_level, pte_flags); wmb(); @@ -262,7 +266,7 @@ int i915_vm_pin_pt_stash(struct i915_address_space *vm, for (n = 0; n < ARRAY_SIZE(stash->pt); n++) { for (pt = stash->pt[n]; pt; pt = pt->stash) { - err = pin_pt_dma(vm, pt->base); + err = pin_pt_dma_locked(vm, pt->base); if (err) return err; } @@ -301,9 +305,10 @@ void ppgtt_init(struct i915_ppgtt *ppgtt, struct intel_gt *gt) ppgtt->vm.gt = gt; ppgtt->vm.i915 = i915; - ppgtt->vm.dma = &i915->drm.pdev->dev; + ppgtt->vm.dma = i915->drm.dev; ppgtt->vm.total = BIT_ULL(INTEL_INFO(i915)->ppgtt_size); + dma_resv_init(&ppgtt->vm.resv); i915_address_space_init(&ppgtt->vm, VM_CLASS_PPGTT); ppgtt->vm.vma_ops.bind_vma = ppgtt_bind_vma; diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c index 35504c97f11d..3b7e62debe7e 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6.c +++ b/drivers/gpu/drm/i915/gt/intel_rc6.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ @@ -176,7 +175,6 @@ static void gen9_rc6_enable(struct intel_rc6 *rc6) /* 3a: Enable RC6 */ set(uncore, GEN6_RC6_THRESHOLD, 37500); /* 37.5/125ms per EI */ - rc6->ctl_enable = GEN6_RC_CTL_HW_ENABLE | GEN6_RC_CTL_RC6_ENABLE | @@ -485,14 +483,14 @@ static bool rc6_supported(struct intel_rc6 *rc6) static void rpm_get(struct intel_rc6 *rc6) { GEM_BUG_ON(rc6->wakeref); - pm_runtime_get_sync(&rc6_to_i915(rc6)->drm.pdev->dev); + pm_runtime_get_sync(rc6_to_i915(rc6)->drm.dev); rc6->wakeref = true; } static void rpm_put(struct intel_rc6 *rc6) { GEM_BUG_ON(!rc6->wakeref); - pm_runtime_put(&rc6_to_i915(rc6)->drm.pdev->dev); + pm_runtime_put(rc6_to_i915(rc6)->drm.dev); rc6->wakeref = false; } diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.h b/drivers/gpu/drm/i915/gt/intel_rc6.h index 9f0f23fca8af..e119ec4a0bcc 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6.h +++ b/drivers/gpu/drm/i915/gt/intel_rc6.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_rc6_types.h b/drivers/gpu/drm/i915/gt/intel_rc6_types.h index bfbb623f7a4f..e747492b2f46 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6_types.h +++ b/drivers/gpu/drm/i915/gt/intel_rc6_types.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_region_lmem.c b/drivers/gpu/drm/i915/gt/intel_region_lmem.c index 60393ce5614d..be6f2c8f5184 100644 --- a/drivers/gpu/drm/i915/gt/intel_region_lmem.c +++ b/drivers/gpu/drm/i915/gt/intel_region_lmem.c @@ -26,12 +26,12 @@ static int init_fake_lmem_bar(struct intel_memory_region *mem) if (ret) return ret; - mem->remap_addr = dma_map_resource(&i915->drm.pdev->dev, + mem->remap_addr = dma_map_resource(i915->drm.dev, mem->region.start, mem->fake_mappable.size, PCI_DMA_BIDIRECTIONAL, DMA_ATTR_FORCE_CONTIGUOUS); - if (dma_mapping_error(&i915->drm.pdev->dev, mem->remap_addr)) { + if (dma_mapping_error(i915->drm.dev, mem->remap_addr)) { drm_mm_remove_node(&mem->fake_mappable); return -EINVAL; } @@ -56,7 +56,7 @@ static void release_fake_lmem_bar(struct intel_memory_region *mem) drm_mm_remove_node(&mem->fake_mappable); - dma_unmap_resource(&mem->i915->drm.pdev->dev, + dma_unmap_resource(mem->i915->drm.dev, mem->remap_addr, mem->fake_mappable.size, PCI_DMA_BIDIRECTIONAL, @@ -90,8 +90,6 @@ region_lmem_init(struct intel_memory_region *mem) if (ret) io_mapping_fini(&mem->iomap); - intel_memory_region_set_name(mem, "local"); - return ret; } @@ -102,20 +100,26 @@ static const struct intel_memory_region_ops intel_region_lmem_ops = { }; struct intel_memory_region * -intel_setup_fake_lmem(struct drm_i915_private *i915) +intel_gt_setup_fake_lmem(struct intel_gt *gt) { - struct pci_dev *pdev = i915->drm.pdev; + struct drm_i915_private *i915 = gt->i915; + struct pci_dev *pdev = to_pci_dev(i915->drm.dev); struct intel_memory_region *mem; resource_size_t mappable_end; resource_size_t io_start; resource_size_t start; + if (!HAS_LMEM(i915)) + return ERR_PTR(-ENODEV); + + if (!i915->params.fake_lmem_start) + return ERR_PTR(-ENODEV); + GEM_BUG_ON(i915_ggtt_has_aperture(&i915->ggtt)); - GEM_BUG_ON(!i915->params.fake_lmem_start); /* Your mappable aperture belongs to me now! */ mappable_end = pci_resource_len(pdev, 2); - io_start = pci_resource_start(pdev, 2), + io_start = pci_resource_start(pdev, 2); start = i915->params.fake_lmem_start; mem = intel_memory_region_create(i915, @@ -136,3 +140,86 @@ intel_setup_fake_lmem(struct drm_i915_private *i915) return mem; } + +static bool get_legacy_lowmem_region(struct intel_uncore *uncore, + u64 *start, u32 *size) +{ + if (!IS_DG1_REVID(uncore->i915, DG1_REVID_A0, DG1_REVID_B0)) + return false; + + *start = 0; + *size = SZ_1M; + + drm_dbg(&uncore->i915->drm, "LMEM: reserved legacy low-memory [0x%llx-0x%llx]\n", + *start, *start + *size); + + return true; +} + +static int reserve_lowmem_region(struct intel_uncore *uncore, + struct intel_memory_region *mem) +{ + u64 reserve_start; + u32 reserve_size; + int ret; + + if (!get_legacy_lowmem_region(uncore, &reserve_start, &reserve_size)) + return 0; + + ret = intel_memory_region_reserve(mem, reserve_start, reserve_size); + if (ret) + drm_err(&uncore->i915->drm, "LMEM: reserving low memory region failed\n"); + + return ret; +} + +static struct intel_memory_region *setup_lmem(struct intel_gt *gt) +{ + struct drm_i915_private *i915 = gt->i915; + struct intel_uncore *uncore = gt->uncore; + struct pci_dev *pdev = i915->drm.pdev; + struct intel_memory_region *mem; + resource_size_t io_start; + resource_size_t lmem_size; + int err; + + if (!IS_DGFX(i915)) + return ERR_PTR(-ENODEV); + + /* Stolen starts from GSMBASE on DG1 */ + lmem_size = intel_uncore_read64(uncore, GEN12_GSMBASE); + + io_start = pci_resource_start(pdev, 2); + if (GEM_WARN_ON(lmem_size > pci_resource_len(pdev, 2))) + return ERR_PTR(-ENODEV); + + mem = intel_memory_region_create(i915, + 0, + lmem_size, + I915_GTT_PAGE_SIZE_4K, + io_start, + &intel_region_lmem_ops); + if (IS_ERR(mem)) + return mem; + + err = reserve_lowmem_region(uncore, mem); + if (err) + goto err_region_put; + + drm_dbg(&i915->drm, "Local memory: %pR\n", &mem->region); + drm_dbg(&i915->drm, "Local memory IO start: %pa\n", + &mem->io_start); + drm_info(&i915->drm, "Local memory available: %pa\n", + &lmem_size); + + return mem; + +err_region_put: + intel_memory_region_put(mem); + return ERR_PTR(err); +} + +struct intel_memory_region *intel_gt_setup_lmem(struct intel_gt *gt) +{ + return setup_lmem(gt); +} diff --git a/drivers/gpu/drm/i915/gt/intel_region_lmem.h b/drivers/gpu/drm/i915/gt/intel_region_lmem.h index 8ea43e538dab..062d0542ae34 100644 --- a/drivers/gpu/drm/i915/gt/intel_region_lmem.h +++ b/drivers/gpu/drm/i915/gt/intel_region_lmem.h @@ -6,9 +6,11 @@ #ifndef __INTEL_REGION_LMEM_H #define __INTEL_REGION_LMEM_H -struct drm_i915_private; +struct intel_gt; + +struct intel_memory_region *intel_gt_setup_lmem(struct intel_gt *gt); struct intel_memory_region * -intel_setup_fake_lmem(struct drm_i915_private *i915); +intel_gt_setup_fake_lmem(struct intel_gt *gt); #endif /* !__INTEL_REGION_LMEM_H */ diff --git a/drivers/gpu/drm/i915/gt/intel_renderstate.c b/drivers/gpu/drm/i915/gt/intel_renderstate.c index ca816ba22197..b03e197b1d99 100644 --- a/drivers/gpu/drm/i915/gt/intel_renderstate.c +++ b/drivers/gpu/drm/i915/gt/intel_renderstate.c @@ -1,28 +1,6 @@ +// SPDX-License-Identifier: MIT /* * Copyright © 2014 Intel Corporation - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice (including the next - * paragraph) shall be included in all copies or substantial portions of the - * Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - * - * Authors: - * Mika Kuoppala <mika.kuoppala@intel.com> - * */ #include "i915_drv.h" @@ -65,7 +43,7 @@ render_state_get_rodata(const struct intel_engine_cs *engine) if ((i) >= PAGE_SIZE / sizeof(u32)) \ goto out; \ (batch)[(i)++] = (val); \ - } while(0) + } while (0) static int render_state_setup(struct intel_renderstate *so, struct drm_i915_private *i915) @@ -84,6 +62,7 @@ static int render_state_setup(struct intel_renderstate *so, if (i * 4 == rodata->reloc[reloc_index]) { u64 r = s + so->vma->node.start; + s = lower_32_bits(r); if (HAS_64BIT_RELOC(i915)) { if (i + 1 >= rodata->batch_items || @@ -197,7 +176,7 @@ retry: if (err) goto err_context; - err = i915_vma_pin(so->vma, 0, 0, PIN_GLOBAL | PIN_HIGH); + err = i915_vma_pin_ww(so->vma, &so->ww, 0, 0, PIN_GLOBAL | PIN_HIGH); if (err) goto err_context; diff --git a/drivers/gpu/drm/i915/gt/intel_renderstate.h b/drivers/gpu/drm/i915/gt/intel_renderstate.h index 713aa1e86c80..48f009203917 100644 --- a/drivers/gpu/drm/i915/gt/intel_renderstate.h +++ b/drivers/gpu/drm/i915/gt/intel_renderstate.h @@ -1,24 +1,6 @@ +/* SPDX-License-Identifier: MIT */ /* * Copyright © 2014 Intel Corporation - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice (including the next - * paragraph) shall be included in all copies or substantial portions of the - * Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. */ #ifndef _INTEL_RENDERSTATE_H_ diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index 61410cd62927..a377c4588aaa 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2008-2018 Intel Corporation */ @@ -178,7 +177,7 @@ static int i915_do_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask, unsigned int retry) { - struct pci_dev *pdev = gt->i915->drm.pdev; + struct pci_dev *pdev = to_pci_dev(gt->i915->drm.dev); int err; /* Assert reset for at least 20 usec, and wait for acknowledgement. */ @@ -207,7 +206,7 @@ static int g33_do_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask, unsigned int retry) { - struct pci_dev *pdev = gt->i915->drm.pdev; + struct pci_dev *pdev = to_pci_dev(gt->i915->drm.dev); pci_write_config_byte(pdev, I915_GDRST, GRDOM_RESET_ENABLE); return wait_for_atomic(g4x_reset_complete(pdev), 50); @@ -217,7 +216,7 @@ static int g4x_do_reset(struct intel_gt *gt, intel_engine_mask_t engine_mask, unsigned int retry) { - struct pci_dev *pdev = gt->i915->drm.pdev; + struct pci_dev *pdev = to_pci_dev(gt->i915->drm.dev); struct intel_uncore *uncore = gt->uncore; int ret; @@ -787,18 +786,15 @@ static void reset_finish(struct intel_gt *gt, intel_engine_mask_t awake) static void nop_submit_request(struct i915_request *request) { - struct intel_engine_cs *engine = request->engine; - unsigned long flags; - RQ_TRACE(request, "-EIO\n"); - i915_request_set_error_once(request, -EIO); - spin_lock_irqsave(&engine->active.lock, flags); - __i915_request_submit(request); - i915_request_mark_complete(request); - spin_unlock_irqrestore(&engine->active.lock, flags); + request = i915_request_mark_eio(request); + if (request) { + i915_request_submit(request); + intel_engine_signal_breadcrumbs(request->engine); - intel_engine_signal_breadcrumbs(engine); + i915_request_put(request); + } } static void __intel_gt_set_wedged(struct intel_gt *gt) @@ -974,8 +970,6 @@ static int do_reset(struct intel_gt *gt, intel_engine_mask_t stalled_mask) { int err, i; - gt_revoke(gt); - err = __intel_gt_reset(gt, ALL_ENGINES); for (i = 0; err && i < RESET_MAX_RETRIES; i++) { msleep(10 * (i + 1)); @@ -1030,6 +1024,13 @@ void intel_gt_reset(struct intel_gt *gt, might_sleep(); GEM_BUG_ON(!test_bit(I915_RESET_BACKOFF, >->reset.flags)); + + /* + * FIXME: Revoking cpu mmap ptes cannot be done from a dma_fence + * critical section like gpu reset. + */ + gt_revoke(gt); + mutex_lock(>->reset.mutex); /* Clear any previous failed attempts at recovery. Time to try again. */ diff --git a/drivers/gpu/drm/i915/gt/intel_reset.h b/drivers/gpu/drm/i915/gt/intel_reset.h index 7dbf5cc8a333..adc734e67387 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.h +++ b/drivers/gpu/drm/i915/gt/intel_reset.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2008-2018 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_reset_types.h b/drivers/gpu/drm/i915/gt/intel_reset_types.h index add6b86d9d03..9312b29f5a97 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset_types.h +++ b/drivers/gpu/drm/i915/gt/intel_reset_types.h @@ -32,7 +32,7 @@ struct intel_reset { * * #I915_WEDGED_ON_INIT - If we fail to initialize the GPU we can no * longer use the GPU - similar to #I915_WEDGED bit. The difference in - * in the way we're handling "forced" unwedged (e.g. through debugfs), + * the way we're handling "forced" unwedged (e.g. through debugfs), * which is not allowed in case we failed to initialize. * * #I915_WEDGED_ON_FINI - Similar to #I915_WEDGED_ON_INIT, except we diff --git a/drivers/gpu/drm/i915/gt/intel_ring.c b/drivers/gpu/drm/i915/gt/intel_ring.c index 78d1360caa0f..aee0a77c77e0 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring.c +++ b/drivers/gpu/drm/i915/gt/intel_ring.c @@ -1,9 +1,9 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ +#include "gem/i915_gem_lmem.h" #include "gem/i915_gem_object.h" #include "i915_drv.h" @@ -109,8 +109,8 @@ static struct i915_vma *create_ring_vma(struct i915_ggtt *ggtt, int size) struct drm_i915_gem_object *obj; struct i915_vma *vma; - obj = ERR_PTR(-ENODEV); - if (i915_ggtt_has_aperture(ggtt)) + obj = i915_gem_object_create_lmem(i915, size, I915_BO_ALLOC_VOLATILE); + if (IS_ERR(obj) && i915_ggtt_has_aperture(ggtt)) obj = i915_gem_object_create_stolen(i915, size); if (IS_ERR(obj)) obj = i915_gem_object_create_internal(i915, size); diff --git a/drivers/gpu/drm/i915/gt/intel_ring.h b/drivers/gpu/drm/i915/gt/intel_ring.h index 1700579bdc93..dbf5f14a136f 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring.h +++ b/drivers/gpu/drm/i915/gt/intel_ring.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ @@ -82,6 +81,7 @@ static inline u32 intel_ring_offset(const struct i915_request *rq, void *addr) { /* Don't write ring->size (equivalent to 0) as that hangs some GPUs. */ u32 offset = addr - rq->ring->vaddr; + GEM_BUG_ON(offset > rq->ring->size); return intel_ring_wrap(rq->ring, offset); } diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c index 4984ff565424..9585546556ee 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c @@ -1,30 +1,6 @@ +// SPDX-License-Identifier: MIT /* - * Copyright © 2008-2010 Intel Corporation - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice (including the next - * paragraph) shall be included in all copies or substantial portions of the - * Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - * - * Authors: - * Eric Anholt <eric@anholt.net> - * Zou Nan hai <nanhai.zou@intel.com> - * Xiang Hai hao<haihao.xiang@intel.com> - * + * Copyright © 2008-2021 Intel Corporation */ #include "gen2_engine_cs.h" @@ -183,15 +159,36 @@ static void set_pp_dir(struct intel_engine_cs *engine) } } +static bool stop_ring(struct intel_engine_cs *engine) +{ + /* Empty the ring by skipping to the end */ + ENGINE_WRITE_FW(engine, RING_HEAD, ENGINE_READ_FW(engine, RING_TAIL)); + ENGINE_POSTING_READ(engine, RING_HEAD); + + /* The ring must be empty before it is disabled */ + ENGINE_WRITE_FW(engine, RING_CTL, 0); + ENGINE_POSTING_READ(engine, RING_CTL); + + /* Then reset the disabled ring */ + ENGINE_WRITE_FW(engine, RING_HEAD, 0); + ENGINE_WRITE_FW(engine, RING_TAIL, 0); + + return (ENGINE_READ_FW(engine, RING_HEAD) & HEAD_ADDR) == 0; +} + static int xcs_resume(struct intel_engine_cs *engine) { - struct drm_i915_private *dev_priv = engine->i915; struct intel_ring *ring = engine->legacy.ring; ENGINE_TRACE(engine, "ring:{HEAD:%04x, TAIL:%04x}\n", ring->head, ring->tail); - if (HWS_NEEDS_PHYSICAL(dev_priv)) + /* Double check the ring is empty & disabled before we resume */ + synchronize_hardirq(engine->i915->drm.irq); + if (!stop_ring(engine)) + goto err; + + if (HWS_NEEDS_PHYSICAL(engine->i915)) ring_setup_phys_status_page(engine); else ring_setup_status_page(engine); @@ -228,21 +225,10 @@ static int xcs_resume(struct intel_engine_cs *engine) if (__intel_wait_for_register_fw(engine->uncore, RING_CTL(engine->mmio_base), RING_VALID, RING_VALID, - 5000, 0, NULL)) { - drm_err(&dev_priv->drm, - "%s initialization failed; " - "ctl %08x (valid? %d) head %08x [%08x] tail %08x [%08x] start %08x [expected %08x]\n", - engine->name, - ENGINE_READ(engine, RING_CTL), - ENGINE_READ(engine, RING_CTL) & RING_VALID, - ENGINE_READ(engine, RING_HEAD), ring->head, - ENGINE_READ(engine, RING_TAIL), ring->tail, - ENGINE_READ(engine, RING_START), - i915_ggtt_offset(ring->vma)); - return -EIO; - } + 5000, 0, NULL)) + goto err; - if (INTEL_GEN(dev_priv) > 2) + if (INTEL_GEN(engine->i915) > 2) ENGINE_WRITE_FW(engine, RING_MI_MODE, _MASKED_BIT_DISABLE(STOP_RING)); @@ -255,6 +241,19 @@ static int xcs_resume(struct intel_engine_cs *engine) /* Papering over lost _interrupts_ immediately following the restart */ intel_engine_signal_breadcrumbs(engine); return 0; + +err: + drm_err(&engine->i915->drm, + "%s initialization failed; " + "ctl %08x (valid? %d) head %08x [%08x] tail %08x [%08x] start %08x [expected %08x]\n", + engine->name, + ENGINE_READ(engine, RING_CTL), + ENGINE_READ(engine, RING_CTL) & RING_VALID, + ENGINE_READ(engine, RING_HEAD), ring->head, + ENGINE_READ(engine, RING_TAIL), ring->tail, + ENGINE_READ(engine, RING_START), + i915_ggtt_offset(ring->vma)); + return -EIO; } static void sanitize_hwsp(struct intel_engine_cs *engine) @@ -290,23 +289,6 @@ static void xcs_sanitize(struct intel_engine_cs *engine) clflush_cache_range(engine->status_page.addr, PAGE_SIZE); } -static bool stop_ring(struct intel_engine_cs *engine) -{ - /* Empty the ring by skipping to the end */ - ENGINE_WRITE_FW(engine, RING_HEAD, ENGINE_READ_FW(engine, RING_TAIL)); - ENGINE_POSTING_READ(engine, RING_HEAD); - - /* The ring must be empty before it is disabled */ - ENGINE_WRITE_FW(engine, RING_CTL, 0); - ENGINE_POSTING_READ(engine, RING_CTL); - - /* Then reset the disabled ring */ - ENGINE_WRITE_FW(engine, RING_HEAD, 0); - ENGINE_WRITE_FW(engine, RING_TAIL, 0); - - return (ENGINE_READ_FW(engine, RING_HEAD) & HEAD_ADDR) == 0; -} - static void reset_prepare(struct intel_engine_cs *engine) { /* @@ -329,25 +311,23 @@ static void reset_prepare(struct intel_engine_cs *engine) if (!stop_ring(engine)) { /* G45 ring initialization often fails to reset head to zero */ - drm_dbg(&engine->i915->drm, - "%s head not reset to zero " - "ctl %08x head %08x tail %08x start %08x\n", - engine->name, - ENGINE_READ_FW(engine, RING_CTL), - ENGINE_READ_FW(engine, RING_HEAD), - ENGINE_READ_FW(engine, RING_TAIL), - ENGINE_READ_FW(engine, RING_START)); - } - - if (!stop_ring(engine)) { - drm_err(&engine->i915->drm, - "failed to set %s head to zero " - "ctl %08x head %08x tail %08x start %08x\n", - engine->name, - ENGINE_READ_FW(engine, RING_CTL), - ENGINE_READ_FW(engine, RING_HEAD), - ENGINE_READ_FW(engine, RING_TAIL), - ENGINE_READ_FW(engine, RING_START)); + ENGINE_TRACE(engine, + "HEAD not reset to zero, " + "{ CTL:%08x, HEAD:%08x, TAIL:%08x, START:%08x }\n", + ENGINE_READ_FW(engine, RING_CTL), + ENGINE_READ_FW(engine, RING_HEAD), + ENGINE_READ_FW(engine, RING_TAIL), + ENGINE_READ_FW(engine, RING_START)); + if (!stop_ring(engine)) { + drm_err(&engine->i915->drm, + "failed to set %s head to zero " + "ctl %08x head %08x tail %08x start %08x\n", + engine->name, + ENGINE_READ_FW(engine, RING_CTL), + ENGINE_READ_FW(engine, RING_HEAD), + ENGINE_READ_FW(engine, RING_TAIL), + ENGINE_READ_FW(engine, RING_START)); + } } } @@ -431,7 +411,7 @@ static void reset_cancel(struct intel_engine_cs *engine) /* Mark all submitted requests as skipped. */ list_for_each_entry(request, &engine->active.requests, sched.link) - i915_request_mark_eio(request); + i915_request_put(i915_request_mark_eio(request)); intel_engine_signal_breadcrumbs(engine); /* Remaining _unready_ requests will be nop'ed when submitted */ @@ -466,6 +446,26 @@ static void ring_context_destroy(struct kref *ref) intel_context_free(ce); } +static int ring_context_init_default_state(struct intel_context *ce, + struct i915_gem_ww_ctx *ww) +{ + struct drm_i915_gem_object *obj = ce->state->obj; + void *vaddr; + + vaddr = i915_gem_object_pin_map(obj, I915_MAP_WB); + if (IS_ERR(vaddr)) + return PTR_ERR(vaddr); + + shmem_read(ce->engine->default_state, 0, + vaddr, ce->engine->context_size); + + i915_gem_object_flush_map(obj); + __i915_gem_object_release_map(obj); + + __set_bit(CONTEXT_VALID_BIT, &ce->flags); + return 0; +} + static int ring_context_pre_pin(struct intel_context *ce, struct i915_gem_ww_ctx *ww, void **unused) @@ -473,6 +473,13 @@ static int ring_context_pre_pin(struct intel_context *ce, struct i915_address_space *vm; int err = 0; + if (ce->engine->default_state && + !test_bit(CONTEXT_VALID_BIT, &ce->flags)) { + err = ring_context_init_default_state(ce, ww); + if (err) + return err; + } + vm = vm_alias(ce->vm); if (vm) err = gen6_ppgtt_pin(i915_vm_to_ppgtt((vm)), ww); @@ -528,22 +535,6 @@ alloc_context_vma(struct intel_engine_cs *engine) if (IS_IVYBRIDGE(i915)) i915_gem_object_set_cache_coherency(obj, I915_CACHE_L3_LLC); - if (engine->default_state) { - void *vaddr; - - vaddr = i915_gem_object_pin_map(obj, I915_MAP_WB); - if (IS_ERR(vaddr)) { - err = PTR_ERR(vaddr); - goto err_obj; - } - - shmem_read(engine->default_state, 0, - vaddr, engine->context_size); - - i915_gem_object_flush_map(obj); - __i915_gem_object_release_map(obj); - } - vma = i915_vma_instance(obj, &engine->gt->ggtt->vm, NULL); if (IS_ERR(vma)) { err = PTR_ERR(vma); @@ -575,8 +566,6 @@ static int ring_context_alloc(struct intel_context *ce) return PTR_ERR(vma); ce->state = vma; - if (engine->default_state) - __set_bit(CONTEXT_VALID_BIT, &ce->flags); } return 0; @@ -761,13 +750,14 @@ static int mi_set_context(struct i915_request *rq, static int remap_l3_slice(struct i915_request *rq, int slice) { +#define L3LOG_DW (GEN7_L3LOG_SIZE / sizeof(u32)) u32 *cs, *remap_info = rq->engine->i915->l3_parity.remap_info[slice]; int i; if (!remap_info) return 0; - cs = intel_ring_begin(rq, GEN7_L3LOG_SIZE/4 * 2 + 2); + cs = intel_ring_begin(rq, L3LOG_DW * 2 + 2); if (IS_ERR(cs)) return PTR_ERR(cs); @@ -776,8 +766,8 @@ static int remap_l3_slice(struct i915_request *rq, int slice) * here because no other code should access these registers other than * at initialization time. */ - *cs++ = MI_LOAD_REGISTER_IMM(GEN7_L3LOG_SIZE/4); - for (i = 0; i < GEN7_L3LOG_SIZE/4; i++) { + *cs++ = MI_LOAD_REGISTER_IMM(L3LOG_DW); + for (i = 0; i < L3LOG_DW; i++) { *cs++ = i915_mmio_reg_offset(GEN7_L3LOG(slice, i)); *cs++ = remap_info[i]; } @@ -785,6 +775,7 @@ static int remap_l3_slice(struct i915_request *rq, int slice) intel_ring_advance(rq, cs); return 0; +#undef L3LOG_DW } static int remap_l3(struct i915_request *rq) @@ -1176,37 +1167,15 @@ static int gen7_ctx_switch_bb_setup(struct intel_engine_cs * const engine, return gen7_setup_clear_gpr_bb(engine, vma); } -static int gen7_ctx_switch_bb_init(struct intel_engine_cs *engine) +static int gen7_ctx_switch_bb_init(struct intel_engine_cs *engine, + struct i915_gem_ww_ctx *ww, + struct i915_vma *vma) { - struct drm_i915_gem_object *obj; - struct i915_vma *vma; - int size; int err; - size = gen7_ctx_switch_bb_setup(engine, NULL /* probe size */); - if (size <= 0) - return size; - - size = ALIGN(size, PAGE_SIZE); - obj = i915_gem_object_create_internal(engine->i915, size); - if (IS_ERR(obj)) - return PTR_ERR(obj); - - vma = i915_vma_instance(obj, engine->gt->vm, NULL); - if (IS_ERR(vma)) { - err = PTR_ERR(vma); - goto err_obj; - } - - vma->private = intel_context_create(engine); /* dummy residuals */ - if (IS_ERR(vma->private)) { - err = PTR_ERR(vma->private); - goto err_obj; - } - - err = i915_vma_pin(vma, 0, 0, PIN_USER | PIN_HIGH); + err = i915_vma_pin_ww(vma, ww, 0, 0, PIN_USER | PIN_HIGH); if (err) - goto err_private; + return err; err = i915_vma_sync(vma); if (err) @@ -1221,17 +1190,53 @@ static int gen7_ctx_switch_bb_init(struct intel_engine_cs *engine) err_unpin: i915_vma_unpin(vma); -err_private: - intel_context_put(vma->private); -err_obj: - i915_gem_object_put(obj); return err; } +static struct i915_vma *gen7_ctx_vma(struct intel_engine_cs *engine) +{ + struct drm_i915_gem_object *obj; + struct i915_vma *vma; + int size, err; + + if (!IS_GEN(engine->i915, 7) || engine->class != RENDER_CLASS) + return 0; + + err = gen7_ctx_switch_bb_setup(engine, NULL /* probe size */); + if (err < 0) + return ERR_PTR(err); + if (!err) + return NULL; + + size = ALIGN(err, PAGE_SIZE); + + obj = i915_gem_object_create_internal(engine->i915, size); + if (IS_ERR(obj)) + return ERR_CAST(obj); + + vma = i915_vma_instance(obj, engine->gt->vm, NULL); + if (IS_ERR(vma)) { + i915_gem_object_put(obj); + return ERR_CAST(vma); + } + + vma->private = intel_context_create(engine); /* dummy residuals */ + if (IS_ERR(vma->private)) { + err = PTR_ERR(vma->private); + vma->private = NULL; + i915_gem_object_put(obj); + return ERR_PTR(err); + } + + return vma; +} + int intel_ring_submission_setup(struct intel_engine_cs *engine) { + struct i915_gem_ww_ctx ww; struct intel_timeline *timeline; struct intel_ring *ring; + struct i915_vma *gen7_wa_vma; int err; setup_common(engine); @@ -1262,43 +1267,72 @@ int intel_ring_submission_setup(struct intel_engine_cs *engine) } GEM_BUG_ON(timeline->has_initial_breadcrumb); - err = intel_timeline_pin(timeline, NULL); - if (err) - goto err_timeline; - ring = intel_engine_create_ring(engine, SZ_16K); if (IS_ERR(ring)) { err = PTR_ERR(ring); - goto err_timeline_unpin; + goto err_timeline; } - err = intel_ring_pin(ring, NULL); - if (err) - goto err_ring; - GEM_BUG_ON(engine->legacy.ring); engine->legacy.ring = ring; engine->legacy.timeline = timeline; - GEM_BUG_ON(timeline->hwsp_ggtt != engine->status_page.vma); + gen7_wa_vma = gen7_ctx_vma(engine); + if (IS_ERR(gen7_wa_vma)) { + err = PTR_ERR(gen7_wa_vma); + goto err_ring; + } - if (IS_GEN(engine->i915, 7) && engine->class == RENDER_CLASS) { - err = gen7_ctx_switch_bb_init(engine); + i915_gem_ww_ctx_init(&ww, false); + +retry: + err = i915_gem_object_lock(timeline->hwsp_ggtt->obj, &ww); + if (!err && gen7_wa_vma) + err = i915_gem_object_lock(gen7_wa_vma->obj, &ww); + if (!err && engine->legacy.ring->vma->obj) + err = i915_gem_object_lock(engine->legacy.ring->vma->obj, &ww); + if (!err) + err = intel_timeline_pin(timeline, &ww); + if (!err) { + err = intel_ring_pin(ring, &ww); if (err) - goto err_ring_unpin; + intel_timeline_unpin(timeline); + } + if (err) + goto out; + + GEM_BUG_ON(timeline->hwsp_ggtt != engine->status_page.vma); + + if (gen7_wa_vma) { + err = gen7_ctx_switch_bb_init(engine, &ww, gen7_wa_vma); + if (err) { + intel_ring_unpin(ring); + intel_timeline_unpin(timeline); + } } +out: + if (err == -EDEADLK) { + err = i915_gem_ww_ctx_backoff(&ww); + if (!err) + goto retry; + } + i915_gem_ww_ctx_fini(&ww); + if (err) + goto err_gen7_put; + /* Finally, take ownership and responsibility for cleanup! */ engine->release = ring_release; return 0; -err_ring_unpin: - intel_ring_unpin(ring); +err_gen7_put: + if (gen7_wa_vma) { + intel_context_put(gen7_wa_vma->private); + i915_gem_object_put(gen7_wa_vma->obj); + } err_ring: intel_ring_put(ring); -err_timeline_unpin: - intel_timeline_unpin(timeline); err_timeline: intel_timeline_put(timeline); err: diff --git a/drivers/gpu/drm/i915/gt/intel_ring_types.h b/drivers/gpu/drm/i915/gt/intel_ring_types.h index 1a189ea00fd8..49ccb76dda3b 100644 --- a/drivers/gpu/drm/i915/gt/intel_ring_types.h +++ b/drivers/gpu/drm/i915/gt/intel_ring_types.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index ee5835c29c03..405d814e9040 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_rps.h b/drivers/gpu/drm/i915/gt/intel_rps.h index 8d3c9d663662..1d2cfc98b510 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.h +++ b/drivers/gpu/drm/i915/gt/intel_rps.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_rps_types.h b/drivers/gpu/drm/i915/gt/intel_rps_types.h index 029fe13cf303..3941d8551f52 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps_types.h +++ b/drivers/gpu/drm/i915/gt/intel_rps_types.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c index 8a72e0fe34ca..0d9f74aec8fe 100644 --- a/drivers/gpu/drm/i915/gt/intel_sseu.c +++ b/drivers/gpu/drm/i915/gt/intel_sseu.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.h b/drivers/gpu/drm/i915/gt/intel_sseu.h index 23ba6c2ebe70..4cd1a8a7298a 100644 --- a/drivers/gpu/drm/i915/gt/intel_sseu.h +++ b/drivers/gpu/drm/i915/gt/intel_sseu.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c index 037b0e3ccbed..f19cf6d2fa85 100644 --- a/drivers/gpu/drm/i915/gt/intel_timeline.c +++ b/drivers/gpu/drm/i915/gt/intel_timeline.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2016-2018 Intel Corporation */ @@ -12,21 +11,9 @@ #include "intel_ring.h" #include "intel_timeline.h" -#define ptr_set_bit(ptr, bit) ((typeof(ptr))((unsigned long)(ptr) | BIT(bit))) -#define ptr_test_bit(ptr, bit) ((unsigned long)(ptr) & BIT(bit)) +#define TIMELINE_SEQNO_BYTES 8 -#define CACHELINE_BITS 6 -#define CACHELINE_FREE CACHELINE_BITS - -struct intel_timeline_hwsp { - struct intel_gt *gt; - struct intel_gt_timelines *gt_timelines; - struct list_head free_link; - struct i915_vma *vma; - u64 free_bitmap; -}; - -static struct i915_vma *__hwsp_alloc(struct intel_gt *gt) +static struct i915_vma *hwsp_alloc(struct intel_gt *gt) { struct drm_i915_private *i915 = gt->i915; struct drm_i915_gem_object *obj; @@ -45,174 +32,42 @@ static struct i915_vma *__hwsp_alloc(struct intel_gt *gt) return vma; } -static struct i915_vma * -hwsp_alloc(struct intel_timeline *timeline, unsigned int *cacheline) -{ - struct intel_gt_timelines *gt = &timeline->gt->timelines; - struct intel_timeline_hwsp *hwsp; - - BUILD_BUG_ON(BITS_PER_TYPE(u64) * CACHELINE_BYTES > PAGE_SIZE); - - spin_lock_irq(>->hwsp_lock); - - /* hwsp_free_list only contains HWSP that have available cachelines */ - hwsp = list_first_entry_or_null(>->hwsp_free_list, - typeof(*hwsp), free_link); - if (!hwsp) { - struct i915_vma *vma; - - spin_unlock_irq(>->hwsp_lock); - - hwsp = kmalloc(sizeof(*hwsp), GFP_KERNEL); - if (!hwsp) - return ERR_PTR(-ENOMEM); - - vma = __hwsp_alloc(timeline->gt); - if (IS_ERR(vma)) { - kfree(hwsp); - return vma; - } - - GT_TRACE(timeline->gt, "new HWSP allocated\n"); - - vma->private = hwsp; - hwsp->gt = timeline->gt; - hwsp->vma = vma; - hwsp->free_bitmap = ~0ull; - hwsp->gt_timelines = gt; - - spin_lock_irq(>->hwsp_lock); - list_add(&hwsp->free_link, >->hwsp_free_list); - } - - GEM_BUG_ON(!hwsp->free_bitmap); - *cacheline = __ffs64(hwsp->free_bitmap); - hwsp->free_bitmap &= ~BIT_ULL(*cacheline); - if (!hwsp->free_bitmap) - list_del(&hwsp->free_link); - - spin_unlock_irq(>->hwsp_lock); - - GEM_BUG_ON(hwsp->vma->private != hwsp); - return hwsp->vma; -} - -static void __idle_hwsp_free(struct intel_timeline_hwsp *hwsp, int cacheline) -{ - struct intel_gt_timelines *gt = hwsp->gt_timelines; - unsigned long flags; - - spin_lock_irqsave(>->hwsp_lock, flags); - - /* As a cacheline becomes available, publish the HWSP on the freelist */ - if (!hwsp->free_bitmap) - list_add_tail(&hwsp->free_link, >->hwsp_free_list); - - GEM_BUG_ON(cacheline >= BITS_PER_TYPE(hwsp->free_bitmap)); - hwsp->free_bitmap |= BIT_ULL(cacheline); - - /* And if no one is left using it, give the page back to the system */ - if (hwsp->free_bitmap == ~0ull) { - i915_vma_put(hwsp->vma); - list_del(&hwsp->free_link); - kfree(hwsp); - } - - spin_unlock_irqrestore(>->hwsp_lock, flags); -} - -static void __rcu_cacheline_free(struct rcu_head *rcu) -{ - struct intel_timeline_cacheline *cl = - container_of(rcu, typeof(*cl), rcu); - - /* Must wait until after all *rq->hwsp are complete before removing */ - i915_gem_object_unpin_map(cl->hwsp->vma->obj); - __idle_hwsp_free(cl->hwsp, ptr_unmask_bits(cl->vaddr, CACHELINE_BITS)); - - i915_active_fini(&cl->active); - kfree(cl); -} - -static void __idle_cacheline_free(struct intel_timeline_cacheline *cl) -{ - GEM_BUG_ON(!i915_active_is_idle(&cl->active)); - call_rcu(&cl->rcu, __rcu_cacheline_free); -} - __i915_active_call -static void __cacheline_retire(struct i915_active *active) +static void __timeline_retire(struct i915_active *active) { - struct intel_timeline_cacheline *cl = - container_of(active, typeof(*cl), active); + struct intel_timeline *tl = + container_of(active, typeof(*tl), active); - i915_vma_unpin(cl->hwsp->vma); - if (ptr_test_bit(cl->vaddr, CACHELINE_FREE)) - __idle_cacheline_free(cl); + i915_vma_unpin(tl->hwsp_ggtt); + intel_timeline_put(tl); } -static int __cacheline_active(struct i915_active *active) +static int __timeline_active(struct i915_active *active) { - struct intel_timeline_cacheline *cl = - container_of(active, typeof(*cl), active); + struct intel_timeline *tl = + container_of(active, typeof(*tl), active); - __i915_vma_pin(cl->hwsp->vma); + __i915_vma_pin(tl->hwsp_ggtt); + intel_timeline_get(tl); return 0; } -static struct intel_timeline_cacheline * -cacheline_alloc(struct intel_timeline_hwsp *hwsp, unsigned int cacheline) +I915_SELFTEST_EXPORT int +intel_timeline_pin_map(struct intel_timeline *timeline) { - struct intel_timeline_cacheline *cl; + struct drm_i915_gem_object *obj = timeline->hwsp_ggtt->obj; + u32 ofs = offset_in_page(timeline->hwsp_offset); void *vaddr; - GEM_BUG_ON(cacheline >= BIT(CACHELINE_BITS)); - - cl = kmalloc(sizeof(*cl), GFP_KERNEL); - if (!cl) - return ERR_PTR(-ENOMEM); - - vaddr = i915_gem_object_pin_map(hwsp->vma->obj, I915_MAP_WB); - if (IS_ERR(vaddr)) { - kfree(cl); - return ERR_CAST(vaddr); - } - - cl->hwsp = hwsp; - cl->vaddr = page_pack_bits(vaddr, cacheline); - - i915_active_init(&cl->active, __cacheline_active, __cacheline_retire); - - return cl; -} - -static void cacheline_acquire(struct intel_timeline_cacheline *cl, - u32 ggtt_offset) -{ - if (!cl) - return; - - cl->ggtt_offset = ggtt_offset; - i915_active_acquire(&cl->active); -} - -static void cacheline_release(struct intel_timeline_cacheline *cl) -{ - if (cl) - i915_active_release(&cl->active); -} - -static void cacheline_free(struct intel_timeline_cacheline *cl) -{ - if (!i915_active_acquire_if_busy(&cl->active)) { - __idle_cacheline_free(cl); - return; - } + vaddr = i915_gem_object_pin_map(obj, I915_MAP_WB); + if (IS_ERR(vaddr)) + return PTR_ERR(vaddr); - GEM_BUG_ON(ptr_test_bit(cl->vaddr, CACHELINE_FREE)); - cl->vaddr = ptr_set_bit(cl->vaddr, CACHELINE_FREE); + timeline->hwsp_map = vaddr; + timeline->hwsp_seqno = memset(vaddr + ofs, 0, TIMELINE_SEQNO_BYTES); + clflush(vaddr + ofs); - i915_active_release(&cl->active); + return 0; } static int intel_timeline_init(struct intel_timeline *timeline, @@ -220,45 +75,25 @@ static int intel_timeline_init(struct intel_timeline *timeline, struct i915_vma *hwsp, unsigned int offset) { - void *vaddr; - kref_init(&timeline->kref); atomic_set(&timeline->pin_count, 0); timeline->gt = gt; - timeline->has_initial_breadcrumb = !hwsp; - timeline->hwsp_cacheline = NULL; - - if (!hwsp) { - struct intel_timeline_cacheline *cl; - unsigned int cacheline; - - hwsp = hwsp_alloc(timeline, &cacheline); + if (hwsp) { + timeline->hwsp_offset = offset; + timeline->hwsp_ggtt = i915_vma_get(hwsp); + } else { + timeline->has_initial_breadcrumb = true; + hwsp = hwsp_alloc(gt); if (IS_ERR(hwsp)) return PTR_ERR(hwsp); - - cl = cacheline_alloc(hwsp->private, cacheline); - if (IS_ERR(cl)) { - __idle_hwsp_free(hwsp->private, cacheline); - return PTR_ERR(cl); - } - - timeline->hwsp_cacheline = cl; - timeline->hwsp_offset = cacheline * CACHELINE_BYTES; - - vaddr = page_mask_bits(cl->vaddr); - } else { - timeline->hwsp_offset = offset; - vaddr = i915_gem_object_pin_map(hwsp->obj, I915_MAP_WB); - if (IS_ERR(vaddr)) - return PTR_ERR(vaddr); + timeline->hwsp_ggtt = hwsp; } - timeline->hwsp_seqno = - memset(vaddr + timeline->hwsp_offset, 0, CACHELINE_BYTES); + timeline->hwsp_map = NULL; + timeline->hwsp_seqno = (void *)(long)timeline->hwsp_offset; - timeline->hwsp_ggtt = i915_vma_get(hwsp); GEM_BUG_ON(timeline->hwsp_offset >= hwsp->size); timeline->fence_context = dma_fence_context_alloc(1); @@ -269,6 +104,7 @@ static int intel_timeline_init(struct intel_timeline *timeline, INIT_LIST_HEAD(&timeline->requests); i915_syncmap_init(&timeline->sync); + i915_active_init(&timeline->active, __timeline_active, __timeline_retire); return 0; } @@ -279,23 +115,19 @@ void intel_gt_init_timelines(struct intel_gt *gt) spin_lock_init(&timelines->lock); INIT_LIST_HEAD(&timelines->active_list); - - spin_lock_init(&timelines->hwsp_lock); - INIT_LIST_HEAD(&timelines->hwsp_free_list); } -static void intel_timeline_fini(struct intel_timeline *timeline) +static void intel_timeline_fini(struct rcu_head *rcu) { - GEM_BUG_ON(atomic_read(&timeline->pin_count)); - GEM_BUG_ON(!list_empty(&timeline->requests)); - GEM_BUG_ON(timeline->retire); + struct intel_timeline *timeline = + container_of(rcu, struct intel_timeline, rcu); - if (timeline->hwsp_cacheline) - cacheline_free(timeline->hwsp_cacheline); - else + if (timeline->hwsp_map) i915_gem_object_unpin_map(timeline->hwsp_ggtt->obj); i915_vma_put(timeline->hwsp_ggtt); + i915_active_fini(&timeline->active); + kfree(timeline); } struct intel_timeline * @@ -351,6 +183,12 @@ int intel_timeline_pin(struct intel_timeline *tl, struct i915_gem_ww_ctx *ww) if (atomic_add_unless(&tl->pin_count, 1, 0)) return 0; + if (!tl->hwsp_map) { + err = intel_timeline_pin_map(tl); + if (err) + return err; + } + err = i915_ggtt_pin(tl->hwsp_ggtt, ww, 0, PIN_HIGH); if (err) return err; @@ -361,9 +199,9 @@ int intel_timeline_pin(struct intel_timeline *tl, struct i915_gem_ww_ctx *ww) GT_TRACE(tl->gt, "timeline:%llx using HWSP offset:%x\n", tl->fence_context, tl->hwsp_offset); - cacheline_acquire(tl->hwsp_cacheline, tl->hwsp_offset); + i915_active_acquire(&tl->active); if (atomic_fetch_inc(&tl->pin_count)) { - cacheline_release(tl->hwsp_cacheline); + i915_active_release(&tl->active); __i915_vma_unpin(tl->hwsp_ggtt); } @@ -372,9 +210,13 @@ int intel_timeline_pin(struct intel_timeline *tl, struct i915_gem_ww_ctx *ww) void intel_timeline_reset_seqno(const struct intel_timeline *tl) { + u32 *hwsp_seqno = (u32 *)tl->hwsp_seqno; /* Must be pinned to be writable, and no requests in flight. */ GEM_BUG_ON(!atomic_read(&tl->pin_count)); - WRITE_ONCE(*(u32 *)tl->hwsp_seqno, tl->seqno); + + memset(hwsp_seqno + 1, 0, TIMELINE_SEQNO_BYTES - sizeof(*hwsp_seqno)); + WRITE_ONCE(*hwsp_seqno, tl->seqno); + clflush(hwsp_seqno); } void intel_timeline_enter(struct intel_timeline *tl) @@ -450,106 +292,23 @@ static u32 timeline_advance(struct intel_timeline *tl) return tl->seqno += 1 + tl->has_initial_breadcrumb; } -static void timeline_rollback(struct intel_timeline *tl) -{ - tl->seqno -= 1 + tl->has_initial_breadcrumb; -} - static noinline int __intel_timeline_get_seqno(struct intel_timeline *tl, - struct i915_request *rq, u32 *seqno) { - struct intel_timeline_cacheline *cl; - unsigned int cacheline; - struct i915_vma *vma; - void *vaddr; - int err; - - might_lock(&tl->gt->ggtt->vm.mutex); - GT_TRACE(tl->gt, "timeline:%llx wrapped\n", tl->fence_context); - - /* - * If there is an outstanding GPU reference to this cacheline, - * such as it being sampled by a HW semaphore on another timeline, - * we cannot wraparound our seqno value (the HW semaphore does - * a strict greater-than-or-equals compare, not i915_seqno_passed). - * So if the cacheline is still busy, we must detach ourselves - * from it and leave it inflight alongside its users. - * - * However, if nobody is watching and we can guarantee that nobody - * will, we could simply reuse the same cacheline. - * - * if (i915_active_request_is_signaled(&tl->last_request) && - * i915_active_is_signaled(&tl->hwsp_cacheline->active)) - * return 0; - * - * That seems unlikely for a busy timeline that needed to wrap in - * the first place, so just replace the cacheline. - */ - - vma = hwsp_alloc(tl, &cacheline); - if (IS_ERR(vma)) { - err = PTR_ERR(vma); - goto err_rollback; - } - - err = i915_ggtt_pin(vma, NULL, 0, PIN_HIGH); - if (err) { - __idle_hwsp_free(vma->private, cacheline); - goto err_rollback; - } - - cl = cacheline_alloc(vma->private, cacheline); - if (IS_ERR(cl)) { - err = PTR_ERR(cl); - __idle_hwsp_free(vma->private, cacheline); - goto err_unpin; - } - GEM_BUG_ON(cl->hwsp->vma != vma); - - /* - * Attach the old cacheline to the current request, so that we only - * free it after the current request is retired, which ensures that - * all writes into the cacheline from previous requests are complete. - */ - err = i915_active_ref(&tl->hwsp_cacheline->active, - tl->fence_context, - &rq->fence); - if (err) - goto err_cacheline; - - cacheline_release(tl->hwsp_cacheline); /* ownership now xfered to rq */ - cacheline_free(tl->hwsp_cacheline); - - i915_vma_unpin(tl->hwsp_ggtt); /* binding kept alive by old cacheline */ - i915_vma_put(tl->hwsp_ggtt); - - tl->hwsp_ggtt = i915_vma_get(vma); + u32 next_ofs = offset_in_page(tl->hwsp_offset + TIMELINE_SEQNO_BYTES); - vaddr = page_mask_bits(cl->vaddr); - tl->hwsp_offset = cacheline * CACHELINE_BYTES; - tl->hwsp_seqno = - memset(vaddr + tl->hwsp_offset, 0, CACHELINE_BYTES); + /* w/a: bit 5 needs to be zero for MI_FLUSH_DW address. */ + if (TIMELINE_SEQNO_BYTES <= BIT(5) && (next_ofs & BIT(5))) + next_ofs = offset_in_page(next_ofs + BIT(5)); - tl->hwsp_offset += i915_ggtt_offset(vma); - GT_TRACE(tl->gt, "timeline:%llx using HWSP offset:%x\n", - tl->fence_context, tl->hwsp_offset); - - cacheline_acquire(cl, tl->hwsp_offset); - tl->hwsp_cacheline = cl; + tl->hwsp_offset = i915_ggtt_offset(tl->hwsp_ggtt) + next_ofs; + tl->hwsp_seqno = tl->hwsp_map + next_ofs; + intel_timeline_reset_seqno(tl); *seqno = timeline_advance(tl); GEM_BUG_ON(i915_seqno_passed(*tl->hwsp_seqno, *seqno)); return 0; - -err_cacheline: - cacheline_free(cl); -err_unpin: - i915_vma_unpin(vma); -err_rollback: - timeline_rollback(tl); - return err; } int intel_timeline_get_seqno(struct intel_timeline *tl, @@ -559,51 +318,52 @@ int intel_timeline_get_seqno(struct intel_timeline *tl, *seqno = timeline_advance(tl); /* Replace the HWSP on wraparound for HW semaphores */ - if (unlikely(!*seqno && tl->hwsp_cacheline)) - return __intel_timeline_get_seqno(tl, rq, seqno); + if (unlikely(!*seqno && tl->has_initial_breadcrumb)) + return __intel_timeline_get_seqno(tl, seqno); return 0; } -static int cacheline_ref(struct intel_timeline_cacheline *cl, - struct i915_request *rq) -{ - return i915_active_add_request(&cl->active, rq); -} - int intel_timeline_read_hwsp(struct i915_request *from, struct i915_request *to, u32 *hwsp) { - struct intel_timeline_cacheline *cl; + struct intel_timeline *tl; int err; - GEM_BUG_ON(!rcu_access_pointer(from->hwsp_cacheline)); - rcu_read_lock(); - cl = rcu_dereference(from->hwsp_cacheline); - if (i915_request_signaled(from)) /* confirm cacheline is valid */ - goto unlock; - if (unlikely(!i915_active_acquire_if_busy(&cl->active))) - goto unlock; /* seqno wrapped and completed! */ - if (unlikely(__i915_request_is_complete(from))) - goto release; + tl = rcu_dereference(from->timeline); + if (i915_request_signaled(from) || + !i915_active_acquire_if_busy(&tl->active)) + tl = NULL; + + if (tl) { + /* hwsp_offset may wraparound, so use from->hwsp_seqno */ + *hwsp = i915_ggtt_offset(tl->hwsp_ggtt) + + offset_in_page(from->hwsp_seqno); + } + + /* ensure we wait on the right request, if not, we completed */ + if (tl && __i915_request_is_complete(from)) { + i915_active_release(&tl->active); + tl = NULL; + } rcu_read_unlock(); - err = cacheline_ref(cl, to); - if (err) + if (!tl) + return 1; + + /* Can't do semaphore waits on kernel context */ + if (!tl->has_initial_breadcrumb) { + err = -EINVAL; goto out; + } + + err = i915_active_add_request(&tl->active, to); - *hwsp = cl->ggtt_offset; out: - i915_active_release(&cl->active); + i915_active_release(&tl->active); return err; - -release: - i915_active_release(&cl->active); -unlock: - rcu_read_unlock(); - return 1; } void intel_timeline_unpin(struct intel_timeline *tl) @@ -612,8 +372,7 @@ void intel_timeline_unpin(struct intel_timeline *tl) if (!atomic_dec_and_test(&tl->pin_count)) return; - cacheline_release(tl->hwsp_cacheline); - + i915_active_release(&tl->active); __i915_vma_unpin(tl->hwsp_ggtt); } @@ -622,8 +381,11 @@ void __intel_timeline_free(struct kref *kref) struct intel_timeline *timeline = container_of(kref, typeof(*timeline), kref); - intel_timeline_fini(timeline); - kfree_rcu(timeline, rcu); + GEM_BUG_ON(atomic_read(&timeline->pin_count)); + GEM_BUG_ON(!list_empty(&timeline->requests)); + GEM_BUG_ON(timeline->retire); + + call_rcu(&timeline->rcu, intel_timeline_fini); } void intel_gt_fini_timelines(struct intel_gt *gt) @@ -631,7 +393,6 @@ void intel_gt_fini_timelines(struct intel_gt *gt) struct intel_gt_timelines *timelines = >->timelines; GEM_BUG_ON(!list_empty(&timelines->active_list)); - GEM_BUG_ON(!list_empty(&timelines->hwsp_free_list)); } void intel_gt_show_timelines(struct intel_gt *gt, diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.h b/drivers/gpu/drm/i915/gt/intel_timeline.h index dcdee692a80e..57308c4d664a 100644 --- a/drivers/gpu/drm/i915/gt/intel_timeline.h +++ b/drivers/gpu/drm/i915/gt/intel_timeline.h @@ -1,25 +1,6 @@ +/* SPDX-License-Identifier: MIT */ /* * Copyright © 2016 Intel Corporation - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice (including the next - * paragraph) shall be included in all copies or substantial portions of the - * Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - * */ #ifndef I915_TIMELINE_H @@ -117,4 +98,6 @@ intel_timeline_is_last(const struct intel_timeline *tl, return list_is_last_rcu(&rq->link, &tl->requests); } +I915_SELFTEST_DECLARE(int intel_timeline_pin_map(struct intel_timeline *tl)); + #endif diff --git a/drivers/gpu/drm/i915/gt/intel_timeline_types.h b/drivers/gpu/drm/i915/gt/intel_timeline_types.h index e360f50706bf..74e67dbf89c5 100644 --- a/drivers/gpu/drm/i915/gt/intel_timeline_types.h +++ b/drivers/gpu/drm/i915/gt/intel_timeline_types.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2016 Intel Corporation */ @@ -18,7 +17,6 @@ struct i915_vma; struct i915_syncmap; struct intel_gt; -struct intel_timeline_hwsp; struct intel_timeline { u64 fence_context; @@ -45,12 +43,11 @@ struct intel_timeline { atomic_t pin_count; atomic_t active_count; + void *hwsp_map; const u32 *hwsp_seqno; struct i915_vma *hwsp_ggtt; u32 hwsp_offset; - struct intel_timeline_cacheline *hwsp_cacheline; - bool has_initial_breadcrumb; /** @@ -67,6 +64,8 @@ struct intel_timeline { */ struct i915_active_fence last_request; + struct i915_active active; + /** A chain of completed timelines ready for early retirement. */ struct intel_timeline *retire; @@ -90,15 +89,4 @@ struct intel_timeline { struct rcu_head rcu; }; -struct intel_timeline_cacheline { - struct i915_active active; - - struct intel_timeline_hwsp *hwsp; - void *vaddr; - - u32 ggtt_offset; - - struct rcu_head rcu; -}; - #endif /* __I915_TIMELINE_TYPES_H__ */ diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index ec366cf9ef56..2c6f7217469f 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2014-2018 Intel Corporation */ @@ -53,37 +52,6 @@ * - Public functions to init or apply the given workaround type. */ -/* - * KBL revision ID ordering is bizarre; higher revision ID's map to lower - * steppings in some cases. So rather than test against the revision ID - * directly, let's map that into our own range of increasing ID's that we - * can test against in a regular manner. - */ - -const struct i915_rev_steppings kbl_revids[] = { - [0] = { .gt_stepping = KBL_REVID_A0, .disp_stepping = KBL_REVID_A0 }, - [1] = { .gt_stepping = KBL_REVID_B0, .disp_stepping = KBL_REVID_B0 }, - [2] = { .gt_stepping = KBL_REVID_C0, .disp_stepping = KBL_REVID_B0 }, - [3] = { .gt_stepping = KBL_REVID_D0, .disp_stepping = KBL_REVID_B0 }, - [4] = { .gt_stepping = KBL_REVID_F0, .disp_stepping = KBL_REVID_C0 }, - [5] = { .gt_stepping = KBL_REVID_C0, .disp_stepping = KBL_REVID_B1 }, - [6] = { .gt_stepping = KBL_REVID_D1, .disp_stepping = KBL_REVID_B1 }, - [7] = { .gt_stepping = KBL_REVID_G0, .disp_stepping = KBL_REVID_C0 }, -}; - -const struct i915_rev_steppings tgl_uy_revids[] = { - [0] = { .gt_stepping = TGL_REVID_A0, .disp_stepping = TGL_REVID_A0 }, - [1] = { .gt_stepping = TGL_REVID_B0, .disp_stepping = TGL_REVID_C0 }, - [2] = { .gt_stepping = TGL_REVID_B1, .disp_stepping = TGL_REVID_C0 }, - [3] = { .gt_stepping = TGL_REVID_C0, .disp_stepping = TGL_REVID_D0 }, -}; - -/* Same GT stepping between tgl_uy_revids and tgl_revids don't mean the same HW */ -const struct i915_rev_steppings tgl_revids[] = { - [0] = { .gt_stepping = TGL_REVID_A0, .disp_stepping = TGL_REVID_B0 }, - [1] = { .gt_stepping = TGL_REVID_B0, .disp_stepping = TGL_REVID_D0 }, -}; - static void wa_init_start(struct i915_wa_list *wal, const char *name, const char *engine_name) { wal->name = name; @@ -273,7 +241,7 @@ static void gen8_ctx_workarounds_init(struct intel_engine_cs *engine, PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE); /* Use Force Non-Coherent whenever executing a 3D context. This is a - * workaround for for a possible hang in the unlikely event a TLB + * workaround for a possible hang in the unlikely event a TLB * invalidation occurs during a PSD flush. */ /* WaForceEnableNonCoherent:bdw,chv */ @@ -513,7 +481,7 @@ static void kbl_ctx_workarounds_init(struct intel_engine_cs *engine, gen9_ctx_workarounds_init(engine, wal); /* WaToEnableHwFixForPushConstHWBug:kbl */ - if (IS_KBL_GT_REVID(i915, KBL_REVID_C0, REVID_FOREVER)) + if (IS_KBL_GT_STEP(i915, STEP_C0, STEP_FOREVER)) wa_masked_en(wal, COMMON_SLICE_CHICKEN2, GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); @@ -722,7 +690,8 @@ __intel_engine_init_ctx_wa(struct intel_engine_cs *engine, if (IS_DG1(i915)) dg1_ctx_workarounds_init(engine, wal); - else if (IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) + else if (IS_ALDERLAKE_S(i915) || IS_ROCKETLAKE(i915) || + IS_TIGERLAKE(i915)) tgl_ctx_workarounds_init(engine, wal); else if (IS_GEN(i915, 12)) gen12_ctx_workarounds_init(engine, wal); @@ -749,7 +718,7 @@ __intel_engine_init_ctx_wa(struct intel_engine_cs *engine, else if (IS_GEN(i915, 6)) gen6_ctx_workarounds_init(engine, wal); else if (INTEL_GEN(i915) < 8) - return; + ; else MISSING_CASE(INTEL_GEN(i915)); @@ -930,7 +899,7 @@ kbl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) gen9_gt_workarounds_init(i915, wal); /* WaDisableDynamicCreditSharing:kbl */ - if (IS_KBL_GT_REVID(i915, 0, KBL_REVID_B0)) + if (IS_KBL_GT_STEP(i915, 0, STEP_B0)) wa_write_or(wal, GAMT_CHKN_BIT_REG, GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING); @@ -1103,11 +1072,10 @@ icl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) /* Wa_1607087056:icl,ehl,jsl */ if (IS_ICELAKE(i915) || - IS_JSL_EHL_REVID(i915, EHL_REVID_A0, EHL_REVID_A0)) { + IS_JSL_EHL_REVID(i915, EHL_REVID_A0, EHL_REVID_A0)) wa_write_or(wal, SLICE_UNIT_LEVEL_CLKGATE, L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS); - } } static void @@ -1123,19 +1091,19 @@ tgl_gt_workarounds_init(struct drm_i915_private *i915, struct i915_wa_list *wal) gen12_gt_workarounds_init(i915, wal); /* Wa_1409420604:tgl */ - if (IS_TGL_UY_GT_REVID(i915, TGL_REVID_A0, TGL_REVID_A0)) + if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_A0)) wa_write_or(wal, SUBSLICE_UNIT_LEVEL_CLKGATE2, CPSSUNIT_CLKGATE_DIS); /* Wa_1607087056:tgl also know as BUG:1409180338 */ - if (IS_TGL_UY_GT_REVID(i915, TGL_REVID_A0, TGL_REVID_A0)) + if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_A0)) wa_write_or(wal, SLICE_UNIT_LEVEL_CLKGATE, L3_CLKGATE_DIS | L3_CR2X_CLKGATE_DIS); /* Wa_1408615072:tgl[a0] */ - if (IS_TGL_UY_GT_REVID(i915, TGL_REVID_A0, TGL_REVID_A0)) + if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_A0)) wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2, VSUNIT_CLKGATE_DIS_TGL); } @@ -1202,7 +1170,7 @@ gt_init_workarounds(struct drm_i915_private *i915, struct i915_wa_list *wal) else if (IS_GEN(i915, 4)) gen4_gt_workarounds_init(i915, wal); else if (INTEL_GEN(i915) <= 8) - return; + ; else MISSING_CASE(INTEL_GEN(i915)); } @@ -1577,7 +1545,7 @@ void intel_engine_init_whitelist(struct intel_engine_cs *engine) else if (IS_SKYLAKE(i915)) skl_whitelist_build(engine); else if (INTEL_GEN(i915) <= 8) - return; + ; else MISSING_CASE(INTEL_GEN(i915)); @@ -1613,7 +1581,7 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) struct drm_i915_private *i915 = engine->i915; if (IS_DG1_REVID(i915, DG1_REVID_A0, DG1_REVID_A0) || - IS_TGL_UY_GT_REVID(i915, TGL_REVID_A0, TGL_REVID_A0)) { + IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_A0)) { /* * Wa_1607138336:tgl[a0],dg1[a0] * Wa_1607063988:tgl[a0],dg1[a0] @@ -1623,7 +1591,7 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) GEN12_DISABLE_POSH_BUSY_FF_DOP_CG); } - if (IS_TGL_UY_GT_REVID(i915, TGL_REVID_A0, TGL_REVID_A0)) { + if (IS_TGL_UY_GT_STEP(i915, STEP_A0, STEP_A0)) { /* * Wa_1606679103:tgl * (see also Wa_1606682166:icl) @@ -1633,45 +1601,45 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) GEN7_DISABLE_SAMPLER_PREFETCH); } - if (IS_DG1(i915) || IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) { - /* Wa_1606931601:tgl,rkl,dg1 */ + if (IS_ALDERLAKE_S(i915) || IS_DG1(i915) || + IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) { + /* Wa_1606931601:tgl,rkl,dg1,adl-s */ wa_masked_en(wal, GEN7_ROW_CHICKEN2, GEN12_DISABLE_EARLY_READ); /* * Wa_1407928979:tgl A* * Wa_18011464164:tgl[B0+],dg1[B0+] * Wa_22010931296:tgl[B0+],dg1[B0+] - * Wa_14010919138:rkl, dg1 + * Wa_14010919138:rkl,dg1,adl-s */ wa_write_or(wal, GEN7_FF_THREAD_MODE, GEN12_FF_TESSELATION_DOP_GATE_DISABLE); /* * Wa_1606700617:tgl,dg1 - * Wa_22010271021:tgl,rkl,dg1 + * Wa_22010271021:tgl,rkl,dg1, adl-s */ wa_masked_en(wal, GEN9_CS_DEBUG_MODE1, FF_DOP_CLOCK_GATE_DISABLE); - - /* Wa_1406941453:tgl,rkl,dg1 */ - wa_masked_en(wal, - GEN10_SAMPLER_MODE, - ENABLE_SMALLPL); } - if (IS_DG1_REVID(i915, DG1_REVID_A0, DG1_REVID_A0) || + if (IS_ALDERLAKE_S(i915) || IS_DG1_REVID(i915, DG1_REVID_A0, DG1_REVID_A0) || IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) { - /* Wa_1409804808:tgl,rkl,dg1[a0] */ + /* Wa_1409804808:tgl,rkl,dg1[a0],adl-s */ wa_masked_en(wal, GEN7_ROW_CHICKEN2, GEN12_PUSH_CONST_DEREF_HOLD_DIS); /* * Wa_1409085225:tgl - * Wa_14010229206:tgl,rkl,dg1[a0] + * Wa_14010229206:tgl,rkl,dg1[a0],adl-s */ wa_masked_en(wal, GEN9_ROW_CHICKEN4, GEN12_DISABLE_TDL_PUSH); + } + + if (IS_DG1_REVID(i915, DG1_REVID_A0, DG1_REVID_A0) || + IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) { /* * Wa_1607030317:tgl * Wa_1607186500:tgl @@ -1688,6 +1656,13 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) GEN8_RC_SEMA_IDLE_MSG_DISABLE); } + if (IS_DG1(i915) || IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) { + /* Wa_1406941453:tgl,rkl,dg1 */ + wa_masked_en(wal, + GEN10_SAMPLER_MODE, + ENABLE_SMALLPL); + } + if (IS_GEN(i915, 11)) { /* This is not an Wa. Enable for better image quality */ wa_masked_en(wal, @@ -2045,7 +2020,7 @@ xcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) struct drm_i915_private *i915 = engine->i915; /* WaKBLVECSSemaphoreWaitPoll:kbl */ - if (IS_KBL_GT_REVID(i915, KBL_REVID_A0, KBL_REVID_E0)) { + if (IS_KBL_GT_STEP(i915, STEP_A0, STEP_E0)) { wa_write(wal, RING_SEMA_WAIT_POLL(engine->mmio_base), 1); @@ -2197,10 +2172,15 @@ retry: if (err) goto err_pm; + err = i915_vma_pin_ww(vma, &ww, 0, 0, + i915_vma_is_ggtt(vma) ? PIN_GLOBAL : PIN_USER); + if (err) + goto err_unpin; + rq = i915_request_create(ce); if (IS_ERR(rq)) { err = PTR_ERR(rq); - goto err_unpin; + goto err_vma; } err = i915_request_await_object(rq, vma->obj, true); @@ -2241,6 +2221,8 @@ retry: err_rq: i915_request_put(rq); +err_vma: + i915_vma_unpin(vma); err_unpin: intel_context_unpin(ce); err_pm: @@ -2251,7 +2233,6 @@ err_pm: } i915_gem_ww_ctx_fini(&ww); intel_engine_pm_put(ce->engine); - i915_vma_unpin(vma); i915_vma_put(vma); return err; } diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.h b/drivers/gpu/drm/i915/gt/intel_workarounds.h index 8c9c769c2204..15abb68b6c00 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.h +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2014-2018 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds_types.h b/drivers/gpu/drm/i915/gt/intel_workarounds_types.h index d166a7145720..c214111ea367 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds_types.h +++ b/drivers/gpu/drm/i915/gt/intel_workarounds_types.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2014-2018 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c index 4b4f03b70df7..e1ba03b93ffa 100644 --- a/drivers/gpu/drm/i915/gt/mock_engine.c +++ b/drivers/gpu/drm/i915/gt/mock_engine.c @@ -1,25 +1,6 @@ +// SPDX-License-Identifier: MIT /* * Copyright © 2016 Intel Corporation - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice (including the next - * paragraph) shall be included in all copies or substantial portions of the - * Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - * */ #include "gem/i915_gem_context.h" @@ -32,9 +13,20 @@ #include "mock_engine.h" #include "selftests/mock_request.h" -static void mock_timeline_pin(struct intel_timeline *tl) +static int mock_timeline_pin(struct intel_timeline *tl) { + int err; + + if (WARN_ON(!i915_gem_object_trylock(tl->hwsp_ggtt->obj))) + return -EBUSY; + + err = intel_timeline_pin_map(tl); + i915_gem_object_unlock(tl->hwsp_ggtt->obj); + if (err) + return err; + atomic_inc(&tl->pin_count); + return 0; } static void mock_timeline_unpin(struct intel_timeline *tl) @@ -152,6 +144,8 @@ static void mock_context_destroy(struct kref *ref) static int mock_context_alloc(struct intel_context *ce) { + int err; + ce->ring = mock_ring(ce->engine); if (!ce->ring) return -ENOMEM; @@ -162,7 +156,12 @@ static int mock_context_alloc(struct intel_context *ce) return PTR_ERR(ce->timeline); } - mock_timeline_pin(ce->timeline); + err = mock_timeline_pin(ce->timeline); + if (err) { + intel_timeline_put(ce->timeline); + ce->timeline = NULL; + return err; + } return 0; } @@ -258,13 +257,15 @@ static void mock_reset_cancel(struct intel_engine_cs *engine) /* Mark all submitted requests as skipped. */ list_for_each_entry(rq, &engine->active.requests, sched.link) - i915_request_mark_eio(rq); + i915_request_put(i915_request_mark_eio(rq)); intel_engine_signal_breadcrumbs(engine); /* Cancel and submit all pending requests. */ list_for_each_entry(rq, &mock->hw_queue, mock.link) { - i915_request_mark_eio(rq); - __i915_request_submit(rq); + if (i915_request_mark_eio(rq)) { + __i915_request_submit(rq); + i915_request_put(rq); + } } INIT_LIST_HEAD(&mock->hw_queue); diff --git a/drivers/gpu/drm/i915/gt/mock_engine.h b/drivers/gpu/drm/i915/gt/mock_engine.h index 3f9b698c49d2..cc5ab6e1f37e 100644 --- a/drivers/gpu/drm/i915/gt/mock_engine.h +++ b/drivers/gpu/drm/i915/gt/mock_engine.h @@ -1,25 +1,6 @@ +/* SPDX-License-Identifier: MIT */ /* * Copyright © 2016 Intel Corporation - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice (including the next - * paragraph) shall be included in all copies or substantial portions of the - * Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - * */ #ifndef __MOCK_ENGINE_H__ diff --git a/drivers/gpu/drm/i915/gt/selftest_context.c b/drivers/gpu/drm/i915/gt/selftest_context.c index db738d400168..b9bdd1d23243 100644 --- a/drivers/gpu/drm/i915/gt/selftest_context.c +++ b/drivers/gpu/drm/i915/gt/selftest_context.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * SPDX-License-Identifier: GPL-2.0 - * * Copyright © 2019 Intel Corporation */ @@ -88,8 +87,8 @@ static int __live_context_size(struct intel_engine_cs *engine) if (err) goto err; - vaddr = i915_gem_object_pin_map(ce->state->obj, - i915_coherent_map_type(engine->i915)); + vaddr = i915_gem_object_pin_map_unlocked(ce->state->obj, + i915_coherent_map_type(engine->i915)); if (IS_ERR(vaddr)) { err = PTR_ERR(vaddr); intel_context_unpin(ce); diff --git a/drivers/gpu/drm/i915/gt/selftest_engine.c b/drivers/gpu/drm/i915/gt/selftest_engine.c index f65b118e261d..262764f6d90a 100644 --- a/drivers/gpu/drm/i915/gt/selftest_engine.c +++ b/drivers/gpu/drm/i915/gt/selftest_engine.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * SPDX-License-Identifier: GPL-2.0 - * * Copyright © 2018 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/selftest_engine.h b/drivers/gpu/drm/i915/gt/selftest_engine.h index ab32d09ec5a1..c6feb3bd2ccc 100644 --- a/drivers/gpu/drm/i915/gt/selftest_engine.h +++ b/drivers/gpu/drm/i915/gt/selftest_engine.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* - * SPDX-License-Identifier: GPL-2.0 - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_cs.c b/drivers/gpu/drm/i915/gt/selftest_engine_cs.c index 439c8984f5fa..b32814a1f20b 100644 --- a/drivers/gpu/drm/i915/gt/selftest_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/selftest_engine_cs.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * SPDX-License-Identifier: GPL-2.0 - * * Copyright © 2018 Intel Corporation */ @@ -42,6 +41,9 @@ static int perf_end(struct intel_gt *gt) static int write_timestamp(struct i915_request *rq, int slot) { + struct intel_timeline *tl = + rcu_dereference_protected(rq->timeline, + !i915_request_signaled(rq)); u32 cmd; u32 *cs; @@ -54,7 +56,7 @@ static int write_timestamp(struct i915_request *rq, int slot) cmd++; *cs++ = cmd; *cs++ = i915_mmio_reg_offset(RING_TIMESTAMP(rq->engine->mmio_base)); - *cs++ = i915_request_timeline(rq)->hwsp_offset + slot * sizeof(u32); + *cs++ = tl->hwsp_offset + slot * sizeof(u32); *cs++ = 0; intel_ring_advance(rq, cs); @@ -73,7 +75,7 @@ static struct i915_vma *create_empty_batch(struct intel_context *ce) if (IS_ERR(obj)) return ERR_CAST(obj); - cs = i915_gem_object_pin_map(obj, I915_MAP_WB); + cs = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WB); if (IS_ERR(cs)) { err = PTR_ERR(cs); goto err_put; @@ -209,7 +211,7 @@ static struct i915_vma *create_nop_batch(struct intel_context *ce) if (IS_ERR(obj)) return ERR_CAST(obj); - cs = i915_gem_object_pin_map(obj, I915_MAP_WB); + cs = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WB); if (IS_ERR(cs)) { err = PTR_ERR(cs); goto err_put; diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c index 223ab88f7e57..b2c369317bf1 100644 --- a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c +++ b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2018 Intel Corporation */ @@ -12,6 +11,12 @@ #include "i915_selftest.h" #include "selftest_engine_heartbeat.h" +static void reset_heartbeat(struct intel_engine_cs *engine) +{ + intel_engine_set_heartbeat(engine, + engine->defaults.heartbeat_interval_ms); +} + static int timeline_sync(struct intel_timeline *tl) { struct dma_fence *fence; @@ -270,7 +275,7 @@ static int __live_heartbeat_fast(struct intel_engine_cs *engine) err = -EINVAL; } - intel_engine_set_heartbeat(engine, CONFIG_DRM_I915_HEARTBEAT_INTERVAL); + reset_heartbeat(engine); err_pm: intel_engine_pm_put(engine); intel_context_put(ce); @@ -285,7 +290,7 @@ static int live_heartbeat_fast(void *arg) int err = 0; /* Check that the heartbeat ticks at the desired rate. */ - if (!CONFIG_DRM_I915_HEARTBEAT_INTERVAL) + if (!IS_ACTIVE(CONFIG_DRM_I915_HEARTBEAT_INTERVAL)) return 0; for_each_engine(engine, gt, id) { @@ -333,7 +338,7 @@ static int __live_heartbeat_off(struct intel_engine_cs *engine) } err_beat: - intel_engine_set_heartbeat(engine, CONFIG_DRM_I915_HEARTBEAT_INTERVAL); + reset_heartbeat(engine); err_pm: intel_engine_pm_put(engine); return err; @@ -347,7 +352,7 @@ static int live_heartbeat_off(void *arg) int err = 0; /* Check that we can turn off heartbeat and not interrupt VIP */ - if (!CONFIG_DRM_I915_HEARTBEAT_INTERVAL) + if (!IS_ACTIVE(CONFIG_DRM_I915_HEARTBEAT_INTERVAL)) return 0; for_each_engine(engine, gt, id) { diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c index c3d965279fc3..2c898622bdfb 100644 --- a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c +++ b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * SPDX-License-Identifier: GPL-2.0 - * * Copyright © 2018 Intel Corporation */ @@ -111,13 +110,15 @@ static int __measure_timestamps(struct intel_context *ce, cpu_relax(); /* Run the request for a 100us, sampling timestamps before/after */ - preempt_disable(); - *dt = local_clock(); + local_irq_disable(); write_semaphore(&sema[2], 0); + while (READ_ONCE(sema[1]) == 0) /* wait for the gpu to catch up */ + cpu_relax(); + *dt = local_clock(); udelay(100); *dt = local_clock() - *dt; write_semaphore(&sema[2], 1); - preempt_enable(); + local_irq_enable(); if (i915_request_wait(rq, 0, HZ / 2) < 0) { i915_request_put(rq); diff --git a/drivers/gpu/drm/i915/gt/selftest_execlists.c b/drivers/gpu/drm/i915/gt/selftest_execlists.c index 264b5ebdb021..1081cd36a2bd 100644 --- a/drivers/gpu/drm/i915/gt/selftest_execlists.c +++ b/drivers/gpu/drm/i915/gt/selftest_execlists.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2018 Intel Corporation */ @@ -321,7 +320,7 @@ static int live_unlite_switch(void *arg) static int live_unlite_preempt(void *arg) { - return live_unlite_restore(arg, I915_USER_PRIORITY(I915_PRIORITY_MAX)); + return live_unlite_restore(arg, I915_PRIORITY_MAX); } static int live_unlite_ring(void *arg) @@ -609,7 +608,7 @@ static int live_hold_reset(void *arg) } tasklet_disable(&engine->execlists.tasklet); - engine->execlists.tasklet.func(engine->execlists.tasklet.data); + engine->execlists.tasklet.callback(&engine->execlists.tasklet); GEM_BUG_ON(execlists_active(&engine->execlists) != rq); i915_request_get(rq); @@ -989,7 +988,7 @@ static int live_timeslice_preempt(void *arg) goto err_obj; } - vaddr = i915_gem_object_pin_map(obj, I915_MAP_WC); + vaddr = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WC); if (IS_ERR(vaddr)) { err = PTR_ERR(vaddr); goto err_obj; @@ -1081,7 +1080,6 @@ create_rewinder(struct intel_context *ce, intel_ring_advance(rq, cs); - rq->sched.attr.priority = I915_PRIORITY_MASK; err = 0; err: i915_request_get(rq); @@ -1297,7 +1295,7 @@ static int live_timeslice_queue(void *arg) goto err_obj; } - vaddr = i915_gem_object_pin_map(obj, I915_MAP_WC); + vaddr = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WC); if (IS_ERR(vaddr)) { err = PTR_ERR(vaddr); goto err_obj; @@ -1312,9 +1310,7 @@ static int live_timeslice_queue(void *arg) goto err_pin; for_each_engine(engine, gt, id) { - struct i915_sched_attr attr = { - .priority = I915_USER_PRIORITY(I915_PRIORITY_MAX), - }; + struct i915_sched_attr attr = { .priority = I915_PRIORITY_MAX }; struct i915_request *rq, *nop; if (!intel_engine_has_preemption(engine)) @@ -1529,14 +1525,12 @@ static int live_busywait_preempt(void *arg) ctx_hi = kernel_context(gt->i915); if (!ctx_hi) return -ENOMEM; - ctx_hi->sched.priority = - I915_USER_PRIORITY(I915_CONTEXT_MAX_USER_PRIORITY); + ctx_hi->sched.priority = I915_CONTEXT_MAX_USER_PRIORITY; ctx_lo = kernel_context(gt->i915); if (!ctx_lo) goto err_ctx_hi; - ctx_lo->sched.priority = - I915_USER_PRIORITY(I915_CONTEXT_MIN_USER_PRIORITY); + ctx_lo->sched.priority = I915_CONTEXT_MIN_USER_PRIORITY; obj = i915_gem_object_create_internal(gt->i915, PAGE_SIZE); if (IS_ERR(obj)) { @@ -1544,7 +1538,7 @@ static int live_busywait_preempt(void *arg) goto err_ctx_lo; } - map = i915_gem_object_pin_map(obj, I915_MAP_WC); + map = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WC); if (IS_ERR(map)) { err = PTR_ERR(map); goto err_obj; @@ -1733,14 +1727,12 @@ static int live_preempt(void *arg) ctx_hi = kernel_context(gt->i915); if (!ctx_hi) goto err_spin_lo; - ctx_hi->sched.priority = - I915_USER_PRIORITY(I915_CONTEXT_MAX_USER_PRIORITY); + ctx_hi->sched.priority = I915_CONTEXT_MAX_USER_PRIORITY; ctx_lo = kernel_context(gt->i915); if (!ctx_lo) goto err_ctx_hi; - ctx_lo->sched.priority = - I915_USER_PRIORITY(I915_CONTEXT_MIN_USER_PRIORITY); + ctx_lo->sched.priority = I915_CONTEXT_MIN_USER_PRIORITY; for_each_engine(engine, gt, id) { struct igt_live_test t; @@ -1833,7 +1825,7 @@ static int live_late_preempt(void *arg) goto err_ctx_hi; /* Make sure ctx_lo stays before ctx_hi until we trigger preemption. */ - ctx_lo->sched.priority = I915_USER_PRIORITY(1); + ctx_lo->sched.priority = 1; for_each_engine(engine, gt, id) { struct igt_live_test t; @@ -1874,7 +1866,7 @@ static int live_late_preempt(void *arg) goto err_wedged; } - attr.priority = I915_USER_PRIORITY(I915_PRIORITY_MAX); + attr.priority = I915_PRIORITY_MAX; engine->schedule(rq, &attr); if (!igt_wait_for_spinner(&spin_hi, rq)) { @@ -1955,7 +1947,7 @@ static int live_nopreempt(void *arg) return -ENOMEM; if (preempt_client_init(gt, &b)) goto err_client_a; - b.ctx->sched.priority = I915_USER_PRIORITY(I915_PRIORITY_MAX); + b.ctx->sched.priority = I915_PRIORITY_MAX; for_each_engine(engine, gt, id) { struct i915_request *rq_a, *rq_b; @@ -2420,11 +2412,9 @@ err_wedged: static int live_suppress_self_preempt(void *arg) { + struct i915_sched_attr attr = { .priority = I915_PRIORITY_MAX }; struct intel_gt *gt = arg; struct intel_engine_cs *engine; - struct i915_sched_attr attr = { - .priority = I915_USER_PRIORITY(I915_PRIORITY_MAX) - }; struct preempt_client a, b; enum intel_engine_id id; int err = -ENOMEM; @@ -2555,9 +2545,7 @@ static int live_chain_preempt(void *arg) goto err_client_hi; for_each_engine(engine, gt, id) { - struct i915_sched_attr attr = { - .priority = I915_USER_PRIORITY(I915_PRIORITY_MAX), - }; + struct i915_sched_attr attr = { .priority = I915_PRIORITY_MAX }; struct igt_live_test t; struct i915_request *rq; int ring_size, count, i; @@ -2714,7 +2702,7 @@ static int create_gang(struct intel_engine_cs *engine, if (err) goto err_obj; - cs = i915_gem_object_pin_map(obj, I915_MAP_WC); + cs = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WC); if (IS_ERR(cs)) { err = PTR_ERR(cs); goto err_obj; @@ -2876,7 +2864,7 @@ static int __live_preempt_ring(struct intel_engine_cs *engine, err = wait_for_submit(engine, rq, HZ / 2); i915_request_put(rq); if (err) { - pr_err("%s: preemption request was not submited\n", + pr_err("%s: preemption request was not submitted\n", engine->name); err = -ETIME; } @@ -2976,9 +2964,7 @@ static int live_preempt_gang(void *arg) return -EIO; do { - struct i915_sched_attr attr = { - .priority = I915_USER_PRIORITY(prio++), - }; + struct i915_sched_attr attr = { .priority = prio++ }; err = create_gang(engine, &rq); if (err) @@ -2997,7 +2983,7 @@ static int live_preempt_gang(void *arg) * it will terminate the next lowest spinner until there * are no more spinners and the gang is complete. */ - cs = i915_gem_object_pin_map(rq->batch->obj, I915_MAP_WC); + cs = i915_gem_object_pin_map_unlocked(rq->batch->obj, I915_MAP_WC); if (!IS_ERR(cs)) { *cs = 0; i915_gem_object_unpin_map(rq->batch->obj); @@ -3014,7 +3000,7 @@ static int live_preempt_gang(void *arg) drm_info_printer(engine->i915->drm.dev); pr_err("Failed to flush chain of %d requests, at %d\n", - prio, rq_prio(rq) >> I915_USER_PRIORITY_SHIFT); + prio, rq_prio(rq)); intel_engine_dump(engine, &p, "%s\n", engine->name); @@ -3062,7 +3048,7 @@ create_gpr_user(struct intel_engine_cs *engine, return ERR_PTR(err); } - cs = i915_gem_object_pin_map(obj, I915_MAP_WC); + cs = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WC); if (IS_ERR(cs)) { i915_vma_put(vma); return ERR_CAST(cs); @@ -3269,7 +3255,7 @@ static int live_preempt_user(void *arg) if (IS_ERR(global)) return PTR_ERR(global); - result = i915_gem_object_pin_map(global->obj, I915_MAP_WC); + result = i915_gem_object_pin_map_unlocked(global->obj, I915_MAP_WC); if (IS_ERR(result)) { i915_vma_unpin_and_release(&global, 0); return PTR_ERR(result); @@ -3384,14 +3370,12 @@ static int live_preempt_timeout(void *arg) ctx_hi = kernel_context(gt->i915); if (!ctx_hi) goto err_spin_lo; - ctx_hi->sched.priority = - I915_USER_PRIORITY(I915_CONTEXT_MAX_USER_PRIORITY); + ctx_hi->sched.priority = I915_CONTEXT_MAX_USER_PRIORITY; ctx_lo = kernel_context(gt->i915); if (!ctx_lo) goto err_ctx_hi; - ctx_lo->sched.priority = - I915_USER_PRIORITY(I915_CONTEXT_MIN_USER_PRIORITY); + ctx_lo->sched.priority = I915_CONTEXT_MIN_USER_PRIORITY; for_each_engine(engine, gt, id) { unsigned long saved_timeout; @@ -3658,7 +3642,7 @@ static int live_preempt_smoke(void *arg) goto err_free; } - cs = i915_gem_object_pin_map(smoke.batch, I915_MAP_WB); + cs = i915_gem_object_pin_map_unlocked(smoke.batch, I915_MAP_WB); if (IS_ERR(cs)) { err = PTR_ERR(cs); goto err_batch; @@ -4197,8 +4181,9 @@ static int preserved_virtual_engine(struct intel_gt *gt, int err = 0; u32 *cs; - scratch = __vm_create_scratch_for_read(&siblings[0]->gt->ggtt->vm, - PAGE_SIZE); + scratch = + __vm_create_scratch_for_read_pinned(&siblings[0]->gt->ggtt->vm, + PAGE_SIZE); if (IS_ERR(scratch)) return PTR_ERR(scratch); @@ -4262,7 +4247,7 @@ static int preserved_virtual_engine(struct intel_gt *gt, goto out_end; } - cs = i915_gem_object_pin_map(scratch->obj, I915_MAP_WB); + cs = i915_gem_object_pin_map_unlocked(scratch->obj, I915_MAP_WB); if (IS_ERR(cs)) { err = PTR_ERR(cs); goto out_end; @@ -4610,7 +4595,7 @@ static int reset_virtual_engine(struct intel_gt *gt, } tasklet_disable(&engine->execlists.tasklet); - engine->execlists.tasklet.func(engine->execlists.tasklet.data); + engine->execlists.tasklet.callback(&engine->execlists.tasklet); GEM_BUG_ON(execlists_active(&engine->execlists) != rq); /* Fake a preemption event; failed of course */ diff --git a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c index 5d911f724ebe..c0845bf72dd3 100644 --- a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c +++ b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c @@ -1,7 +1,5 @@ - +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c index 463bb6a700c8..746985971c3a 100644 --- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c +++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c @@ -1,25 +1,6 @@ +// SPDX-License-Identifier: MIT /* * Copyright © 2016 Intel Corporation - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice (including the next - * paragraph) shall be included in all copies or substantial portions of the - * Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - * */ #include <linux/kthread.h> @@ -80,15 +61,15 @@ static int hang_init(struct hang *h, struct intel_gt *gt) } i915_gem_object_set_cache_coherency(h->hws, I915_CACHE_LLC); - vaddr = i915_gem_object_pin_map(h->hws, I915_MAP_WB); + vaddr = i915_gem_object_pin_map_unlocked(h->hws, I915_MAP_WB); if (IS_ERR(vaddr)) { err = PTR_ERR(vaddr); goto err_obj; } h->seqno = memset(vaddr, 0xff, PAGE_SIZE); - vaddr = i915_gem_object_pin_map(h->obj, - i915_coherent_map_type(gt->i915)); + vaddr = i915_gem_object_pin_map_unlocked(h->obj, + i915_coherent_map_type(gt->i915)); if (IS_ERR(vaddr)) { err = PTR_ERR(vaddr); goto err_unpin_hws; @@ -149,7 +130,7 @@ hang_create_request(struct hang *h, struct intel_engine_cs *engine) return ERR_CAST(obj); } - vaddr = i915_gem_object_pin_map(obj, i915_coherent_map_type(gt->i915)); + vaddr = i915_gem_object_pin_map_unlocked(obj, i915_coherent_map_type(gt->i915)); if (IS_ERR(vaddr)) { i915_gem_object_put(obj); i915_vm_put(vm); diff --git a/drivers/gpu/drm/i915/gt/selftest_llc.c b/drivers/gpu/drm/i915/gt/selftest_llc.c index a912159693fd..94006f117bbd 100644 --- a/drivers/gpu/drm/i915/gt/selftest_llc.c +++ b/drivers/gpu/drm/i915/gt/selftest_llc.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/selftest_llc.h b/drivers/gpu/drm/i915/gt/selftest_llc.h index 873f896e72f2..88ee9480022a 100644 --- a/drivers/gpu/drm/i915/gt/selftest_llc.h +++ b/drivers/gpu/drm/i915/gt/selftest_llc.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c index 920979a89413..85e7df6a5123 100644 --- a/drivers/gpu/drm/i915/gt/selftest_lrc.c +++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c @@ -27,7 +27,7 @@ static struct i915_vma *create_scratch(struct intel_gt *gt) { - return __vm_create_scratch_for_read(>->ggtt->vm, PAGE_SIZE); + return __vm_create_scratch_for_read_pinned(>->ggtt->vm, PAGE_SIZE); } static bool is_active(struct i915_request *rq) @@ -627,7 +627,7 @@ static int __live_lrc_gpr(struct intel_engine_cs *engine, goto err_rq; } - cs = i915_gem_object_pin_map(scratch->obj, I915_MAP_WB); + cs = i915_gem_object_pin_map_unlocked(scratch->obj, I915_MAP_WB); if (IS_ERR(cs)) { err = PTR_ERR(cs); goto err_rq; @@ -733,7 +733,6 @@ create_timestamp(struct intel_context *ce, void *slot, int idx) intel_ring_advance(rq, cs); - rq->sched.attr.priority = I915_PRIORITY_MASK; err = 0; err: i915_request_get(rq); @@ -921,7 +920,7 @@ store_context(struct intel_context *ce, struct i915_vma *scratch) if (IS_ERR(batch)) return batch; - cs = i915_gem_object_pin_map(batch->obj, I915_MAP_WC); + cs = i915_gem_object_pin_map_unlocked(batch->obj, I915_MAP_WC); if (IS_ERR(cs)) { i915_vma_put(batch); return ERR_CAST(cs); @@ -1085,7 +1084,7 @@ static struct i915_vma *load_context(struct intel_context *ce, u32 poison) if (IS_ERR(batch)) return batch; - cs = i915_gem_object_pin_map(batch->obj, I915_MAP_WC); + cs = i915_gem_object_pin_map_unlocked(batch->obj, I915_MAP_WC); if (IS_ERR(cs)) { i915_vma_put(batch); return ERR_CAST(cs); @@ -1199,29 +1198,29 @@ static int compare_isolation(struct intel_engine_cs *engine, u32 *defaults; int err = 0; - A[0] = i915_gem_object_pin_map(ref[0]->obj, I915_MAP_WC); + A[0] = i915_gem_object_pin_map_unlocked(ref[0]->obj, I915_MAP_WC); if (IS_ERR(A[0])) return PTR_ERR(A[0]); - A[1] = i915_gem_object_pin_map(ref[1]->obj, I915_MAP_WC); + A[1] = i915_gem_object_pin_map_unlocked(ref[1]->obj, I915_MAP_WC); if (IS_ERR(A[1])) { err = PTR_ERR(A[1]); goto err_A0; } - B[0] = i915_gem_object_pin_map(result[0]->obj, I915_MAP_WC); + B[0] = i915_gem_object_pin_map_unlocked(result[0]->obj, I915_MAP_WC); if (IS_ERR(B[0])) { err = PTR_ERR(B[0]); goto err_A1; } - B[1] = i915_gem_object_pin_map(result[1]->obj, I915_MAP_WC); + B[1] = i915_gem_object_pin_map_unlocked(result[1]->obj, I915_MAP_WC); if (IS_ERR(B[1])) { err = PTR_ERR(B[1]); goto err_B0; } - lrc = i915_gem_object_pin_map(ce->state->obj, + lrc = i915_gem_object_pin_map_unlocked(ce->state->obj, i915_coherent_map_type(engine->i915)); if (IS_ERR(lrc)) { err = PTR_ERR(lrc); diff --git a/drivers/gpu/drm/i915/gt/selftest_mocs.c b/drivers/gpu/drm/i915/gt/selftest_mocs.c index cf373c72359e..e55a887d11e2 100644 --- a/drivers/gpu/drm/i915/gt/selftest_mocs.c +++ b/drivers/gpu/drm/i915/gt/selftest_mocs.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ @@ -13,8 +12,9 @@ #include "selftests/igt_spinner.h" struct live_mocs { - struct drm_i915_mocs_table mocs; - struct drm_i915_mocs_table l3cc; + struct drm_i915_mocs_table table; + struct drm_i915_mocs_table *mocs; + struct drm_i915_mocs_table *l3cc; struct i915_vma *scratch; void *vaddr; }; @@ -59,27 +59,27 @@ static int request_add_spin(struct i915_request *rq, struct igt_spinner *spin) static int live_mocs_init(struct live_mocs *arg, struct intel_gt *gt) { - struct drm_i915_mocs_table table; unsigned int flags; int err; memset(arg, 0, sizeof(*arg)); - flags = get_mocs_settings(gt->i915, &table); + flags = get_mocs_settings(gt->i915, &arg->table); if (!flags) return -EINVAL; if (flags & HAS_RENDER_L3CC) - arg->l3cc = table; + arg->l3cc = &arg->table; if (flags & (HAS_GLOBAL_MOCS | HAS_ENGINE_MOCS)) - arg->mocs = table; + arg->mocs = &arg->table; - arg->scratch = __vm_create_scratch_for_read(>->ggtt->vm, PAGE_SIZE); + arg->scratch = + __vm_create_scratch_for_read_pinned(>->ggtt->vm, PAGE_SIZE); if (IS_ERR(arg->scratch)) return PTR_ERR(arg->scratch); - arg->vaddr = i915_gem_object_pin_map(arg->scratch->obj, I915_MAP_WB); + arg->vaddr = i915_gem_object_pin_map_unlocked(arg->scratch->obj, I915_MAP_WB); if (IS_ERR(arg->vaddr)) { err = PTR_ERR(arg->vaddr); goto err_scratch; @@ -131,6 +131,9 @@ static int read_mocs_table(struct i915_request *rq, { u32 addr; + if (!table) + return 0; + if (HAS_GLOBAL_MOCS_REGISTERS(rq->engine->i915)) addr = global_mocs_offset(); else @@ -145,6 +148,9 @@ static int read_l3cc_table(struct i915_request *rq, { u32 addr = i915_mmio_reg_offset(GEN9_LNCFCMOCS(0)); + if (!table) + return 0; + return read_regs(rq, addr, (table->n_entries + 1) / 2, offset); } @@ -155,6 +161,9 @@ static int check_mocs_table(struct intel_engine_cs *engine, unsigned int i; u32 expect; + if (!table) + return 0; + for_each_mocs(expect, table, i) { if (**vaddr != expect) { pr_err("%s: Invalid MOCS[%d] entry, found %08x, expected %08x\n", @@ -186,6 +195,9 @@ static int check_l3cc_table(struct intel_engine_cs *engine, unsigned int i; u32 expect; + if (!table) + return 0; + for_each_l3cc(expect, table, i) { if (!mcr_range(engine->i915, reg) && **vaddr != expect) { pr_err("%s: Invalid L3CC[%d] entry, found %08x, expected %08x\n", @@ -223,9 +235,9 @@ static int check_mocs_engine(struct live_mocs *arg, /* Read the mocs tables back using SRM */ offset = i915_ggtt_offset(vma); if (!err) - err = read_mocs_table(rq, &arg->mocs, &offset); + err = read_mocs_table(rq, arg->mocs, &offset); if (!err && ce->engine->class == RENDER_CLASS) - err = read_l3cc_table(rq, &arg->l3cc, &offset); + err = read_l3cc_table(rq, arg->l3cc, &offset); offset -= i915_ggtt_offset(vma); GEM_BUG_ON(offset > PAGE_SIZE); @@ -236,9 +248,9 @@ static int check_mocs_engine(struct live_mocs *arg, /* Compare the results against the expected tables */ vaddr = arg->vaddr; if (!err) - err = check_mocs_table(ce->engine, &arg->mocs, &vaddr); + err = check_mocs_table(ce->engine, arg->mocs, &vaddr); if (!err && ce->engine->class == RENDER_CLASS) - err = check_l3cc_table(ce->engine, &arg->l3cc, &vaddr); + err = check_l3cc_table(ce->engine, arg->l3cc, &vaddr); if (err) return err; diff --git a/drivers/gpu/drm/i915/gt/selftest_rc6.c b/drivers/gpu/drm/i915/gt/selftest_rc6.c index 61abc0556601..f097e420ac45 100644 --- a/drivers/gpu/drm/i915/gt/selftest_rc6.c +++ b/drivers/gpu/drm/i915/gt/selftest_rc6.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/selftest_rc6.h b/drivers/gpu/drm/i915/gt/selftest_rc6.h index 762fd442d7b2..daf0927909bc 100644 --- a/drivers/gpu/drm/i915/gt/selftest_rc6.h +++ b/drivers/gpu/drm/i915/gt/selftest_rc6.h @@ -1,6 +1,5 @@ +/* SPDX-License-Identifier: MIT */ /* - * SPDX-License-Identifier: MIT - * * Copyright © 2019 Intel Corporation */ diff --git a/drivers/gpu/drm/i915/gt/selftest_ring_submission.c b/drivers/gpu/drm/i915/gt/selftest_ring_submission.c index 3350e7c995bc..99609271c3a7 100644 --- a/drivers/gpu/drm/i915/gt/selftest_ring_submission.c +++ b/drivers/gpu/drm/i915/gt/selftest_ring_submission.c @@ -35,7 +35,7 @@ static struct i915_vma *create_wally(struct intel_engine_cs *engine) return ERR_PTR(err); } - cs = i915_gem_object_pin_map(obj, I915_MAP_WC); + cs = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WC); if (IS_ERR(cs)) { i915_gem_object_put(obj); return ERR_CAST(cs); @@ -212,7 +212,7 @@ static int __live_ctx_switch_wa(struct intel_engine_cs *engine) if (IS_ERR(bb)) return PTR_ERR(bb); - result = i915_gem_object_pin_map(bb->obj, I915_MAP_WC); + result = i915_gem_object_pin_map_unlocked(bb->obj, I915_MAP_WC); if (IS_ERR(result)) { intel_context_put(bb->private); i915_vma_unpin_and_release(&bb, 0); diff --git a/drivers/gpu/drm/i915/gt/selftest_timeline.c b/drivers/gpu/drm/i915/gt/selftest_timeline.c index 6f3a3687ef0f..9adbd9d147be 100644 --- a/drivers/gpu/drm/i915/gt/selftest_timeline.c +++ b/drivers/gpu/drm/i915/gt/selftest_timeline.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2017-2018 Intel Corporation */ @@ -35,10 +34,31 @@ static unsigned long hwsp_cacheline(struct intel_timeline *tl) { unsigned long address = (unsigned long)page_address(hwsp_page(tl)); - return (address + tl->hwsp_offset) / CACHELINE_BYTES; + return (address + offset_in_page(tl->hwsp_offset)) / TIMELINE_SEQNO_BYTES; } -#define CACHELINES_PER_PAGE (PAGE_SIZE / CACHELINE_BYTES) +static int selftest_tl_pin(struct intel_timeline *tl) +{ + struct i915_gem_ww_ctx ww; + int err; + + i915_gem_ww_ctx_init(&ww, false); +retry: + err = i915_gem_object_lock(tl->hwsp_ggtt->obj, &ww); + if (!err) + err = intel_timeline_pin(tl, &ww); + + if (err == -EDEADLK) { + err = i915_gem_ww_ctx_backoff(&ww); + if (!err) + goto retry; + } + i915_gem_ww_ctx_fini(&ww); + return err; +} + +/* Only half of seqno's are usable, see __intel_timeline_get_seqno() */ +#define CACHELINES_PER_PAGE (PAGE_SIZE / TIMELINE_SEQNO_BYTES / 2) struct mock_hwsp_freelist { struct intel_gt *gt; @@ -59,6 +79,7 @@ static void __mock_hwsp_record(struct mock_hwsp_freelist *state, tl = xchg(&state->history[idx], tl); if (tl) { radix_tree_delete(&state->cachelines, hwsp_cacheline(tl)); + intel_timeline_unpin(tl); intel_timeline_put(tl); } } @@ -78,6 +99,12 @@ static int __mock_hwsp_timeline(struct mock_hwsp_freelist *state, if (IS_ERR(tl)) return PTR_ERR(tl); + err = selftest_tl_pin(tl); + if (err) { + intel_timeline_put(tl); + return err; + } + cacheline = hwsp_cacheline(tl); err = radix_tree_insert(&state->cachelines, cacheline, tl); if (err) { @@ -85,6 +112,7 @@ static int __mock_hwsp_timeline(struct mock_hwsp_freelist *state, pr_err("HWSP cacheline %lu already used; duplicate allocation!\n", cacheline); } + intel_timeline_unpin(tl); intel_timeline_put(tl); return err; } @@ -452,17 +480,24 @@ static int emit_ggtt_store_dw(struct i915_request *rq, u32 addr, u32 value) } static struct i915_request * -tl_write(struct intel_timeline *tl, struct intel_engine_cs *engine, u32 value) +checked_tl_write(struct intel_timeline *tl, struct intel_engine_cs *engine, u32 value) { struct i915_request *rq; int err; - err = intel_timeline_pin(tl, NULL); + err = selftest_tl_pin(tl); if (err) { rq = ERR_PTR(err); goto out; } + if (READ_ONCE(*tl->hwsp_seqno) != tl->seqno) { + pr_err("Timeline created with incorrect breadcrumb, found %x, expected %x\n", + *tl->hwsp_seqno, tl->seqno); + intel_timeline_unpin(tl); + return ERR_PTR(-EINVAL); + } + rq = intel_engine_create_kernel_request(engine); if (IS_ERR(rq)) goto out_unpin; @@ -484,25 +519,6 @@ out: return rq; } -static struct intel_timeline * -checked_intel_timeline_create(struct intel_gt *gt) -{ - struct intel_timeline *tl; - - tl = intel_timeline_create(gt); - if (IS_ERR(tl)) - return tl; - - if (READ_ONCE(*tl->hwsp_seqno) != tl->seqno) { - pr_err("Timeline created with incorrect breadcrumb, found %x, expected %x\n", - *tl->hwsp_seqno, tl->seqno); - intel_timeline_put(tl); - return ERR_PTR(-EINVAL); - } - - return tl; -} - static int live_hwsp_engine(void *arg) { #define NUM_TIMELINES 4096 @@ -535,13 +551,13 @@ static int live_hwsp_engine(void *arg) struct intel_timeline *tl; struct i915_request *rq; - tl = checked_intel_timeline_create(gt); + tl = intel_timeline_create(gt); if (IS_ERR(tl)) { err = PTR_ERR(tl); break; } - rq = tl_write(tl, engine, count); + rq = checked_tl_write(tl, engine, count); if (IS_ERR(rq)) { intel_timeline_put(tl); err = PTR_ERR(rq); @@ -608,14 +624,14 @@ static int live_hwsp_alternate(void *arg) if (!intel_engine_can_store_dword(engine)) continue; - tl = checked_intel_timeline_create(gt); + tl = intel_timeline_create(gt); if (IS_ERR(tl)) { err = PTR_ERR(tl); goto out; } intel_engine_pm_get(engine); - rq = tl_write(tl, engine, count); + rq = checked_tl_write(tl, engine, count); intel_engine_pm_put(engine); if (IS_ERR(rq)) { intel_timeline_put(tl); @@ -666,10 +682,10 @@ static int live_hwsp_wrap(void *arg) if (IS_ERR(tl)) return PTR_ERR(tl); - if (!tl->has_initial_breadcrumb || !tl->hwsp_cacheline) + if (!tl->has_initial_breadcrumb) goto out_free; - err = intel_timeline_pin(tl, NULL); + err = selftest_tl_pin(tl); if (err) goto out_free; @@ -816,13 +832,13 @@ static int setup_watcher(struct hwsp_watcher *w, struct intel_gt *gt) if (IS_ERR(obj)) return PTR_ERR(obj); - w->map = i915_gem_object_pin_map(obj, I915_MAP_WB); + w->map = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WB); if (IS_ERR(w->map)) { i915_gem_object_put(obj); return PTR_ERR(w->map); } - vma = i915_gem_object_ggtt_pin_ww(obj, NULL, NULL, 0, 0, 0); + vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, 0); if (IS_ERR(vma)) { i915_gem_object_put(obj); return PTR_ERR(vma); @@ -833,12 +849,26 @@ static int setup_watcher(struct hwsp_watcher *w, struct intel_gt *gt) return 0; } +static void switch_tl_lock(struct i915_request *from, struct i915_request *to) +{ + /* some light mutex juggling required; think co-routines */ + + if (from) { + lockdep_unpin_lock(&from->context->timeline->mutex, from->cookie); + mutex_unlock(&from->context->timeline->mutex); + } + + if (to) { + mutex_lock(&to->context->timeline->mutex); + to->cookie = lockdep_pin_lock(&to->context->timeline->mutex); + } +} + static int create_watcher(struct hwsp_watcher *w, struct intel_engine_cs *engine, int ringsz) { struct intel_context *ce; - struct intel_timeline *tl; ce = intel_context_create(engine); if (IS_ERR(ce)) @@ -851,11 +881,8 @@ static int create_watcher(struct hwsp_watcher *w, return PTR_ERR(w->rq); w->addr = i915_ggtt_offset(w->vma); - tl = w->rq->context->timeline; - /* some light mutex juggling required; think co-routines */ - lockdep_unpin_lock(&tl->mutex, w->rq->cookie); - mutex_unlock(&tl->mutex); + switch_tl_lock(w->rq, NULL); return 0; } @@ -864,15 +891,13 @@ static int check_watcher(struct hwsp_watcher *w, const char *name, bool (*op)(u32 hwsp, u32 seqno)) { struct i915_request *rq = fetch_and_zero(&w->rq); - struct intel_timeline *tl = rq->context->timeline; u32 offset, end; int err; GEM_BUG_ON(w->addr - i915_ggtt_offset(w->vma) > w->vma->size); i915_request_get(rq); - mutex_lock(&tl->mutex); - rq->cookie = lockdep_pin_lock(&tl->mutex); + switch_tl_lock(NULL, rq); i915_request_add(rq); if (i915_request_wait(rq, 0, HZ) < 0) { @@ -901,10 +926,7 @@ out: static void cleanup_watcher(struct hwsp_watcher *w) { if (w->rq) { - struct intel_timeline *tl = w->rq->context->timeline; - - mutex_lock(&tl->mutex); - w->rq->cookie = lockdep_pin_lock(&tl->mutex); + switch_tl_lock(NULL, w->rq); i915_request_add(w->rq); } @@ -942,7 +964,7 @@ static struct i915_request *wrap_timeline(struct i915_request *rq) } i915_request_put(rq); - rq = intel_context_create_request(ce); + rq = i915_request_create(ce); if (IS_ERR(rq)) return rq; @@ -977,7 +999,7 @@ static int live_hwsp_read(void *arg) if (IS_ERR(tl)) return PTR_ERR(tl); - if (!tl->hwsp_cacheline) + if (!tl->has_initial_breadcrumb) goto out_free; for (i = 0; i < ARRAY_SIZE(watcher); i++) { @@ -999,7 +1021,7 @@ static int live_hwsp_read(void *arg) do { struct i915_sw_fence *submit; struct i915_request *rq; - u32 hwsp; + u32 hwsp, dummy; submit = heap_fence_create(GFP_KERNEL); if (!submit) { @@ -1017,14 +1039,26 @@ static int live_hwsp_read(void *arg) goto out; } - /* Skip to the end, saving 30 minutes of nops */ - tl->seqno = -10u + 2 * (count & 3); - WRITE_ONCE(*(u32 *)tl->hwsp_seqno, tl->seqno); ce->timeline = intel_timeline_get(tl); - rq = intel_context_create_request(ce); + /* Ensure timeline is mapped, done during first pin */ + err = intel_context_pin(ce); + if (err) { + intel_context_put(ce); + goto out; + } + + /* + * Start at a new wrap, and set seqno right before another wrap, + * saving 30 minutes of nops + */ + tl->seqno = -12u + 2 * (count & 3); + __intel_timeline_get_seqno(tl, &dummy); + + rq = i915_request_create(ce); if (IS_ERR(rq)) { err = PTR_ERR(rq); + intel_context_unpin(ce); intel_context_put(ce); goto out; } @@ -1034,32 +1068,35 @@ static int live_hwsp_read(void *arg) GFP_KERNEL); if (err < 0) { i915_request_add(rq); + intel_context_unpin(ce); intel_context_put(ce); goto out; } - mutex_lock(&watcher[0].rq->context->timeline->mutex); + switch_tl_lock(rq, watcher[0].rq); err = intel_timeline_read_hwsp(rq, watcher[0].rq, &hwsp); if (err == 0) err = emit_read_hwsp(watcher[0].rq, /* before */ rq->fence.seqno, hwsp, &watcher[0].addr); - mutex_unlock(&watcher[0].rq->context->timeline->mutex); + switch_tl_lock(watcher[0].rq, rq); if (err) { i915_request_add(rq); + intel_context_unpin(ce); intel_context_put(ce); goto out; } - mutex_lock(&watcher[1].rq->context->timeline->mutex); + switch_tl_lock(rq, watcher[1].rq); err = intel_timeline_read_hwsp(rq, watcher[1].rq, &hwsp); if (err == 0) err = emit_read_hwsp(watcher[1].rq, /* after */ rq->fence.seqno, hwsp, &watcher[1].addr); - mutex_unlock(&watcher[1].rq->context->timeline->mutex); + switch_tl_lock(watcher[1].rq, rq); if (err) { i915_request_add(rq); + intel_context_unpin(ce); intel_context_put(ce); goto out; } @@ -1068,6 +1105,7 @@ static int live_hwsp_read(void *arg) i915_request_add(rq); rq = wrap_timeline(rq); + intel_context_unpin(ce); intel_context_put(ce); if (IS_ERR(rq)) { err = PTR_ERR(rq); @@ -1107,8 +1145,8 @@ static int live_hwsp_read(void *arg) 3 * watcher[1].rq->ring->size) break; - } while (!__igt_timeout(end_time, NULL)); - WRITE_ONCE(*(u32 *)tl->hwsp_seqno, 0xdeadbeef); + } while (!__igt_timeout(end_time, NULL) && + count < (PAGE_SIZE / TIMELINE_SEQNO_BYTES - 1) / 2); pr_info("%s: simulated %lu wraps\n", engine->name, count); err = check_watcher(&watcher[1], "after", cmp_gte); @@ -1153,9 +1191,7 @@ static int live_hwsp_rollover_kernel(void *arg) } GEM_BUG_ON(i915_active_fence_isset(&tl->last_request)); - tl->seqno = 0; - timeline_rollback(tl); - timeline_rollback(tl); + tl->seqno = -2u; WRITE_ONCE(*(u32 *)tl->hwsp_seqno, tl->seqno); for (i = 0; i < ARRAY_SIZE(rq); i++) { @@ -1235,11 +1271,14 @@ static int live_hwsp_rollover_user(void *arg) goto out; tl = ce->timeline; - if (!tl->has_initial_breadcrumb || !tl->hwsp_cacheline) + if (!tl->has_initial_breadcrumb) + goto out; + + err = intel_context_pin(ce); + if (err) goto out; - timeline_rollback(tl); - timeline_rollback(tl); + tl->seqno = -4u; WRITE_ONCE(*(u32 *)tl->hwsp_seqno, tl->seqno); for (i = 0; i < ARRAY_SIZE(rq); i++) { @@ -1248,7 +1287,7 @@ static int live_hwsp_rollover_user(void *arg) this = intel_context_create_request(ce); if (IS_ERR(this)) { err = PTR_ERR(this); - goto out; + goto out_unpin; } pr_debug("%s: create fence.seqnp:%d\n", @@ -1267,17 +1306,18 @@ static int live_hwsp_rollover_user(void *arg) if (i915_request_wait(rq[2], 0, HZ / 5) < 0) { pr_err("Wait for timeline wrap timed out!\n"); err = -EIO; - goto out; + goto out_unpin; } for (i = 0; i < ARRAY_SIZE(rq); i++) { if (!i915_request_completed(rq[i])) { pr_err("Pre-wrap request not completed!\n"); err = -EINVAL; - goto out; + goto out_unpin; } } - +out_unpin: + intel_context_unpin(ce); out: for (i = 0; i < ARRAY_SIZE(rq); i++) i915_request_put(rq[i]); @@ -1319,13 +1359,13 @@ static int live_hwsp_recycle(void *arg) struct intel_timeline *tl; struct i915_request *rq; - tl = checked_intel_timeline_create(gt); + tl = intel_timeline_create(gt); if (IS_ERR(tl)) { err = PTR_ERR(tl); break; } - rq = tl_write(tl, engine, count); + rq = checked_tl_write(tl, engine, count); if (IS_ERR(rq)) { intel_timeline_put(tl); err = PTR_ERR(rq); diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c index 2070b91cb607..19850489a3fc 100644 --- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c +++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c @@ -1,6 +1,5 @@ +// SPDX-License-Identifier: MIT /* - * SPDX-License-Identifier: MIT - * * Copyright © 2018 Intel Corporation */ @@ -112,7 +111,7 @@ read_nonprivs(struct intel_context *ce) i915_gem_object_set_cache_coherency(result, I915_CACHE_LLC); - cs = i915_gem_object_pin_map(result, I915_MAP_WB); + cs = i915_gem_object_pin_map_unlocked(result, I915_MAP_WB); if (IS_ERR(cs)) { err = PTR_ERR(cs); goto err_obj; @@ -218,7 +217,7 @@ static int check_whitelist(struct intel_context *ce) i915_gem_object_lock(results, NULL); intel_wedge_on_timeout(&wedge, engine->gt, HZ / 5) /* safety net! */ err = i915_gem_object_set_to_cpu_domain(results, false); - i915_gem_object_unlock(results); + if (intel_gt_is_wedged(engine->gt)) err = -EIO; if (err) @@ -246,6 +245,7 @@ static int check_whitelist(struct intel_context *ce) i915_gem_object_unpin_map(results); out_put: + i915_gem_object_unlock(results); i915_gem_object_put(results); return err; } @@ -490,7 +490,7 @@ static int check_dirty_whitelist(struct intel_context *ce) u32 *cs, *results; sz = (2 * ARRAY_SIZE(values) + 1) * sizeof(u32); - scratch = __vm_create_scratch_for_read(ce->vm, sz); + scratch = __vm_create_scratch_for_read_pinned(ce->vm, sz); if (IS_ERR(scratch)) return PTR_ERR(scratch); @@ -502,6 +502,7 @@ static int check_dirty_whitelist(struct intel_context *ce) for (i = 0; i < engine->whitelist.count; i++) { u32 reg = i915_mmio_reg_offset(engine->whitelist.list[i].reg); + struct i915_gem_ww_ctx ww; u64 addr = scratch->node.start; struct i915_request *rq; u32 srm, lrm, rsvd; @@ -517,6 +518,29 @@ static int check_dirty_whitelist(struct intel_context *ce) ro_reg = ro_register(reg); + i915_gem_ww_ctx_init(&ww, false); +retry: + cs = NULL; + err = i915_gem_object_lock(scratch->obj, &ww); + if (!err) + err = i915_gem_object_lock(batch->obj, &ww); + if (!err) + err = intel_context_pin_ww(ce, &ww); + if (err) + goto out; + + cs = i915_gem_object_pin_map(batch->obj, I915_MAP_WC); + if (IS_ERR(cs)) { + err = PTR_ERR(cs); + goto out_ctx; + } + + results = i915_gem_object_pin_map(scratch->obj, I915_MAP_WB); + if (IS_ERR(results)) { + err = PTR_ERR(results); + goto out_unmap_batch; + } + /* Clear non priv flags */ reg &= RING_FORCE_TO_NONPRIV_ADDRESS_MASK; @@ -528,12 +552,6 @@ static int check_dirty_whitelist(struct intel_context *ce) pr_debug("%s: Writing garbage to %x\n", engine->name, reg); - cs = i915_gem_object_pin_map(batch->obj, I915_MAP_WC); - if (IS_ERR(cs)) { - err = PTR_ERR(cs); - goto out_batch; - } - /* SRM original */ *cs++ = srm; *cs++ = reg; @@ -580,11 +598,12 @@ static int check_dirty_whitelist(struct intel_context *ce) i915_gem_object_flush_map(batch->obj); i915_gem_object_unpin_map(batch->obj); intel_gt_chipset_flush(engine->gt); + cs = NULL; - rq = intel_context_create_request(ce); + rq = i915_request_create(ce); if (IS_ERR(rq)) { err = PTR_ERR(rq); - goto out_batch; + goto out_unmap_scratch; } if (engine->emit_init_breadcrumb) { /* Be nice if we hang */ @@ -593,20 +612,16 @@ static int check_dirty_whitelist(struct intel_context *ce) goto err_request; } - i915_vma_lock(batch); err = i915_request_await_object(rq, batch->obj, false); if (err == 0) err = i915_vma_move_to_active(batch, rq, 0); - i915_vma_unlock(batch); if (err) goto err_request; - i915_vma_lock(scratch); err = i915_request_await_object(rq, scratch->obj, true); if (err == 0) err = i915_vma_move_to_active(scratch, rq, EXEC_OBJECT_WRITE); - i915_vma_unlock(scratch); if (err) goto err_request; @@ -622,13 +637,7 @@ err_request: pr_err("%s: Futzing %x timedout; cancelling test\n", engine->name, reg); intel_gt_set_wedged(engine->gt); - goto out_batch; - } - - results = i915_gem_object_pin_map(scratch->obj, I915_MAP_WB); - if (IS_ERR(results)) { - err = PTR_ERR(results); - goto out_batch; + goto out_unmap_scratch; } GEM_BUG_ON(values[ARRAY_SIZE(values) - 1] != 0xffffffff); @@ -639,7 +648,7 @@ err_request: pr_err("%s: Unable to write to whitelisted register %x\n", engine->name, reg); err = -EINVAL; - goto out_unpin; + goto out_unmap_scratch; } } else { rsvd = 0; @@ -705,15 +714,27 @@ err_request: err = -EINVAL; } -out_unpin: +out_unmap_scratch: i915_gem_object_unpin_map(scratch->obj); +out_unmap_batch: + if (cs) + i915_gem_object_unpin_map(batch->obj); +out_ctx: + intel_context_unpin(ce); +out: + if (err == -EDEADLK) { + err = i915_gem_ww_ctx_backoff(&ww); + if (!err) + goto retry; + } + i915_gem_ww_ctx_fini(&ww); if (err) break; } if (igt_flush_test(engine->i915)) err = -EIO; -out_batch: + i915_vma_unpin_and_release(&batch, 0); out_scratch: i915_vma_unpin_and_release(&scratch, 0); @@ -847,7 +868,7 @@ static int scrub_whitelisted_registers(struct intel_context *ce) if (IS_ERR(batch)) return PTR_ERR(batch); - cs = i915_gem_object_pin_map(batch->obj, I915_MAP_WC); + cs = i915_gem_object_pin_map_unlocked(batch->obj, I915_MAP_WC); if (IS_ERR(cs)) { err = PTR_ERR(cs); goto err_batch; @@ -982,11 +1003,11 @@ check_whitelisted_registers(struct intel_engine_cs *engine, u32 *a, *b; int i, err; - a = i915_gem_object_pin_map(A->obj, I915_MAP_WB); + a = i915_gem_object_pin_map_unlocked(A->obj, I915_MAP_WB); if (IS_ERR(a)) return PTR_ERR(a); - b = i915_gem_object_pin_map(B->obj, I915_MAP_WB); + b = i915_gem_object_pin_map_unlocked(B->obj, I915_MAP_WB); if (IS_ERR(b)) { err = PTR_ERR(b); goto err_a; @@ -1030,14 +1051,14 @@ static int live_isolated_whitelist(void *arg) for (i = 0; i < ARRAY_SIZE(client); i++) { client[i].scratch[0] = - __vm_create_scratch_for_read(gt->vm, 4096); + __vm_create_scratch_for_read_pinned(gt->vm, 4096); if (IS_ERR(client[i].scratch[0])) { err = PTR_ERR(client[i].scratch[0]); goto err; } client[i].scratch[1] = - __vm_create_scratch_for_read(gt->vm, 4096); + __vm_create_scratch_for_read_pinned(gt->vm, 4096); if (IS_ERR(client[i].scratch[1])) { err = PTR_ERR(client[i].scratch[1]); i915_vma_unpin_and_release(&client[i].scratch[0], 0); @@ -1220,7 +1241,11 @@ live_engine_reset_workarounds(void *arg) goto err; } - intel_engine_reset(engine, "live_workarounds:idle"); + ret = intel_engine_reset(engine, "live_workarounds:idle"); + if (ret) { + pr_err("%s: Reset failed while idle\n", engine->name); + goto err; + } ok = verify_wa_lists(gt, &lists, "after idle reset"); if (!ok) { @@ -1241,12 +1266,18 @@ live_engine_reset_workarounds(void *arg) ret = request_add_spin(rq, &spin); if (ret) { - pr_err("Spinner failed to start\n"); + pr_err("%s: Spinner failed to start\n", engine->name); igt_spinner_fini(&spin); goto err; } - intel_engine_reset(engine, "live_workarounds:active"); + ret = intel_engine_reset(engine, "live_workarounds:active"); + if (ret) { + pr_err("%s: Reset failed on an active spinner\n", + engine->name); + igt_spinner_fini(&spin); + goto err; + } igt_spinner_end(&spin); igt_spinner_fini(&spin); diff --git a/drivers/gpu/drm/i915/gt/shmem_utils.c b/drivers/gpu/drm/i915/gt/shmem_utils.c index a4d8fc9e2374..f8f02aab842b 100644 --- a/drivers/gpu/drm/i915/gt/shmem_utils.c +++ b/drivers/gpu/drm/i915/gt/shmem_utils.c @@ -39,7 +39,7 @@ struct file *shmem_create_from_object(struct drm_i915_gem_object *obj) return file; } - ptr = i915_gem_object_pin_map(obj, I915_MAP_WB); + ptr = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WB); if (IS_ERR(ptr)) return ERR_CAST(ptr); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c index 4545e90e3bf1..78305b2ec89d 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c @@ -682,7 +682,7 @@ int intel_guc_allocate_and_map_vma(struct intel_guc *guc, u32 size, if (IS_ERR(vma)) return PTR_ERR(vma); - vaddr = i915_gem_object_pin_map(vma->obj, I915_MAP_WB); + vaddr = i915_gem_object_pin_map_unlocked(vma->obj, I915_MAP_WB); if (IS_ERR(vaddr)) { i915_vma_unpin_and_release(&vma, 0); return PTR_ERR(vaddr); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c index c92f2c056db4..c36d5eb5bbb9 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c @@ -335,7 +335,7 @@ static int guc_log_map(struct intel_guc_log *log) * buffer pages, so that we can directly get the data * (up-to-date) from memory. */ - vaddr = i915_gem_object_pin_map(log->vma->obj, I915_MAP_WC); + vaddr = i915_gem_object_pin_map_unlocked(log->vma->obj, I915_MAP_WC); if (IS_ERR(vaddr)) return PTR_ERR(vaddr); @@ -744,7 +744,7 @@ int intel_guc_log_dump(struct intel_guc_log *log, struct drm_printer *p, if (!obj) return 0; - map = i915_gem_object_pin_map(obj, I915_MAP_WC); + map = i915_gem_object_pin_map_unlocked(obj, I915_MAP_WC); if (IS_ERR(map)) { DRM_DEBUG("Failed to pin object\n"); drm_puts(p, "(log data unaccessible)\n"); 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 23dc0aeaa0ab..92688a9b6717 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -206,9 +206,8 @@ static void __guc_dequeue(struct intel_engine_cs *engine) while ((rb = rb_first_cached(&execlists->queue))) { struct i915_priolist *p = to_priolist(rb); struct i915_request *rq, *rn; - int i; - priolist_for_each_request_consume(rq, rn, p, i) { + priolist_for_each_request_consume(rq, rn, p) { if (last && rq->context != last->context) { if (port == last_port) goto done; @@ -238,9 +237,10 @@ done: execlists->active = execlists->inflight; } -static void guc_submission_tasklet(unsigned long data) +static void guc_submission_tasklet(struct tasklet_struct *t) { - struct intel_engine_cs * const engine = (struct intel_engine_cs *)data; + struct intel_engine_cs * const engine = + from_tasklet(engine, t, execlists.tasklet); struct intel_engine_execlists * const execlists = &engine->execlists; struct i915_request **port, *rq; unsigned long flags; @@ -361,9 +361,8 @@ static void guc_reset_cancel(struct intel_engine_cs *engine) /* Flush the queued requests to the timeline list (for retiring). */ while ((rb = rb_first_cached(&execlists->queue))) { struct i915_priolist *p = to_priolist(rb); - int i; - priolist_for_each_request_consume(rq, rn, p, i) { + priolist_for_each_request_consume(rq, rn, p) { list_del_init(&rq->sched.link); __i915_request_submit(rq); dma_fence_set_error(&rq->fence, -EIO); @@ -610,7 +609,7 @@ static void guc_set_default_submission(struct intel_engine_cs *engine) { engine->submit_request = guc_submit_request; engine->schedule = i915_schedule; - engine->execlists.tasklet.func = guc_submission_tasklet; + engine->execlists.tasklet.callback = guc_submission_tasklet; engine->reset.prepare = guc_reset_prepare; engine->reset.rewind = guc_reset_rewind; @@ -702,8 +701,7 @@ int intel_guc_submission_setup(struct intel_engine_cs *engine) */ GEM_BUG_ON(INTEL_GEN(i915) < 11); - tasklet_init(&engine->execlists.tasklet, - guc_submission_tasklet, (unsigned long)engine); + tasklet_setup(&engine->execlists.tasklet, guc_submission_tasklet); guc_default_vfuncs(engine); guc_default_irqs(engine); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c index 65eeb44b397d..2126dd81ac38 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c @@ -82,7 +82,7 @@ static int intel_huc_rsa_data_create(struct intel_huc *huc) if (IS_ERR(vma)) return PTR_ERR(vma); - vaddr = i915_gem_object_pin_map(vma->obj, I915_MAP_WB); + vaddr = i915_gem_object_pin_map_unlocked(vma->obj, I915_MAP_WB); if (IS_ERR(vaddr)) { i915_vma_unpin_and_release(&vma, 0); return PTR_ERR(vaddr); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c index 67b06fde1225..df647c9a8d56 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c @@ -44,9 +44,11 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw, * List of required GuC and HuC binaries per-platform. * Must be ordered based on platform + revid, from newer to older. * - * Note that RKL uses the same firmware as TGL. + * Note that RKL and ADL-S have the same GuC/HuC device ID's and use the same + * firmware as TGL. */ #define INTEL_UC_FIRMWARE_DEFS(fw_def, guc_def, huc_def) \ + fw_def(ALDERLAKE_S, 0, guc_def(tgl, 49, 0, 1), huc_def(tgl, 7, 5, 0)) \ fw_def(ROCKETLAKE, 0, guc_def(tgl, 49, 0, 1), huc_def(tgl, 7, 5, 0)) \ fw_def(TIGERLAKE, 0, guc_def(tgl, 49, 0, 1), huc_def(tgl, 7, 5, 0)) \ fw_def(JASPERLAKE, 0, guc_def(ehl, 49, 0, 1), huc_def(ehl, 9, 0, 0)) \ @@ -537,7 +539,7 @@ int intel_uc_fw_init(struct intel_uc_fw *uc_fw) if (!intel_uc_fw_is_available(uc_fw)) return -ENOEXEC; - err = i915_gem_object_pin_pages(uc_fw->obj); + err = i915_gem_object_pin_pages_unlocked(uc_fw->obj); if (err) { DRM_DEBUG_DRIVER("%s fw pin-pages err=%d\n", intel_uc_fw_type_repr(uc_fw->type), err); |