diff options
Diffstat (limited to 'drivers/gpu/drm/i915/gvt')
| -rw-r--r-- | drivers/gpu/drm/i915/gvt/aperture_gm.c | 24 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/gvt/cmd_parser.c | 27 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/gvt/debugfs.c | 4 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/gvt/firmware.c | 5 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/gvt/gvt.h | 10 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/gvt/kvmgt.c | 2 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/gvt/mmio_context.c | 4 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/gvt/opregion.c | 2 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/gvt/sched_policy.c | 4 | ||||
| -rw-r--r-- | drivers/gpu/drm/i915/gvt/scheduler.c | 190 |
10 files changed, 146 insertions, 126 deletions
diff --git a/drivers/gpu/drm/i915/gvt/aperture_gm.c b/drivers/gpu/drm/i915/gvt/aperture_gm.c index 1fa2f65c3cd1..c3d19d88da40 100644 --- a/drivers/gpu/drm/i915/gvt/aperture_gm.c +++ b/drivers/gpu/drm/i915/gvt/aperture_gm.c @@ -35,6 +35,7 @@ */ #include "i915_drv.h" +#include "i915_gem_fence_reg.h" #include "gvt.h" static int alloc_gm(struct intel_vgpu *vgpu, bool high_gm) @@ -128,10 +129,10 @@ void intel_vgpu_write_fence(struct intel_vgpu *vgpu, { struct intel_gvt *gvt = vgpu->gvt; struct drm_i915_private *dev_priv = gvt->dev_priv; - struct drm_i915_fence_reg *reg; + struct i915_fence_reg *reg; i915_reg_t fence_reg_lo, fence_reg_hi; - assert_rpm_wakelock_held(dev_priv); + assert_rpm_wakelock_held(&dev_priv->runtime_pm); if (WARN_ON(fence >= vgpu_fence_sz(vgpu))) return; @@ -163,13 +164,13 @@ static void free_vgpu_fence(struct intel_vgpu *vgpu) { struct intel_gvt *gvt = vgpu->gvt; struct drm_i915_private *dev_priv = gvt->dev_priv; - struct drm_i915_fence_reg *reg; + struct i915_fence_reg *reg; u32 i; if (WARN_ON(!vgpu_fence_sz(vgpu))) return; - intel_runtime_pm_get(dev_priv); + intel_runtime_pm_get(&dev_priv->runtime_pm); mutex_lock(&dev_priv->drm.struct_mutex); _clear_vgpu_fence(vgpu); @@ -180,17 +181,18 @@ static void free_vgpu_fence(struct intel_vgpu *vgpu) } mutex_unlock(&dev_priv->drm.struct_mutex); - intel_runtime_pm_put_unchecked(dev_priv); + intel_runtime_pm_put_unchecked(&dev_priv->runtime_pm); } static int alloc_vgpu_fence(struct intel_vgpu *vgpu) { struct intel_gvt *gvt = vgpu->gvt; struct drm_i915_private *dev_priv = gvt->dev_priv; - struct drm_i915_fence_reg *reg; + struct intel_runtime_pm *rpm = &dev_priv->runtime_pm; + struct i915_fence_reg *reg; int i; - intel_runtime_pm_get(dev_priv); + intel_runtime_pm_get(rpm); /* Request fences from host */ mutex_lock(&dev_priv->drm.struct_mutex); @@ -206,7 +208,7 @@ static int alloc_vgpu_fence(struct intel_vgpu *vgpu) _clear_vgpu_fence(vgpu); mutex_unlock(&dev_priv->drm.struct_mutex); - intel_runtime_pm_put_unchecked(dev_priv); + intel_runtime_pm_put_unchecked(rpm); return 0; out_free_fence: gvt_vgpu_err("Failed to alloc fences\n"); @@ -219,7 +221,7 @@ out_free_fence: vgpu->fence.regs[i] = NULL; } mutex_unlock(&dev_priv->drm.struct_mutex); - intel_runtime_pm_put_unchecked(dev_priv); + intel_runtime_pm_put_unchecked(rpm); return -ENOSPC; } @@ -315,9 +317,9 @@ void intel_vgpu_reset_resource(struct intel_vgpu *vgpu) { struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; - intel_runtime_pm_get(dev_priv); + intel_runtime_pm_get(&dev_priv->runtime_pm); _clear_vgpu_fence(vgpu); - intel_runtime_pm_put_unchecked(dev_priv); + intel_runtime_pm_put_unchecked(&dev_priv->runtime_pm); } /** diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index de5347725564..6ea88270c818 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -1725,7 +1725,7 @@ static int perform_bb_shadow(struct parser_exec_state *s) int ret = 0; struct intel_vgpu_mm *mm = (s->buf_addr_type == GTT_BUFFER) ? s->vgpu->gtt.ggtt_mm : s->workload->shadow_mm; - unsigned long gma_start_offset = 0; + unsigned long start_offset = 0; /* get the start gm address of the batch buffer */ gma = get_gma_bb_from_cmd(s, 1); @@ -1742,7 +1742,7 @@ static int perform_bb_shadow(struct parser_exec_state *s) bb->ppgtt = (s->buf_addr_type == GTT_BUFFER) ? false : true; - /* the gma_start_offset stores the batch buffer's start gma's + /* the start_offset stores the batch buffer's start gma's * offset relative to page boundary. so for non-privileged batch * buffer, the shadowed gem object holds exactly the same page * layout as original gem object. This is for the convience of @@ -1754,16 +1754,17 @@ static int perform_bb_shadow(struct parser_exec_state *s) * that of shadowed page. */ if (bb->ppgtt) - gma_start_offset = gma & ~I915_GTT_PAGE_MASK; + start_offset = gma & ~I915_GTT_PAGE_MASK; - bb->obj = i915_gem_object_create(s->vgpu->gvt->dev_priv, - roundup(bb_size + gma_start_offset, PAGE_SIZE)); + bb->obj = i915_gem_object_create_shmem(s->vgpu->gvt->dev_priv, + round_up(bb_size + start_offset, + PAGE_SIZE)); if (IS_ERR(bb->obj)) { ret = PTR_ERR(bb->obj); goto err_free_bb; } - ret = i915_gem_obj_prepare_shmem_write(bb->obj, &bb->clflush); + ret = i915_gem_object_prepare_write(bb->obj, &bb->clflush); if (ret) goto err_free_obj; @@ -1780,7 +1781,7 @@ static int perform_bb_shadow(struct parser_exec_state *s) ret = copy_gma_to_hva(s->vgpu, mm, gma, gma + bb_size, - bb->va + gma_start_offset); + bb->va + start_offset); if (ret < 0) { gvt_vgpu_err("fail to copy guest ring buffer\n"); ret = -EFAULT; @@ -1806,13 +1807,13 @@ static int perform_bb_shadow(struct parser_exec_state *s) * buffer's gma in pair. After all, we don't want to pin the shadow * buffer here (too early). */ - s->ip_va = bb->va + gma_start_offset; + s->ip_va = bb->va + start_offset; s->ip_gma = gma; return 0; err_unmap: i915_gem_object_unpin_map(bb->obj); err_finish_shmem_access: - i915_gem_obj_finish_shmem_access(bb->obj); + i915_gem_object_finish_access(bb->obj); err_free_obj: i915_gem_object_put(bb->obj); err_free_bb: @@ -2829,9 +2830,9 @@ static int shadow_indirect_ctx(struct intel_shadow_wa_ctx *wa_ctx) int ret = 0; void *map; - obj = i915_gem_object_create(workload->vgpu->gvt->dev_priv, - roundup(ctx_size + CACHELINE_BYTES, - PAGE_SIZE)); + obj = i915_gem_object_create_shmem(workload->vgpu->gvt->dev_priv, + roundup(ctx_size + CACHELINE_BYTES, + PAGE_SIZE)); if (IS_ERR(obj)) return PTR_ERR(obj); @@ -2843,7 +2844,9 @@ static int shadow_indirect_ctx(struct intel_shadow_wa_ctx *wa_ctx) goto put_obj; } + i915_gem_object_lock(obj); ret = i915_gem_object_set_to_cpu_domain(obj, false); + i915_gem_object_unlock(obj); if (ret) { gvt_vgpu_err("failed to set shadow indirect ctx to CPU\n"); goto unmap_src; diff --git a/drivers/gpu/drm/i915/gvt/debugfs.c b/drivers/gpu/drm/i915/gvt/debugfs.c index 8a9606f91e68..2fb7b73b260d 100644 --- a/drivers/gpu/drm/i915/gvt/debugfs.c +++ b/drivers/gpu/drm/i915/gvt/debugfs.c @@ -58,12 +58,12 @@ static int mmio_offset_compare(void *priv, static inline int mmio_diff_handler(struct intel_gvt *gvt, u32 offset, void *data) { - struct drm_i915_private *dev_priv = gvt->dev_priv; + struct drm_i915_private *i915 = gvt->dev_priv; struct mmio_diff_param *param = data; struct diff_mmio *node; u32 preg, vreg; - preg = I915_READ_NOTRACE(_MMIO(offset)); + preg = intel_uncore_read_notrace(&i915->uncore, _MMIO(offset)); vreg = vgpu_vreg(param->vgpu, offset); if (preg != vreg) { diff --git a/drivers/gpu/drm/i915/gvt/firmware.c b/drivers/gpu/drm/i915/gvt/firmware.c index 4ac18b447247..049775e8e350 100644 --- a/drivers/gpu/drm/i915/gvt/firmware.c +++ b/drivers/gpu/drm/i915/gvt/firmware.c @@ -68,9 +68,10 @@ static struct bin_attribute firmware_attr = { static int mmio_snapshot_handler(struct intel_gvt *gvt, u32 offset, void *data) { - struct drm_i915_private *dev_priv = gvt->dev_priv; + struct drm_i915_private *i915 = gvt->dev_priv; - *(u32 *)(data + offset) = I915_READ_NOTRACE(_MMIO(offset)); + *(u32 *)(data + offset) = intel_uncore_read_notrace(&i915->uncore, + _MMIO(offset)); return 0; } diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index f5a328b5290a..7a1fe44d45af 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -87,7 +87,7 @@ struct intel_vgpu_gm { /* Fences owned by a vGPU */ struct intel_vgpu_fence { - struct drm_i915_fence_reg *regs[INTEL_GVT_MAX_NUM_FENCES]; + struct i915_fence_reg *regs[INTEL_GVT_MAX_NUM_FENCES]; u32 base; u32 size; }; @@ -149,9 +149,9 @@ struct intel_vgpu_submission_ops { struct intel_vgpu_submission { struct intel_vgpu_execlist execlist[I915_NUM_ENGINES]; struct list_head workload_q_head[I915_NUM_ENGINES]; + struct intel_context *shadow[I915_NUM_ENGINES]; struct kmem_cache *workloads; atomic_t running_workload_num; - struct i915_gem_context *shadow_ctx; union { u64 i915_context_pml4; u64 i915_context_pdps[GEN8_3LVL_PDPES]; @@ -390,7 +390,7 @@ int intel_gvt_load_firmware(struct intel_gvt *gvt); #define gvt_hidden_gmadr_end(gvt) (gvt_hidden_gmadr_base(gvt) \ + gvt_hidden_sz(gvt) - 1) -#define gvt_fence_sz(gvt) (gvt->dev_priv->num_fence_regs) +#define gvt_fence_sz(gvt) ((gvt)->dev_priv->ggtt.num_fences) /* Aperture/GM space definitions for vGPU */ #define vgpu_aperture_offset(vgpu) ((vgpu)->gm.low_gm_node.start) @@ -584,12 +584,12 @@ enum { static inline void mmio_hw_access_pre(struct drm_i915_private *dev_priv) { - intel_runtime_pm_get(dev_priv); + intel_runtime_pm_get(&dev_priv->runtime_pm); } static inline void mmio_hw_access_post(struct drm_i915_private *dev_priv) { - intel_runtime_pm_put_unchecked(dev_priv); + intel_runtime_pm_put_unchecked(&dev_priv->runtime_pm); } /** diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index a68addf95c23..144301b778df 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -1576,7 +1576,7 @@ hw_id_show(struct device *dev, struct device_attribute *attr, struct intel_vgpu *vgpu = (struct intel_vgpu *) mdev_get_drvdata(mdev); return sprintf(buf, "%u\n", - vgpu->submission.shadow_ctx->hw_id); + vgpu->submission.shadow[0]->gem_context->hw_id); } return sprintf(buf, "\n"); } diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index 90bb3df0db50..2998999e8568 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -34,6 +34,7 @@ */ #include "i915_drv.h" +#include "gt/intel_context.h" #include "gvt.h" #include "trace.h" @@ -493,8 +494,7 @@ static void switch_mmio(struct intel_vgpu *pre, * itself. */ if (mmio->in_context && - !is_inhibit_context(intel_context_lookup(s->shadow_ctx, - dev_priv->engine[ring_id]))) + !is_inhibit_context(s->shadow[ring_id])) continue; if (mmio->mask) diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c index 276db53f1bf1..867e7629025b 100644 --- a/drivers/gpu/drm/i915/gvt/opregion.c +++ b/drivers/gpu/drm/i915/gvt/opregion.c @@ -30,7 +30,7 @@ * not do like this. */ #define _INTEL_BIOS_PRIVATE -#include "intel_vbt_defs.h" +#include "display/intel_vbt_defs.h" #define OPREGION_SIGNATURE "IntelGraphicsMem" #define MBOX_VBT (1<<3) diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.c b/drivers/gpu/drm/i915/gvt/sched_policy.c index 1c763a27a412..2369d4a9af94 100644 --- a/drivers/gpu/drm/i915/gvt/sched_policy.c +++ b/drivers/gpu/drm/i915/gvt/sched_policy.c @@ -465,7 +465,7 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu) scheduler->current_vgpu = NULL; } - intel_runtime_pm_get(dev_priv); + intel_runtime_pm_get(&dev_priv->runtime_pm); spin_lock_bh(&scheduler->mmio_context_lock); for (ring_id = 0; ring_id < I915_NUM_ENGINES; ring_id++) { if (scheduler->engine_owner[ring_id] == vgpu) { @@ -474,6 +474,6 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu) } } spin_unlock_bh(&scheduler->mmio_context_lock); - intel_runtime_pm_put_unchecked(dev_priv); + intel_runtime_pm_put_unchecked(&dev_priv->runtime_pm); mutex_unlock(&vgpu->gvt->sched_lock); } diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 0f919f0a43d4..2144fb46d0e1 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -35,6 +35,10 @@ #include <linux/kthread.h> +#include "gem/i915_gem_context.h" +#include "gem/i915_gem_pm.h" +#include "gt/intel_context.h" + #include "i915_drv.h" #include "gvt.h" @@ -277,18 +281,23 @@ static int shadow_context_status_change(struct notifier_block *nb, return NOTIFY_OK; } -static void shadow_context_descriptor_update(struct intel_context *ce) +static void +shadow_context_descriptor_update(struct intel_context *ce, + struct intel_vgpu_workload *workload) { - u64 desc = 0; + u64 desc = ce->lrc_desc; - desc = ce->lrc_desc; - - /* Update bits 0-11 of the context descriptor which includes flags + /* + * Update bits 0-11 of the context descriptor which includes flags * like GEN8_CTX_* cached in desc_template */ desc &= U64_MAX << 12; desc |= ce->gem_context->desc_template & ((1ULL << 12) - 1); + desc &= ~(0x3 << GEN8_CTX_ADDRESSING_MODE_SHIFT); + desc |= workload->ctx_desc.addressing_mode << + GEN8_CTX_ADDRESSING_MODE_SHIFT; + ce->lrc_desc = desc; } @@ -359,18 +368,20 @@ static int set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload, struct i915_gem_context *ctx) { struct intel_vgpu_mm *mm = workload->shadow_mm; - struct i915_hw_ppgtt *ppgtt = ctx->ppgtt; + struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(ctx->vm); int i = 0; if (mm->type != INTEL_GVT_MM_PPGTT || !mm->ppgtt_mm.shadowed) return -EINVAL; if (mm->ppgtt_mm.root_entry_type == GTT_TYPE_PPGTT_ROOT_L4_ENTRY) { - px_dma(&ppgtt->pml4) = mm->ppgtt_mm.shadow_pdps[0]; + px_dma(ppgtt->pd) = mm->ppgtt_mm.shadow_pdps[0]; } else { for (i = 0; i < GVT_RING_CTX_NR_PDPS; i++) { - px_dma(ppgtt->pdp.page_directory[i]) = - mm->ppgtt_mm.shadow_pdps[i]; + struct i915_page_directory * const pd = + i915_pd_entry(ppgtt->pd, i); + + px_dma(pd) = mm->ppgtt_mm.shadow_pdps[i]; } } @@ -382,26 +393,22 @@ intel_gvt_workload_req_alloc(struct intel_vgpu_workload *workload) { struct intel_vgpu *vgpu = workload->vgpu; struct intel_vgpu_submission *s = &vgpu->submission; - struct i915_gem_context *shadow_ctx = s->shadow_ctx; struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; - struct intel_engine_cs *engine = dev_priv->engine[workload->ring_id]; struct i915_request *rq; - int ret = 0; lockdep_assert_held(&dev_priv->drm.struct_mutex); if (workload->req) - goto out; + return 0; - rq = i915_request_alloc(engine, shadow_ctx); + rq = i915_request_create(s->shadow[workload->ring_id]); if (IS_ERR(rq)) { gvt_vgpu_err("fail to allocate gem request\n"); - ret = PTR_ERR(rq); - goto out; + return PTR_ERR(rq); } + workload->req = i915_request_get(rq); -out: - return ret; + return 0; } /** @@ -416,10 +423,7 @@ int intel_gvt_scan_and_shadow_workload(struct intel_vgpu_workload *workload) { struct intel_vgpu *vgpu = workload->vgpu; struct intel_vgpu_submission *s = &vgpu->submission; - struct i915_gem_context *shadow_ctx = s->shadow_ctx; struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; - struct intel_engine_cs *engine = dev_priv->engine[workload->ring_id]; - struct intel_context *ce; int ret; lockdep_assert_held(&dev_priv->drm.struct_mutex); @@ -427,29 +431,13 @@ int intel_gvt_scan_and_shadow_workload(struct intel_vgpu_workload *workload) if (workload->shadow) return 0; - /* pin shadow context by gvt even the shadow context will be pinned - * when i915 alloc request. That is because gvt will update the guest - * context from shadow context when workload is completed, and at that - * moment, i915 may already unpined the shadow context to make the - * shadow_ctx pages invalid. So gvt need to pin itself. After update - * the guest context, gvt can unpin the shadow_ctx safely. - */ - ce = intel_context_pin(shadow_ctx, engine); - if (IS_ERR(ce)) { - gvt_vgpu_err("fail to pin shadow context\n"); - return PTR_ERR(ce); - } - - shadow_ctx->desc_template &= ~(0x3 << GEN8_CTX_ADDRESSING_MODE_SHIFT); - shadow_ctx->desc_template |= workload->ctx_desc.addressing_mode << - GEN8_CTX_ADDRESSING_MODE_SHIFT; - if (!test_and_set_bit(workload->ring_id, s->shadow_ctx_desc_updated)) - shadow_context_descriptor_update(ce); + shadow_context_descriptor_update(s->shadow[workload->ring_id], + workload); ret = intel_gvt_scan_and_shadow_ringbuffer(workload); if (ret) - goto err_unpin; + return ret; if (workload->ring_id == RCS0 && workload->wa_ctx.indirect_ctx.size) { ret = intel_gvt_scan_and_shadow_wa_ctx(&workload->wa_ctx); @@ -461,8 +449,6 @@ int intel_gvt_scan_and_shadow_workload(struct intel_vgpu_workload *workload) return 0; err_shadow: release_shadow_wa_ctx(&workload->wa_ctx); -err_unpin: - intel_context_unpin(ce); return ret; } @@ -501,7 +487,7 @@ static int prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload) bb->obj->base.size); bb->clflush &= ~CLFLUSH_AFTER; } - i915_gem_obj_finish_shmem_access(bb->obj); + i915_gem_object_finish_access(bb->obj); bb->accessing = false; } else { @@ -525,18 +511,18 @@ static int prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload) } ret = i915_gem_object_set_to_gtt_domain(bb->obj, - false); + false); if (ret) goto err; - i915_gem_obj_finish_shmem_access(bb->obj); - bb->accessing = false; - ret = i915_vma_move_to_active(bb->vma, workload->req, 0); if (ret) goto err; + + i915_gem_object_finish_access(bb->obj); + bb->accessing = false; } } return 0; @@ -607,7 +593,7 @@ static void release_shadow_batch_buffer(struct intel_vgpu_workload *workload) list_for_each_entry_safe(bb, pos, &workload->shadow_bb, list) { if (bb->obj) { if (bb->accessing) - i915_gem_obj_finish_shmem_access(bb->obj); + i915_gem_object_finish_access(bb->obj); if (bb->va && !IS_ERR(bb->va)) i915_gem_object_unpin_map(bb->obj); @@ -616,7 +602,7 @@ static void release_shadow_batch_buffer(struct intel_vgpu_workload *workload) i915_vma_unpin(bb->vma); i915_vma_close(bb->vma); } - __i915_gem_object_release_unless_active(bb->obj); + i915_gem_object_put(bb->obj); } list_del(&bb->list); kfree(bb); @@ -689,7 +675,6 @@ static int dispatch_workload(struct intel_vgpu_workload *workload) struct intel_vgpu *vgpu = workload->vgpu; struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; struct intel_vgpu_submission *s = &vgpu->submission; - struct i915_gem_context *shadow_ctx = s->shadow_ctx; struct i915_request *rq; int ring_id = workload->ring_id; int ret; @@ -700,7 +685,8 @@ static int dispatch_workload(struct intel_vgpu_workload *workload) mutex_lock(&vgpu->vgpu_lock); mutex_lock(&dev_priv->drm.struct_mutex); - ret = set_context_ppgtt_from_shadow(workload, shadow_ctx); + ret = set_context_ppgtt_from_shadow(workload, + s->shadow[ring_id]->gem_context); if (ret < 0) { gvt_vgpu_err("workload shadow ppgtt isn't ready\n"); goto err_req; @@ -949,11 +935,6 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id) intel_vgpu_trigger_virtual_event(vgpu, event); } - /* unpin shadow ctx as the shadow_ctx update is done */ - mutex_lock(&rq->i915->drm.struct_mutex); - intel_context_unpin(rq->hw_context); - mutex_unlock(&rq->i915->drm.struct_mutex); - i915_request_put(fetch_and_zero(&workload->req)); } @@ -1032,8 +1013,6 @@ static int workload_thread(void *priv) workload->ring_id, workload, workload->vgpu->id); - intel_runtime_pm_get(gvt->dev_priv); - gvt_dbg_sched("ring id %d will dispatch workload %p\n", workload->ring_id, workload); @@ -1063,7 +1042,6 @@ complete: intel_uncore_forcewake_put(&gvt->dev_priv->uncore, FORCEWAKE_ALL); - intel_runtime_pm_put_unchecked(gvt->dev_priv); if (ret && (vgpu_is_vm_unhealthy(ret))) enter_failsafe_mode(vgpu, GVT_FAILSAFE_GUEST_ERR); } @@ -1146,17 +1124,20 @@ err: } static void -i915_context_ppgtt_root_restore(struct intel_vgpu_submission *s) +i915_context_ppgtt_root_restore(struct intel_vgpu_submission *s, + struct i915_ppgtt *ppgtt) { - struct i915_hw_ppgtt *i915_ppgtt = s->shadow_ctx->ppgtt; int i; - if (i915_vm_is_4lvl(&i915_ppgtt->vm)) { - px_dma(&i915_ppgtt->pml4) = s->i915_context_pml4; + if (i915_vm_is_4lvl(&ppgtt->vm)) { + px_dma(ppgtt->pd) = s->i915_context_pml4; } else { - for (i = 0; i < GEN8_3LVL_PDPES; i++) - px_dma(i915_ppgtt->pdp.page_directory[i]) = - s->i915_context_pdps[i]; + for (i = 0; i < GEN8_3LVL_PDPES; i++) { + struct i915_page_directory * const pd = + i915_pd_entry(ppgtt->pd, i); + + px_dma(pd) = s->i915_context_pdps[i]; + } } } @@ -1170,10 +1151,15 @@ i915_context_ppgtt_root_restore(struct intel_vgpu_submission *s) void intel_vgpu_clean_submission(struct intel_vgpu *vgpu) { struct intel_vgpu_submission *s = &vgpu->submission; + struct intel_engine_cs *engine; + enum intel_engine_id id; intel_vgpu_select_submission_ops(vgpu, ALL_ENGINES, 0); - i915_context_ppgtt_root_restore(s); - i915_gem_context_put(s->shadow_ctx); + + i915_context_ppgtt_root_restore(s, i915_vm_to_ppgtt(s->shadow[0]->gem_context->vm)); + for_each_engine(engine, vgpu->gvt->dev_priv, id) + intel_context_unpin(s->shadow[id]); + kmem_cache_destroy(s->workloads); } @@ -1199,17 +1185,20 @@ void intel_vgpu_reset_submission(struct intel_vgpu *vgpu, } static void -i915_context_ppgtt_root_save(struct intel_vgpu_submission *s) +i915_context_ppgtt_root_save(struct intel_vgpu_submission *s, + struct i915_ppgtt *ppgtt) { - struct i915_hw_ppgtt *i915_ppgtt = s->shadow_ctx->ppgtt; int i; - if (i915_vm_is_4lvl(&i915_ppgtt->vm)) - s->i915_context_pml4 = px_dma(&i915_ppgtt->pml4); - else { - for (i = 0; i < GEN8_3LVL_PDPES; i++) - s->i915_context_pdps[i] = - px_dma(i915_ppgtt->pdp.page_directory[i]); + if (i915_vm_is_4lvl(&ppgtt->vm)) { + s->i915_context_pml4 = px_dma(ppgtt->pd); + } else { + for (i = 0; i < GEN8_3LVL_PDPES; i++) { + struct i915_page_directory * const pd = + i915_pd_entry(ppgtt->pd, i); + + s->i915_context_pdps[i] = px_dma(pd); + } } } @@ -1226,16 +1215,36 @@ i915_context_ppgtt_root_save(struct intel_vgpu_submission *s) int intel_vgpu_setup_submission(struct intel_vgpu *vgpu) { struct intel_vgpu_submission *s = &vgpu->submission; - enum intel_engine_id i; struct intel_engine_cs *engine; + struct i915_gem_context *ctx; + enum intel_engine_id i; int ret; - s->shadow_ctx = i915_gem_context_create_gvt( - &vgpu->gvt->dev_priv->drm); - if (IS_ERR(s->shadow_ctx)) - return PTR_ERR(s->shadow_ctx); + ctx = i915_gem_context_create_gvt(&vgpu->gvt->dev_priv->drm); + if (IS_ERR(ctx)) + return PTR_ERR(ctx); + + i915_context_ppgtt_root_save(s, i915_vm_to_ppgtt(ctx->vm)); + + for_each_engine(engine, vgpu->gvt->dev_priv, i) { + struct intel_context *ce; - i915_context_ppgtt_root_save(s); + INIT_LIST_HEAD(&s->workload_q_head[i]); + s->shadow[i] = ERR_PTR(-EINVAL); + + ce = i915_gem_context_get_engine(ctx, i); + if (IS_ERR(ce)) { + ret = PTR_ERR(ce); + goto out_shadow_ctx; + } + + ret = intel_context_pin(ce); + intel_context_put(ce); + if (ret) + goto out_shadow_ctx; + + s->shadow[i] = ce; + } bitmap_zero(s->shadow_ctx_desc_updated, I915_NUM_ENGINES); @@ -1251,16 +1260,21 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu) goto out_shadow_ctx; } - for_each_engine(engine, vgpu->gvt->dev_priv, i) - INIT_LIST_HEAD(&s->workload_q_head[i]); - atomic_set(&s->running_workload_num, 0); bitmap_zero(s->tlb_handle_pending, I915_NUM_ENGINES); + i915_gem_context_put(ctx); return 0; out_shadow_ctx: - i915_gem_context_put(s->shadow_ctx); + i915_context_ppgtt_root_restore(s, i915_vm_to_ppgtt(ctx->vm)); + for_each_engine(engine, vgpu->gvt->dev_priv, i) { + if (IS_ERR(s->shadow[i])) + break; + + intel_context_unpin(s->shadow[i]); + } + i915_gem_context_put(ctx); return ret; } @@ -1520,11 +1534,11 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, int ring_id, * as there is only one pre-allocated buf-obj for shadow. */ if (list_empty(workload_q_head(vgpu, ring_id))) { - intel_runtime_pm_get(dev_priv); + intel_runtime_pm_get(&dev_priv->runtime_pm); mutex_lock(&dev_priv->drm.struct_mutex); ret = intel_gvt_scan_and_shadow_workload(workload); mutex_unlock(&dev_priv->drm.struct_mutex); - intel_runtime_pm_put_unchecked(dev_priv); + intel_runtime_pm_put_unchecked(&dev_priv->runtime_pm); } if (ret) { |