Rework TTMs busy handling
Hi guys, same as the last time. Things I've changed: Implemented the requirements from Zack to correctly fill in the busy placements for VMWGFX. Renamed the placement flags to desired and fallback as suggested by Michel. Rebased on drm-tip instead of drm-misc-next and fixed XE as well. Please review and comment, Christian.
[PATCH 1/5] drm/vmwgfx: remove vmw_vram_gmr_placement
Seems to be unused. Signed-off-by: Christian König --- drivers/gpu/drm/vmwgfx/vmwgfx_drv.h| 1 - drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c | 28 -- 2 files changed, 29 deletions(-) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 3cd5090dedfc..12efecc17df6 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -942,7 +942,6 @@ vmw_is_cursor_bypass3_enabled(const struct vmw_private *dev_priv) extern const size_t vmw_tt_size; extern struct ttm_placement vmw_vram_placement; -extern struct ttm_placement vmw_vram_gmr_placement; extern struct ttm_placement vmw_sys_placement; extern struct ttm_device_funcs vmw_bo_driver; extern const struct vmw_sg_table * diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c index af8562c95cc3..a84fffcef8e1 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c @@ -43,13 +43,6 @@ static const struct ttm_place sys_placement_flags = { .flags = 0 }; -static const struct ttm_place gmr_placement_flags = { - .fpfn = 0, - .lpfn = 0, - .mem_type = VMW_PL_GMR, - .flags = 0 -}; - struct ttm_placement vmw_vram_placement = { .num_placement = 1, .placement = &vram_placement_flags, @@ -57,27 +50,6 @@ struct ttm_placement vmw_vram_placement = { .busy_placement = &vram_placement_flags }; -static const struct ttm_place vram_gmr_placement_flags[] = { - { - .fpfn = 0, - .lpfn = 0, - .mem_type = TTM_PL_VRAM, - .flags = 0 - }, { - .fpfn = 0, - .lpfn = 0, - .mem_type = VMW_PL_GMR, - .flags = 0 - } -}; - -struct ttm_placement vmw_vram_gmr_placement = { - .num_placement = 2, - .placement = vram_gmr_placement_flags, - .num_busy_placement = 1, - .busy_placement = &gmr_placement_flags -}; - struct ttm_placement vmw_sys_placement = { .num_placement = 1, .placement = &sys_placement_flags, -- 2.34.1
[PATCH 3/5] drm/ttm: replace busy placement with flags v6
From: Somalapuram Amaranath Instead of a list of separate busy placement add flags which indicate that a placement should only be used when there is room or if we need to evict. v2: add missing TTM_PL_FLAG_IDLE for i915 v3: fix auto build test ERROR on drm-tip/drm-tip v4: fix some typos pointed out by checkpatch v5: cleanup some rebase problems with VMWGFX v6: implement some missing VMWGFX functionality pointed out by Zack, rename the flags as suggested by Michel, rebase on drm-tip and adjust XE as well Signed-off-by: Christian König Signed-off-by: Somalapuram Amaranath --- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 6 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c| 11 +--- drivers/gpu/drm/drm_gem_vram_helper.c | 2 - drivers/gpu/drm/i915/gem/i915_gem_ttm.c| 37 +-- drivers/gpu/drm/loongson/lsdc_ttm.c| 2 - drivers/gpu/drm/nouveau/nouveau_bo.c | 59 +++-- drivers/gpu/drm/nouveau/nouveau_bo.h | 1 - drivers/gpu/drm/qxl/qxl_object.c | 2 - drivers/gpu/drm/qxl/qxl_ttm.c | 2 - drivers/gpu/drm/radeon/radeon_object.c | 2 - drivers/gpu/drm/radeon/radeon_ttm.c| 8 +-- drivers/gpu/drm/radeon/radeon_uvd.c| 1 - drivers/gpu/drm/ttm/ttm_bo.c | 21 --- drivers/gpu/drm/ttm/ttm_resource.c | 73 +- drivers/gpu/drm/vmwgfx/vmwgfx_bo.c | 33 +++--- drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c | 4 -- drivers/gpu/drm/xe/xe_bo.c | 33 +- include/drm/ttm/ttm_placement.h| 10 +-- include/drm/ttm/ttm_resource.h | 8 +-- 19 files changed, 118 insertions(+), 197 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 425cebcc5cbf..b671b0665492 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -220,9 +220,6 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain) placement->num_placement = c; placement->placement = places; - - placement->num_busy_placement = c; - placement->busy_placement = places; } /** @@ -1397,8 +1394,7 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo) AMDGPU_GEM_DOMAIN_GTT); /* Avoid costly evictions; only set GTT as a busy placement */ - abo->placement.num_busy_placement = 1; - abo->placement.busy_placement = &abo->placements[1]; + abo->placements[0].flags |= TTM_PL_FLAG_DESIRED; r = ttm_bo_validate(bo, &abo->placement, &ctx); if (unlikely(r == -EBUSY || r == -ERESTARTSYS)) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 75c9fd2c6c2a..8722beba494e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -102,23 +102,19 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo, /* Don't handle scatter gather BOs */ if (bo->type == ttm_bo_type_sg) { placement->num_placement = 0; - placement->num_busy_placement = 0; return; } /* Object isn't an AMDGPU object so ignore */ if (!amdgpu_bo_is_amdgpu_bo(bo)) { placement->placement = &placements; - placement->busy_placement = &placements; placement->num_placement = 1; - placement->num_busy_placement = 1; return; } abo = ttm_to_amdgpu_bo(bo); if (abo->flags & AMDGPU_GEM_CREATE_DISCARDABLE) { placement->num_placement = 0; - placement->num_busy_placement = 0; return; } @@ -128,13 +124,13 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo, case AMDGPU_PL_OA: case AMDGPU_PL_DOORBELL: placement->num_placement = 0; - placement->num_busy_placement = 0; return; case TTM_PL_VRAM: if (!adev->mman.buffer_funcs_enabled) { /* Move to system memory */ amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_CPU); + } else if (!amdgpu_gmc_vram_full_visible(&adev->gmc) && !(abo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) && amdgpu_bo_in_cpu_visible_vram(abo)) { @@ -149,8 +145,7 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo, AMDGPU_GEM_DOMAIN_CPU); abo->placements[0].fpfn = adev->gmc.visible_vram_size >> PAGE_SHIFT; abo->placements[0].lpfn = 0; - abo->placement.busy_placement = &abo->placements[1]; - abo->placement.num_busy_placement = 1; +
[PATCH 2/5] drm/ttm: return ENOSPC from ttm_bo_mem_space
Only convert it to ENOMEM in ttm_bo_validate. This allows ttm_bo_validate to distinct between an out of memory situation and just out of space in a placement domain. Signed-off-by: Christian König --- drivers/gpu/drm/ttm/ttm_bo.c | 5 - 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index edf10618fe2b..8c1eaa74fa21 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -830,7 +830,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo, goto error; } - ret = -ENOMEM; + ret = -ENOSPC; if (!type_found) { pr_err(TTM_PFX "No compatible memory type found\n"); ret = -EINVAL; @@ -916,6 +916,9 @@ int ttm_bo_validate(struct ttm_buffer_object *bo, return -EINVAL; ret = ttm_bo_move_buffer(bo, placement, ctx); + /* For backward compatibility with userspace */ + if (ret == -ENOSPC) + return -ENOMEM; if (ret) return ret; -- 2.34.1
[PATCH 4/5] drm/ttm: improve idle/busy handling v3
Previously we would never try to move a BO into the preferred placements when it ever landed in a busy placement since those were considered compatible. Rework the whole handling and finally unify the idle and busy handling. ttm_bo_validate() is now responsible to try idle placement first and then use the busy placement if that didn't worked. Drawback is that we now always try the idle placement first for each validation which might cause some additional CPU overhead on overcommit. v2: fix kerneldoc warning and coding style v3: take care of XE as well Signed-off-by: Christian König --- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 +- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c| 2 +- drivers/gpu/drm/ttm/ttm_bo.c | 131 - drivers/gpu/drm/ttm/ttm_resource.c | 16 ++- drivers/gpu/drm/xe/xe_bo.c | 4 +- include/drm/ttm/ttm_bo.h | 3 +- include/drm/ttm/ttm_resource.h | 3 +- 7 files changed, 68 insertions(+), 93 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index b671b0665492..06fb3fc47eaa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -404,7 +404,7 @@ int amdgpu_bo_create_kernel_at(struct amdgpu_device *adev, (*bo_ptr)->placements[i].lpfn = (offset + size) >> PAGE_SHIFT; } r = ttm_bo_mem_space(&(*bo_ptr)->tbo, &(*bo_ptr)->placement, -&(*bo_ptr)->tbo.resource, &ctx); +&(*bo_ptr)->tbo.resource, &ctx, false); if (r) goto error; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 8722beba494e..f23cdc7c5b08 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -966,7 +966,7 @@ int amdgpu_ttm_alloc_gart(struct ttm_buffer_object *bo) placements.mem_type = TTM_PL_TT; placements.flags = bo->resource->placement; - r = ttm_bo_mem_space(bo, &placement, &tmp, &ctx); + r = ttm_bo_mem_space(bo, &placement, &tmp, &ctx, true); if (unlikely(r)) return r; diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index a5e11a92e0b9..3783be24d832 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -414,7 +414,7 @@ static int ttm_bo_bounce_temp_buffer(struct ttm_buffer_object *bo, hop_placement.placement = hop; /* find space in the bounce domain */ - ret = ttm_bo_mem_space(bo, &hop_placement, &hop_mem, ctx); + ret = ttm_bo_mem_space(bo, &hop_placement, &hop_mem, ctx, true); if (ret) return ret; /* move to the bounce domain */ @@ -454,7 +454,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, return ttm_bo_pipeline_gutting(bo); } - ret = ttm_bo_mem_space(bo, &placement, &evict_mem, ctx); + ret = ttm_bo_mem_space(bo, &placement, &evict_mem, ctx, true); if (ret) { if (ret != -ERESTARTSYS) { pr_err("Failed to find memory space for buffer 0x%p eviction\n", @@ -724,37 +724,6 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo, return ret; } -/* - * Repeatedly evict memory from the LRU for @mem_type until we create enough - * space, or we've evicted everything and there isn't enough space. - */ -static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo, - const struct ttm_place *place, - struct ttm_resource **mem, - struct ttm_operation_ctx *ctx) -{ - struct ttm_device *bdev = bo->bdev; - struct ttm_resource_manager *man; - struct ww_acquire_ctx *ticket; - int ret; - - man = ttm_manager_type(bdev, place->mem_type); - ticket = dma_resv_locking_ctx(bo->base.resv); - do { - ret = ttm_resource_alloc(bo, place, mem); - if (likely(!ret)) - break; - if (unlikely(ret != -ENOSPC)) - return ret; - ret = ttm_mem_evict_first(bdev, man, place, ctx, - ticket); - if (unlikely(ret != 0)) - return ret; - } while (1); - - return ttm_bo_add_move_fence(bo, man, *mem, ctx->no_wait_gpu); -} - /** * ttm_bo_mem_space * @@ -763,6 +732,7 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo, * @placement: Proposed new placement for the buffer object. * @mem: A struct ttm_resource. * @ctx: if and how to sleep, lock buffers and alloc memory + * @force_space: If we should evict buffers to force space * * Allocate memory space for the buffer object pointed to by @bo, using * the placement flags in
[PATCH 5/5] drm/amdgpu: use GTT only as fallback for VRAM|GTT
Try to fill up VRAM as well by setting the busy flag on GTT allocations. This fixes the issue that when VRAM was evacuated for suspend it's never filled up again unless the application is restarted. Signed-off-by: Christian König --- drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 6 ++ 1 file changed, 6 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 06fb3fc47eaa..2752f2a67a44 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -173,6 +173,12 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain) abo->flags & AMDGPU_GEM_CREATE_PREEMPTIBLE ? AMDGPU_PL_PREEMPT : TTM_PL_TT; places[c].flags = 0; + /* +* When GTT is just an alternative to VRAM make sure that we +* only use it as fallback and still try to fill up VRAM first. +*/ + if (domain & abo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM) + places[c].flags |= TTM_PL_FLAG_FALLBACK; c++; } -- 2.34.1
[PATCH] drm/nouveau/disp/r535: fix error code in r535_dp_aux_xfer()
This code was shuffled around but the return wasn't updated. It should return "ret" instead of "ctrl". Fixes: 4ae3a20102b2 ("nouveau/gsp: don't free ctrl messages on errors") Signed-off-by: Dan Carpenter --- drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c index 6a0a4d3b8902..027867c2a8c5 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/r535.c @@ -1080,7 +1080,7 @@ r535_dp_aux_xfer(struct nvkm_outp *outp, u8 type, u32 addr, u8 *data, u8 *psize) ret = nvkm_gsp_rm_ctrl_push(&disp->rm.objcom, &ctrl, sizeof(*ctrl)); if (ret) { nvkm_gsp_rm_ctrl_done(&disp->rm.objcom, ctrl); - return PTR_ERR(ctrl); + return ret; } memcpy(data, ctrl->data, size); -- 2.43.0
[PATCH 1/6] drm/nouveau: convert to using is_hdmi and has_audio from display info
Prefer the parsed results for is_hdmi and has_audio in display info over calling drm_detect_hdmi_monitor() and drm_detect_monitor_audio(), respectively. Conveniently, this also removes the need to use edid_blob_ptr. Cc: Karol Herbst Cc: Lyude Paul Cc: Danilo Krummrich Cc: nouveau@lists.freedesktop.org Signed-off-by: Jani Nikula --- drivers/gpu/drm/nouveau/dispnv50/disp.c | 8 drivers/gpu/drm/nouveau/dispnv50/head.c | 8 +--- drivers/gpu/drm/nouveau/nouveau_connector.c | 2 +- 3 files changed, 6 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 8d37a694b772..908b1042669c 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -750,7 +750,7 @@ nv50_audio_enable(struct drm_encoder *encoder, struct nouveau_crtc *nv_crtc, struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); struct nvif_outp *outp = &nv_encoder->outp; - if (!nv50_audio_supported(encoder) || !drm_detect_monitor_audio(nv_connector->edid)) + if (!nv50_audio_supported(encoder) || !nv_connector->base.display_info.has_audio) return; mutex_lock(&drm->audio.lock); @@ -1764,7 +1764,7 @@ nv50_sor_atomic_enable(struct drm_encoder *encoder, struct drm_atomic_state *sta if ((disp->disp->object.oclass == GT214_DISP || disp->disp->object.oclass >= GF110_DISP) && nv_encoder->dcb->type != DCB_OUTPUT_LVDS && - drm_detect_monitor_audio(nv_connector->edid)) + nv_connector->base.display_info.has_audio) hda = true; if (!nvif_outp_acquired(outp)) @@ -1773,7 +1773,7 @@ nv50_sor_atomic_enable(struct drm_encoder *encoder, struct drm_atomic_state *sta switch (nv_encoder->dcb->type) { case DCB_OUTPUT_TMDS: if (disp->disp->object.oclass != NV50_DISP && - drm_detect_hdmi_monitor(nv_connector->edid)) + !nv_connector->base.display_info.is_hdmi) nv50_hdmi_enable(encoder, nv_crtc, nv_connector, state, mode, hda); if (nv_encoder->outp.or.link & 1) { @@ -1786,7 +1786,7 @@ nv50_sor_atomic_enable(struct drm_encoder *encoder, struct drm_atomic_state *sta */ if (mode->clock >= 165000 && nv_encoder->dcb->duallink_possible && - !drm_detect_hdmi_monitor(nv_connector->edid)) + !nv_connector->base.display_info.is_hdmi) proto = NV507D_SOR_SET_CONTROL_PROTOCOL_DUAL_TMDS; } else { proto = NV507D_SOR_SET_CONTROL_PROTOCOL_SINGLE_TMDS_B; diff --git a/drivers/gpu/drm/nouveau/dispnv50/head.c b/drivers/gpu/drm/nouveau/dispnv50/head.c index 83355dbc15ee..d7c74cc43ba5 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/head.c +++ b/drivers/gpu/drm/nouveau/dispnv50/head.c @@ -127,14 +127,8 @@ nv50_head_atomic_check_view(struct nv50_head_atom *armh, struct drm_display_mode *omode = &asyh->state.adjusted_mode; struct drm_display_mode *umode = &asyh->state.mode; int mode = asyc->scaler.mode; - struct edid *edid; int umode_vdisplay, omode_hdisplay, omode_vdisplay; - if (connector->edid_blob_ptr) - edid = (struct edid *)connector->edid_blob_ptr->data; - else - edid = NULL; - if (!asyc->scaler.full) { if (mode == DRM_MODE_SCALE_NONE) omode = umode; @@ -162,7 +156,7 @@ nv50_head_atomic_check_view(struct nv50_head_atom *armh, */ if ((asyc->scaler.underscan.mode == UNDERSCAN_ON || (asyc->scaler.underscan.mode == UNDERSCAN_AUTO && -drm_detect_hdmi_monitor(edid { +connector->display_info.is_hdmi))) { u32 bX = asyc->scaler.underscan.hborder; u32 bY = asyc->scaler.underscan.vborder; u32 r = (asyh->view.oH << 19) / asyh->view.oW; diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 856b3ef5edb8..938832a6af15 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -1034,7 +1034,7 @@ get_tmds_link_bandwidth(struct drm_connector *connector) unsigned duallink_scale = nouveau_duallink && nv_encoder->dcb->duallink_possible ? 2 : 1; - if (drm_detect_hdmi_monitor(nv_connector->edid)) { + if (nv_connector->base.display_info.is_hdmi) { info = &nv_connector->base.display_info; duallink_scale = 1; } -- 2.39.2