diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-07-01 12:53:43 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-07-01 12:53:43 -0700 |
commit | e058a84bfddc42ba356a2316f2cf1141974625c9 (patch) | |
tree | e6a02dd913e83f44ea9f5a779f9b9bd56d06a9e3 /drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | |
parent | c288d9cd710433e5991d58a0764c4d08a933b871 (diff) | |
parent | 8a02ea42bc1d4c448caf1bab0e05899dad503f74 (diff) |
Merge tag 'drm-next-2021-07-01' of git://anongit.freedesktop.org/drm/drm
Pull drm updates from Dave Airlie:
"Highlights:
- AMD enables two more GPUs, with resulting header files
- i915 has started to move to TTM for discrete GPU and enable DG1
discrete GPU support (not by default yet)
- new HyperV drm driver
- vmwgfx adds arm64 support
- TTM refactoring ongoing
- 16bpc display support for AMD hw
Otherwise it's just the usual insane amounts of work all over the
place in lots of drivers and the core, as mostly summarised below:
Core:
- mark AGP ioctls as legacy
- disable force probing for non-master clients
- HDR metadata property helpers
- HDMI infoframe signal colorimetry support
- remove drm_device.pdev pointer
- remove DRM_KMS_FB_HELPER config option
- remove drm_pci_alloc/free
- drm_err_*/drm_dbg_* helpers
- use drm driver names for fbdev
- leaked DMA handle fix
- 16bpc fixed point format fourcc
- add prefetching memcpy for WC
- Documentation fixes
aperture:
- add aperture ownership helpers
dp:
- aux fixes
- downstream 0 port handling
- use extended base receiver capability DPCD
- Rename DP_PSR_SELECTIVE_UPDATE to better mach eDP spec
- mst: use khz as link rate during init
- VCPI fixes for StarTech hub
ttm:
- provide tt_shrink file via debugfs
- warn about freeing pinned BOs
- fix swapping error handling
- move page alignment into BO
- cleanup ttm_agp_backend
- add ttm_sys_manager
- don't override vm_ops
- ttm_bo_mmap removed
- make ttm_resource base of all managers
- remove VM_MIXEDMAP usage
panel:
- sysfs_emit support
- simple: runtime PM support
- simple: power up panel when reading EDID + caching
bridge:
- MHDP8546: HDCP support + DT bindings
- MHDP8546: Register DP AUX channel with userspace
- TI SN65DSI83 + SN65DSI84: add driver
- Sil8620: Fix module dependencies
- dw-hdmi: make CEC driver loading optional
- Ti-sn65dsi86: refclk fixes, subdrivers, runtime pm
- It66121: Add driver + DT bindings
- Adv7511: Support I2S IEC958 encoding
- Anx7625: fix power-on delay
- Nwi-dsi: Modesetting fixes; Cleanups
- lt6911: add missing MODULE_DEVICE_TABLE
- cdns: fix PM reference leak
hyperv:
- add new DRM driver for HyperV graphics
efifb:
- non-PCI device handling fixes
i915:
- refactor IP/device versioning
- XeLPD Display IP preperation work
- ADL-P enablement patches
- DG1 uAPI behind BROKEN
- disable mmap ioctl for discerte GPUs
- start enabling HuC loading for Gen12+
- major GuC backend rework for new platforms
- initial TTM support for Discrete GPUs
- locking rework for TTM prep
- use correct max source link rate for eDP
- %p4cc format printing
- GLK display fixes
- VLV DSI panel power fixes
- PSR2 disabled for RKL and ADL-S
- ACPI _DSM invalid access fixed
- DMC FW path abstraction
- ADL-S PCI ID update
- uAPI headers converted to kerneldoc
- initial LMEM support for DG1
- x86/gpu: add Jasperlake to gen11 early quirks
amdgpu:
- Aldebaran updates + initial SR-IOV
- new GPU: Beige Goby and Yellow Carp support
- more LTTPR display work
- Vangogh updates
- SDMA 5.x GCR fixes
- PCIe ASPM support
- Renoir TMZ enablement
- initial multiple eDP panel support
- use fdinfo to track devices/process info
- pin/unpin TTM fixes
- free resource on fence usage query
- fix fence calculation
- fix hotunplug/suspend issues
- GC/MM register access macro cleanup for SR-IOV
- W=1 fixes
- ACPI ATCS/ATIF handling rework
- 16bpc fixed point format support
- Initial smartshift support
- RV/PCO power tuning fixes
- new INFO query for additional vbios info
amdkfd:
- SR-IOV aldebaran support
- HMM SVM support
radeon:
- SMU regression fixes
- Oland flickering fix
vmwgfx:
- enable console with fbdev emulation
- fix cpu updates of coherent multisample surfaces
- remove reservation semaphore
- add initial SVGA3 support
- support arm64
msm:
- devcoredump support for display errors
- dpu/dsi: yaml bindings conversion
- mdp5: alpha/blend_mode/zpos support
- a6xx: cached coherent buffer support
- gpu iova fault improvement
- a660 support
rockchip:
- RK3036 win1 scaling support
- RK3066/3188 missing register support
- RK3036/3066/3126/3188 alpha support
mediatek:
- MT8167 HDMI support
- MT8183 DPI dual edge support
tegra:
- fixed YUV support/scaling on Tegra186+
ast:
- use pcim_iomap
- fix DP501 EDID
bochs:
- screen blanking support
etnaviv:
- export more GPU ID values to userspace
- add HWDB entry for GPU on i.MX8MP
- rework linear window calcs
exynos:
- pm runtime changes
imx:
- Annotate dma_fence critical section
- fix PRG modifiers after drmm conversion
- Add 8 pixel alignment fix for 1366x768
- fix YUV advertising
- add color properties
ingenic:
- IPU planes fix
panfrost:
- Mediatek MT8183 support + DT bindings
- export AFBC_FEATURES register to userspace
simpledrm:
- %pr for printing resources
nouveau:
- pin/unpin TTM fixes
qxl:
- unpin shadow BO
virtio:
- create dumb BOs as guest blob
vkms:
- drmm_universal_plane_alloc
- add XRGB plane composition
- overlay support"
* tag 'drm-next-2021-07-01' of git://anongit.freedesktop.org/drm/drm: (1570 commits)
drm/i915: Reinstate the mmap ioctl for some platforms
drm/i915/dsc: abstract helpers to get bigjoiner primary/secondary crtc
Revert "drm/msm/mdp5: provide dynamic bandwidth management"
drm/msm/mdp5: provide dynamic bandwidth management
drm/msm/mdp5: add perf blocks for holding fudge factors
drm/msm/mdp5: switch to standard zpos property
drm/msm/mdp5: add support for alpha/blend_mode properties
drm/msm/mdp5: use drm_plane_state for pixel blend mode
drm/msm/mdp5: use drm_plane_state for storing alpha value
drm/msm/mdp5: use drm atomic helpers to handle base drm plane state
drm/msm/dsi: do not enable PHYs when called for the slave DSI interface
drm/msm: Add debugfs to trigger shrinker
drm/msm/dpu: Avoid ABBA deadlock between IRQ modules
drm/msm: devcoredump iommu fault support
iommu/arm-smmu-qcom: Add stall support
drm/msm: Improve the a6xx page fault handler
iommu/arm-smmu-qcom: Add an adreno-smmu-priv callback to get pagefault info
iommu/arm-smmu: Add support for driver IOMMU fault handlers
drm/msm: export hangcheck_period in debugfs
drm/msm/a6xx: add support for Adreno 660 GPU
...
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_object.c')
-rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 292 |
1 files changed, 149 insertions, 143 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index f9434bc2f9b2..795fa7445abe 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -52,55 +52,44 @@ * */ -/** - * amdgpu_bo_subtract_pin_size - Remove BO from pin_size accounting - * - * @bo: &amdgpu_bo buffer object - * - * This function is called when a BO stops being pinned, and updates the - * &amdgpu_device pin_size values accordingly. - */ -static void amdgpu_bo_subtract_pin_size(struct amdgpu_bo *bo) +static void amdgpu_bo_destroy(struct ttm_buffer_object *tbo) { - struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); + struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo); - if (bo->tbo.mem.mem_type == TTM_PL_VRAM) { - atomic64_sub(amdgpu_bo_size(bo), &adev->vram_pin_size); - atomic64_sub(amdgpu_vram_mgr_bo_visible_size(bo), - &adev->visible_pin_size); - } else if (bo->tbo.mem.mem_type == TTM_PL_TT) { - atomic64_sub(amdgpu_bo_size(bo), &adev->gart_pin_size); - } + amdgpu_bo_kunmap(bo); + + if (bo->tbo.base.import_attach) + drm_prime_gem_destroy(&bo->tbo.base, bo->tbo.sg); + drm_gem_object_release(&bo->tbo.base); + amdgpu_bo_unref(&bo->parent); + kvfree(bo); } -static void amdgpu_bo_destroy(struct ttm_buffer_object *tbo) +static void amdgpu_bo_user_destroy(struct ttm_buffer_object *tbo) { - struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev); struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo); struct amdgpu_bo_user *ubo; - if (bo->tbo.pin_count > 0) - amdgpu_bo_subtract_pin_size(bo); + ubo = to_amdgpu_bo_user(bo); + kfree(ubo->metadata); + amdgpu_bo_destroy(tbo); +} - amdgpu_bo_kunmap(bo); +static void amdgpu_bo_vm_destroy(struct ttm_buffer_object *tbo) +{ + struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev); + struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo); + struct amdgpu_bo_vm *vmbo; - if (bo->tbo.base.import_attach) - drm_prime_gem_destroy(&bo->tbo.base, bo->tbo.sg); - drm_gem_object_release(&bo->tbo.base); + vmbo = to_amdgpu_bo_vm(bo); /* in case amdgpu_device_recover_vram got NULL of bo->parent */ - if (!list_empty(&bo->shadow_list)) { + if (!list_empty(&vmbo->shadow_list)) { mutex_lock(&adev->shadow_list_lock); - list_del_init(&bo->shadow_list); + list_del_init(&vmbo->shadow_list); mutex_unlock(&adev->shadow_list_lock); } - amdgpu_bo_unref(&bo->parent); - - if (bo->tbo.type == ttm_bo_type_device) { - ubo = to_amdgpu_bo_user(bo); - kfree(ubo->metadata); - } - kvfree(bo); + amdgpu_bo_destroy(tbo); } /** @@ -115,8 +104,11 @@ static void amdgpu_bo_destroy(struct ttm_buffer_object *tbo) */ bool amdgpu_bo_is_amdgpu_bo(struct ttm_buffer_object *bo) { - if (bo->destroy == &amdgpu_bo_destroy) + if (bo->destroy == &amdgpu_bo_destroy || + bo->destroy == &amdgpu_bo_user_destroy || + bo->destroy == &amdgpu_bo_vm_destroy) return true; + return false; } @@ -157,7 +149,9 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain) if (domain & AMDGPU_GEM_DOMAIN_GTT) { places[c].fpfn = 0; places[c].lpfn = 0; - places[c].mem_type = TTM_PL_TT; + places[c].mem_type = + abo->flags & AMDGPU_GEM_CREATE_PREEMPTIBLE ? + AMDGPU_PL_PREEMPT : TTM_PL_TT; places[c].flags = 0; c++; } @@ -386,14 +380,14 @@ int amdgpu_bo_create_kernel_at(struct amdgpu_device *adev, if (cpu_addr) amdgpu_bo_kunmap(*bo_ptr); - ttm_resource_free(&(*bo_ptr)->tbo, &(*bo_ptr)->tbo.mem); + ttm_resource_free(&(*bo_ptr)->tbo, &(*bo_ptr)->tbo.resource); for (i = 0; i < (*bo_ptr)->placement.num_placement; ++i) { (*bo_ptr)->placements[i].fpfn = offset >> PAGE_SHIFT; (*bo_ptr)->placements[i].lpfn = (offset + size) >> PAGE_SHIFT; } r = ttm_bo_mem_space(&(*bo_ptr)->tbo, &(*bo_ptr)->placement, - &(*bo_ptr)->tbo.mem, &ctx); + &(*bo_ptr)->tbo.resource, &ctx); if (r) goto error; @@ -515,7 +509,18 @@ bool amdgpu_bo_support_uswc(u64 bo_flags) #endif } -static int amdgpu_bo_do_create(struct amdgpu_device *adev, +/** + * amdgpu_bo_create - create an &amdgpu_bo buffer object + * @adev: amdgpu device object + * @bp: parameters to be used for the buffer object + * @bo_ptr: pointer to the buffer object pointer + * + * Creates an &amdgpu_bo buffer object. + * + * Returns: + * 0 for success or a negative error code on failure. + */ +int amdgpu_bo_create(struct amdgpu_device *adev, struct amdgpu_bo_param *bp, struct amdgpu_bo **bo_ptr) { @@ -556,7 +561,6 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev, if (bo == NULL) return -ENOMEM; drm_gem_private_object_init(adev_to_drm(adev), &bo->tbo.base, size); - INIT_LIST_HEAD(&bo->shadow_list); bo->vm_bo = NULL; bo->preferred_domains = bp->preferred_domain ? bp->preferred_domain : bp->domain; @@ -579,22 +583,25 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev, if (bp->type == ttm_bo_type_kernel) bo->tbo.priority = 1; + if (!bp->destroy) + bp->destroy = &amdgpu_bo_destroy; + r = ttm_bo_init_reserved(&adev->mman.bdev, &bo->tbo, size, bp->type, &bo->placement, page_align, &ctx, NULL, - bp->resv, &amdgpu_bo_destroy); + bp->resv, bp->destroy); if (unlikely(r != 0)) return r; if (!amdgpu_gmc_vram_full_visible(&adev->gmc) && - bo->tbo.mem.mem_type == TTM_PL_VRAM && - bo->tbo.mem.start < adev->gmc.visible_vram_size >> PAGE_SHIFT) + bo->tbo.resource->mem_type == TTM_PL_VRAM && + bo->tbo.resource->start < adev->gmc.visible_vram_size >> PAGE_SHIFT) amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved, ctx.bytes_moved); else amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved, 0); if (bp->flags & AMDGPU_GEM_CREATE_VRAM_CLEARED && - bo->tbo.mem.mem_type == TTM_PL_VRAM) { + bo->tbo.resource->mem_type == TTM_PL_VRAM) { struct dma_fence *fence; r = amdgpu_fill_buffer(bo, 0, bo->tbo.base.resv, &fence); @@ -625,108 +632,68 @@ fail_unreserve: return r; } -static int amdgpu_bo_create_shadow(struct amdgpu_device *adev, - unsigned long size, - struct amdgpu_bo *bo) -{ - struct amdgpu_bo_param bp; - int r; - - if (bo->shadow) - return 0; - - memset(&bp, 0, sizeof(bp)); - bp.size = size; - bp.domain = AMDGPU_GEM_DOMAIN_GTT; - bp.flags = AMDGPU_GEM_CREATE_CPU_GTT_USWC | - AMDGPU_GEM_CREATE_SHADOW; - bp.type = ttm_bo_type_kernel; - bp.resv = bo->tbo.base.resv; - bp.bo_ptr_size = sizeof(struct amdgpu_bo); - - r = amdgpu_bo_do_create(adev, &bp, &bo->shadow); - if (!r) { - bo->shadow->parent = amdgpu_bo_ref(bo); - mutex_lock(&adev->shadow_list_lock); - list_add_tail(&bo->shadow->shadow_list, &adev->shadow_list); - mutex_unlock(&adev->shadow_list_lock); - } - - return r; -} - /** - * amdgpu_bo_create - create an &amdgpu_bo buffer object + * amdgpu_bo_create_user - create an &amdgpu_bo_user buffer object * @adev: amdgpu device object * @bp: parameters to be used for the buffer object - * @bo_ptr: pointer to the buffer object pointer + * @ubo_ptr: pointer to the buffer object pointer * - * Creates an &amdgpu_bo buffer object; and if requested, also creates a - * shadow object. - * Shadow object is used to backup the original buffer object, and is always - * in GTT. + * Create a BO to be used by user application; * * Returns: * 0 for success or a negative error code on failure. */ -int amdgpu_bo_create(struct amdgpu_device *adev, - struct amdgpu_bo_param *bp, - struct amdgpu_bo **bo_ptr) + +int amdgpu_bo_create_user(struct amdgpu_device *adev, + struct amdgpu_bo_param *bp, + struct amdgpu_bo_user **ubo_ptr) { - u64 flags = bp->flags; + struct amdgpu_bo *bo_ptr; int r; - bp->flags = bp->flags & ~AMDGPU_GEM_CREATE_SHADOW; - - r = amdgpu_bo_do_create(adev, bp, bo_ptr); + bp->bo_ptr_size = sizeof(struct amdgpu_bo_user); + bp->destroy = &amdgpu_bo_user_destroy; + r = amdgpu_bo_create(adev, bp, &bo_ptr); if (r) return r; - if ((flags & AMDGPU_GEM_CREATE_SHADOW) && !(adev->flags & AMD_IS_APU)) { - if (!bp->resv) - WARN_ON(dma_resv_lock((*bo_ptr)->tbo.base.resv, - NULL)); - - r = amdgpu_bo_create_shadow(adev, bp->size, *bo_ptr); - - if (!bp->resv) - dma_resv_unlock((*bo_ptr)->tbo.base.resv); - - if (r) - amdgpu_bo_unref(bo_ptr); - } - + *ubo_ptr = to_amdgpu_bo_user(bo_ptr); return r; } /** - * amdgpu_bo_create_user - create an &amdgpu_bo_user buffer object + * amdgpu_bo_create_vm - create an &amdgpu_bo_vm buffer object * @adev: amdgpu device object * @bp: parameters to be used for the buffer object - * @ubo_ptr: pointer to the buffer object pointer + * @vmbo_ptr: pointer to the buffer object pointer * - * Create a BO to be used by user application; + * Create a BO to be for GPUVM. * * Returns: * 0 for success or a negative error code on failure. */ -int amdgpu_bo_create_user(struct amdgpu_device *adev, - struct amdgpu_bo_param *bp, - struct amdgpu_bo_user **ubo_ptr) +int amdgpu_bo_create_vm(struct amdgpu_device *adev, + struct amdgpu_bo_param *bp, + struct amdgpu_bo_vm **vmbo_ptr) { struct amdgpu_bo *bo_ptr; int r; - bp->flags = bp->flags & ~AMDGPU_GEM_CREATE_SHADOW; - bp->bo_ptr_size = sizeof(struct amdgpu_bo_user); - r = amdgpu_bo_do_create(adev, bp, &bo_ptr); + /* bo_ptr_size will be determined by the caller and it depends on + * num of amdgpu_vm_pt entries. + */ + BUG_ON(bp->bo_ptr_size < sizeof(struct amdgpu_bo_vm)); + bp->destroy = &amdgpu_bo_vm_destroy; + r = amdgpu_bo_create(adev, bp, &bo_ptr); if (r) return r; - *ubo_ptr = to_amdgpu_bo_user(bo_ptr); + *vmbo_ptr = to_amdgpu_bo_vm(bo_ptr); + INIT_LIST_HEAD(&(*vmbo_ptr)->shadow_list); return r; } + /** * amdgpu_bo_validate - validate an &amdgpu_bo buffer object * @bo: pointer to the buffer object @@ -762,6 +729,22 @@ retry: } /** + * amdgpu_bo_add_to_shadow_list - add a BO to the shadow list + * + * @bo: BO that will be inserted into the shadow list + * + * Insert a BO to the shadow list. + */ +void amdgpu_bo_add_to_shadow_list(struct amdgpu_bo_vm *vmbo) +{ + struct amdgpu_device *adev = amdgpu_ttm_adev(vmbo->bo.tbo.bdev); + + mutex_lock(&adev->shadow_list_lock); + list_add_tail(&vmbo->shadow_list, &adev->shadow_list); + mutex_unlock(&adev->shadow_list_lock); +} + +/** * amdgpu_bo_restore_shadow - restore an &amdgpu_bo shadow * * @shadow: &amdgpu_bo shadow to be restored @@ -815,12 +798,12 @@ int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr) return 0; } - r = dma_resv_wait_timeout_rcu(bo->tbo.base.resv, false, false, - MAX_SCHEDULE_TIMEOUT); + r = dma_resv_wait_timeout(bo->tbo.base.resv, false, false, + MAX_SCHEDULE_TIMEOUT); if (r < 0) return r; - r = ttm_bo_kmap(&bo->tbo, 0, bo->tbo.mem.num_pages, &bo->kmap); + r = ttm_bo_kmap(&bo->tbo, 0, bo->tbo.resource->num_pages, &bo->kmap); if (r) return r; @@ -943,8 +926,8 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, domain = amdgpu_bo_get_preferred_pin_domain(adev, domain); if (bo->tbo.pin_count) { - uint32_t mem_type = bo->tbo.mem.mem_type; - uint32_t mem_flags = bo->tbo.mem.placement; + uint32_t mem_type = bo->tbo.resource->mem_type; + uint32_t mem_flags = bo->tbo.resource->placement; if (!(domain & amdgpu_mem_type_to_domain(mem_type))) return -EINVAL; @@ -994,7 +977,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain, ttm_bo_pin(&bo->tbo); - domain = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type); + domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type); if (domain == AMDGPU_GEM_DOMAIN_VRAM) { atomic64_add(amdgpu_bo_size(bo), &adev->vram_pin_size); atomic64_add(amdgpu_vram_mgr_bo_visible_size(bo), @@ -1037,14 +1020,22 @@ int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain) */ void amdgpu_bo_unpin(struct amdgpu_bo *bo) { + struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); + ttm_bo_unpin(&bo->tbo); if (bo->tbo.pin_count) return; - amdgpu_bo_subtract_pin_size(bo); - if (bo->tbo.base.import_attach) dma_buf_unpin(bo->tbo.base.import_attach); + + if (bo->tbo.resource->mem_type == TTM_PL_VRAM) { + atomic64_sub(amdgpu_bo_size(bo), &adev->vram_pin_size); + atomic64_sub(amdgpu_vram_mgr_bo_visible_size(bo), + &adev->visible_pin_size); + } else if (bo->tbo.resource->mem_type == TTM_PL_TT) { + atomic64_sub(amdgpu_bo_size(bo), &adev->gart_pin_size); + } } /** @@ -1123,10 +1114,6 @@ int amdgpu_bo_init(struct amdgpu_device *adev) void amdgpu_bo_fini(struct amdgpu_device *adev) { amdgpu_ttm_fini(adev); - if (!adev->gmc.xgmi.connected_to_cpu) { - arch_phys_wc_del(adev->gmc.vram_mtrr); - arch_io_free_memtype_wc(adev->gmc.aper_base, adev->gmc.aper_size); - } } /** @@ -1246,6 +1233,9 @@ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer, BUG_ON(bo->tbo.type == ttm_bo_type_kernel); ubo = to_amdgpu_bo_user(bo); + if (metadata_size) + *metadata_size = ubo->metadata_size; + if (buffer) { if (buffer_size < ubo->metadata_size) return -EINVAL; @@ -1254,8 +1244,6 @@ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer, memcpy(buffer, ubo->metadata, ubo->metadata_size); } - if (metadata_size) - *metadata_size = ubo->metadata_size; if (flags) *flags = ubo->metadata_flags; @@ -1278,7 +1266,7 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); struct amdgpu_bo *abo; - struct ttm_resource *old_mem = &bo->mem; + struct ttm_resource *old_mem = bo->resource; if (!amdgpu_bo_is_amdgpu_bo(bo)) return; @@ -1289,7 +1277,7 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, amdgpu_bo_kunmap(abo); if (abo->tbo.base.dma_buf && !abo->tbo.base.import_attach && - bo->mem.mem_type != TTM_PL_SYSTEM) + bo->resource->mem_type != TTM_PL_SYSTEM) dma_buf_move_notify(abo->tbo.base.dma_buf); /* remember the eviction */ @@ -1304,6 +1292,26 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, trace_amdgpu_bo_move(abo, new_mem->mem_type, old_mem->mem_type); } +void amdgpu_bo_get_memory(struct amdgpu_bo *bo, uint64_t *vram_mem, + uint64_t *gtt_mem, uint64_t *cpu_mem) +{ + unsigned int domain; + + domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type); + switch (domain) { + case AMDGPU_GEM_DOMAIN_VRAM: + *vram_mem += amdgpu_bo_size(bo); + break; + case AMDGPU_GEM_DOMAIN_GTT: + *gtt_mem += amdgpu_bo_size(bo); + break; + case AMDGPU_GEM_DOMAIN_CPU: + default: + *cpu_mem += amdgpu_bo_size(bo); + break; + } +} + /** * amdgpu_bo_release_notify - notification about a BO being released * @bo: pointer to a buffer object @@ -1331,7 +1339,7 @@ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) if (bo->base.resv == &bo->base._resv) amdgpu_amdkfd_remove_fence_on_pt_pd_bos(abo); - if (bo->mem.mem_type != TTM_PL_VRAM || !bo->mem.mm_node || + if (bo->resource->mem_type != TTM_PL_VRAM || !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE)) return; @@ -1362,18 +1370,17 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo) struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); struct ttm_operation_ctx ctx = { false, false }; struct amdgpu_bo *abo = ttm_to_amdgpu_bo(bo); - unsigned long offset, size; + unsigned long offset; int r; /* Remember that this BO was accessed by the CPU */ abo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; - if (bo->mem.mem_type != TTM_PL_VRAM) + if (bo->resource->mem_type != TTM_PL_VRAM) return 0; - size = bo->mem.num_pages << PAGE_SHIFT; - offset = bo->mem.start << PAGE_SHIFT; - if ((offset + size) <= adev->gmc.visible_vram_size) + offset = bo->resource->start << PAGE_SHIFT; + if ((offset + bo->base.size) <= adev->gmc.visible_vram_size) return 0; /* Can't move a pinned BO to visible VRAM */ @@ -1395,10 +1402,10 @@ vm_fault_t amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo) else if (unlikely(r)) return VM_FAULT_SIGBUS; - offset = bo->mem.start << PAGE_SHIFT; + offset = bo->resource->start << PAGE_SHIFT; /* this should never happen */ - if (bo->mem.mem_type == TTM_PL_VRAM && - (offset + size) > adev->gmc.visible_vram_size) + if (bo->resource->mem_type == TTM_PL_VRAM && + (offset + bo->base.size) > adev->gmc.visible_vram_size) return VM_FAULT_SIGBUS; ttm_bo_move_to_lru_tail_unlocked(bo); @@ -1482,11 +1489,11 @@ int amdgpu_bo_sync_wait(struct amdgpu_bo *bo, void *owner, bool intr) */ u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo) { - WARN_ON_ONCE(bo->tbo.mem.mem_type == TTM_PL_SYSTEM); + WARN_ON_ONCE(bo->tbo.resource->mem_type == TTM_PL_SYSTEM); WARN_ON_ONCE(!dma_resv_is_locked(bo->tbo.base.resv) && !bo->tbo.pin_count && bo->tbo.type != ttm_bo_type_kernel); - WARN_ON_ONCE(bo->tbo.mem.start == AMDGPU_BO_INVALID_OFFSET); - WARN_ON_ONCE(bo->tbo.mem.mem_type == TTM_PL_VRAM && + WARN_ON_ONCE(bo->tbo.resource->start == AMDGPU_BO_INVALID_OFFSET); + WARN_ON_ONCE(bo->tbo.resource->mem_type == TTM_PL_VRAM && !(bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)); return amdgpu_bo_gpu_offset_no_check(bo); @@ -1504,8 +1511,8 @@ u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo) struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); uint64_t offset; - offset = (bo->tbo.mem.start << PAGE_SHIFT) + - amdgpu_ttm_domain_start(adev, bo->tbo.mem.mem_type); + offset = (bo->tbo.resource->start << PAGE_SHIFT) + + amdgpu_ttm_domain_start(adev, bo->tbo.resource->mem_type); return amdgpu_gmc_sign_extend(offset); } @@ -1558,7 +1565,7 @@ u64 amdgpu_bo_print_info(int id, struct amdgpu_bo *bo, struct seq_file *m) unsigned int pin_count; u64 size; - domain = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type); + domain = amdgpu_mem_type_to_domain(bo->tbo.resource->mem_type); switch (domain) { case AMDGPU_GEM_DOMAIN_VRAM: placement = "VRAM"; @@ -1592,7 +1599,6 @@ u64 amdgpu_bo_print_info(int id, struct amdgpu_bo *bo, struct seq_file *m) amdgpu_bo_print_flag(m, bo, NO_CPU_ACCESS); amdgpu_bo_print_flag(m, bo, CPU_GTT_USWC); amdgpu_bo_print_flag(m, bo, VRAM_CLEARED); - amdgpu_bo_print_flag(m, bo, SHADOW); amdgpu_bo_print_flag(m, bo, VRAM_CONTIGUOUS); amdgpu_bo_print_flag(m, bo, VM_ALWAYS_VALID); amdgpu_bo_print_flag(m, bo, EXPLICIT_SYNC); |