summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-07-01 22:53:43 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2021-07-01 22:53:43 +0300
commite058a84bfddc42ba356a2316f2cf1141974625c9 (patch)
treee6a02dd913e83f44ea9f5a779f9b9bd56d06a9e3 /drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
parentc288d9cd710433e5991d58a0764c4d08a933b871 (diff)
parent8a02ea42bc1d4c448caf1bab0e05899dad503f74 (diff)
downloadlinux-e058a84bfddc42ba356a2316f2cf1141974625c9.tar.xz
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_amdkfd.h')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h55
1 files changed, 39 insertions, 16 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 5ffb07b02810..db16b3e83694 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -36,13 +36,26 @@
extern uint64_t amdgpu_amdkfd_total_mem_size;
+enum TLB_FLUSH_TYPE {
+ TLB_FLUSH_LEGACY = 0,
+ TLB_FLUSH_LIGHTWEIGHT,
+ TLB_FLUSH_HEAVYWEIGHT
+};
+
struct amdgpu_device;
-struct kfd_bo_va_list {
- struct list_head bo_list;
- struct amdgpu_bo_va *bo_va;
- void *kgd_dev;
+enum kfd_mem_attachment_type {
+ KFD_MEM_ATT_SHARED, /* Share kgd_mem->bo or another attachment's */
+ KFD_MEM_ATT_USERPTR, /* SG bo to DMA map pages from a userptr bo */
+ KFD_MEM_ATT_DMABUF, /* DMAbuf to DMA map TTM BOs */
+};
+
+struct kfd_mem_attachment {
+ struct list_head list;
+ enum kfd_mem_attachment_type type;
bool is_mapped;
+ struct amdgpu_bo_va *bo_va;
+ struct amdgpu_device *adev;
uint64_t va;
uint64_t pte_flags;
};
@@ -50,7 +63,8 @@ struct kfd_bo_va_list {
struct kgd_mem {
struct mutex lock;
struct amdgpu_bo *bo;
- struct list_head bo_va_list;
+ struct dma_buf *dmabuf;
+ struct list_head attachments;
/* protected by amdkfd_process_info.lock */
struct ttm_validate_buffer validate_list;
struct ttm_validate_buffer resv_list;
@@ -75,6 +89,7 @@ struct amdgpu_amdkfd_fence {
struct mm_struct *mm;
spinlock_t lock;
char timeline_name[TASK_COMM_LEN];
+ struct svm_range_bo *svm_bo;
};
struct amdgpu_kfd_dev {
@@ -127,14 +142,15 @@ void amdgpu_amdkfd_interrupt(struct amdgpu_device *adev,
const void *ih_ring_entry);
void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev);
void amdgpu_amdkfd_device_init(struct amdgpu_device *adev);
-void amdgpu_amdkfd_device_fini(struct amdgpu_device *adev);
+void amdgpu_amdkfd_device_fini_sw(struct amdgpu_device *adev);
int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine,
uint32_t vmid, uint64_t gpu_addr,
uint32_t *ib_cmd, uint32_t ib_len);
void amdgpu_amdkfd_set_compute_idle(struct kgd_dev *kgd, bool idle);
bool amdgpu_amdkfd_have_atomics_support(struct kgd_dev *kgd);
int amdgpu_amdkfd_flush_gpu_tlb_vmid(struct kgd_dev *kgd, uint16_t vmid);
-int amdgpu_amdkfd_flush_gpu_tlb_pasid(struct kgd_dev *kgd, uint16_t pasid);
+int amdgpu_amdkfd_flush_gpu_tlb_pasid(struct kgd_dev *kgd, uint16_t pasid,
+ enum TLB_FLUSH_TYPE flush_type);
bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid);
@@ -148,7 +164,8 @@ int amdgpu_queue_mask_bit_to_set_resource_bit(struct amdgpu_device *adev,
int queue_bit);
struct amdgpu_amdkfd_fence *amdgpu_amdkfd_fence_create(u64 context,
- struct mm_struct *mm);
+ struct mm_struct *mm,
+ struct svm_range_bo *svm_bo);
#if IS_ENABLED(CONFIG_HSA_AMD)
bool amdkfd_fence_check_mm(struct dma_fence *f, struct mm_struct *mm);
struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f);
@@ -234,22 +251,27 @@ uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *s
})
/* GPUVM API */
+#define drm_priv_to_vm(drm_priv) \
+ (&((struct amdgpu_fpriv *) \
+ ((struct drm_file *)(drm_priv))->driver_priv)->vm)
+
int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd,
struct file *filp, u32 pasid,
- void **vm, void **process_info,
+ void **process_info,
struct dma_fence **ef);
-void amdgpu_amdkfd_gpuvm_release_process_vm(struct kgd_dev *kgd, void *vm);
-uint64_t amdgpu_amdkfd_gpuvm_get_process_page_dir(void *vm);
+void amdgpu_amdkfd_gpuvm_release_process_vm(struct kgd_dev *kgd, void *drm_priv);
+uint64_t amdgpu_amdkfd_gpuvm_get_process_page_dir(void *drm_priv);
int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
struct kgd_dev *kgd, uint64_t va, uint64_t size,
- void *vm, struct kgd_mem **mem,
+ void *drm_priv, struct kgd_mem **mem,
uint64_t *offset, uint32_t flags);
int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
- struct kgd_dev *kgd, struct kgd_mem *mem, uint64_t *size);
+ struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv,
+ uint64_t *size);
int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
- struct kgd_dev *kgd, struct kgd_mem *mem, void *vm);
+ struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv, bool *table_freed);
int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
- struct kgd_dev *kgd, struct kgd_mem *mem, void *vm);
+ struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv);
int amdgpu_amdkfd_gpuvm_sync_memory(
struct kgd_dev *kgd, struct kgd_mem *mem, bool intr);
int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_dev *kgd,
@@ -260,7 +282,7 @@ int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd,
struct kfd_vm_fault_info *info);
int amdgpu_amdkfd_gpuvm_import_dmabuf(struct kgd_dev *kgd,
struct dma_buf *dmabuf,
- uint64_t va, void *vm,
+ uint64_t va, void *drm_priv,
struct kgd_mem **mem, uint64_t *size,
uint64_t *mmap_offset);
int amdgpu_amdkfd_get_tile_config(struct kgd_dev *kgd,
@@ -270,6 +292,7 @@ void amdgpu_amdkfd_gpuvm_init_mem_limits(void);
void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
struct amdgpu_vm *vm);
void amdgpu_amdkfd_unreserve_memory_limit(struct amdgpu_bo *bo);
+void amdgpu_amdkfd_reserve_system_mem(uint64_t size);
#else
static inline
void amdgpu_amdkfd_gpuvm_init_mem_limits(void)