diff options
| author | Dave Airlie <airlied@redhat.com> | 2023-06-15 14:11:22 +1000 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2023-06-15 14:11:22 +1000 |
| commit | 901bdf5ea1a836400ee69aa32b04e9c209271ec7 (patch) | |
| tree | ccb1851c8a71e776dbccf1ccae132dc9b5f093c6 /drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | |
| parent | ba57b9b11f78530146f02b776854b2b6b6d344a4 (diff) | |
| parent | 3b718dcaf163d17fe907ea098c8449e0cd6bc271 (diff) | |
| download | lwn-901bdf5ea1a836400ee69aa32b04e9c209271ec7.tar.gz lwn-901bdf5ea1a836400ee69aa32b04e9c209271ec7.zip | |
Merge tag 'amd-drm-next-6.5-2023-06-09' of https://gitlab.freedesktop.org/agd5f/linux into drm-next
amd-drm-next-6.5-2023-06-02:
amdgpu:
- SR-IOV fixes
- Warning fixes
- Misc code cleanups and spelling fixes
- DCN 3.2 updates
- Improved DC FAMS support for better power management
- Improved DC SubVP support for better power management
- DCN 3.1.x fixes
- Max IB size query
- DC GPU reset fixes
- RAS updates
- DCN 3.0.x fixes
- S/G display fixes
- CP shadow buffer support
- Implement connector force callback
- Z8 power improvements
- PSP 13.0.10 vbflash support
- Mode2 reset fixes
- Store MQDs in VRAM to improve queue switch latency
- VCN 3.x fixes
- JPEG 3.x fixes
- Enable DC_FP on LoongArch
- GFXOFF fixes
- GC 9.4.3 partition support
- SDMA 4.4.2 partition support
- VCN/JPEG 4.0.3 partition support
- VCN 4.0.3 updates
- NBIO 7.9 updates
- GC 9.4.3 updates
- Take NUMA into account when allocating memory
- Handle NUMA for partitions
- SMU 13.0.6 updates
- GC 9.4.3 RAS updates
- Stop including unused swiotlb.h
- SMU 13.0.7 fixes
- Fix clock output ordering on some APUs
- Clean up DC FPGA code
- GFX9 preemption fixes
- Misc irq fixes
- S0ix fixes
- Add new DRM_AMDGPU_WERROR config parameter to help with CI
- PCIe fix for RDNA2
- kdoc fixes
- Documentation updates
amdkfd:
- Query TTM mem limit rather than hardcoding it
- GC 9.4.3 partition support
- Handle NUMA for partitions
radeon:
- Fix possible double free
- Stop including unused swiotlb.h
- Fix possible division by zero
ttm:
- Add query for TTM mem limit
- Add NUMA awareness to pools
- Export ttm_pool_fini()
UAPI:
- Add new ctx query flag to better handle GPU resets
Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22290
- Add new interface to query and set shadow buffer for RDNA3
Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21986
- Add new INFO query for max IB size
Proposed userspace: https://gitlab.freedesktop.org/bnieuwenhuizen/mesa/-/commits/ib-rejection-v3
amd-drm-next-6.5-2023-06-09:
amdgpu:
- S0ix fixes
- Initial SMU13 Overdrive support
- kdoc fixes
- Misc clode cleanups
- Flexible array fixes
- Display OTG fixes
- SMU 13.0.6 updates
- Revert some broken clock counter updates
- Misc display fixes
- GFX9 preemption fixes
- Add support for newer EEPROM bad page table format
- Add missing radeon secondary id
- Add support for new colorspace KMS API
- CSA fix
- Stable pstate fixes for APUs
- make vbl interface admin only
- Handle PCI accelerator class
amdkfd:
- Add debugger support for gdb
radeon:
- Fix possible UAF
drm:
- Add Colorspace functionality
UAPI:
- Add debugger interface for enabling gdb
Proposed userspace: https://github.com/ROCm-Developer-Tools/ROCdbgapi/tree/wip-dbgapi
- Add KMS colorspace API
Discussion: https://lists.freedesktop.org/archives/dri-devel/2023-June/408128.html
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230609174817.7764-1-alexander.deucher@amd.com
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 111 |
1 files changed, 109 insertions, 2 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index dc474b809604..da26c555af24 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -50,6 +50,26 @@ */ /** + * amdgpu_ring_max_ibs - Return max IBs that fit in a single submission. + * + * @type: ring type for which to return the limit. + */ +unsigned int amdgpu_ring_max_ibs(enum amdgpu_ring_type type) +{ + switch (type) { + case AMDGPU_RING_TYPE_GFX: + /* Need to keep at least 192 on GFX7+ for old radv. */ + return 192; + case AMDGPU_RING_TYPE_COMPUTE: + return 125; + case AMDGPU_RING_TYPE_VCN_JPEG: + return 16; + default: + return 49; + } +} + +/** * amdgpu_ring_alloc - allocate space on the ring buffer * * @ring: amdgpu_ring structure holding ring information @@ -58,7 +78,7 @@ * Allocate @ndw dwords in the ring buffer (all asics). * Returns 0 on success, error on failure. */ -int amdgpu_ring_alloc(struct amdgpu_ring *ring, unsigned ndw) +int amdgpu_ring_alloc(struct amdgpu_ring *ring, unsigned int ndw) { /* Align requested size with padding so unlock_commit can * pad safely */ @@ -182,6 +202,7 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, int sched_hw_submission = amdgpu_sched_hw_submission; u32 *num_sched; u32 hw_ip; + unsigned int max_ibs_dw; /* Set the hw submission limit higher for KIQ because * it's used for a number of gfx/compute tasks by both @@ -290,6 +311,13 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, return r; } + max_ibs_dw = ring->funcs->emit_frame_size + + amdgpu_ring_max_ibs(ring->funcs->type) * ring->funcs->emit_ib_size; + max_ibs_dw = (max_ibs_dw + ring->funcs->align_mask) & ~ring->funcs->align_mask; + + if (WARN_ON(max_ibs_dw > max_dw)) + max_dw = max_ibs_dw; + ring->ring_size = roundup_pow_of_two(max_dw * 4 * sched_hw_submission); ring->buf_mask = (ring->ring_size / 4) - 1; @@ -361,6 +389,8 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring) amdgpu_bo_free_kernel(&ring->ring_obj, &ring->gpu_addr, (void **)&ring->ring); + } else { + kfree(ring->fence_drv.fences); } dma_fence_put(ring->vmid_wait); @@ -478,6 +508,59 @@ static const struct file_operations amdgpu_debugfs_ring_fops = { .llseek = default_llseek }; +static ssize_t amdgpu_debugfs_mqd_read(struct file *f, char __user *buf, + size_t size, loff_t *pos) +{ + struct amdgpu_ring *ring = file_inode(f)->i_private; + volatile u32 *mqd; + int r; + uint32_t value, result; + + if (*pos & 3 || size & 3) + return -EINVAL; + + result = 0; + + r = amdgpu_bo_reserve(ring->mqd_obj, false); + if (unlikely(r != 0)) + return r; + + r = amdgpu_bo_kmap(ring->mqd_obj, (void **)&mqd); + if (r) { + amdgpu_bo_unreserve(ring->mqd_obj); + return r; + } + + while (size) { + if (*pos >= ring->mqd_size) + goto done; + + value = mqd[*pos/4]; + r = put_user(value, (uint32_t *)buf); + if (r) + goto done; + buf += 4; + result += 4; + size -= 4; + *pos += 4; + } + +done: + amdgpu_bo_kunmap(ring->mqd_obj); + mqd = NULL; + amdgpu_bo_unreserve(ring->mqd_obj); + if (r) + return r; + + return result; +} + +static const struct file_operations amdgpu_debugfs_mqd_fops = { + .owner = THIS_MODULE, + .read = amdgpu_debugfs_mqd_read, + .llseek = default_llseek +}; + #endif void amdgpu_debugfs_ring_init(struct amdgpu_device *adev, @@ -489,10 +572,16 @@ void amdgpu_debugfs_ring_init(struct amdgpu_device *adev, char name[32]; sprintf(name, "amdgpu_ring_%s", ring->name); - debugfs_create_file_size(name, S_IFREG | S_IRUGO, root, ring, + debugfs_create_file_size(name, S_IFREG | 0444, root, ring, &amdgpu_debugfs_ring_fops, ring->ring_size + 12); + if (ring->mqd_obj) { + sprintf(name, "amdgpu_mqd_%s", ring->name); + debugfs_create_file_size(name, S_IFREG | 0444, root, ring, + &amdgpu_debugfs_mqd_fops, + ring->mqd_size); + } #endif } @@ -581,3 +670,21 @@ void amdgpu_ring_ib_end(struct amdgpu_ring *ring) if (ring->is_sw_ring) amdgpu_sw_ring_ib_end(ring); } + +void amdgpu_ring_ib_on_emit_cntl(struct amdgpu_ring *ring) +{ + if (ring->is_sw_ring) + amdgpu_sw_ring_ib_mark_offset(ring, AMDGPU_MUX_OFFSET_TYPE_CONTROL); +} + +void amdgpu_ring_ib_on_emit_ce(struct amdgpu_ring *ring) +{ + if (ring->is_sw_ring) + amdgpu_sw_ring_ib_mark_offset(ring, AMDGPU_MUX_OFFSET_TYPE_CE); +} + +void amdgpu_ring_ib_on_emit_de(struct amdgpu_ring *ring) +{ + if (ring->is_sw_ring) + amdgpu_sw_ring_ib_mark_offset(ring, AMDGPU_MUX_OFFSET_TYPE_DE); +} |