diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2024-03-22 05:04:31 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2024-03-22 05:04:31 +0300 |
commit | 7ee04901215b3cab8fa35aa5bf4692d7aa312e36 (patch) | |
tree | e8c8a87c871c6a0efcda49963f0de150aff040a2 /drivers/gpu/drm/xe | |
parent | 661dc19066ef0fdcb2db3e2542c45744a4067e87 (diff) | |
parent | cafd86cbdc607eadc28a008cddacd78f0894c628 (diff) | |
download | linux-7ee04901215b3cab8fa35aa5bf4692d7aa312e36.tar.xz |
Merge tag 'drm-next-2024-03-22' of https://gitlab.freedesktop.org/drm/kernel
Pull drm fixes from Dave Airlie:
"Fixes from the last week (or 3 weeks in amdgpu case), after amdgpu,
it's xe and nouveau then a few scattered core fixes.
core:
- fix rounding in drm_fixp2int_round()
bridge:
- fix documentation for DRM_BRIDGE_OP_EDID
sun4i:
- fix 64-bit division on 32-bit architectures
tests:
- fix dependency on DRM_KMS_HELPER
probe-helper:
- never return negative values from .get_modes() plus driver fixes
xe:
- invalidate userptr vma on page pin fault
- fail early on sysfs file creation error
- skip VMA pinning on xe_exec if no batches
nouveau:
- clear bo resource bus after eviction
- documentation fixes
- don't check devinit disable on GSP
amdgpu:
- Freesync fixes
- UAF IOCTL fixes
- Fix mmhub client ID mapping
- IH 7.0 fix
- DML2 fixes
- VCN 4.0.6 fix
- GART bind fix
- GPU reset fix
- SR-IOV fix
- OD table handling fixes
- Fix TA handling on boards without display hardware
- DML1 fix
- ABM fix
- eDP panel fix
- DPPCLK fix
- HDCP fix
- Revert incorrect error case handling in ioremap
- VPE fix
- HDMI fixes
- SDMA 4.4.2 fix
- Other misc fixes
amdkfd:
- Fix duplicate BO handling in process restore"
* tag 'drm-next-2024-03-22' of https://gitlab.freedesktop.org/drm/kernel: (50 commits)
drm/amdgpu/pm: Don't use OD table on Arcturus
drm/amdgpu: drop setting buffer funcs in sdma442
drm/amd/display: Fix noise issue on HDMI AV mute
drm/amd/display: Revert Remove pixle rate limit for subvp
Revert "drm/amdgpu/vpe: don't emit cond exec command under collaborate mode"
Revert "drm/amd/amdgpu: Fix potential ioremap() memory leaks in amdgpu_device_init()"
drm/amd/display: Add a dc_state NULL check in dc_state_release
drm/amd/display: Return the correct HDCP error code
drm/amd/display: Implement wait_for_odm_update_pending_complete
drm/amd/display: Lock all enabled otg pipes even with no planes
drm/amd/display: Amend coasting vtotal for replay low hz
drm/amd/display: Fix idle check for shared firmware state
drm/amd/display: Update odm when ODM combine is changed on an otg master pipe with no plane
drm/amd/display: Init DPPCLK from SMU on dcn32
drm/amd/display: Add monitor patch for specific eDP
drm/amd/display: Allow dirty rects to be sent to dmub when abm is active
drm/amd/display: Override min required DCFCLK in dml1_validate
drm/amdgpu: Bypass display ta if display hw is not available
drm/amdgpu: correct the KGQ fallback message
drm/amdgpu/pm: Check the validity of overdiver power limit
...
Diffstat (limited to 'drivers/gpu/drm/xe')
-rw-r--r-- | drivers/gpu/drm/xe/xe_exec.c | 41 | ||||
-rw-r--r-- | drivers/gpu/drm/xe/xe_gt_pagefault.c | 4 | ||||
-rw-r--r-- | drivers/gpu/drm/xe/xe_trace.h | 2 | ||||
-rw-r--r-- | drivers/gpu/drm/xe/xe_vm.c | 32 | ||||
-rw-r--r-- | drivers/gpu/drm/xe/xe_vm_types.h | 7 | ||||
-rw-r--r-- | drivers/gpu/drm/xe/xe_vram_freq.c | 4 |
6 files changed, 55 insertions, 35 deletions
diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c index 952496c6260d..826c8b389672 100644 --- a/drivers/gpu/drm/xe/xe_exec.c +++ b/drivers/gpu/drm/xe/xe_exec.c @@ -235,6 +235,29 @@ retry: goto err_unlock_list; } + if (!args->num_batch_buffer) { + err = xe_vm_lock(vm, true); + if (err) + goto err_unlock_list; + + if (!xe_vm_in_lr_mode(vm)) { + struct dma_fence *fence; + + fence = xe_sync_in_fence_get(syncs, num_syncs, q, vm); + if (IS_ERR(fence)) { + err = PTR_ERR(fence); + goto err_unlock_list; + } + for (i = 0; i < num_syncs; i++) + xe_sync_entry_signal(&syncs[i], NULL, fence); + xe_exec_queue_last_fence_set(q, vm, fence); + dma_fence_put(fence); + } + + xe_vm_unlock(vm); + goto err_unlock_list; + } + vm_exec.vm = &vm->gpuvm; vm_exec.flags = DRM_EXEC_INTERRUPTIBLE_WAIT; if (xe_vm_in_lr_mode(vm)) { @@ -254,24 +277,6 @@ retry: goto err_exec; } - if (!args->num_batch_buffer) { - if (!xe_vm_in_lr_mode(vm)) { - struct dma_fence *fence; - - fence = xe_sync_in_fence_get(syncs, num_syncs, q, vm); - if (IS_ERR(fence)) { - err = PTR_ERR(fence); - goto err_exec; - } - for (i = 0; i < num_syncs; i++) - xe_sync_entry_signal(&syncs[i], NULL, fence); - xe_exec_queue_last_fence_set(q, vm, fence); - dma_fence_put(fence); - } - - goto err_exec; - } - if (xe_exec_queue_is_lr(q) && xe_exec_queue_ring_full(q)) { err = -EWOULDBLOCK; /* Aliased to -EAGAIN */ skip_retry = true; diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c index 73c535193a98..241c294270d9 100644 --- a/drivers/gpu/drm/xe/xe_gt_pagefault.c +++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c @@ -69,7 +69,7 @@ static bool access_is_atomic(enum access_type access_type) static bool vma_is_valid(struct xe_tile *tile, struct xe_vma *vma) { return BIT(tile->id) & vma->tile_present && - !(BIT(tile->id) & vma->usm.tile_invalidated); + !(BIT(tile->id) & vma->tile_invalidated); } static bool vma_matches(struct xe_vma *vma, u64 page_addr) @@ -226,7 +226,7 @@ retry_userptr: if (xe_vma_is_userptr(vma)) ret = xe_vma_userptr_check_repin(to_userptr_vma(vma)); - vma->usm.tile_invalidated &= ~BIT(tile->id); + vma->tile_invalidated &= ~BIT(tile->id); unlock_dma_resv: drm_exec_fini(&exec); diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h index 4ddc55527f9a..846f14507d5f 100644 --- a/drivers/gpu/drm/xe/xe_trace.h +++ b/drivers/gpu/drm/xe/xe_trace.h @@ -468,7 +468,7 @@ DEFINE_EVENT(xe_vma, xe_vma_userptr_invalidate, TP_ARGS(vma) ); -DEFINE_EVENT(xe_vma, xe_vma_usm_invalidate, +DEFINE_EVENT(xe_vma, xe_vma_invalidate, TP_PROTO(struct xe_vma *vma), TP_ARGS(vma) ); diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index d28260351af2..f88faef4142b 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -708,6 +708,7 @@ int xe_vm_userptr_pin(struct xe_vm *vm) int err = 0; LIST_HEAD(tmp_evict); + xe_assert(vm->xe, !xe_vm_in_fault_mode(vm)); lockdep_assert_held_write(&vm->lock); /* Collect invalidated userptrs */ @@ -724,11 +725,27 @@ int xe_vm_userptr_pin(struct xe_vm *vm) list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list, userptr.repin_link) { err = xe_vma_userptr_pin_pages(uvma); - if (err < 0) - return err; + if (err == -EFAULT) { + list_del_init(&uvma->userptr.repin_link); - list_del_init(&uvma->userptr.repin_link); - list_move_tail(&uvma->vma.combined_links.rebind, &vm->rebind_list); + /* Wait for pending binds */ + xe_vm_lock(vm, false); + dma_resv_wait_timeout(xe_vm_resv(vm), + DMA_RESV_USAGE_BOOKKEEP, + false, MAX_SCHEDULE_TIMEOUT); + + err = xe_vm_invalidate_vma(&uvma->vma); + xe_vm_unlock(vm); + if (err) + return err; + } else { + if (err < 0) + return err; + + list_del_init(&uvma->userptr.repin_link); + list_move_tail(&uvma->vma.combined_links.rebind, + &vm->rebind_list); + } } return 0; @@ -2024,7 +2041,7 @@ static int xe_vm_prefetch(struct xe_vm *vm, struct xe_vma *vma, return err; } - if (vma->tile_mask != (vma->tile_present & ~vma->usm.tile_invalidated)) { + if (vma->tile_mask != (vma->tile_present & ~vma->tile_invalidated)) { return xe_vm_bind(vm, vma, q, xe_vma_bo(vma), syncs, num_syncs, true, first_op, last_op); } else { @@ -3214,9 +3231,8 @@ int xe_vm_invalidate_vma(struct xe_vma *vma) u8 id; int ret; - xe_assert(xe, xe_vm_in_fault_mode(xe_vma_vm(vma))); xe_assert(xe, !xe_vma_is_null(vma)); - trace_xe_vma_usm_invalidate(vma); + trace_xe_vma_invalidate(vma); /* Check that we don't race with page-table updates */ if (IS_ENABLED(CONFIG_PROVE_LOCKING)) { @@ -3254,7 +3270,7 @@ int xe_vm_invalidate_vma(struct xe_vma *vma) } } - vma->usm.tile_invalidated = vma->tile_mask; + vma->tile_invalidated = vma->tile_mask; return 0; } diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h index 79b5cab57711..ae5fb565f6bf 100644 --- a/drivers/gpu/drm/xe/xe_vm_types.h +++ b/drivers/gpu/drm/xe/xe_vm_types.h @@ -84,11 +84,8 @@ struct xe_vma { struct work_struct destroy_work; }; - /** @usm: unified shared memory state */ - struct { - /** @tile_invalidated: VMA has been invalidated */ - u8 tile_invalidated; - } usm; + /** @tile_invalidated: VMA has been invalidated */ + u8 tile_invalidated; /** @tile_mask: Tile mask of where to create binding for this VMA */ u8 tile_mask; diff --git a/drivers/gpu/drm/xe/xe_vram_freq.c b/drivers/gpu/drm/xe/xe_vram_freq.c index 079cc283a186..c5f6b5a5d117 100644 --- a/drivers/gpu/drm/xe/xe_vram_freq.c +++ b/drivers/gpu/drm/xe/xe_vram_freq.c @@ -111,8 +111,10 @@ void xe_vram_freq_sysfs_init(struct xe_tile *tile) return; kobj = kobject_create_and_add("memory", tile->sysfs); - if (!kobj) + if (!kobj) { drm_warn(&xe->drm, "failed to add memory directory, err: %d\n", -ENOMEM); + return; + } err = sysfs_create_group(kobj, &freq_group_attrs); if (err) { |