diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c | 59 |
1 files changed, 24 insertions, 35 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c index b0bf21682115..a930f1522f96 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c @@ -26,6 +26,7 @@ #include "amdgpu.h" #include "amdgpu_trace.h" #include "amdgpu_vm.h" +#include "amdgpu_job.h" /* * amdgpu_vm_pt_cursor - state for for_each_amdgpu_vm_pt @@ -50,6 +51,7 @@ static unsigned int amdgpu_vm_pt_level_shift(struct amdgpu_device *adev, unsigned int level) { switch (level) { + case AMDGPU_VM_PDB3: case AMDGPU_VM_PDB2: case AMDGPU_VM_PDB1: case AMDGPU_VM_PDB0: @@ -365,6 +367,7 @@ int amdgpu_vm_pt_clear(struct amdgpu_device *adev, struct amdgpu_vm *vm, struct amdgpu_bo *ancestor = &vmbo->bo; unsigned int entries; struct amdgpu_bo *bo = &vmbo->bo; + uint64_t value = 0, flags = 0; uint64_t addr; int r, idx; @@ -395,13 +398,13 @@ int amdgpu_vm_pt_clear(struct amdgpu_device *adev, struct amdgpu_vm *vm, params.vm = vm; params.immediate = immediate; - r = vm->update_funcs->prepare(¶ms, NULL); + r = vm->update_funcs->prepare(¶ms, NULL, + AMDGPU_KERNEL_JOB_ID_VM_PT_CLEAR); if (r) goto exit; addr = 0; - uint64_t value = 0, flags = 0; if (adev->asic_type >= CHIP_VEGA10) { if (level != AMDGPU_VM_PTB) { /* Handle leaf PDEs as PTEs */ @@ -410,7 +413,7 @@ int amdgpu_vm_pt_clear(struct amdgpu_device *adev, struct amdgpu_vm *vm, &value, &flags); } else { /* Workaround for fault priority problem on GMC9 */ - flags = AMDGPU_PTE_EXECUTABLE; + flags = AMDGPU_PTE_EXECUTABLE | adev->gmc.init_pte_flags; } } @@ -547,27 +550,6 @@ static void amdgpu_vm_pt_free(struct amdgpu_vm_bo_base *entry) amdgpu_bo_unref(&entry->bo); } -void amdgpu_vm_pt_free_work(struct work_struct *work) -{ - struct amdgpu_vm_bo_base *entry, *next; - struct amdgpu_vm *vm; - LIST_HEAD(pt_freed); - - vm = container_of(work, struct amdgpu_vm, pt_free_work); - - spin_lock(&vm->status_lock); - list_splice_init(&vm->pt_freed, &pt_freed); - spin_unlock(&vm->status_lock); - - /* flush_work in amdgpu_vm_fini ensure vm->root.bo is valid. */ - amdgpu_bo_reserve(vm->root.bo, true); - - list_for_each_entry_safe(entry, next, &pt_freed, vm_status) - amdgpu_vm_pt_free(entry); - - amdgpu_bo_unreserve(vm->root.bo); -} - /** * amdgpu_vm_pt_free_list - free PD/PT levels * @@ -580,19 +562,15 @@ void amdgpu_vm_pt_free_list(struct amdgpu_device *adev, struct amdgpu_vm_update_params *params) { struct amdgpu_vm_bo_base *entry, *next; - struct amdgpu_vm *vm = params->vm; bool unlocked = params->unlocked; if (list_empty(¶ms->tlb_flush_waitlist)) return; - if (unlocked) { - spin_lock(&vm->status_lock); - list_splice_init(¶ms->tlb_flush_waitlist, &vm->pt_freed); - spin_unlock(&vm->status_lock); - schedule_work(&vm->pt_free_work); - return; - } + /* + * unlocked unmap clear page table leaves, warning to free the page entry. + */ + WARN_ON(unlocked); list_for_each_entry_safe(entry, next, ¶ms->tlb_flush_waitlist, vm_status) amdgpu_vm_pt_free(entry); @@ -715,8 +693,11 @@ static void amdgpu_vm_pte_update_flags(struct amdgpu_vm_update_params *params, !(flags & AMDGPU_PTE_VALID) && !(flags & AMDGPU_PTE_PRT_FLAG(params->adev))) { - /* Workaround for fault priority problem on GMC9 */ - flags |= AMDGPU_PTE_EXECUTABLE; + /* Workaround for fault priority problem on GMC9 and GFX12, + * EXECUTABLE for GMC9 fault priority and init_pte_flags + * (e.g. AMDGPU_PTE_IS_PTE on GFX12) + */ + flags |= AMDGPU_PTE_EXECUTABLE | adev->gmc.init_pte_flags; } /* @@ -900,7 +881,15 @@ int amdgpu_vm_ptes_update(struct amdgpu_vm_update_params *params, incr = (uint64_t)AMDGPU_GPU_PAGE_SIZE << shift; mask = amdgpu_vm_pt_entries_mask(adev, cursor.level); pe_start = ((cursor.pfn >> shift) & mask) * 8; - entry_end = ((uint64_t)mask + 1) << shift; + + if (cursor.level < AMDGPU_VM_PTB && params->unlocked) + /* + * MMU notifier callback unlocked unmap huge page, leave is PDE entry, + * only clear one entry. Next entry search again for PDE or PTE leave. + */ + entry_end = 1ULL << shift; + else + entry_end = ((uint64_t)mask + 1) << shift; entry_end += cursor.pfn & ~(entry_end - 1); entry_end = min(entry_end, end); |
