From: Christian König Date: Sat, 11 Aug 2012 09:54:05 +0000 (+0200) Subject: drm/radeon: Move looping over the PTEs into chip code X-Git-Url: https://git.karo-electronics.de/?a=commitdiff_plain;h=089a786e2cf5d07d495b3cb1ac0b959c6dd10d49;p=linux-beck.git drm/radeon: Move looping over the PTEs into chip code Makes it easier to move it into the rings. Signed-off-by: Christian König Reviewed-by: Jerome Glisse --- diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c index de378d685803..8bec8113d3a1 100644 --- a/drivers/gpu/drm/radeon/ni.c +++ b/drivers/gpu/drm/radeon/ni.c @@ -1503,9 +1503,7 @@ void cayman_vm_fini(struct radeon_device *rdev) #define R600_PTE_READABLE (1 << 5) #define R600_PTE_WRITEABLE (1 << 6) -uint32_t cayman_vm_page_flags(struct radeon_device *rdev, - struct radeon_vm *vm, - uint32_t flags) +uint32_t cayman_vm_page_flags(struct radeon_device *rdev, uint32_t flags) { uint32_t r600_flags = 0; @@ -1520,13 +1518,23 @@ uint32_t cayman_vm_page_flags(struct radeon_device *rdev, } void cayman_vm_set_page(struct radeon_device *rdev, struct radeon_vm *vm, - unsigned pfn, uint64_t addr, uint32_t flags) + unsigned pfn, struct ttm_mem_reg *mem, + unsigned npages, uint32_t flags) { void __iomem *ptr = (void *)vm->pt; + uint64_t addr; + int i; + + addr = flags = cayman_vm_page_flags(rdev, flags); - addr = addr & 0xFFFFFFFFFFFFF000ULL; - addr |= flags; - writeq(addr, ptr + (pfn * 8)); + for (i = 0; i < npages; ++i, ++pfn) { + if (mem) { + addr = radeon_vm_get_addr(rdev, mem, i); + addr = addr & 0xFFFFFFFFFFFFF000ULL; + addr |= flags; + } + writeq(addr, ptr + (pfn * 8)); + } } void cayman_vm_flush(struct radeon_device *rdev, struct radeon_ib *ib) diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h index d6cd1f57fece..ae7409a0f62b 100644 --- a/drivers/gpu/drm/radeon/radeon.h +++ b/drivers/gpu/drm/radeon/radeon.h @@ -1135,11 +1135,9 @@ struct radeon_asic { struct { int (*init)(struct radeon_device *rdev); void (*fini)(struct radeon_device *rdev); - uint32_t (*page_flags)(struct radeon_device *rdev, - struct radeon_vm *vm, - uint32_t flags); void (*set_page)(struct radeon_device *rdev, struct radeon_vm *vm, - unsigned pfn, uint64_t addr, uint32_t flags); + unsigned pfn, struct ttm_mem_reg *mem, + unsigned npages, uint32_t flags); } vm; /* ring specific callbacks */ struct { @@ -1751,8 +1749,7 @@ void radeon_ring_write(struct radeon_ring *ring, uint32_t v); #define radeon_gart_set_page(rdev, i, p) (rdev)->asic->gart.set_page((rdev), (i), (p)) #define radeon_asic_vm_init(rdev) (rdev)->asic->vm.init((rdev)) #define radeon_asic_vm_fini(rdev) (rdev)->asic->vm.fini((rdev)) -#define radeon_asic_vm_page_flags(rdev, v, flags) (rdev)->asic->vm.page_flags((rdev), (v), (flags)) -#define radeon_asic_vm_set_page(rdev, v, pfn, addr, flags) (rdev)->asic->vm.set_page((rdev), (v), (pfn), (addr), (flags)) +#define radeon_asic_vm_set_page(rdev, v, pfn, mem, npages, flags) (rdev)->asic->vm.set_page((rdev), (v), (pfn), (mem), (npages), (flags)) #define radeon_ring_start(rdev, r, cp) (rdev)->asic->ring[(r)].ring_start((rdev), (cp)) #define radeon_ring_test(rdev, r, cp) (rdev)->asic->ring[(r)].ring_test((rdev), (cp)) #define radeon_ib_test(rdev, r, cp) (rdev)->asic->ring[(r)].ib_test((rdev), (cp)) @@ -1837,6 +1834,9 @@ struct radeon_fence *radeon_vm_grab_id(struct radeon_device *rdev, void radeon_vm_fence(struct radeon_device *rdev, struct radeon_vm *vm, struct radeon_fence *fence); +u64 radeon_vm_get_addr(struct radeon_device *rdev, + struct ttm_mem_reg *mem, + unsigned pfn); int radeon_vm_bo_update_pte(struct radeon_device *rdev, struct radeon_vm *vm, struct radeon_bo *bo, diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c index 98c586ac1999..6e4e67edf60f 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.c +++ b/drivers/gpu/drm/radeon/radeon_asic.c @@ -1375,7 +1375,6 @@ static struct radeon_asic cayman_asic = { .vm = { .init = &cayman_vm_init, .fini = &cayman_vm_fini, - .page_flags = &cayman_vm_page_flags, .set_page = &cayman_vm_set_page, }, .ring = { @@ -1479,7 +1478,6 @@ static struct radeon_asic trinity_asic = { .vm = { .init = &cayman_vm_init, .fini = &cayman_vm_fini, - .page_flags = &cayman_vm_page_flags, .set_page = &cayman_vm_set_page, }, .ring = { @@ -1583,7 +1581,6 @@ static struct radeon_asic si_asic = { .vm = { .init = &si_vm_init, .fini = &si_vm_fini, - .page_flags = &cayman_vm_page_flags, .set_page = &cayman_vm_set_page, }, .ring = { diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h index 25e8d000dac9..2b3dd3173022 100644 --- a/drivers/gpu/drm/radeon/radeon_asic.h +++ b/drivers/gpu/drm/radeon/radeon_asic.h @@ -442,11 +442,10 @@ int cayman_vm_init(struct radeon_device *rdev); void cayman_vm_fini(struct radeon_device *rdev); void cayman_vm_unbind(struct radeon_device *rdev, struct radeon_vm *vm); void cayman_vm_flush(struct radeon_device *rdev, struct radeon_ib *ib); -uint32_t cayman_vm_page_flags(struct radeon_device *rdev, - struct radeon_vm *vm, - uint32_t flags); +uint32_t cayman_vm_page_flags(struct radeon_device *rdev, uint32_t flags); void cayman_vm_set_page(struct radeon_device *rdev, struct radeon_vm *vm, - unsigned pfn, uint64_t addr, uint32_t flags); + unsigned pfn, struct ttm_mem_reg *mem, + unsigned npages, uint32_t flags); int evergreen_ib_parse(struct radeon_device *rdev, struct radeon_ib *ib); /* DCE6 - SI */ diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c index da1b2dbe4550..0f9a40f84d7a 100644 --- a/drivers/gpu/drm/radeon/radeon_gart.c +++ b/drivers/gpu/drm/radeon/radeon_gart.c @@ -450,7 +450,7 @@ int radeon_vm_manager_init(struct radeon_device *rdev) r = radeon_asic_vm_init(rdev); if (r) return r; - + rdev->vm_manager.enabled = true; r = radeon_sa_bo_manager_start(rdev, &rdev->vm_manager.sa_manager); @@ -773,9 +773,9 @@ int radeon_vm_bo_add(struct radeon_device *rdev, * to (cayman+). * Returns the physical address of the page. */ -static u64 radeon_vm_get_addr(struct radeon_device *rdev, - struct ttm_mem_reg *mem, - unsigned pfn) +u64 radeon_vm_get_addr(struct radeon_device *rdev, + struct ttm_mem_reg *mem, + unsigned pfn) { u64 addr = 0; @@ -819,9 +819,8 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev, struct ttm_mem_reg *mem) { struct radeon_bo_va *bo_va; - unsigned ngpu_pages, i; - uint64_t addr = 0, pfn; - uint32_t flags; + unsigned ngpu_pages; + uint64_t pfn; /* nothing to do if vm isn't bound */ if (vm->sa_bo == NULL) @@ -848,14 +847,11 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev, bo_va->flags |= RADEON_VM_PAGE_SYSTEM; } } - pfn = bo_va->soffset / RADEON_GPU_PAGE_SIZE; - flags = radeon_asic_vm_page_flags(rdev, bo_va->vm, bo_va->flags); - for (i = 0, addr = 0; i < ngpu_pages; i++) { - if (mem && bo_va->valid) { - addr = radeon_vm_get_addr(rdev, mem, i); - } - radeon_asic_vm_set_page(rdev, bo_va->vm, i + pfn, addr, flags); + if (!bo_va->valid) { + mem = NULL; } + pfn = bo_va->soffset / RADEON_GPU_PAGE_SIZE; + radeon_asic_vm_set_page(rdev, bo_va->vm, pfn, mem, ngpu_pages, bo_va->flags); radeon_fence_unref(&vm->last_flush); return 0; }