From 9d87fa2138d06ff400551800d67d522625033e35 Mon Sep 17 00:00:00 2001 From: Jerome Glisse Date: Wed, 7 Apr 2010 10:21:19 +0000 Subject: drm/ttm: split no_wait argument in 2 GPU or reserve wait There is case where we want to be able to wait only for the GPU while not waiting for other buffer to be unreserved. This patch split the no_wait argument all the way down in the whole ttm path so that upper level can decide on what to wait on or not. [airlied: squashed these 4 for bisectability reasons.] drm/radeon/kms: update to TTM no_wait splitted argument drm/nouveau: update to TTM no_wait splitted argument drm/vmwgfx: update to TTM no_wait splitted argument [vmwgfx patch: Reviewed-by: Thomas Hellstrom ] Signed-off-by: Jerome Glisse Acked-by: Thomas Hellstrom Signed-off-by: Dave Airlie --- drivers/gpu/drm/ttm/ttm_bo.c | 57 +++++++++++++++++++++++++------------------- 1 file changed, 32 insertions(+), 25 deletions(-) (limited to 'drivers/gpu/drm/ttm/ttm_bo.c') diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index dd47b2a9a791..40631e2866f8 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -357,7 +357,8 @@ static int ttm_bo_add_ttm(struct ttm_buffer_object *bo, bool zero_alloc) static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo, struct ttm_mem_reg *mem, - bool evict, bool interruptible, bool no_wait) + bool evict, bool interruptible, + bool no_wait_reserve, bool no_wait_gpu) { struct ttm_bo_device *bdev = bo->bdev; bool old_is_pci = ttm_mem_reg_is_pci(bdev, &bo->mem); @@ -402,12 +403,12 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo, if (!(old_man->flags & TTM_MEMTYPE_FLAG_FIXED) && !(new_man->flags & TTM_MEMTYPE_FLAG_FIXED)) - ret = ttm_bo_move_ttm(bo, evict, no_wait, mem); + ret = ttm_bo_move_ttm(bo, evict, no_wait_reserve, no_wait_gpu, mem); else if (bdev->driver->move) ret = bdev->driver->move(bo, evict, interruptible, - no_wait, mem); + no_wait_reserve, no_wait_gpu, mem); else - ret = ttm_bo_move_memcpy(bo, evict, no_wait, mem); + ret = ttm_bo_move_memcpy(bo, evict, no_wait_reserve, no_wait_gpu, mem); if (ret) goto out_err; @@ -606,7 +607,7 @@ void ttm_bo_unref(struct ttm_buffer_object **p_bo) EXPORT_SYMBOL(ttm_bo_unref); static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible, - bool no_wait) + bool no_wait_reserve, bool no_wait_gpu) { struct ttm_bo_device *bdev = bo->bdev; struct ttm_bo_global *glob = bo->glob; @@ -615,7 +616,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible, int ret = 0; spin_lock(&bo->lock); - ret = ttm_bo_wait(bo, false, interruptible, no_wait); + ret = ttm_bo_wait(bo, false, interruptible, no_wait_gpu); spin_unlock(&bo->lock); if (unlikely(ret != 0)) { @@ -638,7 +639,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible, placement.num_busy_placement = 0; bdev->driver->evict_flags(bo, &placement); ret = ttm_bo_mem_space(bo, &placement, &evict_mem, interruptible, - no_wait); + no_wait_reserve, no_wait_gpu); if (ret) { if (ret != -ERESTARTSYS) { printk(KERN_ERR TTM_PFX @@ -650,7 +651,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible, } ret = ttm_bo_handle_move_mem(bo, &evict_mem, true, interruptible, - no_wait); + no_wait_reserve, no_wait_gpu); if (ret) { if (ret != -ERESTARTSYS) printk(KERN_ERR TTM_PFX "Buffer eviction failed\n"); @@ -670,7 +671,8 @@ out: static int ttm_mem_evict_first(struct ttm_bo_device *bdev, uint32_t mem_type, - bool interruptible, bool no_wait) + bool interruptible, bool no_wait_reserve, + bool no_wait_gpu) { struct ttm_bo_global *glob = bdev->glob; struct ttm_mem_type_manager *man = &bdev->man[mem_type]; @@ -687,11 +689,11 @@ retry: bo = list_first_entry(&man->lru, struct ttm_buffer_object, lru); kref_get(&bo->list_kref); - ret = ttm_bo_reserve_locked(bo, false, true, false, 0); + ret = ttm_bo_reserve_locked(bo, false, no_wait_reserve, false, 0); if (unlikely(ret == -EBUSY)) { spin_unlock(&glob->lru_lock); - if (likely(!no_wait)) + if (likely(!no_wait_gpu)) ret = ttm_bo_wait_unreserved(bo, interruptible); kref_put(&bo->list_kref, ttm_bo_release_list); @@ -713,7 +715,7 @@ retry: while (put_count--) kref_put(&bo->list_kref, ttm_bo_ref_bug); - ret = ttm_bo_evict(bo, interruptible, no_wait); + ret = ttm_bo_evict(bo, interruptible, no_wait_reserve, no_wait_gpu); ttm_bo_unreserve(bo); kref_put(&bo->list_kref, ttm_bo_release_list); @@ -764,7 +766,9 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo, uint32_t mem_type, struct ttm_placement *placement, struct ttm_mem_reg *mem, - bool interruptible, bool no_wait) + bool interruptible, + bool no_wait_reserve, + bool no_wait_gpu) { struct ttm_bo_device *bdev = bo->bdev; struct ttm_bo_global *glob = bdev->glob; @@ -785,7 +789,7 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo, } spin_unlock(&glob->lru_lock); ret = ttm_mem_evict_first(bdev, mem_type, interruptible, - no_wait); + no_wait_reserve, no_wait_gpu); if (unlikely(ret != 0)) return ret; } while (1); @@ -855,7 +859,8 @@ static bool ttm_bo_mt_compatible(struct ttm_mem_type_manager *man, int ttm_bo_mem_space(struct ttm_buffer_object *bo, struct ttm_placement *placement, struct ttm_mem_reg *mem, - bool interruptible, bool no_wait) + bool interruptible, bool no_wait_reserve, + bool no_wait_gpu) { struct ttm_bo_device *bdev = bo->bdev; struct ttm_mem_type_manager *man; @@ -952,7 +957,7 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo, } ret = ttm_bo_mem_force_space(bo, mem_type, placement, mem, - interruptible, no_wait); + interruptible, no_wait_reserve, no_wait_gpu); if (ret == 0 && mem->mm_node) { mem->placement = cur_flags; mem->mm_node->private = bo; @@ -978,7 +983,8 @@ EXPORT_SYMBOL(ttm_bo_wait_cpu); int ttm_bo_move_buffer(struct ttm_buffer_object *bo, struct ttm_placement *placement, - bool interruptible, bool no_wait) + bool interruptible, bool no_wait_reserve, + bool no_wait_gpu) { struct ttm_bo_global *glob = bo->glob; int ret = 0; @@ -992,7 +998,7 @@ int ttm_bo_move_buffer(struct ttm_buffer_object *bo, * instead of doing it here. */ spin_lock(&bo->lock); - ret = ttm_bo_wait(bo, false, interruptible, no_wait); + ret = ttm_bo_wait(bo, false, interruptible, no_wait_gpu); spin_unlock(&bo->lock); if (ret) return ret; @@ -1002,10 +1008,10 @@ int ttm_bo_move_buffer(struct ttm_buffer_object *bo, /* * Determine where to move the buffer. */ - ret = ttm_bo_mem_space(bo, placement, &mem, interruptible, no_wait); + ret = ttm_bo_mem_space(bo, placement, &mem, interruptible, no_wait_reserve, no_wait_gpu); if (ret) goto out_unlock; - ret = ttm_bo_handle_move_mem(bo, &mem, false, interruptible, no_wait); + ret = ttm_bo_handle_move_mem(bo, &mem, false, interruptible, no_wait_reserve, no_wait_gpu); out_unlock: if (ret && mem.mm_node) { spin_lock(&glob->lru_lock); @@ -1039,7 +1045,8 @@ static int ttm_bo_mem_compat(struct ttm_placement *placement, int ttm_bo_validate(struct ttm_buffer_object *bo, struct ttm_placement *placement, - bool interruptible, bool no_wait) + bool interruptible, bool no_wait_reserve, + bool no_wait_gpu) { int ret; @@ -1054,7 +1061,7 @@ int ttm_bo_validate(struct ttm_buffer_object *bo, */ ret = ttm_bo_mem_compat(placement, &bo->mem); if (ret < 0) { - ret = ttm_bo_move_buffer(bo, placement, interruptible, no_wait); + ret = ttm_bo_move_buffer(bo, placement, interruptible, no_wait_reserve, no_wait_gpu); if (ret) return ret; } else { @@ -1175,7 +1182,7 @@ int ttm_bo_init(struct ttm_bo_device *bdev, goto out_err; } - ret = ttm_bo_validate(bo, placement, interruptible, false); + ret = ttm_bo_validate(bo, placement, interruptible, false, false); if (ret) goto out_err; @@ -1249,7 +1256,7 @@ static int ttm_bo_force_list_clean(struct ttm_bo_device *bdev, spin_lock(&glob->lru_lock); while (!list_empty(&man->lru)) { spin_unlock(&glob->lru_lock); - ret = ttm_mem_evict_first(bdev, mem_type, false, false); + ret = ttm_mem_evict_first(bdev, mem_type, false, false, false); if (ret) { if (allow_errors) { return ret; @@ -1839,7 +1846,7 @@ static int ttm_bo_swapout(struct ttm_mem_shrink *shrink) evict_mem.mem_type = TTM_PL_SYSTEM; ret = ttm_bo_handle_move_mem(bo, &evict_mem, true, - false, false); + false, false, false); if (unlikely(ret != 0)) goto out; } -- cgit v1.2.3 From 82c5da6bf8b55a931b042fb531083863d26c8020 Mon Sep 17 00:00:00 2001 From: Jerome Glisse Date: Fri, 9 Apr 2010 14:39:23 +0200 Subject: drm/ttm: ttm_fault callback to allow driver to handle bo placement V6 On fault the driver is given the opportunity to perform any operation it sees fit in order to place the buffer into a CPU visible area of memory. This patch doesn't break TTM users, nouveau, vmwgfx and radeon should keep working properly. Future patch will take advantage of this infrastructure and remove the old path from TTM once driver are converted. V2 return VM_FAULT_NOPAGE if callback return -EBUSY or -ERESTARTSYS V3 balance io_mem_reserve and io_mem_free call, fault_reserve_notify is responsible to perform any necessary task for mapping to succeed V4 minor cleanup, atomic_t -> bool as member is protected by reserve mecanism from concurent access V5 the callback is now responsible for iomapping the bo and providing a virtual address this simplify TTM and will allow to get rid of TTM_MEMTYPE_FLAG_NEEDS_IOREMAP V6 use the bus addr data to decide to ioremap or this isn't needed but we don't necesarily need to ioremap in the callback but still allow driver to use static mapping Signed-off-by: Jerome Glisse Reviewed-by: Thomas Hellstrom Signed-off-by: Dave Airlie --- drivers/gpu/drm/ttm/ttm_bo.c | 7 ++- drivers/gpu/drm/ttm/ttm_bo_util.c | 124 +++++++++++++++++++------------------- drivers/gpu/drm/ttm/ttm_bo_vm.c | 41 +++++++------ include/drm/ttm/ttm_bo_api.h | 23 +++++++ include/drm/ttm/ttm_bo_driver.h | 16 ++++- 5 files changed, 126 insertions(+), 85 deletions(-) (limited to 'drivers/gpu/drm/ttm/ttm_bo.c') diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 40631e2866f8..b42e3fae1bd5 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -632,6 +632,7 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible, evict_mem = bo->mem; evict_mem.mm_node = NULL; + evict_mem.bus.io_reserved = false; placement.fpfn = 0; placement.lpfn = 0; @@ -1005,6 +1006,7 @@ int ttm_bo_move_buffer(struct ttm_buffer_object *bo, mem.num_pages = bo->num_pages; mem.size = mem.num_pages << PAGE_SHIFT; mem.page_alignment = bo->mem.page_alignment; + mem.bus.io_reserved = false; /* * Determine where to move the buffer. */ @@ -1160,6 +1162,7 @@ int ttm_bo_init(struct ttm_bo_device *bdev, bo->mem.num_pages = bo->num_pages; bo->mem.mm_node = NULL; bo->mem.page_alignment = page_alignment; + bo->mem.bus.io_reserved = false; bo->buffer_start = buffer_start & PAGE_MASK; bo->priv_flags = 0; bo->mem.placement = (TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED); @@ -1574,7 +1577,7 @@ int ttm_bo_pci_offset(struct ttm_bo_device *bdev, if (ttm_mem_reg_is_pci(bdev, mem)) { *bus_offset = mem->mm_node->start << PAGE_SHIFT; *bus_size = mem->num_pages << PAGE_SHIFT; - *bus_base = man->io_offset; + *bus_base = man->io_offset + (uintptr_t)man->io_addr; } return 0; @@ -1588,8 +1591,8 @@ void ttm_bo_unmap_virtual(struct ttm_buffer_object *bo) if (!bdev->dev_mapping) return; - unmap_mapping_range(bdev->dev_mapping, offset, holelen, 1); + ttm_mem_io_free(bdev, &bo->mem); } EXPORT_SYMBOL(ttm_bo_unmap_virtual); diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index 865b2a826e13..d58eeb5ed22b 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -81,30 +81,62 @@ int ttm_bo_move_ttm(struct ttm_buffer_object *bo, } EXPORT_SYMBOL(ttm_bo_move_ttm); +int ttm_mem_io_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem) +{ + struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type]; + int ret; + + if (bdev->driver->io_mem_reserve) { + if (!mem->bus.io_reserved) { + mem->bus.io_reserved = true; + ret = bdev->driver->io_mem_reserve(bdev, mem); + if (unlikely(ret != 0)) + return ret; + } + } else { + ret = ttm_bo_pci_offset(bdev, mem, &mem->bus.base, &mem->bus.offset, &mem->bus.size); + if (unlikely(ret != 0)) + return ret; + mem->bus.addr = NULL; + if (!(man->flags & TTM_MEMTYPE_FLAG_NEEDS_IOREMAP)) + mem->bus.addr = (void *)(((u8 *)man->io_addr) + mem->bus.offset); + mem->bus.is_iomem = (mem->bus.size > 0) ? 1 : 0; + } + return 0; +} + +void ttm_mem_io_free(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem) +{ + if (bdev->driver->io_mem_reserve) { + if (mem->bus.io_reserved) { + mem->bus.io_reserved = false; + bdev->driver->io_mem_free(bdev, mem); + } + } +} + int ttm_mem_reg_ioremap(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem, void **virtual) { - struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type]; - unsigned long bus_offset; - unsigned long bus_size; - unsigned long bus_base; int ret; void *addr; *virtual = NULL; - ret = ttm_bo_pci_offset(bdev, mem, &bus_base, &bus_offset, &bus_size); - if (ret || bus_size == 0) + ret = ttm_mem_io_reserve(bdev, mem); + if (ret) return ret; - if (!(man->flags & TTM_MEMTYPE_FLAG_NEEDS_IOREMAP)) - addr = (void *)(((u8 *) man->io_addr) + bus_offset); - else { + if (mem->bus.addr) { + addr = mem->bus.addr; + } else { if (mem->placement & TTM_PL_FLAG_WC) - addr = ioremap_wc(bus_base + bus_offset, bus_size); + addr = ioremap_wc(mem->bus.base + mem->bus.offset, mem->bus.size); else - addr = ioremap_nocache(bus_base + bus_offset, bus_size); - if (!addr) + addr = ioremap_nocache(mem->bus.base + mem->bus.offset, mem->bus.size); + if (!addr) { + ttm_mem_io_free(bdev, mem); return -ENOMEM; + } } *virtual = addr; return 0; @@ -117,8 +149,9 @@ void ttm_mem_reg_iounmap(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem, man = &bdev->man[mem->mem_type]; - if (virtual && (man->flags & TTM_MEMTYPE_FLAG_NEEDS_IOREMAP)) + if (virtual && (man->flags & TTM_MEMTYPE_FLAG_NEEDS_IOREMAP || mem->bus.addr == NULL)) iounmap(virtual); + ttm_mem_io_free(bdev, mem); } static int ttm_copy_io_page(void *dst, void *src, unsigned long page) @@ -370,26 +403,23 @@ pgprot_t ttm_io_prot(uint32_t caching_flags, pgprot_t tmp) EXPORT_SYMBOL(ttm_io_prot); static int ttm_bo_ioremap(struct ttm_buffer_object *bo, - unsigned long bus_base, - unsigned long bus_offset, - unsigned long bus_size, + unsigned long offset, + unsigned long size, struct ttm_bo_kmap_obj *map) { - struct ttm_bo_device *bdev = bo->bdev; struct ttm_mem_reg *mem = &bo->mem; - struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type]; - if (!(man->flags & TTM_MEMTYPE_FLAG_NEEDS_IOREMAP)) { + if (bo->mem.bus.addr) { map->bo_kmap_type = ttm_bo_map_premapped; - map->virtual = (void *)(((u8 *) man->io_addr) + bus_offset); + map->virtual = (void *)(((u8 *)bo->mem.bus.addr) + offset); } else { map->bo_kmap_type = ttm_bo_map_iomap; if (mem->placement & TTM_PL_FLAG_WC) - map->virtual = ioremap_wc(bus_base + bus_offset, - bus_size); + map->virtual = ioremap_wc(bo->mem.bus.base + bo->mem.bus.offset + offset, + size); else - map->virtual = ioremap_nocache(bus_base + bus_offset, - bus_size); + map->virtual = ioremap_nocache(bo->mem.bus.base + bo->mem.bus.offset + offset, + size); } return (!map->virtual) ? -ENOMEM : 0; } @@ -442,13 +472,12 @@ int ttm_bo_kmap(struct ttm_buffer_object *bo, unsigned long start_page, unsigned long num_pages, struct ttm_bo_kmap_obj *map) { + unsigned long offset, size; int ret; - unsigned long bus_base; - unsigned long bus_offset; - unsigned long bus_size; BUG_ON(!list_empty(&bo->swap)); map->virtual = NULL; + map->bo = bo; if (num_pages > bo->num_pages) return -EINVAL; if (start_page > bo->num_pages) @@ -457,16 +486,15 @@ int ttm_bo_kmap(struct ttm_buffer_object *bo, if (num_pages > 1 && !DRM_SUSER(DRM_CURPROC)) return -EPERM; #endif - ret = ttm_bo_pci_offset(bo->bdev, &bo->mem, &bus_base, - &bus_offset, &bus_size); + ret = ttm_mem_io_reserve(bo->bdev, &bo->mem); if (ret) return ret; - if (bus_size == 0) { + if (!bo->mem.bus.is_iomem) { return ttm_bo_kmap_ttm(bo, start_page, num_pages, map); } else { - bus_offset += start_page << PAGE_SHIFT; - bus_size = num_pages << PAGE_SHIFT; - return ttm_bo_ioremap(bo, bus_base, bus_offset, bus_size, map); + offset = start_page << PAGE_SHIFT; + size = num_pages << PAGE_SHIFT; + return ttm_bo_ioremap(bo, offset, size, map); } } EXPORT_SYMBOL(ttm_bo_kmap); @@ -478,6 +506,7 @@ void ttm_bo_kunmap(struct ttm_bo_kmap_obj *map) switch (map->bo_kmap_type) { case ttm_bo_map_iomap: iounmap(map->virtual); + ttm_mem_io_free(map->bo->bdev, &map->bo->mem); break; case ttm_bo_map_vmap: vunmap(map->virtual); @@ -495,35 +524,6 @@ void ttm_bo_kunmap(struct ttm_bo_kmap_obj *map) } EXPORT_SYMBOL(ttm_bo_kunmap); -int ttm_bo_pfn_prot(struct ttm_buffer_object *bo, - unsigned long dst_offset, - unsigned long *pfn, pgprot_t *prot) -{ - struct ttm_mem_reg *mem = &bo->mem; - struct ttm_bo_device *bdev = bo->bdev; - unsigned long bus_offset; - unsigned long bus_size; - unsigned long bus_base; - int ret; - ret = ttm_bo_pci_offset(bdev, mem, &bus_base, &bus_offset, - &bus_size); - if (ret) - return -EINVAL; - if (bus_size != 0) - *pfn = (bus_base + bus_offset + dst_offset) >> PAGE_SHIFT; - else - if (!bo->ttm) - return -EINVAL; - else - *pfn = page_to_pfn(ttm_tt_get_page(bo->ttm, - dst_offset >> - PAGE_SHIFT)); - *prot = (mem->placement & TTM_PL_FLAG_CACHED) ? - PAGE_KERNEL : ttm_io_prot(mem->placement, PAGE_KERNEL); - - return 0; -} - int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo, void *sync_obj, void *sync_obj_arg, diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c index 668dbe8b8dd3..fe6cb77899f4 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_vm.c +++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c @@ -74,9 +74,6 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) struct ttm_buffer_object *bo = (struct ttm_buffer_object *) vma->vm_private_data; struct ttm_bo_device *bdev = bo->bdev; - unsigned long bus_base; - unsigned long bus_offset; - unsigned long bus_size; unsigned long page_offset; unsigned long page_last; unsigned long pfn; @@ -84,7 +81,6 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) struct page *page; int ret; int i; - bool is_iomem; unsigned long address = (unsigned long)vmf->virtual_address; int retval = VM_FAULT_NOPAGE; @@ -101,8 +97,21 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) return VM_FAULT_NOPAGE; } - if (bdev->driver->fault_reserve_notify) - bdev->driver->fault_reserve_notify(bo); + if (bdev->driver->fault_reserve_notify) { + ret = bdev->driver->fault_reserve_notify(bo); + switch (ret) { + case 0: + break; + case -EBUSY: + set_need_resched(); + case -ERESTARTSYS: + retval = VM_FAULT_NOPAGE; + goto out_unlock; + default: + retval = VM_FAULT_SIGBUS; + goto out_unlock; + } + } /* * Wait for buffer data in transit, due to a pipelined @@ -122,15 +131,12 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) spin_unlock(&bo->lock); - ret = ttm_bo_pci_offset(bdev, &bo->mem, &bus_base, &bus_offset, - &bus_size); - if (unlikely(ret != 0)) { + ret = ttm_mem_io_reserve(bdev, &bo->mem); + if (ret) { retval = VM_FAULT_SIGBUS; goto out_unlock; } - is_iomem = (bus_size != 0); - page_offset = ((address - vma->vm_start) >> PAGE_SHIFT) + bo->vm_node->start - vma->vm_pgoff; page_last = ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) + @@ -154,8 +160,7 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) * vma->vm_page_prot when the object changes caching policy, with * the correct locks held. */ - - if (is_iomem) { + if (bo->mem.bus.is_iomem) { vma->vm_page_prot = ttm_io_prot(bo->mem.placement, vma->vm_page_prot); } else { @@ -171,10 +176,8 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) */ for (i = 0; i < TTM_BO_VM_NUM_PREFAULT; ++i) { - - if (is_iomem) - pfn = ((bus_base + bus_offset) >> PAGE_SHIFT) + - page_offset; + if (bo->mem.bus.is_iomem) + pfn = ((bo->mem.bus.base + bo->mem.bus.offset) >> PAGE_SHIFT) + page_offset; else { page = ttm_tt_get_page(ttm, page_offset); if (unlikely(!page && i == 0)) { @@ -198,7 +201,6 @@ static int ttm_bo_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) retval = (ret == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS; goto out_unlock; - } address += PAGE_SIZE; @@ -221,8 +223,7 @@ static void ttm_bo_vm_open(struct vm_area_struct *vma) static void ttm_bo_vm_close(struct vm_area_struct *vma) { - struct ttm_buffer_object *bo = - (struct ttm_buffer_object *)vma->vm_private_data; + struct ttm_buffer_object *bo = (struct ttm_buffer_object *)vma->vm_private_data; ttm_bo_unref(&bo); vma->vm_private_data = NULL; diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index 8c8005ec4eaf..3e273e0b9417 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -66,6 +66,26 @@ struct ttm_placement { const uint32_t *busy_placement; }; +/** + * struct ttm_bus_placement + * + * @addr: mapped virtual address + * @base: bus base address + * @is_iomem: is this io memory ? + * @size: size in byte + * @offset: offset from the base address + * + * Structure indicating the bus placement of an object. + */ +struct ttm_bus_placement { + void *addr; + unsigned long base; + unsigned long size; + unsigned long offset; + bool is_iomem; + bool io_reserved; +}; + /** * struct ttm_mem_reg @@ -75,6 +95,7 @@ struct ttm_placement { * @num_pages: Actual size of memory region in pages. * @page_alignment: Page alignment. * @placement: Placement flags. + * @bus: Placement on io bus accessible to the CPU * * Structure indicating the placement and space resources used by a * buffer object. @@ -87,6 +108,7 @@ struct ttm_mem_reg { uint32_t page_alignment; uint32_t mem_type; uint32_t placement; + struct ttm_bus_placement bus; }; /** @@ -274,6 +296,7 @@ struct ttm_bo_kmap_obj { ttm_bo_map_kmap = 3, ttm_bo_map_premapped = 4 | TTM_BO_MAP_IOMEM_MASK, } bo_kmap_type; + struct ttm_buffer_object *bo; }; /** diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 69f70e418c2c..da39865d67d8 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -352,12 +352,21 @@ struct ttm_bo_driver { struct ttm_mem_reg *new_mem); /* notify the driver we are taking a fault on this BO * and have reserved it */ - void (*fault_reserve_notify)(struct ttm_buffer_object *bo); + int (*fault_reserve_notify)(struct ttm_buffer_object *bo); /** * notify the driver that we're about to swap out this bo */ void (*swap_notify) (struct ttm_buffer_object *bo); + + /** + * Driver callback on when mapping io memory (for bo_move_memcpy + * for instance). TTM will take care to call io_mem_free whenever + * the mapping is not use anymore. io_mem_reserve & io_mem_free + * are balanced. + */ + int (*io_mem_reserve)(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem); + void (*io_mem_free)(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem); }; /** @@ -685,6 +694,11 @@ extern int ttm_bo_pci_offset(struct ttm_bo_device *bdev, unsigned long *bus_offset, unsigned long *bus_size); +extern int ttm_mem_io_reserve(struct ttm_bo_device *bdev, + struct ttm_mem_reg *mem); +extern void ttm_mem_io_free(struct ttm_bo_device *bdev, + struct ttm_mem_reg *mem); + extern void ttm_bo_global_release(struct ttm_global_reference *ref); extern int ttm_bo_global_init(struct ttm_global_reference *ref); -- cgit v1.2.3 From 0c321c79627189204d7d0bf65ab19f5ac419abed Mon Sep 17 00:00:00 2001 From: Jerome Glisse Date: Wed, 7 Apr 2010 10:21:27 +0000 Subject: drm/ttm: remove io_ field from TTM V6 All TTM driver have been converted to new io_mem_reserve/free interface which allow driver to choose and return proper io base, offset to core TTM for ioremapping if necessary. This patch remove what is now deadcode. V2 adapt to match with change in first patch of the patchset V3 update after io_mem_reserve/io_mem_free callback balancing V4 adjust to minor cleanup V5 remove the needs ioremap flag V6 keep the ioremapping facility in TTM [airlied- squashed driver removals in here also] Signed-off-by: Jerome Glisse Reviewed-by: Thomas Hellstrom Signed-off-by: Dave Airlie --- drivers/gpu/drm/nouveau/nouveau_bo.c | 11 ----------- drivers/gpu/drm/radeon/radeon_ttm.c | 13 +------------ drivers/gpu/drm/ttm/ttm_bo.c | 22 ---------------------- drivers/gpu/drm/ttm/ttm_bo_util.c | 19 ++++--------------- drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c | 6 ------ include/drm/ttm/ttm_bo_driver.h | 12 ------------ 6 files changed, 5 insertions(+), 78 deletions(-) (limited to 'drivers/gpu/drm/ttm/ttm_bo.c') diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 288c2ecd937a..34be1924218f 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -390,13 +390,6 @@ nouveau_bo_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC; man->default_caching = TTM_PL_FLAG_WC; - - man->io_addr = NULL; - man->io_offset = drm_get_resource_start(dev, 1); - man->io_size = drm_get_resource_len(dev, 1); - if (man->io_size > nouveau_mem_fb_amount(dev)) - man->io_size = nouveau_mem_fb_amount(dev); - man->gpu_offset = dev_priv->vm_vram_base; break; case TTM_PL_TT: @@ -417,10 +410,6 @@ nouveau_bo_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, dev_priv->gart_info.type); return -EINVAL; } - - man->io_offset = dev_priv->gart_info.aper_base; - man->io_size = dev_priv->gart_info.aper_size; - man->io_addr = NULL; man->gpu_offset = dev_priv->vm_gart_base; break; default: diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index 62b4b800e0a3..91030eab22b0 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -161,21 +161,13 @@ static int radeon_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, (unsigned)type); return -EINVAL; } - man->io_offset = rdev->mc.agp_base; - man->io_size = rdev->mc.gtt_size; - man->io_addr = NULL; if (!rdev->ddev->agp->cant_use_aperture) man->flags = TTM_MEMTYPE_FLAG_MAPPABLE; man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC; man->default_caching = TTM_PL_FLAG_WC; - } else -#endif - { - man->io_offset = 0; - man->io_size = 0; - man->io_addr = NULL; } +#endif break; case TTM_PL_VRAM: /* "On-card" video ram */ @@ -184,9 +176,6 @@ static int radeon_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, TTM_MEMTYPE_FLAG_MAPPABLE; man->available_caching = TTM_PL_FLAG_UNCACHED | TTM_PL_FLAG_WC; man->default_caching = TTM_PL_FLAG_WC; - man->io_addr = NULL; - man->io_offset = rdev->mc.aper_base; - man->io_size = rdev->mc.aper_size; break; default: DRM_ERROR("Unsupported memory type %u\n", (unsigned)type); diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index b42e3fae1bd5..3b5b094b1397 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -79,8 +79,6 @@ static void ttm_mem_type_debug(struct ttm_bo_device *bdev, int mem_type) printk(KERN_ERR TTM_PFX " use_type: %d\n", man->use_type); printk(KERN_ERR TTM_PFX " flags: 0x%08X\n", man->flags); printk(KERN_ERR TTM_PFX " gpu_offset: 0x%08lX\n", man->gpu_offset); - printk(KERN_ERR TTM_PFX " io_offset: 0x%08lX\n", man->io_offset); - printk(KERN_ERR TTM_PFX " io_size: %ld\n", man->io_size); printk(KERN_ERR TTM_PFX " size: %llu\n", man->size); printk(KERN_ERR TTM_PFX " available_caching: 0x%08X\n", man->available_caching); @@ -1563,26 +1561,6 @@ bool ttm_mem_reg_is_pci(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem) return true; } -int ttm_bo_pci_offset(struct ttm_bo_device *bdev, - struct ttm_mem_reg *mem, - unsigned long *bus_base, - unsigned long *bus_offset, unsigned long *bus_size) -{ - struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type]; - - *bus_size = 0; - if (!(man->flags & TTM_MEMTYPE_FLAG_MAPPABLE)) - return -EINVAL; - - if (ttm_mem_reg_is_pci(bdev, mem)) { - *bus_offset = mem->mm_node->start << PAGE_SHIFT; - *bus_size = mem->num_pages << PAGE_SHIFT; - *bus_base = man->io_offset + (uintptr_t)man->io_addr; - } - - return 0; -} - void ttm_bo_unmap_virtual(struct ttm_buffer_object *bo) { struct ttm_bo_device *bdev = bo->bdev; diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index d58eeb5ed22b..333b401ca4c9 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -83,24 +83,13 @@ EXPORT_SYMBOL(ttm_bo_move_ttm); int ttm_mem_io_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem) { - struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type]; int ret; - if (bdev->driver->io_mem_reserve) { - if (!mem->bus.io_reserved) { - mem->bus.io_reserved = true; - ret = bdev->driver->io_mem_reserve(bdev, mem); - if (unlikely(ret != 0)) - return ret; - } - } else { - ret = ttm_bo_pci_offset(bdev, mem, &mem->bus.base, &mem->bus.offset, &mem->bus.size); + if (!mem->bus.io_reserved) { + mem->bus.io_reserved = true; + ret = bdev->driver->io_mem_reserve(bdev, mem); if (unlikely(ret != 0)) return ret; - mem->bus.addr = NULL; - if (!(man->flags & TTM_MEMTYPE_FLAG_NEEDS_IOREMAP)) - mem->bus.addr = (void *)(((u8 *)man->io_addr) + mem->bus.offset); - mem->bus.is_iomem = (mem->bus.size > 0) ? 1 : 0; } return 0; } @@ -149,7 +138,7 @@ void ttm_mem_reg_iounmap(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem, man = &bdev->man[mem->mem_type]; - if (virtual && (man->flags & TTM_MEMTYPE_FLAG_NEEDS_IOREMAP || mem->bus.addr == NULL)) + if (virtual && mem->bus.addr == NULL) iounmap(virtual); ttm_mem_io_free(bdev, mem); } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c index f3558968fdff..c4f5114aee7c 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c @@ -137,9 +137,6 @@ int vmw_invalidate_caches(struct ttm_bo_device *bdev, uint32_t flags) int vmw_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, struct ttm_mem_type_manager *man) { - struct vmw_private *dev_priv = - container_of(bdev, struct vmw_private, bdev); - switch (type) { case TTM_PL_SYSTEM: /* System memory */ @@ -151,10 +148,7 @@ int vmw_init_mem_type(struct ttm_bo_device *bdev, uint32_t type, case TTM_PL_VRAM: /* "On-card" video ram */ man->gpu_offset = 0; - man->io_offset = dev_priv->vram_start; - man->io_size = dev_priv->vram_size; man->flags = TTM_MEMTYPE_FLAG_FIXED | TTM_MEMTYPE_FLAG_MAPPABLE; - man->io_addr = NULL; man->available_caching = TTM_PL_MASK_CACHING; man->default_caching = TTM_PL_FLAG_WC; break; diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index da39865d67d8..7720b1787e23 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -176,8 +176,6 @@ struct ttm_tt { #define TTM_MEMTYPE_FLAG_FIXED (1 << 0) /* Fixed (on-card) PCI memory */ #define TTM_MEMTYPE_FLAG_MAPPABLE (1 << 1) /* Memory mappable */ -#define TTM_MEMTYPE_FLAG_NEEDS_IOREMAP (1 << 2) /* Fixed memory needs ioremap - before kernel access. */ #define TTM_MEMTYPE_FLAG_CMA (1 << 3) /* Can't map aperture */ /** @@ -189,13 +187,6 @@ struct ttm_tt { * managed by this memory type. * @gpu_offset: If used, the GPU offset of the first managed page of * fixed memory or the first managed location in an aperture. - * @io_offset: The io_offset of the first managed page of IO memory or - * the first managed location in an aperture. For TTM_MEMTYPE_FLAG_CMA - * memory, this should be set to NULL. - * @io_size: The size of a managed IO region (fixed memory or aperture). - * @io_addr: Virtual kernel address if the io region is pre-mapped. For - * TTM_MEMTYPE_FLAG_NEEDS_IOREMAP there is no pre-mapped io map and - * @io_addr should be set to NULL. * @size: Size of the managed region. * @available_caching: A mask of available caching types, TTM_PL_FLAG_XX, * as defined in ttm_placement_common.h @@ -221,9 +212,6 @@ struct ttm_mem_type_manager { bool use_type; uint32_t flags; unsigned long gpu_offset; - unsigned long io_offset; - unsigned long io_size; - void *io_addr; uint64_t size; uint32_t available_caching; uint32_t default_caching; -- cgit v1.2.3 From 7c5ee5366f79f53de2a11e73953daee6d58df124 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Mon, 26 Apr 2010 16:00:09 -0400 Subject: ttm: Provide an API for starting and stopping the delayed workqueue We want to be able to prevent the delayed workqueue from changing state while we're reclocking, so add an API to block and unblock it. Signed-off-by: Matthew Garrett Signed-off-by: Dave Airlie --- drivers/gpu/drm/ttm/ttm_bo.c | 14 ++++++++++++++ include/drm/ttm/ttm_bo_api.h | 17 +++++++++++++++++ 2 files changed, 31 insertions(+) (limited to 'drivers/gpu/drm/ttm/ttm_bo.c') diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 3b5b094b1397..4c2299299ab2 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -604,6 +604,20 @@ void ttm_bo_unref(struct ttm_buffer_object **p_bo) } EXPORT_SYMBOL(ttm_bo_unref); +int ttm_bo_lock_delayed_workqueue(struct ttm_bo_device *bdev) +{ + return cancel_delayed_work_sync(&bdev->wq); +} +EXPORT_SYMBOL(ttm_bo_lock_delayed_workqueue); + +void ttm_bo_unlock_delayed_workqueue(struct ttm_bo_device *bdev, int resched) +{ + if (resched) + schedule_delayed_work(&bdev->wq, + ((HZ / 100) < 1) ? 1 : HZ / 100); +} +EXPORT_SYMBOL(ttm_bo_unlock_delayed_workqueue); + static int ttm_bo_evict(struct ttm_buffer_object *bo, bool interruptible, bool no_wait_reserve, bool no_wait_gpu) { diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h index 3e273e0b9417..267a86c74e2e 100644 --- a/include/drm/ttm/ttm_bo_api.h +++ b/include/drm/ttm/ttm_bo_api.h @@ -361,6 +361,23 @@ extern int ttm_bo_validate(struct ttm_buffer_object *bo, */ extern void ttm_bo_unref(struct ttm_buffer_object **bo); +/** + * ttm_bo_lock_delayed_workqueue + * + * Prevent the delayed workqueue from running. + * Returns + * True if the workqueue was queued at the time + */ +extern int ttm_bo_lock_delayed_workqueue(struct ttm_bo_device *bdev); + +/** + * ttm_bo_unlock_delayed_workqueue + * + * Allows the delayed workqueue to run. + */ +extern void ttm_bo_unlock_delayed_workqueue(struct ttm_bo_device *bdev, + int resched); + /** * ttm_bo_synccpu_write_grab * -- cgit v1.2.3