#include "nouveau_drv.h"
#include "nouveau_dma.h"
+#include <linux/log2.h>
+#include <linux/slab.h>
+
static void
nouveau_bo_del_ttm(struct ttm_buffer_object *bo)
{
/*
* Some of the tile_flags have a periodic structure of N*4096 bytes,
- * align to to that as well as the page size. Overallocate memory to
- * avoid corruption of other buffer objects.
+ * align to to that as well as the page size. Align the size to the
+ * appropriate boundaries. This does imply that sizes are rounded up
+ * 3-7 pages, so be aware of this and do not waste memory by allocating
+ * many small buffers.
*/
if (dev_priv->card_type == NV_50) {
+ uint32_t block_size = dev_priv->vram_size >> 15;
+ int i;
+
switch (tile_flags) {
case 0x1800:
case 0x2800:
case 0x4800:
case 0x7a00:
- if (dev_priv->chipset >= 0xA0) {
- /* This is based on high end cards with 448 bits
- * memory bus, could be different elsewhere.*/
- *size += 6 * 28672;
- /* 8 * 28672 is the actual alignment requirement
- * but we must also align to page size. */
- *align = 2 * 8 * 28672;
- } else if (dev_priv->chipset >= 0x90) {
- *size += 3 * 16384;
- *align = 12 * 16384;
+ if (is_power_of_2(block_size)) {
+ for (i = 1; i < 10; i++) {
+ *align = 12 * i * block_size;
+ if (!(*align % 65536))
+ break;
+ }
} else {
- *size += 3 * 8192;
- /* 12 * 8192 is the actual alignment requirement
- * but we must also align to page size. */
- *align = 2 * 12 * 8192;
+ for (i = 1; i < 10; i++) {
+ *align = 8 * i * block_size;
+ if (!(*align % 65536))
+ break;
+ }
}
+ *size = roundup(*size, *align);
break;
default:
break;
}
}
- *size = ALIGN(*size, PAGE_SIZE);
+ /* ALIGN works only on powers of two. */
+ *size = roundup(*size, PAGE_SIZE);
if (dev_priv->card_type == NV_50) {
- *size = ALIGN(*size, 65536);
+ *size = roundup(*size, 65536);
*align = max(65536, *align);
}
}
{
struct drm_nouveau_private *dev_priv = dev->dev_private;
struct nouveau_bo *nvbo;
- int ret, n = 0;
+ int ret = 0;
nvbo = kzalloc(sizeof(struct nouveau_bo), GFP_KERNEL);
if (!nvbo)
nouveau_bo_fixup_align(dev, tile_mode, tile_flags, &align, &size);
align >>= PAGE_SHIFT;
- if (flags & TTM_PL_FLAG_VRAM)
- nvbo->placements[n++] = TTM_PL_FLAG_VRAM | TTM_PL_MASK_CACHING;
- if (flags & TTM_PL_FLAG_TT)
- nvbo->placements[n++] = TTM_PL_FLAG_TT | TTM_PL_MASK_CACHING;
nvbo->placement.fpfn = 0;
nvbo->placement.lpfn = mappable ? dev_priv->fb_mappable_pages : 0;
- nvbo->placement.placement = nvbo->placements;
- nvbo->placement.busy_placement = nvbo->placements;
- nvbo->placement.num_placement = n;
- nvbo->placement.num_busy_placement = n;
+ nouveau_bo_placement_set(nvbo, flags, 0);
nvbo->channel = chan;
- nouveau_bo_placement_set(nvbo, flags);
ret = ttm_bo_init(&dev_priv->ttm.bdev, &nvbo->bo, size,
ttm_bo_type_device, &nvbo->placement, align, 0,
false, NULL, size, nouveau_bo_del_ttm);
return 0;
}
+static void
+set_placement_list(uint32_t *pl, unsigned *n, uint32_t type, uint32_t flags)
+{
+ *n = 0;
+
+ if (type & TTM_PL_FLAG_VRAM)
+ pl[(*n)++] = TTM_PL_FLAG_VRAM | flags;
+ if (type & TTM_PL_FLAG_TT)
+ pl[(*n)++] = TTM_PL_FLAG_TT | flags;
+ if (type & TTM_PL_FLAG_SYSTEM)
+ pl[(*n)++] = TTM_PL_FLAG_SYSTEM | flags;
+}
+
void
-nouveau_bo_placement_set(struct nouveau_bo *nvbo, uint32_t memtype)
+nouveau_bo_placement_set(struct nouveau_bo *nvbo, uint32_t type, uint32_t busy)
{
- int n = 0;
-
- if (memtype & TTM_PL_FLAG_VRAM)
- nvbo->placements[n++] = TTM_PL_FLAG_VRAM | TTM_PL_MASK_CACHING;
- if (memtype & TTM_PL_FLAG_TT)
- nvbo->placements[n++] = TTM_PL_FLAG_TT | TTM_PL_MASK_CACHING;
- if (memtype & TTM_PL_FLAG_SYSTEM)
- nvbo->placements[n++] = TTM_PL_FLAG_SYSTEM | TTM_PL_MASK_CACHING;
- nvbo->placement.placement = nvbo->placements;
- nvbo->placement.busy_placement = nvbo->placements;
- nvbo->placement.num_placement = n;
- nvbo->placement.num_busy_placement = n;
-
- if (nvbo->pin_refcnt) {
- while (n--)
- nvbo->placements[n] |= TTM_PL_FLAG_NO_EVICT;
- }
+ struct ttm_placement *pl = &nvbo->placement;
+ uint32_t flags = TTM_PL_MASK_CACHING |
+ (nvbo->pin_refcnt ? TTM_PL_FLAG_NO_EVICT : 0);
+
+ pl->placement = nvbo->placements;
+ set_placement_list(nvbo->placements, &pl->num_placement,
+ type, flags);
+
+ pl->busy_placement = nvbo->busy_placements;
+ set_placement_list(nvbo->busy_placements, &pl->num_busy_placement,
+ type | busy, flags);
}
int
{
struct drm_nouveau_private *dev_priv = nouveau_bdev(nvbo->bo.bdev);
struct ttm_buffer_object *bo = &nvbo->bo;
- int ret, i;
+ int ret;
if (nvbo->pin_refcnt && !(memtype & (1 << bo->mem.mem_type))) {
NV_ERROR(nouveau_bdev(bo->bdev)->dev,
if (ret)
goto out;
- nouveau_bo_placement_set(nvbo, memtype);
- for (i = 0; i < nvbo->placement.num_placement; i++)
- nvbo->placements[i] |= TTM_PL_FLAG_NO_EVICT;
+ nouveau_bo_placement_set(nvbo, memtype, 0);
ret = ttm_bo_validate(bo, &nvbo->placement, false, false);
if (ret == 0) {
{
struct drm_nouveau_private *dev_priv = nouveau_bdev(nvbo->bo.bdev);
struct ttm_buffer_object *bo = &nvbo->bo;
- int ret, i;
+ int ret;
if (--nvbo->pin_refcnt)
return 0;
if (ret)
return ret;
- for (i = 0; i < nvbo->placement.num_placement; i++)
- nvbo->placements[i] &= ~TTM_PL_FLAG_NO_EVICT;
+ nouveau_bo_placement_set(nvbo, bo->mem.placement, 0);
ret = ttm_bo_validate(bo, &nvbo->placement, false, false);
if (ret == 0) {
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);
+ if (man->io_size > dev_priv->vram_size)
+ man->io_size = dev_priv->vram_size;
man->gpu_offset = dev_priv->vm_vram_base;
break;
switch (bo->mem.mem_type) {
case TTM_PL_VRAM:
- nouveau_bo_placement_set(nvbo, TTM_PL_FLAG_TT |
+ nouveau_bo_placement_set(nvbo, TTM_PL_FLAG_TT,
TTM_PL_FLAG_SYSTEM);
break;
default:
- nouveau_bo_placement_set(nvbo, TTM_PL_FLAG_SYSTEM);
+ nouveau_bo_placement_set(nvbo, TTM_PL_FLAG_SYSTEM, 0);
break;
}
ret = ttm_bo_move_accel_cleanup(&nvbo->bo, fence, NULL,
evict, no_wait, new_mem);
+ if (nvbo->channel && nvbo->channel != chan)
+ ret = nouveau_fence_wait(fence, NULL, false, false);
nouveau_fence_unref((void *)&fence);
return ret;
}
placement.fpfn = placement.lpfn = 0;
placement.num_placement = placement.num_busy_placement = 1;
- placement.placement = &placement_memtype;
+ placement.placement = placement.busy_placement = &placement_memtype;
tmp_mem = *new_mem;
tmp_mem.mm_node = NULL;
placement.fpfn = placement.lpfn = 0;
placement.num_placement = placement.num_busy_placement = 1;
- placement.placement = &placement_memtype;
+ placement.placement = placement.busy_placement = &placement_memtype;
tmp_mem = *new_mem;
tmp_mem.mm_node = NULL;
if (ret)
goto out;
- ret = nouveau_bo_move_m2mf(bo, true, intr, no_wait, new_mem);
+ ret = nouveau_bo_move_m2mf(bo, evict, intr, no_wait, new_mem);
if (ret)
goto out;