Merge branch 'drm-fixes' of git://people.freedesktop.org/~airlied/linux

* 'drm-fixes' of git://people.freedesktop.org/~airlied/linux:
  drm/radeon/kms: Make GPU/CPU page size handling consistent in blit code (v2)
  drm/radeon/kms: fix typo in r100_blit_copy
  drm/radeon: Unreference GEM object outside of spinlock in page flip error path.
  drm/radeon: Don't read from CP ring write pointer registers.
  drm/ttm: request zeroed system memory pages for new TT buffer objects
This commit is contained in:
Linus Torvalds 2011-09-19 07:55:43 -07:00
commit 6d7c2b4cfa
10 changed files with 51 additions and 42 deletions

View File

@ -1404,7 +1404,8 @@ int evergreen_cp_resume(struct radeon_device *rdev)
/* Initialize the ring buffer's read and write pointers */
WREG32(CP_RB_CNTL, tmp | RB_RPTR_WR_ENA);
WREG32(CP_RB_RPTR_WR, 0);
WREG32(CP_RB_WPTR, 0);
rdev->cp.wptr = 0;
WREG32(CP_RB_WPTR, rdev->cp.wptr);
/* set the wb address wether it's enabled or not */
WREG32(CP_RB_RPTR_ADDR,
@ -1426,7 +1427,6 @@ int evergreen_cp_resume(struct radeon_device *rdev)
WREG32(CP_DEBUG, (1 << 27) | (1 << 28));
rdev->cp.rptr = RREG32(CP_RB_RPTR);
rdev->cp.wptr = RREG32(CP_RB_WPTR);
evergreen_cp_start(rdev);
rdev->cp.ready = true;
@ -3171,21 +3171,23 @@ int evergreen_suspend(struct radeon_device *rdev)
}
int evergreen_copy_blit(struct radeon_device *rdev,
uint64_t src_offset, uint64_t dst_offset,
unsigned num_pages, struct radeon_fence *fence)
uint64_t src_offset,
uint64_t dst_offset,
unsigned num_gpu_pages,
struct radeon_fence *fence)
{
int r;
mutex_lock(&rdev->r600_blit.mutex);
rdev->r600_blit.vb_ib = NULL;
r = evergreen_blit_prepare_copy(rdev, num_pages * RADEON_GPU_PAGE_SIZE);
r = evergreen_blit_prepare_copy(rdev, num_gpu_pages * RADEON_GPU_PAGE_SIZE);
if (r) {
if (rdev->r600_blit.vb_ib)
radeon_ib_free(rdev, &rdev->r600_blit.vb_ib);
mutex_unlock(&rdev->r600_blit.mutex);
return r;
}
evergreen_kms_blit_copy(rdev, src_offset, dst_offset, num_pages * RADEON_GPU_PAGE_SIZE);
evergreen_kms_blit_copy(rdev, src_offset, dst_offset, num_gpu_pages * RADEON_GPU_PAGE_SIZE);
evergreen_blit_done_copy(rdev, fence);
mutex_unlock(&rdev->r600_blit.mutex);
return 0;

View File

@ -1187,7 +1187,8 @@ int cayman_cp_resume(struct radeon_device *rdev)
/* Initialize the ring buffer's read and write pointers */
WREG32(CP_RB0_CNTL, tmp | RB_RPTR_WR_ENA);
WREG32(CP_RB0_WPTR, 0);
rdev->cp.wptr = 0;
WREG32(CP_RB0_WPTR, rdev->cp.wptr);
/* set the wb address wether it's enabled or not */
WREG32(CP_RB0_RPTR_ADDR, (rdev->wb.gpu_addr + RADEON_WB_CP_RPTR_OFFSET) & 0xFFFFFFFC);
@ -1207,7 +1208,6 @@ int cayman_cp_resume(struct radeon_device *rdev)
WREG32(CP_RB0_BASE, rdev->cp.gpu_addr >> 8);
rdev->cp.rptr = RREG32(CP_RB0_RPTR);
rdev->cp.wptr = RREG32(CP_RB0_WPTR);
/* ring1 - compute only */
/* Set ring buffer size */
@ -1220,7 +1220,8 @@ int cayman_cp_resume(struct radeon_device *rdev)
/* Initialize the ring buffer's read and write pointers */
WREG32(CP_RB1_CNTL, tmp | RB_RPTR_WR_ENA);
WREG32(CP_RB1_WPTR, 0);
rdev->cp1.wptr = 0;
WREG32(CP_RB1_WPTR, rdev->cp1.wptr);
/* set the wb address wether it's enabled or not */
WREG32(CP_RB1_RPTR_ADDR, (rdev->wb.gpu_addr + RADEON_WB_CP1_RPTR_OFFSET) & 0xFFFFFFFC);
@ -1232,7 +1233,6 @@ int cayman_cp_resume(struct radeon_device *rdev)
WREG32(CP_RB1_BASE, rdev->cp1.gpu_addr >> 8);
rdev->cp1.rptr = RREG32(CP_RB1_RPTR);
rdev->cp1.wptr = RREG32(CP_RB1_WPTR);
/* ring2 - compute only */
/* Set ring buffer size */
@ -1245,7 +1245,8 @@ int cayman_cp_resume(struct radeon_device *rdev)
/* Initialize the ring buffer's read and write pointers */
WREG32(CP_RB2_CNTL, tmp | RB_RPTR_WR_ENA);
WREG32(CP_RB2_WPTR, 0);
rdev->cp2.wptr = 0;
WREG32(CP_RB2_WPTR, rdev->cp2.wptr);
/* set the wb address wether it's enabled or not */
WREG32(CP_RB2_RPTR_ADDR, (rdev->wb.gpu_addr + RADEON_WB_CP2_RPTR_OFFSET) & 0xFFFFFFFC);
@ -1257,7 +1258,6 @@ int cayman_cp_resume(struct radeon_device *rdev)
WREG32(CP_RB2_BASE, rdev->cp2.gpu_addr >> 8);
rdev->cp2.rptr = RREG32(CP_RB2_RPTR);
rdev->cp2.wptr = RREG32(CP_RB2_WPTR);
/* start the rings */
cayman_cp_start(rdev);

View File

@ -721,11 +721,11 @@ void r100_fence_ring_emit(struct radeon_device *rdev,
int r100_copy_blit(struct radeon_device *rdev,
uint64_t src_offset,
uint64_t dst_offset,
unsigned num_pages,
unsigned num_gpu_pages,
struct radeon_fence *fence)
{
uint32_t cur_pages;
uint32_t stride_bytes = PAGE_SIZE;
uint32_t stride_bytes = RADEON_GPU_PAGE_SIZE;
uint32_t pitch;
uint32_t stride_pixels;
unsigned ndw;
@ -737,7 +737,7 @@ int r100_copy_blit(struct radeon_device *rdev,
/* radeon pitch is /64 */
pitch = stride_bytes / 64;
stride_pixels = stride_bytes / 4;
num_loops = DIV_ROUND_UP(num_pages, 8191);
num_loops = DIV_ROUND_UP(num_gpu_pages, 8191);
/* Ask for enough room for blit + flush + fence */
ndw = 64 + (10 * num_loops);
@ -746,12 +746,12 @@ int r100_copy_blit(struct radeon_device *rdev,
DRM_ERROR("radeon: moving bo (%d) asking for %u dw.\n", r, ndw);
return -EINVAL;
}
while (num_pages > 0) {
cur_pages = num_pages;
while (num_gpu_pages > 0) {
cur_pages = num_gpu_pages;
if (cur_pages > 8191) {
cur_pages = 8191;
}
num_pages -= cur_pages;
num_gpu_pages -= cur_pages;
/* pages are in Y direction - height
page width in X direction - width */
@ -773,8 +773,8 @@ int r100_copy_blit(struct radeon_device *rdev,
radeon_ring_write(rdev, (0x1fff) | (0x1fff << 16));
radeon_ring_write(rdev, 0);
radeon_ring_write(rdev, (0x1fff) | (0x1fff << 16));
radeon_ring_write(rdev, num_pages);
radeon_ring_write(rdev, num_pages);
radeon_ring_write(rdev, cur_pages);
radeon_ring_write(rdev, cur_pages);
radeon_ring_write(rdev, cur_pages | (stride_pixels << 16));
}
radeon_ring_write(rdev, PACKET0(RADEON_DSTCACHE_CTLSTAT, 0));
@ -990,7 +990,8 @@ int r100_cp_init(struct radeon_device *rdev, unsigned ring_size)
/* Force read & write ptr to 0 */
WREG32(RADEON_CP_RB_CNTL, tmp | RADEON_RB_RPTR_WR_ENA | RADEON_RB_NO_UPDATE);
WREG32(RADEON_CP_RB_RPTR_WR, 0);
WREG32(RADEON_CP_RB_WPTR, 0);
rdev->cp.wptr = 0;
WREG32(RADEON_CP_RB_WPTR, rdev->cp.wptr);
/* set the wb address whether it's enabled or not */
WREG32(R_00070C_CP_RB_RPTR_ADDR,
@ -1007,9 +1008,6 @@ int r100_cp_init(struct radeon_device *rdev, unsigned ring_size)
WREG32(RADEON_CP_RB_CNTL, tmp);
udelay(10);
rdev->cp.rptr = RREG32(RADEON_CP_RB_RPTR);
rdev->cp.wptr = RREG32(RADEON_CP_RB_WPTR);
/* protect against crazy HW on resume */
rdev->cp.wptr &= rdev->cp.ptr_mask;
/* Set cp mode to bus mastering & enable cp*/
WREG32(RADEON_CP_CSQ_MODE,
REG_SET(RADEON_INDIRECT2_START, indirect2_start) |

View File

@ -84,7 +84,7 @@ static int r200_get_vtx_size_0(uint32_t vtx_fmt_0)
int r200_copy_dma(struct radeon_device *rdev,
uint64_t src_offset,
uint64_t dst_offset,
unsigned num_pages,
unsigned num_gpu_pages,
struct radeon_fence *fence)
{
uint32_t size;
@ -93,7 +93,7 @@ int r200_copy_dma(struct radeon_device *rdev,
int r = 0;
/* radeon pitch is /64 */
size = num_pages << PAGE_SHIFT;
size = num_gpu_pages << RADEON_GPU_PAGE_SHIFT;
num_loops = DIV_ROUND_UP(size, 0x1FFFFF);
r = radeon_ring_lock(rdev, num_loops * 4 + 64);
if (r) {

View File

@ -2209,7 +2209,8 @@ int r600_cp_resume(struct radeon_device *rdev)
/* Initialize the ring buffer's read and write pointers */
WREG32(CP_RB_CNTL, tmp | RB_RPTR_WR_ENA);
WREG32(CP_RB_RPTR_WR, 0);
WREG32(CP_RB_WPTR, 0);
rdev->cp.wptr = 0;
WREG32(CP_RB_WPTR, rdev->cp.wptr);
/* set the wb address whether it's enabled or not */
WREG32(CP_RB_RPTR_ADDR,
@ -2231,7 +2232,6 @@ int r600_cp_resume(struct radeon_device *rdev)
WREG32(CP_DEBUG, (1 << 27) | (1 << 28));
rdev->cp.rptr = RREG32(CP_RB_RPTR);
rdev->cp.wptr = RREG32(CP_RB_WPTR);
r600_cp_start(rdev);
rdev->cp.ready = true;
@ -2353,21 +2353,23 @@ void r600_fence_ring_emit(struct radeon_device *rdev,
}
int r600_copy_blit(struct radeon_device *rdev,
uint64_t src_offset, uint64_t dst_offset,
unsigned num_pages, struct radeon_fence *fence)
uint64_t src_offset,
uint64_t dst_offset,
unsigned num_gpu_pages,
struct radeon_fence *fence)
{
int r;
mutex_lock(&rdev->r600_blit.mutex);
rdev->r600_blit.vb_ib = NULL;
r = r600_blit_prepare_copy(rdev, num_pages * RADEON_GPU_PAGE_SIZE);
r = r600_blit_prepare_copy(rdev, num_gpu_pages * RADEON_GPU_PAGE_SIZE);
if (r) {
if (rdev->r600_blit.vb_ib)
radeon_ib_free(rdev, &rdev->r600_blit.vb_ib);
mutex_unlock(&rdev->r600_blit.mutex);
return r;
}
r600_kms_blit_copy(rdev, src_offset, dst_offset, num_pages * RADEON_GPU_PAGE_SIZE);
r600_kms_blit_copy(rdev, src_offset, dst_offset, num_gpu_pages * RADEON_GPU_PAGE_SIZE);
r600_blit_done_copy(rdev, fence);
mutex_unlock(&rdev->r600_blit.mutex);
return 0;

View File

@ -322,6 +322,7 @@ union radeon_gart_table {
#define RADEON_GPU_PAGE_SIZE 4096
#define RADEON_GPU_PAGE_MASK (RADEON_GPU_PAGE_SIZE - 1)
#define RADEON_GPU_PAGE_SHIFT 12
struct radeon_gart {
dma_addr_t table_addr;
@ -914,17 +915,17 @@ struct radeon_asic {
int (*copy_blit)(struct radeon_device *rdev,
uint64_t src_offset,
uint64_t dst_offset,
unsigned num_pages,
unsigned num_gpu_pages,
struct radeon_fence *fence);
int (*copy_dma)(struct radeon_device *rdev,
uint64_t src_offset,
uint64_t dst_offset,
unsigned num_pages,
unsigned num_gpu_pages,
struct radeon_fence *fence);
int (*copy)(struct radeon_device *rdev,
uint64_t src_offset,
uint64_t dst_offset,
unsigned num_pages,
unsigned num_gpu_pages,
struct radeon_fence *fence);
uint32_t (*get_engine_clock)(struct radeon_device *rdev);
void (*set_engine_clock)(struct radeon_device *rdev, uint32_t eng_clock);

View File

@ -75,7 +75,7 @@ uint32_t r100_pll_rreg(struct radeon_device *rdev, uint32_t reg);
int r100_copy_blit(struct radeon_device *rdev,
uint64_t src_offset,
uint64_t dst_offset,
unsigned num_pages,
unsigned num_gpu_pages,
struct radeon_fence *fence);
int r100_set_surface_reg(struct radeon_device *rdev, int reg,
uint32_t tiling_flags, uint32_t pitch,
@ -143,7 +143,7 @@ extern void r100_post_page_flip(struct radeon_device *rdev, int crtc);
extern int r200_copy_dma(struct radeon_device *rdev,
uint64_t src_offset,
uint64_t dst_offset,
unsigned num_pages,
unsigned num_gpu_pages,
struct radeon_fence *fence);
void r200_set_safe_registers(struct radeon_device *rdev);
@ -311,7 +311,7 @@ void r600_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib);
int r600_ring_test(struct radeon_device *rdev);
int r600_copy_blit(struct radeon_device *rdev,
uint64_t src_offset, uint64_t dst_offset,
unsigned num_pages, struct radeon_fence *fence);
unsigned num_gpu_pages, struct radeon_fence *fence);
void r600_hpd_init(struct radeon_device *rdev);
void r600_hpd_fini(struct radeon_device *rdev);
bool r600_hpd_sense(struct radeon_device *rdev, enum radeon_hpd_id hpd);
@ -403,7 +403,7 @@ void evergreen_bandwidth_update(struct radeon_device *rdev);
void evergreen_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib);
int evergreen_copy_blit(struct radeon_device *rdev,
uint64_t src_offset, uint64_t dst_offset,
unsigned num_pages, struct radeon_fence *fence);
unsigned num_gpu_pages, struct radeon_fence *fence);
void evergreen_hpd_init(struct radeon_device *rdev);
void evergreen_hpd_fini(struct radeon_device *rdev);
bool evergreen_hpd_sense(struct radeon_device *rdev, enum radeon_hpd_id hpd);

View File

@ -473,8 +473,8 @@ pflip_cleanup:
spin_lock_irqsave(&dev->event_lock, flags);
radeon_crtc->unpin_work = NULL;
unlock_free:
drm_gem_object_unreference_unlocked(old_radeon_fb->obj);
spin_unlock_irqrestore(&dev->event_lock, flags);
drm_gem_object_unreference_unlocked(old_radeon_fb->obj);
radeon_fence_unref(&work->fence);
kfree(work);

View File

@ -277,7 +277,12 @@ static int radeon_move_blit(struct ttm_buffer_object *bo,
DRM_ERROR("Trying to move memory with CP turned off.\n");
return -EINVAL;
}
r = radeon_copy(rdev, old_start, new_start, new_mem->num_pages, fence);
BUILD_BUG_ON((PAGE_SIZE % RADEON_GPU_PAGE_SIZE) != 0);
r = radeon_copy(rdev, old_start, new_start,
new_mem->num_pages * (PAGE_SIZE / RADEON_GPU_PAGE_SIZE), /* GPU pages */
fence);
/* FIXME: handle copy error */
r = ttm_bo_move_accel_cleanup(bo, (void *)fence, NULL,
evict, no_wait_reserve, no_wait_gpu, new_mem);

View File

@ -394,7 +394,8 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
if (!(new_man->flags & TTM_MEMTYPE_FLAG_FIXED)) {
if (bo->ttm == NULL) {
ret = ttm_bo_add_ttm(bo, false);
bool zero = !(old_man->flags & TTM_MEMTYPE_FLAG_FIXED);
ret = ttm_bo_add_ttm(bo, zero);
if (ret)
goto out_err;
}