udl-kms: avoid division
Division is slow, so it shouldn't be done by the pixel generating code. The driver supports only 2 or 4 bytes per pixel, so we can replace division with a shift. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: Dave Airlie <airlied@redhat.com>
This commit is contained in:
parent
09a00abe3a
commit
91ba11fb7d
|
@ -112,7 +112,7 @@ udl_fb_user_fb_create(struct drm_device *dev,
|
|||
struct drm_file *file,
|
||||
const struct drm_mode_fb_cmd2 *mode_cmd);
|
||||
|
||||
int udl_render_hline(struct drm_device *dev, int bpp, struct urb **urb_ptr,
|
||||
int udl_render_hline(struct drm_device *dev, int log_bpp, struct urb **urb_ptr,
|
||||
const char *front, char **urb_buf_ptr,
|
||||
u32 byte_offset, u32 device_byte_offset, u32 byte_width,
|
||||
int *ident_ptr, int *sent_ptr);
|
||||
|
|
|
@ -90,7 +90,10 @@ int udl_handle_damage(struct udl_framebuffer *fb, int x, int y,
|
|||
int bytes_identical = 0;
|
||||
struct urb *urb;
|
||||
int aligned_x;
|
||||
int bpp = fb->base.format->cpp[0];
|
||||
int log_bpp;
|
||||
|
||||
BUG_ON(!is_power_of_2(fb->base.format->cpp[0]));
|
||||
log_bpp = __ffs(fb->base.format->cpp[0]);
|
||||
|
||||
if (!fb->active_16)
|
||||
return 0;
|
||||
|
@ -125,12 +128,12 @@ int udl_handle_damage(struct udl_framebuffer *fb, int x, int y,
|
|||
|
||||
for (i = y; i < y + height ; i++) {
|
||||
const int line_offset = fb->base.pitches[0] * i;
|
||||
const int byte_offset = line_offset + (x * bpp);
|
||||
const int dev_byte_offset = (fb->base.width * bpp * i) + (x * bpp);
|
||||
if (udl_render_hline(dev, bpp, &urb,
|
||||
const int byte_offset = line_offset + (x << log_bpp);
|
||||
const int dev_byte_offset = (fb->base.width * i + x) << log_bpp;
|
||||
if (udl_render_hline(dev, log_bpp, &urb,
|
||||
(char *) fb->obj->vmapping,
|
||||
&cmd, byte_offset, dev_byte_offset,
|
||||
width * bpp,
|
||||
width << log_bpp,
|
||||
&bytes_identical, &bytes_sent))
|
||||
goto error;
|
||||
}
|
||||
|
@ -149,7 +152,7 @@ int udl_handle_damage(struct udl_framebuffer *fb, int x, int y,
|
|||
error:
|
||||
atomic_add(bytes_sent, &udl->bytes_sent);
|
||||
atomic_add(bytes_identical, &udl->bytes_identical);
|
||||
atomic_add(width*height*bpp, &udl->bytes_rendered);
|
||||
atomic_add((width * height) << log_bpp, &udl->bytes_rendered);
|
||||
end_cycles = get_cycles();
|
||||
atomic_add(((unsigned int) ((end_cycles - start_cycles)
|
||||
>> 10)), /* Kcycles */
|
||||
|
|
|
@ -83,12 +83,12 @@ static inline u16 pixel32_to_be16(const uint32_t pixel)
|
|||
((pixel >> 8) & 0xf800));
|
||||
}
|
||||
|
||||
static inline u16 get_pixel_val16(const uint8_t *pixel, int bpp)
|
||||
static inline u16 get_pixel_val16(const uint8_t *pixel, int log_bpp)
|
||||
{
|
||||
u16 pixel_val16 = 0;
|
||||
if (bpp == 2)
|
||||
u16 pixel_val16;
|
||||
if (log_bpp == 1)
|
||||
pixel_val16 = *(const uint16_t *)pixel;
|
||||
else if (bpp == 4)
|
||||
else
|
||||
pixel_val16 = pixel32_to_be16(*(const uint32_t *)pixel);
|
||||
return pixel_val16;
|
||||
}
|
||||
|
@ -125,8 +125,9 @@ static void udl_compress_hline16(
|
|||
const u8 *const pixel_end,
|
||||
uint32_t *device_address_ptr,
|
||||
uint8_t **command_buffer_ptr,
|
||||
const uint8_t *const cmd_buffer_end, int bpp)
|
||||
const uint8_t *const cmd_buffer_end, int log_bpp)
|
||||
{
|
||||
const int bpp = 1 << log_bpp;
|
||||
const u8 *pixel = *pixel_start_ptr;
|
||||
uint32_t dev_addr = *device_address_ptr;
|
||||
uint8_t *cmd = *command_buffer_ptr;
|
||||
|
@ -153,12 +154,12 @@ static void udl_compress_hline16(
|
|||
raw_pixels_count_byte = cmd++; /* we'll know this later */
|
||||
raw_pixel_start = pixel;
|
||||
|
||||
cmd_pixel_end = pixel + min3(MAX_CMD_PIXELS + 1UL,
|
||||
(unsigned long)(pixel_end - pixel) / bpp,
|
||||
(unsigned long)(cmd_buffer_end - 1 - cmd) / 2) * bpp;
|
||||
cmd_pixel_end = pixel + (min3(MAX_CMD_PIXELS + 1UL,
|
||||
(unsigned long)(pixel_end - pixel) >> log_bpp,
|
||||
(unsigned long)(cmd_buffer_end - 1 - cmd) / 2) << log_bpp);
|
||||
|
||||
prefetch_range((void *) pixel, cmd_pixel_end - pixel);
|
||||
pixel_val16 = get_pixel_val16(pixel, bpp);
|
||||
pixel_val16 = get_pixel_val16(pixel, log_bpp);
|
||||
|
||||
while (pixel < cmd_pixel_end) {
|
||||
const u8 *const start = pixel;
|
||||
|
@ -170,7 +171,7 @@ static void udl_compress_hline16(
|
|||
pixel += bpp;
|
||||
|
||||
while (pixel < cmd_pixel_end) {
|
||||
pixel_val16 = get_pixel_val16(pixel, bpp);
|
||||
pixel_val16 = get_pixel_val16(pixel, log_bpp);
|
||||
if (pixel_val16 != repeating_pixel_val16)
|
||||
break;
|
||||
pixel += bpp;
|
||||
|
@ -179,10 +180,10 @@ static void udl_compress_hline16(
|
|||
if (unlikely(pixel > start + bpp)) {
|
||||
/* go back and fill in raw pixel count */
|
||||
*raw_pixels_count_byte = (((start -
|
||||
raw_pixel_start) / bpp) + 1) & 0xFF;
|
||||
raw_pixel_start) >> log_bpp) + 1) & 0xFF;
|
||||
|
||||
/* immediately after raw data is repeat byte */
|
||||
*cmd++ = (((pixel - start) / bpp) - 1) & 0xFF;
|
||||
*cmd++ = (((pixel - start) >> log_bpp) - 1) & 0xFF;
|
||||
|
||||
/* Then start another raw pixel span */
|
||||
raw_pixel_start = pixel;
|
||||
|
@ -192,14 +193,14 @@ static void udl_compress_hline16(
|
|||
|
||||
if (pixel > raw_pixel_start) {
|
||||
/* finalize last RAW span */
|
||||
*raw_pixels_count_byte = ((pixel-raw_pixel_start) / bpp) & 0xFF;
|
||||
*raw_pixels_count_byte = ((pixel - raw_pixel_start) >> log_bpp) & 0xFF;
|
||||
} else {
|
||||
/* undo unused byte */
|
||||
cmd--;
|
||||
}
|
||||
|
||||
*cmd_pixels_count_byte = ((pixel - cmd_pixel_start) / bpp) & 0xFF;
|
||||
dev_addr += ((pixel - cmd_pixel_start) / bpp) * 2;
|
||||
*cmd_pixels_count_byte = ((pixel - cmd_pixel_start) >> log_bpp) & 0xFF;
|
||||
dev_addr += ((pixel - cmd_pixel_start) >> log_bpp) * 2;
|
||||
}
|
||||
|
||||
if (cmd_buffer_end <= MIN_RLX_CMD_BYTES + cmd) {
|
||||
|
@ -222,19 +223,19 @@ static void udl_compress_hline16(
|
|||
* (that we can only write to, slowly, and can never read), and (optionally)
|
||||
* our shadow copy that tracks what's been sent to that hardware buffer.
|
||||
*/
|
||||
int udl_render_hline(struct drm_device *dev, int bpp, struct urb **urb_ptr,
|
||||
int udl_render_hline(struct drm_device *dev, int log_bpp, struct urb **urb_ptr,
|
||||
const char *front, char **urb_buf_ptr,
|
||||
u32 byte_offset, u32 device_byte_offset,
|
||||
u32 byte_width,
|
||||
int *ident_ptr, int *sent_ptr)
|
||||
{
|
||||
const u8 *line_start, *line_end, *next_pixel;
|
||||
u32 base16 = 0 + (device_byte_offset / bpp) * 2;
|
||||
u32 base16 = 0 + (device_byte_offset >> log_bpp) * 2;
|
||||
struct urb *urb = *urb_ptr;
|
||||
u8 *cmd = *urb_buf_ptr;
|
||||
u8 *cmd_end = (u8 *) urb->transfer_buffer + urb->transfer_buffer_length;
|
||||
|
||||
BUG_ON(!(bpp == 2 || bpp == 4));
|
||||
BUG_ON(!(log_bpp == 1 || log_bpp == 2));
|
||||
|
||||
line_start = (u8 *) (front + byte_offset);
|
||||
next_pixel = line_start;
|
||||
|
@ -244,7 +245,7 @@ int udl_render_hline(struct drm_device *dev, int bpp, struct urb **urb_ptr,
|
|||
|
||||
udl_compress_hline16(&next_pixel,
|
||||
line_end, &base16,
|
||||
(u8 **) &cmd, (u8 *) cmd_end, bpp);
|
||||
(u8 **) &cmd, (u8 *) cmd_end, log_bpp);
|
||||
|
||||
if (cmd >= cmd_end) {
|
||||
int len = cmd - (u8 *) urb->transfer_buffer;
|
||||
|
|
Loading…
Reference in New Issue