From: Ville Syrjälä ville.syrjala@linux.intel.com
This thing can get called several thousand times per LUT so seems like we want to inline it to: - avoid the function call overhead - allow constant folding
A quick synthetic test (w/o any hardware interaction) with a ridiculously large LUT size shows about 50% reduction in runtime on my HSW and BSW boxes. Slightly less with more reasonable LUT size but still easily measurable in tens of microseconds.
Signed-off-by: Ville Syrjälä ville.syrjala@linux.intel.com --- drivers/gpu/drm/drm_color_mgmt.c | 24 ------------------------ include/drm/drm_color_mgmt.h | 23 ++++++++++++++++++++++- 2 files changed, 22 insertions(+), 25 deletions(-)
diff --git a/drivers/gpu/drm/drm_color_mgmt.c b/drivers/gpu/drm/drm_color_mgmt.c index 4ce5c6d8de99..19c5f635992a 100644 --- a/drivers/gpu/drm/drm_color_mgmt.c +++ b/drivers/gpu/drm/drm_color_mgmt.c @@ -108,30 +108,6 @@ * standard enum values supported by the DRM plane. */
-/** - * drm_color_lut_extract - clamp and round LUT entries - * @user_input: input value - * @bit_precision: number of bits the hw LUT supports - * - * Extract a degamma/gamma LUT value provided by user (in the form of - * &drm_color_lut entries) and round it to the precision supported by the - * hardware. - */ -uint32_t drm_color_lut_extract(uint32_t user_input, uint32_t bit_precision) -{ - uint32_t val = user_input; - uint32_t max = 0xffff >> (16 - bit_precision); - - /* Round only if we're not using full precision. */ - if (bit_precision < 16) { - val += 1UL << (16 - bit_precision - 1); - val >>= 16 - bit_precision; - } - - return clamp_val(val, 0, max); -} -EXPORT_SYMBOL(drm_color_lut_extract); - /** * drm_crtc_enable_color_mgmt - enable color management properties * @crtc: DRM CRTC diff --git a/include/drm/drm_color_mgmt.h b/include/drm/drm_color_mgmt.h index d1c662d92ab7..069b21d61871 100644 --- a/include/drm/drm_color_mgmt.h +++ b/include/drm/drm_color_mgmt.h @@ -29,7 +29,28 @@ struct drm_crtc; struct drm_plane;
-uint32_t drm_color_lut_extract(uint32_t user_input, uint32_t bit_precision); +/** + * drm_color_lut_extract - clamp and round LUT entries + * @user_input: input value + * @bit_precision: number of bits the hw LUT supports + * + * Extract a degamma/gamma LUT value provided by user (in the form of + * &drm_color_lut entries) and round it to the precision supported by the + * hardware. + */ +static inline u32 drm_color_lut_extract(u32 user_input, int bit_precision) +{ + u32 val = user_input; + u32 max = 0xffff >> (16 - bit_precision); + + /* Round only if we're not using full precision. */ + if (bit_precision < 16) { + val += 1UL << (16 - bit_precision - 1); + val >>= 16 - bit_precision; + } + + return clamp_val(val, 0, max); +}
void drm_crtc_enable_color_mgmt(struct drm_crtc *crtc, uint degamma_lut_size,