drm: Inline drm_color_lut_extract()

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.

v2: Include drm_color_mgmt.h in the .rst (Daniel)

Cc: Daniel Vetter <daniel@ffwll.ch>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191108135654.12907-1-ville.syrjala@linux.intel.com

1 files changed, 23 insertions, 1 deletions

diff --git a/include/drm/drm_color_mgmt.h b/include/drm/drm_color_mgmt.h
index 997a42ab29f5..81c298488b0c 100644
--- a/include/drm/drm_color_mgmt.h
+++ b/include/drm/drm_color_mgmt.h
@@ -29,7 +29,29 @@
 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);
+}
+
 u64 drm_color_ctm_s31_32_to_qm_n(u64 user_input, u32 m, u32 n);
 
 void drm_crtc_enable_color_mgmt(struct drm_crtc *crtc,