rockchip/drm: vop2: add support for gamma LUT

Add support for gamma LUT in VOP2 driver. The implementation was inspired
by one found in VOP1 driver. Blue and red channels in gamma LUT register
write were swapped with respect to how gamma LUT values are written in
VOP1. Gamma LUT port selection was added before the write of new gamma LUT
table.

If the current SoC is rk356x, check if no other CRTC has gamma LUT enabled
in atomic_check (only one video port can use gamma LUT at a time) and
disable gamma LUT before the LUT table write.

If the current SoC isn't rk356x, "seamless" gamma lut update is performed
similarly to how it was done in the case of RK3399 in VOP1[1]. In seamless
update gamma LUT disable before the write isn't necessary, check if no
other CRTC has gamma LUT enabled is also not necessary, different register
is being used to select gamma LUT port[2] and after setting DSP_LUT_EN bit,
GAMMA_UPDATE_EN bit is set[3].

Gamma size is set and drm color management is enabled for each video port's
CRTC except ones which have no associated device.

Patch was tested on RK3566 (Pinetab2). When using userspace tools
which set eg. constant color temperature no issues were noticed. When
using userspace tools which adjust eg. color temperature the slight screen
flicker is visible probably because of gamma LUT disable needed in the
case of RK356x before gamma LUT write.

Compare behaviour of eg.:
```
gammastep -O 3000
```

To eg.:
```
gammastep -l 53:23 -t 6000:3000
```

In latter case color temperature is slowly adjusted at the beginning which
causes screen to slighly flicker. Then it adjusts every few seconds which
also causes slight screen flicker.

[1] https://lists.infradead.org/pipermail/linux-rockchip/2021-October/028132.html
[2] https://lore.kernel.org/linux-rockchip/48249708-8c05-40d2-a5d8-23de960c5a77@rock-chips.com/
[3] https://github.com/radxa/kernel/blob/linux-6.1-stan-rkr1/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c#L3437

Helped-by: Daniel Stone <daniel@fooishbar.org>
Helped-by: Dragan Simic <dsimic@manjaro.org>
Helped-by: Diederik de Haas <didi.debian@cknow.org>
Helped-by: Andy Yan <andy.yan@rock-chips.com>
Signed-off-by: Piotr Zalewski <pZ010001011111@proton.me>
Reviewed-by: Andy Yan <andyshrk@163.com>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20241101185545.559090-3-pZ010001011111@proton.me

2 files changed, 191 insertions, 0 deletions

diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
index 312ca816c646..9ad025aa9ab0 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
@@ -278,6 +278,15 @@ static u32 vop2_readl(struct vop2 *vop2, u32 offset)
 	return val;
 }
 
+static u32 vop2_vp_read(struct vop2_video_port *vp, u32 offset)
+{
+	u32 val;
+
+	regmap_read(vp->vop2->map, vp->data->offset + offset, &val);
+
+	return val;
+}
+
 static void vop2_win_write(const struct vop2_win *win, unsigned int reg, u32 v)
 {
 	regmap_field_write(win->reg[reg], v);
@@ -998,6 +1007,67 @@ static void vop2_disable(struct vop2 *vop2)
 	clk_disable_unprepare(vop2->hclk);
 }
 
+static bool vop2_vp_dsp_lut_is_enabled(struct vop2_video_port *vp)
+{
+	u32 dsp_ctrl = vop2_vp_read(vp, RK3568_VP_DSP_CTRL);
+
+	return dsp_ctrl & RK3568_VP_DSP_CTRL__DSP_LUT_EN;
+}
+
+static void vop2_vp_dsp_lut_disable(struct vop2_video_port *vp)
+{
+	u32 dsp_ctrl = vop2_vp_read(vp, RK3568_VP_DSP_CTRL);
+
+	dsp_ctrl &= ~RK3568_VP_DSP_CTRL__DSP_LUT_EN;
+	vop2_vp_write(vp, RK3568_VP_DSP_CTRL, dsp_ctrl);
+}
+
+static bool vop2_vp_dsp_lut_poll_disabled(struct vop2_video_port *vp)
+{
+	u32 dsp_ctrl;
+	int ret = readx_poll_timeout(vop2_vp_dsp_lut_is_enabled, vp, dsp_ctrl,
+				!dsp_ctrl, 5, 30 * 1000);
+	if (ret) {
+		drm_err(vp->vop2->drm, "display LUT RAM enable timeout!\n");
+		return false;
+	}
+
+	return true;
+}
+
+static void vop2_vp_dsp_lut_enable(struct vop2_video_port *vp)
+{
+	u32 dsp_ctrl = vop2_vp_read(vp, RK3568_VP_DSP_CTRL);
+
+	dsp_ctrl |= RK3568_VP_DSP_CTRL__DSP_LUT_EN;
+	vop2_vp_write(vp, RK3568_VP_DSP_CTRL, dsp_ctrl);
+}
+
+static void vop2_vp_dsp_lut_update_enable(struct vop2_video_port *vp)
+{
+	u32 dsp_ctrl = vop2_vp_read(vp, RK3568_VP_DSP_CTRL);
+
+	dsp_ctrl |= RK3588_VP_DSP_CTRL__GAMMA_UPDATE_EN;
+	vop2_vp_write(vp, RK3568_VP_DSP_CTRL, dsp_ctrl);
+}
+
+static inline bool vop2_supports_seamless_gamma_lut_update(struct vop2 *vop2)
+{
+	return (vop2->data->soc_id != 3566 && vop2->data->soc_id != 3568);
+}
+
+static bool vop2_gamma_lut_in_use(struct vop2 *vop2, struct vop2_video_port *vp)
+{
+	const int nr_vps = vop2->data->nr_vps;
+	int gamma_en_vp_id;
+
+	for (gamma_en_vp_id = 0; gamma_en_vp_id < nr_vps; gamma_en_vp_id++)
+		if (vop2_vp_dsp_lut_is_enabled(&vop2->vps[gamma_en_vp_id]))
+			break;
+
+	return gamma_en_vp_id != nr_vps && gamma_en_vp_id != vp->id;
+}
+
 static void vop2_crtc_atomic_disable(struct drm_crtc *crtc,
 				     struct drm_atomic_state *state)
 {
@@ -1484,6 +1554,77 @@ static bool vop2_crtc_mode_fixup(struct drm_crtc *crtc,
 	return true;
 }
 
+static void vop2_crtc_write_gamma_lut(struct vop2 *vop2, struct drm_crtc *crtc)
+{
+	const struct vop2_video_port *vp = to_vop2_video_port(crtc);
+	const struct vop2_video_port_data *vp_data = &vop2->data->vp[vp->id];
+	struct drm_color_lut *lut = crtc->state->gamma_lut->data;
+	unsigned int i, bpc = ilog2(vp_data->gamma_lut_len);
+	u32 word;
+
+	for (i = 0; i < crtc->gamma_size; i++) {
+		word = (drm_color_lut_extract(lut[i].blue, bpc) << (2 * bpc)) |
+		    (drm_color_lut_extract(lut[i].green, bpc) << bpc) |
+		    drm_color_lut_extract(lut[i].red, bpc);
+
+		writel(word, vop2->lut_regs + i * 4);
+	}
+}
+
+static void vop2_crtc_atomic_set_gamma_seamless(struct vop2 *vop2,
+						struct vop2_video_port *vp,
+						struct drm_crtc *crtc)
+{
+	vop2_writel(vop2, RK3568_LUT_PORT_SEL,
+		    FIELD_PREP(RK3588_LUT_PORT_SEL__GAMMA_AHB_WRITE_SEL, vp->id));
+	vop2_vp_dsp_lut_enable(vp);
+	vop2_crtc_write_gamma_lut(vop2, crtc);
+	vop2_vp_dsp_lut_update_enable(vp);
+}
+
+static void vop2_crtc_atomic_set_gamma_rk356x(struct vop2 *vop2,
+					      struct vop2_video_port *vp,
+					      struct drm_crtc *crtc)
+{
+	vop2_vp_dsp_lut_disable(vp);
+	vop2_cfg_done(vp);
+	if (!vop2_vp_dsp_lut_poll_disabled(vp))
+		return;
+
+	vop2_writel(vop2, RK3568_LUT_PORT_SEL, vp->id);
+	vop2_crtc_write_gamma_lut(vop2, crtc);
+	vop2_vp_dsp_lut_enable(vp);
+}
+
+static void vop2_crtc_atomic_try_set_gamma(struct vop2 *vop2,
+					   struct vop2_video_port *vp,
+					   struct drm_crtc *crtc,
+					   struct drm_crtc_state *crtc_state)
+{
+	if (!vop2->lut_regs || !crtc_state->color_mgmt_changed)
+		return;
+
+	if (!crtc_state->gamma_lut) {
+		vop2_vp_dsp_lut_disable(vp);
+		return;
+	}
+
+	if (vop2_supports_seamless_gamma_lut_update(vop2))
+		vop2_crtc_atomic_set_gamma_seamless(vop2, vp, crtc);
+	else
+		vop2_crtc_atomic_set_gamma_rk356x(vop2, vp, crtc);
+}
+
+static inline void vop2_crtc_atomic_try_set_gamma_locked(struct vop2 *vop2,
+							 struct vop2_video_port *vp,
+							 struct drm_crtc *crtc,
+							 struct drm_crtc_state *crtc_state)
+{
+	vop2_lock(vop2);
+	vop2_crtc_atomic_try_set_gamma(vop2, vp, crtc, crtc_state);
+	vop2_unlock(vop2);
+}
+
 static void vop2_dither_setup(struct drm_crtc *crtc, u32 *dsp_ctrl)
 {
 	struct rockchip_crtc_state *vcstate = to_rockchip_crtc_state(crtc->state);
@@ -2059,11 +2200,40 @@ static void vop2_crtc_atomic_enable(struct drm_crtc *crtc,
 
 	vop2_vp_write(vp, RK3568_VP_DSP_CTRL, dsp_ctrl);
 
+	vop2_crtc_atomic_try_set_gamma(vop2, vp, crtc, crtc_state);
+
 	drm_crtc_vblank_on(crtc);
 
 	vop2_unlock(vop2);
 }
 
+static int vop2_crtc_atomic_check_gamma(struct vop2_video_port *vp,
+					struct drm_crtc *crtc,
+					struct drm_atomic_state *state,
+					struct drm_crtc_state *crtc_state)
+{
+	struct vop2 *vop2 = vp->vop2;
+	unsigned int len;
+
+	if (!vp->vop2->lut_regs || !crtc_state->color_mgmt_changed ||
+	    !crtc_state->gamma_lut)
+		return 0;
+
+	len = drm_color_lut_size(crtc_state->gamma_lut);
+	if (len != crtc->gamma_size) {
+		drm_dbg(vop2->drm, "Invalid LUT size; got %d, expected %d\n",
+			len, crtc->gamma_size);
+		return -EINVAL;
+	}
+
+	if (!vop2_supports_seamless_gamma_lut_update(vop2) && vop2_gamma_lut_in_use(vop2, vp)) {
+		drm_info(vop2->drm, "Gamma LUT can be enabled for only one CRTC at a time\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int vop2_crtc_atomic_check(struct drm_crtc *crtc,
 				  struct drm_atomic_state *state)
 {
@@ -2071,6 +2241,11 @@ static int vop2_crtc_atomic_check(struct drm_crtc *crtc,
 	struct drm_plane *plane;
 	int nplanes = 0;
 	struct drm_crtc_state *crtc_state = drm_atomic_get_new_crtc_state(state, crtc);
+	int ret;
+
+	ret = vop2_crtc_atomic_check_gamma(vp, crtc, state, crtc_state);
+	if (ret)
+		return ret;
 
 	drm_atomic_crtc_state_for_each_plane(plane, crtc_state)
 		nplanes++;
@@ -2489,7 +2664,13 @@ static void vop2_crtc_atomic_begin(struct drm_crtc *crtc,
 static void vop2_crtc_atomic_flush(struct drm_crtc *crtc,
 				   struct drm_atomic_state *state)
 {
+	struct drm_crtc_state *crtc_state = drm_atomic_get_new_crtc_state(state, crtc);
 	struct vop2_video_port *vp = to_vop2_video_port(crtc);
+	struct vop2 *vop2 = vp->vop2;
+
+	/* In case of modeset, gamma lut update already happened in atomic enable */
+	if (!drm_atomic_crtc_needs_modeset(crtc_state))
+		vop2_crtc_atomic_try_set_gamma_locked(vop2, vp, crtc, crtc_state);
 
 	vop2_post_config(crtc);
 
@@ -2792,7 +2973,12 @@ static int vop2_create_crtcs(struct vop2 *vop2)
 		}
 
 		drm_crtc_helper_add(&vp->crtc, &vop2_crtc_helper_funcs);
+		if (vop2->lut_regs) {
+			const struct vop2_video_port_data *vp_data = &vop2_data->vp[vp->id];
 
+			drm_mode_crtc_set_gamma_size(&vp->crtc, vp_data->gamma_lut_len);
+			drm_crtc_enable_color_mgmt(&vp->crtc, 0, false, vp_data->gamma_lut_len);
+		}
 		init_completion(&vp->dsp_hold_completion);
 	}
 
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.h b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.h
index 615a16196aff..510dda6f9092 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.h
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.h
@@ -394,6 +394,7 @@ enum dst_factor_mode {
 #define RK3568_REG_CFG_DONE__GLB_CFG_DONE_EN		BIT(15)
 
 #define RK3568_VP_DSP_CTRL__STANDBY			BIT(31)
+#define RK3568_VP_DSP_CTRL__DSP_LUT_EN			BIT(28)
 #define RK3568_VP_DSP_CTRL__DITHER_DOWN_MODE		BIT(20)
 #define RK3568_VP_DSP_CTRL__DITHER_DOWN_SEL		GENMASK(19, 18)
 #define RK3568_VP_DSP_CTRL__DITHER_DOWN_EN		BIT(17)
@@ -408,6 +409,8 @@ enum dst_factor_mode {
 #define RK3568_VP_DSP_CTRL__CORE_DCLK_DIV		BIT(4)
 #define RK3568_VP_DSP_CTRL__OUT_MODE			GENMASK(3, 0)
 
+#define RK3588_VP_DSP_CTRL__GAMMA_UPDATE_EN		BIT(22)
+
 #define RK3588_VP_CLK_CTRL__DCLK_OUT_DIV		GENMASK(3, 2)
 #define RK3588_VP_CLK_CTRL__DCLK_CORE_DIV		GENMASK(1, 0)
 
@@ -460,6 +463,8 @@ enum dst_factor_mode {
 #define RK3588_DSP_IF_POL__DP1_PIN_POL			GENMASK(14, 12)
 #define RK3588_DSP_IF_POL__DP0_PIN_POL			GENMASK(10, 8)
 
+#define RK3588_LUT_PORT_SEL__GAMMA_AHB_WRITE_SEL	GENMASK(13, 12)
+
 #define RK3568_VP0_MIPI_CTRL__DCLK_DIV2_PHASE_LOCK	BIT(5)
 #define RK3568_VP0_MIPI_CTRL__DCLK_DIV2			BIT(4)