2024-03-22 05:29:28

by Shawn Sung (宋孝謙)

[permalink] [raw]
Subject: [PATCH v6 00/14] Support IGT in display driver

From: Hsiao Chien Sung <[email protected]>

This series is based on [email protected].

This series adds support for running IGT (Intel GPU Tool) tests
with MediaTek display driver. The following changes will be
applied:

1. Add a new API for creating GCE thread loop to retrieve CRCs
from the hardware component
2. Support hardware CRC calculation in both VDOSYS0 and VDOSYS1
3. Support alpha blending in both VDOSYS0 and VDOSYS1

Changes in v6:
- Use drm_vblank_work to deffer the CRC work into bottom halves
- Separate the patches for "Premultiplied" and "None" alpha blending

Changes in v5:
- Add more descriptions to the codes
- Add DRM mode configs to the driver data
- Squash and rearrange the commits

Changes in v4:
- Separate the patch into smaller ones
- Change the title of some patches
- Revert the changes that are not related to the series

Changes in v3:
- Modify the dt-binding document of Mediatek OVL
- Set DRM mode configs accroding to the hardware capabilities
- Replace cmdq_pkt_jump_absolute() with cmdq_pkt_jump()

Changes in v2:
- Simplify CMDQ by adding commands that are currently used only
- Integrate CRC related codes into new APIs for Mixer and OVL to reuse
- Add CPU version CRC retrieval when CMDQ is disabled

Hsiao Chien Sung (14):
soc: mediatek: Disable 9-bit alpha in ETHDR
drm/mediatek: Add OVL compatible name for MT8195
drm/mediatek: Add missing plane settings when async update
drm/mediatek: Add DRM_MODE_ROTATE_0 to rotation property
drm/mediatek: Set DRM mode configs accordingly
drm/mediatek: Turn off the layers with zero width or height
drm/mediatek: Support alpha blending in display driver
drm/mediatek: Support "Pre-multiplied" alpha blending in OVL
drm/mediatek: Support "Pre-multiplied" alpha blending in Mixer
drm/mediatek: Support "None" alpha blending in OVL
drm/mediatek: Support "None" alpha blending in Mixer
drm/mediatek: Support CRC in display driver
drm/mediatek: Support CRC in OVL
drm/mediatek: Support CRC in OVL adaptor

drivers/gpu/drm/mediatek/mtk_crtc.c | 260 +++++++++++++++
drivers/gpu/drm/mediatek/mtk_crtc.h | 38 +++
drivers/gpu/drm/mediatek/mtk_ddp_comp.c | 6 +
drivers/gpu/drm/mediatek/mtk_ddp_comp.h | 9 +-
drivers/gpu/drm/mediatek/mtk_disp_drv.h | 6 +
drivers/gpu/drm/mediatek/mtk_disp_ovl.c | 304 ++++++++++++++++--
.../gpu/drm/mediatek/mtk_disp_ovl_adaptor.c | 23 +-
drivers/gpu/drm/mediatek/mtk_drm_drv.c | 24 ++
drivers/gpu/drm/mediatek/mtk_drm_drv.h | 3 +
drivers/gpu/drm/mediatek/mtk_ethdr.c | 94 +++++-
drivers/gpu/drm/mediatek/mtk_ethdr.h | 5 +
drivers/gpu/drm/mediatek/mtk_plane.c | 15 +-
drivers/soc/mediatek/mtk-mmsys.c | 1 +
13 files changed, 744 insertions(+), 44 deletions(-)

--
2.18.0



2024-03-22 05:30:05

by Shawn Sung (宋孝謙)

[permalink] [raw]
Subject: [PATCH v6 09/14] drm/mediatek: Support "Pre-multiplied" alpha blending in Mixer

From: Hsiao Chien Sung <[email protected]>

Support "Pre-multiplied" blend mode on MediaTek's chips.
Before this patch, only the "Coverage" mode is supported.

Please refer to the description of the commit
"drm/mediatek: Support alpha blending in display driver"
for more information.

Signed-off-by: Hsiao Chien Sung <[email protected]>
---
drivers/gpu/drm/mediatek/mtk_ethdr.c | 25 ++++++++++++++++++-------
1 file changed, 18 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_ethdr.c b/drivers/gpu/drm/mediatek/mtk_ethdr.c
index 6bf398850e85f..4b12ca285e84b 100644
--- a/drivers/gpu/drm/mediatek/mtk_ethdr.c
+++ b/drivers/gpu/drm/mediatek/mtk_ethdr.c
@@ -5,6 +5,7 @@

#include <drm/drm_fourcc.h>
#include <drm/drm_framebuffer.h>
+#include <drm/drm_blend.h>
#include <linux/clk.h>
#include <linux/component.h>
#include <linux/of.h>
@@ -35,6 +36,7 @@
#define MIX_SRC_L0_EN BIT(0)
#define MIX_L_SRC_CON(n) (0x28 + 0x18 * (n))
#define NON_PREMULTI_SOURCE (2 << 12)
+#define PREMULTI_SOURCE (3 << 12)
#define MIX_L_SRC_SIZE(n) (0x30 + 0x18 * (n))
#define MIX_L_SRC_OFFSET(n) (0x34 + 0x18 * (n))
#define MIX_FUNC_DCM0 0x120
@@ -153,7 +155,8 @@ void mtk_ethdr_layer_config(struct device *dev, unsigned int idx,
struct mtk_plane_pending_state *pending = &state->pending;
unsigned int offset = (pending->x & 1) << 31 | pending->y << 16 | pending->x;
unsigned int align_width = ALIGN_DOWN(pending->width, 2);
- unsigned int alpha_con = 0;
+ unsigned int mix_con = NON_PREMULTI_SOURCE;
+ bool replace_src_a = false;

dev_dbg(dev, "%s+ idx:%d", __func__, idx);

@@ -170,19 +173,27 @@ void mtk_ethdr_layer_config(struct device *dev, unsigned int idx,
return;
}

- if (state->base.fb && state->base.fb->format->has_alpha)
- alpha_con = MIXER_ALPHA_AEN | MIXER_ALPHA;
+ mix_con |= MIXER_ALPHA_AEN | (state->base.alpha & MIXER_ALPHA);

- mtk_mmsys_mixer_in_config(priv->mmsys_dev, idx + 1, alpha_con ? false : true,
- DEFAULT_9BIT_ALPHA,
+ if (state->base.pixel_blend_mode != DRM_MODE_BLEND_COVERAGE)
+ mix_con |= PREMULTI_SOURCE;
+
+ if (state->base.fb && !state->base.fb->format->has_alpha) {
+ /*
+ * Mixer doesn't support CONST_BLD mode,
+ * use a trick to make the output equivalent
+ */
+ replace_src_a = true;
+ }
+
+ mtk_mmsys_mixer_in_config(priv->mmsys_dev, idx + 1, replace_src_a, MIXER_ALPHA,
pending->x & 1 ? MIXER_INX_MODE_EVEN_EXTEND :
MIXER_INX_MODE_BYPASS, align_width / 2 - 1, cmdq_pkt);

mtk_ddp_write(cmdq_pkt, pending->height << 16 | align_width, &mixer->cmdq_base,
mixer->regs, MIX_L_SRC_SIZE(idx));
mtk_ddp_write(cmdq_pkt, offset, &mixer->cmdq_base, mixer->regs, MIX_L_SRC_OFFSET(idx));
- mtk_ddp_write_mask(cmdq_pkt, alpha_con, &mixer->cmdq_base, mixer->regs, MIX_L_SRC_CON(idx),
- 0x1ff);
+ mtk_ddp_write(cmdq_pkt, mix_con, &mixer->cmdq_base, mixer->regs, MIX_L_SRC_CON(idx));
mtk_ddp_write_mask(cmdq_pkt, BIT(idx), &mixer->cmdq_base, mixer->regs, MIX_SRC_CON,
BIT(idx));
}
--
2.18.0


2024-03-22 05:30:12

by Shawn Sung (宋孝謙)

[permalink] [raw]
Subject: [PATCH v6 14/14] drm/mediatek: Support CRC in OVL adaptor

From: Hsiao Chien Sung <[email protected]>

We choose Mixer as CRC generator in OVL adaptor since
its frame done event will trigger vblanks, we can know
when is safe to retrieve CRC of the frame.

In OVL adaptor, there's no image procession after Mixer,
unlike the OVL in VDOSYS0, Mixer's CRC will include all
the effects that are applied to the frame.

Signed-off-by: Hsiao Chien Sung <[email protected]>
---
drivers/gpu/drm/mediatek/mtk_ddp_comp.c | 3 +
drivers/gpu/drm/mediatek/mtk_disp_drv.h | 3 +
.../gpu/drm/mediatek/mtk_disp_ovl_adaptor.c | 21 +++++++
drivers/gpu/drm/mediatek/mtk_ethdr.c | 61 +++++++++++++++++++
drivers/gpu/drm/mediatek/mtk_ethdr.h | 5 ++
5 files changed, 93 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_ddp_comp.c
index cb71effda9c2a..8aab373ce67c9 100644
--- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.c
@@ -406,6 +406,9 @@ static const struct mtk_ddp_comp_funcs ddp_ovl_adaptor = {
.clk_enable = mtk_ovl_adaptor_clk_enable,
.clk_disable = mtk_ovl_adaptor_clk_disable,
.config = mtk_ovl_adaptor_config,
+ .crc_cnt = mtk_ovl_adaptor_crc_cnt,
+ .crc_entry = mtk_ovl_adaptor_crc_entry,
+ .crc_read = mtk_ovl_adaptor_crc_read,
.start = mtk_ovl_adaptor_start,
.stop = mtk_ovl_adaptor_stop,
.layer_nr = mtk_ovl_adaptor_layer_nr,
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_drv.h b/drivers/gpu/drm/mediatek/mtk_disp_drv.h
index c476056a5cbb5..24af08b1c86d6 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_drv.h
+++ b/drivers/gpu/drm/mediatek/mtk_disp_drv.h
@@ -138,6 +138,9 @@ const u32 *mtk_ovl_adaptor_get_formats(struct device *dev);
size_t mtk_ovl_adaptor_get_num_formats(struct device *dev);
enum drm_mode_status mtk_ovl_adaptor_mode_valid(struct device *dev,
const struct drm_display_mode *mode);
+size_t mtk_ovl_adaptor_crc_cnt(struct device *dev);
+u32 *mtk_ovl_adaptor_crc_entry(struct device *dev);
+void mtk_ovl_adaptor_crc_read(struct device *dev);

void mtk_rdma_bypass_shadow(struct device *dev);
int mtk_rdma_clk_enable(struct device *dev);
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c
index 494f7bf4a7881..9c5e565e6ef92 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c
@@ -207,6 +207,27 @@ void mtk_ovl_adaptor_layer_config(struct device *dev, unsigned int idx,
mtk_ethdr_layer_config(ethdr, idx, state, cmdq_pkt);
}

+size_t mtk_ovl_adaptor_crc_cnt(struct device *dev)
+{
+ struct mtk_disp_ovl_adaptor *ovl_adaptor = dev_get_drvdata(dev);
+
+ return mtk_ethdr_crc_cnt(ovl_adaptor->ovl_adaptor_comp[OVL_ADAPTOR_ETHDR0]);
+}
+
+u32 *mtk_ovl_adaptor_crc_entry(struct device *dev)
+{
+ struct mtk_disp_ovl_adaptor *ovl_adaptor = dev_get_drvdata(dev);
+
+ return mtk_ethdr_crc_entry(ovl_adaptor->ovl_adaptor_comp[OVL_ADAPTOR_ETHDR0]);
+}
+
+void mtk_ovl_adaptor_crc_read(struct device *dev)
+{
+ struct mtk_disp_ovl_adaptor *ovl_adaptor = dev_get_drvdata(dev);
+
+ mtk_ethdr_crc_read(ovl_adaptor->ovl_adaptor_comp[OVL_ADAPTOR_ETHDR0]);
+}
+
void mtk_ovl_adaptor_config(struct device *dev, unsigned int w,
unsigned int h, unsigned int vrefresh,
unsigned int bpc, struct cmdq_pkt *cmdq_pkt)
diff --git a/drivers/gpu/drm/mediatek/mtk_ethdr.c b/drivers/gpu/drm/mediatek/mtk_ethdr.c
index 951e3e82a6a1a..52caf75052d98 100644
--- a/drivers/gpu/drm/mediatek/mtk_ethdr.c
+++ b/drivers/gpu/drm/mediatek/mtk_ethdr.c
@@ -24,6 +24,9 @@
#define MIX_FME_CPL_INTEN BIT(1)
#define MIX_INTSTA 0x8
#define MIX_EN 0xc
+#define MIX_TRIG 0x10
+#define MIX_TRIG_CRC_EN BIT(8)
+#define MIX_TRIG_CRC_RST BIT(9)
#define MIX_RST 0x14
#define MIX_ROI_SIZE 0x18
#define MIX_DATAPATH_CON 0x1c
@@ -39,6 +42,11 @@
#define PREMULTI_SOURCE (3 << 12)
#define MIX_L_SRC_SIZE(n) (0x30 + 0x18 * (n))
#define MIX_L_SRC_OFFSET(n) (0x34 + 0x18 * (n))
+
+/* CRC register offsets for odd and even lines */
+#define MIX_CRC_ODD 0x110
+#define MIX_CRC_EVEN 0x114
+
#define MIX_FUNC_DCM0 0x120
#define MIX_FUNC_DCM1 0x124
#define MIX_FUNC_DCM_ENABLE 0xffffffff
@@ -82,6 +90,7 @@ struct mtk_ethdr {
void *vblank_cb_data;
int irq;
struct reset_control *reset_ctl;
+ struct mtk_crtc_crc crc;
};

static const char * const ethdr_clk_str[] = {
@@ -100,6 +109,32 @@ static const char * const ethdr_clk_str[] = {
"vdo_be_async",
};

+static const u32 ethdr_crc_ofs[] = {
+ MIX_CRC_ODD,
+ MIX_CRC_EVEN,
+};
+
+size_t mtk_ethdr_crc_cnt(struct device *dev)
+{
+ struct mtk_ethdr *priv = dev_get_drvdata(dev);
+
+ return priv->crc.cnt;
+}
+
+u32 *mtk_ethdr_crc_entry(struct device *dev)
+{
+ struct mtk_ethdr *priv = dev_get_drvdata(dev);
+
+ return priv->crc.va;
+}
+
+void mtk_ethdr_crc_read(struct device *dev)
+{
+ struct mtk_ethdr *priv = dev_get_drvdata(dev);
+
+ mtk_crtc_read_crc(&priv->crc, priv->ethdr_comp[ETHDR_MIXER].regs);
+}
+
void mtk_ethdr_register_vblank_cb(struct device *dev,
void (*vblank_cb)(void *),
void *vblank_cb_data)
@@ -256,6 +291,13 @@ void mtk_ethdr_start(struct device *dev)
struct mtk_ethdr_comp *mixer = &priv->ethdr_comp[ETHDR_MIXER];

writel(1, mixer->regs + MIX_EN);
+
+ if (priv->crc.cnt) {
+ writel(MIX_TRIG_CRC_EN, mixer->regs + MIX_TRIG);
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+ mtk_crtc_start_crc_cmdq(&priv->crc);
+#endif
+ }
}

void mtk_ethdr_stop(struct device *dev)
@@ -263,6 +305,9 @@ void mtk_ethdr_stop(struct device *dev)
struct mtk_ethdr *priv = dev_get_drvdata(dev);
struct mtk_ethdr_comp *mixer = &priv->ethdr_comp[ETHDR_MIXER];

+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+ mtk_crtc_stop_crc_cmdq(&priv->crc);
+#endif
writel(0, mixer->regs + MIX_EN);
writel(1, mixer->regs + MIX_RST);
reset_control_reset(priv->reset_ctl);
@@ -317,6 +362,9 @@ static int mtk_ethdr_probe(struct platform_device *pdev)
if (!priv)
return -ENOMEM;

+ mtk_crtc_init_crc(&priv->crc, ethdr_crc_ofs, ARRAY_SIZE(ethdr_crc_ofs),
+ MIX_TRIG, MIX_TRIG_CRC_RST);
+
for (i = 0; i < ETHDR_ID_MAX; i++) {
priv->ethdr_comp[i].dev = dev;
priv->ethdr_comp[i].regs = of_iomap(dev->of_node, i);
@@ -325,6 +373,16 @@ static int mtk_ethdr_probe(struct platform_device *pdev)
&priv->ethdr_comp[i].cmdq_base, i);
if (ret)
dev_dbg(dev, "get mediatek,gce-client-reg fail!\n");
+
+ if (i == ETHDR_MIXER) {
+ if (of_property_read_u32_index(dev->of_node,
+ "mediatek,gce-events", i,
+ &priv->crc.cmdq_event)) {
+ dev_warn(dev, "failed to get gce-events for crc\n");
+ }
+ priv->crc.cmdq_reg = &priv->ethdr_comp[i].cmdq_base;
+ mtk_crtc_create_crc_cmdq(dev, &priv->crc);
+ }
#endif
dev_dbg(dev, "[DRM]regs:0x%p, node:%d\n", priv->ethdr_comp[i].regs, i);
}
@@ -365,6 +423,9 @@ static int mtk_ethdr_probe(struct platform_device *pdev)

static int mtk_ethdr_remove(struct platform_device *pdev)
{
+ struct mtk_ethdr *priv = dev_get_drvdata(&pdev->dev);
+
+ mtk_crtc_destroy_crc(&priv->crc);
component_del(&pdev->dev, &mtk_ethdr_component_ops);
return 0;
}
diff --git a/drivers/gpu/drm/mediatek/mtk_ethdr.h b/drivers/gpu/drm/mediatek/mtk_ethdr.h
index 81af9edea3f74..d17d7256bd120 100644
--- a/drivers/gpu/drm/mediatek/mtk_ethdr.h
+++ b/drivers/gpu/drm/mediatek/mtk_ethdr.h
@@ -22,4 +22,9 @@ void mtk_ethdr_register_vblank_cb(struct device *dev,
void mtk_ethdr_unregister_vblank_cb(struct device *dev);
void mtk_ethdr_enable_vblank(struct device *dev);
void mtk_ethdr_disable_vblank(struct device *dev);
+
+size_t mtk_ethdr_crc_cnt(struct device *dev);
+u32 *mtk_ethdr_crc_entry(struct device *dev);
+void mtk_ethdr_crc_read(struct device *dev);
+
#endif
--
2.18.0


2024-03-22 05:30:21

by Shawn Sung (宋孝謙)

[permalink] [raw]
Subject: [PATCH v6 02/14] drm/mediatek: Add OVL compatible name for MT8195

From: Hsiao Chien Sung <[email protected]>

Add OVL compatible name for MT8195.
Without this commit, DRM won't work after modifying the device tree.

Reviewed-by: CK Hu <[email protected]>
Reviewed-by: AngeloGioacchino Del Regno <[email protected]>
Signed-off-by: Hsiao Chien Sung <[email protected]>
---
drivers/gpu/drm/mediatek/mtk_drm_drv.c | 2 ++
1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index 4710cd8b7288b..621015b64674d 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -761,6 +761,8 @@ static const struct of_device_id mtk_ddp_comp_dt_ids[] = {
.data = (void *)MTK_DISP_OVL },
{ .compatible = "mediatek,mt8192-disp-ovl",
.data = (void *)MTK_DISP_OVL },
+ { .compatible = "mediatek,mt8195-disp-ovl",
+ .data = (void *)MTK_DISP_OVL },
{ .compatible = "mediatek,mt8183-disp-ovl-2l",
.data = (void *)MTK_DISP_OVL_2L },
{ .compatible = "mediatek,mt8192-disp-ovl-2l",
--
2.18.0


2024-03-22 05:31:07

by Shawn Sung (宋孝謙)

[permalink] [raw]
Subject: [PATCH v6 12/14] drm/mediatek: Support CRC in display driver

From: Hsiao Chien Sung <[email protected]>

Register CRC related function pointers to support
CRC retrieval.

Signed-off-by: Hsiao Chien Sung <[email protected]>
---
drivers/gpu/drm/mediatek/mtk_crtc.c | 260 ++++++++++++++++++++++++
drivers/gpu/drm/mediatek/mtk_crtc.h | 38 ++++
drivers/gpu/drm/mediatek/mtk_ddp_comp.h | 3 +
3 files changed, 301 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.c b/drivers/gpu/drm/mediatek/mtk_crtc.c
index d811e4e73a36c..6440c5fb336d7 100644
--- a/drivers/gpu/drm/mediatek/mtk_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_crtc.c
@@ -18,6 +18,7 @@
#include <drm/drm_atomic_helper.h>
#include <drm/drm_probe_helper.h>
#include <drm/drm_vblank.h>
+#include <drm/drm_vblank_work.h>

#include "mtk_crtc.h"
#include "mtk_ddp_comp.h"
@@ -69,6 +70,9 @@ struct mtk_crtc {
/* lock for display hardware access */
struct mutex hw_lock;
bool config_updating;
+
+ struct mtk_ddp_comp *crc_provider;
+ struct drm_vblank_work crc_work;
};

struct mtk_crtc_state {
@@ -703,6 +707,71 @@ static void mtk_crtc_update_output(struct drm_crtc *crtc,
}
}

+static void mtk_crtc_crc_work(struct kthread_work *base)
+{
+ struct drm_vblank_work *work = to_drm_vblank_work(base);
+ struct mtk_crtc *mtk_crtc =
+ container_of(work, typeof(*mtk_crtc), crc_work);
+
+ if (mtk_crtc->base.crc.opened) {
+ struct mtk_ddp_comp *comp = mtk_crtc->crc_provider;
+ u64 vblank = drm_crtc_vblank_count(&mtk_crtc->base);
+
+ comp->funcs->crc_read(comp->dev);
+
+ /* could take more than 50ms to finish */
+ drm_crtc_add_crc_entry(&mtk_crtc->base, true, vblank,
+ comp->funcs->crc_entry(comp->dev));
+
+ drm_vblank_work_schedule(&mtk_crtc->crc_work, vblank + 1, true);
+ }
+}
+
+static int mtk_crtc_set_crc_source(struct drm_crtc *crtc, const char *src)
+{
+ struct mtk_crtc *mtk_crtc = to_mtk_crtc(crtc);
+
+ if (!src)
+ return -EINVAL;
+
+ if (strcmp(src, "auto") != 0) {
+ DRM_ERROR("%s(crtc-%d): unknown source '%s'\n",
+ __func__, drm_crtc_index(crtc), src);
+ return -EINVAL;
+ }
+
+ /*
+ * skip the first crc because the first frame (vblank + 1) is configured
+ * by mtk_crtc_ddp_hw_init() when atomic enable
+ */
+ drm_vblank_work_schedule(&mtk_crtc->crc_work,
+ drm_crtc_vblank_count(crtc) + 2, false);
+ return 0;
+}
+
+static int mtk_crtc_verify_crc_source(struct drm_crtc *crtc, const char *src,
+ size_t *cnt)
+{
+ struct mtk_crtc *mtk_crtc = to_mtk_crtc(crtc);
+ struct mtk_ddp_comp *comp = mtk_crtc->crc_provider;
+
+ if (!comp) {
+ DRM_ERROR("%s(crtc-%d): no crc provider\n",
+ __func__, drm_crtc_index(crtc));
+ return -ENOENT;
+ }
+
+ if (src && strcmp(src, "auto") != 0) {
+ DRM_ERROR("%s(crtc-%d): unknown source '%s'\n",
+ __func__, drm_crtc_index(crtc), src);
+ return -EINVAL;
+ }
+
+ *cnt = comp->funcs->crc_cnt(comp->dev);
+
+ return 0;
+}
+
int mtk_crtc_plane_check(struct drm_crtc *crtc, struct drm_plane *plane,
struct mtk_plane_state *state)
{
@@ -751,6 +820,8 @@ static void mtk_crtc_atomic_enable(struct drm_crtc *crtc,

drm_crtc_vblank_on(crtc);
mtk_crtc->enabled = true;
+
+ drm_vblank_work_init(&mtk_crtc->crc_work, crtc, mtk_crtc_crc_work);
}

static void mtk_crtc_atomic_disable(struct drm_crtc *crtc,
@@ -840,6 +911,8 @@ static const struct drm_crtc_funcs mtk_crtc_funcs = {
.atomic_destroy_state = mtk_crtc_destroy_state,
.enable_vblank = mtk_crtc_enable_vblank,
.disable_vblank = mtk_crtc_disable_vblank,
+ .set_crc_source = mtk_crtc_set_crc_source,
+ .verify_crc_source = mtk_crtc_verify_crc_source,
};

static const struct drm_crtc_helper_funcs mtk_crtc_helper_funcs = {
@@ -1033,6 +1106,11 @@ int mtk_crtc_create(struct drm_device *drm_dev, const unsigned int *path,

if (comp->funcs->ctm_set)
has_ctm = true;
+
+ if (comp->funcs->crc_cnt &&
+ comp->funcs->crc_entry &&
+ comp->funcs->crc_read)
+ mtk_crtc->crc_provider = comp;
}

mtk_ddp_comp_register_vblank_cb(comp, mtk_crtc_ddp_irq,
@@ -1136,3 +1214,185 @@ int mtk_crtc_create(struct drm_device *drm_dev, const unsigned int *path,

return 0;
}
+
+void mtk_crtc_init_crc(struct mtk_crtc_crc *crc, const u32 *crc_offset_table,
+ size_t crc_count, u32 reset_offset, u32 reset_mask)
+{
+ crc->ofs = crc_offset_table;
+ crc->cnt = crc_count;
+ crc->rst_ofs = reset_offset;
+ crc->rst_msk = reset_mask;
+ crc->va = kcalloc(crc->cnt, sizeof(*crc->va), GFP_KERNEL);
+ if (!crc->va) {
+ DRM_ERROR("failed to allocate memory for crc\n");
+ crc->cnt = 0;
+ }
+}
+
+void mtk_crtc_read_crc(struct mtk_crtc_crc *crc, void __iomem *reg)
+{
+ if (!crc->cnt || !crc->ofs || !crc->va)
+ return;
+
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+ /* sync to see the most up-to-date copy of the DMA buffer */
+ dma_sync_single_for_cpu(crc->cmdq_client.chan->mbox->dev,
+ crc->pa, crc->cnt * sizeof(*crc->va),
+ DMA_FROM_DEVICE);
+#endif
+}
+
+void mtk_crtc_destroy_crc(struct mtk_crtc_crc *crc)
+{
+ if (!crc->cnt)
+ return;
+
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+ if (crc->pa) {
+ dma_unmap_single(crc->cmdq_client.chan->mbox->dev,
+ crc->pa, crc->cnt * sizeof(*crc->va),
+ DMA_TO_DEVICE);
+ crc->pa = 0;
+ }
+ if (crc->cmdq_client.chan) {
+ mtk_drm_cmdq_pkt_destroy(&crc->cmdq_handle);
+ mbox_free_channel(crc->cmdq_client.chan);
+ crc->cmdq_client.chan = NULL;
+ }
+#endif
+ kfree(crc->va);
+ crc->va = NULL;
+ crc->cnt = 0;
+}
+
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+/**
+ * mtk_crtc_create_crc_cmdq - Create a CMDQ thread for syncing the CRCs
+ * @dev: Kernel device node of the CRC provider
+ * @crc: Pointer of the CRC to init
+ *
+ * This function will create a looping thread on GCE (Global Command Engine) to
+ * keep the CRC up to date by monitoring the assigned event (usually the frame
+ * done event) of the CRC provider, and read the CRCs from the registers to a
+ * shared memory for the workqueue to read. To start/stop the looping thread,
+ * please call `mtk_crtc_start_crc_cmdq()` and `mtk_crtc_stop_crc_cmdq()`
+ * defined blow.
+ *
+ * The reason why we don't update the CRCs with CPU is that the front porch of
+ * 4K60 timing in CEA-861 is less than 60us, and register read/write speed is
+ * relatively unreliable comparing to GCE due to the bus design.
+ *
+ * We must create a new thread instead of using the original one for plane
+ * update is because:
+ * 1. We cannot add another wait-for-event command at the end of cmdq packet, or
+ * the cmdq callback will delay for too long
+ * 2. Will get the CRC of the previous frame if using the existed wait-for-event
+ * command which is at the beginning of the packet
+ */
+void mtk_crtc_create_crc_cmdq(struct device *dev, struct mtk_crtc_crc *crc)
+{
+ int i;
+
+ if (!crc->cnt) {
+ dev_warn(dev, "%s: not support\n", __func__);
+ goto cleanup;
+ }
+
+ if (!crc->ofs) {
+ dev_warn(dev, "%s: not defined\n", __func__);
+ goto cleanup;
+ }
+
+ crc->cmdq_client.client.dev = dev;
+ crc->cmdq_client.client.tx_block = false;
+ crc->cmdq_client.client.knows_txdone = true;
+ crc->cmdq_client.client.rx_callback = NULL;
+ crc->cmdq_client.chan = mbox_request_channel(&crc->cmdq_client.client, 0);
+ if (IS_ERR(crc->cmdq_client.chan)) {
+ dev_warn(dev, "%s: failed to create mailbox client\n", __func__);
+ crc->cmdq_client.chan = NULL;
+ goto cleanup;
+ }
+
+ if (mtk_drm_cmdq_pkt_create(&crc->cmdq_client, &crc->cmdq_handle, PAGE_SIZE)) {
+ dev_warn(dev, "%s: failed to create cmdq packet\n", __func__);
+ goto cleanup;
+ }
+
+ if (!crc->va) {
+ dev_warn(dev, "%s: no memory\n", __func__);
+ goto cleanup;
+ }
+
+ /* map the entry to get a dma address for cmdq to store the crc */
+ crc->pa = dma_map_single(crc->cmdq_client.chan->mbox->dev,
+ crc->va, crc->cnt * sizeof(*crc->va),
+ DMA_FROM_DEVICE);
+
+ if (dma_mapping_error(crc->cmdq_client.chan->mbox->dev, crc->pa)) {
+ dev_err(dev, "%s: failed to map dma\n", __func__);
+ goto cleanup;
+ }
+
+ if (crc->cmdq_event)
+ cmdq_pkt_wfe(&crc->cmdq_handle, crc->cmdq_event, true);
+
+ for (i = 0; i < crc->cnt; i++) {
+ /* put crc to spr1 register */
+ cmdq_pkt_read_s(&crc->cmdq_handle, crc->cmdq_reg->subsys,
+ crc->cmdq_reg->offset + crc->ofs[i],
+ CMDQ_THR_SPR_IDX1);
+
+ /* copy spr1 register to physical address of the crc */
+ cmdq_pkt_assign(&crc->cmdq_handle, CMDQ_THR_SPR_IDX0,
+ CMDQ_ADDR_HIGH(crc->pa + i * sizeof(*crc->va)));
+ cmdq_pkt_write_s(&crc->cmdq_handle, CMDQ_THR_SPR_IDX0,
+ CMDQ_ADDR_LOW(crc->pa + i * sizeof(*crc->va)),
+ CMDQ_THR_SPR_IDX1);
+ }
+ /* reset crc */
+ mtk_ddp_write_mask(&crc->cmdq_handle, ~0, crc->cmdq_reg, 0,
+ crc->rst_ofs, crc->rst_msk);
+
+ /* clear reset bit */
+ mtk_ddp_write_mask(&crc->cmdq_handle, 0, crc->cmdq_reg, 0,
+ crc->rst_ofs, crc->rst_msk);
+
+ /* jump to head of the cmdq packet */
+ cmdq_pkt_jump(&crc->cmdq_handle, crc->cmdq_handle.pa_base);
+
+ return;
+cleanup:
+ mtk_crtc_destroy_crc(crc);
+}
+
+/**
+ * mtk_crtc_start_crc_cmdq - Start the GCE looping thread for CRC update
+ * @crc: Pointer of the CRC information
+ */
+void mtk_crtc_start_crc_cmdq(struct mtk_crtc_crc *crc)
+{
+ if (!crc->cmdq_client.chan)
+ return;
+
+ dma_sync_single_for_device(crc->cmdq_client.chan->mbox->dev,
+ crc->cmdq_handle.pa_base,
+ crc->cmdq_handle.cmd_buf_size,
+ DMA_TO_DEVICE);
+ mbox_send_message(crc->cmdq_client.chan, &crc->cmdq_handle);
+ mbox_client_txdone(crc->cmdq_client.chan, 0);
+}
+
+/**
+ * mtk_crtc_stop_crc_cmdq - Stop the GCE looping thread for CRC update
+ * @crc: Pointer of the CRC information
+ */
+void mtk_crtc_stop_crc_cmdq(struct mtk_crtc_crc *crc)
+{
+ if (!crc->cmdq_client.chan)
+ return;
+
+ /* remove all the commands from the cmdq packet */
+ mbox_flush(crc->cmdq_client.chan, 2000);
+}
+#endif
diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.h b/drivers/gpu/drm/mediatek/mtk_crtc.h
index 388e900b6f4de..a79c4611754e4 100644
--- a/drivers/gpu/drm/mediatek/mtk_crtc.h
+++ b/drivers/gpu/drm/mediatek/mtk_crtc.h
@@ -14,6 +14,34 @@
#define MTK_MAX_BPC 10
#define MTK_MIN_BPC 3

+/**
+ * struct mtk_crtc_crc - crc related information
+ * @ofs: register offset of crc
+ * @rst_ofs: register offset of crc reset
+ * @rst_msk: register mask of crc reset
+ * @cnt: count of crc
+ * @va: pointer to the start of crc array
+ * @pa: physical address of the crc for gce to access
+ * @cmdq_event: the event to trigger the cmdq
+ * @cmdq_reg: address of the register that cmdq is going to access
+ * @cmdq_client: handler to control cmdq (mbox channel, thread ...etc.)
+ * @cmdq_handle: cmdq packet to store the commands
+ */
+struct mtk_crtc_crc {
+ const u32 *ofs;
+ u32 rst_ofs;
+ u32 rst_msk;
+ size_t cnt;
+ u32 *va;
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+ dma_addr_t pa;
+ u32 cmdq_event;
+ struct cmdq_client_reg *cmdq_reg;
+ struct cmdq_client cmdq_client;
+ struct cmdq_pkt cmdq_handle;
+#endif
+};
+
void mtk_crtc_commit(struct drm_crtc *crtc);
int mtk_crtc_create(struct drm_device *drm_dev, const unsigned int *path,
unsigned int path_len, int priv_data_index,
@@ -25,4 +53,14 @@ void mtk_crtc_async_update(struct drm_crtc *crtc, struct drm_plane *plane,
struct drm_atomic_state *plane_state);
struct device *mtk_crtc_dma_dev_get(struct drm_crtc *crtc);

+void mtk_crtc_init_crc(struct mtk_crtc_crc *crc, const u32 *crc_offset_table,
+ size_t crc_count, u32 reset_offset, u32 reset_mask);
+void mtk_crtc_read_crc(struct mtk_crtc_crc *crc, void __iomem *reg);
+void mtk_crtc_destroy_crc(struct mtk_crtc_crc *crc);
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+void mtk_crtc_create_crc_cmdq(struct device *dev, struct mtk_crtc_crc *crc);
+void mtk_crtc_start_crc_cmdq(struct mtk_crtc_crc *crc);
+void mtk_crtc_stop_crc_cmdq(struct mtk_crtc_crc *crc);
+#endif
+
#endif /* MTK_CRTC_H */
diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
index f7fe2e08dc8e2..b9c79e740abe0 100644
--- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
@@ -88,6 +88,9 @@ struct mtk_ddp_comp_funcs {
void (*remove)(struct device *dev, struct mtk_mutex *mutex);
unsigned int (*encoder_index)(struct device *dev);
enum drm_mode_status (*mode_valid)(struct device *dev, const struct drm_display_mode *mode);
+ size_t (*crc_cnt)(struct device *dev);
+ u32 *(*crc_entry)(struct device *dev);
+ void (*crc_read)(struct device *dev);
};

struct mtk_ddp_comp {
--
2.18.0


2024-03-22 05:32:24

by Shawn Sung (宋孝謙)

[permalink] [raw]
Subject: [PATCH v6 10/14] drm/mediatek: Support "None" alpha blending in OVL

From: Hsiao Chien Sung <[email protected]>

Support "None" blend mode on MediaTek's chips.

Please refer to the description of the commit
"drm/mediatek: Support alpha blending in display driver"
for more information.

Signed-off-by: Hsiao Chien Sung <[email protected]>
---
drivers/gpu/drm/mediatek/mtk_disp_ovl.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
index b1e5d453316cc..a936f338ab79d 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
@@ -484,7 +484,8 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx,
con |= state->base.alpha & OVL_CON_ALPHA;
}

- if (state->base.fb && !state->base.fb->format->has_alpha)
+ if (blend_mode == DRM_MODE_BLEND_PIXEL_NONE ||
+ (state->base.fb && !state->base.fb->format->has_alpha))
ignore_pixel_alpha = OVL_CONST_BLEND;

if (pending->rotation & DRM_MODE_REFLECT_Y) {
--
2.18.0


2024-03-22 05:32:31

by Shawn Sung (宋孝謙)

[permalink] [raw]
Subject: [PATCH v6 04/14] drm/mediatek: Add DRM_MODE_ROTATE_0 to rotation property

From: Hsiao Chien Sung <[email protected]>

Always add DRM_MODE_ROTATE_0 to rotation property to meet
IGT's (Intel GPU Tools) requirement.

Reviewed-by: AngeloGioacchino Del Regno <[email protected]>
Signed-off-by: Hsiao Chien Sung <[email protected]>
---
drivers/gpu/drm/mediatek/mtk_ddp_comp.h | 6 +++++-
drivers/gpu/drm/mediatek/mtk_disp_ovl.c | 21 +++++++++------------
drivers/gpu/drm/mediatek/mtk_plane.c | 2 +-
3 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
index 26236691ce4c2..f7fe2e08dc8e2 100644
--- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
@@ -192,7 +192,11 @@ unsigned int mtk_ddp_comp_supported_rotations(struct mtk_ddp_comp *comp)
if (comp->funcs && comp->funcs->supported_rotations)
return comp->funcs->supported_rotations(comp->dev);

- return 0;
+ /*
+ * In order to pass IGT tests, DRM_MODE_ROTATE_0 is required when
+ * rotation is not supported.
+ */
+ return DRM_MODE_ROTATE_0;
}

static inline unsigned int mtk_ddp_comp_layer_nr(struct mtk_ddp_comp *comp)
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
index 0ebeaf9830d83..2a767a823c83a 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
@@ -288,6 +288,10 @@ unsigned int mtk_ovl_layer_nr(struct device *dev)

unsigned int mtk_ovl_supported_rotations(struct device *dev)
{
+ /*
+ * although currently OVL can only do reflection,
+ * reflect x + reflect y = rotate 180
+ */
return DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_180 |
DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y;
}
@@ -296,27 +300,20 @@ int mtk_ovl_layer_check(struct device *dev, unsigned int idx,
struct mtk_plane_state *mtk_state)
{
struct drm_plane_state *state = &mtk_state->base;
- unsigned int rotation = 0;

- rotation = drm_rotation_simplify(state->rotation,
- DRM_MODE_ROTATE_0 |
- DRM_MODE_REFLECT_X |
- DRM_MODE_REFLECT_Y);
- rotation &= ~DRM_MODE_ROTATE_0;
-
- /* We can only do reflection, not rotation */
- if ((rotation & DRM_MODE_ROTATE_MASK) != 0)
+ /* check if any unsupported rotation is set */
+ if (state->rotation & ~mtk_ovl_supported_rotations(dev))
return -EINVAL;

/*
* TODO: Rotating/reflecting YUV buffers is not supported at this time.
* Only RGB[AX] variants are supported.
+ * Since DRM_MODE_ROTATE_0 means "no rotation", we should not
+ * reject layers with this property.
*/
- if (state->fb->format->is_yuv && rotation != 0)
+ if (state->fb->format->is_yuv && (state->rotation & ~DRM_MODE_ROTATE_0))
return -EINVAL;

- state->rotation = rotation;
-
return 0;
}

diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c b/drivers/gpu/drm/mediatek/mtk_plane.c
index a74b26d359857..1723d4333f371 100644
--- a/drivers/gpu/drm/mediatek/mtk_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_plane.c
@@ -338,7 +338,7 @@ int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane,
return err;
}

- if (supported_rotations & ~DRM_MODE_ROTATE_0) {
+ if (supported_rotations) {
err = drm_plane_create_rotation_property(plane,
DRM_MODE_ROTATE_0,
supported_rotations);
--
2.18.0


2024-03-22 05:33:05

by Shawn Sung (宋孝謙)

[permalink] [raw]
Subject: [PATCH v6 08/14] drm/mediatek: Support "Pre-multiplied" alpha blending in OVL

From: Hsiao Chien Sung <[email protected]>

Support "Pre-multiplied" blend mode on MediaTek's chips.
Before this patch, only the "coverage" mode is supported.

Please refer to the description of the commit
"drm/mediatek: Support alpha blending in display driver"
for more information.

Signed-off-by: Hsiao Chien Sung <[email protected]>
---
drivers/gpu/drm/mediatek/mtk_disp_ovl.c | 84 +++++++++++++++++++++----
1 file changed, 73 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
index 2a767a823c83a..b1e5d453316cc 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
@@ -38,6 +38,7 @@
#define DISP_REG_OVL_PITCH_MSB(n) (0x0040 + 0x20 * (n))
#define OVL_PITCH_MSB_2ND_SUBBUF BIT(16)
#define DISP_REG_OVL_PITCH(n) (0x0044 + 0x20 * (n))
+#define OVL_CONST_BLEND BIT(28)
#define DISP_REG_OVL_RDMA_CTRL(n) (0x00c0 + 0x20 * (n))
#define DISP_REG_OVL_RDMA_GMC(n) (0x00c8 + 0x20 * (n))
#define DISP_REG_OVL_ADDR_MT2701 0x0040
@@ -51,13 +52,16 @@
#define GMC_THRESHOLD_HIGH ((1 << GMC_THRESHOLD_BITS) / 4)
#define GMC_THRESHOLD_LOW ((1 << GMC_THRESHOLD_BITS) / 8)

+#define OVL_CON_CLRFMT_MAN BIT(23)
#define OVL_CON_BYTE_SWAP BIT(24)
-#define OVL_CON_MTX_YUV_TO_RGB (6 << 16)
+#define OVL_CON_RGB_SWAP BIT(25)
#define OVL_CON_CLRFMT_RGB (1 << 12)
#define OVL_CON_CLRFMT_RGBA8888 (2 << 12)
#define OVL_CON_CLRFMT_ARGB8888 (3 << 12)
#define OVL_CON_CLRFMT_UYVY (4 << 12)
#define OVL_CON_CLRFMT_YUYV (5 << 12)
+#define OVL_CON_MTX_YUV_TO_RGB (6 << 16)
+#define OVL_CON_CLRFMT_PARGB8888 (OVL_CON_CLRFMT_ARGB8888 | OVL_CON_CLRFMT_MAN)
#define OVL_CON_CLRFMT_RGB565(ovl) ((ovl)->data->fmt_rgb565_is_0 ? \
0 : OVL_CON_CLRFMT_RGB)
#define OVL_CON_CLRFMT_RGB888(ovl) ((ovl)->data->fmt_rgb565_is_0 ? \
@@ -71,6 +75,24 @@
#define OVL_CON_VIRT_FLIP BIT(9)
#define OVL_CON_HORZ_FLIP BIT(10)

+#define OVL_COLOR_ALPHA GENMASK(31, 24)
+
+static inline bool is_10bit_rgb(u32 fmt)
+{
+ switch (fmt) {
+ case DRM_FORMAT_XRGB2101010:
+ case DRM_FORMAT_ARGB2101010:
+ case DRM_FORMAT_RGBX1010102:
+ case DRM_FORMAT_RGBA1010102:
+ case DRM_FORMAT_XBGR2101010:
+ case DRM_FORMAT_ABGR2101010:
+ case DRM_FORMAT_BGRX1010102:
+ case DRM_FORMAT_BGRA1010102:
+ return true;
+ }
+ return false;
+}
+
static const u32 mt8173_formats[] = {
DRM_FORMAT_XRGB8888,
DRM_FORMAT_ARGB8888,
@@ -88,12 +110,20 @@ static const u32 mt8173_formats[] = {
static const u32 mt8195_formats[] = {
DRM_FORMAT_XRGB8888,
DRM_FORMAT_ARGB8888,
+ DRM_FORMAT_XRGB2101010,
DRM_FORMAT_ARGB2101010,
DRM_FORMAT_BGRX8888,
DRM_FORMAT_BGRA8888,
+ DRM_FORMAT_BGRX1010102,
DRM_FORMAT_BGRA1010102,
DRM_FORMAT_ABGR8888,
DRM_FORMAT_XBGR8888,
+ DRM_FORMAT_XBGR2101010,
+ DRM_FORMAT_ABGR2101010,
+ DRM_FORMAT_RGBX8888,
+ DRM_FORMAT_RGBA8888,
+ DRM_FORMAT_RGBX1010102,
+ DRM_FORMAT_RGBA1010102,
DRM_FORMAT_RGB888,
DRM_FORMAT_BGR888,
DRM_FORMAT_RGB565,
@@ -253,9 +283,7 @@ static void mtk_ovl_set_bit_depth(struct device *dev, int idx, u32 format,
reg = readl(ovl->regs + DISP_REG_OVL_CLRFMT_EXT);
reg &= ~OVL_CON_CLRFMT_BIT_DEPTH_MASK(idx);

- if (format == DRM_FORMAT_RGBA1010102 ||
- format == DRM_FORMAT_BGRA1010102 ||
- format == DRM_FORMAT_ARGB2101010)
+ if (is_10bit_rgb(format))
bit_depth = OVL_CON_CLRFMT_10_BIT;

reg |= OVL_CON_CLRFMT_BIT_DEPTH(bit_depth, idx);
@@ -273,7 +301,13 @@ void mtk_ovl_config(struct device *dev, unsigned int w,
if (w != 0 && h != 0)
mtk_ddp_write_relaxed(cmdq_pkt, h << 16 | w, &ovl->cmdq_reg, ovl->regs,
DISP_REG_OVL_ROI_SIZE);
- mtk_ddp_write_relaxed(cmdq_pkt, 0x0, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_ROI_BGCLR);
+
+ /*
+ * The background color should be opaque black (ARGB),
+ * otherwise there will be no effect with alpha blend
+ */
+ mtk_ddp_write_relaxed(cmdq_pkt, OVL_COLOR_ALPHA, &ovl->cmdq_reg,
+ ovl->regs, DISP_REG_OVL_ROI_BGCLR);

mtk_ddp_write(cmdq_pkt, 0x1, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_RST);
mtk_ddp_write(cmdq_pkt, 0x0, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_RST);
@@ -353,7 +387,8 @@ void mtk_ovl_layer_off(struct device *dev, unsigned int idx,
DISP_REG_OVL_RDMA_CTRL(idx));
}

-static unsigned int ovl_fmt_convert(struct mtk_disp_ovl *ovl, unsigned int fmt)
+static unsigned int ovl_fmt_convert(struct mtk_disp_ovl *ovl, unsigned int fmt,
+ unsigned int blend_mode)
{
/* The return value in switch "MEM_MODE_INPUT_FORMAT_XXX"
* is defined in mediatek HW data sheet.
@@ -372,17 +407,37 @@ static unsigned int ovl_fmt_convert(struct mtk_disp_ovl *ovl, unsigned int fmt)
return OVL_CON_CLRFMT_RGB888(ovl) | OVL_CON_BYTE_SWAP;
case DRM_FORMAT_RGBX8888:
case DRM_FORMAT_RGBA8888:
+ return blend_mode == DRM_MODE_BLEND_COVERAGE ?
+ OVL_CON_CLRFMT_ARGB8888 :
+ OVL_CON_CLRFMT_PARGB8888;
+ case DRM_FORMAT_RGBX1010102:
+ case DRM_FORMAT_RGBA1010102:
return OVL_CON_CLRFMT_ARGB8888;
case DRM_FORMAT_BGRX8888:
case DRM_FORMAT_BGRA8888:
+ return OVL_CON_BYTE_SWAP |
+ (blend_mode == DRM_MODE_BLEND_COVERAGE ?
+ OVL_CON_CLRFMT_ARGB8888 :
+ OVL_CON_CLRFMT_PARGB8888);
+ case DRM_FORMAT_BGRX1010102:
case DRM_FORMAT_BGRA1010102:
return OVL_CON_CLRFMT_ARGB8888 | OVL_CON_BYTE_SWAP;
case DRM_FORMAT_XRGB8888:
case DRM_FORMAT_ARGB8888:
+ return blend_mode == DRM_MODE_BLEND_COVERAGE ?
+ OVL_CON_CLRFMT_RGBA8888 :
+ OVL_CON_CLRFMT_PARGB8888;
+ case DRM_FORMAT_XRGB2101010:
case DRM_FORMAT_ARGB2101010:
return OVL_CON_CLRFMT_RGBA8888;
case DRM_FORMAT_XBGR8888:
case DRM_FORMAT_ABGR8888:
+ return OVL_CON_RGB_SWAP |
+ (blend_mode == DRM_MODE_BLEND_COVERAGE ?
+ OVL_CON_CLRFMT_RGBA8888 :
+ OVL_CON_CLRFMT_PARGB8888);
+ case DRM_FORMAT_XBGR2101010:
+ case DRM_FORMAT_ABGR2101010:
return OVL_CON_CLRFMT_RGBA8888 | OVL_CON_BYTE_SWAP;
case DRM_FORMAT_UYVY:
return OVL_CON_CLRFMT_UYVY | OVL_CON_MTX_YUV_TO_RGB;
@@ -404,6 +459,8 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx,
unsigned int fmt = pending->format;
unsigned int offset = (pending->y << 16) | pending->x;
unsigned int src_size = (pending->height << 16) | pending->width;
+ unsigned int blend_mode = state->base.pixel_blend_mode;
+ unsigned int ignore_pixel_alpha = 0;
unsigned int con;
bool is_afbc = pending->modifier != DRM_FORMAT_MOD_LINEAR;
union overlay_pitch {
@@ -421,9 +478,14 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx,
return;
}

- con = ovl_fmt_convert(ovl, fmt);
- if (state->base.fb && state->base.fb->format->has_alpha)
- con |= OVL_CON_AEN | OVL_CON_ALPHA;
+ con = ovl_fmt_convert(ovl, fmt, blend_mode);
+ if (state->base.fb) {
+ con |= OVL_CON_AEN;
+ con |= state->base.alpha & OVL_CON_ALPHA;
+ }
+
+ if (state->base.fb && !state->base.fb->format->has_alpha)
+ ignore_pixel_alpha = OVL_CONST_BLEND;

if (pending->rotation & DRM_MODE_REFLECT_Y) {
con |= OVL_CON_VIRT_FLIP;
@@ -440,8 +502,8 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx,

mtk_ddp_write_relaxed(cmdq_pkt, con, &ovl->cmdq_reg, ovl->regs,
DISP_REG_OVL_CON(idx));
- mtk_ddp_write_relaxed(cmdq_pkt, overlay_pitch.split_pitch.lsb, &ovl->cmdq_reg, ovl->regs,
- DISP_REG_OVL_PITCH(idx));
+ mtk_ddp_write_relaxed(cmdq_pkt, overlay_pitch.split_pitch.lsb | ignore_pixel_alpha,
+ &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH(idx));
mtk_ddp_write_relaxed(cmdq_pkt, src_size, &ovl->cmdq_reg, ovl->regs,
DISP_REG_OVL_SRC_SIZE(idx));
mtk_ddp_write_relaxed(cmdq_pkt, offset, &ovl->cmdq_reg, ovl->regs,
--
2.18.0


2024-03-22 05:33:20

by Shawn Sung (宋孝謙)

[permalink] [raw]
Subject: [PATCH v6 07/14] drm/mediatek: Support alpha blending in display driver

From: Hsiao Chien Sung <[email protected]>

Support "Pre-multiplied" and "None" blend mode on MediaTek's chips by
adding correct blend mode property when the planes init.
Before this patch, only the "Coverage" mode (default) is supported.

For more information, there are three pixel blend modes in DRM driver:
"None", "Pre-multiplied", and "Coverage".

To understand the difference between these modes, let's take a look at
the following two approaches to do alpha blending:

1. Straight:
dst.RGB = src.RGB * src.A + dst.RGB * (1 - src.A)
This is straightforward and easy to understand, when the source layer is
compositing with the destination layer, it's alpha will affect the
result. This is also known as "post-multiplied", or "Coverage" mode.

2. Pre-multiplied:
dst.RGB = src.RGB + dst.RGB * (1 - src.A)
Since the source RGB have already multiplied its alpha, only destination
RGB need to multiply it. This is the "Pre-multiplied" mode in DRM.

For the "None" blend mode in DRM, it means the pixel alpha is ignored
when compositing the layers, only the constant alpha for the composited
layer will take effects.

Reviewed-by: AngeloGioacchino Del Regno <[email protected]>
Reviewed-by: CK Hu <[email protected]>
Signed-off-by: Hsiao Chien Sung <[email protected]>
---
drivers/gpu/drm/mediatek/mtk_plane.c | 11 +++++++++++
1 file changed, 11 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c b/drivers/gpu/drm/mediatek/mtk_plane.c
index 1723d4333f371..5bf757a3ef202 100644
--- a/drivers/gpu/drm/mediatek/mtk_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_plane.c
@@ -346,6 +346,17 @@ int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane,
DRM_INFO("Create rotation property failed\n");
}

+ err = drm_plane_create_alpha_property(plane);
+ if (err)
+ DRM_ERROR("failed to create property: alpha\n");
+
+ err = drm_plane_create_blend_mode_property(plane,
+ BIT(DRM_MODE_BLEND_PREMULTI) |
+ BIT(DRM_MODE_BLEND_COVERAGE) |
+ BIT(DRM_MODE_BLEND_PIXEL_NONE));
+ if (err)
+ DRM_ERROR("failed to create property: blend_mode\n");
+
drm_plane_helper_add(plane, &mtk_plane_helper_funcs);

return 0;
--
2.18.0


2024-03-22 05:33:42

by Shawn Sung (宋孝謙)

[permalink] [raw]
Subject: [PATCH v6 13/14] drm/mediatek: Support CRC in OVL

From: Hsiao Chien Sung <[email protected]>

We choose OVL as the CRC generator from other hardware
components that are also capable of calculating CRCs,
since its frame done event triggers vblanks, it can be
used as a signal to know when is safe to retrieve CRC of
the frame.

Please note that position of the hardware component
that is chosen as CRC generator in the display path is
significant. For example, while OVL is the first module
in VDOSYS0, its CRC won't be affected by the modules
after it, which means effects applied by PQ, Gamma,
Dither or any other components after OVL won't be
calculated in CRC generation.

Signed-off-by: Hsiao Chien Sung <[email protected]>
---
drivers/gpu/drm/mediatek/mtk_ddp_comp.c | 3 +
drivers/gpu/drm/mediatek/mtk_disp_drv.h | 3 +
drivers/gpu/drm/mediatek/mtk_disp_ovl.c | 198 ++++++++++++++++++++++--
3 files changed, 194 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_ddp_comp.c
index 17b0364112922..cb71effda9c2a 100644
--- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.c
@@ -351,6 +351,9 @@ static const struct mtk_ddp_comp_funcs ddp_ovl = {
.clk_enable = mtk_ovl_clk_enable,
.clk_disable = mtk_ovl_clk_disable,
.config = mtk_ovl_config,
+ .crc_cnt = mtk_ovl_crc_cnt,
+ .crc_entry = mtk_ovl_crc_entry,
+ .crc_read = mtk_ovl_crc_read,
.start = mtk_ovl_start,
.stop = mtk_ovl_stop,
.register_vblank_cb = mtk_ovl_register_vblank_cb,
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_drv.h b/drivers/gpu/drm/mediatek/mtk_disp_drv.h
index 082ac18fe04aa..c476056a5cbb5 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_drv.h
+++ b/drivers/gpu/drm/mediatek/mtk_disp_drv.h
@@ -105,6 +105,9 @@ void mtk_ovl_enable_vblank(struct device *dev);
void mtk_ovl_disable_vblank(struct device *dev);
const u32 *mtk_ovl_get_formats(struct device *dev);
size_t mtk_ovl_get_num_formats(struct device *dev);
+size_t mtk_ovl_crc_cnt(struct device *dev);
+u32 *mtk_ovl_crc_entry(struct device *dev);
+void mtk_ovl_crc_read(struct device *dev);

void mtk_ovl_adaptor_add_comp(struct device *dev, struct mtk_mutex *mutex);
void mtk_ovl_adaptor_remove_comp(struct device *dev, struct mtk_mutex *mutex);
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
index a936f338ab79d..279e6193e7975 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
@@ -24,12 +24,20 @@
#define OVL_FME_CPL_INT BIT(1)
#define DISP_REG_OVL_INTSTA 0x0008
#define DISP_REG_OVL_EN 0x000c
+#define OVL_EN BIT(0)
+#define OVL_OP_8BIT_MODE BIT(4)
+#define OVL_HG_FOVL_CK_ON BIT(8)
+#define OVL_HF_FOVL_CK_ON BIT(10)
+#define DISP_REG_OVL_TRIG 0x0010
+#define OVL_CRC_EN BIT(8)
+#define OVL_CRC_CLR BIT(9)
#define DISP_REG_OVL_RST 0x0014
#define DISP_REG_OVL_ROI_SIZE 0x0020
#define DISP_REG_OVL_DATAPATH_CON 0x0024
#define OVL_LAYER_SMI_ID_EN BIT(0)
#define OVL_BGCLR_SEL_IN BIT(2)
#define OVL_LAYER_AFBC_EN(n) BIT(4+n)
+#define OVL_OUTPUT_CLAMP BIT(26)
#define DISP_REG_OVL_ROI_BGCLR 0x0028
#define DISP_REG_OVL_SRC_CON 0x002c
#define DISP_REG_OVL_CON(n) (0x0030 + 0x20 * (n))
@@ -42,7 +50,26 @@
#define DISP_REG_OVL_RDMA_CTRL(n) (0x00c0 + 0x20 * (n))
#define DISP_REG_OVL_RDMA_GMC(n) (0x00c8 + 0x20 * (n))
#define DISP_REG_OVL_ADDR_MT2701 0x0040
+#define DISP_REG_OVL_CRC 0x0270
+#define OVL_CRC_OUT_MASK GENMASK(30, 0)
#define DISP_REG_OVL_CLRFMT_EXT 0x02D0
+#define DISP_REG_OVL_CLRFMT_EXT1 0x02D8
+#define OVL_CLRFMT_EXT1_CSC_EN(n) (1 << (((n) * 4) + 1))
+#define DISP_REG_OVL_Y2R_PARA_R0(n) (0x0134 + 0x28 * (n))
+#define OVL_Y2R_PARA_C_CF_RMY (GENMASK(14, 0))
+#define DISP_REG_OVL_Y2R_PARA_G0(n) (0x013c + 0x28 * (n))
+#define OVL_Y2R_PARA_C_CF_GMU (GENMASK(30, 16))
+#define DISP_REG_OVL_Y2R_PARA_B1(n) (0x0148 + 0x28 * (n))
+#define OVL_Y2R_PARA_C_CF_BMV (GENMASK(14, 0))
+#define DISP_REG_OVL_Y2R_PARA_YUV_A_0(n) (0x014c + 0x28 * (n))
+#define OVL_Y2R_PARA_C_CF_YA (GENMASK(10, 0))
+#define OVL_Y2R_PARA_C_CF_UA (GENMASK(26, 16))
+#define DISP_REG_OVL_Y2R_PARA_YUV_A_1(n) (0x0150 + 0x28 * (n))
+#define OVL_Y2R_PARA_C_CF_VA (GENMASK(10, 0))
+#define DISP_REG_OVL_Y2R_PRE_ADD2(n) (0x0154 + 0x28 * (n))
+#define DISP_REG_OVL_R2R_R0(n) (0x0500 + 0x40 * (n))
+#define DISP_REG_OVL_R2R_G1(n) (0x0510 + 0x40 * (n))
+#define DISP_REG_OVL_R2R_B2(n) (0x0520 + 0x40 * (n))
#define DISP_REG_OVL_ADDR_MT8173 0x0f40
#define DISP_REG_OVL_ADDR(ovl, n) ((ovl)->data->addr + 0x20 * (n))
#define DISP_REG_OVL_HDR_ADDR(ovl, n) ((ovl)->data->addr + 0x20 * (n) + 0x04)
@@ -55,6 +82,8 @@
#define OVL_CON_CLRFMT_MAN BIT(23)
#define OVL_CON_BYTE_SWAP BIT(24)
#define OVL_CON_RGB_SWAP BIT(25)
+#define OVL_CON_MTX_AUTO_DIS BIT(26)
+#define OVL_CON_MTX_EN BIT(27)
#define OVL_CON_CLRFMT_RGB (1 << 12)
#define OVL_CON_CLRFMT_RGBA8888 (2 << 12)
#define OVL_CON_CLRFMT_ARGB8888 (3 << 12)
@@ -62,6 +91,7 @@
#define OVL_CON_CLRFMT_YUYV (5 << 12)
#define OVL_CON_MTX_YUV_TO_RGB (6 << 16)
#define OVL_CON_CLRFMT_PARGB8888 (OVL_CON_CLRFMT_ARGB8888 | OVL_CON_CLRFMT_MAN)
+#define OVL_CON_MTX_PROGRAMMABLE (8 << 16)
#define OVL_CON_CLRFMT_RGB565(ovl) ((ovl)->data->fmt_rgb565_is_0 ? \
0 : OVL_CON_CLRFMT_RGB)
#define OVL_CON_CLRFMT_RGB888(ovl) ((ovl)->data->fmt_rgb565_is_0 ? \
@@ -131,6 +161,10 @@ static const u32 mt8195_formats[] = {
DRM_FORMAT_YUYV,
};

+static const u32 mt8195_ovl_crc_ofs[] = {
+ DISP_REG_OVL_CRC,
+};
+
struct mtk_disp_ovl_data {
unsigned int addr;
unsigned int gmc_bits;
@@ -141,12 +175,15 @@ struct mtk_disp_ovl_data {
const u32 *formats;
size_t num_formats;
bool supports_clrfmt_ext;
+ const u32 *crc_ofs;
+ size_t crc_cnt;
};

/*
* struct mtk_disp_ovl - DISP_OVL driver structure
* @crtc: associated crtc to report vblank events to
* @data: platform data
+ * @crc: crc related information
*/
struct mtk_disp_ovl {
struct drm_crtc *crtc;
@@ -156,8 +193,31 @@ struct mtk_disp_ovl {
const struct mtk_disp_ovl_data *data;
void (*vblank_cb)(void *data);
void *vblank_cb_data;
+ resource_size_t regs_pa;
+ struct mtk_crtc_crc crc;
};

+size_t mtk_ovl_crc_cnt(struct device *dev)
+{
+ struct mtk_disp_ovl *ovl = dev_get_drvdata(dev);
+
+ return ovl->crc.cnt;
+}
+
+u32 *mtk_ovl_crc_entry(struct device *dev)
+{
+ struct mtk_disp_ovl *ovl = dev_get_drvdata(dev);
+
+ return ovl->crc.va;
+}
+
+void mtk_ovl_crc_read(struct device *dev)
+{
+ struct mtk_disp_ovl *ovl = dev_get_drvdata(dev);
+
+ mtk_crtc_read_crc(&ovl->crc, ovl->regs);
+}
+
static irqreturn_t mtk_disp_ovl_irq_handler(int irq, void *dev_id)
{
struct mtk_disp_ovl *priv = dev_id;
@@ -237,21 +297,40 @@ void mtk_ovl_clk_disable(struct device *dev)
void mtk_ovl_start(struct device *dev)
{
struct mtk_disp_ovl *ovl = dev_get_drvdata(dev);
+ unsigned int reg = readl(ovl->regs + DISP_REG_OVL_DATAPATH_CON);

- if (ovl->data->smi_id_en) {
- unsigned int reg;
+ if (ovl->data->smi_id_en)
+ reg |= OVL_LAYER_SMI_ID_EN;

- reg = readl(ovl->regs + DISP_REG_OVL_DATAPATH_CON);
- reg = reg | OVL_LAYER_SMI_ID_EN;
- writel_relaxed(reg, ovl->regs + DISP_REG_OVL_DATAPATH_CON);
+ /*
+ * When doing Y2R conversion, it's common to get an output
+ * that is larger than 10 bits (negative numbers).
+ * Enable this bit to clamp the output to 10 bits per channel
+ * (should always be enabled)
+ */
+ reg |= OVL_OUTPUT_CLAMP;
+ writel_relaxed(reg, ovl->regs + DISP_REG_OVL_DATAPATH_CON);
+
+ reg = OVL_EN;
+ if (ovl->data->crc_cnt) {
+ /* enable crc and its related clocks */
+ writel_relaxed(OVL_CRC_EN, ovl->regs + DISP_REG_OVL_TRIG);
+ reg |= OVL_OP_8BIT_MODE | OVL_HG_FOVL_CK_ON | OVL_HF_FOVL_CK_ON;
}
- writel_relaxed(0x1, ovl->regs + DISP_REG_OVL_EN);
+ writel_relaxed(reg, ovl->regs + DISP_REG_OVL_EN);
+
+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+ mtk_crtc_start_crc_cmdq(&ovl->crc);
+#endif
}

void mtk_ovl_stop(struct device *dev)
{
struct mtk_disp_ovl *ovl = dev_get_drvdata(dev);

+#if IS_REACHABLE(CONFIG_MTK_CMDQ)
+ mtk_crtc_stop_crc_cmdq(&ovl->crc);
+#endif
writel_relaxed(0x0, ovl->regs + DISP_REG_OVL_EN);
if (ovl->data->smi_id_en) {
unsigned int reg;
@@ -488,6 +567,83 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx,
(state->base.fb && !state->base.fb->format->has_alpha))
ignore_pixel_alpha = OVL_CONST_BLEND;

+ /*
+ * OVL only supports 8 bits data in CRC calculation, transform 10-bit
+ * RGB to 8-bit RGB by leveraging the ability of the Y2R (YUV-to-RGB)
+ * hardware to multiply coefficients, although there is nothing to do
+ * with the YUV format.
+ */
+ if (ovl->data->supports_clrfmt_ext) {
+ u32 y2r_coef = 0, y2r_offset = 0, r2r_coef = 0, csc_en = 0;
+
+ if (is_10bit_rgb(fmt)) {
+ con |= OVL_CON_MTX_AUTO_DIS | OVL_CON_MTX_EN | OVL_CON_MTX_PROGRAMMABLE;
+
+ /*
+ * Y2R coefficient setting
+ * bit 13 is 2^1, bit 12 is 2^0, bit 11 is 2^-1,
+ * bit 10 is 2^-2 = 0.25
+ */
+ y2r_coef = BIT(10);
+
+ /* -1 in 10bit */
+ y2r_offset = GENMASK(10, 0) - 1;
+
+ /*
+ * R2R coefficient setting
+ * bit 19 is 2^1, bit 18 is 2^0, bit 17 is 2^-1,
+ * bit 20 is 2^2 = 4
+ */
+ r2r_coef = BIT(20);
+
+ /* CSC_EN is for R2R */
+ csc_en = OVL_CLRFMT_EXT1_CSC_EN(idx);
+
+ /*
+ * 1. YUV input data - 1 and shift right for 2 bits to remove it
+ * [R'] [0.25 0 0] [Y in - 1]
+ * [G'] = [ 0 0.25 0] * [U in - 1]
+ * [B'] [ 0 0 0.25] [V in - 1]
+ *
+ * 2. shift left for 2 bit letting the last 2 bits become 0
+ * [R out] [ 4 0 0] [R']
+ * [G out] = [ 0 4 0] * [G']
+ * [B out] [ 0 0 4] [B']
+ */
+ }
+
+ mtk_ddp_write_mask(cmdq_pkt, y2r_coef,
+ &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_Y2R_PARA_R0(idx),
+ OVL_Y2R_PARA_C_CF_RMY);
+ mtk_ddp_write_mask(cmdq_pkt, (y2r_coef << 16),
+ &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_Y2R_PARA_G0(idx),
+ OVL_Y2R_PARA_C_CF_GMU);
+ mtk_ddp_write_mask(cmdq_pkt, y2r_coef,
+ &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_Y2R_PARA_B1(idx),
+ OVL_Y2R_PARA_C_CF_BMV);
+
+ mtk_ddp_write_mask(cmdq_pkt, y2r_offset,
+ &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_Y2R_PARA_YUV_A_0(idx),
+ OVL_Y2R_PARA_C_CF_YA);
+ mtk_ddp_write_mask(cmdq_pkt, (y2r_offset << 16),
+ &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_Y2R_PARA_YUV_A_0(idx),
+ OVL_Y2R_PARA_C_CF_UA);
+ mtk_ddp_write_mask(cmdq_pkt, y2r_offset,
+ &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_Y2R_PARA_YUV_A_1(idx),
+ OVL_Y2R_PARA_C_CF_VA);
+
+ mtk_ddp_write_relaxed(cmdq_pkt, r2r_coef,
+ &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_R2R_R0(idx));
+ mtk_ddp_write_relaxed(cmdq_pkt, r2r_coef,
+ &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_R2R_G1(idx));
+ mtk_ddp_write_relaxed(cmdq_pkt, r2r_coef,
+ &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_R2R_B2(idx));
+
+ mtk_ddp_write_mask(cmdq_pkt, csc_en,
+ &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_CLRFMT_EXT1,
+ OVL_CLRFMT_EXT1_CSC_EN(idx));
+ }
+
if (pending->rotation & DRM_MODE_REFLECT_Y) {
con |= OVL_CON_VIRT_FLIP;
addr += (pending->height - 1) * pending->pitch;
@@ -594,15 +750,31 @@ static int mtk_disp_ovl_probe(struct platform_device *pdev)
dev_err(dev, "failed to ioremap ovl\n");
return PTR_ERR(priv->regs);
}
+
+ priv->data = of_device_get_match_data(dev);
+ platform_set_drvdata(pdev, priv);
+
+ if (priv->data->crc_cnt) {
+ mtk_crtc_init_crc(&priv->crc,
+ priv->data->crc_ofs, priv->data->crc_cnt,
+ DISP_REG_OVL_TRIG, OVL_CRC_CLR);
+ }
+
#if IS_REACHABLE(CONFIG_MTK_CMDQ)
ret = cmdq_dev_get_client_reg(dev, &priv->cmdq_reg, 0);
if (ret)
dev_dbg(dev, "get mediatek,gce-client-reg fail!\n");
-#endif
-
- priv->data = of_device_get_match_data(dev);
- platform_set_drvdata(pdev, priv);

+ if (priv->data->crc_cnt) {
+ if (of_property_read_u32_index(dev->of_node,
+ "mediatek,gce-events", 0,
+ &priv->crc.cmdq_event)) {
+ dev_warn(dev, "failed to get gce-events for crc\n");
+ }
+ priv->crc.cmdq_reg = &priv->cmdq_reg;
+ mtk_crtc_create_crc_cmdq(dev, &priv->crc);
+ }
+#endif
ret = devm_request_irq(dev, irq, mtk_disp_ovl_irq_handler,
IRQF_TRIGGER_NONE, dev_name(dev), priv);
if (ret < 0) {
@@ -623,6 +795,10 @@ static int mtk_disp_ovl_probe(struct platform_device *pdev)

static void mtk_disp_ovl_remove(struct platform_device *pdev)
{
+ struct device *dev = &pdev->dev;
+ struct mtk_disp_ovl *ovl = dev_get_drvdata(dev);
+
+ mtk_crtc_destroy_crc(&ovl->crc);
component_del(&pdev->dev, &mtk_disp_ovl_component_ops);
pm_runtime_disable(&pdev->dev);
}
@@ -693,6 +869,8 @@ static const struct mtk_disp_ovl_data mt8195_ovl_driver_data = {
.formats = mt8195_formats,
.num_formats = ARRAY_SIZE(mt8195_formats),
.supports_clrfmt_ext = true,
+ .crc_ofs = mt8195_ovl_crc_ofs,
+ .crc_cnt = ARRAY_SIZE(mt8195_ovl_crc_ofs),
};

static const struct of_device_id mtk_disp_ovl_driver_dt_match[] = {
--
2.18.0


2024-03-22 06:44:16

by CK Hu (胡俊光)

[permalink] [raw]
Subject: Re: [PATCH v6 08/14] drm/mediatek: Support "Pre-multiplied" alpha blending in OVL

Hi, Shawn:

On Fri, 2024-03-22 at 13:28 +0800, Shawn Sung wrote:
> From: Hsiao Chien Sung <[email protected]>
>
> Support "Pre-multiplied" blend mode on MediaTek's chips.
> Before this patch, only the "coverage" mode is supported.
>
> Please refer to the description of the commit
> "drm/mediatek: Support alpha blending in display driver"
> for more information.
>
> Signed-off-by: Hsiao Chien Sung <[email protected]>
> ---
> drivers/gpu/drm/mediatek/mtk_disp_ovl.c | 84 +++++++++++++++++++++
> ----
> 1 file changed, 73 insertions(+), 11 deletions(-)
>
> diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> index 2a767a823c83a..b1e5d453316cc 100644
> --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> @@ -38,6 +38,7 @@
> #define DISP_REG_OVL_PITCH_MSB(n) (0x0040 + 0x20 * (n))
> #define OVL_PITCH_MSB_2ND_SUBBUF BIT(16)
> #define DISP_REG_OVL_PITCH(n) (0x0044 + 0x20
> * (n))
> +#define OVL_CONST_BLEND BIT(28)
> #define DISP_REG_OVL_RDMA_CTRL(n) (0x00c0 + 0x20 * (n))
> #define DISP_REG_OVL_RDMA_GMC(n) (0x00c8 + 0x20 * (n))
> #define DISP_REG_OVL_ADDR_MT2701 0x0040
> @@ -51,13 +52,16 @@
> #define GMC_THRESHOLD_HIGH ((1 << GMC_THRESHOLD_BITS) / 4)
> #define GMC_THRESHOLD_LOW ((1 << GMC_THRESHOLD_BITS) / 8)
>
> +#define OVL_CON_CLRFMT_MAN BIT(23)
> #define OVL_CON_BYTE_SWAP BIT(24)
> -#define OVL_CON_MTX_YUV_TO_RGB (6 << 16)
> +#define OVL_CON_RGB_SWAP BIT(25)
> #define OVL_CON_CLRFMT_RGB (1 << 12)
> #define OVL_CON_CLRFMT_RGBA8888 (2 << 12)
> #define OVL_CON_CLRFMT_ARGB8888 (3 << 12)
> #define OVL_CON_CLRFMT_UYVY (4 << 12)
> #define OVL_CON_CLRFMT_YUYV (5 << 12)
> +#define OVL_CON_MTX_YUV_TO_RGB (6 << 16)
> +#define OVL_CON_CLRFMT_PARGB8888 (OVL_CON_CLRFMT_ARGB8888 |
> OVL_CON_CLRFMT_MAN)
> #define OVL_CON_CLRFMT_RGB565(ovl) ((ovl)->data->fmt_rgb565_is_0 ?
> \
> 0 : OVL_CON_CLRFMT_RGB)
> #define OVL_CON_CLRFMT_RGB888(ovl) ((ovl)->data->fmt_rgb565_is_0 ?
> \
> @@ -71,6 +75,24 @@
> #define OVL_CON_VIRT_FLIP BIT(9)
> #define OVL_CON_HORZ_FLIP BIT(10)
>
> +#define OVL_COLOR_ALPHA GENMASK(31, 24)
> +
> +static inline bool is_10bit_rgb(u32 fmt)
> +{
> + switch (fmt) {
> + case DRM_FORMAT_XRGB2101010:
> + case DRM_FORMAT_ARGB2101010:
> + case DRM_FORMAT_RGBX1010102:
> + case DRM_FORMAT_RGBA1010102:
> + case DRM_FORMAT_XBGR2101010:
> + case DRM_FORMAT_ABGR2101010:
> + case DRM_FORMAT_BGRX1010102:
> + case DRM_FORMAT_BGRA1010102:
> + return true;
> + }
> + return false;
> +}
> +
> static const u32 mt8173_formats[] = {
> DRM_FORMAT_XRGB8888,
> DRM_FORMAT_ARGB8888,
> @@ -88,12 +110,20 @@ static const u32 mt8173_formats[] = {
> static const u32 mt8195_formats[] = {
> DRM_FORMAT_XRGB8888,
> DRM_FORMAT_ARGB8888,
> + DRM_FORMAT_XRGB2101010,

As I know, the 'X' in XRGB means garbage data. It's not alpha. And pre-
multiplied alpha formula is:

result = source RGB + (destination RGB * (1 - source alpha))

So pre-multiplied alpha need source alpha. I think XRGB is not related
to pre-multiplied alpha. So separate X-related format to another patch.

> DRM_FORMAT_ARGB2101010,
> DRM_FORMAT_BGRX8888,
> DRM_FORMAT_BGRA8888,
> + DRM_FORMAT_BGRX1010102,
> DRM_FORMAT_BGRA1010102,
> DRM_FORMAT_ABGR8888,
> DRM_FORMAT_XBGR8888,
> + DRM_FORMAT_XBGR2101010,
> + DRM_FORMAT_ABGR2101010,

It seems 10 bits format has no pre-multiplied alpha function. So
separate 10 bits format modification to another patch.

> + DRM_FORMAT_RGBX8888,
> + DRM_FORMAT_RGBA8888,

For RGBA8888, it both has coverage mode and pre-multiplied mode, so
it's not strongly related to pre-multiplied alpha. Separate this to
another patch which add support this new format.

> + DRM_FORMAT_RGBX1010102,
> + DRM_FORMAT_RGBA1010102,
> DRM_FORMAT_RGB888,
> DRM_FORMAT_BGR888,
> DRM_FORMAT_RGB565,
> @@ -253,9 +283,7 @@ static void mtk_ovl_set_bit_depth(struct device
> *dev, int idx, u32 format,
> reg = readl(ovl->regs + DISP_REG_OVL_CLRFMT_EXT);
> reg &= ~OVL_CON_CLRFMT_BIT_DEPTH_MASK(idx);
>
> - if (format == DRM_FORMAT_RGBA1010102 ||
> - format == DRM_FORMAT_BGRA1010102 ||
> - format == DRM_FORMAT_ARGB2101010)
> + if (is_10bit_rgb(format))
> bit_depth = OVL_CON_CLRFMT_10_BIT;
>
> reg |= OVL_CON_CLRFMT_BIT_DEPTH(bit_depth, idx);
> @@ -273,7 +301,13 @@ void mtk_ovl_config(struct device *dev, unsigned
> int w,
> if (w != 0 && h != 0)
> mtk_ddp_write_relaxed(cmdq_pkt, h << 16 | w, &ovl-
> >cmdq_reg, ovl->regs,
> DISP_REG_OVL_ROI_SIZE);
> - mtk_ddp_write_relaxed(cmdq_pkt, 0x0, &ovl->cmdq_reg, ovl->regs,
> DISP_REG_OVL_ROI_BGCLR);
> +
> + /*
> + * The background color should be opaque black (ARGB),
> + * otherwise there will be no effect with alpha blend
> + */
> + mtk_ddp_write_relaxed(cmdq_pkt, OVL_COLOR_ALPHA, &ovl-
> >cmdq_reg,
> + ovl->regs, DISP_REG_OVL_ROI_BGCLR);

The pre-multiplied alpha formula is:

result = source RGB + (destination RGB * (1 - source alpha))

It does not care destination alpha. Background color is the
destination, so describe more detail why need this modification. For
example, how does hardware calculate with back ground color?

>
> mtk_ddp_write(cmdq_pkt, 0x1, &ovl->cmdq_reg, ovl->regs,
> DISP_REG_OVL_RST);
> mtk_ddp_write(cmdq_pkt, 0x0, &ovl->cmdq_reg, ovl->regs,
> DISP_REG_OVL_RST);
> @@ -353,7 +387,8 @@ void mtk_ovl_layer_off(struct device *dev,
> unsigned int idx,
> DISP_REG_OVL_RDMA_CTRL(idx));
> }
>
> -static unsigned int ovl_fmt_convert(struct mtk_disp_ovl *ovl,
> unsigned int fmt)
> +static unsigned int ovl_fmt_convert(struct mtk_disp_ovl *ovl,
> unsigned int fmt,
> + unsigned int blend_mode)
> {
> /* The return value in switch "MEM_MODE_INPUT_FORMAT_XXX"
> * is defined in mediatek HW data sheet.
> @@ -372,17 +407,37 @@ static unsigned int ovl_fmt_convert(struct
> mtk_disp_ovl *ovl, unsigned int fmt)
> return OVL_CON_CLRFMT_RGB888(ovl) | OVL_CON_BYTE_SWAP;
> case DRM_FORMAT_RGBX8888:
> case DRM_FORMAT_RGBA8888:
> + return blend_mode == DRM_MODE_BLEND_COVERAGE ?
> + OVL_CON_CLRFMT_ARGB8888 :
> + OVL_CON_CLRFMT_PARGB8888;
> + case DRM_FORMAT_RGBX1010102:
> + case DRM_FORMAT_RGBA1010102:
> return OVL_CON_CLRFMT_ARGB8888;
> case DRM_FORMAT_BGRX8888:
> case DRM_FORMAT_BGRA8888:
> + return OVL_CON_BYTE_SWAP |
> + (blend_mode == DRM_MODE_BLEND_COVERAGE ?
> + OVL_CON_CLRFMT_ARGB8888 :
> + OVL_CON_CLRFMT_PARGB8888);
> + case DRM_FORMAT_BGRX1010102:
> case DRM_FORMAT_BGRA1010102:
> return OVL_CON_CLRFMT_ARGB8888 | OVL_CON_BYTE_SWAP;
> case DRM_FORMAT_XRGB8888:
> case DRM_FORMAT_ARGB8888:
> + return blend_mode == DRM_MODE_BLEND_COVERAGE ?
> + OVL_CON_CLRFMT_RGBA8888 :
> + OVL_CON_CLRFMT_PARGB8888;
> + case DRM_FORMAT_XRGB2101010:
> case DRM_FORMAT_ARGB2101010:
> return OVL_CON_CLRFMT_RGBA8888;
> case DRM_FORMAT_XBGR8888:
> case DRM_FORMAT_ABGR8888:
> + return OVL_CON_RGB_SWAP |
> + (blend_mode == DRM_MODE_BLEND_COVERAGE ?
> + OVL_CON_CLRFMT_RGBA8888 :
> + OVL_CON_CLRFMT_PARGB8888);
> + case DRM_FORMAT_XBGR2101010:
> + case DRM_FORMAT_ABGR2101010:
> return OVL_CON_CLRFMT_RGBA8888 | OVL_CON_BYTE_SWAP;
> case DRM_FORMAT_UYVY:
> return OVL_CON_CLRFMT_UYVY | OVL_CON_MTX_YUV_TO_RGB;
> @@ -404,6 +459,8 @@ void mtk_ovl_layer_config(struct device *dev,
> unsigned int idx,
> unsigned int fmt = pending->format;
> unsigned int offset = (pending->y << 16) | pending->x;
> unsigned int src_size = (pending->height << 16) | pending-
> >width;
> + unsigned int blend_mode = state->base.pixel_blend_mode;
> + unsigned int ignore_pixel_alpha = 0;
> unsigned int con;
> bool is_afbc = pending->modifier != DRM_FORMAT_MOD_LINEAR;
> union overlay_pitch {
> @@ -421,9 +478,14 @@ void mtk_ovl_layer_config(struct device *dev,
> unsigned int idx,
> return;
> }
>
> - con = ovl_fmt_convert(ovl, fmt);
> - if (state->base.fb && state->base.fb->format->has_alpha)
> - con |= OVL_CON_AEN | OVL_CON_ALPHA;
> + con = ovl_fmt_convert(ovl, fmt, blend_mode);
> + if (state->base.fb) {
> + con |= OVL_CON_AEN;
> + con |= state->base.alpha & OVL_CON_ALPHA;

Now support pixel alpha, and this seems to support plane alpha. So
separate this to another patch. If possible, describe how plane alpha
calculate with pixel alpha.

> + }
> +
> + if (state->base.fb && !state->base.fb->format->has_alpha)
> + ignore_pixel_alpha = OVL_CONST_BLEND;

Ditto.

Regards,
CK

>
> if (pending->rotation & DRM_MODE_REFLECT_Y) {
> con |= OVL_CON_VIRT_FLIP;
> @@ -440,8 +502,8 @@ void mtk_ovl_layer_config(struct device *dev,
> unsigned int idx,
>
> mtk_ddp_write_relaxed(cmdq_pkt, con, &ovl->cmdq_reg, ovl->regs,
> DISP_REG_OVL_CON(idx));
> - mtk_ddp_write_relaxed(cmdq_pkt, overlay_pitch.split_pitch.lsb,
> &ovl->cmdq_reg, ovl->regs,
> - DISP_REG_OVL_PITCH(idx));
> + mtk_ddp_write_relaxed(cmdq_pkt, overlay_pitch.split_pitch.lsb |
> ignore_pixel_alpha,
> + &ovl->cmdq_reg, ovl->regs,
> DISP_REG_OVL_PITCH(idx));
> mtk_ddp_write_relaxed(cmdq_pkt, src_size, &ovl->cmdq_reg, ovl-
> >regs,
> DISP_REG_OVL_SRC_SIZE(idx));
> mtk_ddp_write_relaxed(cmdq_pkt, offset, &ovl->cmdq_reg, ovl-
> >regs,

2024-03-22 09:03:27

by CK Hu (胡俊光)

[permalink] [raw]
Subject: Re: [PATCH v6 04/14] drm/mediatek: Add DRM_MODE_ROTATE_0 to rotation property

Hi, Shawn:

On Fri, 2024-03-22 at 13:28 +0800, Shawn Sung wrote:
> From: Hsiao Chien Sung <[email protected]>
>
> Always add DRM_MODE_ROTATE_0 to rotation property to meet
> IGT's (Intel GPU Tools) requirement.

Reviewed-by: CK Hu <[email protected]>

>
> Reviewed-by: AngeloGioacchino Del Regno <
> [email protected]>
> Signed-off-by: Hsiao Chien Sung <[email protected]>
> ---
> drivers/gpu/drm/mediatek/mtk_ddp_comp.h | 6 +++++-
> drivers/gpu/drm/mediatek/mtk_disp_ovl.c | 21 +++++++++------------
> drivers/gpu/drm/mediatek/mtk_plane.c | 2 +-
> 3 files changed, 15 insertions(+), 14 deletions(-)
>
> diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
> b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
> index 26236691ce4c2..f7fe2e08dc8e2 100644
> --- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
> +++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
> @@ -192,7 +192,11 @@ unsigned int
> mtk_ddp_comp_supported_rotations(struct mtk_ddp_comp *comp)
> if (comp->funcs && comp->funcs->supported_rotations)
> return comp->funcs->supported_rotations(comp->dev);
>
> - return 0;
> + /*
> + * In order to pass IGT tests, DRM_MODE_ROTATE_0 is required
> when
> + * rotation is not supported.
> + */
> + return DRM_MODE_ROTATE_0;
> }
>
> static inline unsigned int mtk_ddp_comp_layer_nr(struct mtk_ddp_comp
> *comp)
> diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> index 0ebeaf9830d83..2a767a823c83a 100644
> --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> @@ -288,6 +288,10 @@ unsigned int mtk_ovl_layer_nr(struct device
> *dev)
>
> unsigned int mtk_ovl_supported_rotations(struct device *dev)
> {
> + /*
> + * although currently OVL can only do reflection,
> + * reflect x + reflect y = rotate 180
> + */
> return DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_180 |
> DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y;
> }
> @@ -296,27 +300,20 @@ int mtk_ovl_layer_check(struct device *dev,
> unsigned int idx,
> struct mtk_plane_state *mtk_state)
> {
> struct drm_plane_state *state = &mtk_state->base;
> - unsigned int rotation = 0;
>
> - rotation = drm_rotation_simplify(state->rotation,
> - DRM_MODE_ROTATE_0 |
> - DRM_MODE_REFLECT_X |
> - DRM_MODE_REFLECT_Y);
> - rotation &= ~DRM_MODE_ROTATE_0;
> -
> - /* We can only do reflection, not rotation */
> - if ((rotation & DRM_MODE_ROTATE_MASK) != 0)
> + /* check if any unsupported rotation is set */
> + if (state->rotation & ~mtk_ovl_supported_rotations(dev))
> return -EINVAL;
>
> /*
> * TODO: Rotating/reflecting YUV buffers is not supported at
> this time.
> * Only RGB[AX] variants are supported.
> + * Since DRM_MODE_ROTATE_0 means "no rotation", we
> should not
> + * reject layers with this property.
> */
> - if (state->fb->format->is_yuv && rotation != 0)
> + if (state->fb->format->is_yuv && (state->rotation &
> ~DRM_MODE_ROTATE_0))
> return -EINVAL;
>
> - state->rotation = rotation;
> -
> return 0;
> }
>
> diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c
> b/drivers/gpu/drm/mediatek/mtk_plane.c
> index a74b26d359857..1723d4333f371 100644
> --- a/drivers/gpu/drm/mediatek/mtk_plane.c
> +++ b/drivers/gpu/drm/mediatek/mtk_plane.c
> @@ -338,7 +338,7 @@ int mtk_plane_init(struct drm_device *dev, struct
> drm_plane *plane,
> return err;
> }
>
> - if (supported_rotations & ~DRM_MODE_ROTATE_0) {
> + if (supported_rotations) {
> err = drm_plane_create_rotation_property(plane,
> DRM_MODE_ROTAT
> E_0,
> supported_rota
> tions);

2024-03-22 09:27:22

by CK Hu (胡俊光)

[permalink] [raw]
Subject: Re: [PATCH v6 09/14] drm/mediatek: Support "Pre-multiplied" alpha blending in Mixer

Hi, Shawn:

On Fri, 2024-03-22 at 13:28 +0800, Shawn Sung wrote:
> From: Hsiao Chien Sung <[email protected]>
>
> Support "Pre-multiplied" blend mode on MediaTek's chips.
> Before this patch, only the "Coverage" mode is supported.
>
> Please refer to the description of the commit
> "drm/mediatek: Support alpha blending in display driver"
> for more information.
>
> Signed-off-by: Hsiao Chien Sung <[email protected]>
> ---
> drivers/gpu/drm/mediatek/mtk_ethdr.c | 25 ++++++++++++++++++-------
> 1 file changed, 18 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/gpu/drm/mediatek/mtk_ethdr.c
> b/drivers/gpu/drm/mediatek/mtk_ethdr.c
> index 6bf398850e85f..4b12ca285e84b 100644
> --- a/drivers/gpu/drm/mediatek/mtk_ethdr.c
> +++ b/drivers/gpu/drm/mediatek/mtk_ethdr.c
> @@ -5,6 +5,7 @@
>
> #include <drm/drm_fourcc.h>
> #include <drm/drm_framebuffer.h>
> +#include <drm/drm_blend.h>
> #include <linux/clk.h>
> #include <linux/component.h>
> #include <linux/of.h>
> @@ -35,6 +36,7 @@
> #define MIX_SRC_L0_EN BIT(0)
> #define MIX_L_SRC_CON(n) (0x28 + 0x18 * (n))
> #define NON_PREMULTI_SOURCE (2 << 12)
> +#define PREMULTI_SOURCE (3 << 12)
> #define MIX_L_SRC_SIZE(n) (0x30 + 0x18 * (n))
> #define MIX_L_SRC_OFFSET(n) (0x34 + 0x18 * (n))
> #define MIX_FUNC_DCM0 0x120
> @@ -153,7 +155,8 @@ void mtk_ethdr_layer_config(struct device *dev,
> unsigned int idx,
> struct mtk_plane_pending_state *pending = &state->pending;
> unsigned int offset = (pending->x & 1) << 31 | pending->y << 16
> | pending->x;
> unsigned int align_width = ALIGN_DOWN(pending->width, 2);
> - unsigned int alpha_con = 0;
> + unsigned int mix_con = NON_PREMULTI_SOURCE;

I think you should not assign here. You should choose one of
PREMULTI_SOURCE or NON_PREMULTI_SOURCE later.

> + bool replace_src_a = false;
>
> dev_dbg(dev, "%s+ idx:%d", __func__, idx);
>
> @@ -170,19 +173,27 @@ void mtk_ethdr_layer_config(struct device *dev,
> unsigned int idx,
> return;
> }
>
> - if (state->base.fb && state->base.fb->format->has_alpha)
> - alpha_con = MIXER_ALPHA_AEN | MIXER_ALPHA;
> + mix_con |= MIXER_ALPHA_AEN | (state->base.alpha & MIXER_ALPHA);

Now support pixel alpha, and this seems to support plane alpha.
Separate this to another patch.

>
> - mtk_mmsys_mixer_in_config(priv->mmsys_dev, idx + 1, alpha_con ?
> false : true,
> - DEFAULT_9BIT_ALPHA,
> + if (state->base.pixel_blend_mode != DRM_MODE_BLEND_COVERAGE)
> + mix_con |= PREMULTI_SOURCE;
> +
> + if (state->base.fb && !state->base.fb->format->has_alpha) {
> + /*
> + * Mixer doesn't support CONST_BLD mode,
> + * use a trick to make the output equivalent
> + */
> + replace_src_a = true;

Ditto.

Regards,
CK

> + }
> +
> + mtk_mmsys_mixer_in_config(priv->mmsys_dev, idx + 1,
> replace_src_a, MIXER_ALPHA,
> pending->x & 1 ?
> MIXER_INX_MODE_EVEN_EXTEND :
> MIXER_INX_MODE_BYPASS, align_width /
> 2 - 1, cmdq_pkt);
>
> mtk_ddp_write(cmdq_pkt, pending->height << 16 | align_width,
> &mixer->cmdq_base,
> mixer->regs, MIX_L_SRC_SIZE(idx));
> mtk_ddp_write(cmdq_pkt, offset, &mixer->cmdq_base, mixer->regs,
> MIX_L_SRC_OFFSET(idx));
> - mtk_ddp_write_mask(cmdq_pkt, alpha_con, &mixer->cmdq_base,
> mixer->regs, MIX_L_SRC_CON(idx),
> - 0x1ff);
> + mtk_ddp_write(cmdq_pkt, mix_con, &mixer->cmdq_base, mixer-
> >regs, MIX_L_SRC_CON(idx));
> mtk_ddp_write_mask(cmdq_pkt, BIT(idx), &mixer->cmdq_base,
> mixer->regs, MIX_SRC_CON,
> BIT(idx));
> }

2024-03-22 09:37:20

by CK Hu (胡俊光)

[permalink] [raw]
Subject: Re: [PATCH v6 07/14] drm/mediatek: Support alpha blending in display driver

Hi, Shawn:

On Fri, 2024-03-22 at 13:28 +0800, Shawn Sung wrote:
> From: Hsiao Chien Sung <[email protected]>
>
> Support "Pre-multiplied" and "None" blend mode on MediaTek's chips by
> adding correct blend mode property when the planes init.
> Before this patch, only the "Coverage" mode (default) is supported.
>
> For more information, there are three pixel blend modes in DRM
> driver:
> "None", "Pre-multiplied", and "Coverage".
>
> To understand the difference between these modes, let's take a look
> at
> the following two approaches to do alpha blending:
>
> 1. Straight:
> dst.RGB = src.RGB * src.A + dst.RGB * (1 - src.A)
> This is straightforward and easy to understand, when the source layer
> is
> compositing with the destination layer, it's alpha will affect the
> result. This is also known as "post-multiplied", or "Coverage" mode.
>
> 2. Pre-multiplied:
> dst.RGB = src.RGB + dst.RGB * (1 - src.A)
> Since the source RGB have already multiplied its alpha, only
> destination
> RGB need to multiply it. This is the "Pre-multiplied" mode in DRM.
>
> For the "None" blend mode in DRM, it means the pixel alpha is ignored
> when compositing the layers, only the constant alpha for the
> composited
> layer will take effects.
>
> Reviewed-by: AngeloGioacchino Del Regno <
> [email protected]>
> Reviewed-by: CK Hu <[email protected]>
> Signed-off-by: Hsiao Chien Sung <[email protected]>
> ---
> drivers/gpu/drm/mediatek/mtk_plane.c | 11 +++++++++++
> 1 file changed, 11 insertions(+)
>
> diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c
> b/drivers/gpu/drm/mediatek/mtk_plane.c
> index 1723d4333f371..5bf757a3ef202 100644
> --- a/drivers/gpu/drm/mediatek/mtk_plane.c
> +++ b/drivers/gpu/drm/mediatek/mtk_plane.c
> @@ -346,6 +346,17 @@ int mtk_plane_init(struct drm_device *dev,
> struct drm_plane *plane,
> DRM_INFO("Create rotation property failed\n");
> }
>
> + err = drm_plane_create_alpha_property(plane);
> + if (err)
> + DRM_ERROR("failed to create property: alpha\n");
> +
> + err = drm_plane_create_blend_mode_property(plane,
> + BIT(DRM_MODE_BLEND_P
> REMULTI) |
> + BIT(DRM_MODE_BLEND_C
> OVERAGE) |
> + BIT(DRM_MODE_BLEND_P
> IXEL_NONE));

After all sub driver support these function, then create blend
property. So move this patch after all sub driver support these blend
mode.

Regards,
CK

> + if (err)
> + DRM_ERROR("failed to create property: blend_mode\n");
> +
> drm_plane_helper_add(plane, &mtk_plane_helper_funcs);
>
> return 0;

2024-03-22 09:39:24

by CK Hu (胡俊光)

[permalink] [raw]
Subject: Re: [PATCH v6 10/14] drm/mediatek: Support "None" alpha blending in OVL

Hi, Shawn:

On Fri, 2024-03-22 at 13:28 +0800, Shawn Sung wrote:
> From: Hsiao Chien Sung <[email protected]>
>
> Support "None" blend mode on MediaTek's chips.
>
> Please refer to the description of the commit
> "drm/mediatek: Support alpha blending in display driver"
> for more information.

Reviewed-by: CK Hu <[email protected]>

>
> Signed-off-by: Hsiao Chien Sung <[email protected]>
> ---
> drivers/gpu/drm/mediatek/mtk_disp_ovl.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> index b1e5d453316cc..a936f338ab79d 100644
> --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> @@ -484,7 +484,8 @@ void mtk_ovl_layer_config(struct device *dev,
> unsigned int idx,
> con |= state->base.alpha & OVL_CON_ALPHA;
> }
>
> - if (state->base.fb && !state->base.fb->format->has_alpha)
> + if (blend_mode == DRM_MODE_BLEND_PIXEL_NONE ||
> + (state->base.fb && !state->base.fb->format->has_alpha))
> ignore_pixel_alpha = OVL_CONST_BLEND;
>
> if (pending->rotation & DRM_MODE_REFLECT_Y) {

2024-03-25 08:48:19

by CK Hu (胡俊光)

[permalink] [raw]
Subject: Re: [PATCH v6 04/14] drm/mediatek: Add DRM_MODE_ROTATE_0 to rotation property

Hi, Shawn:

On Fri, 2024-03-22 at 17:02 +0800, CK Hu wrote:
> Hi, Shawn:
>
> On Fri, 2024-03-22 at 13:28 +0800, Shawn Sung wrote:
> > From: Hsiao Chien Sung <[email protected]>
> >
> > Always add DRM_MODE_ROTATE_0 to rotation property to meet
> > IGT's (Intel GPU Tools) requirement.
>
> Reviewed-by: CK Hu <[email protected]>
>
> >
> > Reviewed-by: AngeloGioacchino Del Regno <
> > [email protected]>
> > Signed-off-by: Hsiao Chien Sung <[email protected]>
> > ---
> > drivers/gpu/drm/mediatek/mtk_ddp_comp.h | 6 +++++-
> > drivers/gpu/drm/mediatek/mtk_disp_ovl.c | 21 +++++++++------------
> > drivers/gpu/drm/mediatek/mtk_plane.c | 2 +-
> > 3 files changed, 15 insertions(+), 14 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
> > b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
> > index 26236691ce4c2..f7fe2e08dc8e2 100644
> > --- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
> > +++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
> > @@ -192,7 +192,11 @@ unsigned int
> > mtk_ddp_comp_supported_rotations(struct mtk_ddp_comp *comp)
> > if (comp->funcs && comp->funcs->supported_rotations)
> > return comp->funcs->supported_rotations(comp->dev);
> >
> > - return 0;
> > + /*
> > + * In order to pass IGT tests, DRM_MODE_ROTATE_0 is required
> > when
> > + * rotation is not supported.
> > + */
> > + return DRM_MODE_ROTATE_0;
> > }
> >
> > static inline unsigned int mtk_ddp_comp_layer_nr(struct
> > mtk_ddp_comp
> > *comp)
> > diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> > b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> > index 0ebeaf9830d83..2a767a823c83a 100644
> > --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> > +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> > @@ -288,6 +288,10 @@ unsigned int mtk_ovl_layer_nr(struct device
> > *dev)
> >
> > unsigned int mtk_ovl_supported_rotations(struct device *dev)
> > {
> > + /*
> > + * although currently OVL can only do reflection,
> > + * reflect x + reflect y = rotate 180
> > + */

Sorry, this comment is not related to DRM_MODE_ROTATE_0, so after
removing this comment,

Reviewed-by: CK Hu <[email protected]>

> > return DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_180 |
> > DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y;
> > }
> > @@ -296,27 +300,20 @@ int mtk_ovl_layer_check(struct device *dev,
> > unsigned int idx,
> > struct mtk_plane_state *mtk_state)
> > {
> > struct drm_plane_state *state = &mtk_state->base;
> > - unsigned int rotation = 0;
> >
> > - rotation = drm_rotation_simplify(state->rotation,
> > - DRM_MODE_ROTATE_0 |
> > - DRM_MODE_REFLECT_X |
> > - DRM_MODE_REFLECT_Y);
> > - rotation &= ~DRM_MODE_ROTATE_0;
> > -
> > - /* We can only do reflection, not rotation */
> > - if ((rotation & DRM_MODE_ROTATE_MASK) != 0)
> > + /* check if any unsupported rotation is set */
> > + if (state->rotation & ~mtk_ovl_supported_rotations(dev))
> > return -EINVAL;
> >
> > /*
> > * TODO: Rotating/reflecting YUV buffers is not supported at
> > this time.
> > * Only RGB[AX] variants are supported.
> > + * Since DRM_MODE_ROTATE_0 means "no rotation", we
> > should not
> > + * reject layers with this property.
> > */
> > - if (state->fb->format->is_yuv && rotation != 0)
> > + if (state->fb->format->is_yuv && (state->rotation &
> > ~DRM_MODE_ROTATE_0))
> > return -EINVAL;
> >
> > - state->rotation = rotation;
> > -
> > return 0;
> > }
> >
> > diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c
> > b/drivers/gpu/drm/mediatek/mtk_plane.c
> > index a74b26d359857..1723d4333f371 100644
> > --- a/drivers/gpu/drm/mediatek/mtk_plane.c
> > +++ b/drivers/gpu/drm/mediatek/mtk_plane.c
> > @@ -338,7 +338,7 @@ int mtk_plane_init(struct drm_device *dev,
> > struct
> > drm_plane *plane,
> > return err;
> > }
> >
> > - if (supported_rotations & ~DRM_MODE_ROTATE_0) {
> > + if (supported_rotations) {
> > err = drm_plane_create_rotation_property(plane,
> > DRM_MODE_ROTAT
> > E_0,
> > supported_rota
> > tions);

2024-03-26 06:12:28

by CK Hu (胡俊光)

[permalink] [raw]
Subject: Re: [PATCH v6 13/14] drm/mediatek: Support CRC in OVL

Hi, Shawn:

On Fri, 2024-03-22 at 13:28 +0800, Shawn Sung wrote:
> From: Hsiao Chien Sung <[email protected]>
>
> We choose OVL as the CRC generator from other hardware
> components that are also capable of calculating CRCs,
> since its frame done event triggers vblanks, it can be
> used as a signal to know when is safe to retrieve CRC of
> the frame.
>
> Please note that position of the hardware component
> that is chosen as CRC generator in the display path is
> significant. For example, while OVL is the first module
> in VDOSYS0, its CRC won't be affected by the modules
> after it, which means effects applied by PQ, Gamma,
> Dither or any other components after OVL won't be
> calculated in CRC generation.
>
> Signed-off-by: Hsiao Chien Sung <[email protected]>
> ---
> drivers/gpu/drm/mediatek/mtk_ddp_comp.c | 3 +
> drivers/gpu/drm/mediatek/mtk_disp_drv.h | 3 +
> drivers/gpu/drm/mediatek/mtk_disp_ovl.c | 198
> ++++++++++++++++++++++--
> 3 files changed, 194 insertions(+), 10 deletions(-)
>
> diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.c
> b/drivers/gpu/drm/mediatek/mtk_ddp_comp.c
> index 17b0364112922..cb71effda9c2a 100644
> --- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.c
> +++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.c
> @@ -351,6 +351,9 @@ static const struct mtk_ddp_comp_funcs ddp_ovl =
> {
> .clk_enable = mtk_ovl_clk_enable,
> .clk_disable = mtk_ovl_clk_disable,
> .config = mtk_ovl_config,
> + .crc_cnt = mtk_ovl_crc_cnt,
> + .crc_entry = mtk_ovl_crc_entry,
> + .crc_read = mtk_ovl_crc_read,
> .start = mtk_ovl_start,
> .stop = mtk_ovl_stop,
> .register_vblank_cb = mtk_ovl_register_vblank_cb,
> diff --git a/drivers/gpu/drm/mediatek/mtk_disp_drv.h
> b/drivers/gpu/drm/mediatek/mtk_disp_drv.h
> index 082ac18fe04aa..c476056a5cbb5 100644
> --- a/drivers/gpu/drm/mediatek/mtk_disp_drv.h
> +++ b/drivers/gpu/drm/mediatek/mtk_disp_drv.h
> @@ -105,6 +105,9 @@ void mtk_ovl_enable_vblank(struct device *dev);
> void mtk_ovl_disable_vblank(struct device *dev);
> const u32 *mtk_ovl_get_formats(struct device *dev);
> size_t mtk_ovl_get_num_formats(struct device *dev);
> +size_t mtk_ovl_crc_cnt(struct device *dev);
> +u32 *mtk_ovl_crc_entry(struct device *dev);
> +void mtk_ovl_crc_read(struct device *dev);
>
> void mtk_ovl_adaptor_add_comp(struct device *dev, struct mtk_mutex
> *mutex);
> void mtk_ovl_adaptor_remove_comp(struct device *dev, struct
> mtk_mutex *mutex);
> diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> index a936f338ab79d..279e6193e7975 100644
> --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> @@ -24,12 +24,20 @@
> #define OVL_FME_CPL_INT BIT(1)
> #define DISP_REG_OVL_INTSTA 0x0008
> #define DISP_REG_OVL_EN 0x000c
> +#define OVL_EN BIT(0)
> +#define OVL_OP_8BIT_MODE BIT(4)
> +#define OVL_HG_FOVL_CK_ON BIT(8)
> +#define OVL_HF_FOVL_CK_ON BIT(10)
> +#define DISP_REG_OVL_TRIG 0x0010
> +#define OVL_CRC_EN BIT(8)
> +#define OVL_CRC_CLR BIT(9)
> #define DISP_REG_OVL_RST 0x0014
> #define DISP_REG_OVL_ROI_SIZE 0x0020
> #define DISP_REG_OVL_DATAPATH_CON 0x0024
> #define OVL_LAYER_SMI_ID_EN BIT(0)
> #define OVL_BGCLR_SEL_IN BIT(2)
> #define OVL_LAYER_AFBC_EN(n) BIT(4+n)
> +#define OVL_OUTPUT_CLAMP BIT(26)
> #define DISP_REG_OVL_ROI_BGCLR 0x0028
> #define DISP_REG_OVL_SRC_CON 0x002c
> #define DISP_REG_OVL_CON(n) (0x0030 + 0x20 * (n))
> @@ -42,7 +50,26 @@
> #define DISP_REG_OVL_RDMA_CTRL(n) (0x00c0 + 0x20 * (n))
> #define DISP_REG_OVL_RDMA_GMC(n) (0x00c8 + 0x20 * (n))
> #define DISP_REG_OVL_ADDR_MT2701 0x0040
> +#define DISP_REG_OVL_CRC 0x0270
> +#define OVL_CRC_OUT_MASK GENMASK(30, 0)
> #define DISP_REG_OVL_CLRFMT_EXT 0x02D0
> +#define DISP_REG_OVL_CLRFMT_EXT1 0x02D8
> +#define OVL_CLRFMT_EXT1_CSC_EN(n) (1 << (((n) *
> 4) + 1))
> +#define DISP_REG_OVL_Y2R_PARA_R0(n) (0x0134 + 0x28 * (n))
> +#define OVL_Y2R_PARA_C_CF_RMY (GENMAS
> K(14, 0))
> +#define DISP_REG_OVL_Y2R_PARA_G0(n) (0x013c + 0x28 * (n))
> +#define OVL_Y2R_PARA_C_CF_GMU (GENMAS
> K(30, 16))
> +#define DISP_REG_OVL_Y2R_PARA_B1(n) (0x0148 + 0x28 * (n))
> +#define OVL_Y2R_PARA_C_CF_BMV (GENMAS
> K(14, 0))
> +#define DISP_REG_OVL_Y2R_PARA_YUV_A_0(n) (0x014c + 0x28 * (n))
> +#define OVL_Y2R_PARA_C_CF_YA (GENMASK(10,
> 0))
> +#define OVL_Y2R_PARA_C_CF_UA (GENMASK(26,
> 16))
> +#define DISP_REG_OVL_Y2R_PARA_YUV_A_1(n) (0x0150 + 0x28 * (n))
> +#define OVL_Y2R_PARA_C_CF_VA (GENMASK(10,
> 0))
> +#define DISP_REG_OVL_Y2R_PRE_ADD2(n) (0x0154 + 0x28 * (n))
> +#define DISP_REG_OVL_R2R_R0(n) (0x0500 + 0x40
> * (n))
> +#define DISP_REG_OVL_R2R_G1(n) (0x0510 + 0x40
> * (n))
> +#define DISP_REG_OVL_R2R_B2(n) (0x0520 + 0x40
> * (n))
> #define DISP_REG_OVL_ADDR_MT8173 0x0f40
> #define DISP_REG_OVL_ADDR(ovl, n) ((ovl)->data->addr +
> 0x20 * (n))
> #define DISP_REG_OVL_HDR_ADDR(ovl, n) ((ovl)->data-
> >addr + 0x20 * (n) + 0x04)
> @@ -55,6 +82,8 @@
> #define OVL_CON_CLRFMT_MAN BIT(23)
> #define OVL_CON_BYTE_SWAP BIT(24)
> #define OVL_CON_RGB_SWAP BIT(25)
> +#define OVL_CON_MTX_AUTO_DIS BIT(26)
> +#define OVL_CON_MTX_EN BIT(27)
> #define OVL_CON_CLRFMT_RGB (1 << 12)
> #define OVL_CON_CLRFMT_RGBA8888 (2 << 12)
> #define OVL_CON_CLRFMT_ARGB8888 (3 << 12)
> @@ -62,6 +91,7 @@
> #define OVL_CON_CLRFMT_YUYV (5 << 12)
> #define OVL_CON_MTX_YUV_TO_RGB (6 << 16)
> #define OVL_CON_CLRFMT_PARGB8888 (OVL_CON_CLRFMT_ARGB8888 |
> OVL_CON_CLRFMT_MAN)
> +#define OVL_CON_MTX_PROGRAMMABLE (8 << 16)
> #define OVL_CON_CLRFMT_RGB565(ovl) ((ovl)->data->fmt_rgb565_is_0 ?
> \
> 0 : OVL_CON_CLRFMT_RGB)
> #define OVL_CON_CLRFMT_RGB888(ovl) ((ovl)->data->fmt_rgb565_is_0 ?
> \
> @@ -131,6 +161,10 @@ static const u32 mt8195_formats[] = {
> DRM_FORMAT_YUYV,
> };
>
> +static const u32 mt8195_ovl_crc_ofs[] = {
> + DISP_REG_OVL_CRC,
> +};
> +
> struct mtk_disp_ovl_data {
> unsigned int addr;
> unsigned int gmc_bits;
> @@ -141,12 +175,15 @@ struct mtk_disp_ovl_data {
> const u32 *formats;
> size_t num_formats;
> bool supports_clrfmt_ext;
> + const u32 *crc_ofs;
> + size_t crc_cnt;
> };
>
> /*
> * struct mtk_disp_ovl - DISP_OVL driver structure
> * @crtc: associated crtc to report vblank events to
> * @data: platform data
> + * @crc: crc related information
> */
> struct mtk_disp_ovl {
> struct drm_crtc *crtc;
> @@ -156,8 +193,31 @@ struct mtk_disp_ovl {
> const struct mtk_disp_ovl_data *data;
> void (*vblank_cb)(void *data);
> void *vblank_cb_data;
> + resource_size_t regs_pa;
> + struct mtk_crtc_crc crc;
> };
>
> +size_t mtk_ovl_crc_cnt(struct device *dev)
> +{
> + struct mtk_disp_ovl *ovl = dev_get_drvdata(dev);
> +
> + return ovl->crc.cnt;
> +}
> +
> +u32 *mtk_ovl_crc_entry(struct device *dev)
> +{
> + struct mtk_disp_ovl *ovl = dev_get_drvdata(dev);
> +
> + return ovl->crc.va;
> +}
> +
> +void mtk_ovl_crc_read(struct device *dev)
> +{
> + struct mtk_disp_ovl *ovl = dev_get_drvdata(dev);
> +
> + mtk_crtc_read_crc(&ovl->crc, ovl->regs);
> +}
> +
> static irqreturn_t mtk_disp_ovl_irq_handler(int irq, void *dev_id)
> {
> struct mtk_disp_ovl *priv = dev_id;
> @@ -237,21 +297,40 @@ void mtk_ovl_clk_disable(struct device *dev)
> void mtk_ovl_start(struct device *dev)
> {
> struct mtk_disp_ovl *ovl = dev_get_drvdata(dev);
> + unsigned int reg = readl(ovl->regs +
> DISP_REG_OVL_DATAPATH_CON);
>
> - if (ovl->data->smi_id_en) {
> - unsigned int reg;
> + if (ovl->data->smi_id_en)
> + reg |= OVL_LAYER_SMI_ID_EN;
>
> - reg = readl(ovl->regs + DISP_REG_OVL_DATAPATH_CON);
> - reg = reg | OVL_LAYER_SMI_ID_EN;
> - writel_relaxed(reg, ovl->regs +
> DISP_REG_OVL_DATAPATH_CON);
> + /*
> + * When doing Y2R conversion, it's common to get an output
> + * that is larger than 10 bits (negative numbers).
> + * Enable this bit to clamp the output to 10 bits per channel
> + * (should always be enabled)
> + */
> + reg |= OVL_OUTPUT_CLAMP;
> + writel_relaxed(reg, ovl->regs + DISP_REG_OVL_DATAPATH_CON);
> +
> + reg = OVL_EN;
> + if (ovl->data->crc_cnt) {
> + /* enable crc and its related clocks */
> + writel_relaxed(OVL_CRC_EN, ovl->regs +
> DISP_REG_OVL_TRIG);
> + reg |= OVL_OP_8BIT_MODE | OVL_HG_FOVL_CK_ON |
> OVL_HF_FOVL_CK_ON;
> }
> - writel_relaxed(0x1, ovl->regs + DISP_REG_OVL_EN);
> + writel_relaxed(reg, ovl->regs + DISP_REG_OVL_EN);
> +
> +#if IS_REACHABLE(CONFIG_MTK_CMDQ)
> + mtk_crtc_start_crc_cmdq(&ovl->crc);
> +#endif
> }
>
> void mtk_ovl_stop(struct device *dev)
> {
> struct mtk_disp_ovl *ovl = dev_get_drvdata(dev);
>
> +#if IS_REACHABLE(CONFIG_MTK_CMDQ)
> + mtk_crtc_stop_crc_cmdq(&ovl->crc);
> +#endif
> writel_relaxed(0x0, ovl->regs + DISP_REG_OVL_EN);
> if (ovl->data->smi_id_en) {
> unsigned int reg;
> @@ -488,6 +567,83 @@ void mtk_ovl_layer_config(struct device *dev,
> unsigned int idx,
> (state->base.fb && !state->base.fb->format->has_alpha))
> ignore_pixel_alpha = OVL_CONST_BLEND;
>
> + /*
> + * OVL only supports 8 bits data in CRC calculation, transform
> 10-bit
> + * RGB to 8-bit RGB by leveraging the ability of the Y2R (YUV-
> to-RGB)
> + * hardware to multiply coefficients, although there is nothing
> to do
> + * with the YUV format.
> + */
> + if (ovl->data->supports_clrfmt_ext) {
> + u32 y2r_coef = 0, y2r_offset = 0, r2r_coef = 0, csc_en
> = 0;
> +
> + if (is_10bit_rgb(fmt)) {
> + con |= OVL_CON_MTX_AUTO_DIS | OVL_CON_MTX_EN |
> OVL_CON_MTX_PROGRAMMABLE;
> +
> + /*
> + * Y2R coefficient setting
> + * bit 13 is 2^1, bit 12 is 2^0, bit 11 is 2^-
> 1,
> + * bit 10 is 2^-2 = 0.25
> + */
> + y2r_coef = BIT(10);
> +
> + /* -1 in 10bit */
> + y2r_offset = GENMASK(10, 0) - 1;

I don't know why do this? If an input value is 0x100, then

0x100 right shit 2 bit become 0x40.
0x40 - 1 = 0x3f.
0x3f left shift 2 bit become 0xfc.

So input 0x100 and output 0xfc. Why?

> +
> + /*
> + * R2R coefficient setting
> + * bit 19 is 2^1, bit 18 is 2^0, bit 17 is 2^-
> 1,
> + * bit 20 is 2^2 = 4
> + */
> + r2r_coef = BIT(20);
> +
> + /* CSC_EN is for R2R */
> + csc_en = OVL_CLRFMT_EXT1_CSC_EN(idx);
> +
> + /*
> + * 1. YUV input data - 1 and shift right for 2
> bits to remove it
> + * [R'] [0.25 0 0] [Y in - 1]
> + * [G'] = [ 0 0.25 0] * [U in - 1]
> + * [B'] [ 0 0 0.25] [V in - 1]
> + *
> + * 2. shift left for 2 bit letting the last 2
> bits become 0

You truncate the last two bit, so some quality lost. I think the
quality is main function and CRC is just for debug. So it's better that
in normal case we keep quality and only for debug to lost the quality.

I have another question. You just truncate the last two bit but it is
still 10 bit value, so CRC could calculate this 10 bit value? I don't
know why you say CRC just for 8 bit?

Regards,
CK

> + * [R out] [ 4 0 0] [R']
> + * [G out] = [ 0 4 0] * [G']
> + * [B out] [ 0 0 4] [B']
> + */
> + }
> +
> + mtk_ddp_write_mask(cmdq_pkt, y2r_coef,
> + &ovl->cmdq_reg, ovl->regs,
> DISP_REG_OVL_Y2R_PARA_R0(idx),
> + OVL_Y2R_PARA_C_CF_RMY);
> + mtk_ddp_write_mask(cmdq_pkt, (y2r_coef << 16),
> + &ovl->cmdq_reg, ovl->regs,
> DISP_REG_OVL_Y2R_PARA_G0(idx),
> + OVL_Y2R_PARA_C_CF_GMU);
> + mtk_ddp_write_mask(cmdq_pkt, y2r_coef,
> + &ovl->cmdq_reg, ovl->regs,
> DISP_REG_OVL_Y2R_PARA_B1(idx),
> + OVL_Y2R_PARA_C_CF_BMV);
> +
> + mtk_ddp_write_mask(cmdq_pkt, y2r_offset,
> + &ovl->cmdq_reg, ovl->regs,
> DISP_REG_OVL_Y2R_PARA_YUV_A_0(idx),
> + OVL_Y2R_PARA_C_CF_YA);
> + mtk_ddp_write_mask(cmdq_pkt, (y2r_offset << 16),
> + &ovl->cmdq_reg, ovl->regs,
> DISP_REG_OVL_Y2R_PARA_YUV_A_0(idx),
> + OVL_Y2R_PARA_C_CF_UA);
> + mtk_ddp_write_mask(cmdq_pkt, y2r_offset,
> + &ovl->cmdq_reg, ovl->regs,
> DISP_REG_OVL_Y2R_PARA_YUV_A_1(idx),
> + OVL_Y2R_PARA_C_CF_VA);
> +
> + mtk_ddp_write_relaxed(cmdq_pkt, r2r_coef,
> + &ovl->cmdq_reg, ovl->regs,
> DISP_REG_OVL_R2R_R0(idx));
> + mtk_ddp_write_relaxed(cmdq_pkt, r2r_coef,
> + &ovl->cmdq_reg, ovl->regs,
> DISP_REG_OVL_R2R_G1(idx));
> + mtk_ddp_write_relaxed(cmdq_pkt, r2r_coef,
> + &ovl->cmdq_reg, ovl->regs,
> DISP_REG_OVL_R2R_B2(idx));
> +
> + mtk_ddp_write_mask(cmdq_pkt, csc_en,
> + &ovl->cmdq_reg, ovl->regs,
> DISP_REG_OVL_CLRFMT_EXT1,
> + OVL_CLRFMT_EXT1_CSC_EN(idx));
> + }
> +
> if (pending->rotation & DRM_MODE_REFLECT_Y) {
> con |= OVL_CON_VIRT_FLIP;
> addr += (pending->height - 1) * pending->pitch;
> @@ -594,15 +750,31 @@ static int mtk_disp_ovl_probe(struct
> platform_device *pdev)
> dev_err(dev, "failed to ioremap ovl\n");
> return PTR_ERR(priv->regs);
> }
> +
> + priv->data = of_device_get_match_data(dev);
> + platform_set_drvdata(pdev, priv);
> +
> + if (priv->data->crc_cnt) {
> + mtk_crtc_init_crc(&priv->crc,
> + priv->data->crc_ofs, priv->data-
> >crc_cnt,
> + DISP_REG_OVL_TRIG, OVL_CRC_CLR);
> + }
> +
> #if IS_REACHABLE(CONFIG_MTK_CMDQ)
> ret = cmdq_dev_get_client_reg(dev, &priv->cmdq_reg, 0);
> if (ret)
> dev_dbg(dev, "get mediatek,gce-client-reg fail!\n");
> -#endif
> -
> - priv->data = of_device_get_match_data(dev);
> - platform_set_drvdata(pdev, priv);
>
> + if (priv->data->crc_cnt) {
> + if (of_property_read_u32_index(dev->of_node,
> + "mediatek,gce-events",
> 0,
> + &priv->crc.cmdq_event))
> {
> + dev_warn(dev, "failed to get gce-events for
> crc\n");
> + }
> + priv->crc.cmdq_reg = &priv->cmdq_reg;
> + mtk_crtc_create_crc_cmdq(dev, &priv->crc);
> + }
> +#endif
> ret = devm_request_irq(dev, irq, mtk_disp_ovl_irq_handler,
> IRQF_TRIGGER_NONE, dev_name(dev), priv);
> if (ret < 0) {
> @@ -623,6 +795,10 @@ static int mtk_disp_ovl_probe(struct
> platform_device *pdev)
>
> static void mtk_disp_ovl_remove(struct platform_device *pdev)
> {
> + struct device *dev = &pdev->dev;
> + struct mtk_disp_ovl *ovl = dev_get_drvdata(dev);
> +
> + mtk_crtc_destroy_crc(&ovl->crc);
> component_del(&pdev->dev, &mtk_disp_ovl_component_ops);
> pm_runtime_disable(&pdev->dev);
> }
> @@ -693,6 +869,8 @@ static const struct mtk_disp_ovl_data
> mt8195_ovl_driver_data = {
> .formats = mt8195_formats,
> .num_formats = ARRAY_SIZE(mt8195_formats),
> .supports_clrfmt_ext = true,
> + .crc_ofs = mt8195_ovl_crc_ofs,
> + .crc_cnt = ARRAY_SIZE(mt8195_ovl_crc_ofs),
> };
>
> static const struct of_device_id mtk_disp_ovl_driver_dt_match[] = {

2024-03-28 02:51:16

by Shawn Sung (宋孝謙)

[permalink] [raw]
Subject: Re: [PATCH v6 04/14] drm/mediatek: Add DRM_MODE_ROTATE_0 to rotation property

Hi CK,

On Mon, 2024-03-25 at 01:52 +0000, CK Hu (胡俊光) wrote:
>
> > > diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> > > b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> > > index 0ebeaf9830d83..2a767a823c83a 100644
> > > --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> > > +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
> > > @@ -288,6 +288,10 @@ unsigned int mtk_ovl_layer_nr(struct device
> > > *dev)
> > >
> > > unsigned int mtk_ovl_supported_rotations(struct device *dev)
> > > {
> > > + /*
> > > + * although currently OVL can only do reflection,
> > > + * reflect x + reflect y = rotate 180
> > > + */
>
> Sorry, this comment is not related to DRM_MODE_ROTATE_0, so after
> removing this comment,
>
> Reviewed-by: CK Hu <[email protected]>
>

Got it. No problem. Will remove it from this series.

Thanks,
Shawn

2024-03-28 02:54:36

by Shawn Sung (宋孝謙)

[permalink] [raw]
Subject: Re: [PATCH v6 07/14] drm/mediatek: Support alpha blending in display driver

Hi CK,

On Fri, 2024-03-22 at 09:37 +0000, CK Hu (胡俊光) wrote:
> > diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c
> > b/drivers/gpu/drm/mediatek/mtk_plane.c
> > index 1723d4333f371..5bf757a3ef202 100644
> > --- a/drivers/gpu/drm/mediatek/mtk_plane.c
> > +++ b/drivers/gpu/drm/mediatek/mtk_plane.c
> > @@ -346,6 +346,17 @@ int mtk_plane_init(struct drm_device *dev,
> > struct drm_plane *plane,
> > DRM_INFO("Create rotation property failed\n");
> > }
> >
> > + err = drm_plane_create_alpha_property(plane);
> > + if (err)
> > + DRM_ERROR("failed to create property: alpha\n");
> > +
> > + err = drm_plane_create_blend_mode_property(plane,
> > + BIT(DRM_MODE_BLEND_P
> > REMULTI) |
> > + BIT(DRM_MODE_BLEND_C
> > OVERAGE) |
> > + BIT(DRM_MODE_BLEND_P
> > IXEL_NONE));
>
> After all sub driver support these function, then create blend
> property. So move this patch after all sub driver support these blend
> mode.
>

Got it. Will rearrange the patches in the next version

Thanks,
Shawn

2024-03-28 03:22:20

by Shawn Sung (宋孝謙)

[permalink] [raw]
Subject: Re: [PATCH v6 13/14] drm/mediatek: Support CRC in OVL

Hi CK,

On Tue, 2024-03-26 at 06:11 +0000, CK Hu (胡俊光) wrote:
> > @@ -488,6 +567,83 @@ void mtk_ovl_layer_config(struct device *dev,
> > unsigned int idx,
> > (state->base.fb && !state->base.fb->format->has_alpha))
> > ignore_pixel_alpha = OVL_CONST_BLEND;
> >
> > + /*
> > + * OVL only supports 8 bits data in CRC calculation, transform
> > 10-bit
> > + * RGB to 8-bit RGB by leveraging the ability of the Y2R (YUV-
> > to-RGB)
> > + * hardware to multiply coefficients, although there is nothing
> > to do
> > + * with the YUV format.
> > + */
> > + if (ovl->data->supports_clrfmt_ext) {
> > + u32 y2r_coef = 0, y2r_offset = 0, r2r_coef = 0, csc_en
> > = 0;
> > +
> > + if (is_10bit_rgb(fmt)) {
> > + con |= OVL_CON_MTX_AUTO_DIS | OVL_CON_MTX_EN |
> > OVL_CON_MTX_PROGRAMMABLE;
> > +
> > + /*
> > + * Y2R coefficient setting
> > + * bit 13 is 2^1, bit 12 is 2^0, bit 11 is 2^-
> > 1,
> > + * bit 10 is 2^-2 = 0.25
> > + */
> > + y2r_coef = BIT(10);
> > +
> > + /* -1 in 10bit */
> > + y2r_offset = GENMASK(10, 0) - 1;
>
> I don't know why do this? If an input value is 0x100, then
>
> 0x100 right shit 2 bit become 0x40.
> 0x40 - 1 = 0x3f.
> 0x3f left shift 2 bit become 0xfc.
>
> So input 0x100 and output 0xfc. Why?
>

There is no input here, all the settings are direct bit assignment, and
all the values are calculated by the designer. The main purpose of it
is to configure the Y2R module to be able to transform 10bit RGB format
into 8bit RGB, while this is not Y2R module is originally designed for.

> > +
> > + /*
> > + * R2R coefficient setting
> > + * bit 19 is 2^1, bit 18 is 2^0, bit 17 is 2^-
> > 1,
> > + * bit 20 is 2^2 = 4
> > + */
> > + r2r_coef = BIT(20);
> > +
> > + /* CSC_EN is for R2R */
> > + csc_en = OVL_CLRFMT_EXT1_CSC_EN(idx);
> > +
> > + /*
> > + * 1. YUV input data - 1 and shift right for 2
> > bits to remove it
> > + * [R'] [0.25 0 0] [Y in - 1]
> > + * [G'] = [ 0 0.25 0] * [U in - 1]
> > + * [B'] [ 0 0 0.25] [V in - 1]
> > + *
> > + * 2. shift left for 2 bit letting the last 2
> > bits become 0
>
> You truncate the last two bit, so some quality lost. I think the
> quality is main function and CRC is just for debug. So it's better
> that
> in normal case we keep quality and only for debug to lost the
> quality.

Got it. Will modify in the next version to enter this section only if
we need to calculate the CRC.

> I have another question. You just truncate the last two bit but it is
> still 10 bit value, so CRC could calculate this 10 bit value? I don't
> know why you say CRC just for 8 bit?
>

Yes, for RGB format, OVL can only handle 8bit per channel for CRC
calculation, so I assume there may be similar issue handling 10bit YUV
formats (P010) in the future.

Thanks,
Shawn

2024-03-28 05:21:53

by CK Hu (胡俊光)

[permalink] [raw]
Subject: Re: [PATCH v6 13/14] drm/mediatek: Support CRC in OVL

Hi, Shawn:

On Thu, 2024-03-28 at 03:22 +0000, Shawn Sung (宋孝謙) wrote:
> Hi CK,
>
> On Tue, 2024-03-26 at 06:11 +0000, CK Hu (胡俊光) wrote:
> > > @@ -488,6 +567,83 @@ void mtk_ovl_layer_config(struct device
> > > *dev,
> > > unsigned int idx,
> > > (state->base.fb && !state->base.fb->format->has_alpha))
> > > ignore_pixel_alpha = OVL_CONST_BLEND;
> > >
> > > + /*
> > > + * OVL only supports 8 bits data in CRC calculation, transform
> > > 10-bit
> > > + * RGB to 8-bit RGB by leveraging the ability of the Y2R (YUV-
> > > to-RGB)
> > > + * hardware to multiply coefficients, although there is nothing
> > > to do
> > > + * with the YUV format.
> > > + */
> > > + if (ovl->data->supports_clrfmt_ext) {
> > > + u32 y2r_coef = 0, y2r_offset = 0, r2r_coef = 0, csc_en
> > > = 0;
> > > +
> > > + if (is_10bit_rgb(fmt)) {
> > > + con |= OVL_CON_MTX_AUTO_DIS | OVL_CON_MTX_EN |
> > > OVL_CON_MTX_PROGRAMMABLE;
> > > +
> > > + /*
> > > + * Y2R coefficient setting
> > > + * bit 13 is 2^1, bit 12 is 2^0, bit 11 is 2^-
> > > 1,
> > > + * bit 10 is 2^-2 = 0.25
> > > + */
> > > + y2r_coef = BIT(10);
> > > +
> > > + /* -1 in 10bit */
> > > + y2r_offset = GENMASK(10, 0) - 1;
> >
> > I don't know why do this? If an input value is 0x100, then
> >
> > 0x100 right shit 2 bit become 0x40.
> > 0x40 - 1 = 0x3f.
> > 0x3f left shift 2 bit become 0xfc.
> >
> > So input 0x100 and output 0xfc. Why?
> >
>
> There is no input here, all the settings are direct bit assignment,
> and
> all the values are calculated by the designer. The main purpose of it
> is to configure the Y2R module to be able to transform 10bit RGB
> format
> into 8bit RGB, while this is not Y2R module is originally designed
> for.

The input I mean is the input of Y2R, the pixel value. If input a pixel
value 0x100 into Y2R, then Y2R output pixel value 0xfc, why do this? I
think it should not be minus 1. If remove the minus 1, then input 0x100
and output 0x100.

>
> > > +
> > > + /*
> > > + * R2R coefficient setting
> > > + * bit 19 is 2^1, bit 18 is 2^0, bit 17 is 2^-
> > > 1,
> > > + * bit 20 is 2^2 = 4
> > > + */
> > > + r2r_coef = BIT(20);
> > > +
> > > + /* CSC_EN is for R2R */
> > > + csc_en = OVL_CLRFMT_EXT1_CSC_EN(idx);
> > > +
> > > + /*
> > > + * 1. YUV input data - 1 and shift right for 2
> > > bits to remove it
> > > + * [R'] [0.25 0 0] [Y in - 1]
> > > + * [G'] = [ 0 0.25 0] * [U in - 1]
> > > + * [B'] [ 0 0 0.25] [V in - 1]
> > > + *
> > > + * 2. shift left for 2 bit letting the last 2
> > > bits become 0
> >
> > You truncate the last two bit, so some quality lost. I think the
> > quality is main function and CRC is just for debug. So it's better
> > that
> > in normal case we keep quality and only for debug to lost the
> > quality.
>
> Got it. Will modify in the next version to enter this section only if
> we need to calculate the CRC.
>
> > I have another question. You just truncate the last two bit but it
> > is
> > still 10 bit value, so CRC could calculate this 10 bit value? I
> > don't
> > know why you say CRC just for 8 bit?
> >
>
> Yes, for RGB format, OVL can only handle 8bit per channel for CRC
> calculation, so I assume there may be similar issue handling 10bit
> YUV
> formats (P010) in the future.

I think this truncation is not necessary. No matter you truncate in
Y2R, OVL would finally truncate pixel value last 2 two bit when
calculate CRC. So this truncation is not necessary.

Regards,
CK


>
> Thanks,
> Shawn
>

2024-04-01 05:31:42

by CK Hu (胡俊光)

[permalink] [raw]
Subject: Re: [PATCH v6 12/14] drm/mediatek: Support CRC in display driver

Hi, Shawn:

On Fri, 2024-03-22 at 13:28 +0800, Shawn Sung wrote:
> From: Hsiao Chien Sung <[email protected]>
>
> Register CRC related function pointers to support
> CRC retrieval.
>
> Signed-off-by: Hsiao Chien Sung <[email protected]>
> ---
> drivers/gpu/drm/mediatek/mtk_crtc.c | 260
> ++++++++++++++++++++++++
> drivers/gpu/drm/mediatek/mtk_crtc.h | 38 ++++
> drivers/gpu/drm/mediatek/mtk_ddp_comp.h | 3 +
> 3 files changed, 301 insertions(+)
>
> diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.c
> b/drivers/gpu/drm/mediatek/mtk_crtc.c
> index d811e4e73a36c..6440c5fb336d7 100644
> --- a/drivers/gpu/drm/mediatek/mtk_crtc.c
> +++ b/drivers/gpu/drm/mediatek/mtk_crtc.c
> @@ -18,6 +18,7 @@
> #include <drm/drm_atomic_helper.h>
> #include <drm/drm_probe_helper.h>
> #include <drm/drm_vblank.h>
> +#include <drm/drm_vblank_work.h>
>
> #include "mtk_crtc.h"
> #include "mtk_ddp_comp.h"
> @@ -69,6 +70,9 @@ struct mtk_crtc {
> /* lock for display hardware access */
> struct mutex hw_lock;
> bool config_updating;
> +
> + struct mtk_ddp_comp *crc_provider;
> + struct drm_vblank_work crc_work;
> };
>
> struct mtk_crtc_state {
> @@ -703,6 +707,71 @@ static void mtk_crtc_update_output(struct
> drm_crtc *crtc,
> }
> }
>
> +static void mtk_crtc_crc_work(struct kthread_work *base)
> +{
> + struct drm_vblank_work *work = to_drm_vblank_work(base);
> + struct mtk_crtc *mtk_crtc =
> + container_of(work, typeof(*mtk_crtc), crc_work);
> +
> + if (mtk_crtc->base.crc.opened) {
> + struct mtk_ddp_comp *comp = mtk_crtc->crc_provider;
> + u64 vblank = drm_crtc_vblank_count(&mtk_crtc->base);
> +
> + comp->funcs->crc_read(comp->dev);
> +
> + /* could take more than 50ms to finish */
> + drm_crtc_add_crc_entry(&mtk_crtc->base, true, vblank,
> + comp->funcs->crc_entry(comp-
> >dev));

It seems that you could regenerate cmdq packet for crc here. So crtc
atomic flush and crc could use the same mailbox channel.

Regards,
CK

> +
> + drm_vblank_work_schedule(&mtk_crtc->crc_work, vblank +
> 1, true);
> + }
> +}
> +
> +static int mtk_crtc_set_crc_source(struct drm_crtc *crtc, const char
> *src)
> +{
> + struct mtk_crtc *mtk_crtc = to_mtk_crtc(crtc);
> +
> + if (!src)
> + return -EINVAL;
> +
> + if (strcmp(src, "auto") != 0) {
> + DRM_ERROR("%s(crtc-%d): unknown source '%s'\n",
> + __func__, drm_crtc_index(crtc), src);
> + return -EINVAL;
> + }
> +
> + /*
> + * skip the first crc because the first frame (vblank + 1) is
> configured
> + * by mtk_crtc_ddp_hw_init() when atomic enable
> + */
> + drm_vblank_work_schedule(&mtk_crtc->crc_work,
> + drm_crtc_vblank_count(crtc) + 2,
> false);
> + return 0;
> +}
> +
> +static int mtk_crtc_verify_crc_source(struct drm_crtc *crtc, const
> char *src,
> + size_t *cnt)
> +{
> + struct mtk_crtc *mtk_crtc = to_mtk_crtc(crtc);
> + struct mtk_ddp_comp *comp = mtk_crtc->crc_provider;
> +
> + if (!comp) {
> + DRM_ERROR("%s(crtc-%d): no crc provider\n",
> + __func__, drm_crtc_index(crtc));
> + return -ENOENT;
> + }
> +
> + if (src && strcmp(src, "auto") != 0) {
> + DRM_ERROR("%s(crtc-%d): unknown source '%s'\n",
> + __func__, drm_crtc_index(crtc), src);
> + return -EINVAL;
> + }
> +
> + *cnt = comp->funcs->crc_cnt(comp->dev);
> +
> + return 0;
> +}
> +
> int mtk_crtc_plane_check(struct drm_crtc *crtc, struct drm_plane
> *plane,
> struct mtk_plane_state *state)
> {
> @@ -751,6 +820,8 @@ static void mtk_crtc_atomic_enable(struct
> drm_crtc *crtc,
>
> drm_crtc_vblank_on(crtc);
> mtk_crtc->enabled = true;
> +
> + drm_vblank_work_init(&mtk_crtc->crc_work, crtc,
> mtk_crtc_crc_work);
> }
>
> static void mtk_crtc_atomic_disable(struct drm_crtc *crtc,
> @@ -840,6 +911,8 @@ static const struct drm_crtc_funcs mtk_crtc_funcs
> = {
> .atomic_destroy_state = mtk_crtc_destroy_state,
> .enable_vblank = mtk_crtc_enable_vblank,
> .disable_vblank = mtk_crtc_disable_vblank,
> + .set_crc_source = mtk_crtc_set_crc_source,
> + .verify_crc_source = mtk_crtc_verify_crc_source,
> };
>
> static const struct drm_crtc_helper_funcs mtk_crtc_helper_funcs = {
> @@ -1033,6 +1106,11 @@ int mtk_crtc_create(struct drm_device
> *drm_dev, const unsigned int *path,
>
> if (comp->funcs->ctm_set)
> has_ctm = true;
> +
> + if (comp->funcs->crc_cnt &&
> + comp->funcs->crc_entry &&
> + comp->funcs->crc_read)
> + mtk_crtc->crc_provider = comp;
> }
>
> mtk_ddp_comp_register_vblank_cb(comp, mtk_crtc_ddp_irq,
> @@ -1136,3 +1214,185 @@ int mtk_crtc_create(struct drm_device
> *drm_dev, const unsigned int *path,
>
> return 0;
> }
> +
> +void mtk_crtc_init_crc(struct mtk_crtc_crc *crc, const u32
> *crc_offset_table,
> + size_t crc_count, u32 reset_offset, u32
> reset_mask)
> +{
> + crc->ofs = crc_offset_table;
> + crc->cnt = crc_count;
> + crc->rst_ofs = reset_offset;
> + crc->rst_msk = reset_mask;
> + crc->va = kcalloc(crc->cnt, sizeof(*crc->va), GFP_KERNEL);
> + if (!crc->va) {
> + DRM_ERROR("failed to allocate memory for crc\n");
> + crc->cnt = 0;
> + }
> +}
> +
> +void mtk_crtc_read_crc(struct mtk_crtc_crc *crc, void __iomem *reg)
> +{
> + if (!crc->cnt || !crc->ofs || !crc->va)
> + return;
> +
> +#if IS_REACHABLE(CONFIG_MTK_CMDQ)
> + /* sync to see the most up-to-date copy of the DMA buffer */
> + dma_sync_single_for_cpu(crc->cmdq_client.chan->mbox->dev,
> + crc->pa, crc->cnt * sizeof(*crc->va),
> + DMA_FROM_DEVICE);
> +#endif
> +}
> +
> +void mtk_crtc_destroy_crc(struct mtk_crtc_crc *crc)
> +{
> + if (!crc->cnt)
> + return;
> +
> +#if IS_REACHABLE(CONFIG_MTK_CMDQ)
> + if (crc->pa) {
> + dma_unmap_single(crc->cmdq_client.chan->mbox->dev,
> + crc->pa, crc->cnt * sizeof(*crc->va),
> + DMA_TO_DEVICE);
> + crc->pa = 0;
> + }
> + if (crc->cmdq_client.chan) {
> + mtk_drm_cmdq_pkt_destroy(&crc->cmdq_handle);
> + mbox_free_channel(crc->cmdq_client.chan);
> + crc->cmdq_client.chan = NULL;
> + }
> +#endif
> + kfree(crc->va);
> + crc->va = NULL;
> + crc->cnt = 0;
> +}
> +
> +#if IS_REACHABLE(CONFIG_MTK_CMDQ)
> +/**
> + * mtk_crtc_create_crc_cmdq - Create a CMDQ thread for syncing the
> CRCs
> + * @dev: Kernel device node of the CRC provider
> + * @crc: Pointer of the CRC to init
> + *
> + * This function will create a looping thread on GCE (Global Command
> Engine) to
> + * keep the CRC up to date by monitoring the assigned event (usually
> the frame
> + * done event) of the CRC provider, and read the CRCs from the
> registers to a
> + * shared memory for the workqueue to read. To start/stop the
> looping thread,
> + * please call `mtk_crtc_start_crc_cmdq()` and
> `mtk_crtc_stop_crc_cmdq()`
> + * defined blow.
> + *
> + * The reason why we don't update the CRCs with CPU is that the
> front porch of
> + * 4K60 timing in CEA-861 is less than 60us, and register read/write
> speed is
> + * relatively unreliable comparing to GCE due to the bus design.
> + *
> + * We must create a new thread instead of using the original one for
> plane
> + * update is because:
> + * 1. We cannot add another wait-for-event command at the end of
> cmdq packet, or
> + * the cmdq callback will delay for too long
> + * 2. Will get the CRC of the previous frame if using the existed
> wait-for-event
> + * command which is at the beginning of the packet
> + */
> +void mtk_crtc_create_crc_cmdq(struct device *dev, struct
> mtk_crtc_crc *crc)
> +{
> + int i;
> +
> + if (!crc->cnt) {
> + dev_warn(dev, "%s: not support\n", __func__);
> + goto cleanup;
> + }
> +
> + if (!crc->ofs) {
> + dev_warn(dev, "%s: not defined\n", __func__);
> + goto cleanup;
> + }
> +
> + crc->cmdq_client.client.dev = dev;
> + crc->cmdq_client.client.tx_block = false;
> + crc->cmdq_client.client.knows_txdone = true;
> + crc->cmdq_client.client.rx_callback = NULL;
> + crc->cmdq_client.chan = mbox_request_channel(&crc-
> >cmdq_client.client, 0);
> + if (IS_ERR(crc->cmdq_client.chan)) {
> + dev_warn(dev, "%s: failed to create mailbox client\n",
> __func__);
> + crc->cmdq_client.chan = NULL;
> + goto cleanup;
> + }
> +
> + if (mtk_drm_cmdq_pkt_create(&crc->cmdq_client, &crc-
> >cmdq_handle, PAGE_SIZE)) {
> + dev_warn(dev, "%s: failed to create cmdq packet\n",
> __func__);
> + goto cleanup;
> + }
> +
> + if (!crc->va) {
> + dev_warn(dev, "%s: no memory\n", __func__);
> + goto cleanup;
> + }
> +
> + /* map the entry to get a dma address for cmdq to store the crc
> */
> + crc->pa = dma_map_single(crc->cmdq_client.chan->mbox->dev,
> + crc->va, crc->cnt * sizeof(*crc->va),
> + DMA_FROM_DEVICE);
> +
> + if (dma_mapping_error(crc->cmdq_client.chan->mbox->dev, crc-
> >pa)) {
> + dev_err(dev, "%s: failed to map dma\n", __func__);
> + goto cleanup;
> + }
> +
> + if (crc->cmdq_event)
> + cmdq_pkt_wfe(&crc->cmdq_handle, crc->cmdq_event, true);
> +
> + for (i = 0; i < crc->cnt; i++) {
> + /* put crc to spr1 register */
> + cmdq_pkt_read_s(&crc->cmdq_handle, crc->cmdq_reg-
> >subsys,
> + crc->cmdq_reg->offset + crc->ofs[i],
> + CMDQ_THR_SPR_IDX1);
> +
> + /* copy spr1 register to physical address of the crc */
> + cmdq_pkt_assign(&crc->cmdq_handle, CMDQ_THR_SPR_IDX0,
> + CMDQ_ADDR_HIGH(crc->pa + i *
> sizeof(*crc->va)));
> + cmdq_pkt_write_s(&crc->cmdq_handle, CMDQ_THR_SPR_IDX0,
> + CMDQ_ADDR_LOW(crc->pa + i *
> sizeof(*crc->va)),
> + CMDQ_THR_SPR_IDX1);
> + }
> + /* reset crc */
> + mtk_ddp_write_mask(&crc->cmdq_handle, ~0, crc->cmdq_reg, 0,
> + crc->rst_ofs, crc->rst_msk);
> +
> + /* clear reset bit */
> + mtk_ddp_write_mask(&crc->cmdq_handle, 0, crc->cmdq_reg, 0,
> + crc->rst_ofs, crc->rst_msk);
> +
> + /* jump to head of the cmdq packet */
> + cmdq_pkt_jump(&crc->cmdq_handle, crc->cmdq_handle.pa_base);
> +
> + return;
> +cleanup:
> + mtk_crtc_destroy_crc(crc);
> +}
> +
> +/**
> + * mtk_crtc_start_crc_cmdq - Start the GCE looping thread for CRC
> update
> + * @crc: Pointer of the CRC information
> + */
> +void mtk_crtc_start_crc_cmdq(struct mtk_crtc_crc *crc)
> +{
> + if (!crc->cmdq_client.chan)
> + return;
> +
> + dma_sync_single_for_device(crc->cmdq_client.chan->mbox->dev,
> + crc->cmdq_handle.pa_base,
> + crc->cmdq_handle.cmd_buf_size,
> + DMA_TO_DEVICE);
> + mbox_send_message(crc->cmdq_client.chan, &crc->cmdq_handle);
> + mbox_client_txdone(crc->cmdq_client.chan, 0);
> +}
> +
> +/**
> + * mtk_crtc_stop_crc_cmdq - Stop the GCE looping thread for CRC
> update
> + * @crc: Pointer of the CRC information
> + */
> +void mtk_crtc_stop_crc_cmdq(struct mtk_crtc_crc *crc)
> +{
> + if (!crc->cmdq_client.chan)
> + return;
> +
> + /* remove all the commands from the cmdq packet */
> + mbox_flush(crc->cmdq_client.chan, 2000);
> +}
> +#endif
> diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.h
> b/drivers/gpu/drm/mediatek/mtk_crtc.h
> index 388e900b6f4de..a79c4611754e4 100644
> --- a/drivers/gpu/drm/mediatek/mtk_crtc.h
> +++ b/drivers/gpu/drm/mediatek/mtk_crtc.h
> @@ -14,6 +14,34 @@
> #define MTK_MAX_BPC 10
> #define MTK_MIN_BPC 3
>
> +/**
> + * struct mtk_crtc_crc - crc related information
> + * @ofs: register offset of crc
> + * @rst_ofs: register offset of crc reset
> + * @rst_msk: register mask of crc reset
> + * @cnt: count of crc
> + * @va: pointer to the start of crc array
> + * @pa: physical address of the crc for gce to access
> + * @cmdq_event: the event to trigger the cmdq
> + * @cmdq_reg: address of the register that cmdq is going to access
> + * @cmdq_client: handler to control cmdq (mbox channel, thread
> ...etc.)
> + * @cmdq_handle: cmdq packet to store the commands
> + */
> +struct mtk_crtc_crc {
> + const u32 *ofs;
> + u32 rst_ofs;
> + u32 rst_msk;
> + size_t cnt;
> + u32 *va;
> +#if IS_REACHABLE(CONFIG_MTK_CMDQ)
> + dma_addr_t pa;
> + u32 cmdq_event;
> + struct cmdq_client_reg *cmdq_reg;
> + struct cmdq_client cmdq_client;
> + struct cmdq_pkt cmdq_handle;
> +#endif
> +};
> +
> void mtk_crtc_commit(struct drm_crtc *crtc);
> int mtk_crtc_create(struct drm_device *drm_dev, const unsigned int
> *path,
> unsigned int path_len, int priv_data_index,
> @@ -25,4 +53,14 @@ void mtk_crtc_async_update(struct drm_crtc *crtc,
> struct drm_plane *plane,
> struct drm_atomic_state *plane_state);
> struct device *mtk_crtc_dma_dev_get(struct drm_crtc *crtc);
>
> +void mtk_crtc_init_crc(struct mtk_crtc_crc *crc, const u32
> *crc_offset_table,
> + size_t crc_count, u32 reset_offset, u32
> reset_mask);
> +void mtk_crtc_read_crc(struct mtk_crtc_crc *crc, void __iomem *reg);
> +void mtk_crtc_destroy_crc(struct mtk_crtc_crc *crc);
> +#if IS_REACHABLE(CONFIG_MTK_CMDQ)
> +void mtk_crtc_create_crc_cmdq(struct device *dev, struct
> mtk_crtc_crc *crc);
> +void mtk_crtc_start_crc_cmdq(struct mtk_crtc_crc *crc);
> +void mtk_crtc_stop_crc_cmdq(struct mtk_crtc_crc *crc);
> +#endif
> +
> #endif /* MTK_CRTC_H */
> diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
> b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
> index f7fe2e08dc8e2..b9c79e740abe0 100644
> --- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
> +++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
> @@ -88,6 +88,9 @@ struct mtk_ddp_comp_funcs {
> void (*remove)(struct device *dev, struct mtk_mutex *mutex);
> unsigned int (*encoder_index)(struct device *dev);
> enum drm_mode_status (*mode_valid)(struct device *dev, const
> struct drm_display_mode *mode);
> + size_t (*crc_cnt)(struct device *dev);
> + u32 *(*crc_entry)(struct device *dev);
> + void (*crc_read)(struct device *dev);
> };
>
> struct mtk_ddp_comp {