openwrt/target/linux/brcm2708/patches-4.14/950-0357-drm-vc4-Add-support-for-SAND-modifier.patch
Koen Vandeputte 9a1d7ff187 kernel: bump 4.14 to 4.14.99
Refreshed all patches.

Remove upstreamed:
- 950-0434-mmc-bcm2835-Recover-from-MMC_SEND_EXT_CSD.patch

Compile-tested on: ar71xx, cns3xxx, imx6, x86_64
Runtime-tested on: ar71xx, cns3xxx, imx6

Signed-off-by: Koen Vandeputte <koen.vandeputte@ncentric.com>
2019-02-14 16:45:01 +01:00

267 lines
9.2 KiB
Diff

From 7d83a48b50ac24af7763e7ba5304e9a82f37f014 Mon Sep 17 00:00:00 2001
From: Dave Stevenson <dave.stevenson@raspberrypi.org>
Date: Fri, 16 Mar 2018 15:04:35 -0700
Subject: [PATCH 357/454] drm/vc4: Add support for SAND modifier.
This is the format generated by VC4's H.264 engine, and preferred by
the ISP as well. By displaying SAND buffers directly, we can avoid
needing to use the ISP to rewrite the SAND H.264 output to linear
before display.
This is a joint effort by Dave Stevenson (who wrote the initial patch
and DRM demo) and Eric Anholt (drm_fourcc.h generalization, safety
checks, RGBA support).
v2: Make the parameter macro give all of the middle 48 bits (suggested
by Daniels). Fix fourcc_mod_broadcom_mod()'s bits/shift being
swapped. Mark NV12/21 as supported, not YUV420.
Signed-off-by: Dave Stevenson <dave.stevenson@raspberrypi.org>
Signed-off-by: Eric Anholt <eric@anholt.net>
Cc: Daniel Vetter <daniel@ffwll.ch>
Acked-by: Daniel Stone <daniels@collabora.com> (v1)
Cc: Boris Brezillon <boris.brezillon@bootlin.com>
Cc: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180316220435.31416-3-eric@anholt.net
(cherry picked from commit e065a8dd30af703b4794dc740c0825ee12b92efd)
---
drivers/gpu/drm/vc4/vc4_plane.c | 84 ++++++++++++++++++++++++++++++---
drivers/gpu/drm/vc4/vc4_regs.h | 6 +++
include/uapi/drm/drm_fourcc.h | 59 +++++++++++++++++++++++
3 files changed, 142 insertions(+), 7 deletions(-)
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -469,11 +469,13 @@ static int vc4_plane_mode_set(struct drm
struct drm_framebuffer *fb = state->fb;
u32 ctl0_offset = vc4_state->dlist_count;
const struct hvs_format *format = vc4_get_hvs_format(fb->format->format);
+ u64 base_format_mod = fourcc_mod_broadcom_mod(fb->modifier);
int num_planes = drm_format_num_planes(format->drm);
bool covers_screen;
u32 scl0, scl1, pitch0;
u32 lbm_size, tiling;
unsigned long irqflags;
+ u32 hvs_format = format->hvs;
int ret, i;
ret = vc4_plane_setup_clipping_and_scaling(state);
@@ -513,7 +515,7 @@ static int vc4_plane_mode_set(struct drm
scl1 = vc4_get_scl_field(state, 0);
}
- switch (fb->modifier) {
+ switch (base_format_mod) {
case DRM_FORMAT_MOD_LINEAR:
tiling = SCALER_CTL0_TILING_LINEAR;
pitch0 = VC4_SET_FIELD(fb->pitches[0], SCALER_SRC_PITCH);
@@ -536,6 +538,49 @@ static int vc4_plane_mode_set(struct drm
break;
}
+ case DRM_FORMAT_MOD_BROADCOM_SAND64:
+ case DRM_FORMAT_MOD_BROADCOM_SAND128:
+ case DRM_FORMAT_MOD_BROADCOM_SAND256: {
+ uint32_t param = fourcc_mod_broadcom_param(fb->modifier);
+
+ /* Column-based NV12 or RGBA.
+ */
+ if (fb->format->num_planes > 1) {
+ if (hvs_format != HVS_PIXEL_FORMAT_YCBCR_YUV420_2PLANE) {
+ DRM_DEBUG_KMS("SAND format only valid for NV12/21");
+ return -EINVAL;
+ }
+ hvs_format = HVS_PIXEL_FORMAT_H264;
+ } else {
+ if (base_format_mod == DRM_FORMAT_MOD_BROADCOM_SAND256) {
+ DRM_DEBUG_KMS("SAND256 format only valid for H.264");
+ return -EINVAL;
+ }
+ }
+
+ switch (base_format_mod) {
+ case DRM_FORMAT_MOD_BROADCOM_SAND64:
+ tiling = SCALER_CTL0_TILING_64B;
+ break;
+ case DRM_FORMAT_MOD_BROADCOM_SAND128:
+ tiling = SCALER_CTL0_TILING_128B;
+ break;
+ case DRM_FORMAT_MOD_BROADCOM_SAND256:
+ tiling = SCALER_CTL0_TILING_256B_OR_T;
+ break;
+ default:
+ break;
+ }
+
+ if (param > SCALER_TILE_HEIGHT_MASK) {
+ DRM_DEBUG_KMS("SAND height too large (%d)\n", param);
+ return -EINVAL;
+ }
+
+ pitch0 = VC4_SET_FIELD(param, SCALER_TILE_HEIGHT);
+ break;
+ }
+
default:
DRM_DEBUG_KMS("Unsupported FB tiling flag 0x%16llx",
(long long)fb->modifier);
@@ -546,7 +591,7 @@ static int vc4_plane_mode_set(struct drm
vc4_dlist_write(vc4_state,
SCALER_CTL0_VALID |
(format->pixel_order << SCALER_CTL0_ORDER_SHIFT) |
- (format->hvs << SCALER_CTL0_PIXEL_FORMAT_SHIFT) |
+ (hvs_format << SCALER_CTL0_PIXEL_FORMAT_SHIFT) |
VC4_SET_FIELD(tiling, SCALER_CTL0_TILING) |
(vc4_state->is_unity ? SCALER_CTL0_UNITY : 0) |
VC4_SET_FIELD(scl0, SCALER_CTL0_SCL0) |
@@ -600,8 +645,13 @@ static int vc4_plane_mode_set(struct drm
/* Pitch word 1/2 */
for (i = 1; i < num_planes; i++) {
- vc4_dlist_write(vc4_state,
- VC4_SET_FIELD(fb->pitches[i], SCALER_SRC_PITCH));
+ if (hvs_format != HVS_PIXEL_FORMAT_H264) {
+ vc4_dlist_write(vc4_state,
+ VC4_SET_FIELD(fb->pitches[i],
+ SCALER_SRC_PITCH));
+ } else {
+ vc4_dlist_write(vc4_state, pitch0);
+ }
}
/* Colorspace conversion words */
@@ -884,13 +934,30 @@ static bool vc4_format_mod_supported(str
case DRM_FORMAT_BGR565:
case DRM_FORMAT_ARGB1555:
case DRM_FORMAT_XRGB1555:
- return true;
+ switch (fourcc_mod_broadcom_mod(modifier)) {
+ case DRM_FORMAT_MOD_LINEAR:
+ case DRM_FORMAT_MOD_BROADCOM_VC4_T_TILED:
+ case DRM_FORMAT_MOD_BROADCOM_SAND64:
+ case DRM_FORMAT_MOD_BROADCOM_SAND128:
+ return true;
+ default:
+ return false;
+ }
+ case DRM_FORMAT_NV12:
+ case DRM_FORMAT_NV21:
+ switch (fourcc_mod_broadcom_mod(modifier)) {
+ case DRM_FORMAT_MOD_LINEAR:
+ case DRM_FORMAT_MOD_BROADCOM_SAND64:
+ case DRM_FORMAT_MOD_BROADCOM_SAND128:
+ case DRM_FORMAT_MOD_BROADCOM_SAND256:
+ return true;
+ default:
+ return false;
+ }
case DRM_FORMAT_YUV422:
case DRM_FORMAT_YVU422:
case DRM_FORMAT_YUV420:
case DRM_FORMAT_YVU420:
- case DRM_FORMAT_NV12:
- case DRM_FORMAT_NV21:
case DRM_FORMAT_NV16:
case DRM_FORMAT_NV61:
default:
@@ -920,6 +987,9 @@ struct drm_plane *vc4_plane_init(struct
unsigned i;
static const uint64_t modifiers[] = {
DRM_FORMAT_MOD_BROADCOM_VC4_T_TILED,
+ DRM_FORMAT_MOD_BROADCOM_SAND128,
+ DRM_FORMAT_MOD_BROADCOM_SAND64,
+ DRM_FORMAT_MOD_BROADCOM_SAND256,
DRM_FORMAT_MOD_LINEAR,
DRM_FORMAT_MOD_INVALID
};
--- a/drivers/gpu/drm/vc4/vc4_regs.h
+++ b/drivers/gpu/drm/vc4/vc4_regs.h
@@ -1059,6 +1059,12 @@ enum hvs_pixel_format {
#define SCALER_SRC_PITCH_MASK VC4_MASK(15, 0)
#define SCALER_SRC_PITCH_SHIFT 0
+/* PITCH0/1/2 fields for tiled (SAND). */
+#define SCALER_TILE_SKIP_0_MASK VC4_MASK(18, 16)
+#define SCALER_TILE_SKIP_0_SHIFT 16
+#define SCALER_TILE_HEIGHT_MASK VC4_MASK(15, 0)
+#define SCALER_TILE_HEIGHT_SHIFT 0
+
/* PITCH0 fields for T-tiled. */
#define SCALER_PITCH0_TILE_WIDTH_L_MASK VC4_MASK(22, 16)
#define SCALER_PITCH0_TILE_WIDTH_L_SHIFT 16
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -383,6 +383,23 @@ extern "C" {
#define NV_FORMAT_MOD_TEGRA_16BX2_BLOCK(v) fourcc_mod_tegra_code(2, v)
/*
+ * Some Broadcom modifiers take parameters, for example the number of
+ * vertical lines in the image. Reserve the lower 32 bits for modifier
+ * type, and the next 24 bits for parameters. Top 8 bits are the
+ * vendor code.
+ */
+#define __fourcc_mod_broadcom_param_shift 8
+#define __fourcc_mod_broadcom_param_bits 48
+#define fourcc_mod_broadcom_code(val, params) \
+ fourcc_mod_code(BROADCOM, ((((__u64)params) << __fourcc_mod_broadcom_param_shift) | val))
+#define fourcc_mod_broadcom_param(m) \
+ ((int)(((m) >> __fourcc_mod_broadcom_param_shift) & \
+ ((1ULL << __fourcc_mod_broadcom_param_bits) - 1)))
+#define fourcc_mod_broadcom_mod(m) \
+ ((m) & ~(((1ULL << __fourcc_mod_broadcom_param_bits) - 1) << \
+ __fourcc_mod_broadcom_param_shift))
+
+/*
* Broadcom VC4 "T" format
*
* This is the primary layout that the V3D GPU can texture from (it
@@ -403,6 +420,48 @@ extern "C" {
*/
#define DRM_FORMAT_MOD_BROADCOM_VC4_T_TILED fourcc_mod_code(BROADCOM, 1)
+/*
+ * Broadcom SAND format
+ *
+ * This is the native format that the H.264 codec block uses. For VC4
+ * HVS, it is only valid for H.264 (NV12/21) and RGBA modes.
+ *
+ * The image can be considered to be split into columns, and the
+ * columns are placed consecutively into memory. The width of those
+ * columns can be either 32, 64, 128, or 256 pixels, but in practice
+ * only 128 pixel columns are used.
+ *
+ * The pitch between the start of each column is set to optimally
+ * switch between SDRAM banks. This is passed as the number of lines
+ * of column width in the modifier (we can't use the stride value due
+ * to various core checks that look at it , so you should set the
+ * stride to width*cpp).
+ *
+ * Note that the column height for this format modifier is the same
+ * for all of the planes, assuming that each column contains both Y
+ * and UV. Some SAND-using hardware stores UV in a separate tiled
+ * image from Y to reduce the column height, which is not supported
+ * with these modifiers.
+ */
+
+#define DRM_FORMAT_MOD_BROADCOM_SAND32_COL_HEIGHT(v) \
+ fourcc_mod_broadcom_code(2, v)
+#define DRM_FORMAT_MOD_BROADCOM_SAND64_COL_HEIGHT(v) \
+ fourcc_mod_broadcom_code(3, v)
+#define DRM_FORMAT_MOD_BROADCOM_SAND128_COL_HEIGHT(v) \
+ fourcc_mod_broadcom_code(4, v)
+#define DRM_FORMAT_MOD_BROADCOM_SAND256_COL_HEIGHT(v) \
+ fourcc_mod_broadcom_code(5, v)
+
+#define DRM_FORMAT_MOD_BROADCOM_SAND32 \
+ DRM_FORMAT_MOD_BROADCOM_SAND32_COL_HEIGHT(0)
+#define DRM_FORMAT_MOD_BROADCOM_SAND64 \
+ DRM_FORMAT_MOD_BROADCOM_SAND64_COL_HEIGHT(0)
+#define DRM_FORMAT_MOD_BROADCOM_SAND128 \
+ DRM_FORMAT_MOD_BROADCOM_SAND128_COL_HEIGHT(0)
+#define DRM_FORMAT_MOD_BROADCOM_SAND256 \
+ DRM_FORMAT_MOD_BROADCOM_SAND256_COL_HEIGHT(0)
+
#if defined(__cplusplus)
}
#endif