libretro/Lakka-LibreELEC
0
0
Fork 1
mirror of https://github.com/libretro/Lakka-LibreELEC.git synced 2025-03-01 03:21:21 +00:00
Code Issues
Lakka-LibreELEC/projects/Rockchip/patches/linux/default/linux-0021-drm-from-list.patch
Alex Bee d714b15a77 Rockchip: linux update patches for 5.10.103
2022-03-08 21:13:53 +01:00

601 lines
22 KiB
Diff
Raw Permalink Blame History

From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Mon, 6 Jul 2020 22:30:13 +0000
Subject: [PATCH] drm: drm_fourcc: add NV20 and NV30 YUV formats
DRM_FORMAT_NV20 and DRM_FORMAT_NV30 formats is the 2x1 and non-subsampled
variant of NV15, a 10-bit 2-plane YUV format that has no padding between
components. Instead, luminance and chrominance samples are grouped into 4s
so that each group is packed into an integer number of bytes:
YYYY = UVUV = 4 * 10 bits = 40 bits = 5 bytes
The '20' and '30' suffix refers to the optimum effective bits per pixel
which is achieved when the total number of luminance samples is a multiple
of 4.
V2: Added NV30 format
Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Reviewed-by: Sandy Huang <hjc@rock-chips.com>
---
drivers/gpu/drm/drm_fourcc.c | 8 ++++++++
include/uapi/drm/drm_fourcc.h | 2 ++
2 files changed, 10 insertions(+)
diff --git a/drivers/gpu/drm/drm_fourcc.c b/drivers/gpu/drm/drm_fourcc.c
index 722c7ebe4e88..2daf8a304b53 100644
--- a/drivers/gpu/drm/drm_fourcc.c
+++ b/drivers/gpu/drm/drm_fourcc.c
@@ -278,6 +278,14 @@ const struct drm_format_info *__drm_format_info(u32 format)
.num_planes = 2, .char_per_block = { 5, 5, 0 },
.block_w = { 4, 2, 0 }, .block_h = { 1, 1, 0 }, .hsub = 2,
.vsub = 2, .is_yuv = true },
+ { .format = DRM_FORMAT_NV20, .depth = 0,
+ .num_planes = 2, .char_per_block = { 5, 5, 0 },
+ .block_w = { 4, 2, 0 }, .block_h = { 1, 1, 0 }, .hsub = 2,
+ .vsub = 1, .is_yuv = true },
+ { .format = DRM_FORMAT_NV30, .depth = 0,
+ .num_planes = 2, .char_per_block = { 5, 5, 0 },
+ .block_w = { 4, 2, 0 }, .block_h = { 1, 1, 0 }, .hsub = 1,
+ .vsub = 1, .is_yuv = true },
{ .format = DRM_FORMAT_Q410, .depth = 0,
.num_planes = 3, .char_per_block = { 2, 2, 2 },
.block_w = { 1, 1, 1 }, .block_h = { 1, 1, 1 }, .hsub = 0,
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index 5498d7a6556a..5b5db0381729 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -242,6 +242,8 @@ extern "C" {
* index 1 = Cr:Cb plane, [39:0] Cr1:Cb1:Cr0:Cb0 little endian
*/
#define DRM_FORMAT_NV15 fourcc_code('N', 'V', '1', '5') /* 2x2 subsampled Cr:Cb plane */
+#define DRM_FORMAT_NV20 fourcc_code('N', 'V', '2', '0') /* 2x1 subsampled Cr:Cb plane */
+#define DRM_FORMAT_NV30 fourcc_code('N', 'V', '3', '0') /* non-subsampled Cr:Cb plane */
/*
* 2 plane YCbCr MSB aligned
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Mon, 6 Jul 2020 22:30:13 +0000
Subject: [PATCH] drm: rockchip: add NV15, NV20 and NV30 support
Add support for displaying 10-bit 4:2:0 and 4:2:2 formats produced by the
Rockchip Video Decoder on RK322X, RK3288, RK3328, RK3368 and RK3399.
Also add support for 10-bit 4:4:4 format while at it.
V2: Added NV30 support
Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Reviewed-by: Sandy Huang <hjc@rock-chips.com>
---
drivers/gpu/drm/rockchip/rockchip_drm_vop.c | 29 +++++++++++++++++--
drivers/gpu/drm/rockchip/rockchip_drm_vop.h | 1 +
drivers/gpu/drm/rockchip/rockchip_vop_reg.c | 32 +++++++++++++++++----
3 files changed, 54 insertions(+), 8 deletions(-)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index 0f23144491e4..b149f0ab5201 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -261,6 +261,18 @@ static bool has_rb_swapped(uint32_t format)
}
}
+static bool is_fmt_10(uint32_t format)
+{
+ switch (format) {
+ case DRM_FORMAT_NV15:
+ case DRM_FORMAT_NV20:
+ case DRM_FORMAT_NV30:
+ return true;
+ default:
+ return false;
+ }
+}
+
static enum vop_data_format vop_convert_format(uint32_t format)
{
switch (format) {
@@ -276,10 +288,13 @@ static enum vop_data_format vop_convert_format(uint32_t format)
case DRM_FORMAT_BGR565:
return VOP_FMT_RGB565;
case DRM_FORMAT_NV12:
+ case DRM_FORMAT_NV15:
return VOP_FMT_YUV420SP;
case DRM_FORMAT_NV16:
+ case DRM_FORMAT_NV20:
return VOP_FMT_YUV422SP;
case DRM_FORMAT_NV24:
+ case DRM_FORMAT_NV30:
return VOP_FMT_YUV444SP;
default:
DRM_ERROR("unsupported format[%08x]\n", format);
@@ -922,7 +937,12 @@ static void vop_plane_atomic_update(struct drm_plane *plane,
dsp_sty = dest->y1 + crtc->mode.vtotal - crtc->mode.vsync_start;
dsp_st = dsp_sty << 16 | (dsp_stx & 0xffff);
- offset = (src->x1 >> 16) * fb->format->cpp[0];
+ if (fb->format->block_w[0])
+ offset = (src->x1 >> 16) * fb->format->char_per_block[0] /
+ fb->format->block_w[0];
+ else
+ offset = (src->x1 >> 16) * fb->format->cpp[0];
+
offset += (src->y1 >> 16) * fb->pitches[0];
dma_addr = rk_obj->dma_addr + offset + fb->offsets[0];
@@ -948,6 +968,7 @@ static void vop_plane_atomic_update(struct drm_plane *plane,
}
VOP_WIN_SET(vop, win, format, format);
+ VOP_WIN_SET(vop, win, fmt_10, is_fmt_10(fb->format->format));
VOP_WIN_SET(vop, win, yrgb_vir, DIV_ROUND_UP(fb->pitches[0], 4));
VOP_WIN_SET(vop, win, yrgb_mst, dma_addr);
VOP_WIN_YUV2YUV_SET(vop, win_yuv2yuv, y2r_en, is_yuv);
@@ -964,7 +985,11 @@ static void vop_plane_atomic_update(struct drm_plane *plane,
uv_obj = fb->obj[1];
rk_uv_obj = to_rockchip_obj(uv_obj);
- offset = (src->x1 >> 16) * bpp / hsub;
+ if (fb->format->block_w[1])
+ offset = (src->x1 >> 16) * bpp /
+ fb->format->block_w[1] / hsub;
+ else
+ offset = (src->x1 >> 16) * bpp / hsub;
offset += (src->y1 >> 16) * fb->pitches[1] / vsub;
dma_addr = rk_uv_obj->dma_addr + offset + fb->offsets[1];
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
index 857d97cdc67c..b7169010622a 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
@@ -165,6 +165,7 @@ struct vop_win_phy {
struct vop_reg enable;
struct vop_reg gate;
struct vop_reg format;
+ struct vop_reg fmt_10;
struct vop_reg rb_swap;
struct vop_reg act_info;
struct vop_reg dsp_info;
diff --git a/drivers/gpu/drm/rockchip/rockchip_vop_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop_reg.c
index 39e1e1ebea92..5f78697da1b6 100644
--- a/drivers/gpu/drm/rockchip/rockchip_vop_reg.c
+++ b/drivers/gpu/drm/rockchip/rockchip_vop_reg.c
@@ -50,6 +50,23 @@ static const uint32_t formats_win_full[] = {
DRM_FORMAT_NV24,
};
+static const uint32_t formats_win_full_10[] = {
+ DRM_FORMAT_XRGB8888,
+ DRM_FORMAT_ARGB8888,
+ DRM_FORMAT_XBGR8888,
+ DRM_FORMAT_ABGR8888,
+ DRM_FORMAT_RGB888,
+ DRM_FORMAT_BGR888,
+ DRM_FORMAT_RGB565,
+ DRM_FORMAT_BGR565,
+ DRM_FORMAT_NV12,
+ DRM_FORMAT_NV16,
+ DRM_FORMAT_NV24,
+ DRM_FORMAT_NV15,
+ DRM_FORMAT_NV20,
+ DRM_FORMAT_NV30,
+};
+
static const uint64_t format_modifiers_win_full[] = {
DRM_FORMAT_MOD_LINEAR,
DRM_FORMAT_MOD_INVALID,
@@ -584,11 +601,12 @@ static const struct vop_scl_regs rk3288_win_full_scl = {
static const struct vop_win_phy rk3288_win01_data = {
.scl = &rk3288_win_full_scl,
- .data_formats = formats_win_full,
- .nformats = ARRAY_SIZE(formats_win_full),
+ .data_formats = formats_win_full_10,
+ .nformats = ARRAY_SIZE(formats_win_full_10),
.format_modifiers = format_modifiers_win_full,
.enable = VOP_REG(RK3288_WIN0_CTRL0, 0x1, 0),
.format = VOP_REG(RK3288_WIN0_CTRL0, 0x7, 1),
+ .fmt_10 = VOP_REG(RK3288_WIN0_CTRL0, 0x1, 4),
.rb_swap = VOP_REG(RK3288_WIN0_CTRL0, 0x1, 12),
.act_info = VOP_REG(RK3288_WIN0_ACT_INFO, 0x1fff1fff, 0),
.dsp_info = VOP_REG(RK3288_WIN0_DSP_INFO, 0x0fff0fff, 0),
@@ -718,11 +736,12 @@ static const struct vop_intr rk3368_vop_intr = {
static const struct vop_win_phy rk3368_win01_data = {
.scl = &rk3288_win_full_scl,
- .data_formats = formats_win_full,
- .nformats = ARRAY_SIZE(formats_win_full),
+ .data_formats = formats_win_full_10,
+ .nformats = ARRAY_SIZE(formats_win_full_10),
.format_modifiers = format_modifiers_win_full,
.enable = VOP_REG(RK3368_WIN0_CTRL0, 0x1, 0),
.format = VOP_REG(RK3368_WIN0_CTRL0, 0x7, 1),
+ .fmt_10 = VOP_REG(RK3368_WIN0_CTRL0, 0x1, 4),
.rb_swap = VOP_REG(RK3368_WIN0_CTRL0, 0x1, 12),
.x_mir_en = VOP_REG(RK3368_WIN0_CTRL0, 0x1, 21),
.y_mir_en = VOP_REG(RK3368_WIN0_CTRL0, 0x1, 22),
@@ -867,11 +886,12 @@ static const struct vop_win_yuv2yuv_data rk3399_vop_big_win_yuv2yuv_data[] = {
static const struct vop_win_phy rk3399_win01_data = {
.scl = &rk3288_win_full_scl,
- .data_formats = formats_win_full,
- .nformats = ARRAY_SIZE(formats_win_full),
+ .data_formats = formats_win_full_10,
+ .nformats = ARRAY_SIZE(formats_win_full_10),
.format_modifiers = format_modifiers_win_full_afbc,
.enable = VOP_REG(RK3288_WIN0_CTRL0, 0x1, 0),
.format = VOP_REG(RK3288_WIN0_CTRL0, 0x7, 1),
+ .fmt_10 = VOP_REG(RK3288_WIN0_CTRL0, 0x1, 4),
.rb_swap = VOP_REG(RK3288_WIN0_CTRL0, 0x1, 12),
.x_mir_en = VOP_REG(RK3288_WIN0_CTRL0, 0x1, 21),
.y_mir_en = VOP_REG(RK3288_WIN0_CTRL0, 0x1, 22),
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Qinglang Miao <miaoqinglang@huawei.com>
Date: Tue, 1 Dec 2020 20:54:57 +0800
Subject: [PATCH] drm/rockchip: cdn-dp: fix reference leak when
pm_runtime_get_sync fails
The PM reference count is not expected to be incremented on
return in cdn_dp_clk_enable.
However, pm_runtime_get_sync will increment the PM reference
count even failed. Forgetting to putting operation will result
in a reference leak here.
Replace it with pm_runtime_resume_and_get to keep usage
counter balanced.
Fixes: efe0220fc2d2 ("drm/rockchip: cdn-dp: Fix error handling")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Qinglang Miao <miaoqinglang@huawei.com>
---
drivers/gpu/drm/rockchip/cdn-dp-core.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c
index dec54c70e008..de7b162f44fe 100644
--- a/drivers/gpu/drm/rockchip/cdn-dp-core.c
+++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c
@@ -99,7 +99,7 @@ static int cdn_dp_clk_enable(struct cdn_dp_device *dp)
goto err_core_clk;
}
- ret = pm_runtime_get_sync(dp->dev);
+ ret = pm_runtime_resume_and_get(dp->dev);
if (ret < 0) {
DRM_DEV_ERROR(dp->dev, "cannot get pm runtime %d\n", ret);
goto err_pm_runtime_get;
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Qinglang Miao <miaoqinglang@huawei.com>
Date: Tue, 1 Dec 2020 20:54:58 +0800
Subject: [PATCH] drm/rockchip: vop: fix reference leak when
pm_runtime_get_sync fails
The PM reference count is not expected to be incremented on
return in functions vop_enable and vop_enable.
However, pm_runtime_get_sync will increment the PM reference
count even failed. Forgetting to putting operation will result
in a reference leak here.
Replace it with pm_runtime_resume_and_get to keep usage
counter balanced.
Fixes: 5e570373c015 ("drm/rockchip: vop: Enable pm domain before vop_initial")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Qinglang Miao <miaoqinglang@huawei.com>
---
drivers/gpu/drm/rockchip/rockchip_drm_vop.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index b149f0ab5201..35a056e2c49b 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -602,7 +602,7 @@ static int vop_enable(struct drm_crtc *crtc, struct drm_crtc_state *old_state)
struct vop *vop = to_vop(crtc);
int ret, i;
- ret = pm_runtime_get_sync(vop->dev);
+ ret = pm_runtime_resume_and_get(vop->dev);
if (ret < 0) {
DRM_DEV_ERROR(vop->dev, "failed to get pm runtime: %d\n", ret);
return ret;
@@ -1934,7 +1934,7 @@ static int vop_initial(struct vop *vop)
return PTR_ERR(vop->dclk);
}
- ret = pm_runtime_get_sync(vop->dev);
+ ret = pm_runtime_resume_and_get(vop->dev);
if (ret < 0) {
DRM_DEV_ERROR(vop->dev, "failed to get pm runtime: %d\n", ret);
return ret;
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Qinglang Miao <miaoqinglang@huawei.com>
Date: Tue, 1 Dec 2020 20:54:59 +0800
Subject: [PATCH] drm/rockchip: lvds: fix reference leak when
pm_runtime_get_sync fails
The PM reference count is not expected to be incremented on
return in functions rk3288_lvds_poweron and px30_lvds_poweron.
However, pm_runtime_get_sync will increment the PM reference
count even failed. Forgetting to putting operation will result
in a reference leak here.
Replace it with pm_runtime_resume_and_get to keep usage
counter balanced.
Fixes: cca1705c3d89 ("drm/rockchip: lvds: Add PX30 support")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Qinglang Miao <miaoqinglang@huawei.com>
---
drivers/gpu/drm/rockchip/rockchip_lvds.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/rockchip/rockchip_lvds.c b/drivers/gpu/drm/rockchip/rockchip_lvds.c
index 7c20b4a24a7e..b5311c99a0e1 100644
--- a/drivers/gpu/drm/rockchip/rockchip_lvds.c
+++ b/drivers/gpu/drm/rockchip/rockchip_lvds.c
@@ -145,7 +145,7 @@ static int rk3288_lvds_poweron(struct rockchip_lvds *lvds)
DRM_DEV_ERROR(lvds->dev, "failed to enable lvds pclk %d\n", ret);
return ret;
}
- ret = pm_runtime_get_sync(lvds->dev);
+ ret = pm_runtime_resume_and_get(lvds->dev);
if (ret < 0) {
DRM_DEV_ERROR(lvds->dev, "failed to get pm runtime: %d\n", ret);
clk_disable(lvds->pclk);
@@ -329,7 +329,7 @@ static int px30_lvds_poweron(struct rockchip_lvds *lvds)
{
int ret;
- ret = pm_runtime_get_sync(lvds->dev);
+ ret = pm_runtime_resume_and_get(lvds->dev);
if (ret < 0) {
DRM_DEV_ERROR(lvds->dev, "failed to get pm runtime: %d\n", ret);
return ret;
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Lukasz Luba <lukasz.luba@arm.com>
Date: Tue, 5 Jan 2021 16:41:11 +0000
Subject: [PATCH] drm/panfrost: Use delayed timer as default in devfreq profile
Devfreq framework supports 2 modes for monitoring devices.
Use delayed timer as default instead of deferrable timer
in order to monitor the GPU status regardless of CPU idle.
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Reviewed-by: Steven Price <steven.price@arm.com>
---
drivers/gpu/drm/panfrost/panfrost_devfreq.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
index 913eaa6d0bc6..17d5fa6e0b83 100644
--- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c
+++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
@@ -76,6 +76,7 @@ static int panfrost_devfreq_get_dev_status(struct device *dev,
}
static struct devfreq_dev_profile panfrost_devfreq_profile = {
+ .timer = DEVFREQ_TIMER_DELAYED,
.polling_ms = 50, /* ~3 frames */
.target = panfrost_devfreq_target,
.get_dev_status = panfrost_devfreq_get_dev_status,
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Lukasz Luba <lukasz.luba@arm.com>
Date: Thu, 21 Jan 2021 17:04:45 +0000
Subject: [PATCH] drm/panfrost: Add governor data with pre-defined thresholds
The simple_ondemand devfreq governor uses two thresholds to decide about
the frequency change: upthreshold, downdifferential. These two tunable
change the behavior of the governor decision, e.g. how fast to increase
the frequency or how rapidly limit the frequency. This patch adds needed
governor data with thresholds values gathered experimentally in different
workloads.
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
---
drivers/gpu/drm/panfrost/panfrost_devfreq.c | 10 +++++++++-
drivers/gpu/drm/panfrost/panfrost_devfreq.h | 2 ++
2 files changed, 11 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
index 17d5fa6e0b83..53e0188ce8e8 100644
--- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c
+++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
@@ -130,8 +130,16 @@ int panfrost_devfreq_init(struct panfrost_device *pfdev)
panfrost_devfreq_profile.initial_freq = cur_freq;
dev_pm_opp_put(opp);
+ /*
+ * Setup default thresholds for the simple_ondemand governor.
+ * The values are chosen based on experiments.
+ */
+ pfdevfreq->gov_data.upthreshold = 45;
+ pfdevfreq->gov_data.downdifferential = 5;
+
devfreq = devm_devfreq_add_device(dev, &panfrost_devfreq_profile,
- DEVFREQ_GOV_SIMPLE_ONDEMAND, NULL);
+ DEVFREQ_GOV_SIMPLE_ONDEMAND,
+ &pfdevfreq->gov_data);
if (IS_ERR(devfreq)) {
DRM_DEV_ERROR(dev, "Couldn't initialize GPU devfreq\n");
ret = PTR_ERR(devfreq);
diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.h b/drivers/gpu/drm/panfrost/panfrost_devfreq.h
index db6ea48e21f9..1e2a4de941aa 100644
--- a/drivers/gpu/drm/panfrost/panfrost_devfreq.h
+++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.h
@@ -4,6 +4,7 @@
#ifndef __PANFROST_DEVFREQ_H__
#define __PANFROST_DEVFREQ_H__
+#include <linux/devfreq.h>
#include <linux/spinlock.h>
#include <linux/ktime.h>
@@ -17,6 +18,7 @@ struct panfrost_devfreq {
struct devfreq *devfreq;
struct opp_table *regulators_opp_table;
struct thermal_cooling_device *cooling;
+ struct devfreq_simple_ondemand_data gov_data;
bool opp_of_table_added;
ktime_t busy_time;
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@collabora.com>
Date: Fri, 5 Feb 2021 12:17:57 +0100
Subject: [PATCH] drm/panfrost: Stay in the threaded MMU IRQ handler until
we've handled all IRQs
Doing a hw-irq -> threaded-irq round-trip is counter-productive, stay
in the threaded irq handler as long as we can.
v2:
* Rework the loop to avoid a goto
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Steven Price <steven.price@arm.com>
Reviewed-by: Rob Herring <robh@kernel.org>
---
drivers/gpu/drm/panfrost/panfrost_mmu.c | 26 +++++++++++++------------
1 file changed, 14 insertions(+), 12 deletions(-)
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index 7fc45b13a52c..0dbbf2cf298a 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -632,22 +632,20 @@ static irqreturn_t panfrost_mmu_irq_handler_thread(int irq, void *data)
{
struct panfrost_device *pfdev = data;
u32 status = mmu_read(pfdev, MMU_INT_RAWSTAT);
- int i, ret;
+ int ret;
- for (i = 0; status; i++) {
- u32 mask = BIT(i) | BIT(i + 16);
+ while (status) {
+ u32 as = ffs(status | (status >> 16)) - 1;
+ u32 mask = BIT(as) | BIT(as + 16);
u64 addr;
u32 fault_status;
u32 exception_type;
u32 access_type;
u32 source_id;
- if (!(status & mask))
- continue;
-
- fault_status = mmu_read(pfdev, AS_FAULTSTATUS(i));
- addr = mmu_read(pfdev, AS_FAULTADDRESS_LO(i));
- addr |= (u64)mmu_read(pfdev, AS_FAULTADDRESS_HI(i)) << 32;
+ fault_status = mmu_read(pfdev, AS_FAULTSTATUS(as));
+ addr = mmu_read(pfdev, AS_FAULTADDRESS_LO(as));
+ addr |= (u64)mmu_read(pfdev, AS_FAULTADDRESS_HI(as)) << 32;
/* decode the fault status */
exception_type = fault_status & 0xFF;
@@ -658,8 +656,8 @@ static irqreturn_t panfrost_mmu_irq_handler_thread(int irq, void *data)
/* Page fault only */
ret = -1;
- if ((status & mask) == BIT(i) && (exception_type & 0xF8) == 0xC0)
- ret = panfrost_mmu_map_fault_addr(pfdev, i, addr);
+ if ((status & mask) == BIT(as) && (exception_type & 0xF8) == 0xC0)
+ ret = panfrost_mmu_map_fault_addr(pfdev, as, addr);
if (ret)
/* terminal fault, print info about the fault */
@@ -671,7 +669,7 @@ static irqreturn_t panfrost_mmu_irq_handler_thread(int irq, void *data)
"exception type 0x%X: %s\n"
"access type 0x%X: %s\n"
"source id 0x%X\n",
- i, addr,
+ as, addr,
"TODO",
fault_status,
(fault_status & (1 << 10) ? "DECODER FAULT" : "SLAVE FAULT"),
@@ -680,6 +678,10 @@ static irqreturn_t panfrost_mmu_irq_handler_thread(int irq, void *data)
source_id);
status &= ~mask;
+
+ /* If we received new MMU interrupts, process them before returning. */
+ if (!status)
+ status = mmu_read(pfdev, MMU_INT_RAWSTAT);
}
mmu_write(pfdev, MMU_INT_MASK, ~0);
From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Christian Hewitt <christianshewitt@gmail.com>
Date: Wed, 27 Jan 2021 19:40:47 +0000
Subject: [PATCH] drm/lima: add governor data with pre-defined thresholds
This patch adapts the panfrost pre-defined thresholds change [0] to the
lima driver to improve real-world performance. The upthreshold value has
been set to ramp GPU frequency to max freq faster (compared to panfrost)
to compensate for the lower overall performance of utgard devices.
[0] https://patchwork.kernel.org/project/dri-devel/patch/20210121170445.19761-1-lukasz.luba@arm.com/
Signed-off-by: Christian Hewitt <christianshewitt@gmail.com>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Reviewed-by: Qiang Yu <yuq825@gmail.com>
---
drivers/gpu/drm/lima/lima_devfreq.c | 10 +++++++++-
drivers/gpu/drm/lima/lima_devfreq.h | 2 ++
2 files changed, 11 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/lima/lima_devfreq.c b/drivers/gpu/drm/lima/lima_devfreq.c
index 5686ad4aaf7c..c9854315a0b5 100644
--- a/drivers/gpu/drm/lima/lima_devfreq.c
+++ b/drivers/gpu/drm/lima/lima_devfreq.c
@@ -163,8 +163,16 @@ int lima_devfreq_init(struct lima_device *ldev)
lima_devfreq_profile.initial_freq = cur_freq;
dev_pm_opp_put(opp);
+ /*
+ * Setup default thresholds for the simple_ondemand governor.
+ * The values are chosen based on experiments.
+ */
+ ldevfreq->gov_data.upthreshold = 30;
+ ldevfreq->gov_data.downdifferential = 5;
+
devfreq = devm_devfreq_add_device(dev, &lima_devfreq_profile,
- DEVFREQ_GOV_SIMPLE_ONDEMAND, NULL);
+ DEVFREQ_GOV_SIMPLE_ONDEMAND,
+ &ldevfreq->gov_data);
if (IS_ERR(devfreq)) {
dev_err(dev, "Couldn't initialize GPU devfreq\n");
ret = PTR_ERR(devfreq);
diff --git a/drivers/gpu/drm/lima/lima_devfreq.h b/drivers/gpu/drm/lima/lima_devfreq.h
index 2d9b3008ce77..b0c7c736e81a 100644
--- a/drivers/gpu/drm/lima/lima_devfreq.h
+++ b/drivers/gpu/drm/lima/lima_devfreq.h
@@ -4,6 +4,7 @@
#ifndef __LIMA_DEVFREQ_H__
#define __LIMA_DEVFREQ_H__
+#include <linux/devfreq.h>
#include <linux/spinlock.h>
#include <linux/ktime.h>
@@ -18,6 +19,7 @@ struct lima_devfreq {
struct opp_table *clkname_opp_table;
struct opp_table *regulators_opp_table;
struct thermal_cooling_device *cooling;
+ struct devfreq_simple_ondemand_data gov_data;
ktime_t busy_time;
ktime_t idle_time;
View Git Blame Copy Permalink