jetson-optimize-memory

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

jetson-optimize-memory

Jetson内存优化

Memory is reserved across four layers ordered by boot chronology (higher row = earlier in boot, closer to hardware):

Layer	Content	Key files
MB1 BCT	firmware carveouts	per-module misc DTS
MB2 BCT	firmware loading + AST controls	per-module misc DTS
Kernel DTS	reserved-memory and driver binding	per-module DTS
SWIOTLB	DMA bounce pool size	`<module>.conf.common` ( `CMDLINE_ADD` )

Critical rules:

Only the scenarios in Scenario recipes are validated. Refuse any request to disable a carveout/cluster/node not in that table.
Zeroing a carveout requires both: disabling the cluster's loading controls AND removing the AST that references it.
Emit explicit overrides for every cluster in the recipe, regardless of how the source
```
#ifdef
```
/
```
#else
```
looks. Verify the merged binary.
GPU SW stack must match the chip: T234 -> nvgpu, T264 and later -> OpenRM. Follow the shared derived-platform rule in
```
target-platform-contract.md
```
; stop on mismatches instead of guessing.
Do not set SWIOTLB to 0 — some peripherals can't use the IOMMU.

内存会按启动时序分为四层进行预留（行数越靠上，启动阶段越早，越接近硬件）：

层级	内容	关键文件
MB1 BCT	固件内存划分	各模块misc DTS
MB2 BCT	固件加载 + AST控制	各模块misc DTS
Kernel DTS	保留内存与驱动绑定	各模块DTS
SWIOTLB	DMA bounce池大小	`<module>.conf.common` （ `CMDLINE_ADD` ）

关键规则：

仅验证场景方案中列出的场景。拒绝任何禁用方案表格之外的内存划分/集群/节点的请求。
清空内存划分需同时执行两项操作：禁用集群的加载控制 AND 删除引用它的AST。
为方案中的每个集群添加显式覆盖配置，无论源文件中的
```
#ifdef
```
/
```
#else
```
结构如何。请验证合并后的二进制文件。
GPU软件栈必须与芯片匹配：T234 → nvgpu，T264及之后的芯片 → OpenRM。遵循
```
target-platform-contract.md
```
中的共享派生平台规则；若不匹配则停止操作，不要猜测。
请勿将SWIOTLB设置为0 — 部分外设无法使用IOMMU。

Scenario recipes

场景方案

Keyword	MB1 BCT carveouts	MB2 BCT	Kernel DTS
`headless`	DCE-family (see chip table)	DCE `auxp_controls` + DCE AST(s)	`display@<addr>` (and `dce@<addr>` if exposed) → disabled
`no-camera`	RCE/VI/ISP-family	RCE `auxp_controls` (each instance) + RCE AST(s)	recommended: VI/ISP/NVCSI → disabled

关键词	MB1 BCT内存划分	MB2 BCT	Kernel DTS
`headless`	DCE系列（见芯片表格）	DCE `auxp_controls` + DCE AST(s)	`display@<addr>` （若 `dce@<addr>` 暴露则同时包含）→ 禁用
`no-camera`	RCE/VI/ISP系列	RCE `auxp_controls` （每个实例） + RCE AST(s)	推荐：VI/ISP/NVCSI → 禁用

Chip-specific carveouts

芯片专属内存划分

Scenario T234 (Orin) T264 (Thor)

Scenario	T234 (Orin)	T264 (Thor)
`headless`	`CARVEOUT_BPMP_DCE` , `CARVEOUT_DCE` , `CARVEOUT_DCE_TSEC` , `CARVEOUT_TSEC_DCE` , `CARVEOUT_DISP_EARLY_BOOT_FB`	`CARVEOUT_DCE` , `CARVEOUT_TSEC_DCE` , `CARVEOUT_HPSE_DCE` , `CARVEOUT_DISP_EARLY_BOOT_FB`
`no-camera`	`CARVEOUT_RCE` , `CARVEOUT_CAMERA_TASKLIST`	`CARVEOUT_RCE` , `CARVEOUT_RCE1` , `CARVEOUT_RCE_RW` , `CARVEOUT_VI_TASKLIST` , `CARVEOUT_VI1_TASKLIST` , `CARVEOUT_ISP_TASKLIST` , `CARVEOUT_ISP1_TASKLIST`

headless

CARVEOUT_BPMP_DCE

CARVEOUT_DCE

CARVEOUT_DCE_TSEC

CARVEOUT_TSEC_DCE

CARVEOUT_DISP_EARLY_BOOT_FB

CARVEOUT_DCE

CARVEOUT_TSEC_DCE

CARVEOUT_HPSE_DCE

CARVEOUT_DISP_EARLY_BOOT_FB

no-camera

CARVEOUT_RCE

CARVEOUT_CAMERA_TASKLIST

CARVEOUT_RCE

CARVEOUT_RCE1

CARVEOUT_RCE_RW

CARVEOUT_VI_TASKLIST

CARVEOUT_VI1_TASKLIST

CARVEOUT_ISP_TASKLIST

CARVEOUT_ISP1_TASKLIST

Post-boot:

headless

→

sudo systemctl set-default multi-user.target

场景 T234（Orin） T264（Thor）

场景	T234（Orin）	T264（Thor）
`headless`	`CARVEOUT_BPMP_DCE` , `CARVEOUT_DCE` , `CARVEOUT_DCE_TSEC` , `CARVEOUT_TSEC_DCE` , `CARVEOUT_DISP_EARLY_BOOT_FB`	`CARVEOUT_DCE` , `CARVEOUT_TSEC_DCE` , `CARVEOUT_HPSE_DCE` , `CARVEOUT_DISP_EARLY_BOOT_FB`
`no-camera`	`CARVEOUT_RCE` , `CARVEOUT_CAMERA_TASKLIST`	`CARVEOUT_RCE` , `CARVEOUT_RCE1` , `CARVEOUT_RCE_RW` , `CARVEOUT_VI_TASKLIST` , `CARVEOUT_VI1_TASKLIST` , `CARVEOUT_ISP_TASKLIST` , `CARVEOUT_ISP1_TASKLIST`

headless

CARVEOUT_BPMP_DCE

CARVEOUT_DCE

CARVEOUT_DCE_TSEC

CARVEOUT_TSEC_DCE

CARVEOUT_DISP_EARLY_BOOT_FB

CARVEOUT_DCE

CARVEOUT_TSEC_DCE

CARVEOUT_HPSE_DCE

CARVEOUT_DISP_EARLY_BOOT_FB

no-camera

CARVEOUT_RCE

CARVEOUT_CAMERA_TASKLIST

CARVEOUT_RCE

CARVEOUT_RCE1

CARVEOUT_RCE_RW

CARVEOUT_VI_TASKLIST

CARVEOUT_VI1_TASKLIST

CARVEOUT_ISP_TASKLIST

CARVEOUT_ISP1_TASKLIST

启动后操作：
headless
场景 →
sudo systemctl set-default multi-user.target
。

MB1 BCT carveout overrides

MB1 BCT内存划分覆盖配置

File:

Linux_for_Tegra/bootloader/generic/BCT/tegra<chip>-mb1-bct-misc-<module>.dts

(e.g.

tegra234-mb1-bct-misc-p3767-0000.dts

for Orin Nano,

tegra264-mb1-bct-misc-p3834-0008-p4071-0000.dts

for Thor).

For each carveout, add inside the existing

carveout

node:

dts

aux_info@<CARVEOUT_NAME> {
    pref_base = <0x0 0x0>;
    size      = <0x0 0x0>;
    alignment = <0x0 0x0>;
};

文件路径：

Linux_for_Tegra/bootloader/generic/BCT/tegra<chip>-mb1-bct-misc-<module>.dts

（例如，Orin Nano对应

tegra234-mb1-bct-misc-p3767-0000.dts

，Thor对应

tegra264-mb1-bct-misc-p3834-0008-p4071-0000.dts

）。

针对每个内存划分，在已有的

carveout

节点内添加：

dts

aux_info@<CARVEOUT_NAME> {
    pref_base = <0x0 0x0>;
    size      = <0x0 0x0>;
    alignment = <0x0 0x0>;
};

MB2 BCT cluster + AST overrides

MB2 BCT集群 + AST覆盖配置

File:

Linux_for_Tegra/bootloader/generic/BCT/tegra<chip>-mb2-bct-misc-<module>.dts

(includes

tegra<chip>-mb2-bct-common.dtsi

For each target cluster:

Override

auxp_controls@<index>

dts

auxp_controls@<index> {
    enable_init    = <0>;
    enable_fw_load = <0>;
    enable_unhalt  = <0>;
};

```
/delete-node/ auxp_ast_config@<idx>;
```

Look up indices in

common.dtsi

auxp_controls@N

carries a comment naming its cluster;

auxp_ast_config@N

has

ast_region

children whose

carveout = <CARVEOUT_…>;

lines identify the owner.

文件路径：

Linux_for_Tegra/bootloader/generic/BCT/tegra<chip>-mb2-bct-misc-<module>.dts

（包含

tegra<chip>-mb2-bct-common.dtsi

）。

针对每个目标集群：

覆盖

auxp_controls@<index>

：

dts

auxp_controls@<index> {
    enable_init    = <0>;
    enable_fw_load = <0>;
    enable_unhalt  = <0>;
};

添加
```
/delete-node/ auxp_ast_config@<idx>;
```

在

common.dtsi

中查找索引：

auxp_controls@N

带有注释说明其所属集群；

auxp_ast_config@N

的

ast_region

子节点包含

carveout = <CARVEOUT_…>;

行，用于标识所属内存划分。

Kernel DT reserved-memory

内核DT保留内存

DTB=Linux_for_Tegra/kernel/dtb/<platform-dtb-name>.dtb
dtc -I dtb -O dts -o /tmp/platform.dts $DTB

DTB=Linux_for_Tegra/kernel/dtb/<platform-dtb-name>.dtb
dtc -I dtb -O dts -o /tmp/platform.dts $DTB

edit: status = "disabled" on target nodes

编辑：将目标节点的status设置为"disabled"

dtc -I dts -O dtb -o $DTB /tmp/platform.dts


**Display** — disable `display@<addr>`, plus `dce@<addr>` if exposed as
a separate kernel node.

**Camera** — under `host1x@<addr>`, disable whichever of `vi*` / `isp*`
/ `nvcsi` exist on the BSP (only emit present nodes):

Locate the display controller node in the decompiled DTS and disable it.
The node's unit address is chip-specific — find it by `compatible` string
(e.g. `nvidia,tegra234-display`) rather than hard-coding the address.

```dts
host1x@<addr> {
    vi0@<addr>   { status = "disabled"; };
    vi1@<addr>   { status = "disabled"; };
    isp@<addr>   { status = "disabled"; };
    isp1@<addr>  { status = "disabled"; };
    nvcsi@<addr> { status = "disabled"; };
};

dtc -I dts -O dtb -o $DTB /tmp/platform.dts


**显示模块** — 禁用`display@<addr>`，若`dce@<addr>`作为独立内核节点暴露则同时禁用。

**摄像头模块** — 在`host1x@<addr>`下，禁用BSP中存在的`vi*` / `isp*` / `nvcsi`节点（仅对已存在的节点进行配置）：

在反编译后的DTS中找到显示控制器节点并禁用。节点的单元地址是芯片专属的 — 通过`compatible`字符串（例如`nvidia,tegra234-display`）查找，而非硬编码地址。

```dts
host1x@<addr> {
    vi0@<addr>   { status = "disabled"; };
    vi1@<addr>   { status = "disabled"; };
    isp@<addr>   { status = "disabled"; };
    isp1@<addr>  { status = "disabled"; };
    nvcsi@<addr> { status = "disabled"; };
};

SWIOTLB DMA bounce pool

SWIOTLB DMA bounce池

The NVIDIA IOMMU covers peripheral DMA, so SWIOTLB is rarely used. Edit

CMDLINE_ADD

(never

CMDLINE

) in

Linux_for_Tegra/<module>.conf.common

undefined

NVIDIA IOMMU覆盖了外设DMA，因此SWIOTLB很少被使用。编辑

Linux_for_Tegra/<module>.conf.common

中的

CMDLINE_ADD

（切勿修改

CMDLINE

）：

undefined

Total bytes = swiotlb_value × 2048; 4 MiB pool:

总字节数 = swiotlb_value × 2048；4 MiB池配置：

CMDLINE_ADD="... swiotlb=2048"

---

CMDLINE_ADD="... swiotlb=2048"

---

Override verification (mandatory)

覆盖配置验证（必填）

After every patched MB1/MB2 BCT

.dts

, reproduce the BSP's compile + decompile using the same

-D…

flags from

bct_flags.append(...)

bootloader/tegraflash_impl_t<chip>.py

gcc -E -nostdinc -x assembler-with-cpp \
    -DENABLE_<FLAG_1> -DENABLE_<FLAG_2> \
    -I bootloader -I bootloader/generic/BCT \
    -o /tmp/cpp.dts <patched-bct.dts>
dtc -q -I dts -O dtb -o /tmp/cpp.dtb /tmp/cpp.dts
dtc -q -I dtb -O dts /tmp/cpp.dtb | less

Confirm in the merged output:

Each zeroed

aux_info@<NAME>

(or

aux_info@<id>U

post macro expansion) has

size = <0x0 0x0>

and

pref_base = <0x0 0x0>

Each disabled
```
auxp_controls@<idx>
```
has all three
```
enable_*
```
fields
```
<0>
```
.
Each
```
/delete-node/
```
'd
```
auxp_ast_config@<idx>
```
is absent.

在每次修改MB1/MB2 BCT的

.dts

文件后，使用

bootloader/tegraflash_impl_t<chip>.py

中

bct_flags.append(...)

的相同

-D…

参数，重现BSP的编译+反编译流程：

gcc -E -nostdinc -x assembler-with-cpp \
    -DENABLE_<FLAG_1> -DENABLE_<FLAG_2> \
    -I bootloader -I bootloader/generic/BCT \
    -o /tmp/cpp.dts <patched-bct.dts>
dtc -q -I dts -O dtb -o /tmp/cpp.dtb /tmp/cpp.dts
dtc -q -I dtb -O dts /tmp/cpp.dtb | less

在合并后的输出中确认：

每个被清空的

aux_info@<NAME>

（或宏展开后的

aux_info@<id>U

）的

size = <0x0 0x0>

且

pref_base = <0x0 0x0>

。

每个被禁用的
```
auxp_controls@<idx>
```
的三个
```
enable_*
```
字段均为
```
<0>
```
。
每个被
```
/delete-node/
```
删除的
```
auxp_ast_config@<idx>
```
不存在。

Verification (on booted target)

启动后验证

sudo cat /proc/iomem | grep -iE 'nv-reserved|cma|fb|carveout'
ls /proc/device-tree/reserved-memory/
dmesg | grep -iE 'firmware|carveout|bpmp|reserved|fail|error' | head -20
free -m

Scenario	Sysfs	dmesg grep
Display off	`ls /sys/class/drm/` (empty)	`tegra-drm\|nvdisplay\|dce\|host1x\|fb0`
Camera off	`ls /dev/video* 2>/dev/null` (none)	`rce\|nvcsi\|tegra-camera\|vi0\|vi1\|isp`
SWIOTLB shrink	`cat /sys/kernel/debug/swiotlb/io_tlb_nslabs` matches cmdline	`swiotlb`

For SWIOTLB:

/proc/cmdline

must contain

swiotlb=<value>

, and

watch -n5 cat /sys/kernel/debug/swiotlb/io_tlb_used

must stay under

io_tlb_nslabs

during full workload — if exceeded, restore original

CMDLINE_ADD

and re-flash

kernel-dtb

sudo cat /proc/iomem | grep -iE 'nv-reserved|cma|fb|carveout'
ls /proc/device-tree/reserved-memory/
dmesg | grep -iE 'firmware|carveout|bpmp|reserved|fail|error' | head -20
free -m

场景	Sysfs验证	dmesg过滤关键词
显示关闭	`ls /sys/class/drm/` （无输出）	`tegra-drm\|nvdisplay\|dce\|host1x\|fb0`
摄像头关闭	`ls /dev/video* 2>/dev/null` （无输出）	`rce\|nvcsi\|tegra-camera\|vi0\|vi1\|isp`
SWIOTLB缩小	`cat /sys/kernel/debug/swiotlb/io_tlb_nslabs` 与命令行参数匹配	`swiotlb`

对于SWIOTLB：

/proc/cmdline

必须包含

swiotlb=<value>

，且在全负载运行时

watch -n5 cat /sys/kernel/debug/swiotlb/io_tlb_used

必须小于

io_tlb_nslabs

— 若超出限制，恢复原始

CMDLINE_ADD

并重新刷写

kernel-dtb

。

Purpose

目标

Cut the unused DRAM carveouts that ship enabled in the reference BSP when a Jetson deployment skips display, camera, or other peripherals, freeing the freed bytes for the application. Always edits the four layers in boot order so an early-stage carveout never outranks a later-stage shrink.

当Jetson部署场景无需显示、摄像头或其他外设时，削减参考BSP中默认启用的未使用DRAM内存划分，释放出的内存可供应用使用。始终按照启动顺序修改四个层级，确保早期阶段的内存划分不会覆盖后期阶段的缩减配置。

Prerequisites

前置条件

Active target profile resolved per

../../context/target-platform-contract.md

BSP image extracted and source tree initialized (
```
/jetson-init-image
```
,
```
/jetson-init-source
```
complete).
For headless / no-camera recipes: confirm the workload truly does not need display or camera.

已根据

../../context/target-platform-contract.md

确定目标设备配置。

BSP镜像已提取且源码树已初始化（
```
/jetson-init-image
```
、
```
/jetson-init-source
```
执行完成）。
对于无界面/无摄像头方案：确认工作负载确实不需要显示或摄像头功能。

Limitations

限制

Only the validated recipes (
```
headless
```
,
```
no-camera
```
,
```
swiotlb
```
) are exposed; ad-hoc subsystem disables outside the recipe set are refused.
SWIOTLB shrink is bounded by peak in-flight DMA — exceeding the new
```
io_tlb_nslabs
```
requires reverting the change.
BPMP-DTB edits land in the overlay tracker only after Customize + Build + Deploy run; this skill does not flash on its own.

仅提供已验证的方案（
```
headless
```
、
```
no-camera
```
、
```
swiotlb
```
）；拒绝方案集之外的临时子系统禁用请求。
SWIOTLB的缩小受限于峰值DMA流量 — 若超出新的
```
io_tlb_nslabs
```
限制，需恢复修改。
BPMP-DTB修改需在执行Customize + Build + Deploy后才会加入覆盖跟踪；本操作不会自行完成刷写。

Troubleshooting

故障排除

Boot fails after MB1 BCT carveout disable — restore the pristine misc DTS and re-flash; the missing carveout is mandatory for the active SoC.
io_tlb_used
exceeds
io_tlb_nslabs
— revert
```
swiotlb=
```
in
```
CMDLINE_ADD
```
and re-flash the kernel DTB partition.
Reclaimed delta smaller than expected — verify the recipe truly matched the deployment (e.g. display still attached); use the
```
dmesg | grep -iE 'firmware|carveout'
```
check in this file to confirm.
Validation
dmesg
shows the disabled subsystem still probing — the change probably did not promote through to
```
bsp_image
```
; re-run
```
/jetson-promote-image
```
.

MB1 BCT内存划分禁用后启动失败 — 恢复原始misc DTS并重新刷写；该内存划分对当前SoC是必需的。
io_tlb_used
超出
io_tlb_nslabs
— 恢复
```
CMDLINE_ADD
```
中的
```
swiotlb=
```
配置并重新刷写内核DTB分区。
回收的内存增量低于预期 — 验证方案是否与部署场景匹配（例如是否仍连接了显示器）；使用本文中的
```
dmesg | grep -iE 'firmware|carveout'
```
命令进行检查确认。
验证时dmesg显示已禁用的子系统仍在探测 — 修改可能未同步到
```
bsp_image
```
；重新执行
```
/jetson-promote-image
```
。