Introduce in-kernel headers and other artifacts which are made available
as an archive through proc (/proc/kheaders.txz file). This archive makes
it possible to build kernel modules, run eBPF programs, and other
tracing programs that need to extend the kernel for tracing purposes
without any dependency on the file system having headers and build
artifacts.
On Android and embedded systems, it is common to switch kernels but not
have kernel headers available on the file system. Raw kernel headers
also cannot be copied into the filesystem like they can be on other
distros, due to licensing and other issues. There's no linux-headers
package on Android. Further once a different kernel is booted, any
headers stored on the file system will no longer be useful. By storing
the headers as a compressed archive within the kernel, we can avoid these
issues that have been a hindrance for a long time.
The feature is also buildable as a module just in case the user desires
it not being part of the kernel image. This makes it possible to load
and unload the headers on demand. A tracing program, or a kernel module
builder can load the module, do its operations, and then unload the
module to save kernel memory. The total memory needed is 3.8MB.
The code to read the headers is based on /proc/config.gz code and uses
the same technique to embed the headers.
To build a module, the below steps have been tested on an x86 machine:
modprobe kheaders
rm -rf $HOME/headers
mkdir -p $HOME/headers
tar -xvf /proc/kheaders.txz -C $HOME/headers >/dev/null
cd my-kernel-module
make -C $HOME/headers M=$(pwd) modules
rmmod kheaders
Signed-off-by: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>
---
Changes since v1:
- removed IKH_EXTRA variable, not needed (Masahiro Yamada)
- small fix ups to selftest
- added target to main Makefile etc
- added MODULE_LICENSE to test module
- made selftest more quiet
Changes since RFC:
Both changes bring size down to 3.8MB:
- use xz for compression
- strip comments except SPDX lines
- Call out the module name in Kconfig
- Also added selftests in second patch to ensure headers are always
working.
Documentation/dontdiff | 1 +
init/Kconfig | 11 ++++++
kernel/.gitignore | 2 ++
kernel/Makefile | 27 ++++++++++++++
kernel/kheaders.c | 74 +++++++++++++++++++++++++++++++++++++++
scripts/gen_ikh_data.sh | 19 ++++++++++
scripts/strip-comments.pl | 8 +++++
7 files changed, 142 insertions(+)
create mode 100644 kernel/kheaders.c
create mode 100755 scripts/gen_ikh_data.sh
create mode 100755 scripts/strip-comments.pl
diff --git a/Documentation/dontdiff b/Documentation/dontdiff
index 2228fcc8e29f..05a2319ee2a2 100644
--- a/Documentation/dontdiff
+++ b/Documentation/dontdiff
@@ -151,6 +151,7 @@ int8.c
kallsyms
kconfig
keywords.c
+kheaders_data.h*
ksym.c*
ksym.h*
kxgettext
diff --git a/init/Kconfig b/init/Kconfig
index c9386a365eea..9fbf4f73d98c 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -563,6 +563,17 @@ config IKCONFIG_PROC
This option enables access to the kernel configuration file
through /proc/config.gz.
+config IKHEADERS_PROC
+ tristate "Enable kernel header artifacts through /proc/kheaders.txz"
+ select BUILD_BIN2C
+ depends on PROC_FS
+ help
+ This option enables access to the kernel header and other artifacts that
+ are generated during the build process. These can be used to build kernel
+ modules, and other in-kernel programs such as those generated by eBPF
+ and systemtap tools. If you build the headers as a module, a module
+ called kheaders.ko is built which can be loaded to get access to them.
+
config LOG_BUF_SHIFT
int "Kernel log buffer size (16 => 64KB, 17 => 128KB)"
range 12 25
diff --git a/kernel/.gitignore b/kernel/.gitignore
index b3097bde4e9c..6acf71acbdcb 100644
--- a/kernel/.gitignore
+++ b/kernel/.gitignore
@@ -3,5 +3,7 @@
#
config_data.h
config_data.gz
+kheaders_data.h
+kheaders_data.txz
timeconst.h
hz.bc
diff --git a/kernel/Makefile b/kernel/Makefile
index 6aa7543bcdb2..1d13a7a6c537 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -70,6 +70,7 @@ obj-$(CONFIG_UTS_NS) += utsname.o
obj-$(CONFIG_USER_NS) += user_namespace.o
obj-$(CONFIG_PID_NS) += pid_namespace.o
obj-$(CONFIG_IKCONFIG) += configs.o
+obj-$(CONFIG_IKHEADERS_PROC) += kheaders.o
obj-$(CONFIG_SMP) += stop_machine.o
obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o
obj-$(CONFIG_AUDIT) += audit.o auditfilter.o
@@ -130,3 +131,29 @@ filechk_ikconfiggz = \
targets += config_data.h
$(obj)/config_data.h: $(obj)/config_data.gz FORCE
$(call filechk,ikconfiggz)
+
+# Build a list of in-kernel headers for building kernel modules
+ikh_file_list := include/
+ikh_file_list += arch/$(ARCH)/Makefile
+ikh_file_list += arch/$(ARCH)/include/
+ikh_file_list += scripts/
+ikh_file_list += Makefile
+ikh_file_list += Module.symvers
+ifeq ($(CONFIG_STACK_VALIDATION), y)
+ikh_file_list += $(objtree)/tools/objtool/objtool
+endif
+
+$(obj)/kheaders.o: $(obj)/kheaders_data.h
+
+targets += kheaders_data.txz
+
+quiet_cmd_genikh = GEN $(obj)/kheaders_data.txz
+cmd_genikh = $(srctree)/scripts/gen_ikh_data.sh $@ $^ >/dev/null 2>&1
+$(obj)/kheaders_data.txz: $(ikh_file_list) FORCE
+ $(call cmd,genikh)
+
+filechk_ikheadersxz = (echo "static const char kernel_headers_data[] __used = KH_MAGIC_START"; cat $< | scripts/bin2c; echo "KH_MAGIC_END;")
+
+targets += kheaders_data.h
+$(obj)/kheaders_data.h: $(obj)/kheaders_data.txz FORCE
+ $(call filechk,ikheadersxz)
diff --git a/kernel/kheaders.c b/kernel/kheaders.c
new file mode 100644
index 000000000000..c39930f51202
--- /dev/null
+++ b/kernel/kheaders.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * kernel/kheaders.c
+ * Provide headers and artifacts needed to build kernel modules.
+ * (Borrowed code from kernel/configs.c)
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/init.h>
+#include <linux/uaccess.h>
+
+/*
+ * Define kernel_headers_data and kernel_headers_data_size, which contains the
+ * compressed kernel headers. The file is first compressed with xz and then
+ * bounded by two eight byte magic numbers to allow extraction from a binary
+ * kernel image:
+ *
+ * IKHD_ST
+ * <image>
+ * IKHD_ED
+ */
+#define KH_MAGIC_START "IKHD_ST"
+#define KH_MAGIC_END "IKHD_ED"
+#include "kheaders_data.h"
+
+
+#define KH_MAGIC_SIZE (sizeof(KH_MAGIC_START) - 1)
+#define kernel_headers_data_size \
+ (sizeof(kernel_headers_data) - 1 - KH_MAGIC_SIZE * 2)
+
+static ssize_t
+ikheaders_read_current(struct file *file, char __user *buf,
+ size_t len, loff_t *offset)
+{
+ return simple_read_from_buffer(buf, len, offset,
+ kernel_headers_data + KH_MAGIC_SIZE,
+ kernel_headers_data_size);
+}
+
+static const struct file_operations ikheaders_file_ops = {
+ .owner = THIS_MODULE,
+ .read = ikheaders_read_current,
+ .llseek = default_llseek,
+};
+
+static int __init ikheaders_init(void)
+{
+ struct proc_dir_entry *entry;
+
+ /* create the current headers file */
+ entry = proc_create("kheaders.txz", S_IFREG | S_IRUGO, NULL,
+ &ikheaders_file_ops);
+ if (!entry)
+ return -ENOMEM;
+
+ proc_set_size(entry, kernel_headers_data_size);
+
+ return 0;
+}
+
+static void __exit ikheaders_cleanup(void)
+{
+ remove_proc_entry("kheaders.txz", NULL);
+}
+
+module_init(ikheaders_init);
+module_exit(ikheaders_cleanup);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Joel Fernandes");
+MODULE_DESCRIPTION("Echo the kernel header artifacts used to build the kernel");
diff --git a/scripts/gen_ikh_data.sh b/scripts/gen_ikh_data.sh
new file mode 100755
index 000000000000..609196b5cea2
--- /dev/null
+++ b/scripts/gen_ikh_data.sh
@@ -0,0 +1,19 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+spath="$(dirname "$(readlink -f "$0")")"
+
+rm -rf $1.tmp
+mkdir $1.tmp
+
+for f in "${@:2}";
+ do find "$f" ! -name "*.c" ! -name "*.o" ! -name "*.cmd" ! -name ".*";
+done | cpio -pd $1.tmp
+
+for f in $(find $1.tmp); do
+ $spath/strip-comments.pl $f
+done
+
+tar -Jcf $1 -C $1.tmp/ . > /dev/null
+
+rm -rf $1.tmp
diff --git a/scripts/strip-comments.pl b/scripts/strip-comments.pl
new file mode 100755
index 000000000000..f8ada87c5802
--- /dev/null
+++ b/scripts/strip-comments.pl
@@ -0,0 +1,8 @@
+#!/usr/bin/perl -pi
+# SPDX-License-Identifier: GPL-2.0
+
+# This script removes /**/ comments from a file, unless such comments
+# contain "SPDX". It is used when building compressed in-kernel headers.
+
+BEGIN {undef $/;}
+s/\/\*((?!SPDX).)*?\*\///smg;
--
2.20.1.791.gb4d0f1c61a-goog
