| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20181018162548.6399-5-changbin.du@gmail.com>
Date: Thu, 18 Oct 2018 16:25:48 +0000
From: Du Changbin <changbin.du@...il.com>
To: yamada.masahiro@...ionext.com, michal.lkml@...kovi.net,
tglx@...utronix.de, mingo@...hat.com, linux@...linux.org.uk,
akpm@...ux-foundation.org
Cc: rostedt@...dmis.org, x86@...nel.org, linux-kbuild@...r.kernel.org,
linux-kernel@...r.kernel.org, linux-arm-kernel@...ts.infradead.org,
linux-sparse@...r.kernel.org, Changbin Du <changbin.du@...el.com>
Subject: [PATCH 4/4] kernel hacking: new config CC_OPTIMIZE_FOR_DEBUGGING to apply GCC -Og optimization
From: Changbin Du <changbin.du@...el.com>
This will apply GCC '-Og' optimization level which is supported
since GCC 4.8. This optimization level offers a reasonable level
of optimization while maintaining fast compilation and a good
debugging experience. It is similar to '-O1' while perferring
to keep debug ability over runtime speed.
If enabling this option breaks your kernel, you should either
disable this or find a fix (mostly in the arch code). Currently
this option has only been tested on x86_64 and arm platform.
This option can satisfy people who was searching for a method
to disable compiler optimizations so to achieve better kernel
debugging experience with kgdb or qemu.
The main problem of '-Og' is we must not use __attribute__((error(msg))).
The compiler will report error though the call to error function
still can be optimize out. So we must fallback to array tricky.
Comparison of vmlinux size: a bit smaller.
w/o CONFIG_CC_OPTIMIZE_FOR_DEBUGGING
$ size vmlinux
text data bss dec hex filename
22665554 9709674 2920908 35296136 21a9388 vmlinux
w/ CONFIG_CC_OPTIMIZE_FOR_DEBUGGING
$ size vmlinux
text data bss dec hex filename
21499032 10102758 2920908 34522698 20ec64a vmlinux
Comparison of system performance: a bit drop (~6%).
This benchmark of kernel compilation is suggested by Ingo Molnar.
https://lkml.org/lkml/2018/5/2/74
Preparation: Set cpufreq to 'performance'.
for ((cpu=0; cpu<120; cpu++)); do
G=/sys/devices/system/cpu/cpu$cpu/cpufreq/scaling_governor
[ -f $G ] && echo performance > $G
done
w/o CONFIG_CC_OPTIMIZE_FOR_DEBUGGING
$ perf stat --repeat 5 --null --pre '\
cp -a kernel ../kernel.copy.$(date +%s); \
rm -rf *; \
git checkout .; \
echo 1 > /proc/sys/vm/drop_caches; \
find ../kernel* -type f | xargs cat >/dev/null; \
make -j kernel >/dev/null; \
make clean >/dev/null 2>&1; \
sync '\
\
make -j8 >/dev/null
Performance counter stats for 'make -j8' (5 runs):
219.764246652 seconds time elapsed ( +- 0.78% )
w/ CONFIG_CC_OPTIMIZE_FOR_DEBUGGING
$ perf stat --repeat 5 --null --pre '\
cp -a kernel ../kernel.copy.$(date +%s); \
rm -rf *; \
git checkout .; \
echo 1 > /proc/sys/vm/drop_caches; \
find ../kernel* -type f | xargs cat >/dev/null; \
make -j kernel >/dev/null; \
make clean >/dev/null 2>&1; \
sync '\
\
make -j8 >/dev/null
Performance counter stats for 'make -j8' (5 runs):
233.574187771 seconds time elapsed ( +- 0.19% )
Signed-off-by: Changbin Du <changbin.du@...el.com>
Acked-by: Steven Rostedt (VMware) <rostedt@...dmis.org>
---
Makefile | 5 +++++
include/linux/compiler-gcc.h | 2 +-
include/linux/compiler.h | 2 +-
init/Kconfig | 19 +++++++++++++++++++
4 files changed, 26 insertions(+), 2 deletions(-)
diff --git a/Makefile b/Makefile
index 757d6507cb5c..0e747fafb53b 100644
--- a/Makefile
+++ b/Makefile
@@ -657,6 +657,10 @@ KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation)
KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow)
KBUILD_CFLAGS += $(call cc-disable-warning, int-in-bool-context)
+ifdef CONFIG_CC_OPTIMIZE_FOR_DEBUGGING
+KBUILD_CFLAGS += $(call cc-option, -Og)
+KBUILD_CFLAGS += $(call cc-disable-warning,maybe-uninitialized,)
+else
ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
KBUILD_CFLAGS += $(call cc-option,-Oz,-Os)
KBUILD_CFLAGS += $(call cc-disable-warning,maybe-uninitialized,)
@@ -667,6 +671,7 @@ else
KBUILD_CFLAGS += -O2
endif
endif
+endif
KBUILD_CFLAGS += $(call cc-ifversion, -lt, 0409, \
$(call cc-disable-warning,maybe-uninitialized,))
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 4d36b27214fd..2a76f7c64b54 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -85,7 +85,7 @@
#define __compiletime_object_size(obj) __builtin_object_size(obj, 0)
-#ifndef __CHECKER__
+#if !defined(__CHECKER__) && !defined(CONFIG_CC_OPTIMIZE_FOR_DEBUGGING)
#define __compiletime_warning(message) __attribute__((warning(message)))
#define __compiletime_error(message) __attribute__((error(message)))
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 681d866efb1e..9385c62e9f00 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -320,7 +320,7 @@ static inline void *offset_to_ptr(const int *off)
* sparse see a constant array size without breaking compiletime_assert on old
* versions of GCC (e.g. 4.2.4), so hide the array from sparse altogether.
*/
-# ifndef __CHECKER__
+# if !defined(__CHECKER__) && !defined(CONFIG_CC_OPTIMIZE_FOR_DEBUGGING)
# define __compiletime_error_fallback(condition) \
do { ((void)sizeof(char[1 - 2 * condition])); } while (0)
# endif
diff --git a/init/Kconfig b/init/Kconfig
index 1e234e2f1cba..b01c7c654570 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1081,6 +1081,25 @@ config CC_OPTIMIZE_FOR_SIZE
If unsure, say N.
+config CC_OPTIMIZE_FOR_DEBUGGING
+ bool "Optimize for better debugging experience (-Og)"
+ select NO_AUTO_INLINE
+ help
+ This will apply GCC '-Og' optimization level which is supported
+ since GCC 4.8. This optimization level offers a reasonable level
+ of optimization while maintaining fast compilation and a good
+ debugging experience. It is similar to '-O1' while preferring to
+ keep debug ability over runtime speed. The overall performance
+ will drop a bit (~6%).
+
+ Use only if you want to debug the kernel, especially if you want
+ to have better kernel debugging experience with gdb facilities
+ like kgdb or qemu. If enabling this option breaks your kernel,
+ you should either disable this or find a fix (mostly in the arch
+ code).
+
+ If unsure, select N.
+
endchoice
config HAVE_LD_DEAD_CODE_DATA_ELIMINATION
--
2.17.1
Powered by blists - more mailing lists