| 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
| ||
|
Date: Fri, 19 Feb 2010 15:22:05 +0100
From: Borislav Petkov <bp@...64.org>
To: "H. Peter Anvin" <hpa@...or.com>
Cc: Michal Marek <mmarek@...e.cz>, Borislav Petkov <bp@...64.org>,
linux-kbuild <linux-kbuild@...r.kernel.org>,
Peter Zijlstra <peterz@...radead.org>,
Andrew Morton <akpm@...ux-foundation.org>,
Wu Fengguang <fengguang.wu@...el.com>,
LKML <linux-kernel@...r.kernel.org>,
Jamie Lokier <jamie@...reable.org>,
Roland Dreier <rdreier@...co.com>,
Al Viro <viro@...IV.linux.org.uk>,
"linux-fsdevel@...r.kernel.org" <linux-fsdevel@...r.kernel.org>,
Ingo Molnar <mingo@...e.hu>, Brian Gerst <brgerst@...il.com>
Subject: [PATCH] x86: Add optimized popcnt variants
From: Borislav Petkov <borislav.petkov@....com>
Add support for the hardware version of the Hamming weight function,
popcnt, present in CPUs which advertize it under CPUID, Function
0x0000_0001_ECX[23]. On CPUs which don't support it, we fallback to the
default lib/hweight.c sw versions.
A synthetic benchmark comparing popcnt with __sw_hweight64 showed almost
a 3x speedup on a F10h machine.
Signed-off-by: Borislav Petkov <borislav.petkov@....com>
---
arch/x86/Kconfig | 5 ++
arch/x86/include/asm/bitops.h | 7 +++-
arch/x86/lib/Makefile | 2 +-
arch/x86/lib/hweight.c | 62 +++++++++++++++++++++++++++++
include/asm-generic/bitops/arch_hweight.h | 22 ++++++++--
lib/Makefile | 3 +
lib/hweight.c | 20 +++++-----
scripts/Makefile.lib | 4 ++
8 files changed, 109 insertions(+), 16 deletions(-)
create mode 100644 arch/x86/lib/hweight.c
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index eb40925..176950e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -230,6 +230,11 @@ config X86_32_LAZY_GS
def_bool y
depends on X86_32 && !CC_STACKPROTECTOR
+config ARCH_HWEIGHT_CFLAGS
+ string
+ default "-fcall-saved-ecx -fcall-saved-edx" if X86_32
+ default "-fcall-saved-rsi -fcall-saved-rdx -fcall-saved-rcx -fcall-saved-r8 -fcall-saved-r9 -fcall-saved-r10 -fcall-saved-r11" if X86_64
+
config KTIME_SCALAR
def_bool X86_32
source "init/Kconfig"
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 02b47a6..5ec3bd8 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -444,7 +444,12 @@ static inline int fls(int x)
#define ARCH_HAS_FAST_MULTIPLIER 1
-#include <asm-generic/bitops/hweight.h>
+extern unsigned int __arch_hweight32(unsigned int w);
+extern unsigned int __arch_hweight16(unsigned int w);
+extern unsigned int __arch_hweight8(unsigned int w);
+extern unsigned long __arch_hweight64(__u64 w);
+
+#include <asm-generic/bitops/const_hweight.h>
#endif /* __KERNEL__ */
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index cffd754..e811bbd 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -22,7 +22,7 @@ lib-y += usercopy_$(BITS).o getuser.o putuser.o
lib-y += memcpy_$(BITS).o
lib-$(CONFIG_KPROBES) += insn.o inat.o
-obj-y += msr.o msr-reg.o msr-reg-export.o
+obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o
ifeq ($(CONFIG_X86_32),y)
obj-y += atomic64_32.o
diff --git a/arch/x86/lib/hweight.c b/arch/x86/lib/hweight.c
new file mode 100644
index 0000000..54d3cb0
--- /dev/null
+++ b/arch/x86/lib/hweight.c
@@ -0,0 +1,62 @@
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/bitops.h>
+
+#ifdef CONFIG_64BIT
+/* popcnt %rdi, %rax */
+#define POPCNT ".byte 0xf3\n\t.byte 0x48\n\t.byte 0x0f\n\t.byte 0xb8\n\t.byte 0xc7"
+#define REG_IN "D"
+#define REG_OUT "a"
+#else
+/* popcnt %eax, %eax */
+#define POPCNT ".byte 0xf3\n\t.byte 0x0f\n\t.byte 0xb8\n\t.byte 0xc0"
+#define REG_IN "a"
+#define REG_OUT "a"
+#endif
+
+/*
+ * __sw_hweightXX are called from within the alternatives below
+ * and callee-clobbered registers need to be taken care of. See
+ * ARCH_HWEIGHT_CFLAGS in <arch/x86/Kconfig> for the respective
+ * compiler switches.
+ */
+unsigned int __arch_hweight32(unsigned int w)
+{
+ unsigned int res = 0;
+
+ asm (ALTERNATIVE("call __sw_hweight32", POPCNT, X86_FEATURE_POPCNT)
+ : "="REG_OUT (res)
+ : REG_IN (w));
+
+ return res;
+}
+EXPORT_SYMBOL(__arch_hweight32);
+
+unsigned int __arch_hweight16(unsigned int w)
+{
+ return __arch_hweight32(w & 0xffff);
+}
+EXPORT_SYMBOL(__arch_hweight16);
+
+unsigned int __arch_hweight8(unsigned int w)
+{
+ return __arch_hweight32(w & 0xff);
+}
+EXPORT_SYMBOL(__arch_hweight8);
+
+unsigned long __arch_hweight64(__u64 w)
+{
+ unsigned long res = 0;
+
+#ifdef CONFIG_X86_32
+ return __arch_hweight32((u32)w) +
+ __arch_hweight32((u32)(w >> 32));
+#else
+ asm (ALTERNATIVE("call __sw_hweight64", POPCNT, X86_FEATURE_POPCNT)
+ : "="REG_OUT (res)
+ : REG_IN (w));
+#endif /* CONFIG_X86_32 */
+
+ return res;
+}
+EXPORT_SYMBOL(__arch_hweight64);
diff --git a/include/asm-generic/bitops/arch_hweight.h b/include/asm-generic/bitops/arch_hweight.h
index 3a7be84..1c82306 100644
--- a/include/asm-generic/bitops/arch_hweight.h
+++ b/include/asm-generic/bitops/arch_hweight.h
@@ -3,9 +3,23 @@
#include <asm/types.h>
-extern unsigned int __arch_hweight32(unsigned int w);
-extern unsigned int __arch_hweight16(unsigned int w);
-extern unsigned int __arch_hweight8(unsigned int w);
-extern unsigned long __arch_hweight64(__u64 w);
+unsigned int __arch_hweight32(unsigned int w)
+{
+ return __sw_hweight32(w);
+}
+unsigned int __arch_hweight16(unsigned int w)
+{
+ return __sw_hweight16(w);
+}
+
+unsigned int __arch_hweight8(unsigned int w)
+{
+ return __sw_hweight8(w);
+}
+
+unsigned long __arch_hweight64(__u64 w)
+{
+ return __sw_hweight64(w);
+}
#endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */
diff --git a/lib/Makefile b/lib/Makefile
index 3b0b4a6..e2ad17c 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -39,7 +39,10 @@ lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
lib-$(CONFIG_GENERIC_FIND_FIRST_BIT) += find_next_bit.o
lib-$(CONFIG_GENERIC_FIND_NEXT_BIT) += find_next_bit.o
obj-$(CONFIG_GENERIC_FIND_LAST_BIT) += find_last_bit.o
+
+CFLAGS_hweight.o = $(subst $(quote),,$(CONFIG_ARCH_HWEIGHT_CFLAGS))
obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
+
obj-$(CONFIG_LOCK_KERNEL) += kernel_lock.o
obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o
obj-$(CONFIG_DEBUG_LIST) += list_debug.o
diff --git a/lib/hweight.c b/lib/hweight.c
index 9ff86df..f9ce440 100644
--- a/lib/hweight.c
+++ b/lib/hweight.c
@@ -9,7 +9,7 @@
* The Hamming Weight of a number is the total number of bits set in it.
*/
-unsigned int __arch_hweight32(unsigned int w)
+unsigned int __sw_hweight32(unsigned int w)
{
unsigned int res = w - ((w >> 1) & 0x55555555);
res = (res & 0x33333333) + ((res >> 2) & 0x33333333);
@@ -17,30 +17,30 @@ unsigned int __arch_hweight32(unsigned int w)
res = res + (res >> 8);
return (res + (res >> 16)) & 0x000000FF;
}
-EXPORT_SYMBOL(__arch_hweight32);
+EXPORT_SYMBOL(__sw_hweight32);
-unsigned int __arch_hweight16(unsigned int w)
+unsigned int __sw_hweight16(unsigned int w)
{
unsigned int res = w - ((w >> 1) & 0x5555);
res = (res & 0x3333) + ((res >> 2) & 0x3333);
res = (res + (res >> 4)) & 0x0F0F;
return (res + (res >> 8)) & 0x00FF;
}
-EXPORT_SYMBOL(__arch_hweight16);
+EXPORT_SYMBOL(__sw_hweight16);
-unsigned int __arch_hweight8(unsigned int w)
+unsigned int __sw_hweight8(unsigned int w)
{
unsigned int res = w - ((w >> 1) & 0x55);
res = (res & 0x33) + ((res >> 2) & 0x33);
return (res + (res >> 4)) & 0x0F;
}
-EXPORT_SYMBOL(__arch_hweight8);
+EXPORT_SYMBOL(__sw_hweight8);
-unsigned long __arch_hweight64(__u64 w)
+unsigned long __sw_hweight64(__u64 w)
{
#if BITS_PER_LONG == 32
- return __arch_hweight32((unsigned int)(w >> 32)) +
- __arch_hweight32((unsigned int)w);
+ return __sw_hweight32((unsigned int)(w >> 32)) +
+ __sw_hweight32((unsigned int)w);
#elif BITS_PER_LONG == 64
#ifdef ARCH_HAS_FAST_MULTIPLIER
w -= (w >> 1) & 0x5555555555555555ul;
@@ -57,4 +57,4 @@ unsigned long __arch_hweight64(__u64 w)
#endif
#endif
}
-EXPORT_SYMBOL(__arch_hweight64);
+EXPORT_SYMBOL(__sw_hweight64);
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index f9bdf26..cbcd654 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -245,3 +245,7 @@ quiet_cmd_lzo = LZO $@
cmd_lzo = (cat $(filter-out FORCE,$^) | \
lzop -9 && $(call size_append, $(filter-out FORCE,$^))) > $@ || \
(rm -f $@ ; false)
+
+# misc stuff
+# ---------------------------------------------------------------------------
+quote:="
--
1.6.5.4
--
Regards/Gruss,
Boris.
-
Advanced Micro Devices, Inc.
Operating Systems Research Center
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists