linux-kernel - [PATCH 2/3] x86/hweight: Force inlining of __arch

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

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1438697716-28121-2-git-send-email-dvlasenk@redhat.com>
Date:	Tue,  4 Aug 2015 16:15:15 +0200
From:	Denys Vlasenko <dvlasenk@...hat.com>
To:	Ingo Molnar <mingo@...nel.org>
Cc:	Denys Vlasenko <dvlasenk@...hat.com>, Thomas Graf <tgraf@...g.ch>,
	Peter Zijlstra <peterz@...radead.org>,
	David Rientjes <rientjes@...gle.com>,
	Andrew Morton <akpm@...ux-foundation.org>,
	linux-kernel@...r.kernel.org
Subject: [PATCH 2/3] x86/hweight: Force inlining of __arch_hweight{32,64}()

With this config:
http://busybox.net/~vda/kernel_config_OPTIMIZE_INLINING_and_Os

gcc-4.7.2 generates many copies of these tiny functions:

__arch_hweight32 (35 copies):
55                      push   %rbp
e8 66 9b 4a 00          callq  __sw_hweight32
48 89 e5                mov    %rsp,%rbp
5d                      pop    %rbp
c3                      retq

__arch_hweight64 (8 copies):
55                      push   %rbp
e8 5e c2 8a 00          callq  __sw_hweight64
48 89 e5                mov    %rsp,%rbp
5d                      pop    %rbp
c3                      retq

See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122

This patch fixes this via s/inline/__always_inline/

To avoid touching 32-bit case where such change was not tested to be a win,
reformat __arch_hweight64() to have completely disjoint 64-bit and 32-bit
implementations. IOW: made #ifdef / #else / #endif blocks contain
complete function definitions for 32 bits and 64 bits
instead of having #ifdef / #else / #endif inside a single function body.
Only 64-bit __arch_hweight64() is __always_inline'd.

    text     data      bss       dec     hex filename
86971120 17195912 36659200 140826232 864d678 vmlinux.before
86970954 17195912 36659200 140826066 864d5d2 vmlinux

Signed-off-by: Denys Vlasenko <dvlasenk@...hat.com>
Cc: Ingo Molnar <mingo@...nel.org>
Cc: Thomas Graf <tgraf@...g.ch>
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: David Rientjes <rientjes@...gle.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>
Cc: linux-kernel@...r.kernel.org
---
 arch/x86/include/asm/arch_hweight.h | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h
index 9686c3d..259a7c1 100644
--- a/arch/x86/include/asm/arch_hweight.h
+++ b/arch/x86/include/asm/arch_hweight.h
@@ -21,7 +21,7 @@
  * ARCH_HWEIGHT_CFLAGS in <arch/x86/Kconfig> for the respective
  * compiler switches.
  */
-static inline unsigned int __arch_hweight32(unsigned int w)
+static __always_inline unsigned int __arch_hweight32(unsigned int w)
 {
 	unsigned int res = 0;
 
@@ -42,20 +42,23 @@ static inline unsigned int __arch_hweight8(unsigned int w)
 	return __arch_hweight32(w & 0xff);
 }
 
+#ifdef CONFIG_X86_32
 static inline 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
+static __always_inline unsigned long __arch_hweight64(__u64 w)
+{
+	unsigned long res = 0;
+
 	asm (ALTERNATIVE("call __sw_hweight64", POPCNT64, X86_FEATURE_POPCNT)
 		     : "="REG_OUT (res)
 		     : REG_IN (w));
-#endif /* CONFIG_X86_32 */
 
 	return res;
 }
+#endif /* CONFIG_X86_32 */
 
 #endif
-- 
1.8.1.4

--
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/