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: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:	Thu, 15 Dec 2011 01:55:59 -0800
From:	tip-bot for Jan Beulich <JBeulich@...e.com>
To:	linux-tip-commits@...r.kernel.org
Cc:	linux-kernel@...r.kernel.org, hpa@...or.com, mingo@...hat.com,
	a.p.zijlstra@...llo.nl, torvalds@...ux-foundation.org,
	jbeulich@...e.com, cl@...ux.com, dhowells@...hat.com,
	akpm@...ux-foundation.org, JBeulich@...e.com, tglx@...utronix.de,
	mingo@...e.hu
Subject: [tip:x86/asm] x86: Fix and improve percpu_cmpxchg{8,16}b_double()

Commit-ID:  cebef5beed3de3037de85a521495897256b2c5da
Gitweb:     http://git.kernel.org/tip/cebef5beed3de3037de85a521495897256b2c5da
Author:     Jan Beulich <JBeulich@...e.com>
AuthorDate: Wed, 14 Dec 2011 08:33:25 +0000
Committer:  Ingo Molnar <mingo@...e.hu>
CommitDate: Thu, 15 Dec 2011 08:17:14 +0100

x86: Fix and improve percpu_cmpxchg{8,16}b_double()

They had several problems/shortcomings:

Only the first memory operand was mentioned in the 2x32bit asm()
operands, and 2x64-bit version had a memory clobber. The first
allowed the compiler to not recognize the need to re-load the
data in case it had it cached in some register, and the second
was overly destructive.

The memory operand in the 2x32-bit asm() was declared to only be
an output.

The types of the local copies of the old and new values were
incorrect (as in other per-CPU ops, the types of the per-CPU
variables accessed should be used here, to make sure the
respective types are compatible).

The __dummy variable was pointless (and needlessly initialized
in the 2x32-bit case), given that local copies of the inputs
already exist.

The 2x64-bit variant forced the address of the first object into
%rsi, even though this is needed only for the call to the
emulation function. The real cmpxchg16b can operate on an
memory.

At once also change the return value type to what it really is -
'bool'.

Signed-off-by: Jan Beulich <jbeulich@...e.com>
Cc: Linus Torvalds <torvalds@...ux-foundation.org>
Cc: Andrew Morton <akpm@...ux-foundation.org>
Cc: David Howells <dhowells@...hat.com>
Cc: Christoph Lameter <cl@...ux.com>
Cc: Peter Zijlstra <a.p.zijlstra@...llo.nl>
Link: http://lkml.kernel.org/r/4EE86D6502000078000679FE@nat28.tlf.novell.com
Signed-off-by: Ingo Molnar <mingo@...e.hu>
---
 arch/x86/include/asm/percpu.h |   53 ++++++++++++++++------------------------
 1 files changed, 21 insertions(+), 32 deletions(-)

diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 3470c9d..529bf07e 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -451,23 +451,20 @@ do {									\
 #endif /* !CONFIG_M386 */
 
 #ifdef CONFIG_X86_CMPXCHG64
-#define percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2)			\
+#define percpu_cmpxchg8b_double(pcp1, pcp2, o1, o2, n1, n2)		\
 ({									\
-	char __ret;							\
-	typeof(o1) __o1 = o1;						\
-	typeof(o1) __n1 = n1;						\
-	typeof(o2) __o2 = o2;						\
-	typeof(o2) __n2 = n2;						\
-	typeof(o2) __dummy = n2;					\
+	bool __ret;							\
+	typeof(pcp1) __o1 = (o1), __n1 = (n1);				\
+	typeof(pcp2) __o2 = (o2), __n2 = (n2);				\
 	asm volatile("cmpxchg8b "__percpu_arg(1)"\n\tsetz %0\n\t"	\
-		    : "=a"(__ret), "=m" (pcp1), "=d"(__dummy)		\
-		    :  "b"(__n1), "c"(__n2), "a"(__o1), "d"(__o2));	\
+		    : "=a" (__ret), "+m" (pcp1), "+m" (pcp2), "+d" (__o2) \
+		    :  "b" (__n1), "c" (__n2), "a" (__o1));		\
 	__ret;								\
 })
 
-#define __this_cpu_cmpxchg_double_4(pcp1, pcp2, o1, o2, n1, n2)		percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2)
-#define this_cpu_cmpxchg_double_4(pcp1, pcp2, o1, o2, n1, n2)		percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2)
-#define irqsafe_cpu_cmpxchg_double_4(pcp1, pcp2, o1, o2, n1, n2)	percpu_cmpxchg8b_double(pcp1, o1, o2, n1, n2)
+#define __this_cpu_cmpxchg_double_4	percpu_cmpxchg8b_double
+#define this_cpu_cmpxchg_double_4	percpu_cmpxchg8b_double
+#define irqsafe_cpu_cmpxchg_double_4	percpu_cmpxchg8b_double
 #endif /* CONFIG_X86_CMPXCHG64 */
 
 /*
@@ -508,31 +505,23 @@ do {									\
  * it in software.  The address used in the cmpxchg16 instruction must be
  * aligned to a 16 byte boundary.
  */
-#ifdef CONFIG_SMP
-#define CMPXCHG16B_EMU_CALL "call this_cpu_cmpxchg16b_emu\n\t" ASM_NOP3
-#else
-#define CMPXCHG16B_EMU_CALL "call this_cpu_cmpxchg16b_emu\n\t" ASM_NOP2
-#endif
-#define percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2)			\
+#define percpu_cmpxchg16b_double(pcp1, pcp2, o1, o2, n1, n2)		\
 ({									\
-	char __ret;							\
-	typeof(o1) __o1 = o1;						\
-	typeof(o1) __n1 = n1;						\
-	typeof(o2) __o2 = o2;						\
-	typeof(o2) __n2 = n2;						\
-	typeof(o2) __dummy;						\
-	alternative_io(CMPXCHG16B_EMU_CALL,				\
-		       "cmpxchg16b " __percpu_prefix "(%%rsi)\n\tsetz %0\n\t",	\
+	bool __ret;							\
+	typeof(pcp1) __o1 = (o1), __n1 = (n1);				\
+	typeof(pcp2) __o2 = (o2), __n2 = (n2);				\
+	alternative_io("leaq %P1,%%rsi\n\tcall this_cpu_cmpxchg16b_emu\n\t", \
+		       "cmpxchg16b " __percpu_arg(1) "\n\tsetz %0\n\t",	\
 		       X86_FEATURE_CX16,				\
-		       ASM_OUTPUT2("=a"(__ret), "=d"(__dummy)),		\
-		       "S" (&pcp1), "b"(__n1), "c"(__n2),		\
-		       "a"(__o1), "d"(__o2) : "memory");		\
+		       ASM_OUTPUT2("=a" (__ret), "+m" (pcp1),		\
+				   "+m" (pcp2), "+d" (__o2)),		\
+		       "b" (__n1), "c" (__n2), "a" (__o1) : "rsi");	\
 	__ret;								\
 })
 
-#define __this_cpu_cmpxchg_double_8(pcp1, pcp2, o1, o2, n1, n2)		percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2)
-#define this_cpu_cmpxchg_double_8(pcp1, pcp2, o1, o2, n1, n2)		percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2)
-#define irqsafe_cpu_cmpxchg_double_8(pcp1, pcp2, o1, o2, n1, n2)	percpu_cmpxchg16b_double(pcp1, o1, o2, n1, n2)
+#define __this_cpu_cmpxchg_double_8	percpu_cmpxchg16b_double
+#define this_cpu_cmpxchg_double_8	percpu_cmpxchg16b_double
+#define irqsafe_cpu_cmpxchg_double_8	percpu_cmpxchg16b_double
 
 #endif
 
--
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

Powered by Openwall GNU/*/Linux Powered by OpenVZ