i386: work around miscompilation of alternatives code

A recent change makes my Dell 1501 hang on boot.  It's an AMD MK-36.  I use
an x86_64 kernel.  It is 100% reproducible.

I debugged this problem a bit and my compiler[1]interprets the =A constraint
as %rax instead of %edx:%eax on x86_64 which causes the problem.  The appended
patch provides a workaround for this and fixed the hang on my machine.

[1] gcc version 4.1.3 20070429 (prerelease) (Debian 4.1.2-5)

Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Cc: Andi Kleen <ak@suse.de>
Cc: Benny Halevy <bhalevy@panasas.com>
Cc: Pete Zaitcev <zaitcev@redhat.com>
Cc: "Joerg Roedel" <joerg.roedel@amd.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/asm-i386/alternative.h b/include/asm-i386/alternative.h
index 0f70b37..eb7da54 100644 (file)
--- a/include/asm-i386/alternative.h
+++ b/include/asm-i386/alternative.h
@@ -98,6 +98,12 @@ static inline void alternatives_smp_switch(int smp) {}
                      ".previous" : output : [feat] "i" (feature), ##input)
 
 /*
+ * use this macro(s) if you need more than one output parameter
+ * in alternative_io
+ */
+#define ASM_OUTPUT2(a, b) a, b
+
+/*
  * Alternative inline assembly for SMP.
  *
  * The LOCK_PREFIX macro defined here replaces the LOCK and

diff --git a/include/asm-i386/tsc.h b/include/asm-i386/tsc.h
index 3f3c1fa..62c091f 100644 (file)
--- a/include/asm-i386/tsc.h
+++ b/include/asm-i386/tsc.h
@@ -35,14 +35,16 @@ static inline cycles_t get_cycles(void)
 static __always_inline cycles_t get_cycles_sync(void)
 {
        unsigned long long ret;
-       unsigned eax;
+       unsigned eax, edx;
 
        /*
         * Use RDTSCP if possible; it is guaranteed to be synchronous
         * and doesn't cause a VMEXIT on Hypervisors
         */
        alternative_io(ASM_NOP3, ".byte 0x0f,0x01,0xf9", X86_FEATURE_RDTSCP,
-                                "=A" (ret), "0" (0ULL) : "ecx", "memory");
+                      ASM_OUTPUT2("=a" (eax), "=d" (edx)),
+                      "a" (0U), "d" (0U) : "ecx", "memory");
+       ret = (((unsigned long long)edx) << 32) | ((unsigned long long)eax);
        if (ret)
                return ret;
 

diff --git a/include/asm-x86_64/alternative.h b/include/asm-x86_64/alternative.h
index a09fe85..a094276 100644 (file)
--- a/include/asm-x86_64/alternative.h
+++ b/include/asm-x86_64/alternative.h
@@ -103,6 +103,12 @@ static inline void alternatives_smp_switch(int smp) {}
                      ".previous" : output : [feat] "i" (feature), ##input)
 
 /*
+ * use this macro(s) if you need more than one output parameter
+ * in alternative_io
+ */
+#define ASM_OUTPUT2(a, b) a, b
+
+/*
  * Alternative inline assembly for SMP.
  *
  * The LOCK_PREFIX macro defined here replaces the LOCK and