x86: multi-byte single instruction NOPs

Add support for and use the multi-byte NOPs recently documented to be
available on all PentiumPro and later processors.

This patch only applies cleanly on top of the "x86: misc.
constifications" patch sent earlier.

[ tglx: arch/x86 adaptation ]

Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

 arch/x86/kernel/alternative.c  |   23 ++++++++++++++++++++++-
 include/asm-x86/processor_32.h |   22 ++++++++++++++++++++++
 include/asm-x86/processor_64.h |   22 ++++++++++++++++++++++
 3 files changed, 66 insertions(+), 1 deletion(-)
diff --git a/include/asm-x86/processor_64.h b/include/asm-x86/processor_64.h
index 2f12eb6..f422bec 100644
--- a/include/asm-x86/processor_64.h
+++ b/include/asm-x86/processor_64.h
@@ -334,6 +334,16 @@
 };
 
 
+#if defined(CONFIG_MPSC) || defined(CONFIG_MCORE2)
+#define ASM_NOP1 P6_NOP1
+#define ASM_NOP2 P6_NOP2
+#define ASM_NOP3 P6_NOP3
+#define ASM_NOP4 P6_NOP4
+#define ASM_NOP5 P6_NOP5
+#define ASM_NOP6 P6_NOP6
+#define ASM_NOP7 P6_NOP7
+#define ASM_NOP8 P6_NOP8
+#else
 #define ASM_NOP1 K8_NOP1
 #define ASM_NOP2 K8_NOP2
 #define ASM_NOP3 K8_NOP3
@@ -342,6 +352,7 @@
 #define ASM_NOP6 K8_NOP6
 #define ASM_NOP7 K8_NOP7
 #define ASM_NOP8 K8_NOP8
+#endif
 
 /* Opteron nops */
 #define K8_NOP1 ".byte 0x90\n"
@@ -353,6 +364,17 @@
 #define K8_NOP7	K8_NOP4 K8_NOP3
 #define K8_NOP8	K8_NOP4 K8_NOP4
 
+/* P6 nops */
+/* uses eax dependencies (Intel-recommended choice) */
+#define P6_NOP1	".byte 0x90\n"
+#define P6_NOP2	".byte 0x66,0x90\n"
+#define P6_NOP3	".byte 0x0f,0x1f,0x00\n"
+#define P6_NOP4	".byte 0x0f,0x1f,0x40,0\n"
+#define P6_NOP5	".byte 0x0f,0x1f,0x44,0x00,0\n"
+#define P6_NOP6	".byte 0x66,0x0f,0x1f,0x44,0x00,0\n"
+#define P6_NOP7	".byte 0x0f,0x1f,0x80,0,0,0,0\n"
+#define P6_NOP8	".byte 0x0f,0x1f,0x84,0x00,0,0,0,0\n"
+
 #define ASM_NOP_MAX 8
 
 /* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */