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(-)

3 files changed, 66 insertions, 1 deletions

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 8cb5dbb..a3ae8e6 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -116,12 +116,31 @@ static const unsigned char *const k7_nops[ASM_NOP_MAX+1] = {
 };
 #endif
 
+#ifdef P6_NOP1
+asm("\t.section .rodata, \"a\"\np6nops: "
+	P6_NOP1 P6_NOP2 P6_NOP3 P6_NOP4 P6_NOP5 P6_NOP6
+	P6_NOP7 P6_NOP8);
+extern const unsigned char p6nops[];
+static const unsigned char *const p6_nops[ASM_NOP_MAX+1] = {
+	NULL,
+	p6nops,
+	p6nops + 1,
+	p6nops + 1 + 2,
+	p6nops + 1 + 2 + 3,
+	p6nops + 1 + 2 + 3 + 4,
+	p6nops + 1 + 2 + 3 + 4 + 5,
+	p6nops + 1 + 2 + 3 + 4 + 5 + 6,
+	p6nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+};
+#endif
+
 #ifdef CONFIG_X86_64
 
 extern char __vsyscall_0;
 static inline const unsigned char*const * find_nop_table(void)
 {
-	return k8_nops;
+	return boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
+	       boot_cpu_data.x86 < 6 ? k8_nops : p6_nops;
 }
 
 #else /* CONFIG_X86_64 */
@@ -132,6 +151,8 @@ static const struct nop {
 } noptypes[] = {
 	{ X86_FEATURE_K8, k8_nops },
 	{ X86_FEATURE_K7, k7_nops },
+	{ X86_FEATURE_P4, p6_nops },
+	{ X86_FEATURE_P3, p6_nops },
 	{ -1, NULL }
 };
 
diff --git a/include/asm-x86/processor_32.h b/include/asm-x86/processor_32.h
index 38cc106..83800e7 100644
--- a/include/asm-x86/processor_32.h
+++ b/include/asm-x86/processor_32.h
@@ -677,6 +677,17 @@ static inline unsigned int cpuid_edx(unsigned int op)
 #define K7_NOP7        ".byte 0x8D,0x04,0x05,0,0,0,0\n"
 #define K7_NOP8        K7_NOP7 ASM_NOP1
 
+/* P6 nops */
+/* uses eax dependencies (Intel-recommended choice) */
+#define P6_NOP1	GENERIC_NOP1
+#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"
+
 #ifdef CONFIG_MK8
 #define ASM_NOP1 K8_NOP1
 #define ASM_NOP2 K8_NOP2
@@ -695,6 +706,17 @@ static inline unsigned int cpuid_edx(unsigned int op)
 #define ASM_NOP6 K7_NOP6
 #define ASM_NOP7 K7_NOP7
 #define ASM_NOP8 K7_NOP8
+#elif defined(CONFIG_M686) || defined(CONFIG_MPENTIUMII) || \
+      defined(CONFIG_MPENTIUMIII) || defined(CONFIG_MPENTIUMM) || \
+      defined(CONFIG_MCORE2) || defined(CONFIG_PENTIUM4)
+#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 GENERIC_NOP1
 #define ASM_NOP2 GENERIC_NOP2
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 @@ struct extended_sigtable {
 };
 
 
+#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 @@ struct extended_sigtable {
 #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 @@ struct extended_sigtable {
 #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. */