x86, cpu: Clean up and unify the NOP selection infrastructure

Clean up and unify the NOP selection infrastructure:

- Make the atomic 5-byte NOP a part of the selection system.
- Pick NOPs once during early boot and then be done with it.

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jason Baron <jbaron@redhat.com>
Link: http://lkml.kernel.org/r/1303166160-10315-3-git-send-email-hpa@linux.intel.com

4 files changed, 106 insertions, 91 deletions

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 4a234677e213..846f61eb89c1 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -67,17 +67,30 @@ __setup("noreplace-paravirt", setup_noreplace_paravirt);
 #define DPRINTK(fmt, args...) if (debug_alternative) \
 	printk(KERN_DEBUG fmt, args)
 
+/*
+ * Each GENERIC_NOPX is of X bytes, and defined as an array of bytes
+ * that correspond to that nop. Getting from one nop to the next, we
+ * add to the array the offset that is equal to the sum of all sizes of
+ * nops preceding the one we are after.
+ *
+ * Note: The GENERIC_NOP5_ATOMIC is at the end, as it breaks the
+ * nice symmetry of sizes of the previous nops.
+ */
 #if defined(GENERIC_NOP1) && !defined(CONFIG_X86_64)
-/* Use inline assembly to define this because the nops are defined
-   as inline assembly strings in the include files and we cannot
-   get them easily into strings. */
-asm("\t" __stringify(__INITRODATA_OR_MODULE) "\nintelnops: "
-	GENERIC_NOP1 GENERIC_NOP2 GENERIC_NOP3 GENERIC_NOP4 GENERIC_NOP5 GENERIC_NOP6
-	GENERIC_NOP7 GENERIC_NOP8
-    "\t.previous");
-extern const unsigned char intelnops[];
-static const unsigned char *const __initconst_or_module
-intel_nops[ASM_NOP_MAX+1] = {
+static const unsigned char intelnops[] =
+{
+	GENERIC_NOP1,
+	GENERIC_NOP2,
+	GENERIC_NOP3,
+	GENERIC_NOP4,
+	GENERIC_NOP5,
+	GENERIC_NOP6,
+	GENERIC_NOP7,
+	GENERIC_NOP8,
+	GENERIC_NOP5_ATOMIC
+};
+static const unsigned char * const intel_nops[ASM_NOP_MAX+2] =
+{
 	NULL,
 	intelnops,
 	intelnops + 1,
@@ -87,17 +100,25 @@ intel_nops[ASM_NOP_MAX+1] = {
 	intelnops + 1 + 2 + 3 + 4 + 5,
 	intelnops + 1 + 2 + 3 + 4 + 5 + 6,
 	intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+	intelnops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
 };
 #endif
 
 #ifdef K8_NOP1
-asm("\t" __stringify(__INITRODATA_OR_MODULE) "\nk8nops: "
-	K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6
-	K8_NOP7 K8_NOP8
-    "\t.previous");
-extern const unsigned char k8nops[];
-static const unsigned char *const __initconst_or_module
-k8_nops[ASM_NOP_MAX+1] = {
+static const unsigned char k8nops[] =
+{
+	K8_NOP1,
+	K8_NOP2,
+	K8_NOP3,
+	K8_NOP4,
+	K8_NOP5,
+	K8_NOP6,
+	K8_NOP7,
+	K8_NOP8,
+	K8_NOP5_ATOMIC
+};
+static const unsigned char * const k8_nops[ASM_NOP_MAX+2] =
+{
 	NULL,
 	k8nops,
 	k8nops + 1,
@@ -107,17 +128,25 @@ k8_nops[ASM_NOP_MAX+1] = {
 	k8nops + 1 + 2 + 3 + 4 + 5,
 	k8nops + 1 + 2 + 3 + 4 + 5 + 6,
 	k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+	k8nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
 };
 #endif
 
 #if defined(K7_NOP1) && !defined(CONFIG_X86_64)
-asm("\t" __stringify(__INITRODATA_OR_MODULE) "\nk7nops: "
-	K7_NOP1 K7_NOP2 K7_NOP3 K7_NOP4 K7_NOP5 K7_NOP6
-	K7_NOP7 K7_NOP8
-    "\t.previous");
-extern const unsigned char k7nops[];
-static const unsigned char *const __initconst_or_module
-k7_nops[ASM_NOP_MAX+1] = {
+static const unsigned char k7nops[] =
+{
+	K7_NOP1,
+	K7_NOP2,
+	K7_NOP3,
+	K7_NOP4,
+	K7_NOP5,
+	K7_NOP6,
+	K7_NOP7,
+	K7_NOP8,
+	K7_NOP5_ATOMIC
+};
+static const unsigned char * const k7_nops[ASM_NOP_MAX+2] =
+{
 	NULL,
 	k7nops,
 	k7nops + 1,
@@ -127,17 +156,25 @@ k7_nops[ASM_NOP_MAX+1] = {
 	k7nops + 1 + 2 + 3 + 4 + 5,
 	k7nops + 1 + 2 + 3 + 4 + 5 + 6,
 	k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+	k7nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
 };
 #endif
 
 #ifdef P6_NOP1
-asm("\t" __stringify(__INITRODATA_OR_MODULE) "\np6nops: "
-	P6_NOP1 P6_NOP2 P6_NOP3 P6_NOP4 P6_NOP5 P6_NOP6
-	P6_NOP7 P6_NOP8
-    "\t.previous");
-extern const unsigned char p6nops[];
-static const unsigned char *const __initconst_or_module
-p6_nops[ASM_NOP_MAX+1] = {
+static const unsigned char  __initconst_or_module p6nops[] =
+{
+	P6_NOP1,
+	P6_NOP2,
+	P6_NOP3,
+	P6_NOP4,
+	P6_NOP5,
+	P6_NOP6,
+	P6_NOP7,
+	P6_NOP8,
+	P6_NOP5_ATOMIC
+};
+static const unsigned char * const p6_nops[ASM_NOP_MAX+2] =
+{
 	NULL,
 	p6nops,
 	p6nops + 1,
@@ -147,47 +184,53 @@ p6_nops[ASM_NOP_MAX+1] = {
 	p6nops + 1 + 2 + 3 + 4 + 5,
 	p6nops + 1 + 2 + 3 + 4 + 5 + 6,
 	p6nops + 1 + 2 + 3 + 4 + 5 + 6 + 7,
+	p6nops + 1 + 2 + 3 + 4 + 5 + 6 + 7 + 8,
 };
 #endif
 
+/* Initialize these to a safe default */
 #ifdef CONFIG_X86_64
+const unsigned char * const *ideal_nops = p6_nops;
+#else
+const unsigned char * const *ideal_nops = intel_nops;
+#endif
 
-extern char __vsyscall_0;
-static const unsigned char *const *__init_or_module find_nop_table(void)
+void __init arch_init_ideal_nops(void)
 {
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
-	    boot_cpu_has(X86_FEATURE_NOPL))
-		return p6_nops;
-	else
-		return k8_nops;
-}
-
-#else /* CONFIG_X86_64 */
+	switch (boot_cpu_data.x86_vendor) {
+	case X86_VENDOR_INTEL:
+		if (boot_cpu_has(X86_FEATURE_NOPL)) {
+			   ideal_nops = p6_nops;
+		} else {
+#ifdef CONFIG_X86_64
+			ideal_nops = k8_nops;
+#else
+			ideal_nops = intel_nops;
+#endif
+		}
 
-static const unsigned char *const *__init_or_module find_nop_table(void)
-{
-	if (boot_cpu_has(X86_FEATURE_K8))
-		return k8_nops;
-	else if (boot_cpu_has(X86_FEATURE_K7))
-		return k7_nops;
-	else if (boot_cpu_has(X86_FEATURE_NOPL))
-		return p6_nops;
-	else
-		return intel_nops;
+	default:
+#ifdef CONFIG_X86_64
+		ideal_nops = k8_nops;
+#else
+		if (boot_cpu_has(X86_FEATURE_K8))
+			ideal_nops = k8_nops;
+		else if (boot_cpu_has(X86_FEATURE_K7))
+			ideal_nops = k7_nops;
+		else
+			ideal_nops = intel_nops;
+#endif
+	}
 }
 
-#endif /* CONFIG_X86_64 */
-
 /* Use this to add nops to a buffer, then text_poke the whole buffer. */
 static void __init_or_module add_nops(void *insns, unsigned int len)
 {
-	const unsigned char *const *noptable = find_nop_table();
-
 	while (len > 0) {
 		unsigned int noplen = len;
 		if (noplen > ASM_NOP_MAX)
 			noplen = ASM_NOP_MAX;
-		memcpy(insns, noptable[noplen], noplen);
+		memcpy(insns, ideal_nops[noplen], noplen);
 		insns += noplen;
 		len -= noplen;
 	}
@@ -195,6 +238,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len)
 
 extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
 extern s32 __smp_locks[], __smp_locks_end[];
+extern char __vsyscall_0;
 void *text_poke_early(void *addr, const void *opcode, size_t len);
 
 /* Replace instructions with better alternatives for this CPU type.
@@ -678,29 +722,3 @@ void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n)
 	wrote_text = 0;
 	__stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
 }
-
-#if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
-
-#ifdef CONFIG_X86_64
-unsigned char ideal_nop5[5] = { 0x66, 0x66, 0x66, 0x66, 0x90 };
-#else
-unsigned char ideal_nop5[5] = { 0x3e, 0x8d, 0x74, 0x26, 0x00 };
-#endif
-
-void __init arch_init_ideal_nop5(void)
-{
-	/*
-	 * There is no good nop for all x86 archs.  This selection
-	 * algorithm should be unified with the one in find_nop_table(),
-	 * but this should be good enough for now.
-	 *
-	 * For cases other than the ones below, use the safe (as in
-	 * always functional) defaults above.
-	 */
-#ifdef CONFIG_X86_64
-	/* Don't use these on 32 bits due to broken virtualizers */
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
-		memcpy(ideal_nop5, p6_nops[5], 5);
-#endif
-}
-#endif
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index a93742a57468..0ba15a6cc57e 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -260,9 +260,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code)
 	return mod_code_status;
 }
 
-static unsigned char *ftrace_nop_replace(void)
+static const unsigned char *ftrace_nop_replace(void)
 {
-	return ideal_nop5;
+	return ideal_nops[NOP_ATOMIC5];
 }
 
 static int
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index 961b6b30ba90..3fee346ef545 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -34,7 +34,7 @@ void arch_jump_label_transform(struct jump_entry *entry,
 		code.offset = entry->target -
 				(entry->code + JUMP_LABEL_NOP_SIZE);
 	} else
-		memcpy(&code, ideal_nop5, JUMP_LABEL_NOP_SIZE);
+		memcpy(&code, ideal_nops[NOP_ATOMIC5], JUMP_LABEL_NOP_SIZE);
 	get_online_cpus();
 	mutex_lock(&text_mutex);
 	text_poke_smp((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE);
@@ -44,7 +44,8 @@ void arch_jump_label_transform(struct jump_entry *entry,
 
 void arch_jump_label_text_poke_early(jump_label_t addr)
 {
-	text_poke_early((void *)addr, ideal_nop5, JUMP_LABEL_NOP_SIZE);
+	text_poke_early((void *)addr, ideal_nops[NOP_ATOMIC5],
+			JUMP_LABEL_NOP_SIZE);
 }
 
 #endif
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 5a0484a95ad6..390a663894d8 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -691,8 +691,6 @@ early_param("reservelow", parse_reservelow);
 
 void __init setup_arch(char **cmdline_p)
 {
-	unsigned long flags;
-
 #ifdef CONFIG_X86_32
 	memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
 	visws_early_detect();
@@ -1036,9 +1034,7 @@ void __init setup_arch(char **cmdline_p)
 
 	mcheck_init();
 
-	local_irq_save(flags);
-	arch_init_ideal_nop5();
-	local_irq_restore(flags);
+	arch_init_ideal_nops();
 }
 
 #ifdef CONFIG_X86_32