jump label: Make dynamic no-op selection available outside of ftrace

Move Steve's code for finding the best 5-byte no-op from ftrace.c to
alternative.c. The idea is that other consumers (in this case jump label)
want to make use of that code.

Signed-off-by: Jason Baron <jbaron@redhat.com>
LKML-Reference: <96259ae74172dcac99c0020c249743c523a92e18.1284733808.git.jbaron@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

3 files changed, 71 insertions, 62 deletions

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index f65ab8b014c4..1849d8036ee8 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -641,3 +641,67 @@ void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len)
         return addr;
 }
 
+#if defined(CONFIG_DYNAMIC_FTRACE)
+
+unsigned char ideal_nop5[IDEAL_NOP_SIZE_5];
+
+void __init arch_init_ideal_nop5(void)
+{
+        extern const unsigned char ftrace_test_p6nop[];
+        extern const unsigned char ftrace_test_nop5[];
+        extern const unsigned char ftrace_test_jmp[];
+        int faulted = 0;
+
+        /*
+         * There is no good nop for all x86 archs.
+         * We will default to using the P6_NOP5, but first we
+         * will test to make sure that the nop will actually
+         * work on this CPU. If it faults, we will then
+         * go to a lesser efficient 5 byte nop. If that fails
+         * we then just use a jmp as our nop. This isn't the most
+         * efficient nop, but we can not use a multi part nop
+         * since we would then risk being preempted in the middle
+         * of that nop, and if we enabled tracing then, it might
+         * cause a system crash.
+         *
+         * TODO: check the cpuid to determine the best nop.
+         */
+        asm volatile (
+                "ftrace_test_jmp:"
+                "jmp ftrace_test_p6nop\n"
+                "nop\n"
+                "nop\n"
+                "nop\n"  /* 2 byte jmp + 3 bytes */
+                "ftrace_test_p6nop:"
+                P6_NOP5
+                "jmp 1f\n"
+                "ftrace_test_nop5:"
+                ".byte 0x66,0x66,0x66,0x66,0x90\n"
+                "1:"
+                ".section .fixup, \"ax\"\n"
+                "2:     movl $1, %0\n"
+                "       jmp ftrace_test_nop5\n"
+                "3:     movl $2, %0\n"
+                "       jmp 1b\n"
+                ".previous\n"
+                _ASM_EXTABLE(ftrace_test_p6nop, 2b)
+                _ASM_EXTABLE(ftrace_test_nop5, 3b)
+                : "=r"(faulted) : "0" (faulted));
+
+        switch (faulted) {
+        case 0:
+                pr_info("converting mcount calls to 0f 1f 44 00 00\n");
+                memcpy(ideal_nop5, ftrace_test_p6nop, IDEAL_NOP_SIZE_5);
+                break;
+        case 1:
+                pr_info("converting mcount calls to 66 66 66 66 90\n");
+                memcpy(ideal_nop5, ftrace_test_nop5, IDEAL_NOP_SIZE_5);
+                break;
+        case 2:
+                pr_info("converting mcount calls to jmp . + 5\n");
+                memcpy(ideal_nop5, ftrace_test_jmp, IDEAL_NOP_SIZE_5);
+                break;
+        }
+
+}
+#endif
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index cd37469b54ee..3afb33f14d2d 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -257,14 +257,9 @@ do_ftrace_mod_code(unsigned long ip, void *new_code)
         return mod_code_status;
 }
 
-
-
-
-static unsigned char ftrace_nop[MCOUNT_INSN_SIZE];
-
 static unsigned char *ftrace_nop_replace(void)
 {
-        return ftrace_nop;
+        return ideal_nop5;
 }
 
 static int
@@ -338,62 +333,6 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 
 int __init ftrace_dyn_arch_init(void *data)
 {
-        extern const unsigned char ftrace_test_p6nop[];
-        extern const unsigned char ftrace_test_nop5[];
-        extern const unsigned char ftrace_test_jmp[];
-        int faulted = 0;
-
-        /*
-         * There is no good nop for all x86 archs.
-         * We will default to using the P6_NOP5, but first we
-         * will test to make sure that the nop will actually
-         * work on this CPU. If it faults, we will then
-         * go to a lesser efficient 5 byte nop. If that fails
-         * we then just use a jmp as our nop. This isn't the most
-         * efficient nop, but we can not use a multi part nop
-         * since we would then risk being preempted in the middle
-         * of that nop, and if we enabled tracing then, it might
-         * cause a system crash.
-         *
-         * TODO: check the cpuid to determine the best nop.
-         */
-        asm volatile (
-                "ftrace_test_jmp:"
-                "jmp ftrace_test_p6nop\n"
-                "nop\n"
-                "nop\n"
-                "nop\n"  /* 2 byte jmp + 3 bytes */
-                "ftrace_test_p6nop:"
-                P6_NOP5
-                "jmp 1f\n"
-                "ftrace_test_nop5:"
-                ".byte 0x66,0x66,0x66,0x66,0x90\n"
-                "1:"
-                ".section .fixup, \"ax\"\n"
-                "2:     movl $1, %0\n"
-                "       jmp ftrace_test_nop5\n"
-                "3:     movl $2, %0\n"
-                "       jmp 1b\n"
-                ".previous\n"
-                _ASM_EXTABLE(ftrace_test_p6nop, 2b)
-                _ASM_EXTABLE(ftrace_test_nop5, 3b)
-                : "=r"(faulted) : "0" (faulted));
-
-        switch (faulted) {
-        case 0:
-                pr_info("converting mcount calls to 0f 1f 44 00 00\n");
-                memcpy(ftrace_nop, ftrace_test_p6nop, MCOUNT_INSN_SIZE);
-                break;
-        case 1:
-                pr_info("converting mcount calls to 66 66 66 66 90\n");
-                memcpy(ftrace_nop, ftrace_test_nop5, MCOUNT_INSN_SIZE);
-                break;
-        case 2:
-                pr_info("converting mcount calls to jmp . + 5\n");
-                memcpy(ftrace_nop, ftrace_test_jmp, MCOUNT_INSN_SIZE);
-                break;
-        }
-
         /* The return code is retured via data */
         *(unsigned long *)data = 0;
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index c3a4fbb2b996..00e167870f71 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -112,6 +112,7 @@
 #include <asm/numa_64.h>
 #endif
 #include <asm/mce.h>
+#include <asm/alternative.h>
 
 /*
  * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
@@ -726,6 +727,7 @@ void __init setup_arch(char **cmdline_p)
 {
         int acpi = 0;
         int k8 = 0;
+        unsigned long flags;
 
 #ifdef CONFIG_X86_32
         memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
@@ -1071,6 +1073,10 @@ void __init setup_arch(char **cmdline_p)
         x86_init.oem.banner();
 
         mcheck_init();
+
+        local_irq_save(flags);
+        arch_init_ideal_nop5();
+        local_irq_restore(flags);
 }
 
 #ifdef CONFIG_X86_32