7 files changed, 154 insertions, 3 deletions

diff --git a/arch/arm/include/asm/ftrace.h b/arch/arm/include/asm/ftrace.h
index 39c8bc1a006a..d4c24a7a9280 100644
--- a/arch/arm/include/asm/ftrace.h
+++ b/arch/arm/include/asm/ftrace.h
@@ -1,6 +1,11 @@
 #ifndef _ASM_ARM_FTRACE
 #define _ASM_ARM_FTRACE
 
+#ifndef __ASSEMBLY__
+#define ftrace_nmi_enter()      do { } while (0)
+#define ftrace_nmi_exit()       do { } while (0)
+#endif
+
 #ifdef CONFIG_FUNCTION_TRACER
 #define MCOUNT_ADDR             ((long)(mcount))
 #define MCOUNT_INSN_SIZE        4 /* sizeof mcount call */
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index b298f7a631e6..7652755dc000 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -1,6 +1,11 @@
 #ifndef _ASM_POWERPC_FTRACE
 #define _ASM_POWERPC_FTRACE
 
+#ifndef __ASSEMBLY__
+#define ftrace_nmi_enter()      do { } while (0)
+#define ftrace_nmi_exit()       do { } while (0)
+#endif
+
 #ifdef CONFIG_FUNCTION_TRACER
 #define MCOUNT_ADDR             ((long)(_mcount))
 #define MCOUNT_INSN_SIZE        4 /* sizeof mcount call */
diff --git a/arch/sh/include/asm/ftrace.h b/arch/sh/include/asm/ftrace.h
index 3aed362c9463..cdf2cb0b9ffe 100644
--- a/arch/sh/include/asm/ftrace.h
+++ b/arch/sh/include/asm/ftrace.h
@@ -2,6 +2,11 @@
 #define __ASM_SH_FTRACE_H
 
 #ifndef __ASSEMBLY__
+#define ftrace_nmi_enter()      do { } while (0)
+#define ftrace_nmi_exit()       do { } while (0)
+#endif
+
+#ifndef __ASSEMBLY__
 extern void mcount(void);
 #endif
 
diff --git a/arch/sparc/include/asm/ftrace.h b/arch/sparc/include/asm/ftrace.h
index d27716cd38c1..33a95feeb137 100644
--- a/arch/sparc/include/asm/ftrace.h
+++ b/arch/sparc/include/asm/ftrace.h
@@ -1,6 +1,11 @@
 #ifndef _ASM_SPARC64_FTRACE
 #define _ASM_SPARC64_FTRACE
 
+#ifndef __ASSEMBLY__
+#define ftrace_nmi_enter()      do { } while (0)
+#define ftrace_nmi_exit()       do { } while (0)
+#endif
+
 #ifdef CONFIG_MCOUNT
 #define MCOUNT_ADDR             ((long)(_mcount))
 #define MCOUNT_INSN_SIZE        4 /* sizeof mcount call */
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 9e8bc29b8b17..f2ed6b704a75 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -17,6 +17,21 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
          */
         return addr - 1;
 }
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+extern void ftrace_nmi_enter(void);
+extern void ftrace_nmi_exit(void);
+#else
+#define ftrace_nmi_enter()      do { } while (0)
+#define ftrace_nmi_exit()       do { } while (0)
+#endif
+#endif
+
+#else /* CONFIG_FUNCTION_TRACER */
+
+#ifndef __ASSEMBLY__
+#define ftrace_nmi_enter()      do { } while (0)
+#define ftrace_nmi_exit()       do { } while (0)
 #endif
 
 #endif /* CONFIG_FUNCTION_TRACER */
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 50ea0ac8c9bf..fe5f859130b5 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -56,6 +56,111 @@ unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
         return calc.code;
 }
 
+/*
+ * Modifying code must take extra care. On an SMP machine, if
+ * the code being modified is also being executed on another CPU
+ * that CPU will have undefined results and possibly take a GPF.
+ * We use kstop_machine to stop other CPUS from exectuing code.
+ * But this does not stop NMIs from happening. We still need
+ * to protect against that. We separate out the modification of
+ * the code to take care of this.
+ *
+ * Two buffers are added: An IP buffer and a "code" buffer.
+ *
+ * 1) Put in the instruction pointer into the IP buffer
+ *    and the new code into the "code" buffer.
+ * 2) Set a flag that says we are modifying code
+ * 3) Wait for any running NMIs to finish.
+ * 4) Write the code
+ * 5) clear the flag.
+ * 6) Wait for any running NMIs to finish.
+ *
+ * If an NMI is executed, the first thing it does is to call
+ * "ftrace_nmi_enter". This will check if the flag is set to write
+ * and if it is, it will write what is in the IP and "code" buffers.
+ *
+ * The trick is, it does not matter if everyone is writing the same
+ * content to the code location. Also, if a CPU is executing code
+ * it is OK to write to that code location if the contents being written
+ * are the same as what exists.
+ */
+
+static atomic_t in_nmi;
+static int mod_code_status;
+static int mod_code_write;
+static void *mod_code_ip;
+static void *mod_code_newcode;
+
+static void ftrace_mod_code(void)
+{
+        /*
+         * Yes, more than one CPU process can be writing to mod_code_status.
+         *    (and the code itself)
+         * But if one were to fail, then they all should, and if one were
+         * to succeed, then they all should.
+         */
+        mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode,
+                                             MCOUNT_INSN_SIZE);
+
+}
+
+void ftrace_nmi_enter(void)
+{
+        atomic_inc(&in_nmi);
+        /* Must have in_nmi seen before reading write flag */
+        smp_mb();
+        if (mod_code_write)
+                ftrace_mod_code();
+}
+
+void ftrace_nmi_exit(void)
+{
+        /* Finish all executions before clearing in_nmi */
+        smp_wmb();
+        atomic_dec(&in_nmi);
+}
+
+static void wait_for_nmi(void)
+{
+        while (atomic_read(&in_nmi))
+                cpu_relax();
+}
+
+static int
+do_ftrace_mod_code(unsigned long ip, void *new_code)
+{
+        mod_code_ip = (void *)ip;
+        mod_code_newcode = new_code;
+
+        /* The buffers need to be visible before we let NMIs write them */
+        smp_wmb();
+
+        mod_code_write = 1;
+
+        /* Make sure write bit is visible before we wait on NMIs */
+        smp_mb();
+
+        wait_for_nmi();
+
+        /* Make sure all running NMIs have finished before we write the code */
+        smp_mb();
+
+        ftrace_mod_code();
+
+        /* Make sure the write happens before clearing the bit */
+        smp_wmb();
+
+        mod_code_write = 0;
+
+        /* make sure NMIs see the cleared bit */
+        smp_mb();
+
+        wait_for_nmi();
+
+        return mod_code_status;
+}
+
+
 int
 ftrace_modify_code(unsigned long ip, unsigned char *old_code,
                    unsigned char *new_code)
@@ -81,7 +186,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
                 return -EINVAL;
 
         /* replace the text with the new text */
-        if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
+        if (do_ftrace_mod_code(ip, new_code))
                 return -EPERM;
 
         sync_core();
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 181006cc94a0..0087cb43becf 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -5,6 +5,7 @@
 #include <linux/smp_lock.h>
 #include <linux/lockdep.h>
 #include <asm/hardirq.h>
+#include <asm/ftrace.h>
 #include <asm/system.h>
 
 /*
@@ -161,7 +162,17 @@ extern void irq_enter(void);
  */
 extern void irq_exit(void);
 
-#define nmi_enter()             do { lockdep_off(); __irq_enter(); } while (0)
-#define nmi_exit()              do { __irq_exit(); lockdep_on(); } while (0)
+#define nmi_enter()                             \
+        do {                                    \
+                ftrace_nmi_enter();             \
+                lockdep_off();                  \
+                __irq_enter();                  \
+        } while (0)
+#define nmi_exit()                              \
+        do {                                    \
+                __irq_exit();                   \
+                lockdep_on();                   \
+                ftrace_nmi_exit();              \
+        } while (0)
 
 #endif /* LINUX_HARDIRQ_H */