1 files changed, 148 insertions, 29 deletions

diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index d073d981a730..69149337f2fe 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -21,8 +21,7 @@
 #include <asm/nops.h>
 
 
-/* Long is fine, even if it is only 4 bytes ;-) */
-static unsigned long *ftrace_nop;
+static unsigned char ftrace_nop[MCOUNT_INSN_SIZE];
 
 union ftrace_code_union {
 	char code[MCOUNT_INSN_SIZE];
@@ -33,17 +32,17 @@ union ftrace_code_union {
 };
 
 
-static int notrace ftrace_calc_offset(long ip, long addr)
+static int ftrace_calc_offset(long ip, long addr)
 {
 	return (int)(addr - ip);
 }
 
-notrace unsigned char *ftrace_nop_replace(void)
+unsigned char *ftrace_nop_replace(void)
 {
-	return (char *)ftrace_nop;
+	return ftrace_nop;
 }
 
-notrace unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
+unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 {
 	static union ftrace_code_union calc;
 
@@ -57,7 +56,134 @@ notrace unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 	return calc.code;
 }
 
-notrace int
+/*
+ * 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 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 = ATOMIC_INIT(0);
+static int mod_code_status;		/* holds return value of text write */
+static int mod_code_write;		/* set when NMI should do the write */
+static void *mod_code_ip;		/* holds the IP to write to */
+static void *mod_code_newcode;		/* holds the text to write to the IP */
+
+static unsigned nmi_wait_count;
+static atomic_t nmi_update_count = ATOMIC_INIT(0);
+
+int ftrace_arch_read_dyn_info(char *buf, int size)
+{
+	int r;
+
+	r = snprintf(buf, size, "%u %u",
+		     nmi_wait_count,
+		     atomic_read(&nmi_update_count));
+	return r;
+}
+
+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();
+		atomic_inc(&nmi_update_count);
+	}
+}
+
+void ftrace_nmi_exit(void)
+{
+	/* Finish all executions before clearing in_nmi */
+	smp_wmb();
+	atomic_dec(&in_nmi);
+}
+
+static void wait_for_nmi(void)
+{
+	int waited = 0;
+
+	while (atomic_read(&in_nmi)) {
+		waited = 1;
+		cpu_relax();
+	}
+
+	if (waited)
+		nmi_wait_count++;
+}
+
+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)
 {
@@ -66,26 +192,31 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 	/*
 	 * Note: Due to modules and __init, code can
 	 *  disappear and change, we need to protect against faulting
-	 *  as well as code changing.
+	 *  as well as code changing. We do this by using the
+	 *  probe_kernel_* functions.
 	 *
 	 * No real locking needed, this code is run through
 	 * kstop_machine, or before SMP starts.
 	 */
-	if (__copy_from_user_inatomic(replaced, (char __user *)ip, MCOUNT_INSN_SIZE))
-		return 1;
 
+	/* read the text we want to modify */
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* Make sure it is what we expect it to be */
 	if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
-		return 2;
+		return -EINVAL;
 
-	WARN_ON_ONCE(__copy_to_user_inatomic((char __user *)ip, new_code,
-				    MCOUNT_INSN_SIZE));
+	/* replace the text with the new text */
+	if (do_ftrace_mod_code(ip, new_code))
+		return -EPERM;
 
 	sync_core();
 
 	return 0;
 }
 
-notrace int ftrace_update_ftrace_func(ftrace_func_t func)
+int ftrace_update_ftrace_func(ftrace_func_t func)
 {
 	unsigned long ip = (unsigned long)(&ftrace_call);
 	unsigned char old[MCOUNT_INSN_SIZE], *new;
@@ -98,13 +229,6 @@ notrace int ftrace_update_ftrace_func(ftrace_func_t func)
 	return ret;
 }
 
-notrace int ftrace_mcount_set(unsigned long *data)
-{
-	/* mcount is initialized as a nop */
-	*data = 0;
-	return 0;
-}
-
 int __init ftrace_dyn_arch_init(void *data)
 {
 	extern const unsigned char ftrace_test_p6nop[];
@@ -127,9 +251,6 @@ int __init ftrace_dyn_arch_init(void *data)
 	 * TODO: check the cpuid to determine the best nop.
 	 */
 	asm volatile (
-		"jmp ftrace_test_jmp\n"
-		/* This code needs to stay around */
-		".section .text, \"ax\"\n"
 		"ftrace_test_jmp:"
 		"jmp ftrace_test_p6nop\n"
 		"nop\n"
@@ -140,8 +261,6 @@ int __init ftrace_dyn_arch_init(void *data)
 		"jmp 1f\n"
 		"ftrace_test_nop5:"
 		".byte 0x66,0x66,0x66,0x66,0x90\n"
-		"jmp 1f\n"
-		".previous\n"
 		"1:"
 		".section .fixup, \"ax\"\n"
 		"2:	movl $1, %0\n"
@@ -156,15 +275,15 @@ int __init ftrace_dyn_arch_init(void *data)
 	switch (faulted) {
 	case 0:
 		pr_info("ftrace: converting mcount calls to 0f 1f 44 00 00\n");
-		ftrace_nop = (unsigned long *)ftrace_test_p6nop;
+		memcpy(ftrace_nop, ftrace_test_p6nop, MCOUNT_INSN_SIZE);
 		break;
 	case 1:
 		pr_info("ftrace: converting mcount calls to 66 66 66 66 90\n");
-		ftrace_nop = (unsigned long *)ftrace_test_nop5;
+		memcpy(ftrace_nop, ftrace_test_nop5, MCOUNT_INSN_SIZE);
 		break;
 	case 2:
 		pr_info("ftrace: converting mcount calls to jmp . + 5\n");
-		ftrace_nop = (unsigned long *)ftrace_test_jmp;
+		memcpy(ftrace_nop, ftrace_test_jmp, MCOUNT_INSN_SIZE);
 		break;
 	}