1 files changed, 517 insertions, 301 deletions

diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 231bdd3c5b1..cbc4a91b131 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -9,6 +9,8 @@
  * the dangers of modifying code on the run.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/spinlock.h>
 #include <linux/hardirq.h>
 #include <linux/uaccess.h>
@@ -17,15 +19,31 @@
 #include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/list.h>
+#include <linux/module.h>
+
+#include <trace/syscall.h>
 
+#include <asm/cacheflush.h>
+#include <asm/kprobes.h>
 #include <asm/ftrace.h>
-#include <linux/ftrace.h>
 #include <asm/nops.h>
-#include <asm/nmi.h>
-
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
+int ftrace_arch_code_modify_prepare(void)
+{
+	set_kernel_text_rw();
+	set_all_modules_text_rw();
+	return 0;
+}
+
+int ftrace_arch_code_modify_post_process(void)
+{
+	set_all_modules_text_ro();
+	set_kernel_text_ro();
+	return 0;
+}
+
 union ftrace_code_union {
 	char code[MCOUNT_INSN_SIZE];
 	struct {
@@ -53,144 +71,36 @@ static 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 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)
+static inline int
+within(unsigned long addr, unsigned long start, unsigned long end)
 {
-	int r;
-
-	r = snprintf(buf, size, "%u %u",
-		     nmi_wait_count,
-		     atomic_read(&nmi_update_count));
-	return r;
+	return addr >= start && addr < end;
 }
 
-static void ftrace_mod_code(void)
+static unsigned long text_ip_addr(unsigned long ip)
 {
 	/*
-	 * 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.
+	 * On x86_64, kernel text mappings are mapped read-only with
+	 * CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead
+	 * of the kernel text mapping to modify the kernel text.
+	 *
+	 * For 32bit kernels, these mappings are same and we can use
+	 * kernel identity mapping to modify code.
 	 */
-	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);
-	}
-}
+	if (within(ip, (unsigned long)_text, (unsigned long)_etext))
+		ip = (unsigned long)__va(__pa_symbol(ip));
 
-void ftrace_nmi_exit(void)
-{
-	/* Finish all executions before clearing in_nmi */
-	smp_wmb();
-	atomic_dec(&in_nmi);
+	return ip;
 }
 
-static void wait_for_nmi(void)
+static const unsigned char *ftrace_nop_replace(void)
 {
-	int waited = 0;
-
-	while (atomic_read(&in_nmi)) {
-		waited = 1;
-		cpu_relax();
-	}
-
-	if (waited)
-		nmi_wait_count++;
+	return ideal_nops[NOP_ATOMIC5];
 }
 
 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;
-}
-
-
-
-
-static unsigned char ftrace_nop[MCOUNT_INSN_SIZE];
-
-static unsigned char *ftrace_nop_replace(void)
-{
-	return ftrace_nop;
-}
-
-static int
-ftrace_modify_code(unsigned long ip, unsigned char *old_code,
-		   unsigned char *new_code)
+ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code,
+		   unsigned const char *new_code)
 {
 	unsigned char replaced[MCOUNT_INSN_SIZE];
 
@@ -212,8 +122,10 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 	if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
 		return -EINVAL;
 
+	ip = text_ip_addr(ip);
+
 	/* replace the text with the new text */
-	if (do_ftrace_mod_code(ip, new_code))
+	if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
 		return -EPERM;
 
 	sync_core();
@@ -224,261 +136,573 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 int ftrace_make_nop(struct module *mod,
 		    struct dyn_ftrace *rec, unsigned long addr)
 {
-	unsigned char *new, *old;
+	unsigned const char *new, *old;
 	unsigned long ip = rec->ip;
 
 	old = ftrace_call_replace(ip, addr);
 	new = ftrace_nop_replace();
 
-	return ftrace_modify_code(rec->ip, old, new);
+	/*
+	 * On boot up, and when modules are loaded, the MCOUNT_ADDR
+	 * is converted to a nop, and will never become MCOUNT_ADDR
+	 * again. This code is either running before SMP (on boot up)
+	 * or before the code will ever be executed (module load).
+	 * We do not want to use the breakpoint version in this case,
+	 * just modify the code directly.
+	 */
+	if (addr == MCOUNT_ADDR)
+		return ftrace_modify_code_direct(rec->ip, old, new);
+
+	/* Normal cases use add_brk_on_nop */
+	WARN_ONCE(1, "invalid use of ftrace_make_nop");
+	return -EINVAL;
 }
 
 int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 {
-	unsigned char *new, *old;
+	unsigned const char *new, *old;
 	unsigned long ip = rec->ip;
 
 	old = ftrace_nop_replace();
 	new = ftrace_call_replace(ip, addr);
 
-	return ftrace_modify_code(rec->ip, old, new);
+	/* Should only be called when module is loaded */
+	return ftrace_modify_code_direct(rec->ip, old, new);
 }
 
-int ftrace_update_ftrace_func(ftrace_func_t func)
+/*
+ * The modifying_ftrace_code is used to tell the breakpoint
+ * handler to call ftrace_int3_handler(). If it fails to
+ * call this handler for a breakpoint added by ftrace, then
+ * the kernel may crash.
+ *
+ * As atomic_writes on x86 do not need a barrier, we do not
+ * need to add smp_mb()s for this to work. It is also considered
+ * that we can not read the modifying_ftrace_code before
+ * executing the breakpoint. That would be quite remarkable if
+ * it could do that. Here's the flow that is required:
+ *
+ *   CPU-0                          CPU-1
+ *
+ * atomic_inc(mfc);
+ * write int3s
+ *				<trap-int3> // implicit (r)mb
+ *				if (atomic_read(mfc))
+ *					call ftrace_int3_handler()
+ *
+ * Then when we are finished:
+ *
+ * atomic_dec(mfc);
+ *
+ * If we hit a breakpoint that was not set by ftrace, it does not
+ * matter if ftrace_int3_handler() is called or not. It will
+ * simply be ignored. But it is crucial that a ftrace nop/caller
+ * breakpoint is handled. No other user should ever place a
+ * breakpoint on an ftrace nop/caller location. It must only
+ * be done by this code.
+ */
+atomic_t modifying_ftrace_code __read_mostly;
+
+static int
+ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
+		   unsigned const char *new_code);
+
+/*
+ * Should never be called:
+ *  As it is only called by __ftrace_replace_code() which is called by
+ *  ftrace_replace_code() that x86 overrides, and by ftrace_update_code()
+ *  which is called to turn mcount into nops or nops into function calls
+ *  but not to convert a function from not using regs to one that uses
+ *  regs, which ftrace_modify_call() is for.
+ */
+int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
+				 unsigned long addr)
 {
-	unsigned long ip = (unsigned long)(&ftrace_call);
-	unsigned char old[MCOUNT_INSN_SIZE], *new;
+	WARN_ON(1);
+	return -EINVAL;
+}
+
+static unsigned long ftrace_update_func;
+
+static int update_ftrace_func(unsigned long ip, void *new)
+{
+	unsigned char old[MCOUNT_INSN_SIZE];
 	int ret;
 
-	memcpy(old, &ftrace_call, MCOUNT_INSN_SIZE);
-	new = ftrace_call_replace(ip, (unsigned long)func);
+	memcpy(old, (void *)ip, MCOUNT_INSN_SIZE);
+
+	ftrace_update_func = ip;
+	/* Make sure the breakpoints see the ftrace_update_func update */
+	smp_wmb();
+
+	/* See comment above by declaration of modifying_ftrace_code */
+	atomic_inc(&modifying_ftrace_code);
+
 	ret = ftrace_modify_code(ip, old, new);
 
+	atomic_dec(&modifying_ftrace_code);
+
 	return ret;
 }
 
-int __init ftrace_dyn_arch_init(void *data)
+int ftrace_update_ftrace_func(ftrace_func_t func)
 {
-	extern const unsigned char ftrace_test_p6nop[];
-	extern const unsigned char ftrace_test_nop5[];
-	extern const unsigned char ftrace_test_jmp[];
-	int faulted = 0;
+	unsigned long ip = (unsigned long)(&ftrace_call);
+	unsigned char *new;
+	int ret;
 
-	/*
-	 * 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("ftrace: converting mcount calls to 0f 1f 44 00 00\n");
-		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");
-		memcpy(ftrace_nop, ftrace_test_nop5, MCOUNT_INSN_SIZE);
-		break;
-	case 2:
-		pr_info("ftrace: converting mcount calls to jmp . + 5\n");
-		memcpy(ftrace_nop, ftrace_test_jmp, MCOUNT_INSN_SIZE);
-		break;
+	new = ftrace_call_replace(ip, (unsigned long)func);
+	ret = update_ftrace_func(ip, new);
+
+	/* Also update the regs callback function */
+	if (!ret) {
+		ip = (unsigned long)(&ftrace_regs_call);
+		new = ftrace_call_replace(ip, (unsigned long)func);
+		ret = update_ftrace_func(ip, new);
 	}
 
-	/* The return code is retured via data */
-	*(unsigned long *)data = 0;
+	return ret;
+}
+
+static int is_ftrace_caller(unsigned long ip)
+{
+	if (ip == ftrace_update_func)
+		return 1;
 
 	return 0;
 }
-#endif
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+/*
+ * A breakpoint was added to the code address we are about to
+ * modify, and this is the handle that will just skip over it.
+ * We are either changing a nop into a trace call, or a trace
+ * call to a nop. While the change is taking place, we treat
+ * it just like it was a nop.
+ */
+int ftrace_int3_handler(struct pt_regs *regs)
+{
+	unsigned long ip;
 
-#ifdef CONFIG_DYNAMIC_FTRACE
-extern void ftrace_graph_call(void);
+	if (WARN_ON_ONCE(!regs))
+		return 0;
 
-static int ftrace_mod_jmp(unsigned long ip,
-			  int old_offset, int new_offset)
-{
-	unsigned char code[MCOUNT_INSN_SIZE];
+	ip = regs->ip - 1;
+	if (!ftrace_location(ip) && !is_ftrace_caller(ip))
+		return 0;
 
-	if (probe_kernel_read(code, (void *)ip, MCOUNT_INSN_SIZE))
-		return -EFAULT;
+	regs->ip += MCOUNT_INSN_SIZE - 1;
 
-	if (code[0] != 0xe9 || old_offset != *(int *)(&code[1]))
-		return -EINVAL;
+	return 1;
+}
 
-	*(int *)(&code[1]) = new_offset;
+static int ftrace_write(unsigned long ip, const char *val, int size)
+{
+	ip = text_ip_addr(ip);
 
-	if (do_ftrace_mod_code(ip, &code))
+	if (probe_kernel_write((void *)ip, val, size))
 		return -EPERM;
 
 	return 0;
 }
 
-int ftrace_enable_ftrace_graph_caller(void)
+static int add_break(unsigned long ip, const char *old)
 {
-	unsigned long ip = (unsigned long)(&ftrace_graph_call);
-	int old_offset, new_offset;
+	unsigned char replaced[MCOUNT_INSN_SIZE];
+	unsigned char brk = BREAKPOINT_INSTRUCTION;
+
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
 
-	old_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE);
-	new_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE);
+	/* Make sure it is what we expect it to be */
+	if (memcmp(replaced, old, MCOUNT_INSN_SIZE) != 0)
+		return -EINVAL;
 
-	return ftrace_mod_jmp(ip, old_offset, new_offset);
+	return ftrace_write(ip, &brk, 1);
 }
 
-int ftrace_disable_ftrace_graph_caller(void)
+static int add_brk_on_call(struct dyn_ftrace *rec, unsigned long addr)
 {
-	unsigned long ip = (unsigned long)(&ftrace_graph_call);
-	int old_offset, new_offset;
+	unsigned const char *old;
+	unsigned long ip = rec->ip;
 
-	old_offset = (unsigned long)(&ftrace_graph_caller) - (ip + MCOUNT_INSN_SIZE);
-	new_offset = (unsigned long)(&ftrace_stub) - (ip + MCOUNT_INSN_SIZE);
+	old = ftrace_call_replace(ip, addr);
 
-	return ftrace_mod_jmp(ip, old_offset, new_offset);
+	return add_break(rec->ip, old);
 }
 
-#else /* CONFIG_DYNAMIC_FTRACE */
+
+static int add_brk_on_nop(struct dyn_ftrace *rec)
+{
+	unsigned const char *old;
+
+	old = ftrace_nop_replace();
+
+	return add_break(rec->ip, old);
+}
+
+static int add_breakpoints(struct dyn_ftrace *rec, int enable)
+{
+	unsigned long ftrace_addr;
+	int ret;
+
+	ftrace_addr = ftrace_get_addr_curr(rec);
+
+	ret = ftrace_test_record(rec, enable);
+
+	switch (ret) {
+	case FTRACE_UPDATE_IGNORE:
+		return 0;
+
+	case FTRACE_UPDATE_MAKE_CALL:
+		/* converting nop to call */
+		return add_brk_on_nop(rec);
+
+	case FTRACE_UPDATE_MODIFY_CALL:
+	case FTRACE_UPDATE_MAKE_NOP:
+		/* converting a call to a nop */
+		return add_brk_on_call(rec, ftrace_addr);
+	}
+	return 0;
+}
 
 /*
- * These functions are picked from those used on
- * this page for dynamic ftrace. They have been
- * simplified to ignore all traces in NMI context.
+ * On error, we need to remove breakpoints. This needs to
+ * be done caefully. If the address does not currently have a
+ * breakpoint, we know we are done. Otherwise, we look at the
+ * remaining 4 bytes of the instruction. If it matches a nop
+ * we replace the breakpoint with the nop. Otherwise we replace
+ * it with the call instruction.
  */
-static atomic_t in_nmi;
+static int remove_breakpoint(struct dyn_ftrace *rec)
+{
+	unsigned char ins[MCOUNT_INSN_SIZE];
+	unsigned char brk = BREAKPOINT_INSTRUCTION;
+	const unsigned char *nop;
+	unsigned long ftrace_addr;
+	unsigned long ip = rec->ip;
+
+	/* If we fail the read, just give up */
+	if (probe_kernel_read(ins, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* If this does not have a breakpoint, we are done */
+	if (ins[0] != brk)
+		return 0;
+
+	nop = ftrace_nop_replace();
+
+	/*
+	 * If the last 4 bytes of the instruction do not match
+	 * a nop, then we assume that this is a call to ftrace_addr.
+	 */
+	if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) {
+		/*
+		 * For extra paranoidism, we check if the breakpoint is on
+		 * a call that would actually jump to the ftrace_addr.
+		 * If not, don't touch the breakpoint, we make just create
+		 * a disaster.
+		 */
+		ftrace_addr = ftrace_get_addr_new(rec);
+		nop = ftrace_call_replace(ip, ftrace_addr);
+
+		if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) == 0)
+			goto update;
+
+		/* Check both ftrace_addr and ftrace_old_addr */
+		ftrace_addr = ftrace_get_addr_curr(rec);
+		nop = ftrace_call_replace(ip, ftrace_addr);
+
+		if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0)
+			return -EINVAL;
+	}
 
-void ftrace_nmi_enter(void)
+ update:
+	return ftrace_write(ip, nop, 1);
+}
+
+static int add_update_code(unsigned long ip, unsigned const char *new)
 {
-	atomic_inc(&in_nmi);
+	/* skip breakpoint */
+	ip++;
+	new++;
+	return ftrace_write(ip, new, MCOUNT_INSN_SIZE - 1);
 }
 
-void ftrace_nmi_exit(void)
+static int add_update_call(struct dyn_ftrace *rec, unsigned long addr)
 {
-	atomic_dec(&in_nmi);
+	unsigned long ip = rec->ip;
+	unsigned const char *new;
+
+	new = ftrace_call_replace(ip, addr);
+	return add_update_code(ip, new);
 }
 
-#endif /* !CONFIG_DYNAMIC_FTRACE */
+static int add_update_nop(struct dyn_ftrace *rec)
+{
+	unsigned long ip = rec->ip;
+	unsigned const char *new;
+
+	new = ftrace_nop_replace();
+	return add_update_code(ip, new);
+}
 
-/* Add a function return address to the trace stack on thread info.*/
-static int push_return_trace(unsigned long ret, unsigned long long time,
-				unsigned long func, int *depth)
+static int add_update(struct dyn_ftrace *rec, int enable)
 {
-	int index;
+	unsigned long ftrace_addr;
+	int ret;
 
-	if (!current->ret_stack)
-		return -EBUSY;
+	ret = ftrace_test_record(rec, enable);
 
-	/* The return trace stack is full */
-	if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) {
-		atomic_inc(&current->trace_overrun);
-		return -EBUSY;
-	}
+	ftrace_addr  = ftrace_get_addr_new(rec);
+
+	switch (ret) {
+	case FTRACE_UPDATE_IGNORE:
+		return 0;
 
-	index = ++current->curr_ret_stack;
-	barrier();
-	current->ret_stack[index].ret = ret;
-	current->ret_stack[index].func = func;
-	current->ret_stack[index].calltime = time;
-	*depth = index;
+	case FTRACE_UPDATE_MODIFY_CALL:
+	case FTRACE_UPDATE_MAKE_CALL:
+		/* converting nop to call */
+		return add_update_call(rec, ftrace_addr);
+
+	case FTRACE_UPDATE_MAKE_NOP:
+		/* converting a call to a nop */
+		return add_update_nop(rec);
+	}
 
 	return 0;
 }
 
-/* Retrieve a function return address to the trace stack on thread info.*/
-static void pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
+static int finish_update_call(struct dyn_ftrace *rec, unsigned long addr)
 {
-	int index;
+	unsigned long ip = rec->ip;
+	unsigned const char *new;
+
+	new = ftrace_call_replace(ip, addr);
 
-	index = current->curr_ret_stack;
+	return ftrace_write(ip, new, 1);
+}
 
-	if (unlikely(index < 0)) {
-		ftrace_graph_stop();
-		WARN_ON(1);
-		/* Might as well panic, otherwise we have no where to go */
-		*ret = (unsigned long)panic;
-		return;
+static int finish_update_nop(struct dyn_ftrace *rec)
+{
+	unsigned long ip = rec->ip;
+	unsigned const char *new;
+
+	new = ftrace_nop_replace();
+
+	return ftrace_write(ip, new, 1);
+}
+
+static int finish_update(struct dyn_ftrace *rec, int enable)
+{
+	unsigned long ftrace_addr;
+	int ret;
+
+	ret = ftrace_update_record(rec, enable);
+
+	ftrace_addr = ftrace_get_addr_new(rec);
+
+	switch (ret) {
+	case FTRACE_UPDATE_IGNORE:
+		return 0;
+
+	case FTRACE_UPDATE_MODIFY_CALL:
+	case FTRACE_UPDATE_MAKE_CALL:
+		/* converting nop to call */
+		return finish_update_call(rec, ftrace_addr);
+
+	case FTRACE_UPDATE_MAKE_NOP:
+		/* converting a call to a nop */
+		return finish_update_nop(rec);
 	}
 
-	*ret = current->ret_stack[index].ret;
-	trace->func = current->ret_stack[index].func;
-	trace->calltime = current->ret_stack[index].calltime;
-	trace->overrun = atomic_read(&current->trace_overrun);
-	trace->depth = index;
-	barrier();
-	current->curr_ret_stack--;
+	return 0;
+}
 
+static void do_sync_core(void *data)
+{
+	sync_core();
 }
 
-/*
- * Send the trace to the ring-buffer.
- * @return the original return address.
- */
-unsigned long ftrace_return_to_handler(void)
+static void run_sync(void)
 {
-	struct ftrace_graph_ret trace;
-	unsigned long ret;
+	int enable_irqs = irqs_disabled();
+
+	/* We may be called with interrupts disbled (on bootup). */
+	if (enable_irqs)
+		local_irq_enable();
+	on_each_cpu(do_sync_core, NULL, 1);
+	if (enable_irqs)
+		local_irq_disable();
+}
 
-	pop_return_trace(&trace, &ret);
-	trace.rettime = cpu_clock(raw_smp_processor_id());
-	ftrace_graph_return(&trace);
+void ftrace_replace_code(int enable)
+{
+	struct ftrace_rec_iter *iter;
+	struct dyn_ftrace *rec;
+	const char *report = "adding breakpoints";
+	int count = 0;
+	int ret;
 
-	if (unlikely(!ret)) {
-		ftrace_graph_stop();
-		WARN_ON(1);
-		/* Might as well panic. What else to do? */
-		ret = (unsigned long)panic;
+	for_ftrace_rec_iter(iter) {
+		rec = ftrace_rec_iter_record(iter);
+
+		ret = add_breakpoints(rec, enable);
+		if (ret)
+			goto remove_breakpoints;
+		count++;
+	}
+
+	run_sync();
+
+	report = "updating code";
+
+	for_ftrace_rec_iter(iter) {
+		rec = ftrace_rec_iter_record(iter);
+
+		ret = add_update(rec, enable);
+		if (ret)
+			goto remove_breakpoints;
 	}
 
+	run_sync();
+
+	report = "removing breakpoints";
+
+	for_ftrace_rec_iter(iter) {
+		rec = ftrace_rec_iter_record(iter);
+
+		ret = finish_update(rec, enable);
+		if (ret)
+			goto remove_breakpoints;
+	}
+
+	run_sync();
+
+	return;
+
+ remove_breakpoints:
+	pr_warn("Failed on %s (%d):\n", report, count);
+	ftrace_bug(ret, rec ? rec->ip : 0);
+	for_ftrace_rec_iter(iter) {
+		rec = ftrace_rec_iter_record(iter);
+		/*
+		 * Breakpoints are handled only when this function is in
+		 * progress. The system could not work with them.
+		 */
+		if (remove_breakpoint(rec))
+			BUG();
+	}
+	run_sync();
+}
+
+static int
+ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
+		   unsigned const char *new_code)
+{
+	int ret;
+
+	ret = add_break(ip, old_code);
+	if (ret)
+		goto out;
+
+	run_sync();
+
+	ret = add_update_code(ip, new_code);
+	if (ret)
+		goto fail_update;
+
+	run_sync();
+
+	ret = ftrace_write(ip, new_code, 1);
+	/*
+	 * The breakpoint is handled only when this function is in progress.
+	 * The system could not work if we could not remove it.
+	 */
+	BUG_ON(ret);
+ out:
+	run_sync();
 	return ret;
+
+ fail_update:
+	/* Also here the system could not work with the breakpoint */
+	if (ftrace_write(ip, old_code, 1))
+		BUG();
+	goto out;
+}
+
+void arch_ftrace_update_code(int command)
+{
+	/* See comment above by declaration of modifying_ftrace_code */
+	atomic_inc(&modifying_ftrace_code);
+
+	ftrace_modify_all_code(command);
+
+	atomic_dec(&modifying_ftrace_code);
+}
+
+int __init ftrace_dyn_arch_init(void)
+{
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+extern void ftrace_graph_call(void);
+
+static unsigned char *ftrace_jmp_replace(unsigned long ip, unsigned long addr)
+{
+	static union ftrace_code_union calc;
+
+	/* Jmp not a call (ignore the .e8) */
+	calc.e8		= 0xe9;
+	calc.offset	= ftrace_calc_offset(ip + MCOUNT_INSN_SIZE, addr);
+
+	/*
+	 * ftrace external locks synchronize the access to the static variable.
+	 */
+	return calc.code;
 }
 
+static int ftrace_mod_jmp(unsigned long ip, void *func)
+{
+	unsigned char *new;
+
+	new = ftrace_jmp_replace(ip, (unsigned long)func);
+
+	return update_ftrace_func(ip, new);
+}
+
+int ftrace_enable_ftrace_graph_caller(void)
+{
+	unsigned long ip = (unsigned long)(&ftrace_graph_call);
+
+	return ftrace_mod_jmp(ip, &ftrace_graph_caller);
+}
+
+int ftrace_disable_ftrace_graph_caller(void)
+{
+	unsigned long ip = (unsigned long)(&ftrace_graph_call);
+
+	return ftrace_mod_jmp(ip, &ftrace_stub);
+}
+
+#endif /* !CONFIG_DYNAMIC_FTRACE */
+
 /*
  * Hook the return address and push it in the stack of return addrs
  * in current thread info.
  */
-void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+			   unsigned long frame_pointer)
 {
 	unsigned long old;
-	unsigned long long calltime;
 	int faulted;
 	struct ftrace_graph_ent trace;
 	unsigned long return_hooker = (unsigned long)
 				&return_to_handler;
 
-	/* Nmi's are currently unsupported */
-	if (unlikely(atomic_read(&in_nmi)))
-		return;
-
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
 
@@ -501,7 +725,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 		_ASM_EXTABLE(1b, 4b)
 		_ASM_EXTABLE(2b, 4b)
 
-		: [old] "=r" (old), [faulted] "=r" (faulted)
+		: [old] "=&r" (old), [faulted] "=r" (faulted)
 		: [parent] "r" (parent), [return_hooker] "r" (return_hooker)
 		: "memory"
 	);
@@ -512,27 +736,19 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 		return;
 	}
 
-	if (unlikely(!__kernel_text_address(old))) {
-		ftrace_graph_stop();
-		*parent = old;
-		WARN_ON(1);
-		return;
-	}
-
-	calltime = cpu_clock(raw_smp_processor_id());
+	trace.func = self_addr;
+	trace.depth = current->curr_ret_stack + 1;
 
-	if (push_return_trace(old, calltime,
-				self_addr, &trace.depth) == -EBUSY) {
+	/* Only trace if the calling function expects to */
+	if (!ftrace_graph_entry(&trace)) {
 		*parent = old;
 		return;
 	}
 
-	trace.func = self_addr;
-
-	/* Only trace if the calling function expects to */
-	if (!ftrace_graph_entry(&trace)) {
-		current->curr_ret_stack--;
+	if (ftrace_push_return_trace(old, self_addr, &trace.depth,
+		    frame_pointer) == -EBUSY) {
 		*parent = old;
+		return;
 	}
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */