ftrace: use dynamic patching for updating mcount calls

This patch replaces the indirect call to the mcount function
pointer with a direct call that will be patched by the
dynamic ftrace routines.

On boot up, the mcount function calls the ftace_stub function.
When the dynamic ftrace code is initialized, the ftrace_stub
is replaced with a call to the ftrace_record_ip, which records
the instruction pointers of the locations that call it.

Later, the ftraced daemon will call kstop_machine and patch all
the locations to nops.

When a ftrace is enabled, the original calls to mcount will now
be set top call ftrace_caller, which will do a direct call
to the registered ftrace function. This direct call is also patched
when the function that should be called is updated.

All patching is performed by a kstop_machine routine to prevent any
type of race conditions that is associated with modifying code
on the fly.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

3 files changed, 150 insertions, 5 deletions

diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index f47b9b544..e6517ce 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1110,10 +1110,50 @@ ENDPROC(xen_failsafe_callback)
 #endif	/* CONFIG_XEN */
 
 #ifdef CONFIG_FTRACE
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+ENTRY(mcount)
+	pushl %eax
+	pushl %ecx
+	pushl %edx
+	movl 0xc(%esp), %eax
+
+.globl mcount_call
+mcount_call:
+	call ftrace_stub
+
+	popl %edx
+	popl %ecx
+	popl %eax
+
+	ret
+END(mcount)
+
+ENTRY(ftrace_caller)
+	pushl %eax
+	pushl %ecx
+	pushl %edx
+	movl 0xc(%esp), %eax
+	movl 0x4(%ebp), %edx
+
+.globl ftrace_call
+ftrace_call:
+	call ftrace_stub
+
+	popl %edx
+	popl %ecx
+	popl %eax
+
+.globl ftrace_stub
+ftrace_stub:
+	ret
+END(ftrace_caller)
+
+#else /* ! CONFIG_DYNAMIC_FTRACE */
+
 ENTRY(mcount)
 	cmpl $ftrace_stub, ftrace_trace_function
 	jnz trace
-
 .globl ftrace_stub
 ftrace_stub:
 	ret
@@ -1126,7 +1166,7 @@ trace:
 	movl 0xc(%esp), %eax
 	movl 0x4(%ebp), %edx
 
-	call   *ftrace_trace_function
+	call *ftrace_trace_function
 
 	popl %edx
 	popl %ecx
@@ -1134,7 +1174,8 @@ trace:
 
 	jmp ftrace_stub
 END(mcount)
-#endif
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FTRACE */
 
 .section .rodata,"a"
 #include "syscall_table_32.S"
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index f046e0c..fe25e5f 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -55,6 +55,70 @@
 	.code64
 
 #ifdef CONFIG_FTRACE
+#ifdef CONFIG_DYNAMIC_FTRACE
+ENTRY(mcount)
+
+	subq $0x38, %rsp
+	movq %rax, (%rsp)
+	movq %rcx, 8(%rsp)
+	movq %rdx, 16(%rsp)
+	movq %rsi, 24(%rsp)
+	movq %rdi, 32(%rsp)
+	movq %r8, 40(%rsp)
+	movq %r9, 48(%rsp)
+
+	movq 0x38(%rsp), %rdi
+
+.globl mcount_call
+mcount_call:
+	call ftrace_stub
+
+	movq 48(%rsp), %r9
+	movq 40(%rsp), %r8
+	movq 32(%rsp), %rdi
+	movq 24(%rsp), %rsi
+	movq 16(%rsp), %rdx
+	movq 8(%rsp), %rcx
+	movq (%rsp), %rax
+	addq $0x38, %rsp
+
+	retq
+END(mcount)
+
+ENTRY(ftrace_caller)
+
+	/* taken from glibc */
+	subq $0x38, %rsp
+	movq %rax, (%rsp)
+	movq %rcx, 8(%rsp)
+	movq %rdx, 16(%rsp)
+	movq %rsi, 24(%rsp)
+	movq %rdi, 32(%rsp)
+	movq %r8, 40(%rsp)
+	movq %r9, 48(%rsp)
+
+	movq 0x38(%rsp), %rdi
+	movq 8(%rbp), %rsi
+
+.globl ftrace_call
+ftrace_call:
+	call ftrace_stub
+
+	movq 48(%rsp), %r9
+	movq 40(%rsp), %r8
+	movq 32(%rsp), %rdi
+	movq 24(%rsp), %rsi
+	movq 16(%rsp), %rdx
+	movq 8(%rsp), %rcx
+	movq (%rsp), %rax
+	addq $0x38, %rsp
+
+.globl ftrace_stub
+ftrace_stub:
+	retq
+END(ftrace_caller)
+
+#else /* ! CONFIG_DYNAMIC_FTRACE */
 ENTRY(mcount)
 	cmpq $ftrace_stub, ftrace_trace_function
 	jnz trace
@@ -89,7 +153,8 @@ trace:
 
 	jmp ftrace_stub
 END(mcount)
-#endif
+#endif /* CONFIG_DYNAMIC_FTRACE */
+#endif /* CONFIG_FTRACE */
 
 #ifndef CONFIG_PREEMPT
 #define retint_kernel retint_restore_args
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index b69795e..9f44623 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -109,10 +109,49 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 	return faulted;
 }
 
-int __init ftrace_dyn_arch_init(void)
+notrace int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	unsigned long ip = (unsigned long)(&ftrace_call);
+	unsigned char old[5], *new;
+	int ret;
+
+	ip += CALL_BACK;
+
+	memcpy(old, &ftrace_call, 5);
+	new = ftrace_call_replace(ip, (unsigned long)func);
+	ret = ftrace_modify_code(ip, old, new);
+
+	return ret;
+}
+
+notrace int ftrace_mcount_set(unsigned long *data)
+{
+	unsigned long ip = (long)(&mcount_call);
+	unsigned long *addr = data;
+	unsigned char old[5], *new;
+
+	/* ip is at the location, but modify code will subtact this */
+	ip += CALL_BACK;
+
+	/*
+	 * Replace the mcount stub with a pointer to the
+	 * ip recorder function.
+	 */
+	memcpy(old, &mcount_call, 5);
+	new = ftrace_call_replace(ip, *addr);
+	*addr = ftrace_modify_code(ip, old, new);
+
+	return 0;
+}
+
+int __init ftrace_dyn_arch_init(void *data)
 {
 	const unsigned char *const *noptable = find_nop_table();
 
+	/* This is running in kstop_machine */
+
+	ftrace_mcount_set(data);
+
 	ftrace_nop = (unsigned long *)noptable[CALL_BACK];
 
 	return 0;