ftrace/x86: Add separate function to save regs

Add a way to have different functions calling different trampolines.
If a ftrace_ops wants regs saved on the return, then have only the
functions with ops registered to save regs. Functions registered by
other ops would not be affected, unless the functions overlap.

If one ftrace_ops registered functions A, B and C and another ops
registered fucntions to save regs on A, and D, then only functions
A and D would be saving regs. Function B and C would work as normal.
Although A is registered by both ops: normal and saves regs; this is fine
as saving the regs is needed to satisfy one of the ops that calls it
but the regs are ignored by the other ops function.

x86_64 implements the full regs saving, and i386 just passes a NULL
for regs to satisfy the ftrace_ops passing. Where an arch must supply
both regs and ftrace_ops parameters, even if regs is just NULL.

It is OK for an arch to pass NULL regs. All function trace users that
require regs passing must add the flag FTRACE_OPS_FL_SAVE_REGS when
registering the ftrace_ops. If the arch does not support saving regs
then the ftrace_ops will fail to register. The flag
FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED may be set that will prevent the
ftrace_ops from failing to register. In this case, the handler may
either check if regs is not NULL or check if ARCH_SUPPORTS_FTRACE_SAVE_REGS.
If the arch supports passing regs it will set this macro and pass regs
for ops that request them. All other archs will just pass NULL.

Link: Link: http://lkml.kernel.org/r/20120711195745.107705970@goodmis.org

Cc: Alexander van Heukelum <heukelum@fastmail.fm>
Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

4 files changed, 190 insertions, 32 deletions

diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index b3bb1f3f277..a8475014c4a 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -3,27 +3,33 @@
 
 #ifdef __ASSEMBLY__
 
-	.macro MCOUNT_SAVE_FRAME
-	/* 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)
+	/* skip is set if the stack was already partially adjusted */
+	.macro MCOUNT_SAVE_FRAME skip=0
+	 /*
+	  * We add enough stack to save all regs.
+	  */
+	subq $(SS+8-\skip), %rsp
+	movq %rax, RAX(%rsp)
+	movq %rcx, RCX(%rsp)
+	movq %rdx, RDX(%rsp)
+	movq %rsi, RSI(%rsp)
+	movq %rdi, RDI(%rsp)
+	movq %r8, R8(%rsp)
+	movq %r9, R9(%rsp)
+	 /* Move RIP to its proper location */
+	movq SS+8(%rsp), %rdx
+	movq %rdx, RIP(%rsp)
 	.endm
 
-	.macro MCOUNT_RESTORE_FRAME
-	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
+	.macro MCOUNT_RESTORE_FRAME skip=0
+	movq R9(%rsp), %r9
+	movq R8(%rsp), %r8
+	movq RDI(%rsp), %rdi
+	movq RSI(%rsp), %rsi
+	movq RDX(%rsp), %rdx
+	movq RCX(%rsp), %rcx
+	movq RAX(%rsp), %rax
+	addq $(SS+8-\skip), %rsp
 	.endm
 
 #endif
@@ -34,6 +40,9 @@
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 #define ARCH_SUPPORTS_FTRACE_OPS 1
+#ifdef CONFIG_X86_64
+#define ARCH_SUPPORTS_FTRACE_SAVE_REGS
+#endif
 #endif
 
 #ifndef __ASSEMBLY__
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index e3e17a0b7ff..5da11d1b85a 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -1109,7 +1109,8 @@ ENTRY(ftrace_caller)
 	pushl %eax
 	pushl %ecx
 	pushl %edx
-	movl 0xc(%esp), %eax
+	pushl $0	/* Pass NULL as regs pointer */
+	movl 4*4(%esp), %eax
 	movl 0x4(%ebp), %edx
 	leal function_trace_op, %ecx
 	subl $MCOUNT_INSN_SIZE, %eax
@@ -1118,6 +1119,7 @@ ENTRY(ftrace_caller)
 ftrace_call:
 	call ftrace_stub
 
+	addl $4,%esp	/* skip NULL pointer */
 	popl %edx
 	popl %ecx
 	popl %eax
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 2b4f94c5dc6..52bda2e8f7a 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -73,21 +73,34 @@ ENTRY(mcount)
 	retq
 END(mcount)
 
+/* skip is set if stack has been adjusted */
+.macro ftrace_caller_setup skip=0
+	MCOUNT_SAVE_FRAME \skip
+
+	/* Load the ftrace_ops into the 3rd parameter */
+	leaq function_trace_op, %rdx
+
+	/* Load ip into the first parameter */
+	movq RIP(%rsp), %rdi
+	subq $MCOUNT_INSN_SIZE, %rdi
+	/* Load the parent_ip into the second parameter */
+	movq 8(%rbp), %rsi
+.endm
+
 ENTRY(ftrace_caller)
+	/* Check if tracing was disabled (quick check) */
 	cmpl $0, function_trace_stop
 	jne  ftrace_stub
 
-	MCOUNT_SAVE_FRAME
-
-	leaq function_trace_op, %rdx
-	movq 0x38(%rsp), %rdi
-	movq 8(%rbp), %rsi
-	subq $MCOUNT_INSN_SIZE, %rdi
+	ftrace_caller_setup
+	/* regs go into 4th parameter (but make it NULL) */
+	movq $0, %rcx
 
 GLOBAL(ftrace_call)
 	call ftrace_stub
 
 	MCOUNT_RESTORE_FRAME
+ftrace_return:
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 GLOBAL(ftrace_graph_call)
@@ -98,6 +111,71 @@ GLOBAL(ftrace_stub)
 	retq
 END(ftrace_caller)
 
+ENTRY(ftrace_regs_caller)
+	/* Save the current flags before compare (in SS location)*/
+	pushfq
+
+	/* Check if tracing was disabled (quick check) */
+	cmpl $0, function_trace_stop
+	jne  ftrace_restore_flags
+
+	/* skip=8 to skip flags saved in SS */
+	ftrace_caller_setup 8
+
+	/* Save the rest of pt_regs */
+	movq %r15, R15(%rsp)
+	movq %r14, R14(%rsp)
+	movq %r13, R13(%rsp)
+	movq %r12, R12(%rsp)
+	movq %r11, R11(%rsp)
+	movq %r10, R10(%rsp)
+	movq %rbp, RBP(%rsp)
+	movq %rbx, RBX(%rsp)
+	/* Copy saved flags */
+	movq SS(%rsp), %rcx
+	movq %rcx, EFLAGS(%rsp)
+	/* Kernel segments */
+	movq $__KERNEL_DS, %rcx
+	movq %rcx, SS(%rsp)
+	movq $__KERNEL_CS, %rcx
+	movq %rcx, CS(%rsp)
+	/* Stack - skipping return address */
+	leaq SS+16(%rsp), %rcx
+	movq %rcx, RSP(%rsp)
+
+	/* regs go into 4th parameter */
+	leaq (%rsp), %rcx
+
+GLOBAL(ftrace_regs_call)
+	call ftrace_stub
+
+	/* Copy flags back to SS, to restore them */
+	movq EFLAGS(%rsp), %rax
+	movq %rax, SS(%rsp)
+
+	/* restore the rest of pt_regs */
+	movq R15(%rsp), %r15
+	movq R14(%rsp), %r14
+	movq R13(%rsp), %r13
+	movq R12(%rsp), %r12
+	movq R10(%rsp), %r10
+	movq RBP(%rsp), %rbp
+	movq RBX(%rsp), %rbx
+
+	/* skip=8 to skip flags saved in SS */
+	MCOUNT_RESTORE_FRAME 8
+
+	/* Restore flags */
+	popfq
+
+	jmp ftrace_return
+ftrace_restore_flags:
+	popfq
+	jmp  ftrace_stub
+
+END(ftrace_regs_caller)
+
+
 #else /* ! CONFIG_DYNAMIC_FTRACE */
 ENTRY(mcount)
 	cmpl $0, function_trace_stop
@@ -120,7 +198,7 @@ GLOBAL(ftrace_stub)
 trace:
 	MCOUNT_SAVE_FRAME
 
-	movq 0x38(%rsp), %rdi
+	movq RIP(%rsp), %rdi
 	movq 8(%rbp), %rsi
 	subq $MCOUNT_INSN_SIZE, %rdi
 
@@ -141,7 +219,7 @@ ENTRY(ftrace_graph_caller)
 	MCOUNT_SAVE_FRAME
 
 	leaq 8(%rbp), %rdi
-	movq 0x38(%rsp), %rsi
+	movq RIP(%rsp), %rsi
 	movq (%rbp), %rdx
 	subq $MCOUNT_INSN_SIZE, %rsi
 
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index c3a7cb4bf6e..b90eb1a1307 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -206,6 +206,23 @@ static int
 ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
 		   unsigned const char *new_code);
 
+#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS
+/*
+ * 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)
+{
+	WARN_ON(1);
+	return -EINVAL;
+}
+#endif
+
 int ftrace_update_ftrace_func(ftrace_func_t func)
 {
 	unsigned long ip = (unsigned long)(&ftrace_call);
@@ -220,6 +237,16 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 
 	ret = ftrace_modify_code(ip, old, new);
 
+#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS
+	/* Also update the regs callback function */
+	if (!ret) {
+		ip = (unsigned long)(&ftrace_regs_call);
+		memcpy(old, &ftrace_regs_call, MCOUNT_INSN_SIZE);
+		new = ftrace_call_replace(ip, (unsigned long)func);
+		ret = ftrace_modify_code(ip, old, new);
+	}
+#endif
+
 	atomic_dec(&modifying_ftrace_code);
 
 	return ret;
@@ -299,6 +326,32 @@ static int add_brk_on_nop(struct dyn_ftrace *rec)
 	return add_break(rec->ip, old);
 }
 
+/*
+ * If the record has the FTRACE_FL_REGS set, that means that it
+ * wants to convert to a callback that saves all regs. If FTRACE_FL_REGS
+ * is not not set, then it wants to convert to the normal callback.
+ */
+static unsigned long get_ftrace_addr(struct dyn_ftrace *rec)
+{
+	if (rec->flags & FTRACE_FL_REGS)
+		return (unsigned long)FTRACE_REGS_ADDR;
+	else
+		return (unsigned long)FTRACE_ADDR;
+}
+
+/*
+ * The FTRACE_FL_REGS_EN is set when the record already points to
+ * a function that saves all the regs. Basically the '_EN' version
+ * represents the current state of the function.
+ */
+static unsigned long get_ftrace_old_addr(struct dyn_ftrace *rec)
+{
+	if (rec->flags & FTRACE_FL_REGS_EN)
+		return (unsigned long)FTRACE_REGS_ADDR;
+	else
+		return (unsigned long)FTRACE_ADDR;
+}
+
 static int add_breakpoints(struct dyn_ftrace *rec, int enable)
 {
 	unsigned long ftrace_addr;
@@ -306,7 +359,7 @@ static int add_breakpoints(struct dyn_ftrace *rec, int enable)
 
 	ret = ftrace_test_record(rec, enable);
 
-	ftrace_addr = (unsigned long)FTRACE_ADDR;
+	ftrace_addr = get_ftrace_addr(rec);
 
 	switch (ret) {
 	case FTRACE_UPDATE_IGNORE:
@@ -316,6 +369,10 @@ static int add_breakpoints(struct dyn_ftrace *rec, int enable)
 		/* converting nop to call */
 		return add_brk_on_nop(rec);
 
+	case FTRACE_UPDATE_MODIFY_CALL_REGS:
+	case FTRACE_UPDATE_MODIFY_CALL:
+		ftrace_addr = get_ftrace_old_addr(rec);
+		/* fall through */
 	case FTRACE_UPDATE_MAKE_NOP:
 		/* converting a call to a nop */
 		return add_brk_on_call(rec, ftrace_addr);
@@ -360,13 +417,21 @@ static int remove_breakpoint(struct dyn_ftrace *rec)
 		 * If not, don't touch the breakpoint, we make just create
 		 * a disaster.
 		 */
-		ftrace_addr = (unsigned long)FTRACE_ADDR;
+		ftrace_addr = get_ftrace_addr(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 = get_ftrace_old_addr(rec);
 		nop = ftrace_call_replace(ip, ftrace_addr);
 
 		if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0)
 			return -EINVAL;
 	}
 
+ update:
 	return probe_kernel_write((void *)ip, &nop[0], 1);
 }
 
@@ -405,12 +470,14 @@ static int add_update(struct dyn_ftrace *rec, int enable)
 
 	ret = ftrace_test_record(rec, enable);
 
-	ftrace_addr = (unsigned long)FTRACE_ADDR;
+	ftrace_addr  = get_ftrace_addr(rec);
 
 	switch (ret) {
 	case FTRACE_UPDATE_IGNORE:
 		return 0;
 
+	case FTRACE_UPDATE_MODIFY_CALL_REGS:
+	case FTRACE_UPDATE_MODIFY_CALL:
 	case FTRACE_UPDATE_MAKE_CALL:
 		/* converting nop to call */
 		return add_update_call(rec, ftrace_addr);
@@ -455,12 +522,14 @@ static int finish_update(struct dyn_ftrace *rec, int enable)
 
 	ret = ftrace_update_record(rec, enable);
 
-	ftrace_addr = (unsigned long)FTRACE_ADDR;
+	ftrace_addr = get_ftrace_addr(rec);
 
 	switch (ret) {
 	case FTRACE_UPDATE_IGNORE:
 		return 0;
 
+	case FTRACE_UPDATE_MODIFY_CALL_REGS:
+	case FTRACE_UPDATE_MODIFY_CALL:
 	case FTRACE_UPDATE_MAKE_CALL:
 		/* converting nop to call */
 		return finish_update_call(rec, ftrace_addr);