[PATCH 3/5][RFC] ftrace: Return pt_regs to function trace callback (x86_64 only so
From: Steven Rostedt
Date: Wed Aug 10 2011 - 12:31:10 EST
From: Steven Rostedt <srostedt@xxxxxxxxxx>
Return as the 4th paramater to the function tracer callback the pt_regs.
So far this is only supported by x86_64. The ftrace_ops flag
FTRACE_OPS_FL_SAVE_REGS is added to tell the arch to save all regs
to the pt_regs, otherwise a minimum is just passed back (the same
regs that is saved by mcount itself).
Signed-off-by: Steven Rostedt <rostedt@xxxxxxxxxxx>
---
arch/x86/include/asm/ftrace.h | 38 ++++++++++++++++++++----------------
arch/x86/kernel/entry_64.S | 23 +++++++++++++++++++++-
include/linux/ftrace.h | 15 ++++++++++++-
kernel/trace/ftrace.c | 29 ++++++++++++++++++---------
kernel/trace/trace_events.c | 2 +-
kernel/trace/trace_functions.c | 7 +++--
kernel/trace/trace_irqsoff.c | 2 +-
kernel/trace/trace_sched_wakeup.c | 3 +-
kernel/trace/trace_selftest.c | 15 +++++++++----
kernel/trace/trace_stack.c | 3 +-
10 files changed, 95 insertions(+), 42 deletions(-)
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index b3fcf16..0750c2a 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -4,26 +4,29 @@
#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)
+ /*
+ * We add enough stack to save all regs,
+ * and we what we need in the location of pt_regs.
+ */
+ subq $ORIG_RAX, %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)
.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
+ 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 $ORIG_RAX, %rsp
.endm
#endif
@@ -34,6 +37,7 @@
#if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_X86_64)
#define ARCH_SUPPORTS_FTRACE_OPS 1
+#define ARCH_SUPPORTS_FTRACE_SAVE_REGS 1
#endif
#ifndef __ASSEMBLY__
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 27adc2b..b77f297 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -78,7 +78,16 @@ ENTRY(ftrace_caller)
MCOUNT_SAVE_FRAME
leaq function_trace_op, %rdx
- movq 0x38(%rsp), %rdi
+
+ cmpl $0, ftrace_save_regs
+ jne save_all_regs
+
+call_func:
+
+ /* regs go into 4th parameter */
+ leaq (%rsp), %rcx
+
+ movq ORIG_RAX(%rsp), %rdi
movq 8(%rbp), %rsi
subq $MCOUNT_INSN_SIZE, %rdi
@@ -96,6 +105,18 @@ GLOBAL(ftrace_stub)
retq
END(ftrace_caller)
+save_all_regs:
+ /* Save the rest of pt_regs */
+ movq %r15, R15(%rsp)
+ movq %r14, R14(%rsp)
+ movq %r13, R13(%rsp)
+ movq %r12, R12(%rsp)
+ movq %r10, R10(%rsp)
+ movq %rbp, RBP(%rsp)
+ movq %rbx, RBX(%rsp)
+ jmp call_func
+
+
#else /* ! CONFIG_DYNAMIC_FTRACE */
ENTRY(mcount)
cmpl $0, function_trace_stop
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index e1fe5be..14dcc98 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -11,6 +11,7 @@
#include <linux/linkage.h>
#include <linux/bitops.h>
#include <linux/module.h>
+#include <linux/ptrace.h>
#include <linux/ktime.h>
#include <linux/sched.h>
#include <linux/types.h>
@@ -28,6 +29,14 @@
#define ARCH_SUPPORTS_FTRACE_OPS 0
#endif
+/*
+ * If the arch supports saving the regs to the ftrace_ops
+ * then it should set this to 1.
+ */
+#ifndef ARCH_SUPPORTS_FTRACE_SAVE_REGS
+#define ARCH_SUPPORTS_FTRACE_SAVE_REGS 0
+#endif
+
struct ftrace_hash;
#ifdef CONFIG_FUNCTION_TRACER
@@ -41,12 +50,13 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
struct ftrace_ops;
typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
- struct ftrace_ops *op);
+ struct ftrace_ops *op, struct pt_regs *pt_regs);
enum {
FTRACE_OPS_FL_ENABLED = 1 << 0,
FTRACE_OPS_FL_GLOBAL = 1 << 1,
FTRACE_OPS_FL_DYNAMIC = 1 << 2,
+ FTRACE_OPS_FL_SAVE_REGS = 1 << 3,
};
struct ftrace_ops {
@@ -109,7 +119,8 @@ int register_ftrace_function(struct ftrace_ops *ops);
int unregister_ftrace_function(struct ftrace_ops *ops);
void clear_ftrace_function(void);
-extern void ftrace_stub(unsigned long a0, unsigned long a1, struct ftrace_ops *op);
+extern void ftrace_stub(unsigned long a0, unsigned long a1,
+ struct ftrace_ops *op, struct pt_regs *pt_regs);
#else /* !CONFIG_FUNCTION_TRACER */
/*
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 1d720cb..c92f433 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -74,6 +74,9 @@ int function_trace_stop __read_mostly;
/* Current function tracing op */
struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end;
+/* If the arch supports it, return pt_regs to caller */
+int ftrace_save_regs __read_mostly;
+
/* List for set_ftrace_pid's pids. */
LIST_HEAD(ftrace_pids);
struct ftrace_pid {
@@ -98,7 +101,7 @@ ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
static struct ftrace_ops global_ops;
static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
- struct ftrace_ops *op);
+ struct ftrace_ops *op, struct pt_regs *pt_regs);
/*
* Traverse the ftrace_global_list, invoking all entries. The reason that we
@@ -111,7 +114,7 @@ static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
*/
static void
ftrace_global_list_func(unsigned long ip, unsigned long parent_ip,
- struct ftrace_ops *op)
+ struct ftrace_ops *op, struct pt_regs *pt_regs)
{
if (unlikely(trace_recursion_test(TRACE_GLOBAL_BIT)))
return;
@@ -119,19 +122,19 @@ ftrace_global_list_func(unsigned long ip, unsigned long parent_ip,
trace_recursion_set(TRACE_GLOBAL_BIT);
op = rcu_dereference_raw(ftrace_global_list); /*see above*/
while (op != &ftrace_list_end) {
- op->func(ip, parent_ip, op);
+ op->func(ip, parent_ip, op, pt_regs);
op = rcu_dereference_raw(op->next); /*see above*/
};
trace_recursion_clear(TRACE_GLOBAL_BIT);
}
static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
- struct ftrace_ops *op)
+ struct ftrace_ops *op, struct pt_regs *pt_regs)
{
if (!test_tsk_trace_trace(current))
return;
- ftrace_pid_function(ip, parent_ip, op);
+ ftrace_pid_function(ip, parent_ip, op, pt_regs);
}
static void set_ftrace_pid_function(ftrace_func_t func)
@@ -162,12 +165,12 @@ void clear_ftrace_function(void)
* mcount call site, we need to do it from C.
*/
static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip,
- struct ftrace_ops *op)
+ struct ftrace_ops *op, struct pt_regs *pt_regs)
{
if (function_trace_stop)
return;
- __ftrace_trace_function(ip, parent_ip, op);
+ __ftrace_trace_function(ip, parent_ip, op, pt_regs);
}
#endif
@@ -285,6 +288,9 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
if (!core_kernel_data((unsigned long)ops))
ops->flags |= FTRACE_OPS_FL_DYNAMIC;
+ if (ops->flags & FTRACE_OPS_FL_SAVE_REGS)
+ ftrace_save_regs++;
+
if (ops->flags & FTRACE_OPS_FL_GLOBAL) {
int first = ftrace_global_list == &ftrace_list_end;
add_ftrace_ops(&ftrace_global_list, ops);
@@ -313,6 +319,9 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
if (FTRACE_WARN_ON(ops == &global_ops))
return -EINVAL;
+ if (ops->flags & FTRACE_OPS_FL_SAVE_REGS)
+ ftrace_save_regs--;
+
if (ops->flags & FTRACE_OPS_FL_GLOBAL) {
ret = remove_ftrace_ops(&ftrace_global_list, ops);
if (!ret && ftrace_global_list == &ftrace_list_end)
@@ -2527,7 +2536,7 @@ static int __init ftrace_mod_cmd_init(void)
device_initcall(ftrace_mod_cmd_init);
static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip,
- struct ftrace_ops *op)
+ struct ftrace_ops *op, struct pt_regs *pt_regs)
{
struct ftrace_func_probe *entry;
struct hlist_head *hhd;
@@ -3575,7 +3584,7 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip)
static void
ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
- struct ftrace_ops *op)
+ struct ftrace_ops *op, struct pt_regs *pt_regs)
{
if (unlikely(trace_recursion_test(TRACE_INTERNAL_BIT)))
return;
@@ -3589,7 +3598,7 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
op = rcu_dereference_raw(ftrace_ops_list);
while (op != &ftrace_list_end) {
if (ftrace_ops_test(op, ip))
- op->func(ip, parent_ip, op);
+ op->func(ip, parent_ip, op, pt_regs);
op = rcu_dereference_raw(op->next);
};
preempt_enable_notrace();
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index d2a6f94..fe2c1ac 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1674,7 +1674,7 @@ static DEFINE_PER_CPU(atomic_t, ftrace_test_event_disable);
static void
function_test_events_call(unsigned long ip, unsigned long parent_ip,
- struct ftrace_ops *op)
+ struct ftrace_ops *op, struct pt_regs *pt_regs)
{
struct ring_buffer_event *event;
struct ring_buffer *buffer;
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index fceb7a9..5675ebd 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -49,7 +49,7 @@ static void function_trace_start(struct trace_array *tr)
static void
function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip,
- struct ftrace_ops *op)
+ struct ftrace_ops *op, struct pt_regs *pt_regs)
{
struct trace_array *tr = func_trace;
struct trace_array_cpu *data;
@@ -77,7 +77,8 @@ function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip,
static void
function_trace_call(unsigned long ip, unsigned long parent_ip,
- struct ftrace_ops *op)
+ struct ftrace_ops *op, struct pt_regs *pt_regs)
+
{
struct trace_array *tr = func_trace;
struct trace_array_cpu *data;
@@ -109,7 +110,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip,
static void
function_stack_trace_call(unsigned long ip, unsigned long parent_ip,
- struct ftrace_ops *op)
+ struct ftrace_ops *op, struct pt_regs *pt_regs)
{
struct trace_array *tr = func_trace;
struct trace_array_cpu *data;
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 7649609..009b3c4 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -137,7 +137,7 @@ static int func_prolog_dec(struct trace_array *tr,
*/
static void
irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip,
- struct ftrace_ops *op)
+ struct ftrace_ops *op, struct pt_regs *pt_regs)
{
struct trace_array *tr = irqsoff_trace;
struct trace_array_cpu *data;
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index a311bfd..fdafb79 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -108,7 +108,8 @@ out_enable:
* wakeup uses its own tracer function to keep the overhead down:
*/
static void
-wakeup_tracer_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op)
+wakeup_tracer_call(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct pt_regs *pt_regs)
{
struct trace_array *tr = wakeup_trace;
struct trace_array_cpu *data;
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 9ae40c8..add37e0 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -104,7 +104,8 @@ static inline void warn_failed_init_tracer(struct tracer *trace, int init_ret)
static int trace_selftest_test_probe1_cnt;
static void trace_selftest_test_probe1_func(unsigned long ip,
unsigned long pip,
- struct ftrace_ops *op)
+ struct ftrace_ops *op,
+ struct pt_regs *pt_regs)
{
trace_selftest_test_probe1_cnt++;
}
@@ -112,7 +113,8 @@ static void trace_selftest_test_probe1_func(unsigned long ip,
static int trace_selftest_test_probe2_cnt;
static void trace_selftest_test_probe2_func(unsigned long ip,
unsigned long pip,
- struct ftrace_ops *op)
+ struct ftrace_ops *op,
+ struct pt_regs *pt_regs)
{
trace_selftest_test_probe2_cnt++;
}
@@ -120,7 +122,8 @@ static void trace_selftest_test_probe2_func(unsigned long ip,
static int trace_selftest_test_probe3_cnt;
static void trace_selftest_test_probe3_func(unsigned long ip,
unsigned long pip,
- struct ftrace_ops *op)
+ struct ftrace_ops *op,
+ struct pt_regs *pt_regs)
{
trace_selftest_test_probe3_cnt++;
}
@@ -128,7 +131,8 @@ static void trace_selftest_test_probe3_func(unsigned long ip,
static int trace_selftest_test_global_cnt;
static void trace_selftest_test_global_func(unsigned long ip,
unsigned long pip,
- struct ftrace_ops *op)
+ struct ftrace_ops *op,
+ struct pt_regs *pt_regs)
{
trace_selftest_test_global_cnt++;
}
@@ -136,7 +140,8 @@ static void trace_selftest_test_global_func(unsigned long ip,
static int trace_selftest_test_dyn_cnt;
static void trace_selftest_test_dyn_func(unsigned long ip,
unsigned long pip,
- struct ftrace_ops *op)
+ struct ftrace_ops *op,
+ struct pt_regs *pt_regs)
{
trace_selftest_test_dyn_cnt++;
}
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 456f262..d22ba11 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -108,7 +108,8 @@ static inline void check_stack(void)
}
static void
-stack_trace_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op)
+stack_trace_call(unsigned long ip, unsigned long parent_ip,
+ struct ftrace_ops *op, struct pt_regs *pt_regs)
{
int cpu;
--
1.7.5.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/