[RFC][PATCH 03/12] ftrace: Return pt_regs to function trace callback (x86_64 only sofar)

From: Steven Rostedt
Date: Wed Jun 06 2012 - 00:02:43 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. Currently only the regs that
are saved for mcount is stored. The rest of the regs are not defined.

When an arch supports passing the ftrace_ops as the third parameter,
it is also expected to pass regs (or partial regs) as the forth.

If an arch can pass full regs, then it should also define:
ARCH_SUPPORTS_FTRACE_SAVE_REGS to 1

Signed-off-by: Steven Rostedt <rostedt@xxxxxxxxxxx>
---
arch/x86/include/asm/ftrace.h | 40 +++++++++++++++++++++----------------
arch/x86/kernel/entry_64.S | 8 ++++++--
include/linux/ftrace.h | 6 ++++--
kernel/trace/ftrace.c | 37 ++++++++++++++++++++--------------
kernel/trace/trace_event_perf.c | 2 +-
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 ++-
11 files changed, 76 insertions(+), 49 deletions(-)

diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 783b107..1fca3c2 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -4,26 +4,31 @@
#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.
+ */
+ subq $(SS+8), %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
+ 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), %rsp
.endm

#endif
@@ -34,6 +39,7 @@

#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 2b4f94c..08854a9 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -80,7 +80,11 @@ ENTRY(ftrace_caller)
MCOUNT_SAVE_FRAME

leaq function_trace_op, %rdx
- movq 0x38(%rsp), %rdi
+
+ /* regs go into 4th parameter */
+ leaq (%rsp), %rcx
+
+ movq RIP(%rsp), %rdi
movq 8(%rbp), %rsi
subq $MCOUNT_INSN_SIZE, %rdi

@@ -141,7 +145,7 @@ 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/include/linux/ftrace.h b/include/linux/ftrace.h
index 3651fdc..e420288 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -10,6 +10,7 @@
#include <linux/kallsyms.h>
#include <linux/linkage.h>
#include <linux/bitops.h>
+#include <linux/ptrace.h>
#include <linux/ktime.h>
#include <linux/sched.h>
#include <linux/types.h>
@@ -54,7 +55,7 @@ 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 *regs);

/*
* FTRACE_OPS_FL_* bits denote the state of ftrace_ops struct and are
@@ -188,7 +189,8 @@ static inline int ftrace_function_local_disabled(struct ftrace_ops *ops)
return *this_cpu_ptr(ops->disabled);
}

-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 *regs);

#else /* !CONFIG_FUNCTION_TRACER */
/*
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 24654a2..f3c4317 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -104,7 +104,7 @@ static struct ftrace_ops control_ops;
/* See comment below, where ftrace_ops_list_func is defined */
#if ARCH_SUPPORTS_FTRACE_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 *regs);
#else
static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip);
#define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops)
@@ -121,7 +121,7 @@ static void ftrace_ops_no_ops(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 *regs)
{
if (unlikely(trace_recursion_test(TRACE_GLOBAL_BIT)))
return;
@@ -129,19 +129,19 @@ 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, 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 *regs)
{
if (!test_tsk_trace_trace(current))
return;

- ftrace_pid_function(ip, parent_ip, op);
+ ftrace_pid_function(ip, parent_ip, op, regs);
}

static void set_ftrace_pid_function(ftrace_func_t func)
@@ -763,7 +763,7 @@ ftrace_profile_alloc(struct ftrace_profile_stat *stat, unsigned long ip)

static void
function_profile_call(unsigned long ip, unsigned long parent_ip,
- struct ftrace_ops *ops)
+ struct ftrace_ops *ops, struct pt_regs *regs)
{
struct ftrace_profile_stat *stat;
struct ftrace_profile *rec;
@@ -793,7 +793,7 @@ function_profile_call(unsigned long ip, unsigned long parent_ip,
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
static int profile_graph_entry(struct ftrace_graph_ent *trace)
{
- function_profile_call(trace->func, 0, NULL);
+ function_profile_call(trace->func, 0, NULL, NULL);
return 1;
}

@@ -2771,7 +2771,7 @@ 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;
@@ -3923,7 +3923,7 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip)

static void
ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip,
- struct ftrace_ops *op)
+ struct ftrace_ops *op, struct pt_regs *regs)
{
if (unlikely(trace_recursion_test(TRACE_CONTROL_BIT)))
return;
@@ -3938,7 +3938,7 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip,
while (op != &ftrace_list_end) {
if (!ftrace_function_local_disabled(op) &&
ftrace_ops_test(op, ip))
- op->func(ip, parent_ip, op);
+ op->func(ip, parent_ip, op, regs);

op = rcu_dereference_raw(op->next);
};
@@ -3952,7 +3952,7 @@ static struct ftrace_ops control_ops = {

static inline void
__ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
- struct ftrace_ops *ignored)
+ struct ftrace_ops *ignored, struct pt_regs *regs)
{
struct ftrace_ops *op;

@@ -3971,7 +3971,7 @@ __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, regs);
op = rcu_dereference_raw(op->next);
};
preempt_enable_notrace();
@@ -3983,17 +3983,24 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
* the list function ignores the op parameter, we do not want any
* C side effects, where a function is called without the caller
* sending a third parameter.
+ * Archs are to support both the regs and ftrace_ops at the same time.
+ * If they support ftrace_ops, it is assumed they support regs.
+ * If call backs want to use regs, they must either check for regs
+ * being NULL, or ARCH_SUPPORTS_FTRACE_SAVE_REGS.
+ * Note, ARCH_SUPPORT_SAVE_REGS expects a full regs to be saved.
+ * An architecture can pass partial regs with ftrace_ops and still
+ * set the ARCH_SUPPORT_FTARCE_OPS.
*/
#if ARCH_SUPPORTS_FTRACE_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 *regs)
{
- __ftrace_ops_list_func(ip, parent_ip, NULL);
+ __ftrace_ops_list_func(ip, parent_ip, NULL, regs);
}
#else
static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip)
{
- __ftrace_ops_list_func(ip, parent_ip, NULL);
+ __ftrace_ops_list_func(ip, parent_ip, NULL, NULL);
}
#endif

diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index a872a9a..9824419 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -259,7 +259,7 @@ EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
#ifdef CONFIG_FUNCTION_TRACER
static void
perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,
- struct ftrace_ops *ops)
+ struct ftrace_ops *ops, struct pt_regs *pt_regs)
{
struct ftrace_entry *entry;
struct hlist_head *head;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 88daa51..8c66968 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1682,7 +1682,7 @@ 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 2862c77..c7a9ba9 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 0caf4f5..7547e36 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 e20006d..2fa5328 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -111,7 +111,8 @@ 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;

--
1.7.10


--
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/