Hi,
Here is the stacktrace support with dynamic event tracer.
This series also includes save_stack_trace_regs() API
cleanup and an weak symbol for the arch which doesn't
support it.
Thank you,
---
Masami Hiramatsu (3):
[BUGFIX]tracing/kprobes: Fix kprobe-tracer to support stack trace
Add weak save_stack_trace_regs()
[CLEANUP]x86: Swap save_stack_trace_regs parameters
arch/x86/kernel/stacktrace.c | 2 +-
arch/x86/mm/kmemcheck/error.c | 2 +-
include/linux/ftrace_event.h | 4 ++++
include/linux/stacktrace.h | 4 ++--
kernel/stacktrace.c | 13 ++++++++++---
kernel/trace/trace.c | 35 ++++++++++++++++++++++++++++++-----
kernel/trace/trace.h | 9 +++++++++
kernel/trace/trace_kprobe.c | 6 ++++--
8 files changed, 61 insertions(+), 14 deletions(-)
--
Masami HIRAMATSU
Software Platform Research Dept. Linux Technology Center
Hitachi, Ltd., Yokohama Research Laboratory
E-mail: [email protected]
Swap the 1st and 2nd parameters of save_stack_trace_regs()
as same as the parameters of save_stack_trace_tsk().
Signed-off-by: Masami Hiramatsu <[email protected]>
Cc: Steven Rostedt <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: [email protected]
---
arch/x86/kernel/stacktrace.c | 2 +-
arch/x86/mm/kmemcheck/error.c | 2 +-
include/linux/stacktrace.h | 4 ++--
3 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 55d9bc0..fdd0c64 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -66,7 +66,7 @@ void save_stack_trace(struct stack_trace *trace)
}
EXPORT_SYMBOL_GPL(save_stack_trace);
-void save_stack_trace_regs(struct stack_trace *trace, struct pt_regs *regs)
+void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
{
dump_trace(current, regs, NULL, 0, &save_stack_ops, trace);
if (trace->nr_entries < trace->max_entries)
diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c
index 704a37c..dab4187 100644
--- a/arch/x86/mm/kmemcheck/error.c
+++ b/arch/x86/mm/kmemcheck/error.c
@@ -185,7 +185,7 @@ void kmemcheck_error_save(enum kmemcheck_shadow state,
e->trace.entries = e->trace_entries;
e->trace.max_entries = ARRAY_SIZE(e->trace_entries);
e->trace.skip = 0;
- save_stack_trace_regs(&e->trace, regs);
+ save_stack_trace_regs(regs, &e->trace);
/* Round address down to nearest 16 bytes */
shadow_copy = kmemcheck_shadow_lookup(address
diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h
index 25310f1..115b570 100644
--- a/include/linux/stacktrace.h
+++ b/include/linux/stacktrace.h
@@ -14,8 +14,8 @@ struct stack_trace {
};
extern void save_stack_trace(struct stack_trace *trace);
-extern void save_stack_trace_regs(struct stack_trace *trace,
- struct pt_regs *regs);
+extern void save_stack_trace_regs(struct pt_regs *regs,
+ struct stack_trace *trace);
extern void save_stack_trace_tsk(struct task_struct *tsk,
struct stack_trace *trace);
Add weak symbol of save_stack_trace_regs() as same as
save_stack_trace_tsk() since that is not implemented
except x86 yet.
Signed-off-by: Masami Hiramatsu <[email protected]>
Cc: Steven Rostedt <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: [email protected]
---
kernel/stacktrace.c | 13 ++++++++++---
1 files changed, 10 insertions(+), 3 deletions(-)
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index eb212f8..6fa38bc 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -26,12 +26,19 @@ void print_stack_trace(struct stack_trace *trace, int spaces)
EXPORT_SYMBOL_GPL(print_stack_trace);
/*
- * Architectures that do not implement save_stack_trace_tsk get this
- * weak alias and a once-per-bootup warning (whenever this facility
- * is utilized - for example by procfs):
+ * Architectures that do not implement save_stack_trace_tsk or
+ * save_stack_trace_regs get this weak alias and a once-per-bootup warning
+ * (whenever this facility is utilized - for example by procfs):
*/
__weak void
save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
{
WARN_ONCE(1, KERN_INFO "save_stack_trace_tsk() not implemented yet.\n");
}
+
+__weak void
+save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
+{
+ WARN_ONCE(1,
+ KERN_INFO "save_stack_trace_regs() not implemented yet.\n");
+}
Fix to support kernel stack trace correctly on kprobe-tracer.
Since the execution path of kprobe-based dynamic events is different
from other tracepoint-based events, normal ftrace_trace_stack() doesn't
work correctly. To fix that, this introduces ftrace_trace_stack_regs()
which traces stack via pt_regs instead of current stack register.
e.g.
# echo p schedule+4 > /sys/kernel/debug/tracing/kprobe_events
# echo 1 > /sys/kernel/debug/tracing/options/stacktrace
# echo 1 > /sys/kernel/debug/tracing/events/kprobes/enable
# head -n 20 /sys/kernel/debug/tracing/trace
# tracer: nop
#
# TASK-PID CPU# TIMESTAMP FUNCTION
# | | | | |
bash-2968 [000] 10297.050245: p_schedule_4: (schedule+0x4/0x4ca)
bash-2968 [000] 10297.050247: <stack trace>
=> schedule_timeout
=> n_tty_read
=> tty_read
=> vfs_read
=> sys_read
=> system_call_fastpath
kworker/0:1-2940 [000] 10297.050265: p_schedule_4: (schedule+0x4/0x4ca)
kworker/0:1-2940 [000] 10297.050266: <stack trace>
=> worker_thread
=> kthread
=> kernel_thread_helper
sshd-1132 [000] 10297.050365: p_schedule_4: (schedule+0x4/0x4ca)
sshd-1132 [000] 10297.050365: <stack trace>
=> sysret_careful
Note: Even with this fix, the first entry will be skipped
if the probe is put on the function entry area before
the frame pointer is set up (usually, that is 4 bytes
(push %bp; mov %sp %bp) on x86), because stack unwinder
depends on the frame pointer.
Signed-off-by: Masami Hiramatsu <[email protected]>
Cc: Steven Rostedt <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: [email protected]
---
include/linux/ftrace_event.h | 4 ++++
kernel/trace/trace.c | 35 ++++++++++++++++++++++++++++++-----
kernel/trace/trace.h | 9 +++++++++
kernel/trace/trace_kprobe.c | 6 ++++--
4 files changed, 47 insertions(+), 7 deletions(-)
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 59d3ef1..b1e69ee 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -129,6 +129,10 @@ void trace_current_buffer_unlock_commit(struct ring_buffer *buffer,
void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer,
struct ring_buffer_event *event,
unsigned long flags, int pc);
+void trace_nowake_buffer_unlock_commit_regs(struct ring_buffer *buffer,
+ struct ring_buffer_event *event,
+ unsigned long flags, int pc,
+ struct pt_regs *regs);
void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
struct ring_buffer_event *event);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index ee9c921..67856d5 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1191,6 +1191,18 @@ void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer,
}
EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit);
+void trace_nowake_buffer_unlock_commit_regs(struct ring_buffer *buffer,
+ struct ring_buffer_event *event,
+ unsigned long flags, int pc,
+ struct pt_regs *regs)
+{
+ ring_buffer_unlock_commit(buffer, event);
+
+ ftrace_trace_stack_regs(buffer, flags, 0, pc, regs);
+ ftrace_trace_userstack(buffer, flags, pc);
+}
+EXPORT_SYMBOL_GPL(trace_nowake_buffer_unlock_commit_regs);
+
void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
struct ring_buffer_event *event)
{
@@ -1236,7 +1248,7 @@ ftrace(struct trace_array *tr, struct trace_array_cpu *data,
#ifdef CONFIG_STACKTRACE
static void __ftrace_trace_stack(struct ring_buffer *buffer,
unsigned long flags,
- int skip, int pc)
+ int skip, int pc, struct pt_regs *regs)
{
struct ftrace_event_call *call = &event_kernel_stack;
struct ring_buffer_event *event;
@@ -1255,24 +1267,36 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
trace.skip = skip;
trace.entries = entry->caller;
- save_stack_trace(&trace);
+ if (regs)
+ save_stack_trace_regs(regs, &trace);
+ else
+ save_stack_trace(&trace);
if (!filter_check_discard(call, entry, buffer, event))
ring_buffer_unlock_commit(buffer, event);
}
+void ftrace_trace_stack_regs(struct ring_buffer *buffer, unsigned long flags,
+ int skip, int pc, struct pt_regs *regs)
+{
+ if (!(trace_flags & TRACE_ITER_STACKTRACE))
+ return;
+
+ __ftrace_trace_stack(buffer, flags, skip, pc, regs);
+}
+
void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
int skip, int pc)
{
if (!(trace_flags & TRACE_ITER_STACKTRACE))
return;
- __ftrace_trace_stack(buffer, flags, skip, pc);
+ __ftrace_trace_stack(buffer, flags, skip, pc, NULL);
}
void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
int pc)
{
- __ftrace_trace_stack(tr->buffer, flags, skip, pc);
+ __ftrace_trace_stack(tr->buffer, flags, skip, pc, NULL);
}
/**
@@ -1288,7 +1312,8 @@ void trace_dump_stack(void)
local_save_flags(flags);
/* skipping 3 traces, seems to get us at the caller of this function */
- __ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count());
+ __ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count(),
+ NULL);
}
static DEFINE_PER_CPU(int, user_stack_count);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 229f859..caee141 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -389,6 +389,9 @@ void update_max_tr_single(struct trace_array *tr,
void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
int skip, int pc);
+void ftrace_trace_stack_regs(struct ring_buffer *buffer, unsigned long flags,
+ int skip, int pc, struct pt_regs *regs);
+
void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags,
int pc);
@@ -400,6 +403,12 @@ static inline void ftrace_trace_stack(struct ring_buffer *buffer,
{
}
+static inline void ftrace_trace_stack_regs(struct ring_buffer *buffer,
+ unsigned long flags, int skip,
+ int pc, struct pt_regs *regs)
+{
+}
+
static inline void ftrace_trace_userstack(struct ring_buffer *buffer,
unsigned long flags, int pc)
{
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index f925c45..7053ef3 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1397,7 +1397,8 @@ static __kprobes void kprobe_trace_func(struct kprobe *kp, struct pt_regs *regs)
store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
if (!filter_current_check_discard(buffer, call, entry, event))
- trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
+ trace_nowake_buffer_unlock_commit_regs(buffer, event,
+ irq_flags, pc, regs);
}
/* Kretprobe handler */
@@ -1429,7 +1430,8 @@ static __kprobes void kretprobe_trace_func(struct kretprobe_instance *ri,
store_trace_args(sizeof(*entry), tp, regs, (u8 *)&entry[1], dsize);
if (!filter_current_check_discard(buffer, call, entry, event))
- trace_nowake_buffer_unlock_commit(buffer, event, irq_flags, pc);
+ trace_nowake_buffer_unlock_commit_regs(buffer, event,
+ irq_flags, pc, regs);
}
/* Event entry printers */