tracing: Support for syscall events raw records in perfcounters
This bring the support for raw syscall events in perfcounters.
The arguments or exit value are saved as a raw sample using
the PERF_SAMPLE_RAW attribute in a perf counter.
Example (for now you must explicitly set the PERF_SAMPLE_RAW flag
in perf record):
perf record -e syscalls:sys_enter_open -f -F 1 -a
perf report -D
0x2cbb8 [0x50]: event: 9
.
. ... raw event: size 80 bytes
. 0000: 09 00 00 00 02 00 50 00 20 e9 39 ab 0a 7f 00 00 ......P. .9....
. 0010: bc 14 00 00 bc 14 00 00 01 00 00 00 00 00 00 00 ...............
. 0020: 2c 00 00 00 15 01 01 00 bc 14 00 00 bc 14 00 00 ,..............
^ ^ ^ ^ ^ ^ ^ ..........................
Event Size struct trace_entry
. 0030: 00 00 00 00 46 98 43 02 00 00 00 00 80 08 00 00 ....F.C........
^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^
ptr to file name open flags
. 0040: 00 00 00 00 02 00 00 00 00 00 00 00 00 00 00 00 ...............
^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^ ^
. open mode padding
0x2cbb8 [0x50]: PERF_EVENT_SAMPLE (IP, 2): 5308: 0x7f0aab39e920 period: 1
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: Jiaying Zhang <jiayingz@google.com>
Cc: Martin Bligh <mbligh@google.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Jason Baron <jbaron@redhat.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 9ee6386..f837ccc 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -301,6 +301,17 @@
};
#ifdef CONFIG_EVENT_PROFILE
+
+struct syscall_enter_record {
+ struct trace_entry entry;
+ unsigned long args[0];
+};
+
+struct syscall_exit_record {
+ struct trace_entry entry;
+ unsigned long ret;
+};
+
static DECLARE_BITMAP(enabled_prof_enter_syscalls, FTRACE_SYSCALL_MAX);
static DECLARE_BITMAP(enabled_prof_exit_syscalls, FTRACE_SYSCALL_MAX);
static int sys_prof_refcount_enter;
@@ -308,8 +319,10 @@
static void prof_syscall_enter(struct pt_regs *regs, long id)
{
+ struct syscall_enter_record *rec;
struct syscall_metadata *sys_data;
int syscall_nr;
+ int size;
syscall_nr = syscall_get_nr(current, regs);
if (!test_bit(syscall_nr, enabled_prof_enter_syscalls))
@@ -319,7 +332,24 @@
if (!sys_data)
return;
- perf_tpcounter_event(sys_data->enter_id, 0, 1, NULL, 0);
+ /* get the size after alignment with the u32 buffer size field */
+ size = sizeof(unsigned long) * sys_data->nb_args + sizeof(*rec);
+ size = ALIGN(size + sizeof(u32), sizeof(u64));
+ size -= sizeof(u32);
+
+ do {
+ char raw_data[size];
+
+ /* zero the dead bytes from align to not leak stack to user */
+ *(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+
+ rec = (struct syscall_enter_record *) raw_data;
+ tracing_generic_entry_update(&rec->entry, 0, 0);
+ rec->entry.type = sys_data->enter_id;
+ syscall_get_arguments(current, regs, 0, sys_data->nb_args,
+ (unsigned long *)&rec->args);
+ perf_tpcounter_event(sys_data->enter_id, 0, 1, rec, size);
+ } while(0);
}
int reg_prof_syscall_enter(char *name)
@@ -364,6 +394,7 @@
static void prof_syscall_exit(struct pt_regs *regs, long ret)
{
struct syscall_metadata *sys_data;
+ struct syscall_exit_record rec;
int syscall_nr;
syscall_nr = syscall_get_nr(current, regs);
@@ -374,7 +405,11 @@
if (!sys_data)
return;
- perf_tpcounter_event(sys_data->exit_id, 0, 1, NULL, 0);
+ tracing_generic_entry_update(&rec.entry, 0, 0);
+ rec.entry.type = sys_data->exit_id;
+ rec.ret = syscall_get_return_value(current, regs);
+
+ perf_tpcounter_event(sys_data->exit_id, 0, 1, &rec, sizeof(rec));
}
int reg_prof_syscall_exit(char *name)