/*
- * kprobe based kernel tracer
+ * Kprobes-based tracing events
*
* Created by Masami Hiramatsu <mhiramat@redhat.com>
*
#define MAX_EVENT_NAME_LEN 64
#define KPROBE_EVENT_SYSTEM "kprobes"
-/* currently, trace_kprobe only supports X86. */
+/* Reserved field names */
+#define FIELD_STRING_IP "__probe_ip"
+#define FIELD_STRING_NARGS "__probe_nargs"
+#define FIELD_STRING_RETIP "__probe_ret_ip"
+#define FIELD_STRING_FUNC "__probe_func"
+
+const char *reserved_field_names[] = {
+ "common_type",
+ "common_flags",
+ "common_preempt_count",
+ "common_pid",
+ "common_tgid",
+ "common_lock_depth",
+ FIELD_STRING_IP,
+ FIELD_STRING_NARGS,
+ FIELD_STRING_RETIP,
+ FIELD_STRING_FUNC,
+};
struct fetch_func {
unsigned long (*func)(struct pt_regs *, void *);
}
/**
- * Kprobe tracer core functions
+ * Kprobe event core functions
*/
struct probe_arg {
kfree(tp);
}
-static struct trace_probe *find_probe_event(const char *event)
+static struct trace_probe *find_probe_event(const char *event,
+ const char *group)
{
struct trace_probe *tp;
list_for_each_entry(tp, &probe_list, list)
- if (!strcmp(tp->call.name, event))
+ if (strcmp(tp->call.name, event) == 0 &&
+ strcmp(tp->call.system, group) == 0)
return tp;
return NULL;
}
mutex_lock(&probe_lock);
/* register as an event */
- old_tp = find_probe_event(tp->call.name);
+ old_tp = find_probe_event(tp->call.name, tp->call.system);
if (old_tp) {
/* delete old event */
unregister_trace_probe(old_tp);
return ret;
}
+/* Return 1 if name is reserved or already used by another argument */
+static int conflict_field_name(const char *name,
+ struct probe_arg *args, int narg)
+{
+ int i;
+ for (i = 0; i < ARRAY_SIZE(reserved_field_names); i++)
+ if (strcmp(reserved_field_names[i], name) == 0)
+ return 1;
+ for (i = 0; i < narg; i++)
+ if (strcmp(args[i].name, name) == 0)
+ return 1;
+ return 0;
+}
+
static int create_trace_probe(int argc, char **argv)
{
/*
void *addr = NULL;
char buf[MAX_EVENT_NAME_LEN];
- if (argc < 2)
+ if (argc < 2) {
+ pr_info("Probe point is not specified.\n");
return -EINVAL;
+ }
if (argv[0][0] == 'p')
is_return = 0;
else if (argv[0][0] == 'r')
is_return = 1;
- else
+ else {
+ pr_info("Probe definition must be started with 'p' or 'r'.\n");
return -EINVAL;
+ }
if (argv[0][1] == ':') {
event = &argv[0][2];
}
if (isdigit(argv[1][0])) {
- if (is_return)
+ if (is_return) {
+ pr_info("Return probe point must be a symbol.\n");
return -EINVAL;
+ }
/* an address specified */
ret = strict_strtoul(&argv[0][2], 0, (unsigned long *)&addr);
- if (ret)
+ if (ret) {
+ pr_info("Failed to parse address.\n");
return ret;
+ }
} else {
/* a symbol specified */
symbol = argv[1];
/* TODO: support .init module functions */
ret = split_symbol_offset(symbol, &offset);
- if (ret)
+ if (ret) {
+ pr_info("Failed to parse symbol.\n");
return ret;
- if (offset && is_return)
+ }
+ if (offset && is_return) {
+ pr_info("Return probe must be used without offset.\n");
return -EINVAL;
+ }
}
argc -= 2; argv += 2;
}
tp = alloc_trace_probe(group, event, addr, symbol, offset, argc,
is_return);
- if (IS_ERR(tp))
+ if (IS_ERR(tp)) {
+ pr_info("Failed to allocate trace_probe.(%d)\n",
+ (int)PTR_ERR(tp));
return PTR_ERR(tp);
+ }
/* parse arguments */
ret = 0;
*arg++ = '\0';
else
arg = argv[i];
+
+ if (conflict_field_name(argv[i], tp->args, i)) {
+ pr_info("Argument%d name '%s' conflicts with "
+ "another field.\n", i, argv[i]);
+ ret = -EINVAL;
+ goto error;
+ }
+
tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
/* Parse fetch argument */
goto error;
}
ret = parse_probe_arg(arg, &tp->args[i].fetch, is_return);
- if (ret)
+ if (ret) {
+ pr_info("Parse error at argument%d. (%d)\n", i, ret);
goto error;
+ }
}
tp->nr_args = i;
if (!ret)
return ret;
- DEFINE_FIELD(unsigned long, ip, "ip", 0);
- DEFINE_FIELD(int, nargs, "nargs", 1);
+ DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
+ DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1);
/* Set argument names as fields */
for (i = 0; i < tp->nr_args; i++)
DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0);
if (!ret)
return ret;
- DEFINE_FIELD(unsigned long, func, "func", 0);
- DEFINE_FIELD(unsigned long, ret_ip, "ret_ip", 0);
- DEFINE_FIELD(int, nargs, "nargs", 1);
+ DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0);
+ DEFINE_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP, 0);
+ DEFINE_FIELD(int, nargs, FIELD_STRING_NARGS, 1);
/* Set argument names as fields */
for (i = 0; i < tp->nr_args; i++)
DEFINE_FIELD(unsigned long, args[i], tp->args[i].name, 0);
int ret, i;
struct trace_probe *tp = (struct trace_probe *)call->data;
- SHOW_FIELD(unsigned long, ip, "ip");
- SHOW_FIELD(int, nargs, "nargs");
+ SHOW_FIELD(unsigned long, ip, FIELD_STRING_IP);
+ SHOW_FIELD(int, nargs, FIELD_STRING_NARGS);
/* Show fields */
for (i = 0; i < tp->nr_args; i++)
SHOW_FIELD(unsigned long, args[i], tp->args[i].name);
trace_seq_puts(s, "\n");
- return __probe_event_show_format(s, tp, "(%lx)", "REC->ip");
+ return __probe_event_show_format(s, tp, "(%lx)",
+ "REC->" FIELD_STRING_IP);
}
static int kretprobe_event_show_format(struct ftrace_event_call *call,
int ret, i;
struct trace_probe *tp = (struct trace_probe *)call->data;
- SHOW_FIELD(unsigned long, func, "func");
- SHOW_FIELD(unsigned long, ret_ip, "ret_ip");
- SHOW_FIELD(int, nargs, "nargs");
+ SHOW_FIELD(unsigned long, func, FIELD_STRING_FUNC);
+ SHOW_FIELD(unsigned long, ret_ip, FIELD_STRING_RETIP);
+ SHOW_FIELD(int, nargs, FIELD_STRING_NARGS);
/* Show fields */
for (i = 0; i < tp->nr_args; i++)
trace_seq_puts(s, "\n");
return __probe_event_show_format(s, tp, "(%lx <- %lx)",
- "REC->func, REC->ret_ip");
+ "REC->" FIELD_STRING_FUNC
+ ", REC->" FIELD_STRING_RETIP);
}
#ifdef CONFIG_EVENT_PROFILE
struct trace_entry *ent;
int size, __size, i, pc, __cpu;
unsigned long irq_flags;
+ char *trace_buf;
char *raw_data;
+ int rctx;
pc = preempt_count();
__size = SIZEOF_KPROBE_TRACE_ENTRY(tp->nr_args);
* This also protects the rcu read side
*/
local_irq_save(irq_flags);
+
+ rctx = perf_swevent_get_recursion_context();
+ if (rctx < 0)
+ goto end_recursion;
+
__cpu = smp_processor_id();
if (in_nmi())
- raw_data = rcu_dereference(trace_profile_buf_nmi);
+ trace_buf = rcu_dereference(perf_trace_buf_nmi);
else
- raw_data = rcu_dereference(trace_profile_buf);
+ trace_buf = rcu_dereference(perf_trace_buf);
- if (!raw_data)
+ if (!trace_buf)
goto end;
- raw_data = per_cpu_ptr(raw_data, __cpu);
+ raw_data = per_cpu_ptr(trace_buf, __cpu);
+
/* Zero dead bytes from alignment to avoid buffer leak to userspace */
*(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
entry = (struct kprobe_trace_entry *)raw_data;
for (i = 0; i < tp->nr_args; i++)
entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
perf_tp_event(call->id, entry->ip, 1, entry, size);
+
end:
+ perf_swevent_put_recursion_context(rctx);
+end_recursion:
local_irq_restore(irq_flags);
+
return 0;
}
struct trace_entry *ent;
int size, __size, i, pc, __cpu;
unsigned long irq_flags;
+ char *trace_buf;
char *raw_data;
+ int rctx;
pc = preempt_count();
__size = SIZEOF_KRETPROBE_TRACE_ENTRY(tp->nr_args);
* This also protects the rcu read side
*/
local_irq_save(irq_flags);
+
+ rctx = perf_swevent_get_recursion_context();
+ if (rctx < 0)
+ goto end_recursion;
+
__cpu = smp_processor_id();
if (in_nmi())
- raw_data = rcu_dereference(trace_profile_buf_nmi);
+ trace_buf = rcu_dereference(perf_trace_buf_nmi);
else
- raw_data = rcu_dereference(trace_profile_buf);
+ trace_buf = rcu_dereference(perf_trace_buf);
- if (!raw_data)
+ if (!trace_buf)
goto end;
- raw_data = per_cpu_ptr(raw_data, __cpu);
+ raw_data = per_cpu_ptr(trace_buf, __cpu);
+
/* Zero dead bytes from alignment to avoid buffer leak to userspace */
*(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
entry = (struct kretprobe_trace_entry *)raw_data;
for (i = 0; i < tp->nr_args; i++)
entry->args[i] = call_fetch(&tp->args[i].fetch, regs);
perf_tp_event(call->id, entry->ret_ip, 1, entry, size);
+
end:
+ perf_swevent_put_recursion_context(rctx);
+end_recursion:
local_irq_restore(irq_flags);
+
return 0;
}
pr_info("Testing kprobe tracing: ");
ret = command_trace_probe("p:testprobe kprobe_trace_selftest_target "
- "a1 a2 a3 a4 a5 a6");
+ "$arg1 $arg2 $arg3 $arg4 $stack $stack0");
if (WARN_ON_ONCE(ret))
pr_warning("error enabling function entry\n");
ret = command_trace_probe("r:testprobe2 kprobe_trace_selftest_target "
- "ra rv");
+ "$retval");
if (WARN_ON_ONCE(ret))
pr_warning("error enabling function return\n");