linux_old1/kernel/trace/trace_syscalls.c

457 lines
10 KiB
C
Raw Normal View History

tracing/syscalls: use a dedicated file header Impact: fix build warnings and possibe compat misbehavior on IA64 Building a kernel on ia64 might trigger these ugly build warnings: CC arch/ia64/ia32/sys_ia32.o In file included from arch/ia64/ia32/sys_ia32.c:55: arch/ia64/ia32/ia32priv.h:290:1: warning: "elf_check_arch" redefined In file included from include/linux/elf.h:7, from include/linux/module.h:14, from include/linux/ftrace.h:8, from include/linux/syscalls.h:68, from arch/ia64/ia32/sys_ia32.c:18: arch/ia64/include/asm/elf.h:19:1: warning: this is the location of the previous definition [...] sys_ia32.c includes linux/syscalls.h which in turn includes linux/ftrace.h to import the syscalls tracing prototypes. But including ftrace.h can pull too much things for a low level file, especially on ia64 where the ia32 private headers conflict with higher level headers. Now we isolate the syscall tracing headers in their own lightweight file. Reported-by: Tony Luck <tony.luck@intel.com> Tested-by: Tony Luck <tony.luck@intel.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Tony Luck <tony.luck@intel.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Jason Baron <jbaron@redhat.com> Cc: "Frank Ch. Eigler" <fche@redhat.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Jiaying Zhang <jiayingz@google.com> Cc: Michael Rubin <mrubin@google.com> Cc: Martin Bligh <mbligh@google.com> Cc: Michael Davidson <md@google.com> LKML-Reference: <20090408184058.GB6017@nowhere> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-04-09 02:40:59 +08:00
#include <trace/syscall.h>
#include <linux/kernel.h>
#include <linux/ftrace.h>
#include <linux/perf_counter.h>
#include <asm/syscall.h>
#include "trace_output.h"
#include "trace.h"
static DEFINE_MUTEX(syscall_trace_lock);
static int sys_refcount_enter;
static int sys_refcount_exit;
static DECLARE_BITMAP(enabled_enter_syscalls, FTRACE_SYSCALL_MAX);
static DECLARE_BITMAP(enabled_exit_syscalls, FTRACE_SYSCALL_MAX);
/* Option to display the parameters types */
enum {
TRACE_SYSCALLS_OPT_TYPES = 0x1,
};
static struct tracer_opt syscalls_opts[] = {
{ TRACER_OPT(syscall_arg_type, TRACE_SYSCALLS_OPT_TYPES) },
{ }
};
static struct tracer_flags syscalls_flags = {
.val = 0, /* By default: no parameters types */
.opts = syscalls_opts
};
enum print_line_t
print_syscall_enter(struct trace_iterator *iter, int flags)
{
struct trace_seq *s = &iter->seq;
struct trace_entry *ent = iter->ent;
struct syscall_trace_enter *trace;
struct syscall_metadata *entry;
int i, ret, syscall;
trace = (typeof(trace))ent;
syscall = trace->nr;
entry = syscall_nr_to_meta(syscall);
if (!entry)
goto end;
if (entry->enter_id != ent->type) {
WARN_ON_ONCE(1);
goto end;
}
ret = trace_seq_printf(s, "%s(", entry->name);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
for (i = 0; i < entry->nb_args; i++) {
/* parameter types */
if (syscalls_flags.val & TRACE_SYSCALLS_OPT_TYPES) {
ret = trace_seq_printf(s, "%s ", entry->types[i]);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
}
/* parameter values */
ret = trace_seq_printf(s, "%s: %lx%s ", entry->args[i],
trace->args[i],
i == entry->nb_args - 1 ? ")" : ",");
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
}
end:
trace_seq_printf(s, "\n");
return TRACE_TYPE_HANDLED;
}
enum print_line_t
print_syscall_exit(struct trace_iterator *iter, int flags)
{
struct trace_seq *s = &iter->seq;
struct trace_entry *ent = iter->ent;
struct syscall_trace_exit *trace;
int syscall;
struct syscall_metadata *entry;
int ret;
trace = (typeof(trace))ent;
syscall = trace->nr;
entry = syscall_nr_to_meta(syscall);
if (!entry) {
trace_seq_printf(s, "\n");
return TRACE_TYPE_HANDLED;
}
if (entry->exit_id != ent->type) {
WARN_ON_ONCE(1);
return TRACE_TYPE_UNHANDLED;
}
ret = trace_seq_printf(s, "%s -> 0x%lx\n", entry->name,
trace->ret);
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
return TRACE_TYPE_HANDLED;
}
int ftrace_format_syscall(struct ftrace_event_call *call, struct trace_seq *s)
{
int i;
int nr;
int ret = 0;
struct syscall_metadata *entry;
int offset = sizeof(struct trace_entry);
nr = syscall_name_to_nr((char *)call->data);
entry = syscall_nr_to_meta(nr);
if (!entry)
return ret;
for (i = 0; i < entry->nb_args; i++) {
ret = trace_seq_printf(s, "\tfield:%s %s;", entry->types[i],
entry->args[i]);
if (!ret)
return 0;
ret = trace_seq_printf(s, "\toffset:%d;\tsize:%lu;\n", offset,
sizeof(unsigned long));
if (!ret)
return 0;
offset += sizeof(unsigned long);
}
trace_seq_printf(s, "\nprint fmt: \"");
for (i = 0; i < entry->nb_args; i++) {
ret = trace_seq_printf(s, "%s: 0x%%0%lulx%s", entry->args[i],
sizeof(unsigned long),
i == entry->nb_args - 1 ? "\", " : ", ");
if (!ret)
return 0;
}
for (i = 0; i < entry->nb_args; i++) {
ret = trace_seq_printf(s, "((unsigned long)(REC->%s))%s",
entry->args[i],
i == entry->nb_args - 1 ? "\n" : ", ");
if (!ret)
return 0;
}
return ret;
}
void ftrace_syscall_enter(struct pt_regs *regs, long id)
{
struct syscall_trace_enter *entry;
struct syscall_metadata *sys_data;
struct ring_buffer_event *event;
int size;
int syscall_nr;
syscall_nr = syscall_get_nr(current, regs);
if (!test_bit(syscall_nr, enabled_enter_syscalls))
return;
sys_data = syscall_nr_to_meta(syscall_nr);
if (!sys_data)
return;
size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
event = trace_current_buffer_lock_reserve(sys_data->enter_id, size,
0, 0);
if (!event)
return;
entry = ring_buffer_event_data(event);
entry->nr = syscall_nr;
syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args);
trace_current_buffer_unlock_commit(event, 0, 0);
trace_wake_up();
}
void ftrace_syscall_exit(struct pt_regs *regs, long ret)
{
struct syscall_trace_exit *entry;
struct syscall_metadata *sys_data;
struct ring_buffer_event *event;
int syscall_nr;
syscall_nr = syscall_get_nr(current, regs);
if (!test_bit(syscall_nr, enabled_exit_syscalls))
return;
sys_data = syscall_nr_to_meta(syscall_nr);
if (!sys_data)
return;
event = trace_current_buffer_lock_reserve(sys_data->exit_id,
sizeof(*entry), 0, 0);
if (!event)
return;
entry = ring_buffer_event_data(event);
entry->nr = syscall_nr;
entry->ret = syscall_get_return_value(current, regs);
trace_current_buffer_unlock_commit(event, 0, 0);
trace_wake_up();
}
int reg_event_syscall_enter(void *ptr)
{
int ret = 0;
int num;
char *name;
name = (char *)ptr;
num = syscall_name_to_nr(name);
if (num < 0 || num >= FTRACE_SYSCALL_MAX)
return -ENOSYS;
mutex_lock(&syscall_trace_lock);
if (!sys_refcount_enter)
ret = register_trace_syscall_enter(ftrace_syscall_enter);
if (ret) {
pr_info("event trace: Could not activate"
"syscall entry trace point");
} else {
set_bit(num, enabled_enter_syscalls);
sys_refcount_enter++;
}
mutex_unlock(&syscall_trace_lock);
return ret;
}
void unreg_event_syscall_enter(void *ptr)
{
int num;
char *name;
name = (char *)ptr;
num = syscall_name_to_nr(name);
if (num < 0 || num >= FTRACE_SYSCALL_MAX)
return;
mutex_lock(&syscall_trace_lock);
sys_refcount_enter--;
clear_bit(num, enabled_enter_syscalls);
if (!sys_refcount_enter)
unregister_trace_syscall_enter(ftrace_syscall_enter);
mutex_unlock(&syscall_trace_lock);
}
int reg_event_syscall_exit(void *ptr)
{
int ret = 0;
int num;
char *name;
name = (char *)ptr;
num = syscall_name_to_nr(name);
if (num < 0 || num >= FTRACE_SYSCALL_MAX)
return -ENOSYS;
mutex_lock(&syscall_trace_lock);
if (!sys_refcount_exit)
ret = register_trace_syscall_exit(ftrace_syscall_exit);
if (ret) {
pr_info("event trace: Could not activate"
"syscall exit trace point");
} else {
set_bit(num, enabled_exit_syscalls);
sys_refcount_exit++;
}
mutex_unlock(&syscall_trace_lock);
return ret;
}
void unreg_event_syscall_exit(void *ptr)
{
int num;
char *name;
name = (char *)ptr;
num = syscall_name_to_nr(name);
if (num < 0 || num >= FTRACE_SYSCALL_MAX)
return;
mutex_lock(&syscall_trace_lock);
sys_refcount_exit--;
clear_bit(num, enabled_exit_syscalls);
if (!sys_refcount_exit)
unregister_trace_syscall_exit(ftrace_syscall_exit);
mutex_unlock(&syscall_trace_lock);
}
struct trace_event event_syscall_enter = {
.trace = print_syscall_enter,
};
struct trace_event event_syscall_exit = {
.trace = print_syscall_exit,
};
#ifdef CONFIG_EVENT_PROFILE
2009-08-12 02:22:53 +08:00
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;
static int sys_prof_refcount_exit;
static void prof_syscall_enter(struct pt_regs *regs, long id)
{
2009-08-12 02:22:53 +08:00
struct syscall_enter_record *rec;
struct syscall_metadata *sys_data;
int syscall_nr;
2009-08-12 02:22:53 +08:00
int size;
syscall_nr = syscall_get_nr(current, regs);
if (!test_bit(syscall_nr, enabled_prof_enter_syscalls))
return;
sys_data = syscall_nr_to_meta(syscall_nr);
if (!sys_data)
return;
2009-08-12 02:22:53 +08:00
/* 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)
{
int ret = 0;
int num;
num = syscall_name_to_nr(name);
if (num < 0 || num >= FTRACE_SYSCALL_MAX)
return -ENOSYS;
mutex_lock(&syscall_trace_lock);
if (!sys_prof_refcount_enter)
ret = register_trace_syscall_enter(prof_syscall_enter);
if (ret) {
pr_info("event trace: Could not activate"
"syscall entry trace point");
} else {
set_bit(num, enabled_prof_enter_syscalls);
sys_prof_refcount_enter++;
}
mutex_unlock(&syscall_trace_lock);
return ret;
}
void unreg_prof_syscall_enter(char *name)
{
int num;
num = syscall_name_to_nr(name);
if (num < 0 || num >= FTRACE_SYSCALL_MAX)
return;
mutex_lock(&syscall_trace_lock);
sys_prof_refcount_enter--;
clear_bit(num, enabled_prof_enter_syscalls);
if (!sys_prof_refcount_enter)
unregister_trace_syscall_enter(prof_syscall_enter);
mutex_unlock(&syscall_trace_lock);
}
static void prof_syscall_exit(struct pt_regs *regs, long ret)
{
struct syscall_metadata *sys_data;
2009-08-12 02:22:53 +08:00
struct syscall_exit_record rec;
int syscall_nr;
syscall_nr = syscall_get_nr(current, regs);
if (!test_bit(syscall_nr, enabled_prof_exit_syscalls))
return;
sys_data = syscall_nr_to_meta(syscall_nr);
if (!sys_data)
return;
2009-08-12 02:22:53 +08:00
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)
{
int ret = 0;
int num;
num = syscall_name_to_nr(name);
if (num < 0 || num >= FTRACE_SYSCALL_MAX)
return -ENOSYS;
mutex_lock(&syscall_trace_lock);
if (!sys_prof_refcount_exit)
ret = register_trace_syscall_exit(prof_syscall_exit);
if (ret) {
pr_info("event trace: Could not activate"
"syscall entry trace point");
} else {
set_bit(num, enabled_prof_exit_syscalls);
sys_prof_refcount_exit++;
}
mutex_unlock(&syscall_trace_lock);
return ret;
}
void unreg_prof_syscall_exit(char *name)
{
int num;
num = syscall_name_to_nr(name);
if (num < 0 || num >= FTRACE_SYSCALL_MAX)
return;
mutex_lock(&syscall_trace_lock);
sys_prof_refcount_exit--;
clear_bit(num, enabled_prof_exit_syscalls);
if (!sys_prof_refcount_exit)
unregister_trace_syscall_exit(prof_syscall_exit);
mutex_unlock(&syscall_trace_lock);
}
#endif