linux/kernel/trace/trace_syscalls.c
Tejun Heo 5a0e3ad6af include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files.  percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.

percpu.h -> slab.h dependency is about to be removed.  Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability.  As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.

  http://userweb.kernel.org/~tj/misc/slabh-sweep.py

The script does the followings.

* Scan files for gfp and slab usages and update includes such that
  only the necessary includes are there.  ie. if only gfp is used,
  gfp.h, if slab is used, slab.h.

* When the script inserts a new include, it looks at the include
  blocks and try to put the new include such that its order conforms
  to its surrounding.  It's put in the include block which contains
  core kernel includes, in the same order that the rest are ordered -
  alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
  doesn't seem to be any matching order.

* If the script can't find a place to put a new include (mostly
  because the file doesn't have fitting include block), it prints out
  an error message indicating which .h file needs to be added to the
  file.

The conversion was done in the following steps.

1. The initial automatic conversion of all .c files updated slightly
   over 4000 files, deleting around 700 includes and adding ~480 gfp.h
   and ~3000 slab.h inclusions.  The script emitted errors for ~400
   files.

2. Each error was manually checked.  Some didn't need the inclusion,
   some needed manual addition while adding it to implementation .h or
   embedding .c file was more appropriate for others.  This step added
   inclusions to around 150 files.

3. The script was run again and the output was compared to the edits
   from #2 to make sure no file was left behind.

4. Several build tests were done and a couple of problems were fixed.
   e.g. lib/decompress_*.c used malloc/free() wrappers around slab
   APIs requiring slab.h to be added manually.

5. The script was run on all .h files but without automatically
   editing them as sprinkling gfp.h and slab.h inclusions around .h
   files could easily lead to inclusion dependency hell.  Most gfp.h
   inclusion directives were ignored as stuff from gfp.h was usually
   wildly available and often used in preprocessor macros.  Each
   slab.h inclusion directive was examined and added manually as
   necessary.

6. percpu.h was updated not to include slab.h.

7. Build test were done on the following configurations and failures
   were fixed.  CONFIG_GCOV_KERNEL was turned off for all tests (as my
   distributed build env didn't work with gcov compiles) and a few
   more options had to be turned off depending on archs to make things
   build (like ipr on powerpc/64 which failed due to missing writeq).

   * x86 and x86_64 UP and SMP allmodconfig and a custom test config.
   * powerpc and powerpc64 SMP allmodconfig
   * sparc and sparc64 SMP allmodconfig
   * ia64 SMP allmodconfig
   * s390 SMP allmodconfig
   * alpha SMP allmodconfig
   * um on x86_64 SMP allmodconfig

8. percpu.h modifications were reverted so that it could be applied as
   a separate patch and serve as bisection point.

Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.

Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-30 22:02:32 +09:00

585 lines
14 KiB
C

#include <trace/syscall.h>
#include <trace/events/syscalls.h>
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/ftrace.h>
#include <linux/perf_event.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, NR_syscalls);
static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
extern unsigned long __start_syscalls_metadata[];
extern unsigned long __stop_syscalls_metadata[];
static struct syscall_metadata **syscalls_metadata;
static struct syscall_metadata *find_syscall_meta(unsigned long syscall)
{
struct syscall_metadata *start;
struct syscall_metadata *stop;
char str[KSYM_SYMBOL_LEN];
start = (struct syscall_metadata *)__start_syscalls_metadata;
stop = (struct syscall_metadata *)__stop_syscalls_metadata;
kallsyms_lookup(syscall, NULL, NULL, NULL, str);
for ( ; start < stop; start++) {
/*
* Only compare after the "sys" prefix. Archs that use
* syscall wrappers may have syscalls symbols aliases prefixed
* with "SyS" instead of "sys", leading to an unwanted
* mismatch.
*/
if (start->name && !strcmp(start->name + 3, str + 3))
return start;
}
return NULL;
}
static struct syscall_metadata *syscall_nr_to_meta(int nr)
{
if (!syscalls_metadata || nr >= NR_syscalls || nr < 0)
return NULL;
return syscalls_metadata[nr];
}
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_event->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 (trace_flags & TRACE_ITER_VERBOSE) {
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;
}
ret = trace_seq_putc(s, ')');
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
end:
ret = trace_seq_putc(s, '\n');
if (!ret)
return TRACE_TYPE_PARTIAL_LINE;
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_event->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;
}
extern char *__bad_type_size(void);
#define SYSCALL_FIELD(type, name) \
sizeof(type) != sizeof(trace.name) ? \
__bad_type_size() : \
#type, #name, offsetof(typeof(trace), name), \
sizeof(trace.name), is_signed_type(type)
static
int __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len)
{
int i;
int pos = 0;
/* When len=0, we just calculate the needed length */
#define LEN_OR_ZERO (len ? len - pos : 0)
pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
for (i = 0; i < entry->nb_args; i++) {
pos += snprintf(buf + pos, LEN_OR_ZERO, "%s: 0x%%0%zulx%s",
entry->args[i], sizeof(unsigned long),
i == entry->nb_args - 1 ? "" : ", ");
}
pos += snprintf(buf + pos, LEN_OR_ZERO, "\"");
for (i = 0; i < entry->nb_args; i++) {
pos += snprintf(buf + pos, LEN_OR_ZERO,
", ((unsigned long)(REC->%s))", entry->args[i]);
}
#undef LEN_OR_ZERO
/* return the length of print_fmt */
return pos;
}
static int set_syscall_print_fmt(struct ftrace_event_call *call)
{
char *print_fmt;
int len;
struct syscall_metadata *entry = call->data;
if (entry->enter_event != call) {
call->print_fmt = "\"0x%lx\", REC->ret";
return 0;
}
/* First: called with 0 length to calculate the needed length */
len = __set_enter_print_fmt(entry, NULL, 0);
print_fmt = kmalloc(len + 1, GFP_KERNEL);
if (!print_fmt)
return -ENOMEM;
/* Second: actually write the @print_fmt */
__set_enter_print_fmt(entry, print_fmt, len + 1);
call->print_fmt = print_fmt;
return 0;
}
static void free_syscall_print_fmt(struct ftrace_event_call *call)
{
struct syscall_metadata *entry = call->data;
if (entry->enter_event == call)
kfree(call->print_fmt);
}
int syscall_enter_define_fields(struct ftrace_event_call *call)
{
struct syscall_trace_enter trace;
struct syscall_metadata *meta = call->data;
int ret;
int i;
int offset = offsetof(typeof(trace), args);
ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER);
if (ret)
return ret;
for (i = 0; i < meta->nb_args; i++) {
ret = trace_define_field(call, meta->types[i],
meta->args[i], offset,
sizeof(unsigned long), 0,
FILTER_OTHER);
offset += sizeof(unsigned long);
}
return ret;
}
int syscall_exit_define_fields(struct ftrace_event_call *call)
{
struct syscall_trace_exit trace;
int ret;
ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER);
if (ret)
return ret;
ret = trace_define_field(call, SYSCALL_FIELD(long, ret),
FILTER_OTHER);
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;
struct ring_buffer *buffer;
int size;
int syscall_nr;
syscall_nr = syscall_get_nr(current, regs);
if (syscall_nr < 0)
return;
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(&buffer,
sys_data->enter_event->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);
if (!filter_current_check_discard(buffer, sys_data->enter_event,
entry, event))
trace_current_buffer_unlock_commit(buffer, event, 0, 0);
}
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;
struct ring_buffer *buffer;
int syscall_nr;
syscall_nr = syscall_get_nr(current, regs);
if (syscall_nr < 0)
return;
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(&buffer,
sys_data->exit_event->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);
if (!filter_current_check_discard(buffer, sys_data->exit_event,
entry, event))
trace_current_buffer_unlock_commit(buffer, event, 0, 0);
}
int reg_event_syscall_enter(struct ftrace_event_call *call)
{
int ret = 0;
int num;
num = ((struct syscall_metadata *)call->data)->syscall_nr;
if (num < 0 || num >= NR_syscalls)
return -ENOSYS;
mutex_lock(&syscall_trace_lock);
if (!sys_refcount_enter)
ret = register_trace_sys_enter(ftrace_syscall_enter);
if (!ret) {
set_bit(num, enabled_enter_syscalls);
sys_refcount_enter++;
}
mutex_unlock(&syscall_trace_lock);
return ret;
}
void unreg_event_syscall_enter(struct ftrace_event_call *call)
{
int num;
num = ((struct syscall_metadata *)call->data)->syscall_nr;
if (num < 0 || num >= NR_syscalls)
return;
mutex_lock(&syscall_trace_lock);
sys_refcount_enter--;
clear_bit(num, enabled_enter_syscalls);
if (!sys_refcount_enter)
unregister_trace_sys_enter(ftrace_syscall_enter);
mutex_unlock(&syscall_trace_lock);
}
int reg_event_syscall_exit(struct ftrace_event_call *call)
{
int ret = 0;
int num;
num = ((struct syscall_metadata *)call->data)->syscall_nr;
if (num < 0 || num >= NR_syscalls)
return -ENOSYS;
mutex_lock(&syscall_trace_lock);
if (!sys_refcount_exit)
ret = register_trace_sys_exit(ftrace_syscall_exit);
if (!ret) {
set_bit(num, enabled_exit_syscalls);
sys_refcount_exit++;
}
mutex_unlock(&syscall_trace_lock);
return ret;
}
void unreg_event_syscall_exit(struct ftrace_event_call *call)
{
int num;
num = ((struct syscall_metadata *)call->data)->syscall_nr;
if (num < 0 || num >= NR_syscalls)
return;
mutex_lock(&syscall_trace_lock);
sys_refcount_exit--;
clear_bit(num, enabled_exit_syscalls);
if (!sys_refcount_exit)
unregister_trace_sys_exit(ftrace_syscall_exit);
mutex_unlock(&syscall_trace_lock);
}
int init_syscall_trace(struct ftrace_event_call *call)
{
int id;
if (set_syscall_print_fmt(call) < 0)
return -ENOMEM;
id = trace_event_raw_init(call);
if (id < 0) {
free_syscall_print_fmt(call);
return id;
}
return id;
}
unsigned long __init arch_syscall_addr(int nr)
{
return (unsigned long)sys_call_table[nr];
}
int __init init_ftrace_syscalls(void)
{
struct syscall_metadata *meta;
unsigned long addr;
int i;
syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) *
NR_syscalls, GFP_KERNEL);
if (!syscalls_metadata) {
WARN_ON(1);
return -ENOMEM;
}
for (i = 0; i < NR_syscalls; i++) {
addr = arch_syscall_addr(i);
meta = find_syscall_meta(addr);
if (!meta)
continue;
meta->syscall_nr = i;
syscalls_metadata[i] = meta;
}
return 0;
}
core_initcall(init_ftrace_syscalls);
#ifdef CONFIG_PERF_EVENTS
static DECLARE_BITMAP(enabled_perf_enter_syscalls, NR_syscalls);
static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls);
static int sys_perf_refcount_enter;
static int sys_perf_refcount_exit;
static void perf_syscall_enter(struct pt_regs *regs, long id)
{
struct syscall_metadata *sys_data;
struct syscall_trace_enter *rec;
unsigned long flags;
int syscall_nr;
int rctx;
int size;
syscall_nr = syscall_get_nr(current, regs);
if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
return;
sys_data = syscall_nr_to_meta(syscall_nr);
if (!sys_data)
return;
/* 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);
if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
"perf buffer not large enough"))
return;
rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size,
sys_data->enter_event->id, &rctx, &flags);
if (!rec)
return;
rec->nr = syscall_nr;
syscall_get_arguments(current, regs, 0, sys_data->nb_args,
(unsigned long *)&rec->args);
perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs);
}
int perf_sysenter_enable(struct ftrace_event_call *call)
{
int ret = 0;
int num;
num = ((struct syscall_metadata *)call->data)->syscall_nr;
mutex_lock(&syscall_trace_lock);
if (!sys_perf_refcount_enter)
ret = register_trace_sys_enter(perf_syscall_enter);
if (ret) {
pr_info("event trace: Could not activate"
"syscall entry trace point");
} else {
set_bit(num, enabled_perf_enter_syscalls);
sys_perf_refcount_enter++;
}
mutex_unlock(&syscall_trace_lock);
return ret;
}
void perf_sysenter_disable(struct ftrace_event_call *call)
{
int num;
num = ((struct syscall_metadata *)call->data)->syscall_nr;
mutex_lock(&syscall_trace_lock);
sys_perf_refcount_enter--;
clear_bit(num, enabled_perf_enter_syscalls);
if (!sys_perf_refcount_enter)
unregister_trace_sys_enter(perf_syscall_enter);
mutex_unlock(&syscall_trace_lock);
}
static void perf_syscall_exit(struct pt_regs *regs, long ret)
{
struct syscall_metadata *sys_data;
struct syscall_trace_exit *rec;
unsigned long flags;
int syscall_nr;
int rctx;
int size;
syscall_nr = syscall_get_nr(current, regs);
if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
return;
sys_data = syscall_nr_to_meta(syscall_nr);
if (!sys_data)
return;
/* We can probably do that at build time */
size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64));
size -= sizeof(u32);
/*
* Impossible, but be paranoid with the future
* How to put this check outside runtime?
*/
if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
"exit event has grown above perf buffer size"))
return;
rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size,
sys_data->exit_event->id, &rctx, &flags);
if (!rec)
return;
rec->nr = syscall_nr;
rec->ret = syscall_get_return_value(current, regs);
perf_trace_buf_submit(rec, size, rctx, 0, 1, flags, regs);
}
int perf_sysexit_enable(struct ftrace_event_call *call)
{
int ret = 0;
int num;
num = ((struct syscall_metadata *)call->data)->syscall_nr;
mutex_lock(&syscall_trace_lock);
if (!sys_perf_refcount_exit)
ret = register_trace_sys_exit(perf_syscall_exit);
if (ret) {
pr_info("event trace: Could not activate"
"syscall exit trace point");
} else {
set_bit(num, enabled_perf_exit_syscalls);
sys_perf_refcount_exit++;
}
mutex_unlock(&syscall_trace_lock);
return ret;
}
void perf_sysexit_disable(struct ftrace_event_call *call)
{
int num;
num = ((struct syscall_metadata *)call->data)->syscall_nr;
mutex_lock(&syscall_trace_lock);
sys_perf_refcount_exit--;
clear_bit(num, enabled_perf_exit_syscalls);
if (!sys_perf_refcount_exit)
unregister_trace_sys_exit(perf_syscall_exit);
mutex_unlock(&syscall_trace_lock);
}
#endif /* CONFIG_PERF_EVENTS */