bac5fb97a1
Add a generic event_command.set_trigger_filter() op implementation and have the current set of trigger commands use it - this essentially gives them all support for filters. Syntactically, filters are supported by adding 'if <filter>' just after the command, in which case only events matching the filter will invoke the trigger. For example, to add a filter to an enable/disable_event command: echo 'enable_event:system:event if common_pid == 999' > \ .../othersys/otherevent/trigger The above command will only enable the system:event event if the common_pid field in the othersys:otherevent event is 999. As another example, to add a filter to a stacktrace command: echo 'stacktrace if common_pid == 999' > \ .../somesys/someevent/trigger The above command will only trigger a stacktrace if the common_pid field in the event is 999. The filter syntax is the same as that described in the 'Event filtering' section of Documentation/trace/events.txt. Because triggers can now use filters, the trigger-invoking logic needs to be moved in those cases - e.g. for ftrace_raw_event_calls, if a trigger has a filter associated with it, the trigger invocation now needs to happen after the { assign; } part of the call, in order for the trigger condition to be tested. There's still a SOFT_DISABLED-only check at the top of e.g. the ftrace_raw_events function, so when an event is soft disabled but not because of the presence of a trigger, the original SOFT_DISABLED behavior remains unchanged. There's also a bit of trickiness in that some triggers need to avoid being invoked while an event is currently in the process of being logged, since the trigger may itself log data into the trace buffer. Thus we make sure the current event is committed before invoking those triggers. To do that, we split the trigger invocation in two - the first part (event_triggers_call()) checks the filter using the current trace record; if a command has the post_trigger flag set, it sets a bit for itself in the return value, otherwise it directly invoks the trigger. Once all commands have been either invoked or set their return flag, event_triggers_call() returns. The current record is then either committed or discarded; if any commands have deferred their triggers, those commands are finally invoked following the close of the current event by event_triggers_post_call(). To simplify the above and make it more efficient, the TRIGGER_COND bit is introduced, which is set only if a soft-disabled trigger needs to use the log record for filter testing or needs to wait until the current log record is closed. The syscall event invocation code is also changed in analogous ways. Because event triggers need to be able to create and free filters, this also adds a couple external wrappers for the existing create_filter and free_filter functions, which are too generic to be made extern functions themselves. Link: http://lkml.kernel.org/r/7164930759d8719ef460357f143d995406e4eead.1382622043.git.tom.zanussi@linux.intel.com Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
795 lines
20 KiB
C
795 lines
20 KiB
C
#include <trace/syscall.h>
|
|
#include <trace/events/syscalls.h>
|
|
#include <linux/syscalls.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/module.h> /* for MODULE_NAME_LEN via KSYM_SYMBOL_LEN */
|
|
#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 syscall_enter_register(struct ftrace_event_call *event,
|
|
enum trace_reg type, void *data);
|
|
static int syscall_exit_register(struct ftrace_event_call *event,
|
|
enum trace_reg type, void *data);
|
|
|
|
static struct list_head *
|
|
syscall_get_enter_fields(struct ftrace_event_call *call)
|
|
{
|
|
struct syscall_metadata *entry = call->data;
|
|
|
|
return &entry->enter_fields;
|
|
}
|
|
|
|
extern struct syscall_metadata *__start_syscalls_metadata[];
|
|
extern struct syscall_metadata *__stop_syscalls_metadata[];
|
|
|
|
static struct syscall_metadata **syscalls_metadata;
|
|
|
|
#ifndef ARCH_HAS_SYSCALL_MATCH_SYM_NAME
|
|
static inline bool arch_syscall_match_sym_name(const char *sym, const char *name)
|
|
{
|
|
/*
|
|
* Only compare after the "sys" prefix. Archs that use
|
|
* syscall wrappers may have syscalls symbols aliases prefixed
|
|
* with ".SyS" or ".sys" instead of "sys", leading to an unwanted
|
|
* mismatch.
|
|
*/
|
|
return !strcmp(sym + 3, name + 3);
|
|
}
|
|
#endif
|
|
|
|
#ifdef ARCH_TRACE_IGNORE_COMPAT_SYSCALLS
|
|
/*
|
|
* Some architectures that allow for 32bit applications
|
|
* to run on a 64bit kernel, do not map the syscalls for
|
|
* the 32bit tasks the same as they do for 64bit tasks.
|
|
*
|
|
* *cough*x86*cough*
|
|
*
|
|
* In such a case, instead of reporting the wrong syscalls,
|
|
* simply ignore them.
|
|
*
|
|
* For an arch to ignore the compat syscalls it needs to
|
|
* define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS as well as
|
|
* define the function arch_trace_is_compat_syscall() to let
|
|
* the tracing system know that it should ignore it.
|
|
*/
|
|
static int
|
|
trace_get_syscall_nr(struct task_struct *task, struct pt_regs *regs)
|
|
{
|
|
if (unlikely(arch_trace_is_compat_syscall(regs)))
|
|
return -1;
|
|
|
|
return syscall_get_nr(task, regs);
|
|
}
|
|
#else
|
|
static inline int
|
|
trace_get_syscall_nr(struct task_struct *task, struct pt_regs *regs)
|
|
{
|
|
return syscall_get_nr(task, regs);
|
|
}
|
|
#endif /* ARCH_TRACE_IGNORE_COMPAT_SYSCALLS */
|
|
|
|
static __init struct syscall_metadata *
|
|
find_syscall_meta(unsigned long syscall)
|
|
{
|
|
struct syscall_metadata **start;
|
|
struct syscall_metadata **stop;
|
|
char str[KSYM_SYMBOL_LEN];
|
|
|
|
|
|
start = __start_syscalls_metadata;
|
|
stop = __stop_syscalls_metadata;
|
|
kallsyms_lookup(syscall, NULL, NULL, NULL, str);
|
|
|
|
if (arch_syscall_match_sym_name(str, "sys_ni_syscall"))
|
|
return NULL;
|
|
|
|
for ( ; start < stop; start++) {
|
|
if ((*start)->name && arch_syscall_match_sym_name(str, (*start)->name))
|
|
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];
|
|
}
|
|
|
|
static enum print_line_t
|
|
print_syscall_enter(struct trace_iterator *iter, int flags,
|
|
struct trace_event *event)
|
|
{
|
|
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->event.type != 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;
|
|
}
|
|
|
|
static enum print_line_t
|
|
print_syscall_exit(struct trace_iterator *iter, int flags,
|
|
struct trace_event *event)
|
|
{
|
|
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_putc(s, '\n');
|
|
return TRACE_TYPE_HANDLED;
|
|
}
|
|
|
|
if (entry->exit_event->event.type != 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 __init
|
|
__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 __init 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 __init free_syscall_print_fmt(struct ftrace_event_call *call)
|
|
{
|
|
struct syscall_metadata *entry = call->data;
|
|
|
|
if (entry->enter_event == call)
|
|
kfree(call->print_fmt);
|
|
}
|
|
|
|
static int __init 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;
|
|
}
|
|
|
|
static int __init 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;
|
|
}
|
|
|
|
static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
|
|
{
|
|
struct trace_array *tr = data;
|
|
struct ftrace_event_file *ftrace_file;
|
|
struct syscall_trace_enter *entry;
|
|
struct syscall_metadata *sys_data;
|
|
struct ring_buffer_event *event;
|
|
enum event_trigger_type __tt = ETT_NONE;
|
|
struct ring_buffer *buffer;
|
|
unsigned long irq_flags;
|
|
unsigned long eflags;
|
|
int pc;
|
|
int syscall_nr;
|
|
int size;
|
|
|
|
syscall_nr = trace_get_syscall_nr(current, regs);
|
|
if (syscall_nr < 0)
|
|
return;
|
|
|
|
/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE) */
|
|
ftrace_file = rcu_dereference_sched(tr->enter_syscall_files[syscall_nr]);
|
|
if (!ftrace_file)
|
|
return;
|
|
|
|
eflags = ftrace_file->flags;
|
|
|
|
if (!(eflags & FTRACE_EVENT_FL_TRIGGER_COND)) {
|
|
if (eflags & FTRACE_EVENT_FL_TRIGGER_MODE)
|
|
event_triggers_call(ftrace_file, NULL);
|
|
if (eflags & FTRACE_EVENT_FL_SOFT_DISABLED)
|
|
return;
|
|
}
|
|
|
|
sys_data = syscall_nr_to_meta(syscall_nr);
|
|
if (!sys_data)
|
|
return;
|
|
|
|
size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
|
|
|
|
local_save_flags(irq_flags);
|
|
pc = preempt_count();
|
|
|
|
buffer = tr->trace_buffer.buffer;
|
|
event = trace_buffer_lock_reserve(buffer,
|
|
sys_data->enter_event->event.type, size, irq_flags, pc);
|
|
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 (eflags & FTRACE_EVENT_FL_TRIGGER_COND)
|
|
__tt = event_triggers_call(ftrace_file, entry);
|
|
|
|
if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
|
|
ring_buffer_discard_commit(buffer, event);
|
|
else if (!filter_check_discard(ftrace_file, entry, buffer, event))
|
|
trace_current_buffer_unlock_commit(buffer, event,
|
|
irq_flags, pc);
|
|
if (__tt)
|
|
event_triggers_post_call(ftrace_file, __tt);
|
|
}
|
|
|
|
static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
|
|
{
|
|
struct trace_array *tr = data;
|
|
struct ftrace_event_file *ftrace_file;
|
|
struct syscall_trace_exit *entry;
|
|
struct syscall_metadata *sys_data;
|
|
struct ring_buffer_event *event;
|
|
enum event_trigger_type __tt = ETT_NONE;
|
|
struct ring_buffer *buffer;
|
|
unsigned long irq_flags;
|
|
unsigned long eflags;
|
|
int pc;
|
|
int syscall_nr;
|
|
|
|
syscall_nr = trace_get_syscall_nr(current, regs);
|
|
if (syscall_nr < 0)
|
|
return;
|
|
|
|
/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE()) */
|
|
ftrace_file = rcu_dereference_sched(tr->exit_syscall_files[syscall_nr]);
|
|
if (!ftrace_file)
|
|
return;
|
|
|
|
eflags = ftrace_file->flags;
|
|
|
|
if (!(eflags & FTRACE_EVENT_FL_TRIGGER_COND)) {
|
|
if (eflags & FTRACE_EVENT_FL_TRIGGER_MODE)
|
|
event_triggers_call(ftrace_file, NULL);
|
|
if (eflags & FTRACE_EVENT_FL_SOFT_DISABLED)
|
|
return;
|
|
}
|
|
|
|
sys_data = syscall_nr_to_meta(syscall_nr);
|
|
if (!sys_data)
|
|
return;
|
|
|
|
local_save_flags(irq_flags);
|
|
pc = preempt_count();
|
|
|
|
buffer = tr->trace_buffer.buffer;
|
|
event = trace_buffer_lock_reserve(buffer,
|
|
sys_data->exit_event->event.type, sizeof(*entry),
|
|
irq_flags, pc);
|
|
if (!event)
|
|
return;
|
|
|
|
entry = ring_buffer_event_data(event);
|
|
entry->nr = syscall_nr;
|
|
entry->ret = syscall_get_return_value(current, regs);
|
|
|
|
if (eflags & FTRACE_EVENT_FL_TRIGGER_COND)
|
|
__tt = event_triggers_call(ftrace_file, entry);
|
|
|
|
if (test_bit(FTRACE_EVENT_FL_SOFT_DISABLED_BIT, &ftrace_file->flags))
|
|
ring_buffer_discard_commit(buffer, event);
|
|
else if (!filter_check_discard(ftrace_file, entry, buffer, event))
|
|
trace_current_buffer_unlock_commit(buffer, event,
|
|
irq_flags, pc);
|
|
if (__tt)
|
|
event_triggers_post_call(ftrace_file, __tt);
|
|
}
|
|
|
|
static int reg_event_syscall_enter(struct ftrace_event_file *file,
|
|
struct ftrace_event_call *call)
|
|
{
|
|
struct trace_array *tr = file->tr;
|
|
int ret = 0;
|
|
int num;
|
|
|
|
num = ((struct syscall_metadata *)call->data)->syscall_nr;
|
|
if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
|
|
return -ENOSYS;
|
|
mutex_lock(&syscall_trace_lock);
|
|
if (!tr->sys_refcount_enter)
|
|
ret = register_trace_sys_enter(ftrace_syscall_enter, tr);
|
|
if (!ret) {
|
|
rcu_assign_pointer(tr->enter_syscall_files[num], file);
|
|
tr->sys_refcount_enter++;
|
|
}
|
|
mutex_unlock(&syscall_trace_lock);
|
|
return ret;
|
|
}
|
|
|
|
static void unreg_event_syscall_enter(struct ftrace_event_file *file,
|
|
struct ftrace_event_call *call)
|
|
{
|
|
struct trace_array *tr = file->tr;
|
|
int num;
|
|
|
|
num = ((struct syscall_metadata *)call->data)->syscall_nr;
|
|
if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
|
|
return;
|
|
mutex_lock(&syscall_trace_lock);
|
|
tr->sys_refcount_enter--;
|
|
rcu_assign_pointer(tr->enter_syscall_files[num], NULL);
|
|
if (!tr->sys_refcount_enter)
|
|
unregister_trace_sys_enter(ftrace_syscall_enter, tr);
|
|
mutex_unlock(&syscall_trace_lock);
|
|
}
|
|
|
|
static int reg_event_syscall_exit(struct ftrace_event_file *file,
|
|
struct ftrace_event_call *call)
|
|
{
|
|
struct trace_array *tr = file->tr;
|
|
int ret = 0;
|
|
int num;
|
|
|
|
num = ((struct syscall_metadata *)call->data)->syscall_nr;
|
|
if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
|
|
return -ENOSYS;
|
|
mutex_lock(&syscall_trace_lock);
|
|
if (!tr->sys_refcount_exit)
|
|
ret = register_trace_sys_exit(ftrace_syscall_exit, tr);
|
|
if (!ret) {
|
|
rcu_assign_pointer(tr->exit_syscall_files[num], file);
|
|
tr->sys_refcount_exit++;
|
|
}
|
|
mutex_unlock(&syscall_trace_lock);
|
|
return ret;
|
|
}
|
|
|
|
static void unreg_event_syscall_exit(struct ftrace_event_file *file,
|
|
struct ftrace_event_call *call)
|
|
{
|
|
struct trace_array *tr = file->tr;
|
|
int num;
|
|
|
|
num = ((struct syscall_metadata *)call->data)->syscall_nr;
|
|
if (WARN_ON_ONCE(num < 0 || num >= NR_syscalls))
|
|
return;
|
|
mutex_lock(&syscall_trace_lock);
|
|
tr->sys_refcount_exit--;
|
|
rcu_assign_pointer(tr->exit_syscall_files[num], NULL);
|
|
if (!tr->sys_refcount_exit)
|
|
unregister_trace_sys_exit(ftrace_syscall_exit, tr);
|
|
mutex_unlock(&syscall_trace_lock);
|
|
}
|
|
|
|
static int __init init_syscall_trace(struct ftrace_event_call *call)
|
|
{
|
|
int id;
|
|
int num;
|
|
|
|
num = ((struct syscall_metadata *)call->data)->syscall_nr;
|
|
if (num < 0 || num >= NR_syscalls) {
|
|
pr_debug("syscall %s metadata not mapped, disabling ftrace event\n",
|
|
((struct syscall_metadata *)call->data)->name);
|
|
return -ENOSYS;
|
|
}
|
|
|
|
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;
|
|
}
|
|
|
|
struct trace_event_functions enter_syscall_print_funcs = {
|
|
.trace = print_syscall_enter,
|
|
};
|
|
|
|
struct trace_event_functions exit_syscall_print_funcs = {
|
|
.trace = print_syscall_exit,
|
|
};
|
|
|
|
struct ftrace_event_class __refdata event_class_syscall_enter = {
|
|
.system = "syscalls",
|
|
.reg = syscall_enter_register,
|
|
.define_fields = syscall_enter_define_fields,
|
|
.get_fields = syscall_get_enter_fields,
|
|
.raw_init = init_syscall_trace,
|
|
};
|
|
|
|
struct ftrace_event_class __refdata event_class_syscall_exit = {
|
|
.system = "syscalls",
|
|
.reg = syscall_exit_register,
|
|
.define_fields = syscall_exit_define_fields,
|
|
.fields = LIST_HEAD_INIT(event_class_syscall_exit.fields),
|
|
.raw_init = init_syscall_trace,
|
|
};
|
|
|
|
unsigned long __init __weak arch_syscall_addr(int nr)
|
|
{
|
|
return (unsigned long)sys_call_table[nr];
|
|
}
|
|
|
|
static int __init init_ftrace_syscalls(void)
|
|
{
|
|
struct syscall_metadata *meta;
|
|
unsigned long addr;
|
|
int i;
|
|
|
|
syscalls_metadata = kcalloc(NR_syscalls, sizeof(*syscalls_metadata),
|
|
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;
|
|
}
|
|
early_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(void *ignore, struct pt_regs *regs, long id)
|
|
{
|
|
struct syscall_metadata *sys_data;
|
|
struct syscall_trace_enter *rec;
|
|
struct hlist_head *head;
|
|
int syscall_nr;
|
|
int rctx;
|
|
int size;
|
|
|
|
syscall_nr = trace_get_syscall_nr(current, regs);
|
|
if (syscall_nr < 0)
|
|
return;
|
|
if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
|
|
return;
|
|
|
|
sys_data = syscall_nr_to_meta(syscall_nr);
|
|
if (!sys_data)
|
|
return;
|
|
|
|
head = this_cpu_ptr(sys_data->enter_event->perf_events);
|
|
if (hlist_empty(head))
|
|
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);
|
|
|
|
rec = (struct syscall_trace_enter *)perf_trace_buf_prepare(size,
|
|
sys_data->enter_event->event.type, regs, &rctx);
|
|
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, regs, head, NULL);
|
|
}
|
|
|
|
static 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, NULL);
|
|
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;
|
|
}
|
|
|
|
static 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, NULL);
|
|
mutex_unlock(&syscall_trace_lock);
|
|
}
|
|
|
|
static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
|
|
{
|
|
struct syscall_metadata *sys_data;
|
|
struct syscall_trace_exit *rec;
|
|
struct hlist_head *head;
|
|
int syscall_nr;
|
|
int rctx;
|
|
int size;
|
|
|
|
syscall_nr = trace_get_syscall_nr(current, regs);
|
|
if (syscall_nr < 0)
|
|
return;
|
|
if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
|
|
return;
|
|
|
|
sys_data = syscall_nr_to_meta(syscall_nr);
|
|
if (!sys_data)
|
|
return;
|
|
|
|
head = this_cpu_ptr(sys_data->exit_event->perf_events);
|
|
if (hlist_empty(head))
|
|
return;
|
|
|
|
/* We can probably do that at build time */
|
|
size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64));
|
|
size -= sizeof(u32);
|
|
|
|
rec = (struct syscall_trace_exit *)perf_trace_buf_prepare(size,
|
|
sys_data->exit_event->event.type, regs, &rctx);
|
|
if (!rec)
|
|
return;
|
|
|
|
rec->nr = syscall_nr;
|
|
rec->ret = syscall_get_return_value(current, regs);
|
|
perf_trace_buf_submit(rec, size, rctx, 0, 1, regs, head, NULL);
|
|
}
|
|
|
|
static 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, NULL);
|
|
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;
|
|
}
|
|
|
|
static 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, NULL);
|
|
mutex_unlock(&syscall_trace_lock);
|
|
}
|
|
|
|
#endif /* CONFIG_PERF_EVENTS */
|
|
|
|
static int syscall_enter_register(struct ftrace_event_call *event,
|
|
enum trace_reg type, void *data)
|
|
{
|
|
struct ftrace_event_file *file = data;
|
|
|
|
switch (type) {
|
|
case TRACE_REG_REGISTER:
|
|
return reg_event_syscall_enter(file, event);
|
|
case TRACE_REG_UNREGISTER:
|
|
unreg_event_syscall_enter(file, event);
|
|
return 0;
|
|
|
|
#ifdef CONFIG_PERF_EVENTS
|
|
case TRACE_REG_PERF_REGISTER:
|
|
return perf_sysenter_enable(event);
|
|
case TRACE_REG_PERF_UNREGISTER:
|
|
perf_sysenter_disable(event);
|
|
return 0;
|
|
case TRACE_REG_PERF_OPEN:
|
|
case TRACE_REG_PERF_CLOSE:
|
|
case TRACE_REG_PERF_ADD:
|
|
case TRACE_REG_PERF_DEL:
|
|
return 0;
|
|
#endif
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static int syscall_exit_register(struct ftrace_event_call *event,
|
|
enum trace_reg type, void *data)
|
|
{
|
|
struct ftrace_event_file *file = data;
|
|
|
|
switch (type) {
|
|
case TRACE_REG_REGISTER:
|
|
return reg_event_syscall_exit(file, event);
|
|
case TRACE_REG_UNREGISTER:
|
|
unreg_event_syscall_exit(file, event);
|
|
return 0;
|
|
|
|
#ifdef CONFIG_PERF_EVENTS
|
|
case TRACE_REG_PERF_REGISTER:
|
|
return perf_sysexit_enable(event);
|
|
case TRACE_REG_PERF_UNREGISTER:
|
|
perf_sysexit_disable(event);
|
|
return 0;
|
|
case TRACE_REG_PERF_OPEN:
|
|
case TRACE_REG_PERF_CLOSE:
|
|
case TRACE_REG_PERF_ADD:
|
|
case TRACE_REG_PERF_DEL:
|
|
return 0;
|
|
#endif
|
|
}
|
|
return 0;
|
|
}
|