summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/compat.c267
-rw-r--r--kernel/module.c6
-rw-r--r--kernel/signal.c155
-rw-r--r--kernel/sys.c100
-rw-r--r--kernel/trace/Kconfig22
-rw-r--r--kernel/trace/ftrace.c366
-rw-r--r--kernel/trace/trace.c358
-rw-r--r--kernel/trace/trace.h30
-rw-r--r--kernel/trace/trace_events.c66
-rw-r--r--kernel/trace/trace_output.c27
-rw-r--r--kernel/trace/trace_sched_switch.c72
11 files changed, 978 insertions, 491 deletions
diff --git a/kernel/compat.c b/kernel/compat.c
index 0621c8e1ab72..6f0a0e723a06 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -247,53 +247,6 @@ int put_compat_itimerval(struct compat_itimerval __user *o, const struct itimerv
return copy_to_user(o, &v32, sizeof(struct compat_itimerval)) ? -EFAULT : 0;
}
-static compat_clock_t clock_t_to_compat_clock_t(clock_t x)
-{
- return compat_jiffies_to_clock_t(clock_t_to_jiffies(x));
-}
-
-COMPAT_SYSCALL_DEFINE1(times, struct compat_tms __user *, tbuf)
-{
- if (tbuf) {
- struct tms tms;
- struct compat_tms tmp;
-
- do_sys_times(&tms);
- /* Convert our struct tms to the compat version. */
- tmp.tms_utime = clock_t_to_compat_clock_t(tms.tms_utime);
- tmp.tms_stime = clock_t_to_compat_clock_t(tms.tms_stime);
- tmp.tms_cutime = clock_t_to_compat_clock_t(tms.tms_cutime);
- tmp.tms_cstime = clock_t_to_compat_clock_t(tms.tms_cstime);
- if (copy_to_user(tbuf, &tmp, sizeof(tmp)))
- return -EFAULT;
- }
- force_successful_syscall_return();
- return compat_jiffies_to_clock_t(jiffies);
-}
-
-#ifdef __ARCH_WANT_SYS_SIGPENDING
-
-/*
- * Assumption: old_sigset_t and compat_old_sigset_t are both
- * types that can be passed to put_user()/get_user().
- */
-
-COMPAT_SYSCALL_DEFINE1(sigpending, compat_old_sigset_t __user *, set)
-{
- old_sigset_t s;
- long ret;
- mm_segment_t old_fs = get_fs();
-
- set_fs(KERNEL_DS);
- ret = sys_sigpending((old_sigset_t __user *) &s);
- set_fs(old_fs);
- if (ret == 0)
- ret = put_user(s, set);
- return ret;
-}
-
-#endif
-
#ifdef __ARCH_WANT_SYS_SIGPROCMASK
/*
@@ -348,94 +301,29 @@ COMPAT_SYSCALL_DEFINE3(sigprocmask, int, how,
#endif
-COMPAT_SYSCALL_DEFINE2(setrlimit, unsigned int, resource,
- struct compat_rlimit __user *, rlim)
-{
- struct rlimit r;
-
- if (!access_ok(VERIFY_READ, rlim, sizeof(*rlim)) ||
- __get_user(r.rlim_cur, &rlim->rlim_cur) ||
- __get_user(r.rlim_max, &rlim->rlim_max))
- return -EFAULT;
-
- if (r.rlim_cur == COMPAT_RLIM_INFINITY)
- r.rlim_cur = RLIM_INFINITY;
- if (r.rlim_max == COMPAT_RLIM_INFINITY)
- r.rlim_max = RLIM_INFINITY;
- return do_prlimit(current, resource, &r, NULL);
-}
-
-#ifdef COMPAT_RLIM_OLD_INFINITY
-
-COMPAT_SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
- struct compat_rlimit __user *, rlim)
-{
- struct rlimit r;
- int ret;
- mm_segment_t old_fs = get_fs();
-
- set_fs(KERNEL_DS);
- ret = sys_old_getrlimit(resource, (struct rlimit __user *)&r);
- set_fs(old_fs);
-
- if (!ret) {
- if (r.rlim_cur > COMPAT_RLIM_OLD_INFINITY)
- r.rlim_cur = COMPAT_RLIM_INFINITY;
- if (r.rlim_max > COMPAT_RLIM_OLD_INFINITY)
- r.rlim_max = COMPAT_RLIM_INFINITY;
-
- if (!access_ok(VERIFY_WRITE, rlim, sizeof(*rlim)) ||
- __put_user(r.rlim_cur, &rlim->rlim_cur) ||
- __put_user(r.rlim_max, &rlim->rlim_max))
- return -EFAULT;
- }
- return ret;
-}
-
-#endif
-
-COMPAT_SYSCALL_DEFINE2(getrlimit, unsigned int, resource,
- struct compat_rlimit __user *, rlim)
-{
- struct rlimit r;
- int ret;
-
- ret = do_prlimit(current, resource, NULL, &r);
- if (!ret) {
- if (r.rlim_cur > COMPAT_RLIM_INFINITY)
- r.rlim_cur = COMPAT_RLIM_INFINITY;
- if (r.rlim_max > COMPAT_RLIM_INFINITY)
- r.rlim_max = COMPAT_RLIM_INFINITY;
-
- if (!access_ok(VERIFY_WRITE, rlim, sizeof(*rlim)) ||
- __put_user(r.rlim_cur, &rlim->rlim_cur) ||
- __put_user(r.rlim_max, &rlim->rlim_max))
- return -EFAULT;
- }
- return ret;
-}
-
int put_compat_rusage(const struct rusage *r, struct compat_rusage __user *ru)
{
- if (!access_ok(VERIFY_WRITE, ru, sizeof(*ru)) ||
- __put_user(r->ru_utime.tv_sec, &ru->ru_utime.tv_sec) ||
- __put_user(r->ru_utime.tv_usec, &ru->ru_utime.tv_usec) ||
- __put_user(r->ru_stime.tv_sec, &ru->ru_stime.tv_sec) ||
- __put_user(r->ru_stime.tv_usec, &ru->ru_stime.tv_usec) ||
- __put_user(r->ru_maxrss, &ru->ru_maxrss) ||
- __put_user(r->ru_ixrss, &ru->ru_ixrss) ||
- __put_user(r->ru_idrss, &ru->ru_idrss) ||
- __put_user(r->ru_isrss, &ru->ru_isrss) ||
- __put_user(r->ru_minflt, &ru->ru_minflt) ||
- __put_user(r->ru_majflt, &ru->ru_majflt) ||
- __put_user(r->ru_nswap, &ru->ru_nswap) ||
- __put_user(r->ru_inblock, &ru->ru_inblock) ||
- __put_user(r->ru_oublock, &ru->ru_oublock) ||
- __put_user(r->ru_msgsnd, &ru->ru_msgsnd) ||
- __put_user(r->ru_msgrcv, &ru->ru_msgrcv) ||
- __put_user(r->ru_nsignals, &ru->ru_nsignals) ||
- __put_user(r->ru_nvcsw, &ru->ru_nvcsw) ||
- __put_user(r->ru_nivcsw, &ru->ru_nivcsw))
+ struct compat_rusage r32;
+ memset(&r32, 0, sizeof(r32));
+ r32.ru_utime.tv_sec = r->ru_utime.tv_sec;
+ r32.ru_utime.tv_usec = r->ru_utime.tv_usec;
+ r32.ru_stime.tv_sec = r->ru_stime.tv_sec;
+ r32.ru_stime.tv_usec = r->ru_stime.tv_usec;
+ r32.ru_maxrss = r->ru_maxrss;
+ r32.ru_ixrss = r->ru_ixrss;
+ r32.ru_idrss = r->ru_idrss;
+ r32.ru_isrss = r->ru_isrss;
+ r32.ru_minflt = r->ru_minflt;
+ r32.ru_majflt = r->ru_majflt;
+ r32.ru_nswap = r->ru_nswap;
+ r32.ru_inblock = r->ru_inblock;
+ r32.ru_oublock = r->ru_oublock;
+ r32.ru_msgsnd = r->ru_msgsnd;
+ r32.ru_msgrcv = r->ru_msgrcv;
+ r32.ru_nsignals = r->ru_nsignals;
+ r32.ru_nvcsw = r->ru_nvcsw;
+ r32.ru_nivcsw = r->ru_nivcsw;
+ if (copy_to_user(ru, &r32, sizeof(r32)))
return -EFAULT;
return 0;
}
@@ -565,84 +453,59 @@ int get_compat_sigevent(struct sigevent *event,
long compat_get_bitmap(unsigned long *mask, const compat_ulong_t __user *umask,
unsigned long bitmap_size)
{
- int i, j;
- unsigned long m;
- compat_ulong_t um;
unsigned long nr_compat_longs;
/* align bitmap up to nearest compat_long_t boundary */
bitmap_size = ALIGN(bitmap_size, BITS_PER_COMPAT_LONG);
+ nr_compat_longs = BITS_TO_COMPAT_LONGS(bitmap_size);
if (!access_ok(VERIFY_READ, umask, bitmap_size / 8))
return -EFAULT;
- nr_compat_longs = BITS_TO_COMPAT_LONGS(bitmap_size);
-
- for (i = 0; i < BITS_TO_LONGS(bitmap_size); i++) {
- m = 0;
-
- for (j = 0; j < sizeof(m)/sizeof(um); j++) {
- /*
- * We dont want to read past the end of the userspace
- * bitmap. We must however ensure the end of the
- * kernel bitmap is zeroed.
- */
- if (nr_compat_longs) {
- nr_compat_longs--;
- if (__get_user(um, umask))
- return -EFAULT;
- } else {
- um = 0;
- }
-
- umask++;
- m |= (long)um << (j * BITS_PER_COMPAT_LONG);
- }
- *mask++ = m;
+ user_access_begin();
+ while (nr_compat_longs > 1) {
+ compat_ulong_t l1, l2;
+ unsafe_get_user(l1, umask++, Efault);
+ unsafe_get_user(l2, umask++, Efault);
+ *mask++ = ((unsigned long)l2 << BITS_PER_COMPAT_LONG) | l1;
+ nr_compat_longs -= 2;
}
-
+ if (nr_compat_longs)
+ unsafe_get_user(*mask, umask++, Efault);
+ user_access_end();
return 0;
+
+Efault:
+ user_access_end();
+ return -EFAULT;
}
long compat_put_bitmap(compat_ulong_t __user *umask, unsigned long *mask,
unsigned long bitmap_size)
{
- int i, j;
- unsigned long m;
- compat_ulong_t um;
unsigned long nr_compat_longs;
/* align bitmap up to nearest compat_long_t boundary */
bitmap_size = ALIGN(bitmap_size, BITS_PER_COMPAT_LONG);
+ nr_compat_longs = BITS_TO_COMPAT_LONGS(bitmap_size);
if (!access_ok(VERIFY_WRITE, umask, bitmap_size / 8))
return -EFAULT;
- nr_compat_longs = BITS_TO_COMPAT_LONGS(bitmap_size);
-
- for (i = 0; i < BITS_TO_LONGS(bitmap_size); i++) {
- m = *mask++;
-
- for (j = 0; j < sizeof(m)/sizeof(um); j++) {
- um = m;
-
- /*
- * We dont want to write past the end of the userspace
- * bitmap.
- */
- if (nr_compat_longs) {
- nr_compat_longs--;
- if (__put_user(um, umask))
- return -EFAULT;
- }
-
- umask++;
- m >>= 4*sizeof(um);
- m >>= 4*sizeof(um);
- }
+ user_access_begin();
+ while (nr_compat_longs > 1) {
+ unsigned long m = *mask++;
+ unsafe_put_user((compat_ulong_t)m, umask++, Efault);
+ unsafe_put_user(m >> BITS_PER_COMPAT_LONG, umask++, Efault);
+ nr_compat_longs -= 2;
}
-
+ if (nr_compat_longs)
+ unsafe_put_user((compat_ulong_t)*mask, umask++, Efault);
+ user_access_end();
return 0;
+Efault:
+ user_access_end();
+ return -EFAULT;
}
void
@@ -668,38 +531,6 @@ sigset_to_compat(compat_sigset_t *compat, const sigset_t *set)
}
}
-COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait, compat_sigset_t __user *, uthese,
- struct compat_siginfo __user *, uinfo,
- struct compat_timespec __user *, uts, compat_size_t, sigsetsize)
-{
- compat_sigset_t s32;
- sigset_t s;
- struct timespec t;
- siginfo_t info;
- long ret;
-
- if (sigsetsize != sizeof(sigset_t))
- return -EINVAL;
-
- if (copy_from_user(&s32, uthese, sizeof(compat_sigset_t)))
- return -EFAULT;
- sigset_from_compat(&s, &s32);
-
- if (uts) {
- if (compat_get_timespec(&t, uts))
- return -EFAULT;
- }
-
- ret = do_sigtimedwait(&s, &info, uts ? &t : NULL);
-
- if (ret > 0 && uinfo) {
- if (copy_siginfo_to_user32(uinfo, &info))
- ret = -EFAULT;
- }
-
- return ret;
-}
-
#ifdef CONFIG_NUMA
COMPAT_SYSCALL_DEFINE6(move_pages, pid_t, pid, compat_ulong_t, nr_pages,
compat_uptr_t __user *, pages32,
diff --git a/kernel/module.c b/kernel/module.c
index 8f883d86cedc..b3dbdde82e80 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -3072,9 +3072,9 @@ static int find_module_sections(struct module *mod, struct load_info *info)
mod->trace_events = section_objs(info, "_ftrace_events",
sizeof(*mod->trace_events),
&mod->num_trace_events);
- mod->trace_enums = section_objs(info, "_ftrace_enum_map",
- sizeof(*mod->trace_enums),
- &mod->num_trace_enums);
+ mod->trace_evals = section_objs(info, "_ftrace_eval_map",
+ sizeof(*mod->trace_evals),
+ &mod->num_trace_evals);
#endif
#ifdef CONFIG_TRACING
mod->trace_bprintk_fmt_start = section_objs(info, "__trace_printk_fmt",
diff --git a/kernel/signal.c b/kernel/signal.c
index 35a570f71f07..48a59eefd8ad 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2776,7 +2776,7 @@ int copy_siginfo_to_user(siginfo_t __user *to, const siginfo_t *from)
* @info: if non-null, the signal's siginfo is returned here
* @ts: upper bound on process time suspension
*/
-int do_sigtimedwait(const sigset_t *which, siginfo_t *info,
+static int do_sigtimedwait(const sigset_t *which, siginfo_t *info,
const struct timespec *ts)
{
ktime_t *to = NULL, timeout = KTIME_MAX;
@@ -2865,6 +2865,40 @@ SYSCALL_DEFINE4(rt_sigtimedwait, const sigset_t __user *, uthese,
return ret;
}
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait, compat_sigset_t __user *, uthese,
+ struct compat_siginfo __user *, uinfo,
+ struct compat_timespec __user *, uts, compat_size_t, sigsetsize)
+{
+ compat_sigset_t s32;
+ sigset_t s;
+ struct timespec t;
+ siginfo_t info;
+ long ret;
+
+ if (sigsetsize != sizeof(sigset_t))
+ return -EINVAL;
+
+ if (copy_from_user(&s32, uthese, sizeof(compat_sigset_t)))
+ return -EFAULT;
+ sigset_from_compat(&s, &s32);
+
+ if (uts) {
+ if (compat_get_timespec(&t, uts))
+ return -EFAULT;
+ }
+
+ ret = do_sigtimedwait(&s, &info, uts ? &t : NULL);
+
+ if (ret > 0 && uinfo) {
+ if (copy_siginfo_to_user32(uinfo, &info))
+ ret = -EFAULT;
+ }
+
+ return ret;
+}
+#endif
+
/**
* sys_kill - send a signal to a process
* @pid: the PID of the process
@@ -3121,78 +3155,68 @@ int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact)
}
static int
-do_sigaltstack (const stack_t __user *uss, stack_t __user *uoss, unsigned long sp)
+do_sigaltstack (const stack_t *ss, stack_t *oss, unsigned long sp)
{
- stack_t oss;
- int error;
+ struct task_struct *t = current;
- oss.ss_sp = (void __user *) current->sas_ss_sp;
- oss.ss_size = current->sas_ss_size;
- oss.ss_flags = sas_ss_flags(sp) |
- (current->sas_ss_flags & SS_FLAG_BITS);
+ if (oss) {
+ memset(oss, 0, sizeof(stack_t));
+ oss->ss_sp = (void __user *) t->sas_ss_sp;
+ oss->ss_size = t->sas_ss_size;
+ oss->ss_flags = sas_ss_flags(sp) |
+ (current->sas_ss_flags & SS_FLAG_BITS);
+ }
- if (uss) {
- void __user *ss_sp;
- size_t ss_size;
- unsigned ss_flags;
+ if (ss) {
+ void __user *ss_sp = ss->ss_sp;
+ size_t ss_size = ss->ss_size;
+ unsigned ss_flags = ss->ss_flags;
int ss_mode;
- error = -EFAULT;
- if (!access_ok(VERIFY_READ, uss, sizeof(*uss)))
- goto out;
- error = __get_user(ss_sp, &uss->ss_sp) |
- __get_user(ss_flags, &uss->ss_flags) |
- __get_user(ss_size, &uss->ss_size);
- if (error)
- goto out;
-
- error = -EPERM;
- if (on_sig_stack(sp))
- goto out;
+ if (unlikely(on_sig_stack(sp)))
+ return -EPERM;
ss_mode = ss_flags & ~SS_FLAG_BITS;
- error = -EINVAL;
- if (ss_mode != SS_DISABLE && ss_mode != SS_ONSTACK &&
- ss_mode != 0)
- goto out;
+ if (unlikely(ss_mode != SS_DISABLE && ss_mode != SS_ONSTACK &&
+ ss_mode != 0))
+ return -EINVAL;
if (ss_mode == SS_DISABLE) {
ss_size = 0;
ss_sp = NULL;
} else {
- error = -ENOMEM;
- if (ss_size < MINSIGSTKSZ)
- goto out;
+ if (unlikely(ss_size < MINSIGSTKSZ))
+ return -ENOMEM;
}
- current->sas_ss_sp = (unsigned long) ss_sp;
- current->sas_ss_size = ss_size;
- current->sas_ss_flags = ss_flags;
+ t->sas_ss_sp = (unsigned long) ss_sp;
+ t->sas_ss_size = ss_size;
+ t->sas_ss_flags = ss_flags;
}
-
- error = 0;
- if (uoss) {
- error = -EFAULT;
- if (!access_ok(VERIFY_WRITE, uoss, sizeof(*uoss)))
- goto out;
- error = __put_user(oss.ss_sp, &uoss->ss_sp) |
- __put_user(oss.ss_size, &uoss->ss_size) |
- __put_user(oss.ss_flags, &uoss->ss_flags);
- }
-
-out:
- return error;
+ return 0;
}
+
SYSCALL_DEFINE2(sigaltstack,const stack_t __user *,uss, stack_t __user *,uoss)
{
- return do_sigaltstack(uss, uoss, current_user_stack_pointer());
+ stack_t new, old;
+ int err;
+ if (uss && copy_from_user(&new, uss, sizeof(stack_t)))
+ return -EFAULT;
+ err = do_sigaltstack(uss ? &new : NULL, uoss ? &old : NULL,
+ current_user_stack_pointer());
+ if (!err && uoss && copy_to_user(uoss, &old, sizeof(stack_t)))
+ err = -EFAULT;
+ return err;
}
int restore_altstack(const stack_t __user *uss)
{
- int err = do_sigaltstack(uss, NULL, current_user_stack_pointer());
+ stack_t new;
+ if (copy_from_user(&new, uss, sizeof(stack_t)))
+ return -EFAULT;
+ (void)do_sigaltstack(&new, NULL, current_user_stack_pointer());
/* squash all but EFAULT for now */
- return err == -EFAULT ? err : 0;
+ return 0;
}
int __save_altstack(stack_t __user *uss, unsigned long sp)
@@ -3215,29 +3239,24 @@ COMPAT_SYSCALL_DEFINE2(sigaltstack,
{
stack_t uss, uoss;
int ret;
- mm_segment_t seg;
if (uss_ptr) {
compat_stack_t uss32;
-
- memset(&uss, 0, sizeof(stack_t));
if (copy_from_user(&uss32, uss_ptr, sizeof(compat_stack_t)))
return -EFAULT;
uss.ss_sp = compat_ptr(uss32.ss_sp);
uss.ss_flags = uss32.ss_flags;
uss.ss_size = uss32.ss_size;
}
- seg = get_fs();
- set_fs(KERNEL_DS);
- ret = do_sigaltstack((stack_t __force __user *) (uss_ptr ? &uss : NULL),
- (stack_t __force __user *) &uoss,
+ ret = do_sigaltstack(uss_ptr ? &uss : NULL, &uoss,
compat_user_stack_pointer());
- set_fs(seg);
if (ret >= 0 && uoss_ptr) {
- if (!access_ok(VERIFY_WRITE, uoss_ptr, sizeof(compat_stack_t)) ||
- __put_user(ptr_to_compat(uoss.ss_sp), &uoss_ptr->ss_sp) ||
- __put_user(uoss.ss_flags, &uoss_ptr->ss_flags) ||
- __put_user(uoss.ss_size, &uoss_ptr->ss_size))
+ compat_stack_t old;
+ memset(&old, 0, sizeof(old));
+ old.ss_sp = ptr_to_compat(uoss.ss_sp);
+ old.ss_flags = uoss.ss_flags;
+ old.ss_size = uoss.ss_size;
+ if (copy_to_user(uoss_ptr, &old, sizeof(compat_stack_t)))
ret = -EFAULT;
}
return ret;
@@ -3277,6 +3296,18 @@ SYSCALL_DEFINE1(sigpending, old_sigset_t __user *, set)
return sys_rt_sigpending((sigset_t __user *)set, sizeof(old_sigset_t));
}
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE1(sigpending, compat_old_sigset_t __user *, set32)
+{
+ sigset_t set;
+ int err = do_sigpending(&set, sizeof(old_sigset_t));
+ if (err == 0)
+ if (copy_to_user(set32, &set, sizeof(old_sigset_t)))
+ err = -EFAULT;
+ return err;
+}
+#endif
+
#endif
#ifdef __ARCH_WANT_SYS_SIGPROCMASK
diff --git a/kernel/sys.c b/kernel/sys.c
index dab1a0658a92..47d901586b4e 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -886,7 +886,7 @@ SYSCALL_DEFINE0(getegid)
return from_kgid_munged(current_user_ns(), current_egid());
}
-void do_sys_times(struct tms *tms)
+static void do_sys_times(struct tms *tms)
{
u64 tgutime, tgstime, cutime, cstime;
@@ -912,6 +912,32 @@ SYSCALL_DEFINE1(times, struct tms __user *, tbuf)
return (long) jiffies_64_to_clock_t(get_jiffies_64());
}
+#ifdef CONFIG_COMPAT
+static compat_clock_t clock_t_to_compat_clock_t(clock_t x)
+{
+ return compat_jiffies_to_clock_t(clock_t_to_jiffies(x));
+}
+
+COMPAT_SYSCALL_DEFINE1(times, struct compat_tms __user *, tbuf)
+{
+ if (tbuf) {
+ struct tms tms;
+ struct compat_tms tmp;
+
+ do_sys_times(&tms);
+ /* Convert our struct tms to the compat version. */
+ tmp.tms_utime = clock_t_to_compat_clock_t(tms.tms_utime);
+ tmp.tms_stime = clock_t_to_compat_clock_t(tms.tms_stime);
+ tmp.tms_cutime = clock_t_to_compat_clock_t(tms.tms_cutime);
+ tmp.tms_cstime = clock_t_to_compat_clock_t(tms.tms_cstime);
+ if (copy_to_user(tbuf, &tmp, sizeof(tmp)))
+ return -EFAULT;
+ }
+ force_successful_syscall_return();
+ return compat_jiffies_to_clock_t(jiffies);
+}
+#endif
+
/*
* This needs some heavy checking ...
* I just haven't the stomach for it. I also don't fully
@@ -1306,6 +1332,54 @@ SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim)
return ret;
}
+#ifdef CONFIG_COMPAT
+
+COMPAT_SYSCALL_DEFINE2(setrlimit, unsigned int, resource,
+ struct compat_rlimit __user *, rlim)
+{
+ struct rlimit r;
+ struct compat_rlimit r32;
+
+ if (copy_from_user(&r32, rlim, sizeof(struct compat_rlimit)))
+ return -EFAULT;
+
+ if (r32.rlim_cur == COMPAT_RLIM_INFINITY)
+ r.rlim_cur = RLIM_INFINITY;
+ else
+ r.rlim_cur = r32.rlim_cur;
+ if (r32.rlim_max == COMPAT_RLIM_INFINITY)
+ r.rlim_max = RLIM_INFINITY;
+ else
+ r.rlim_max = r32.rlim_max;
+ return do_prlimit(current, resource, &r, NULL);
+}
+
+COMPAT_SYSCALL_DEFINE2(getrlimit, unsigned int, resource,
+ struct compat_rlimit __user *, rlim)
+{
+ struct rlimit r;
+ int ret;
+
+ ret = do_prlimit(current, resource, NULL, &r);
+ if (!ret) {
+ struct rlimit r32;
+ if (r.rlim_cur > COMPAT_RLIM_INFINITY)
+ r32.rlim_cur = COMPAT_RLIM_INFINITY;
+ else
+ r32.rlim_cur = r.rlim_cur;
+ if (r.rlim_max > COMPAT_RLIM_INFINITY)
+ r32.rlim_max = COMPAT_RLIM_INFINITY;
+ else
+ r32.rlim_max = r.rlim_max;
+
+ if (copy_to_user(rlim, &r32, sizeof(struct compat_rlimit)))
+ return -EFAULT;
+ }
+ return ret;
+}
+
+#endif
+
#ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT
/*
@@ -1328,6 +1402,30 @@ SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
return copy_to_user(rlim, &x, sizeof(x)) ? -EFAULT : 0;
}
+#ifdef CONFIG_COMPAT
+COMPAT_SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource,
+ struct compat_rlimit __user *, rlim)
+{
+ struct rlimit r;
+
+ if (resource >= RLIM_NLIMITS)
+ return -EINVAL;
+
+ task_lock(current->group_leader);
+ r = current->signal->rlim[resource];
+ task_unlock(current->group_leader);
+ if (r.rlim_cur > 0x7FFFFFFF)
+ r.rlim_cur = 0x7FFFFFFF;
+ if (r.rlim_max > 0x7FFFFFFF)
+ r.rlim_max = 0x7FFFFFFF;
+
+ if (put_user(r.rlim_cur, &rlim->rlim_cur) ||
+ put_user(r.rlim_max, &rlim->rlim_max))
+ return -EFAULT;
+ return 0;
+}
+#endif
+
#endif
static inline bool rlim64_is_infinity(__u64 rlim64)
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 7e06f04e98fe..434c840e2d82 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -667,30 +667,30 @@ config RING_BUFFER_STARTUP_TEST
If unsure, say N
-config TRACE_ENUM_MAP_FILE
- bool "Show enum mappings for trace events"
+config TRACE_EVAL_MAP_FILE
+ bool "Show eval mappings for trace events"
depends on TRACING
help
- The "print fmt" of the trace events will show the enum names instead
- of their values. This can cause problems for user space tools that
- use this string to parse the raw data as user space does not know
+ The "print fmt" of the trace events will show the enum/sizeof names
+ instead of their values. This can cause problems for user space tools
+ that use this string to parse the raw data as user space does not know
how to convert the string to its value.
To fix this, there's a special macro in the kernel that can be used
- to convert the enum into its value. If this macro is used, then the
- print fmt strings will have the enums converted to their values.
+ to convert an enum/sizeof into its value. If this macro is used, then
+ the print fmt strings will be converted to their values.
If something does not get converted properly, this option can be
- used to show what enums the kernel tried to convert.
+ used to show what enums/sizeof the kernel tried to convert.
- This option is for debugging the enum conversions. A file is created
- in the tracing directory called "enum_map" that will show the enum
+ This option is for debugging the conversions. A file is created
+ in the tracing directory called "eval_map" that will show the
names matched with their values and what trace event system they
belong too.
Normally, the mapping of the strings to values will be freed after
boot up or module load. With this option, they will not be freed, as
- they are needed for the "enum_map" file. Enabling this option will
+ they are needed for the "eval_map" file. Enabling this option will
increase the memory footprint of the running kernel.
If unsure, say N
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index b308be30dfb9..2953d558bbee 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1293,6 +1293,28 @@ static void ftrace_hash_clear(struct ftrace_hash *hash)
FTRACE_WARN_ON(hash->count);
}
+static void free_ftrace_mod(struct ftrace_mod_load *ftrace_mod)
+{
+ list_del(&ftrace_mod->list);
+ kfree(ftrace_mod->module);
+ kfree(ftrace_mod->func);
+ kfree(ftrace_mod);
+}
+
+static void clear_ftrace_mod_list(struct list_head *head)
+{
+ struct ftrace_mod_load *p, *n;
+
+ /* stack tracer isn't supported yet */
+ if (!head)
+ return;
+
+ mutex_lock(&ftrace_lock);
+ list_for_each_entry_safe(p, n, head, list)
+ free_ftrace_mod(p);
+ mutex_unlock(&ftrace_lock);
+}
+
static void free_ftrace_hash(struct ftrace_hash *hash)
{
if (!hash || hash == EMPTY_HASH)
@@ -1346,6 +1368,35 @@ static struct ftrace_hash *alloc_ftrace_hash(int size_bits)
return hash;
}
+
+static int ftrace_add_mod(struct trace_array *tr,
+ const char *func, const char *module,
+ int enable)
+{
+ struct ftrace_mod_load *ftrace_mod;
+ struct list_head *mod_head = enable ? &tr->mod_trace : &tr->mod_notrace;
+
+ ftrace_mod = kzalloc(sizeof(*ftrace_mod), GFP_KERNEL);
+ if (!ftrace_mod)
+ return -ENOMEM;
+
+ ftrace_mod->func = kstrdup(func, GFP_KERNEL);
+ ftrace_mod->module = kstrdup(module, GFP_KERNEL);
+ ftrace_mod->enable = enable;
+
+ if (!ftrace_mod->func || !ftrace_mod->module)
+ goto out_free;
+
+ list_add(&ftrace_mod->list, mod_head);
+
+ return 0;
+
+ out_free:
+ free_ftrace_mod(ftrace_mod);
+
+ return -ENOMEM;
+}
+
static struct ftrace_hash *
alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash)
{
@@ -1359,6 +1410,9 @@ alloc_and_copy_ftrace_hash(int size_bits, struct ftrace_hash *hash)
if (!new_hash)
return NULL;
+ if (hash)
+ new_hash->flags = hash->flags;
+
/* Empty hash? */
if (ftrace_hash_empty(hash))
return new_hash;
@@ -1403,7 +1457,7 @@ __ftrace_hash_move(struct ftrace_hash *src)
/*
* If the new source is empty, just return the empty_hash.
*/
- if (!src->count)
+ if (ftrace_hash_empty(src))
return EMPTY_HASH;
/*
@@ -1420,6 +1474,8 @@ __ftrace_hash_move(struct ftrace_hash *src)
if (!new_hash)
return NULL;
+ new_hash->flags = src->flags;
+
size = 1 << src->size_bits;
for (i = 0; i < size; i++) {
hhd = &src->buckets[i];
@@ -1650,7 +1706,7 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
struct dyn_ftrace *rec;
bool update = false;
int count = 0;
- int all = 0;
+ int all = false;
/* Only update if the ops has been registered */
if (!(ops->flags & FTRACE_OPS_FL_ENABLED))
@@ -1671,7 +1727,7 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops,
hash = ops->func_hash->filter_hash;
other_hash = ops->func_hash->notrace_hash;
if (ftrace_hash_empty(hash))
- all = 1;
+ all = true;
} else {
inc = !inc;
hash = ops->func_hash->notrace_hash;
@@ -3061,6 +3117,7 @@ ftrace_allocate_pages(unsigned long num_to_init)
struct ftrace_iterator {
loff_t pos;
loff_t func_pos;
+ loff_t mod_pos;
struct ftrace_page *pg;
struct dyn_ftrace *func;
struct ftrace_func_probe *probe;
@@ -3068,6 +3125,8 @@ struct ftrace_iterator {
struct trace_parser parser;
struct ftrace_hash *hash;
struct ftrace_ops *ops;
+ struct trace_array *tr;
+ struct list_head *mod_list;
int pidx;
int idx;
unsigned flags;
@@ -3152,13 +3211,13 @@ static void *t_probe_start(struct seq_file *m, loff_t *pos)
if (!(iter->flags & FTRACE_ITER_DO_PROBES))
return NULL;
- if (iter->func_pos > *pos)
+ if (iter->mod_pos > *pos)
return NULL;
iter->probe = NULL;
iter->probe_entry = NULL;
iter->pidx = 0;
- for (l = 0; l <= (*pos - iter->func_pos); ) {
+ for (l = 0; l <= (*pos - iter->mod_pos); ) {
p = t_probe_next(m, &l);
if (!p)
break;
@@ -3197,6 +3256,82 @@ t_probe_show(struct seq_file *m, struct ftrace_iterator *iter)
}
static void *
+t_mod_next(struct seq_file *m, loff_t *pos)
+{
+ struct ftrace_iterator *iter = m->private;
+ struct trace_array *tr = iter->tr;
+
+ (*pos)++;
+ iter->pos = *pos;
+
+ iter->mod_list = iter->mod_list->next;
+
+ if (iter->mod_list == &tr->mod_trace ||
+ iter->mod_list == &tr->mod_notrace) {
+ iter->flags &= ~FTRACE_ITER_MOD;
+ return NULL;
+ }
+
+ iter->mod_pos = *pos;
+
+ return iter;
+}
+
+static void *t_mod_start(struct seq_file *m, loff_t *pos)
+{
+ struct ftrace_iterator *iter = m->private;
+ void *p = NULL;
+ loff_t l;
+
+ if (iter->func_pos > *pos)
+ return NULL;
+
+ iter->mod_pos = iter->func_pos;
+
+ /* probes are only available if tr is set */
+ if (!iter->tr)
+ return NULL;
+
+ for (l = 0; l <= (*pos - iter->func_pos); ) {
+ p = t_mod_next(m, &l);
+ if (!p)
+ break;
+ }
+ if (!p) {
+ iter->flags &= ~FTRACE_ITER_MOD;
+ return t_probe_start(m, pos);
+ }
+
+ /* Only set this if we have an item */
+ iter->flags |= FTRACE_ITER_MOD;
+
+ return iter;
+}
+
+static int
+t_mod_show(struct seq_file *m, struct ftrace_iterator *iter)
+{
+ struct ftrace_mod_load *ftrace_mod;
+ struct trace_array *tr = iter->tr;
+
+ if (WARN_ON_ONCE(!iter->mod_list) ||
+ iter->mod_list == &tr->mod_trace ||
+ iter->mod_list == &tr->mod_notrace)
+ return -EIO;
+
+ ftrace_mod = list_entry(iter->mod_list, struct ftrace_mod_load, list);
+
+ if (ftrace_mod->func)
+ seq_printf(m, "%s", ftrace_mod->func);
+ else
+ seq_putc(m, '*');
+
+ seq_printf(m, ":mod:%s\n", ftrace_mod->module);
+
+ return 0;
+}
+
+static void *
t_func_next(struct seq_file *m, loff_t *pos)
{
struct ftrace_iterator *iter = m->private;
@@ -3237,7 +3372,7 @@ static void *
t_next(struct seq_file *m, void *v, loff_t *pos)
{
struct ftrace_iterator *iter = m->private;
- loff_t l = *pos; /* t_hash_start() must use original pos */
+ loff_t l = *pos; /* t_probe_start() must use original pos */
void *ret;
if (unlikely(ftrace_disabled))
@@ -3246,16 +3381,19 @@ t_next(struct seq_file *m, void *v, loff_t *pos)
if (iter->flags & FTRACE_ITER_PROBE)
return t_probe_next(m, pos);
+ if (iter->flags & FTRACE_ITER_MOD)
+ return t_mod_next(m, pos);
+
if (iter->flags & FTRACE_ITER_PRINTALL) {
/* next must increment pos, and t_probe_start does not */
(*pos)++;
- return t_probe_start(m, &l);
+ return t_mod_start(m, &l);
}
ret = t_func_next(m, pos);
if (!ret)
- return t_probe_start(m, &l);
+ return t_mod_start(m, &l);
return ret;
}
@@ -3264,7 +3402,7 @@ static void reset_iter_read(struct ftrace_iterator *iter)
{
iter->pos = 0;
iter->func_pos = 0;
- iter->flags &= ~(FTRACE_ITER_PRINTALL | FTRACE_ITER_PROBE);
+ iter->flags &= ~(FTRACE_ITER_PRINTALL | FTRACE_ITER_PROBE | FTRACE_ITER_MOD);
}
static void *t_start(struct seq_file *m, loff_t *pos)
@@ -3293,15 +3431,15 @@ static void *t_start(struct seq_file *m, loff_t *pos)
ftrace_hash_empty(iter->hash)) {
iter->func_pos = 1; /* Account for the message */
if (*pos > 0)
- return t_probe_start(m, pos);
+ return t_mod_start(m, pos);
iter->flags |= FTRACE_ITER_PRINTALL;
/* reset in case of seek/pread */
iter->flags &= ~FTRACE_ITER_PROBE;
return iter;
}
- if (iter->flags & FTRACE_ITER_PROBE)
- return t_probe_start(m, pos);
+ if (iter->flags & FTRACE_ITER_MOD)
+ return t_mod_start(m, pos);
/*
* Unfortunately, we need to restart at ftrace_pages_start
@@ -3317,7 +3455,7 @@ static void *t_start(struct seq_file *m, loff_t *pos)
}
if (!p)
- return t_probe_start(m, pos);
+ return t_mod_start(m, pos);
return iter;
}
@@ -3351,6 +3489,9 @@ static int t_show(struct seq_file *m, void *v)
if (iter->flags & FTRACE_ITER_PROBE)
return t_probe_show(m, iter);
+ if (iter->flags & FTRACE_ITER_MOD)
+ return t_mod_show(m, iter);
+
if (iter->flags & FTRACE_ITER_PRINTALL) {
if (iter->flags & FTRACE_ITER_NOTRACE)
seq_puts(m, "#### no functions disabled ####\n");
@@ -3457,6 +3598,8 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
{
struct ftrace_iterator *iter;
struct ftrace_hash *hash;
+ struct list_head *mod_head;
+ struct trace_array *tr = ops->private;
int ret = 0;
ftrace_ops_init(ops);
@@ -3475,21 +3618,29 @@ ftrace_regex_open(struct ftrace_ops *ops, int flag,
iter->ops = ops;
iter->flags = flag;
+ iter->tr = tr;
mutex_lock(&ops->func_hash->regex_lock);
- if (flag & FTRACE_ITER_NOTRACE)
+ if (flag & FTRACE_ITER_NOTRACE) {
hash = ops->func_hash->notrace_hash;
- else
+ mod_head = tr ? &tr->mod_notrace : NULL;
+ } else {
hash = ops->func_hash->filter_hash;
+ mod_head = tr ? &tr->mod_trace : NULL;
+ }
+
+ iter->mod_list = mod_head;
if (file->f_mode & FMODE_WRITE) {
const int size_bits = FTRACE_HASH_DEFAULT_BITS;
- if (file->f_flags & O_TRUNC)
+ if (file->f_flags & O_TRUNC) {
iter->hash = alloc_ftrace_hash(size_bits);
- else
+ clear_ftrace_mod_list(mod_head);
+ } else {
iter->hash = alloc_and_copy_ftrace_hash(size_bits, hash);
+ }
if (!iter->hash) {
trace_parser_put(&iter->parser);
@@ -3761,6 +3912,163 @@ static int ftrace_hash_move_and_update_ops(struct ftrace_ops *ops,
return ret;
}
+static bool module_exists(const char *module)
+{
+ /* All modules have the symbol __this_module */
+ const char this_mod[] = "__this_module";
+ const int modname_size = MAX_PARAM_PREFIX_LEN + sizeof(this_mod) + 1;
+ char modname[modname_size + 1];
+ unsigned long val;
+ int n;
+
+ n = snprintf(modname, modname_size + 1, "%s:%s", module, this_mod);
+
+ if (n > modname_size)
+ return false;
+
+ val = module_kallsyms_lookup_name(modname);
+ return val != 0;
+}
+
+static int cache_mod(struct trace_array *tr,
+ const char *func, char *module, int enable)
+{
+ struct ftrace_mod_load *ftrace_mod, *n;
+ struct list_head *head = enable ? &tr->mod_trace : &tr->mod_notrace;
+ int ret;
+
+ mutex_lock(&ftrace_lock);
+
+ /* We do not cache inverse filters */
+ if (func[0] == '!') {
+ func++;
+ ret = -EINVAL;
+
+ /* Look to remove this hash */
+ list_for_each_entry_safe(ftrace_mod, n, head, list) {
+ if (strcmp(ftrace_mod->module, module) != 0)
+ continue;
+
+ /* no func matches all */
+ if (!func || strcmp(func, "*") == 0 ||
+ (ftrace_mod->func &&
+ strcmp(ftrace_mod->func, func) == 0)) {
+ ret = 0;
+ free_ftrace_mod(ftrace_mod);
+ continue;
+ }
+ }
+ goto out;
+ }
+
+ ret = -EINVAL;
+ /* We only care about modules that have not been loaded yet */
+ if (module_exists(module))
+ goto out;
+
+ /* Save this string off, and execute it when the module is loaded */
+ ret = ftrace_add_mod(tr, func, module, enable);
+ out:
+ mutex_unlock(&ftrace_lock);
+
+ return ret;
+}
+
+static int
+ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
+ int reset, int enable);
+
+static void process_mod_list(struct list_head *head, struct ftrace_ops *ops,
+ char *mod, bool enable)
+{
+ struct ftrace_mod_load *ftrace_mod, *n;
+ struct ftrace_hash **orig_hash, *new_hash;
+ LIST_HEAD(process_mods);
+ char *func;
+ int ret;
+
+ mutex_lock(&ops->func_hash->regex_lock);
+
+ if (enable)
+ orig_hash = &ops->func_hash->filter_hash;
+ else
+ orig_hash = &ops->func_hash->notrace_hash;
+
+ new_hash = alloc_and_copy_ftrace_hash(FTRACE_HASH_DEFAULT_BITS,
+ *orig_hash);
+ if (!new_hash)
+ goto out; /* warn? */
+
+ mutex_lock(&ftrace_lock);
+
+ list_for_each_entry_safe(ftrace_mod, n, head, list) {
+
+ if (strcmp(ftrace_mod->module, mod) != 0)
+ continue;
+
+ if (ftrace_mod->func)
+ func = kstrdup(ftrace_mod->func, GFP_KERNEL);
+ else
+ func = kstrdup("*", GFP_KERNEL);
+
+ if (!func) /* warn? */
+ continue;
+
+ list_del(&ftrace_mod->list);
+ list_add(&ftrace_mod->list, &process_mods);
+
+ /* Use the newly allocated func, as it may be "*" */
+ kfree(ftrace_mod->func);
+ ftrace_mod->func = func;
+ }
+
+ mutex_unlock(&ftrace_lock);
+
+ list_for_each_entry_safe(ftrace_mod, n, &process_mods, list) {
+
+ func = ftrace_mod->func;
+
+ /* Grabs ftrace_lock, which is why we have this extra step */
+ match_records(new_hash, func, strlen(func), mod);
+ free_ftrace_mod(ftrace_mod);
+ }
+
+ if (enable && list_empty(head))
+ new_hash->flags &= ~FTRACE_HASH_FL_MOD;
+
+ mutex_lock(&ftrace_lock);
+
+ ret = ftrace_hash_move_and_update_ops(ops, orig_hash,
+ new_hash, enable);
+ mutex_unlock(&ftrace_lock);
+
+ out:
+ mutex_unlock(&ops->func_hash->regex_lock);
+
+ free_ftrace_hash(new_hash);
+}
+
+static void process_cached_mods(const char *mod_name)
+{
+ struct trace_array *tr;
+ char *mod;
+
+ mod = kstrdup(mod_name, GFP_KERNEL);
+ if (!mod)
+ return;
+
+ mutex_lock(&trace_types_lock);
+ list_for_each_entry(tr, &ftrace_trace_arrays, list) {
+ if (!list_empty(&tr->mod_trace))
+ process_mod_list(&tr->mod_trace, tr->ops, mod, true);
+ if (!list_empty(&tr->mod_notrace))
+ process_mod_list(&tr->mod_notrace, tr->ops, mod, false);
+ }
+ mutex_unlock(&trace_types_lock);
+
+ kfree(mod);
+}
+
/*
* We register the module command as a template to show others how
* to register the a command as well.
@@ -3768,10 +4076,16 @@ static int ftrace_hash_move_and_update_ops(struct ftrace_ops *ops,
static int
ftrace_mod_callback(struct trace_array *tr, struct ftrace_hash *hash,
- char *func, char *cmd, char *module, int enable)
+ char *func_orig, char *cmd, char *module, int enable)
{
+ char *func;
int ret;
+ /* match_records() modifies func, and we need the original */
+ func = kstrdup(func_orig, GFP_KERNEL);
+ if (!func)
+ return -ENOMEM;
+
/*
* cmd == 'mod' because we only registered this func
* for the 'mod' ftrace_func_command.
@@ -3780,8 +4094,10 @@ ftrace_mod_callback(struct trace_array *tr, struct ftrace_hash *hash,
* parameter.
*/
ret = match_records(hash, func, strlen(func), module);
+ kfree(func);
+
if (!ret)
- return -EINVAL;
+ return cache_mod(tr, func_orig, module, enable);
if (ret < 0)
return ret;
return 0;
@@ -4725,9 +5041,11 @@ int ftrace_regex_release(struct inode *inode, struct file *file)
if (file->f_mode & FMODE_WRITE) {
filter_hash = !!(iter->flags & FTRACE_ITER_FILTER);
- if (filter_hash)
+ if (filter_hash) {
orig_hash = &iter->ops->func_hash->filter_hash;
- else
+ if (iter->tr && !list_empty(&iter->tr->mod_trace))
+ iter->hash->flags |= FTRACE_HASH_FL_MOD;
+ } else
orig_hash = &iter->ops->func_hash->notrace_hash;
mutex_lock(&ftrace_lock);
@@ -5385,6 +5703,7 @@ void ftrace_release_mod(struct module *mod)
if (pg == ftrace_pages)
ftrace_pages = next_to_ftrace_page(last_pg);
+ ftrace_update_tot_cnt -= pg->index;
*last_pg = pg->next;
order = get_count_order(pg->size / ENTRIES_PER_PAGE);
free_pages((unsigned long)pg->records, order);
@@ -5463,6 +5782,8 @@ void ftrace_module_enable(struct module *mod)
out_unlock:
mutex_unlock(&ftrace_lock);
+
+ process_cached_mods(mod->name);
}
void ftrace_module_init(struct module *mod)
@@ -5501,6 +5822,7 @@ void __init ftrace_free_init_mem(void)
if (!rec)
continue;
pg->index--;
+ ftrace_update_tot_cnt--;
if (!pg->index) {
*last_pg = pg->next;
order = get_count_order(pg->size / ENTRIES_PER_PAGE);
@@ -5567,6 +5889,8 @@ static void ftrace_update_trampoline(struct ftrace_ops *ops)
void ftrace_init_trace_array(struct trace_array *tr)
{
INIT_LIST_HEAD(&tr->func_probes);
+ INIT_LIST_HEAD(&tr->mod_trace);
+ INIT_LIST_HEAD(&tr->mod_notrace);
}
#else
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 091e801145c9..00e2e4169b1e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -87,7 +87,7 @@ dummy_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set)
* tracing is active, only save the comm when a trace event
* occurred.
*/
-static DEFINE_PER_CPU(bool, trace_cmdline_save);
+static DEFINE_PER_CPU(bool, trace_taskinfo_save);
/*
* Kill all tracing for good (never come back).
@@ -120,41 +120,41 @@ enum ftrace_dump_mode ftrace_dump_on_oops;
/* When set, tracing will stop when a WARN*() is hit */
int __disable_trace_on_warning;
-#ifdef CONFIG_TRACE_ENUM_MAP_FILE
-/* Map of enums to their values, for "enum_map" file */
-struct trace_enum_map_head {
+#ifdef CONFIG_TRACE_EVAL_MAP_FILE
+/* Map of enums to their values, for "eval_map" file */
+struct trace_eval_map_head {
struct module *mod;
unsigned long length;
};
-union trace_enum_map_item;
+union trace_eval_map_item;
-struct trace_enum_map_tail {
+struct trace_eval_map_tail {
/*
* "end" is first and points to NULL as it must be different
- * than "mod" or "enum_string"
+ * than "mod" or "eval_string"
*/
- union trace_enum_map_item *next;
+ union trace_eval_map_item *next;
const char *end; /* points to NULL */
};
-static DEFINE_MUTEX(trace_enum_mutex);
+static DEFINE_MUTEX(trace_eval_mutex);
/*
- * The trace_enum_maps are saved in an array with two extra elements,
+ * The trace_eval_maps are saved in an array with two extra elements,
* one at the beginning, and one at the end. The beginning item contains
* the count of the saved maps (head.length), and the module they
* belong to if not built in (head.mod). The ending item contains a
- * pointer to the next array of saved enum_map items.
+ * pointer to the next array of saved eval_map items.
*/
-union trace_enum_map_item {
- struct trace_enum_map map;
- struct trace_enum_map_head head;
- struct trace_enum_map_tail tail;
+union trace_eval_map_item {
+ struct trace_eval_map map;
+ struct trace_eval_map_head head;
+ struct trace_eval_map_tail tail;
};
-static union trace_enum_map_item *trace_enum_maps;
-#endif /* CONFIG_TRACE_ENUM_MAP_FILE */
+static union trace_eval_map_item *trace_eval_maps;
+#endif /* CONFIG_TRACE_EVAL_MAP_FILE */
static int tracing_set_tracer(struct trace_array *tr, const char *buf);
@@ -790,7 +790,7 @@ EXPORT_SYMBOL_GPL(tracing_on);
static __always_inline void
__buffer_unlock_commit(struct ring_buffer *buffer, struct ring_buffer_event *event)
{
- __this_cpu_write(trace_cmdline_save, true);
+ __this_cpu_write(trace_taskinfo_save, true);
/* If this is the temp buffer, we need to commit fully */
if (this_cpu_read(trace_buffered_event) == event) {
@@ -1141,9 +1141,9 @@ unsigned long nsecs_to_usecs(unsigned long nsecs)
/*
* TRACE_FLAGS is defined as a tuple matching bit masks with strings.
- * It uses C(a, b) where 'a' is the enum name and 'b' is the string that
+ * It uses C(a, b) where 'a' is the eval (enum) name and 'b' is the string that
* matches it. By defining "C(a, b) b", TRACE_FLAGS becomes a list
- * of strings in the order that the enums were defined.
+ * of strings in the order that the evals (enum) were defined.
*/
#undef C
#define C(a, b) b
@@ -1709,6 +1709,8 @@ void tracing_reset_all_online_cpus(void)
}
}
+static int *tgid_map;
+
#define SAVED_CMDLINES_DEFAULT 128
#define NO_CMDLINE_MAP UINT_MAX
static arch_spinlock_t trace_cmdline_lock = __ARCH_SPIN_LOCK_UNLOCKED;
@@ -1722,7 +1724,7 @@ struct saved_cmdlines_buffer {
static struct saved_cmdlines_buffer *savedcmd;
/* temporary disable recording */
-static atomic_t trace_record_cmdline_disabled __read_mostly;
+static atomic_t trace_record_taskinfo_disabled __read_mostly;
static inline char *get_saved_cmdlines(int idx)
{
@@ -1910,8 +1912,6 @@ static void tracing_stop_tr(struct trace_array *tr)
raw_spin_unlock_irqrestore(&tr->start_lock, flags);
}
-void trace_stop_cmdline_recording(void);
-
static int trace_save_cmdline(struct task_struct *tsk)
{
unsigned pid, idx;
@@ -1992,16 +1992,87 @@ void trace_find_cmdline(int pid, char comm[])
preempt_enable();
}
-void tracing_record_cmdline(struct task_struct *tsk)
+int trace_find_tgid(int pid)
+{
+ if (unlikely(!tgid_map || !pid || pid > PID_MAX_DEFAULT))
+ return 0;
+
+ return tgid_map[pid];
+}
+
+static int trace_save_tgid(struct task_struct *tsk)
+{
+ if (unlikely(!tgid_map || !tsk->pid || tsk->pid > PID_MAX_DEFAULT))
+ return 0;
+
+ tgid_map[tsk->pid] = tsk->tgid;
+ return 1;
+}
+
+static bool tracing_record_taskinfo_skip(int flags)
+{
+ if (unlikely(!(flags & (TRACE_RECORD_CMDLINE | TRACE_RECORD_TGID))))
+ return true;
+ if (atomic_read(&trace_record_taskinfo_disabled) || !tracing_is_on())
+ return true;
+ if (!__this_cpu_read(trace_taskinfo_save))
+ return true;
+ return false;
+}
+
+/**
+ * tracing_record_taskinfo - record the task info of a task
+ *
+ * @task - task to record
+ * @flags - TRACE_RECORD_CMDLINE for recording comm
+ * - TRACE_RECORD_TGID for recording tgid
+ */
+void tracing_record_taskinfo(struct task_struct *task, int flags)
+{
+ if (tracing_record_taskinfo_skip(flags))
+ return;
+ if ((flags & TRACE_RECORD_CMDLINE) && !trace_save_cmdline(task))
+ return;
+ if ((flags & TRACE_RECORD_TGID) && !trace_save_tgid(task))
+ return;
+
+ __this_cpu_write(trace_taskinfo_save, false);
+}
+
+/**
+ * tracing_record_taskinfo_sched_switch - record task info for sched_switch
+ *
+ * @prev - previous task during sched_switch
+ * @next - next task during sched_switch
+ * @flags - TRACE_RECORD_CMDLINE for recording comm
+ * TRACE_RECORD_TGID for recording tgid
+ */
+void tracing_record_taskinfo_sched_switch(struct task_struct *prev,
+ struct task_struct *next, int flags)
{
- if (atomic_read(&trace_record_cmdline_disabled) || !tracing_is_on())
+ if (tracing_record_taskinfo_skip(flags))
+ return;
+
+ if ((flags & TRACE_RECORD_CMDLINE) &&
+ (!trace_save_cmdline(prev) || !trace_save_cmdline(next)))
return;
- if (!__this_cpu_read(trace_cmdline_save))
+ if ((flags & TRACE_RECORD_TGID) &&
+ (!trace_save_tgid(prev) || !trace_save_tgid(next)))
return;
- if (trace_save_cmdline(tsk))
- __this_cpu_write(trace_cmdline_save, false);
+ __this_cpu_write(trace_taskinfo_save, false);
+}
+
+/* Helpers to record a specific task information */
+void tracing_record_cmdline(struct task_struct *task)
+{
+ tracing_record_taskinfo(task, TRACE_RECORD_CMDLINE);
+}
+
+void tracing_record_tgid(struct task_struct *task)
+{
+ tracing_record_taskinfo(task, TRACE_RECORD_TGID);
}
/*
@@ -3146,7 +3217,7 @@ static void *s_start(struct seq_file *m, loff_t *pos)
#endif
if (!iter->snapshot)
- atomic_inc(&trace_record_cmdline_disabled);
+ atomic_inc(&trace_record_taskinfo_disabled);
if (*pos != iter->pos) {
iter->ent = NULL;
@@ -3191,7 +3262,7 @@ static void s_stop(struct seq_file *m, void *p)
#endif
if (!iter->snapshot)
- atomic_dec(&trace_record_cmdline_disabled);
+ atomic_dec(&trace_record_taskinfo_disabled);
trace_access_unlock(iter->cpu_file);
trace_event_read_unlock();
@@ -3248,23 +3319,29 @@ static void print_event_info(struct trace_buffer *buf, struct seq_file *m)
seq_puts(m, "#\n");
}
-static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m)
+static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m,
+ unsigned int flags)
{
+ bool tgid = flags & TRACE_ITER_RECORD_TGID;
+
print_event_info(buf, m);
- seq_puts(m, "# TASK-PID CPU# TIMESTAMP FUNCTION\n"
- "# | | | | |\n");
+
+ seq_printf(m, "# TASK-PID CPU# %s TIMESTAMP FUNCTION\n", tgid ? "TGID " : "");
+ seq_printf(m, "# | | | %s | |\n", tgid ? " | " : "");
}
-static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m)
+static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m,
+ unsigned int flags)
{
- print_event_info(buf, m);
- seq_puts(m, "# _-----=> irqs-off\n"
- "# / _----=> need-resched\n"
- "# | / _---=> hardirq/softirq\n"
- "# || / _--=> preempt-depth\n"
- "# ||| / delay\n"
- "# TASK-PID CPU# |||| TIMESTAMP FUNCTION\n"
- "# | | | |||| | |\n");
+ bool tgid = flags & TRACE_ITER_RECORD_TGID;
+
+ seq_printf(m, "# %s _-----=> irqs-off\n", tgid ? " " : "");
+ seq_printf(m, "# %s / _----=> need-resched\n", tgid ? " " : "");
+ seq_printf(m, "# %s| / _---=> hardirq/softirq\n", tgid ? " " : "");
+ seq_printf(m, "# %s|| / _--=> preempt-depth\n", tgid ? " " : "");
+ seq_printf(m, "# %s||| / delay\n", tgid ? " " : "");
+ seq_printf(m, "# TASK-PID CPU#%s|||| TIMESTAMP FUNCTION\n", tgid ? " TGID " : "");
+ seq_printf(m, "# | | | %s|||| | |\n", tgid ? " | " : "");
}
void
@@ -3580,9 +3657,11 @@ void trace_default_header(struct seq_file *m)
} else {
if (!(trace_flags & TRACE_ITER_VERBOSE)) {
if (trace_flags & TRACE_ITER_IRQ_INFO)
- print_func_help_header_irq(iter->trace_buffer, m);
+ print_func_help_header_irq(iter->trace_buffer,
+ m, trace_flags);
else
- print_func_help_header(iter->trace_buffer, m);
+ print_func_help_header(iter->trace_buffer, m,
+ trace_flags);
}
}
}
@@ -4238,6 +4317,18 @@ int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled)
if (mask == TRACE_ITER_RECORD_CMD)
trace_event_enable_cmd_record(enabled);
+ if (mask == TRACE_ITER_RECORD_TGID) {
+ if (!tgid_map)
+ tgid_map = kzalloc((PID_MAX_DEFAULT + 1) * sizeof(*tgid_map),
+ GFP_KERNEL);
+ if (!tgid_map) {
+ tr->trace_flags &= ~TRACE_ITER_RECORD_TGID;
+ return -ENOMEM;
+ }
+
+ trace_event_enable_tgid_record(enabled);
+ }
+
if (mask == TRACE_ITER_EVENT_FORK)
trace_event_follow_fork(tr, enabled);
@@ -4746,11 +4837,11 @@ static const struct file_operations tracing_saved_cmdlines_size_fops = {
.write = tracing_saved_cmdlines_size_write,
};
-#ifdef CONFIG_TRACE_ENUM_MAP_FILE
-static union trace_enum_map_item *
-update_enum_map(union trace_enum_map_item *ptr)
+#ifdef CONFIG_TRACE_EVAL_MAP_FILE
+static union trace_eval_map_item *
+update_eval_map(union trace_eval_map_item *ptr)
{
- if (!ptr->map.enum_string) {
+ if (!ptr->map.eval_string) {
if (ptr->tail.next) {
ptr = ptr->tail.next;
/* Set ptr to the next real item (skip head) */
@@ -4761,15 +4852,15 @@ update_enum_map(union trace_enum_map_item *ptr)
return ptr;
}
-static void *enum_map_next(struct seq_file *m, void *v, loff_t *pos)
+static void *eval_map_next(struct seq_file *m, void *v, loff_t *pos)
{
- union trace_enum_map_item *ptr = v;
+ union trace_eval_map_item *ptr = v;
/*
* Paranoid! If ptr points to end, we don't want to increment past it.
* This really should never happen.
*/
- ptr = update_enum_map(ptr);
+ ptr = update_eval_map(ptr);
if (WARN_ON_ONCE(!ptr))
return NULL;
@@ -4777,104 +4868,104 @@ static void *enum_map_next(struct seq_file *m, void *v, loff_t *pos)
(*pos)++;
- ptr = update_enum_map(ptr);
+ ptr = update_eval_map(ptr);
return ptr;
}
-static void *enum_map_start(struct seq_file *m, loff_t *pos)
+static void *eval_map_start(struct seq_file *m, loff_t *pos)
{
- union trace_enum_map_item *v;
+ union trace_eval_map_item *v;
loff_t l = 0;
- mutex_lock(&trace_enum_mutex);
+ mutex_lock(&trace_eval_mutex);
- v = trace_enum_maps;
+ v = trace_eval_maps;
if (v)
v++;
while (v && l < *pos) {
- v = enum_map_next(m, v, &l);
+ v = eval_map_next(m, v, &l);
}
return v;
}
-static void enum_map_stop(struct seq_file *m, void *v)
+static void eval_map_stop(struct seq_file *m, void *v)
{
- mutex_unlock(&trace_enum_mutex);
+ mutex_unlock(&trace_eval_mutex);
}
-static int enum_map_show(struct seq_file *m, void *v)
+static int eval_map_show(struct seq_file *m, void *v)
{
- union trace_enum_map_item *ptr = v;
+ union trace_eval_map_item *ptr = v;
seq_printf(m, "%s %ld (%s)\n",
- ptr->map.enum_string, ptr->map.enum_value,
+ ptr->map.eval_string, ptr->map.eval_value,
ptr->map.system);
return 0;
}
-static const struct seq_operations tracing_enum_map_seq_ops = {
- .start = enum_map_start,
- .next = enum_map_next,
- .stop = enum_map_stop,
- .show = enum_map_show,
+static const struct seq_operations tracing_eval_map_seq_ops = {
+ .start = eval_map_start,
+ .next = eval_map_next,
+ .stop = eval_map_stop,
+ .show = eval_map_show,
};
-static int tracing_enum_map_open(struct inode *inode, struct file *filp)
+static int tracing_eval_map_open(struct inode *inode, struct file *filp)
{
if (tracing_disabled)
return -ENODEV;
- return seq_open(filp, &tracing_enum_map_seq_ops);
+ return seq_open(filp, &tracing_eval_map_seq_ops);
}
-static const struct file_operations tracing_enum_map_fops = {
- .open = tracing_enum_map_open,
+static const struct file_operations tracing_eval_map_fops = {
+ .open = tracing_eval_map_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
-static inline union trace_enum_map_item *
-trace_enum_jmp_to_tail(union trace_enum_map_item *ptr)
+static inline union trace_eval_map_item *
+trace_eval_jmp_to_tail(union trace_eval_map_item *ptr)
{
/* Return tail of array given the head */
return ptr + ptr->head.length + 1;
}
static void
-trace_insert_enum_map_file(struct module *mod, struct trace_enum_map **start,
+trace_insert_eval_map_file(struct module *mod, struct trace_eval_map **start,
int len)
{
- struct trace_enum_map **stop;
- struct trace_enum_map **map;
- union trace_enum_map_item *map_array;
- union trace_enum_map_item *ptr;
+ struct trace_eval_map **stop;
+ struct trace_eval_map **map;
+ union trace_eval_map_item *map_array;
+ union trace_eval_map_item *ptr;
stop = start + len;
/*
- * The trace_enum_maps contains the map plus a head and tail item,
+ * The trace_eval_maps contains the map plus a head and tail item,
* where the head holds the module and length of array, and the
* tail holds a pointer to the next list.
*/
map_array = kmalloc(sizeof(*map_array) * (len + 2), GFP_KERNEL);
if (!map_array) {
- pr_warn("Unable to allocate trace enum mapping\n");
+ pr_warn("Unable to allocate trace eval mapping\n");
return;
}
- mutex_lock(&trace_enum_mutex);
+ mutex_lock(&trace_eval_mutex);
- if (!trace_enum_maps)
- trace_enum_maps = map_array;
+ if (!trace_eval_maps)
+ trace_eval_maps = map_array;
else {
- ptr = trace_enum_maps;
+ ptr = trace_eval_maps;
for (;;) {
- ptr = trace_enum_jmp_to_tail(ptr);
+ ptr = trace_eval_jmp_to_tail(ptr);
if (!ptr->tail.next)
break;
ptr = ptr->tail.next;
@@ -4892,34 +4983,34 @@ trace_insert_enum_map_file(struct module *mod, struct trace_enum_map **start,
}
memset(map_array, 0, sizeof(*map_array));
- mutex_unlock(&trace_enum_mutex);
+ mutex_unlock(&trace_eval_mutex);
}
-static void trace_create_enum_file(struct dentry *d_tracer)
+static void trace_create_eval_file(struct dentry *d_tracer)
{
- trace_create_file("enum_map", 0444, d_tracer,
- NULL, &tracing_enum_map_fops);
+ trace_create_file("eval_map", 0444, d_tracer,
+ NULL, &tracing_eval_map_fops);
}
-#else /* CONFIG_TRACE_ENUM_MAP_FILE */
-static inline void trace_create_enum_file(struct dentry *d_tracer) { }
-static inline void trace_insert_enum_map_file(struct module *mod,
- struct trace_enum_map **start, int len) { }
-#endif /* !CONFIG_TRACE_ENUM_MAP_FILE */
+#else /* CONFIG_TRACE_EVAL_MAP_FILE */
+static inline void trace_create_eval_file(struct dentry *d_tracer) { }
+static inline void trace_insert_eval_map_file(struct module *mod,
+ struct trace_eval_map **start, int len) { }
+#endif /* !CONFIG_TRACE_EVAL_MAP_FILE */
-static void trace_insert_enum_map(struct module *mod,
- struct trace_enum_map **start, int len)
+static void trace_insert_eval_map(struct module *mod,
+ struct trace_eval_map **start, int len)
{
- struct trace_enum_map **map;
+ struct trace_eval_map **map;
if (len <= 0)
return;
map = start;
- trace_event_enum_update(map, len);
+ trace_event_eval_update(map, len);
- trace_insert_enum_map_file(mod, start, len);
+ trace_insert_eval_map_file(mod, start, len);
}
static ssize_t
@@ -6739,33 +6830,18 @@ static const struct file_operations tracing_stats_fops = {
#ifdef CONFIG_DYNAMIC_FTRACE
-int __weak ftrace_arch_read_dyn_info(char *buf, int size)
-{
- return 0;
-}
-
static ssize_t
tracing_read_dyn_info(struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos)
{
- static char ftrace_dyn_info_buffer[1024];
- static DEFINE_MUTEX(dyn_info_mutex);
unsigned long *p = filp->private_data;
- char *buf = ftrace_dyn_info_buffer;
- int size = ARRAY_SIZE(ftrace_dyn_info_buffer);
+ char buf[64]; /* Not too big for a shallow stack */
int r;
- mutex_lock(&dyn_info_mutex);
- r = sprintf(buf, "%ld ", *p);
-
- r += ftrace_arch_read_dyn_info(buf+r, (size-1)-r);
+ r = scnprintf(buf, 63, "%ld", *p);
buf[r++] = '\n';
- r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
-
- mutex_unlock(&dyn_info_mutex);
-
- return r;
+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
}
static const struct file_operations tracing_dyn_info_fops = {
@@ -7737,21 +7813,21 @@ struct dentry *tracing_init_dentry(void)
return NULL;
}
-extern struct trace_enum_map *__start_ftrace_enum_maps[];
-extern struct trace_enum_map *__stop_ftrace_enum_maps[];
+extern struct trace_eval_map *__start_ftrace_eval_maps[];
+extern struct trace_eval_map *__stop_ftrace_eval_maps[];
-static void __init trace_enum_init(void)
+static void __init trace_eval_init(void)
{
int len;
- len = __stop_ftrace_enum_maps - __start_ftrace_enum_maps;
- trace_insert_enum_map(NULL, __start_ftrace_enum_maps, len);
+ len = __stop_ftrace_eval_maps - __start_ftrace_eval_maps;
+ trace_insert_eval_map(NULL, __start_ftrace_eval_maps, len);
}
#ifdef CONFIG_MODULES
-static void trace_module_add_enums(struct module *mod)
+static void trace_module_add_evals(struct module *mod)
{
- if (!mod->num_trace_enums)
+ if (!mod->num_trace_evals)
return;
/*
@@ -7761,40 +7837,40 @@ static void trace_module_add_enums(struct module *mod)
if (trace_module_has_bad_taint(mod))
return;
- trace_insert_enum_map(mod, mod->trace_enums, mod->num_trace_enums);
+ trace_insert_eval_map(mod, mod->trace_evals, mod->num_trace_evals);
}
-#ifdef CONFIG_TRACE_ENUM_MAP_FILE
-static void trace_module_remove_enums(struct module *mod)
+#ifdef CONFIG_TRACE_EVAL_MAP_FILE
+static void trace_module_remove_evals(struct module *mod)
{
- union trace_enum_map_item *map;
- union trace_enum_map_item **last = &trace_enum_maps;
+ union trace_eval_map_item *map;
+ union trace_eval_map_item **last = &trace_eval_maps;
- if (!mod->num_trace_enums)
+ if (!mod->num_trace_evals)
return;
- mutex_lock(&trace_enum_mutex);
+ mutex_lock(&trace_eval_mutex);
- map = trace_enum_maps;
+ map = trace_eval_maps;
while (map) {
if (map->head.mod == mod)
break;
- map = trace_enum_jmp_to_tail(map);
+ map = trace_eval_jmp_to_tail(map);
last = &map->tail.next;
map = map->tail.next;
}
if (!map)
goto out;
- *last = trace_enum_jmp_to_tail(map)->tail.next;
+ *last = trace_eval_jmp_to_tail(map)->tail.next;
kfree(map);
out:
- mutex_unlock(&trace_enum_mutex);
+ mutex_unlock(&trace_eval_mutex);
}
#else
-static inline void trace_module_remove_enums(struct module *mod) { }
-#endif /* CONFIG_TRACE_ENUM_MAP_FILE */
+static inline void trace_module_remove_evals(struct module *mod) { }
+#endif /* CONFIG_TRACE_EVAL_MAP_FILE */
static int trace_module_notify(struct notifier_block *self,
unsigned long val, void *data)
@@ -7803,10 +7879,10 @@ static int trace_module_notify(struct notifier_block *self,
switch (val) {
case MODULE_STATE_COMING:
- trace_module_add_enums(mod);
+ trace_module_add_evals(mod);
break;
case MODULE_STATE_GOING:
- trace_module_remove_enums(mod);
+ trace_module_remove_evals(mod);
break;
}
@@ -7844,9 +7920,9 @@ static __init int tracer_init_tracefs(void)
trace_create_file("saved_cmdlines_size", 0644, d_tracer,
NULL, &tracing_saved_cmdlines_size_fops);
- trace_enum_init();
+ trace_eval_init();
- trace_create_enum_file(d_tracer);
+ trace_create_eval_file(d_tracer);
#ifdef CONFIG_MODULES
register_module_notifier(&trace_module_nb);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 39fd77330aab..6ade1c55cc3a 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -263,7 +263,10 @@ struct trace_array {
struct ftrace_ops *ops;
struct trace_pid_list __rcu *function_pids;
#ifdef CONFIG_DYNAMIC_FTRACE
+ /* All of these are protected by the ftrace_lock */
struct list_head func_probes;
+ struct list_head mod_trace;
+ struct list_head mod_notrace;
#endif
/* function tracing enabled */
int function_enabled;
@@ -637,6 +640,9 @@ void set_graph_array(struct trace_array *tr);
void tracing_start_cmdline_record(void);
void tracing_stop_cmdline_record(void);
+void tracing_start_tgid_record(void);
+void tracing_stop_tgid_record(void);
+
int register_tracer(struct tracer *type);
int is_tracing_stopped(void);
@@ -697,6 +703,7 @@ static inline void __trace_stack(struct trace_array *tr, unsigned long flags,
extern u64 ftrace_now(int cpu);
extern void trace_find_cmdline(int pid, char comm[]);
+extern int trace_find_tgid(int pid);
extern void trace_event_follow_fork(struct trace_array *tr, bool enable);
#ifdef CONFIG_DYNAMIC_FTRACE
@@ -761,10 +768,24 @@ enum print_line_t print_trace_line(struct trace_iterator *iter);
extern char trace_find_mark(unsigned long long duration);
+struct ftrace_hash;
+
+struct ftrace_mod_load {
+ struct list_head list;
+ char *func;
+ char *module;
+ int enable;
+};
+
+enum {
+ FTRACE_HASH_FL_MOD = (1 << 0),
+};
+
struct ftrace_hash {
unsigned long size_bits;
struct hlist_head *buckets;
unsigned long count;
+ unsigned long flags;
struct rcu_head rcu;
};
@@ -773,7 +794,7 @@ ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip);
static __always_inline bool ftrace_hash_empty(struct ftrace_hash *hash)
{
- return !hash || !hash->count;
+ return !hash || !(hash->count || (hash->flags & FTRACE_HASH_FL_MOD));
}
/* Standard output formatting function used for function return traces */
@@ -1107,6 +1128,7 @@ extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
C(CONTEXT_INFO, "context-info"), /* Print pid/cpu/time */ \
C(LATENCY_FMT, "latency-format"), \
C(RECORD_CMD, "record-cmd"), \
+ C(RECORD_TGID, "record-tgid"), \
C(OVERWRITE, "overwrite"), \
C(STOP_ON_FREE, "disable_on_free"), \
C(IRQ_INFO, "irq-info"), \
@@ -1423,6 +1445,8 @@ struct ftrace_event_field *
trace_find_event_field(struct trace_event_call *call, char *name);
extern void trace_event_enable_cmd_record(bool enable);
+extern void trace_event_enable_tgid_record(bool enable);
+
extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr);
extern int event_trace_del_tracer(struct trace_array *tr);
@@ -1773,10 +1797,10 @@ static inline const char *get_syscall_name(int syscall)
#ifdef CONFIG_EVENT_TRACING
void trace_event_init(void);
-void trace_event_enum_update(struct trace_enum_map **map, int len);
+void trace_event_eval_update(struct trace_eval_map **map, int len);
#else
static inline void __init trace_event_init(void) { }
-static inline void trace_event_enum_update(struct trace_enum_map **map, int len) { }
+static inline void trace_event_eval_update(struct trace_eval_map **map, int len) { }
#endif
extern struct trace_iterator *tracepoint_print_iter;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index e7973e10398c..36132f9280e6 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -343,6 +343,28 @@ void trace_event_enable_cmd_record(bool enable)
mutex_unlock(&event_mutex);
}
+void trace_event_enable_tgid_record(bool enable)
+{
+ struct trace_event_file *file;
+ struct trace_array *tr;
+
+ mutex_lock(&event_mutex);
+ do_for_each_event_file(tr, file) {
+ if (!(file->flags & EVENT_FILE_FL_ENABLED))
+ continue;
+
+ if (enable) {
+ tracing_start_tgid_record();
+ set_bit(EVENT_FILE_FL_RECORDED_TGID_BIT, &file->flags);
+ } else {
+ tracing_stop_tgid_record();
+ clear_bit(EVENT_FILE_FL_RECORDED_TGID_BIT,
+ &file->flags);
+ }
+ } while_for_each_event_file();
+ mutex_unlock(&event_mutex);
+}
+
static int __ftrace_event_enable_disable(struct trace_event_file *file,
int enable, int soft_disable)
{
@@ -381,6 +403,12 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
tracing_stop_cmdline_record();
clear_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags);
}
+
+ if (file->flags & EVENT_FILE_FL_RECORDED_TGID) {
+ tracing_stop_tgid_record();
+ clear_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags);
+ }
+
call->class->reg(call, TRACE_REG_UNREGISTER, file);
}
/* If in SOFT_MODE, just set the SOFT_DISABLE_BIT, else clear it */
@@ -407,18 +435,30 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
}
if (!(file->flags & EVENT_FILE_FL_ENABLED)) {
+ bool cmd = false, tgid = false;
/* Keep the event disabled, when going to SOFT_MODE. */
if (soft_disable)
set_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags);
if (tr->trace_flags & TRACE_ITER_RECORD_CMD) {
+ cmd = true;
tracing_start_cmdline_record();
set_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags);
}
+
+ if (tr->trace_flags & TRACE_ITER_RECORD_TGID) {
+ tgid = true;
+ tracing_start_tgid_record();
+ set_bit(EVENT_FILE_FL_RECORDED_TGID_BIT, &file->flags);
+ }
+
ret = call->class->reg(call, TRACE_REG_REGISTER, file);
if (ret) {
- tracing_stop_cmdline_record();
+ if (cmd)
+ tracing_stop_cmdline_record();
+ if (tgid)
+ tracing_stop_tgid_record();
pr_info("event trace: Could not enable event "
"%s\n", trace_event_name(call));
break;
@@ -2067,18 +2107,18 @@ __register_event(struct trace_event_call *call, struct module *mod)
return 0;
}
-static char *enum_replace(char *ptr, struct trace_enum_map *map, int len)
+static char *eval_replace(char *ptr, struct trace_eval_map *map, int len)
{
int rlen;
int elen;
- /* Find the length of the enum value as a string */
- elen = snprintf(ptr, 0, "%ld", map->enum_value);
+ /* Find the length of the eval value as a string */
+ elen = snprintf(ptr, 0, "%ld", map->eval_value);
/* Make sure there's enough room to replace the string with the value */
if (len < elen)
return NULL;
- snprintf(ptr, elen + 1, "%ld", map->enum_value);
+ snprintf(ptr, elen + 1, "%ld", map->eval_value);
/* Get the rest of the string of ptr */
rlen = strlen(ptr + len);
@@ -2090,11 +2130,11 @@ static char *enum_replace(char *ptr, struct trace_enum_map *map, int len)
}
static void update_event_printk(struct trace_event_call *call,
- struct trace_enum_map *map)
+ struct trace_eval_map *map)
{
char *ptr;
int quote = 0;
- int len = strlen(map->enum_string);
+ int len = strlen(map->eval_string);
for (ptr = call->print_fmt; *ptr; ptr++) {
if (*ptr == '\\') {
@@ -2125,16 +2165,16 @@ static void update_event_printk(struct trace_event_call *call,
continue;
}
if (isalpha(*ptr) || *ptr == '_') {
- if (strncmp(map->enum_string, ptr, len) == 0 &&
+ if (strncmp(map->eval_string, ptr, len) == 0 &&
!isalnum(ptr[len]) && ptr[len] != '_') {
- ptr = enum_replace(ptr, map, len);
- /* Hmm, enum string smaller than value */
+ ptr = eval_replace(ptr, map, len);
+ /* enum/sizeof string smaller than value */
if (WARN_ON_ONCE(!ptr))
return;
/*
- * No need to decrement here, as enum_replace()
+ * No need to decrement here, as eval_replace()
* returns the pointer to the character passed
- * the enum, and two enums can not be placed
+ * the eval, and two evals can not be placed
* back to back without something in between.
* We can skip that something in between.
*/
@@ -2165,7 +2205,7 @@ static void update_event_printk(struct trace_event_call *call,
}
}
-void trace_event_enum_update(struct trace_enum_map **map, int len)
+void trace_event_eval_update(struct trace_eval_map **map, int len)
{
struct trace_event_call *call, *p;
const char *last_system = NULL;
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 08f9bab8089e..bac629af2285 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -340,31 +340,41 @@ static inline const char *kretprobed(const char *name)
static void
seq_print_sym_short(struct trace_seq *s, const char *fmt, unsigned long address)
{
-#ifdef CONFIG_KALLSYMS
char str[KSYM_SYMBOL_LEN];
+#ifdef CONFIG_KALLSYMS
const char *name;
kallsyms_lookup(address, NULL, NULL, NULL, str);
name = kretprobed(str);
- trace_seq_printf(s, fmt, name);
+ if (name && strlen(name)) {
+ trace_seq_printf(s, fmt, name);
+ return;
+ }
#endif
+ snprintf(str, KSYM_SYMBOL_LEN, "0x%08lx", address);
+ trace_seq_printf(s, fmt, str);
}
static void
seq_print_sym_offset(struct trace_seq *s, const char *fmt,
unsigned long address)
{
-#ifdef CONFIG_KALLSYMS
char str[KSYM_SYMBOL_LEN];
+#ifdef CONFIG_KALLSYMS
const char *name;
sprint_symbol(str, address);
name = kretprobed(str);
- trace_seq_printf(s, fmt, name);
+ if (name && strlen(name)) {
+ trace_seq_printf(s, fmt, name);
+ return;
+ }
#endif
+ snprintf(str, KSYM_SYMBOL_LEN, "0x%08lx", address);
+ trace_seq_printf(s, fmt, str);
}
#ifndef CONFIG_64BIT
@@ -587,6 +597,15 @@ int trace_print_context(struct trace_iterator *iter)
trace_seq_printf(s, "%16s-%-5d [%03d] ",
comm, entry->pid, iter->cpu);
+ if (tr->trace_flags & TRACE_ITER_RECORD_TGID) {
+ unsigned int tgid = trace_find_tgid(entry->pid);
+
+ if (!tgid)
+ trace_seq_printf(s, "(-----) ");
+ else
+ trace_seq_printf(s, "(%5d) ", tgid);
+ }
+
if (tr->trace_flags & TRACE_ITER_IRQ_INFO)
trace_print_lat_fmt(s, entry);
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 4c896a0101bd..b341c02730be 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -12,27 +12,38 @@
#include "trace.h"
-static int sched_ref;
+#define RECORD_CMDLINE 1
+#define RECORD_TGID 2
+
+static int sched_cmdline_ref;
+static int sched_tgid_ref;
static DEFINE_MUTEX(sched_register_mutex);
static void
probe_sched_switch(void *ignore, bool preempt,
struct task_struct *prev, struct task_struct *next)
{
- if (unlikely(!sched_ref))
- return;
+ int flags;
+
+ flags = (RECORD_TGID * !!sched_tgid_ref) +
+ (RECORD_CMDLINE * !!sched_cmdline_ref);
- tracing_record_cmdline(prev);
- tracing_record_cmdline(next);
+ if (!flags)
+ return;
+ tracing_record_taskinfo_sched_switch(prev, next, flags);
}
static void
probe_sched_wakeup(void *ignore, struct task_struct *wakee)
{
- if (unlikely(!sched_ref))
- return;
+ int flags;
+
+ flags = (RECORD_TGID * !!sched_tgid_ref) +
+ (RECORD_CMDLINE * !!sched_cmdline_ref);
- tracing_record_cmdline(current);
+ if (!flags)
+ return;
+ tracing_record_taskinfo(current, flags);
}
static int tracing_sched_register(void)
@@ -75,28 +86,61 @@ static void tracing_sched_unregister(void)
unregister_trace_sched_wakeup(probe_sched_wakeup, NULL);
}
-static void tracing_start_sched_switch(void)
+static void tracing_start_sched_switch(int ops)
{
+ bool sched_register = (!sched_cmdline_ref && !sched_tgid_ref);
mutex_lock(&sched_register_mutex);
- if (!(sched_ref++))
+
+ switch (ops) {
+ case RECORD_CMDLINE:
+ sched_cmdline_ref++;
+ break;
+
+ case RECORD_TGID:
+ sched_tgid_ref++;
+ break;
+ }
+
+ if (sched_register && (sched_cmdline_ref || sched_tgid_ref))
tracing_sched_register();
mutex_unlock(&sched_register_mutex);
}
-static void tracing_stop_sched_switch(void)
+static void tracing_stop_sched_switch(int ops)
{
mutex_lock(&sched_register_mutex);
- if (!(--sched_ref))
+
+ switch (ops) {
+ case RECORD_CMDLINE:
+ sched_cmdline_ref--;
+ break;
+
+ case RECORD_TGID:
+ sched_tgid_ref--;
+ break;
+ }
+
+ if (!sched_cmdline_ref && !sched_tgid_ref)
tracing_sched_unregister();
mutex_unlock(&sched_register_mutex);
}
void tracing_start_cmdline_record(void)
{
- tracing_start_sched_switch();
+ tracing_start_sched_switch(RECORD_CMDLINE);
}
void tracing_stop_cmdline_record(void)
{
- tracing_stop_sched_switch();
+ tracing_stop_sched_switch(RECORD_CMDLINE);
+}
+
+void tracing_start_tgid_record(void)
+{
+ tracing_start_sched_switch(RECORD_TGID);
+}
+
+void tracing_stop_tgid_record(void)
+{
+ tracing_stop_sched_switch(RECORD_TGID);
}
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-24 13:22:59 +0000