dtrace: augment SDT probes with type information

With all the other work done, we can finally move the SDT probe
type information out of the static sdt_args array in the SDT kernel
module and put them in the probe definitions they relate to.

Most of it is already there -- all probes already carry type
information.  All that is missing is translations, so we add those.

The syntax for these is

type: translation
  or
type : (translation, ...)

i.e. a source type, followed by a colon, followed by zero or more
translated types (if there is more than one, they must be bracketed),
with optional spaces if you like.  The resulting probe will have as many
arguments as there are translations.  Obviously, if DTrace userspace is
to do anything with this knowledge it will need a translator from the
specified source type to each of the specified translated types: DTrace
picks these up from kernel-versioned subdirectories of
/usr/lib64/dtrace/ (e.g. /usr/lib64/dtrace/4.1).

If a probe appears more than once (say, in different functions), each
instance must presently have the same types.  Changing translations
between instances of a single probe will be diagnosed if CONFIG_DT_DEBUG
is enabled.

Typos in the types are only diagnosed at runtime: a dtrace -vln of your
new probe will tell you if all is well.

Signed-off-by: Nick Alcock <nick.alcock@oracle.com>
Acked-by: Kris Van Hees <kris.van.hees@oracle.com>
Orabug: 24661801

diff --git a/fs/buffer.c b/fs/buffer.c
index 3842fbb96d78d688ebac029e1c28e89529b9942f..af04bc0a0498dd6b37b94a71c9005cbc3bdbb2cf 100644 (file)
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -116,9 +116,9 @@ EXPORT_SYMBOL(buffer_check_dirty_writeback);
  */
 void __wait_on_buffer(struct buffer_head * bh)
 {
-       DTRACE_IO1(wait__start, struct buffer_head *, bh);
+       DTRACE_IO1(wait__start, struct buffer_head * : (bufinfo_t *, devinfo_t *, fileinfo_t *), bh);
        wait_on_bit_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE);
-       DTRACE_IO1(wait__done, struct buffer_head *, bh);
+       DTRACE_IO1(wait__done, struct buffer_head * : (bufinfo_t *, devinfo_t *, fileinfo_t *), bh);
 }
 EXPORT_SYMBOL(__wait_on_buffer);
 
@@ -2947,7 +2947,7 @@ static void end_bio_bh_io_sync(struct bio *bio, int err)
        if (unlikely (test_bit(BIO_QUIET,&bio->bi_flags)))
                set_bit(BH_Quiet, &bh->b_state);
 
-       DTRACE_IO2(done, struct buffer_head *, bh, int, bio->bi_rw);
+       DTRACE_IO2(done, struct buffer_head * : (bufinfo_t *, devinfo_t *, fileinfo_t *), bh, int, bio->bi_rw);
        bh->b_end_io(bh, test_bit(BIO_UPTODATE, &bio->bi_flags));
        bio_put(bio);
 }
@@ -3045,7 +3045,8 @@ int _submit_bh(int rw, struct buffer_head *bh, unsigned long bio_flags)
                rw |= REQ_PRIO;
 
        bio_get(bio);
-       DTRACE_IO2(start, struct buffer_head *, bh, int, rw);
+       DTRACE_IO2(start, struct buffer_head * : (bufinfo_t *, devinfo_t *,
+                                                 fileinfo_t *), bh, int, rw);
        submit_bio(rw, bio);
 
        if (bio_flagged(bio, BIO_EOPNOTSUPP))

diff --git a/kernel/fork.c b/kernel/fork.c
index a5431f06b398a33f1ca546b0f9df02da3cabae1b..d23b00fc4cf49a437cc5578c8b270c2e6aef3298 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1761,8 +1761,8 @@ long do_fork(unsigned long clone_flags,
                }
 
                put_pid(pid);
-               DTRACE_PROC1(lwp__create, struct task_struct *, p);
-               DTRACE_PROC1(create, struct task_struct *, p);
+               DTRACE_PROC1(lwp__create, struct task_struct * : (lwpsinfo_t *, psinfo_t *), p);
+               DTRACE_PROC1(create, struct task_struct * : psinfo_t *, p);
        } else {
                nr = PTR_ERR(p);
        }

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8c1c58a9c62c8606b6d1bd9c35fca00c236fabb7..aa285729aa5d7317bfdf4732c6823946e55a7bf6 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -805,7 +805,8 @@ static void set_load_weight(struct task_struct *p)
 
 static void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 {
-       DTRACE_SCHED2(enqueue, struct task_struct *, p,
+       DTRACE_SCHED2(enqueue, struct task_struct * : (lwpsinfo_t *,
+                                                      psinfo_t *), p,
                               cpuinfo_t *, rq->dtrace_cpu_info);
        update_rq_clock(rq);
        sched_info_queued(rq, p);
@@ -814,7 +815,8 @@ static void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 
 static void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 {
-       DTRACE_SCHED3(dequeue, struct task_struct *, p,
+       DTRACE_SCHED3(dequeue, struct task_struct * : (lwpsinfo_t *,
+                                                      psinfo_t *), p,
                               cpuinfo_t *, rq->dtrace_cpu_info,
                               int, 0);
        update_rq_clock(rq);
@@ -1678,7 +1680,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
        success = 1; /* we're going to change ->state */
        cpu = task_cpu(p);
 
-       DTRACE_SCHED1(wakeup, struct task_struct *, p);
+       DTRACE_SCHED1(wakeup, struct task_struct * : (lwpsinfo_t *,
+                                                     psinfo_t *), p);
 
        if (p->on_rq && ttwu_remote(p, wake_flags))
                goto stat;
@@ -2187,7 +2190,8 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
        trace_sched_switch(prev, next);
        sched_info_switch(rq, prev, next);
        perf_event_task_sched_out(prev, next);
-       DTRACE_SCHED1(off__cpu, struct task_struct *, next);
+       DTRACE_SCHED1(off__cpu, struct task_struct * : (lwpsinfo_t *,
+                                                       psinfo_t *), next);
        fire_sched_out_preempt_notifiers(prev, next);
        prepare_lock_switch(rq, next);
        prepare_arch_switch(next);
@@ -3130,7 +3134,9 @@ void set_user_nice(struct task_struct *p, long nice)
        p->prio = effective_prio(p);
        delta = p->prio - old_prio;
 
-       DTRACE_SCHED2(change__pri, struct task_struct *, p, int, old_prio);
+       DTRACE_SCHED2(change__pri, struct task_struct * : (lwpsinfo_t *,
+                                                          psinfo_t *), p,
+                     int, old_prio);
        if (queued) {
                enqueue_task(rq, p, 0);
                /*
@@ -4244,7 +4250,9 @@ SYSCALL_DEFINE0(sched_yield)
        do_raw_spin_unlock(&rq->lock);
        sched_preempt_enable_no_resched();
 
-       DTRACE_SCHED1(surrender, struct task_struct *, current);
+       DTRACE_SCHED1(surrender,
+                     struct task_struct * : (lwpsinfo_t *, psinfo_t *),
+                     current);
        schedule();
 
        return 0;
@@ -4399,7 +4407,9 @@ out_irq:
        local_irq_restore(flags);
 
        if (yielded > 0) {
-               DTRACE_SCHED1(surrender, struct task_struct *, curr);
+               DTRACE_SCHED1(surrender,
+                             struct task_struct * : (lwpsinfo_t *, psinfo_t *),
+                             curr);
                schedule();
        }
 

diff --git a/kernel/signal.c b/kernel/signal.c
index a263c1d87d2ca5b0a3a01c815cc3409d0f7590c6..ac6c3e8b823e3032ba49ecdc9a1ecaf81317e78b 100644 (file)
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1034,7 +1034,8 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
        result = TRACE_SIGNAL_IGNORED;
        if (!prepare_signal(sig, t,
                            from_ancestor_ns || (info == SEND_SIG_FORCED))) {
-               DTRACE_PROC2(signal__discard, struct task_struct *, t,
+               DTRACE_PROC2(signal__discard,
+                            struct task_struct * : (lwpsinfo_t *, psinfo_t *), t,
                             int, sig);
                goto ret;
        }
@@ -1123,7 +1124,9 @@ out_set:
        signalfd_notify(t, sig);
        sigaddset(&pending->signal, sig);
        complete_signal(sig, t, group);
-       DTRACE_PROC2(signal__send, struct task_struct *, t, int, sig);
+       DTRACE_PROC2(signal__send,
+                    struct task_struct * : (lwpsinfo_t *, psinfo_t *), t,
+                    int, sig);
 ret:
        trace_signal_generate(sig, info, t, group, result);
        return ret;
@@ -1610,7 +1613,9 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
        list_add_tail(&q->list, &pending->list);
        sigaddset(&pending->signal, sig);
        complete_signal(sig, t, group);
-       DTRACE_PROC2(signal__send, struct task_struct *, t, int, sig);
+       DTRACE_PROC2(signal__send,
+                    struct task_struct * : (lwpsinfo_t *, psinfo_t *), t,
+                    int, sig);
        result = TRACE_SIGNAL_DELIVERED;
 out:
        trace_signal_generate(sig, &q->info, t, group, result);

diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index fe2174eb87e388897159a8d7d21e55190e0d69e7..b16eaa7fb044eb77a8e85987d0f855acd99f1f01 100644 (file)
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1391,7 +1391,8 @@ void update_process_times(int user_tick)
 {
        struct task_struct *p = current;
 
-       DTRACE_SCHED1(tick, struct task_struct *, p);
+       DTRACE_SCHED1(tick, struct task_struct * : (lwpsinfo_t *, psinfo_t *),
+                     p);
 
        /* Note: this timer irq context must be accounted for as well. */
        account_process_tick(p, user_tick);