Rework how we store process times in the kernel such that we always store

the raw values including for child process statistics and only compute the
system and user timevals on demand.

- Fix the various kern_wait() syscall wrappers to only pass in a rusage
  pointer if they are going to use the result.
- Add a kern_getrusage() function for the ABI syscalls to use so that they
  don't have to play stackgap games to call getrusage().
- Fix the svr4_sys_times() syscall to just call calcru() to calculate the
  times it needs rather than calling getrusage() twice with associated
  stackgap, etc.
- Add a new rusage_ext structure to store raw time stats such as tick counts
  for user, system, and interrupt time as well as a bintime of the total
  runtime.  A new p_rux field in struct proc replaces the same inline fields
  from struct proc (i.e. p_[isu]ticks, p_[isu]u, and p_runtime).  A new p_crux
  field in struct proc contains the "raw" child time usage statistics.
  ruadd() has been changed to handle adding the associated rusage_ext
  structures as well as the values in rusage.  Effectively, the values in
  rusage_ext replace the ru_utime and ru_stime values in struct rusage.  These
  two fields in struct rusage are no longer used in the kernel.
- calcru() has been split into a static worker function calcru1() that
  calculates appropriate timevals for user and system time as well as updating
  the rux_[isu]u fields of a passed in rusage_ext structure.  calcru() uses a
  copy of the process' p_rux structure to compute the timevals after updating
  the runtime appropriately if any of the threads in that process are
  currently executing.  It also now only locks sched_lock internally while
  doing the rux_runtime fixup.  calcru() now only requires the caller to
  hold the proc lock and calcru1() only requires the proc lock internally.
  calcru() also no longer allows callers to ask for an interrupt timeval
  since none of them actually did.
- calcru() now correctly handles threads executing on other CPUs.
- A new calccru() function computes the child system and user timevals by
  calling calcru1() on p_crux.  Note that this means that any code that wants
  child times must now call this function rather than reading from p_cru
  directly.  This function also requires the proc lock.
- This finishes the locking for rusage and friends so some of the Giant locks
  in exit1() and kern_wait() are now gone.
- The locking in ttyinfo() has been tweaked so that a shared lock of the
  proctree lock is used to protect the process group rather than the process
  group lock.  By holding this lock until the end of the function we now
  ensure that the process/thread that we pick to dump info about will no
  longer vanish while we are trying to output its info to the console.

Submitted by:	bde (mostly)
MFC after:	1 month

1 files changed, 17 insertions, 19 deletions

diff --git a/sys/kern/kern_exit.c b/sys/kern/kern_exit.c
index cd7e2a4..ae44fc3 100644
--- a/sys/kern/kern_exit.c
+++ b/sys/kern/kern_exit.c
@@ -410,20 +410,16 @@ retry:
 	}
 
 	/*
-	 * Save exit status and final rusage info, adding in child rusage
-	 * info and self times.
+	 * Save exit status and finalize rusage info except for times,
+	 * adding in child rusage info.
 	 */
-	mtx_lock(&Giant);	
 	PROC_LOCK(p);
 	p->p_xstat = rv;
 	p->p_xthread = td;
+	p->p_stats->p_ru.ru_nvcsw++;
 	*p->p_ru = p->p_stats->p_ru;
-	mtx_lock_spin(&sched_lock);
-	calcru(p, &p->p_ru->ru_utime, &p->p_ru->ru_stime, NULL);
-	mtx_unlock_spin(&sched_lock);
-	ruadd(p->p_ru, &p->p_stats->p_cru);
+	ruadd(p->p_ru, &p->p_rux, &p->p_stats->p_cru, &p->p_crux);
 
-	mtx_unlock(&Giant);	
 	/*
 	 * Notify interested parties of our demise.
 	 */
@@ -487,9 +483,6 @@ retry:
 	PROC_LOCK(p->p_pptr);
 	sx_xunlock(&proctree_lock);
 
-	while (mtx_owned(&Giant))
-		mtx_unlock(&Giant);
-
 	/*
 	 * We have to wait until after acquiring all locks before
 	 * changing p_state.  We need to avoid all possible context
@@ -508,8 +501,8 @@ retry:
 
 	/* Do the same timestamp bookkeeping that mi_switch() would do. */
 	binuptime(&new_switchtime);
-	bintime_add(&p->p_runtime, &new_switchtime);
-	bintime_sub(&p->p_runtime, PCPU_PTR(switchtime));
+	bintime_add(&p->p_rux.rux_runtime, &new_switchtime);
+	bintime_sub(&p->p_rux.rux_runtime, PCPU_PTR(switchtime));
 	PCPU_SET(switchtime, new_switchtime);
 	PCPU_SET(switchticks, ticks);
 	cnt.v_swtch++;
@@ -556,10 +549,14 @@ owait(struct thread *td, struct owait_args *uap __unused)
 int
 wait4(struct thread *td, struct wait_args *uap)
 {
-	struct rusage ru;
+	struct rusage ru, *rup;
 	int error, status;
 
-	error = kern_wait(td, uap->pid, &status, uap->options, &ru);
+	if (uap->rusage != NULL)
+		rup = &ru;
+	else
+		rup = NULL;
+	error = kern_wait(td, uap->pid, &status, uap->options, rup);
 	if (uap->status != NULL && error == 0)
 		error = copyout(&status, uap->status, sizeof(status));
 	if (uap->rusage != NULL && error == 0)
@@ -612,8 +609,10 @@ loop:
 			td->td_retval[0] = p->p_pid;
 			if (status)
 				*status = p->p_xstat;	/* convert to int */
-			if (rusage)
+			if (rusage) {
 				bcopy(p->p_ru, rusage, sizeof(struct rusage));
+				calcru(p, &rusage->ru_utime, &rusage->ru_stime);
+			}
 
 			/*
 			 * If we got the child via a ptrace 'attach',
@@ -648,16 +647,15 @@ loop:
 			 * all other writes to this proc are visible now, so
 			 * no more locking is needed for p.
 			 */
-			mtx_lock(&Giant);
 			PROC_LOCK(p);
 			p->p_xstat = 0;		/* XXX: why? */
 			PROC_UNLOCK(p);
 			PROC_LOCK(q);
-			ruadd(&q->p_stats->p_cru, p->p_ru);
+			ruadd(&q->p_stats->p_cru, &q->p_crux, p->p_ru,
+			    &p->p_rux);
 			PROC_UNLOCK(q);
 			FREE(p->p_ru, M_ZOMBIE);
 			p->p_ru = NULL;
-			mtx_unlock(&Giant);
 
 			/*
 			 * Decrement the count of procs running with this uid.