rseq: Eliminate useless task_work on execve

Eliminate a useless task_work on execve by moving the call to
rseq_set_notify_resume() from sched_mm_cid_after_execve() to the error
path of bprm_execve().

The call to rseq_set_notify_resume() from sched_mm_cid_after_execve() is
pointless in the success case, because rseq_execve() will clear the rseq
pointer before returning to userspace.

sched_mm_cid_after_execve() is called from both the success and error
paths of bprm_execve(). The call to rseq_set_notify_resume() is needed
on error because the mm_cid may have changed.

Also move the rseq_execve() to right after sched_mm_cid_after_execve()
in bprm_execve().

[ mingo: Merged to a recent upstream kernel, extended the changelog. ]

Signed-off-by: Mathieu Desnoyers <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Cc: Oleg Nesterov <[email protected]>
Cc: Linus Torvalds <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: compudj

fs/exec.c

@@ -1864,9 +1864,9 @@ static int bprm_execve(struct linux_binprm *bprm)
 		goto out;
 
 	sched_mm_cid_after_execve(current);
+	rseq_execve(current);
 	/* execve succeeded */
 	current->in_execve = 0;
-	rseq_execve(current);
 	user_events_execve(current);
 	acct_update_integrals(current);
 	task_numa_free(current, false);
@@ -1883,6 +1883,7 @@ static int bprm_execve(struct linux_binprm *bprm)
 		force_fatal_sig(SIGSEGV);
 
 	sched_mm_cid_after_execve(current);
+	rseq_set_notify_resume(current);
 	current->in_execve = 0;
 
 	return retval;

kernel/sched/core.c

@@ -10703,7 +10703,6 @@ void sched_mm_cid_after_execve(struct task_struct *t)
 		smp_mb();
 		t->last_mm_cid = t->mm_cid = mm_cid_get(rq, t, mm);
 	}
-	rseq_set_notify_resume(t);
 }
 
 void sched_mm_cid_fork(struct task_struct *t)