diff options
| author | Nick Piggin <nickpiggin@yahoo.com.au> | 2005-06-25 14:57:29 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@ppc970.osdl.org> | 2005-06-25 16:24:44 -0700 |
| commit | 476d139c218e44e045e4bc6d4cc02b010b343939 (patch) | |
| tree | 82a6537b829b2b35156fba5a312f4e44273a4356 /kernel/fork.c | |
| parent | 674311d5b411e9042df4fdf7aef0b3c8217b6240 (diff) | |
| download | lwn-476d139c218e44e045e4bc6d4cc02b010b343939.tar.gz lwn-476d139c218e44e045e4bc6d4cc02b010b343939.zip | |
[PATCH] sched: consolidate sbe sbf
Consolidate balance-on-exec with balance-on-fork. This is made easy by the
sched-domains RCU patches.
As well as the general goodness of code reduction, this allows the runqueues
to be unlocked during balance-on-fork.
schedstats is a problem. Maybe just have balance-on-event instead of
distinguishing fork and exec?
Signed-off-by: Nick Piggin <nickpiggin@yahoo.com.au>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'kernel/fork.c')
| -rw-r--r-- | kernel/fork.c | 21 |
1 files changed, 12 insertions, 9 deletions
diff --git a/kernel/fork.c b/kernel/fork.c index a28d11e10877..2c7806873bfd 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1003,9 +1003,6 @@ static task_t *copy_process(unsigned long clone_flags, p->pdeath_signal = 0; p->exit_state = 0; - /* Perform scheduler related setup */ - sched_fork(p); - /* * Ok, make it visible to the rest of the system. * We dont wake it up yet. @@ -1014,18 +1011,24 @@ static task_t *copy_process(unsigned long clone_flags, INIT_LIST_HEAD(&p->ptrace_children); INIT_LIST_HEAD(&p->ptrace_list); + /* Perform scheduler related setup. Assign this task to a CPU. */ + sched_fork(p, clone_flags); + /* Need tasklist lock for parent etc handling! */ write_lock_irq(&tasklist_lock); /* - * The task hasn't been attached yet, so cpus_allowed mask cannot - * have changed. The cpus_allowed mask of the parent may have - * changed after it was copied first time, and it may then move to - * another CPU - so we re-copy it here and set the child's CPU to - * the parent's CPU. This avoids alot of nasty races. + * The task hasn't been attached yet, so its cpus_allowed mask will + * not be changed, nor will its assigned CPU. + * + * The cpus_allowed mask of the parent may have changed after it was + * copied first time - so re-copy it here, then check the child's CPU + * to ensure it is on a valid CPU (and if not, just force it back to + * parent's CPU). This avoids alot of nasty races. */ p->cpus_allowed = current->cpus_allowed; - set_task_cpu(p, smp_processor_id()); + if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed))) + set_task_cpu(p, smp_processor_id()); /* * Check for pending SIGKILL! The new thread should not be allowed |