sched/core: Free the stack early if CONFIG_THREAD_INFO_IN_TASK
We currently keep every task's stack around until the task_struct
itself is freed. This means that we keep the stack allocation alive
for longer than necessary and that, under load, we free stacks in
big batches whenever RCU drops the last task reference. Neither of
these is good for reuse of cache-hot memory, and freeing in batches
prevents us from usefully caching small numbers of vmalloced stacks.
On architectures that have thread_info on the stack, we can't easily
change this, but on architectures that set THREAD_INFO_IN_TASK, we
can free it as soon as the task is dead.
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jann Horn <jann@thejh.net>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/08ca06cde00ebed0046c5d26cbbf3fbb7ef5b812.1474003868.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/include/linux/sched.h b/include/linux/sched.h
index a958672..abb795a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1936,6 +1936,10 @@
#ifdef CONFIG_VMAP_STACK
struct vm_struct *stack_vm_area;
#endif
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+ /* A live task holds one reference. */
+ atomic_t stack_refcount;
+#endif
/* CPU-specific state of this task */
struct thread_struct thread;
/*
@@ -3143,12 +3147,22 @@
#endif
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+static inline void *try_get_task_stack(struct task_struct *tsk)
+{
+ return atomic_inc_not_zero(&tsk->stack_refcount) ?
+ task_stack_page(tsk) : NULL;
+}
+
+extern void put_task_stack(struct task_struct *tsk);
+#else
static inline void *try_get_task_stack(struct task_struct *tsk)
{
return task_stack_page(tsk);
}
static inline void put_task_stack(struct task_struct *tsk) {}
+#endif
#define task_stack_end_corrupted(task) \
(*(end_of_stack(task)) != STACK_END_MAGIC)
