Merge branch 'WIP.sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull sched.h split-up from Ingo Molnar:
 "The point of these changes is to significantly reduce the
  <linux/sched.h> header footprint, to speed up the kernel build and to
  have a cleaner header structure.

  After these changes the new <linux/sched.h>'s typical preprocessed
  size goes down from a previous ~0.68 MB (~22K lines) to ~0.45 MB (~15K
  lines), which is around 40% faster to build on typical configs.

  Not much changed from the last version (-v2) posted three weeks ago: I
  eliminated quirks, backmerged fixes plus I rebased it to an upstream
  SHA1 from yesterday that includes most changes queued up in -next plus
  all sched.h changes that were pending from Andrew.

  I've re-tested the series both on x86 and on cross-arch defconfigs,
  and did a bisectability test at a number of random points.

  I tried to test as many build configurations as possible, but some
  build breakage is probably still left - but it should be mostly
  limited to architectures that have no cross-compiler binaries
  available on kernel.org, and non-default configurations"

* 'WIP.sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (146 commits)
  sched/headers: Clean up <linux/sched.h>
  sched/headers: Remove #ifdefs from <linux/sched.h>
  sched/headers: Remove the <linux/topology.h> include from <linux/sched.h>
  sched/headers, hrtimer: Remove the <linux/wait.h> include from <linux/hrtimer.h>
  sched/headers, x86/apic: Remove the <linux/pm.h> header inclusion from <asm/apic.h>
  sched/headers, timers: Remove the <linux/sysctl.h> include from <linux/timer.h>
  sched/headers: Remove <linux/magic.h> from <linux/sched/task_stack.h>
  sched/headers: Remove <linux/sched.h> from <linux/sched/init.h>
  sched/core: Remove unused prefetch_stack()
  sched/headers: Remove <linux/rculist.h> from <linux/sched.h>
  sched/headers: Remove the 'init_pid_ns' prototype from <linux/sched.h>
  sched/headers: Remove <linux/signal.h> from <linux/sched.h>
  sched/headers: Remove <linux/rwsem.h> from <linux/sched.h>
  sched/headers: Remove the runqueue_is_locked() prototype
  sched/headers: Remove <linux/sched.h> from <linux/sched/hotplug.h>
  sched/headers: Remove <linux/sched.h> from <linux/sched/debug.h>
  sched/headers: Remove <linux/sched.h> from <linux/sched/nohz.h>
  sched/headers: Remove <linux/sched.h> from <linux/sched/stat.h>
  sched/headers: Remove the <linux/gfp.h> include from <linux/sched.h>
  sched/headers: Remove <linux/rtmutex.h> from <linux/sched.h>
  ...

1 files changed, 174 insertions, 0 deletions

diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
new file mode 100644
index 000000000000..830953ebb391
--- /dev/null
+++ b/include/linux/sched/mm.h
@@ -0,0 +1,174 @@
+#ifndef _LINUX_SCHED_MM_H
+#define _LINUX_SCHED_MM_H
+
+#include <linux/kernel.h>
+#include <linux/atomic.h>
+#include <linux/sched.h>
+#include <linux/mm_types.h>
+#include <linux/gfp.h>
+
+/*
+ * Routines for handling mm_structs
+ */
+extern struct mm_struct * mm_alloc(void);
+
+/**
+ * mmgrab() - Pin a &struct mm_struct.
+ * @mm: The &struct mm_struct to pin.
+ *
+ * Make sure that @mm will not get freed even after the owning task
+ * exits. This doesn't guarantee that the associated address space
+ * will still exist later on and mmget_not_zero() has to be used before
+ * accessing it.
+ *
+ * This is a preferred way to to pin @mm for a longer/unbounded amount
+ * of time.
+ *
+ * Use mmdrop() to release the reference acquired by mmgrab().
+ *
+ * See also <Documentation/vm/active_mm.txt> for an in-depth explanation
+ * of &mm_struct.mm_count vs &mm_struct.mm_users.
+ */
+static inline void mmgrab(struct mm_struct *mm)
+{
+	atomic_inc(&mm->mm_count);
+}
+
+/* mmdrop drops the mm and the page tables */
+extern void __mmdrop(struct mm_struct *);
+static inline void mmdrop(struct mm_struct *mm)
+{
+	if (unlikely(atomic_dec_and_test(&mm->mm_count)))
+		__mmdrop(mm);
+}
+
+static inline void mmdrop_async_fn(struct work_struct *work)
+{
+	struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work);
+	__mmdrop(mm);
+}
+
+static inline void mmdrop_async(struct mm_struct *mm)
+{
+	if (unlikely(atomic_dec_and_test(&mm->mm_count))) {
+		INIT_WORK(&mm->async_put_work, mmdrop_async_fn);
+		schedule_work(&mm->async_put_work);
+	}
+}
+
+/**
+ * mmget() - Pin the address space associated with a &struct mm_struct.
+ * @mm: The address space to pin.
+ *
+ * Make sure that the address space of the given &struct mm_struct doesn't
+ * go away. This does not protect against parts of the address space being
+ * modified or freed, however.
+ *
+ * Never use this function to pin this address space for an
+ * unbounded/indefinite amount of time.
+ *
+ * Use mmput() to release the reference acquired by mmget().
+ *
+ * See also <Documentation/vm/active_mm.txt> for an in-depth explanation
+ * of &mm_struct.mm_count vs &mm_struct.mm_users.
+ */
+static inline void mmget(struct mm_struct *mm)
+{
+	atomic_inc(&mm->mm_users);
+}
+
+static inline bool mmget_not_zero(struct mm_struct *mm)
+{
+	return atomic_inc_not_zero(&mm->mm_users);
+}
+
+/* mmput gets rid of the mappings and all user-space */
+extern void mmput(struct mm_struct *);
+#ifdef CONFIG_MMU
+/* same as above but performs the slow path from the async context. Can
+ * be called from the atomic context as well
+ */
+extern void mmput_async(struct mm_struct *);
+#endif
+
+/* Grab a reference to a task's mm, if it is not already going away */
+extern struct mm_struct *get_task_mm(struct task_struct *task);
+/*
+ * Grab a reference to a task's mm, if it is not already going away
+ * and ptrace_may_access with the mode parameter passed to it
+ * succeeds.
+ */
+extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode);
+/* Remove the current tasks stale references to the old mm_struct */
+extern void mm_release(struct task_struct *, struct mm_struct *);
+
+#ifdef CONFIG_MEMCG
+extern void mm_update_next_owner(struct mm_struct *mm);
+#else
+static inline void mm_update_next_owner(struct mm_struct *mm)
+{
+}
+#endif /* CONFIG_MEMCG */
+
+#ifdef CONFIG_MMU
+extern void arch_pick_mmap_layout(struct mm_struct *mm);
+extern unsigned long
+arch_get_unmapped_area(struct file *, unsigned long, unsigned long,
+		       unsigned long, unsigned long);
+extern unsigned long
+arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
+			  unsigned long len, unsigned long pgoff,
+			  unsigned long flags);
+#else
+static inline void arch_pick_mmap_layout(struct mm_struct *mm) {}
+#endif
+
+static inline bool in_vfork(struct task_struct *tsk)
+{
+	bool ret;
+
+	/*
+	 * need RCU to access ->real_parent if CLONE_VM was used along with
+	 * CLONE_PARENT.
+	 *
+	 * We check real_parent->mm == tsk->mm because CLONE_VFORK does not
+	 * imply CLONE_VM
+	 *
+	 * CLONE_VFORK can be used with CLONE_PARENT/CLONE_THREAD and thus
+	 * ->real_parent is not necessarily the task doing vfork(), so in
+	 * theory we can't rely on task_lock() if we want to dereference it.
+	 *
+	 * And in this case we can't trust the real_parent->mm == tsk->mm
+	 * check, it can be false negative. But we do not care, if init or
+	 * another oom-unkillable task does this it should blame itself.
+	 */
+	rcu_read_lock();
+	ret = tsk->vfork_done && tsk->real_parent->mm == tsk->mm;
+	rcu_read_unlock();
+
+	return ret;
+}
+
+/* __GFP_IO isn't allowed if PF_MEMALLOC_NOIO is set in current->flags
+ * __GFP_FS is also cleared as it implies __GFP_IO.
+ */
+static inline gfp_t memalloc_noio_flags(gfp_t flags)
+{
+	if (unlikely(current->flags & PF_MEMALLOC_NOIO))
+		flags &= ~(__GFP_IO | __GFP_FS);
+	return flags;
+}
+
+static inline unsigned int memalloc_noio_save(void)
+{
+	unsigned int flags = current->flags & PF_MEMALLOC_NOIO;
+	current->flags |= PF_MEMALLOC_NOIO;
+	return flags;
+}
+
+static inline void memalloc_noio_restore(unsigned int flags)
+{
+	current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags;
+}
+
+#endif /* _LINUX_SCHED_MM_H */