diff options
author | Hugh Dickins <hugh@veritas.com> | 2004-10-19 18:17:12 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@ppc970.osdl.org> | 2004-10-19 18:17:12 -0700 |
commit | 1b46884a372f362e5edb1bb406bf0c5ca98bade7 (patch) | |
tree | cdfc9bfc76b98cc06f270e0a19f1da04005ee26d /kernel | |
parent | 5dfd31d1133be6b1c697c082900cc0e50d878639 (diff) | |
download | history-1b46884a372f362e5edb1bb406bf0c5ca98bade7.tar.gz |
[PATCH] lighten mmlist_lock
Let's lighten the global spinlock mmlist_lock.
What's it for?
1. Its original role is to guard mmlist.
2. It later got a second role, to prevent get_task_mm from raising
mm_users from the dead, just after it went down to 0.
Firstly consider the second: __exit_mm sets tsk->mm NULL while holding
task_lock before calling mmput; so mmlist_lock only guards against the
exceptional case, of get_task_mm on a kernel workthread which did AIO's
use_mm (which transiently sets its tsk->mm without raising mm_users) on an
mm now exiting.
Well, I don't think get_task_mm should succeed at all on use_mm tasks.
It's mainly used by /proc/pid and ptrace, seems at best confusing for those
to present the kernel thread as having a user mm, which it won't have a
moment later. Define PF_BORROWED_MM, set in use_mm, clear in unuse_mm
(though we could just leave it), get_task_mm give NULL if set.
Secondly consider the first: and what's mmlist for?
1. Its original role was for swap_out to scan: rmap ended that in 2.5.27.
2. In 2.4.10 it got a second role, for try_to_unuse to scan for swapoff.
So, make mmlist a list of mms which maybe have pages on swap: add mm to
mmlist when first swap entry is assigned in try_to_unmap_one (pageout), or
in copy_page_range (fork); and mmput remove it from mmlist as before,
except usually list_empty and there's no need to lock. drain_mmlist added
to swapoff, to empty out the mmlist if no swap is then in use.
mmput leave mm on mmlist until after its exit_mmap, so try_to_unmap_one can
still add mm to mmlist without worrying about the mm_users 0 case; but
try_to_unuse must avoid the mm_users 0 case (when an mm might be removed
from mmlist, and freed, while it's down in unuse_process): use
atomic_inc_return now all architectures support that.
Some of the detailed comments in try_to_unuse have grown out of date:
updated and trimmed some, but leave SWAP_MAP_MAX for another occasion.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/fork.c | 37 |
1 files changed, 11 insertions, 26 deletions
diff --git a/kernel/fork.c b/kernel/fork.c index 96714c501cc831..7d9cd6f7b27869 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -179,17 +179,6 @@ static inline int dup_mmap(struct mm_struct * mm, struct mm_struct * oldmm) rb_parent = NULL; pprev = &mm->mmap; - /* - * Add it to the mmlist after the parent. - * Doing it this way means that we can order the list, - * and fork() won't mess up the ordering significantly. - * Add it first so that swapoff can see any swap entries. - */ - spin_lock(&mmlist_lock); - list_add(&mm->mmlist, ¤t->mm->mmlist); - mmlist_nr++; - spin_unlock(&mmlist_lock); - for (mpnt = current->mm->mmap ; mpnt ; mpnt = mpnt->vm_next) { struct file *file; @@ -289,7 +278,6 @@ static inline void mm_free_pgd(struct mm_struct * mm) #endif /* CONFIG_MMU */ spinlock_t mmlist_lock __cacheline_aligned_in_smp = SPIN_LOCK_UNLOCKED; -int mmlist_nr; #define allocate_mm() (kmem_cache_alloc(mm_cachep, SLAB_KERNEL)) #define free_mm(mm) (kmem_cache_free(mm_cachep, (mm))) @@ -301,6 +289,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm) atomic_set(&mm->mm_users, 1); atomic_set(&mm->mm_count, 1); init_rwsem(&mm->mmap_sem); + INIT_LIST_HEAD(&mm->mmlist); mm->core_waiters = 0; mm->nr_ptes = 0; mm->page_table_lock = SPIN_LOCK_UNLOCKED; @@ -350,12 +339,14 @@ void fastcall __mmdrop(struct mm_struct *mm) */ void mmput(struct mm_struct *mm) { - if (atomic_dec_and_lock(&mm->mm_users, &mmlist_lock)) { - list_del(&mm->mmlist); - mmlist_nr--; - spin_unlock(&mmlist_lock); + if (atomic_dec_and_test(&mm->mm_users)) { exit_aio(mm); exit_mmap(mm); + if (!list_empty(&mm->mmlist)) { + spin_lock(&mmlist_lock); + list_del(&mm->mmlist); + spin_unlock(&mmlist_lock); + } put_swap_token(mm); mmdrop(mm); } @@ -365,15 +356,11 @@ EXPORT_SYMBOL_GPL(mmput); /** * get_task_mm - acquire a reference to the task's mm * - * Returns %NULL if the task has no mm. Checks if the use count - * of the mm is non-zero and if so returns a reference to it, after + * Returns %NULL if the task has no mm. Checks PF_BORROWED_MM (meaning + * this kernel workthread has transiently adopted a user mm with use_mm, + * to do its AIO) is not set and if so returns a reference to it, after * bumping up the use count. User must release the mm via mmput() * after use. Typically used by /proc and ptrace. - * - * If the use count is zero, it means that this mm is going away, - * so return %NULL. This only happens in the case of an AIO daemon - * which has temporarily adopted an mm (see use_mm), in the course - * of its final mmput, before exit_aio has completed. */ struct mm_struct *get_task_mm(struct task_struct *task) { @@ -382,12 +369,10 @@ struct mm_struct *get_task_mm(struct task_struct *task) task_lock(task); mm = task->mm; if (mm) { - spin_lock(&mmlist_lock); - if (!atomic_read(&mm->mm_users)) + if (task->flags & PF_BORROWED_MM) mm = NULL; else atomic_inc(&mm->mm_users); - spin_unlock(&mmlist_lock); } task_unlock(task); return mm; |