+/*
+ * speculatively take a reference to a page.
+ * If the page is free (_count == 0), then _count is untouched, and 0
+ * is returned. Otherwise, _count is incremented by 1 and 1 is returned.
+ *
+ * This function must be called inside the same rcu_read_lock() section as has
+ * been used to lookup the page in the pagecache radix-tree (or page table):
+ * this allows allocators to use a synchronize_rcu() to stabilize _count.
+ *
+ * Unless an RCU grace period has passed, the count of all pages coming out
+ * of the allocator must be considered unstable. page_count may return higher
+ * than expected, and put_page must be able to do the right thing when the
+ * page has been finished with, no matter what it is subsequently allocated
+ * for (because put_page is what is used here to drop an invalid speculative
+ * reference).
+ *
+ * This is the interesting part of the lockless pagecache (and lockless
+ * get_user_pages) locking protocol, where the lookup-side (eg. find_get_page)
+ * has the following pattern:
+ * 1. find page in radix tree
+ * 2. conditionally increment refcount
+ * 3. check the page is still in pagecache (if no, goto 1)
+ *
+ * Remove-side that cares about stability of _count (eg. reclaim) has the
+ * following (with tree_lock held for write):
+ * A. atomically check refcount is correct and set it to 0 (atomic_cmpxchg)
+ * B. remove page from pagecache
+ * C. free the page
+ *
+ * There are 2 critical interleavings that matter:
+ * - 2 runs before A: in this case, A sees elevated refcount and bails out
+ * - A runs before 2: in this case, 2 sees zero refcount and retries;
+ * subsequently, B will complete and 1 will find no page, causing the
+ * lookup to return NULL.
+ *
+ * It is possible that between 1 and 2, the page is removed then the exact same
+ * page is inserted into the same position in pagecache. That's OK: the
+ * old find_get_page using tree_lock could equally have run before or after
+ * such a re-insertion, depending on order that locks are granted.
+ *
+ * Lookups racing against pagecache insertion isn't a big problem: either 1
+ * will find the page or it will not. Likewise, the old find_get_page could run
+ * either before the insertion or afterwards, depending on timing.
+ */
+static inline int page_cache_get_speculative(struct page *page)
+{
+ VM_BUG_ON(in_interrupt());
+
+#if !defined(CONFIG_SMP) && defined(CONFIG_CLASSIC_RCU)
+# ifdef CONFIG_PREEMPT
+ VM_BUG_ON(!in_atomic());
+# endif
+ /*
+ * Preempt must be disabled here - we rely on rcu_read_lock doing
+ * this for us.
+ *
+ * Pagecache won't be truncated from interrupt context, so if we have
+ * found a page in the radix tree here, we have pinned its refcount by
+ * disabling preempt, and hence no need for the "speculative get" that
+ * SMP requires.
+ */
+ VM_BUG_ON(page_count(page) == 0);
+ atomic_inc(&page->_count);
+
+#else
+ if (unlikely(!get_page_unless_zero(page))) {
+ /*
+ * Either the page has been freed, or will be freed.
+ * In either case, retry here and the caller should
+ * do the right thing (see comments above).
+ */
+ return 0;
+ }
+#endif
+ VM_BUG_ON(PageTail(page));
+
+ return 1;
+}
+
+static inline int page_freeze_refs(struct page *page, int count)
+{
+ return likely(atomic_cmpxchg(&page->_count, count, 0) == count);
+}
+
+static inline void page_unfreeze_refs(struct page *page, int count)
+{
+ VM_BUG_ON(page_count(page) != 0);
+ VM_BUG_ON(count == 0);
+
+ atomic_set(&page->_count, count);
+}
+
git://ftp.safe.ca / safe / jmp / linux-2.6 / commitdiff