summaryrefslogtreecommitdiffstats
path: root/include/linux/pagemap.h
diff options
context:
space:
mode:
authorNick Piggin <npiggin@suse.de>2008-07-25 19:45:30 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2008-07-26 12:00:06 -0700
commite286781d5f2e9c846e012a39653a166e9d31777d (patch)
tree14958fe6d8f3e0459c96c68b3034ea2433ab85ac /include/linux/pagemap.h
parent47feff2c8eefe85099f87c43d3096855f0085ca0 (diff)
downloadlinux-e286781d5f2e9c846e012a39653a166e9d31777d.tar.gz
linux-e286781d5f2e9c846e012a39653a166e9d31777d.tar.bz2
linux-e286781d5f2e9c846e012a39653a166e9d31777d.zip
mm: speculative page references
If we can be sure that elevating the page_count on a pagecache page will pin it, we can speculatively run this operation, and subsequently check to see if we hit the right page rather than relying on holding a lock or otherwise pinning a reference to the page. This can be done if get_page/put_page behaves consistently throughout the whole tree (ie. if we "get" the page after it has been used for something else, we must be able to free it with a put_page). Actually, there is a period where the count behaves differently: when the page is free or if it is a constituent page of a compound page. We need an atomic_inc_not_zero operation to ensure we don't try to grab the page in either case. This patch introduces the core locking protocol to the pagecache (ie. adds page_cache_get_speculative, and tweaks some update-side code to make it work). Thanks to Hugh for pointing out an improvement to the algorithm setting page_count to zero when we have control of all references, in order to hold off speculative getters. [kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()] [hugh@veritas.com: fix add_to_page_cache] [akpm@linux-foundation.org: repair a comment] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeff Garzik <jeff@garzik.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Hugh Dickins <hugh@veritas.com> Cc: "Paul E. McKenney" <paulmck@us.ibm.com> Reviewed-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Nick Piggin <npiggin@suse.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include/linux/pagemap.h')
-rw-r--r--include/linux/pagemap.h111
1 files changed, 110 insertions, 1 deletions
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index ee1ec2c7723c..a81d81890422 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -12,6 +12,7 @@
#include <asm/uaccess.h>
#include <linux/gfp.h>
#include <linux/bitops.h>
+#include <linux/hardirq.h> /* for in_interrupt() */
/*
* Bits in mapping->flags. The lower __GFP_BITS_SHIFT bits are the page
@@ -62,6 +63,98 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
#define page_cache_release(page) put_page(page)
void release_pages(struct page **pages, int nr, int cold);
+/*
+ * 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);
+}
+
#ifdef CONFIG_NUMA
extern struct page *__page_cache_alloc(gfp_t gfp);
#else
@@ -133,7 +226,7 @@ static inline struct page *read_mapping_page(struct address_space *mapping,
return read_cache_page(mapping, index, filler, data);
}
-int add_to_page_cache(struct page *page, struct address_space *mapping,
+int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
pgoff_t index, gfp_t gfp_mask);
int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
pgoff_t index, gfp_t gfp_mask);
@@ -141,6 +234,22 @@ extern void remove_from_page_cache(struct page *page);
extern void __remove_from_page_cache(struct page *page);
/*
+ * Like add_to_page_cache_locked, but used to add newly allocated pages:
+ * the page is new, so we can just run SetPageLocked() against it.
+ */
+static inline int add_to_page_cache(struct page *page,
+ struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask)
+{
+ int error;
+
+ SetPageLocked(page);
+ error = add_to_page_cache_locked(page, mapping, offset, gfp_mask);
+ if (unlikely(error))
+ ClearPageLocked(page);
+ return error;
+}
+
+/*
* Return byte-offset into filesystem object for page.
*/
static inline loff_t page_offset(struct page *page)