| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20080220160702.4715.97008.stgit@warthog.procyon.org.uk>
Date: Wed, 20 Feb 2008 16:07:03 +0000
From: David Howells <dhowells@...hat.com>
To: Trond.Myklebust@...app.com, chuck.lever@...cle.com,
casey@...aufler-ca.com
Cc: nfsv4@...ux-nfs.org, linux-kernel@...r.kernel.org,
linux-fsdevel@...r.kernel.org, selinux@...ho.nsa.gov,
linux-security-module@...r.kernel.org, dhowells@...hat.com
Subject: [PATCH 12/37] FS-Cache: Recruit a couple of page flags for cache
management
Recruit a couple of page flags to aid in cache management. The following extra
flags are defined:
(1) PG_fscache (PG_private_2)
The marked page is backed by a local cache and is pinning resources in the
cache driver.
(2) PG_fscache_write (PG_owner_priv_2)
The marked page is being written to the local cache. The page may not be
modified whilst this is in progress.
If PG_fscache is set, then things that checked for PG_private will now also
check for that. This includes things like truncation and page invalidation.
The function page_has_private() had been added to make the checks for both
PG_private and PG_private_2 at the same time.
Signed-off-by: David Howells <dhowells@...hat.com>
---
fs/splice.c | 2 +-
include/linux/page-flags.h | 39 +++++++++++++++++++++++++++++++++++++--
include/linux/pagemap.h | 11 +++++++++++
mm/filemap.c | 18 ++++++++++++++++++
mm/migrate.c | 2 +-
mm/page_alloc.c | 3 +++
mm/readahead.c | 9 +++++----
mm/swap.c | 4 ++--
mm/swap_state.c | 4 ++--
mm/truncate.c | 10 +++++-----
mm/vmscan.c | 2 +-
11 files changed, 86 insertions(+), 18 deletions(-)
diff --git a/fs/splice.c b/fs/splice.c
index 9b559ee..f2a7a06 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -58,7 +58,7 @@ static int page_cache_pipe_buf_steal(struct pipe_inode_info *pipe,
*/
wait_on_page_writeback(page);
- if (PagePrivate(page))
+ if (page_has_private(page))
try_to_release_page(page, GFP_KERNEL);
/*
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index bbad43f..cc16c23 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -77,25 +77,32 @@
#define PG_active 6
#define PG_slab 7 /* slab debug (Suparna wants this) */
-#define PG_owner_priv_1 8 /* Owner use. If pagecache, fs may use*/
+#define PG_owner_priv_1 8 /* Owner use. fs may use in pagecache */
#define PG_arch_1 9
#define PG_reserved 10
#define PG_private 11 /* If pagecache, has fs-private data */
#define PG_writeback 12 /* Page is under writeback */
+#define PG_private_2 13 /* If pagecache, has fs aux data */
#define PG_compound 14 /* Part of a compound page */
#define PG_swapcache 15 /* Swap page: swp_entry_t in private */
#define PG_mappedtodisk 16 /* Has blocks allocated on-disk */
#define PG_reclaim 17 /* To be reclaimed asap */
+#define PG_owner_priv_2 18 /* Owner use. fs may use in pagecache */
#define PG_buddy 19 /* Page is free, on buddy lists */
/* PG_readahead is only used for file reads; PG_reclaim is only for writes */
#define PG_readahead PG_reclaim /* Reminder to do async read-ahead */
-/* PG_owner_priv_1 users should have descriptive aliases */
+/* PG_owner_priv_1/2 users should have descriptive aliases */
#define PG_checked PG_owner_priv_1 /* Used by some filesystems */
#define PG_pinned PG_owner_priv_1 /* Xen pinned pagetable */
+#define PG_fscache_write PG_owner_priv_2 /* Writing to local cache */
+
+/* PG_private_2 causes releasepage() and co to be invoked */
+#define PG_fscache PG_private_2 /* Backed by local cache */
+
#if (BITS_PER_LONG > 32)
/*
@@ -235,6 +242,23 @@ static inline void SetPageUptodate(struct page *page)
#define TestClearPageWriteback(page) test_and_clear_bit(PG_writeback, \
&(page)->flags)
+#define PagePrivate2(page) test_bit(PG_private_2, &(page)->flags)
+#define SetPagePrivate2(page) set_bit(PG_private_2, &(page)->flags)
+#define ClearPagePrivate2(page) clear_bit(PG_private_2, &(page)->flags)
+#define TestSetPagePrivate2(page) test_and_set_bit(PG_private_2, &(page)->flags)
+#define TestClearPagePrivate2(page) test_and_clear_bit(PG_private_2, \
+ &(page)->flags)
+
+#define PageOwnerPriv2(page) test_bit(PG_owner_priv_2, \
+ &(page)->flags)
+#define SetPageOwnerPriv2(page) set_bit(PG_owner_priv_2, &(page)->flags)
+#define ClearPageOwnerPriv2(page) clear_bit(PG_owner_priv_2, \
+ &(page)->flags)
+#define TestSetPageOwnerPriv2(page) test_and_set_bit(PG_owner_priv_2, \
+ &(page)->flags)
+#define TestClearPageOwnerPriv2(page) test_and_clear_bit(PG_owner_priv_2, \
+ &(page)->flags)
+
#define PageBuddy(page) test_bit(PG_buddy, &(page)->flags)
#define __SetPageBuddy(page) __set_bit(PG_buddy, &(page)->flags)
#define __ClearPageBuddy(page) __clear_bit(PG_buddy, &(page)->flags)
@@ -308,4 +332,15 @@ static inline void set_page_writeback(struct page *page)
test_set_page_writeback(page);
}
+/**
+ * page_has_private - Determine if page has private stuff
+ * @page: The page to be checked
+ *
+ * Determine if a page has private stuff, indicating that release routines
+ * should be invoked upon it.
+ */
+#define page_has_private(page) \
+ ((page)->flags & ((1 << PG_private) | \
+ (1 << PG_private_2)))
+
#endif /* PAGE_FLAGS_H */
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index d2fca80..c5df3ae 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -226,6 +226,17 @@ static inline void wait_on_page_writeback(struct page *page)
extern void end_page_writeback(struct page *page);
/*
+ * Wait for a PG_owner_priv_2 to become clear
+ */
+static inline void wait_on_page_owner_priv_2(struct page *page)
+{
+ if (PageOwnerPriv2(page))
+ wait_on_page_bit(page, PG_owner_priv_2);
+}
+
+extern void end_page_owner_priv_2(struct page *page);
+
+/*
* Fault a userspace page into pagetables. Return non-zero on a fault.
*
* This assumes that two userspace pages are always sufficient. That's
diff --git a/mm/filemap.c b/mm/filemap.c
index 5c74b68..8951d67 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -587,6 +587,21 @@ void end_page_writeback(struct page *page)
EXPORT_SYMBOL(end_page_writeback);
/**
+ * end_page_own - Clear PG_owner_priv_2 and wake up any waiters
+ * @page: the page
+ *
+ * Clear PG_owner_priv_2 and wake up any processes waiting for that event.
+ */
+void end_page_owner_priv_2(struct page *page)
+{
+ if (!TestClearPageOwnerPriv2(page))
+ BUG();
+ smp_mb__after_clear_bit();
+ wake_up_page(page, PG_owner_priv_2);
+}
+EXPORT_SYMBOL(end_page_owner_priv_2);
+
+/**
* __lock_page - get a lock on the page, assuming we need to sleep to get it
* @page: the page to lock
*
@@ -2562,6 +2577,9 @@ out:
* (presumably at page->private). If the release was successful, return `1'.
* Otherwise return zero.
*
+ * This may also be called if PG_fscache is set on a page, indicating that the
+ * page is known to the local caching routines.
+ *
* The @gfp_mask argument specifies whether I/O may be performed to release
* this page (__GFP_IO), and whether the call may block (__GFP_WAIT).
*
diff --git a/mm/migrate.c b/mm/migrate.c
index 75ae1fb..ba4a9b2 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -546,7 +546,7 @@ static int fallback_migrate_page(struct address_space *mapping,
* Buffers may be managed in a filesystem specific way.
* We must have no buffers or drop them.
*/
- if (PagePrivate(page) &&
+ if (page_has_private(page) &&
!try_to_release_page(page, GFP_KERNEL))
return -EAGAIN;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 75b9793..036e80a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -231,6 +231,7 @@ static void bad_page(struct page *page)
dump_stack();
page->flags &= ~(1 << PG_lru |
1 << PG_private |
+ 1 << PG_fscache |
1 << PG_locked |
1 << PG_active |
1 << PG_dirty |
@@ -457,6 +458,7 @@ static inline int free_pages_check(struct page *page)
(page->flags & (
1 << PG_lru |
1 << PG_private |
+ 1 << PG_fscache |
1 << PG_locked |
1 << PG_active |
1 << PG_slab |
@@ -606,6 +608,7 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
(page->flags & (
1 << PG_lru |
1 << PG_private |
+ 1 << PG_fscache |
1 << PG_locked |
1 << PG_active |
1 << PG_dirty |
diff --git a/mm/readahead.c b/mm/readahead.c
index 75aa6b6..272ffc7 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -46,14 +46,15 @@ EXPORT_SYMBOL_GPL(file_ra_state_init);
/*
* see if a page needs releasing upon read_cache_pages() failure
- * - the caller of read_cache_pages() may have set PG_private before calling,
- * such as the NFS fs marking pages that are cached locally on disk, thus we
- * need to give the fs a chance to clean up in the event of an error
+ * - the caller of read_cache_pages() may have set PG_private or PG_fscache
+ * before calling, such as the NFS fs marking pages that are cached locally
+ * on disk, thus we need to give the fs a chance to clean up in the event of
+ * an error
*/
static void read_cache_pages_invalidate_page(struct address_space *mapping,
struct page *page)
{
- if (PagePrivate(page)) {
+ if (page_has_private(page)) {
if (TestSetPageLocked(page))
BUG();
page->mapping = mapping;
diff --git a/mm/swap.c b/mm/swap.c
index 710a20b..36aa619 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -457,8 +457,8 @@ void pagevec_strip(struct pagevec *pvec)
for (i = 0; i < pagevec_count(pvec); i++) {
struct page *page = pvec->pages[i];
- if (PagePrivate(page) && !TestSetPageLocked(page)) {
- if (PagePrivate(page))
+ if (page_has_private(page) && !TestSetPageLocked(page)) {
+ if (page_has_private(page))
try_to_release_page(page, 0);
unlock_page(page);
}
diff --git a/mm/swap_state.c b/mm/swap_state.c
index ec42f01..c3509f2 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -73,7 +73,7 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask)
BUG_ON(!PageLocked(page));
BUG_ON(PageSwapCache(page));
- BUG_ON(PagePrivate(page));
+ BUG_ON(page_has_private(page));
error = radix_tree_preload(gfp_mask);
if (!error) {
write_lock_irq(&swapper_space.tree_lock);
@@ -102,7 +102,7 @@ void __delete_from_swap_cache(struct page *page)
BUG_ON(!PageLocked(page));
BUG_ON(!PageSwapCache(page));
BUG_ON(PageWriteback(page));
- BUG_ON(PagePrivate(page));
+ BUG_ON(page_has_private(page));
radix_tree_delete(&swapper_space.page_tree, page_private(page));
set_page_private(page, 0);
diff --git a/mm/truncate.c b/mm/truncate.c
index c35c49e..78b22a1 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -49,7 +49,7 @@ void do_invalidatepage(struct page *page, unsigned long offset)
static inline void truncate_partial_page(struct page *page, unsigned partial)
{
zero_user_segment(page, partial, PAGE_CACHE_SIZE);
- if (PagePrivate(page))
+ if (page_has_private(page))
do_invalidatepage(page, partial);
}
@@ -98,7 +98,7 @@ truncate_complete_page(struct address_space *mapping, struct page *page)
if (page->mapping != mapping)
return;
- if (PagePrivate(page))
+ if (page_has_private(page))
do_invalidatepage(page, 0);
cancel_dirty_page(page, PAGE_CACHE_SIZE);
@@ -125,7 +125,7 @@ invalidate_complete_page(struct address_space *mapping, struct page *page)
if (page->mapping != mapping)
return 0;
- if (PagePrivate(page) && !try_to_release_page(page, 0))
+ if (page_has_private(page) && !try_to_release_page(page, 0))
return 0;
ret = remove_mapping(mapping, page);
@@ -347,14 +347,14 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
if (page->mapping != mapping)
return 0;
- if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL))
+ if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL))
return 0;
write_lock_irq(&mapping->tree_lock);
if (PageDirty(page))
goto failed;
- BUG_ON(PagePrivate(page));
+ BUG_ON(page_has_private(page));
__remove_from_page_cache(page);
write_unlock_irq(&mapping->tree_lock);
ClearPageUptodate(page);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a26dabd..e1cc660 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -607,7 +607,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
* process address space (page_count == 1) it can be freed.
* Otherwise, leave the page on the LRU so it is swappable.
*/
- if (PagePrivate(page)) {
+ if (page_has_private(page)) {
if (!try_to_release_page(page, sc->gfp_mask))
goto activate_locked;
if (!mapping && page_count(page) == 1)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists