| 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: <20120211074356.30852.88524.stgit@zurg>
Date: Sat, 11 Feb 2012 11:44:08 +0400
From: Konstantin Khlebnikov <khlebnikov@...nvz.org>
To: linux-mm@...ck.org, Andrew Morton <akpm@...ux-foundation.org>,
Hugh Dickins <hughd@...gle.com>, linux-kernel@...r.kernel.org
Cc: Linus Torvalds <torvalds@...ux-foundation.org>
Subject: [PATCH 6/4] shmem: simplify shmem_truncate_range
find_get_pages() now can skip unlimited count of exeptional entries,
so truncate_inode_pages_range() can truncate pages from shmem inodes.
Thus shmem_truncate_range() can be simplified.
Signed-off-by: Konstantin Khlebnikov <khlebnikov@...nvz.org>
---
mm/shmem.c | 199 +++++++++++++++---------------------------------------------
1 files changed, 49 insertions(+), 150 deletions(-)
diff --git a/mm/shmem.c b/mm/shmem.c
index 709e3d8..b981fa9 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -302,57 +302,6 @@ static int shmem_add_to_page_cache(struct page *page,
}
/*
- * Like find_get_pages, but collecting swap entries as well as pages.
- */
-static unsigned shmem_find_get_pages_and_swap(struct address_space *mapping,
- pgoff_t start, unsigned int nr_pages,
- struct page **pages, pgoff_t *indices)
-{
- unsigned int i;
- unsigned int ret;
- unsigned int nr_found;
-
- rcu_read_lock();
-restart:
- nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree,
- (void ***)pages, indices, start, nr_pages);
- ret = 0;
- for (i = 0; i < nr_found; i++) {
- struct page *page;
-repeat:
- page = radix_tree_deref_slot((void **)pages[i]);
- if (unlikely(!page))
- continue;
- if (radix_tree_exception(page)) {
- if (radix_tree_deref_retry(page))
- goto restart;
- /*
- * Otherwise, we must be storing a swap entry
- * here as an exceptional entry: so return it
- * without attempting to raise page count.
- */
- goto export;
- }
- if (!page_cache_get_speculative(page))
- goto repeat;
-
- /* Has the page moved? */
- if (unlikely(page != *((void **)pages[i]))) {
- page_cache_release(page);
- goto repeat;
- }
-export:
- indices[ret] = indices[i];
- pages[ret] = page;
- ret++;
- }
- if (unlikely(!ret && nr_found))
- goto restart;
- rcu_read_unlock();
- return ret;
-}
-
-/*
* Remove swap entry from radix tree, free the swap and its page cache.
*/
static int shmem_free_swap(struct address_space *mapping,
@@ -369,21 +318,6 @@ static int shmem_free_swap(struct address_space *mapping,
}
/*
- * Pagevec may contain swap entries, so shuffle up pages before releasing.
- */
-static void shmem_deswap_pagevec(struct pagevec *pvec)
-{
- int i, j;
-
- for (i = 0, j = 0; i < pagevec_count(pvec); i++) {
- struct page *page = pvec->pages[i];
- if (!radix_tree_exceptional_entry(page))
- pvec->pages[j++] = page;
- }
- pvec->nr = j;
-}
-
-/*
* SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists.
*/
void shmem_unlock_mapping(struct address_space *mapping)
@@ -406,6 +340,50 @@ void shmem_unlock_mapping(struct address_space *mapping)
}
/*
+ * Remove range of swap entries from radix tree, and free them.
+ */
+static long shmem_truncate_swap_range(struct address_space *mapping,
+ pgoff_t start, pgoff_t end)
+{
+ struct radix_tree_iter iter;
+ void **slot, *data, *radswaps[PAGEVEC_SIZE];
+ unsigned long indices[PAGEVEC_SIZE];
+ long nr_swaps_freed = 0;
+ int i, nr;
+
+next:
+ rcu_read_lock();
+ nr = 0;
+restart:
+ radix_tree_for_each_tagged(slot, &mapping->page_tree, &iter,
+ start, SHMEM_TAG_SWAP) {
+ if (iter.index > end)
+ break;
+ data = radix_tree_deref_slot(slot);
+ if (!data || !radix_tree_exception(data))
+ continue;
+ if (radix_tree_deref_retry(data))
+ goto restart;
+ radswaps[nr] = data;
+ indices[nr] = iter.index;
+ if (++nr == PAGEVEC_SIZE)
+ break;
+ }
+ rcu_read_unlock();
+
+ for ( i = 0 ; i < nr ; i++ ) {
+ if (!shmem_free_swap(mapping, indices[i], radswaps[i]))
+ nr_swaps_freed++;
+ start = indices[i] + 1;
+ }
+
+ if (nr == PAGEVEC_SIZE && start)
+ goto next;
+
+ return nr_swaps_freed;
+}
+
+/*
* Remove range of pages and swap entries from radix tree, and free them.
*/
void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
@@ -415,52 +393,11 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
pgoff_t start = (lstart + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
unsigned partial = lstart & (PAGE_CACHE_SIZE - 1);
pgoff_t end = (lend >> PAGE_CACHE_SHIFT);
- struct pagevec pvec;
- pgoff_t indices[PAGEVEC_SIZE];
long nr_swaps_freed = 0;
- pgoff_t index;
- int i;
BUG_ON((lend & (PAGE_CACHE_SIZE - 1)) != (PAGE_CACHE_SIZE - 1));
- pagevec_init(&pvec, 0);
- index = start;
- while (index <= end) {
- pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
- min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
- pvec.pages, indices);
- if (!pvec.nr)
- break;
- mem_cgroup_uncharge_start();
- for (i = 0; i < pagevec_count(&pvec); i++) {
- struct page *page = pvec.pages[i];
-
- index = indices[i];
- if (index > end)
- break;
-
- if (radix_tree_exceptional_entry(page)) {
- nr_swaps_freed += !shmem_free_swap(mapping,
- index, page);
- continue;
- }
-
- if (!trylock_page(page))
- continue;
- if (page->mapping == mapping) {
- VM_BUG_ON(PageWriteback(page));
- truncate_inode_page(mapping, page);
- }
- unlock_page(page);
- }
- shmem_deswap_pagevec(&pvec);
- pagevec_release(&pvec);
- mem_cgroup_uncharge_end();
- cond_resched();
- index++;
- }
-
- if (partial) {
+ if (IS_ENABLED(CONFIG_SWAP) && partial) {
struct page *page = NULL;
shmem_getpage(inode, start - 1, &page, SGP_READ, NULL);
if (page) {
@@ -469,51 +406,13 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
unlock_page(page);
page_cache_release(page);
}
+ lstart += PAGE_CACHE_SIZE - partial;
}
- index = start;
- for ( ; ; ) {
- cond_resched();
- pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
- min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
- pvec.pages, indices);
- if (!pvec.nr) {
- if (index == start)
- break;
- index = start;
- continue;
- }
- if (index == start && indices[0] > end) {
- shmem_deswap_pagevec(&pvec);
- pagevec_release(&pvec);
- break;
- }
- mem_cgroup_uncharge_start();
- for (i = 0; i < pagevec_count(&pvec); i++) {
- struct page *page = pvec.pages[i];
-
- index = indices[i];
- if (index > end)
- break;
+ truncate_inode_pages_range(mapping, lstart, lend);
- if (radix_tree_exceptional_entry(page)) {
- nr_swaps_freed += !shmem_free_swap(mapping,
- index, page);
- continue;
- }
-
- lock_page(page);
- if (page->mapping == mapping) {
- VM_BUG_ON(PageWriteback(page));
- truncate_inode_page(mapping, page);
- }
- unlock_page(page);
- }
- shmem_deswap_pagevec(&pvec);
- pagevec_release(&pvec);
- mem_cgroup_uncharge_end();
- index++;
- }
+ if (IS_ENABLED(CONFIG_SWAP))
+ nr_swaps_freed = shmem_truncate_swap_range(mapping, start, end);
spin_lock(&info->lock);
info->swapped -= nr_swaps_freed;
--
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