nfs: disable data cache revalidation for swapfiles
The VM does not like PG_private set on PG_swapcache pages. As suggested
by Trond in http://lkml.org/lkml/2006/8/25/348, this patch disables NFS
data cache revalidation on swap files. as it does not make sense to have
other clients change the file while it is being used as swap. This avoids
setting PG_private on swap pages, since there ought to be no further races
with invalidate_inode_pages2() to deal with.
Since we cannot set PG_private we cannot use page->private which is
already used by PG_swapcache pages to store the nfs_page. Thus augment
the new nfs_page_find_request logic.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Eric B Munson <emunson@mgebm.net>
Cc: Eric Paris <eparis@redhat.com>
Cc: James Morris <jmorris@namei.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mike Christie <michaelc@cs.wisc.edu>
Cc: Neil Brown <neilb@suse.de>
Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Cc: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Xiaotian Feng <dfeng@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index d0feca3..974e9c2 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -139,15 +139,28 @@
set_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
}
-static struct nfs_page *nfs_page_find_request_locked(struct page *page)
+static struct nfs_page *
+nfs_page_find_request_locked(struct nfs_inode *nfsi, struct page *page)
{
struct nfs_page *req = NULL;
- if (PagePrivate(page)) {
+ if (PagePrivate(page))
req = (struct nfs_page *)page_private(page);
- if (req != NULL)
- kref_get(&req->wb_kref);
+ else if (unlikely(PageSwapCache(page))) {
+ struct nfs_page *freq, *t;
+
+ /* Linearly search the commit list for the correct req */
+ list_for_each_entry_safe(freq, t, &nfsi->commit_info.list, wb_list) {
+ if (freq->wb_page == page) {
+ req = freq;
+ break;
+ }
+ }
}
+
+ if (req)
+ kref_get(&req->wb_kref);
+
return req;
}
@@ -157,7 +170,7 @@
struct nfs_page *req = NULL;
spin_lock(&inode->i_lock);
- req = nfs_page_find_request_locked(page);
+ req = nfs_page_find_request_locked(NFS_I(inode), page);
spin_unlock(&inode->i_lock);
return req;
}
@@ -258,7 +271,7 @@
spin_lock(&inode->i_lock);
for (;;) {
- req = nfs_page_find_request_locked(page);
+ req = nfs_page_find_request_locked(NFS_I(inode), page);
if (req == NULL)
break;
if (nfs_lock_request(req))
@@ -413,9 +426,15 @@
spin_lock(&inode->i_lock);
if (!nfsi->npages && NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
inode->i_version++;
- set_bit(PG_MAPPED, &req->wb_flags);
- SetPagePrivate(req->wb_page);
- set_page_private(req->wb_page, (unsigned long)req);
+ /*
+ * Swap-space should not get truncated. Hence no need to plug the race
+ * with invalidate/truncate.
+ */
+ if (likely(!PageSwapCache(req->wb_page))) {
+ set_bit(PG_MAPPED, &req->wb_flags);
+ SetPagePrivate(req->wb_page);
+ set_page_private(req->wb_page, (unsigned long)req);
+ }
nfsi->npages++;
kref_get(&req->wb_kref);
spin_unlock(&inode->i_lock);
@@ -432,9 +451,11 @@
BUG_ON (!NFS_WBACK_BUSY(req));
spin_lock(&inode->i_lock);
- set_page_private(req->wb_page, 0);
- ClearPagePrivate(req->wb_page);
- clear_bit(PG_MAPPED, &req->wb_flags);
+ if (likely(!PageSwapCache(req->wb_page))) {
+ set_page_private(req->wb_page, 0);
+ ClearPagePrivate(req->wb_page);
+ clear_bit(PG_MAPPED, &req->wb_flags);
+ }
nfsi->npages--;
spin_unlock(&inode->i_lock);
nfs_release_request(req);
@@ -730,7 +751,7 @@
spin_lock(&inode->i_lock);
for (;;) {
- req = nfs_page_find_request_locked(page);
+ req = nfs_page_find_request_locked(NFS_I(inode), page);
if (req == NULL)
goto out_unlock;
@@ -1744,7 +1765,7 @@
*/
int nfs_wb_page(struct inode *inode, struct page *page)
{
- loff_t range_start = page_offset(page);
+ loff_t range_start = page_file_offset(page);
loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1);
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,