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 <[email protected]>
Signed-off-by: Mel Gorman <[email protected]>
Acked-by: Rik van Riel <[email protected]>
Cc: Christoph Hellwig <[email protected]>
Cc: David S. Miller <[email protected]>
Cc: Eric B Munson <[email protected]>
Cc: Eric Paris <[email protected]>
Cc: James Morris <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Mike Christie <[email protected]>
Cc: Neil Brown <[email protected]>
Cc: Sebastian Andrzej Siewior <[email protected]>
Cc: Trond Myklebust <[email protected]>
Cc: Xiaotian Feng <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

2 files changed, 39 insertions, 14 deletions

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 35f7e4bc680e..1d57fe9f49a9 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -882,6 +882,10 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
 	struct nfs_inode *nfsi = NFS_I(inode);
 	int ret = 0;
 
+	/* swapfiles are not supposed to be shared. */
+	if (IS_SWAPFILE(inode))
+		goto out;
+
 	if (nfs_mapping_need_revalidate_inode(inode)) {
 		ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
 		if (ret < 0)
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index d0feca32b4fe..974e9c2d31fd 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -139,15 +139,28 @@ static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error)
 	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 @@ static struct nfs_page *nfs_page_find_request(struct page *page)
 	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 @@ static struct nfs_page *nfs_find_and_lock_request(struct page *page, bool nonblo
 
 	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 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
 	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 @@ static void nfs_inode_remove_request(struct nfs_page *req)
 	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 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode,
 	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_cancel(struct inode *inode, struct page *page)
  */
 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,