ceph: fix rdcache_gen usage and invalidate

We used to use rdcache_gen to indicate whether we "might" have cached
pages.  Now we just look at the mapping to determine that.  However, some
old behavior remains from that transition.

First, rdcache_gen == 0 no longer means we have no pages.  That can happen
at any time (presumably when we carry FILE_CACHE).  We should not reset it
to zero, and we should not check that it is zero.

That means that the only purpose for rdcache_revoking is to resolve races
between new issues of FILE_CACHE and an async invalidate.  If they are
equal, we should invalidate.  On success, we decrement rdcache_revoking,
so that it is no longer equal to rdcache_gen.  Similarly, if we success
in doing a sync invalidate, set revoking = gen - 1.  (This is a small
optimization to avoid doing unnecessary invalidate work and does not
affect correctness.)

Signed-off-by: Sage Weil <sage@newdream.net>

3 files changed, 10 insertions, 14 deletions

diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 04b207b..60d27bc 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1430,8 +1430,8 @@ static int try_nonblocking_invalidate(struct inode *inode)
 	    invalidating_gen == ci->i_rdcache_gen) {
 		/* success. */
 		dout("try_nonblocking_invalidate %p success\n", inode);
-		ci->i_rdcache_gen = 0;
-		ci->i_rdcache_revoking = 0;
+		/* save any racing async invalidate some trouble */
+		ci->i_rdcache_revoking = ci->i_rdcache_gen - 1;
 		return 0;
 	}
 	dout("try_nonblocking_invalidate %p failed\n", inode);
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 0a49ffd..5a9f907 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1394,11 +1394,8 @@ static void ceph_invalidate_work(struct work_struct *work)
 	spin_lock(&inode->i_lock);
 	dout("invalidate_pages %p gen %d revoking %d\n", inode,
 	     ci->i_rdcache_gen, ci->i_rdcache_revoking);
-	if (ci->i_rdcache_gen == 0 ||
-	    ci->i_rdcache_revoking != ci->i_rdcache_gen) {
-		BUG_ON(ci->i_rdcache_revoking > ci->i_rdcache_gen);
+	if (ci->i_rdcache_revoking != ci->i_rdcache_gen) {
 		/* nevermind! */
-		ci->i_rdcache_revoking = 0;
 		spin_unlock(&inode->i_lock);
 		goto out;
 	}
@@ -1408,15 +1405,16 @@ static void ceph_invalidate_work(struct work_struct *work)
 	ceph_invalidate_nondirty_pages(inode->i_mapping);
 
 	spin_lock(&inode->i_lock);
-	if (orig_gen == ci->i_rdcache_gen) {
+	if (orig_gen == ci->i_rdcache_gen &&
+	    orig_gen == ci->i_rdcache_revoking) {
 		dout("invalidate_pages %p gen %d successful\n", inode,
 		     ci->i_rdcache_gen);
-		ci->i_rdcache_gen = 0;
-		ci->i_rdcache_revoking = 0;
+		ci->i_rdcache_revoking--;
 		check = 1;
 	} else {
-		dout("invalidate_pages %p gen %d raced, gen now %d\n",
-		     inode, orig_gen, ci->i_rdcache_gen);
+		dout("invalidate_pages %p gen %d raced, now %d revoking %d\n",
+		     inode, orig_gen, ci->i_rdcache_gen,
+		     ci->i_rdcache_revoking);
 	}
 	spin_unlock(&inode->i_lock);
 
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 1886294..7f01728 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -293,9 +293,7 @@ struct ceph_inode_info {
 	int i_rd_ref, i_rdcache_ref, i_wr_ref;
 	int i_wrbuffer_ref, i_wrbuffer_ref_head;
 	u32 i_shared_gen;       /* increment each time we get FILE_SHARED */
-	u32 i_rdcache_gen;      /* we increment this each time we get
-				   FILE_CACHE.  If it's non-zero, we
-				   _may_ have cached pages. */
+	u32 i_rdcache_gen;      /* incremented each time we get FILE_CACHE. */
 	u32 i_rdcache_revoking; /* RDCACHE gen to async invalidate, if any */
 
 	struct list_head i_unsafe_writes; /* uncommitted sync writes */