mount/fuse: use a queue instead of pipe to communicate with thread

doing inode/entry invalidations.

Writing to pipe can block if pipe is full. This can lead to deadlocks
in some situations. Consider following situation:

1. Kernel sends a write on an inode. Client is waiting for a response
   to write from brick.
2. A lookup happens on behalf of different application/thread on the
   same inode. In response, mdc tries to invalidate the inode.
3. fuse_invalidate_inode is called. It writes a invalidation request
   to pipe. Another thread which reads from this pipe writes the
   request to /dev/fuse. The invalidate code in fuse-kernel-module,
   tries to acquire lock on all pages for the inode and is blocked as
   a write is in progress on same inode (step 1)
4. Now, poller thread is blocked in invalidate notification and cannot
   receive any messages from same socket (on which lookup response
   came). But client is expecting a response for write from same
   socket (again step1) and we've a deadlock.

The deadlock can be solved in two ways:
1. Use a queue (and a conditional variable for notifications) to pass
   invalidation requests from poller to invalidate thread. This is a
   variant of using non-blocking pipe, but doesn't have any limit on the
   amount of data (worst case we run out of memory and error out).

2. Allow events from sockets, immediately after we read one
   rpc-msg. Currently we disallow events till that rpc-msg is read from
   socket, processed and handled by higher layers. That way we won't run
   into these kind of issues. Also, it'll increase parallelism in way of
   reading from sockets.

This patch implements solution 1 above.

Change-Id: I8e8199fd7f4da9eab46a719d9292f35c039967e1
BUG: 1273387
Signed-off-by: Raghavendra G <rgowdapp@redhat.com>
Reviewed-on: http://review.gluster.org/12402

1 files changed, 15 insertions, 7 deletions

diff --git a/xlators/mount/fuse/src/fuse-bridge.h b/xlators/mount/fuse/src/fuse-bridge.h
index ea346c05f9e..08af454be63 100644
--- a/xlators/mount/fuse/src/fuse-bridge.h
+++ b/xlators/mount/fuse/src/fuse-bridge.h
@@ -110,8 +110,9 @@ struct fuse_private {
         char                *fuse_mountopts;
 
         /* For fuse-reverse-validation */
-        int                  revchan_in;
-        int                  revchan_out;
+        struct list_head     invalidate_list;
+        pthread_cond_t       invalidate_cond;
+        pthread_mutex_t      invalidate_mutex;
         gf_boolean_t         reverse_fuse_thread_started;
 
         /* For communicating with separate mount thread. */
@@ -133,6 +134,18 @@ struct fuse_private {
 };
 typedef struct fuse_private fuse_private_t;
 
+#define INVAL_BUF_SIZE (sizeof (struct fuse_out_header) +               \
+                        max (sizeof (struct fuse_notify_inval_inode_out), \
+                             sizeof (struct fuse_notify_inval_entry_out) + \
+                             NAME_MAX + 1))
+
+
+struct fuse_invalidate_node {
+        char             inval_buf[INVAL_BUF_SIZE];
+        struct list_head next;
+};
+typedef struct fuse_invalidate_node fuse_invalidate_node_t;
+
 struct fuse_graph_switch_args {
         xlator_t        *this;
         xlator_t        *old_subvol;
@@ -140,11 +153,6 @@ struct fuse_graph_switch_args {
 };
 typedef struct fuse_graph_switch_args fuse_graph_switch_args_t;
 
-#define INVAL_BUF_SIZE (sizeof (struct fuse_out_header) +               \
-                        max (sizeof (struct fuse_notify_inval_inode_out), \
-                             sizeof (struct fuse_notify_inval_entry_out) + \
-                             NAME_MAX + 1))
-
 #define FUSE_EVENT_HISTORY_SIZE 1024
 
 #define _FH_TO_FD(fh) ((fd_t *)(uintptr_t)(fh))