libceph: don't bail early from try_read() when skipping a message

commit e7a88e82fe380459b864e05b372638aeacb0f52d upstream.

The contract between try_read() and try_write() is that when called
each processes as much data as possible.  When instructed by osd_client
to skip a message, try_read() is violating this contract by returning
after receiving and discarding a single message instead of checking for
more.  try_write() then gets a chance to write out more requests,
generating more replies/skips for try_read() to handle, forcing the
messenger into a starvation loop.

Reported-by: Varada Kari <Varada.Kari@sandisk.com>
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Tested-by: Varada Kari <Varada.Kari@sandisk.com>
Reviewed-by: Alex Elder <elder@linaro.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index e3bea2e0821a4e64591e0cd6cc4b9dd3c364b35c..025ced8fbb5779f5e5eaba8ebaf3101323e56b3f 100644 (file)
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -2277,7 +2277,7 @@ static int read_partial_message(struct ceph_connection *con)
                con->in_base_pos = -front_len - middle_len - data_len -
                        sizeof(m->footer);
                con->in_tag = CEPH_MSGR_TAG_READY;
-               return 0;
+               return 1;
        } else if ((s64)seq - (s64)con->in_seq > 1) {
                pr_err("read_partial_message bad seq %lld expected %lld\n",
                       seq, con->in_seq + 1);
@@ -2310,7 +2310,7 @@ static int read_partial_message(struct ceph_connection *con)
                                sizeof(m->footer);
                        con->in_tag = CEPH_MSGR_TAG_READY;
                        con->in_seq++;
-                       return 0;
+                       return 1;
                }
 
                BUG_ON(!con->in_msg);