nfsd41: sunrpc: Added rpc server-side backchannel handling

When the call direction is a reply, copy the xid and call direction into the
req->rq_private_buf.head[0].iov_base otherwise rpc_verify_header returns
rpc_garbage.

Signed-off-by: Rahul Iyer <iyer@netapp.com>
Signed-off-by: Mike Sager <sager@netapp.com>
Signed-off-by: Marc Eshel <eshel@almaden.ibm.com>
Signed-off-by: Benny Halevy <bhalevy@panasas.com>
Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com>
Signed-off-by: Andy Adamson <andros@netapp.com>
Signed-off-by: Benny Halevy <bhalevy@panasas.com>
[get rid of CONFIG_NFSD_V4_1]
[sunrpc: refactoring of svc_tcp_recvfrom]
[nfsd41: sunrpc: create common send routine for the fore and the back channels]
[nfsd41: sunrpc: Use free_page() to free server backchannel pages]
[nfsd41: sunrpc: Document server backchannel locking]
[nfsd41: sunrpc: remove bc_connect_worker()]
[nfsd41: sunrpc: Define xprt_server_backchannel()[
[nfsd41: sunrpc: remove bc_close and bc_init_auto_disconnect dummy functions]
[nfsd41: sunrpc: eliminate unneeded switch statement in xs_setup_tcp()]
[nfsd41: sunrpc: Don't auto close the server backchannel connection]
[nfsd41: sunrpc: Remove unused functions]
Signed-off-by: Alexandros Batsakis <batsakis@netapp.com>
Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com>
Signed-off-by: Benny Halevy <bhalevy@panasas.com>
[nfsd41: change bc_sock to bc_xprt]
[nfsd41: sunrpc: move struct rpc_buffer def into a common header file]
[nfsd41: sunrpc: use rpc_sleep in bc_send_request so not to block on mutex]
[removed cosmetic changes]
Signed-off-by: Benny Halevy <bhalevy@panasas.com>
[sunrpc: add new xprt class for nfsv4.1 backchannel]
[sunrpc: v2.1 change handling of auto_close and init_auto_disconnect operations for the nfsv4.1 backchannel]
Signed-off-by: Alexandros Batsakis <batsakis@netapp.com>
[reverted more cosmetic leftovers]
[got rid of xprt_server_backchannel]
[separated "nfsd41: sunrpc: add new xprt class for nfsv4.1 backchannel"]
Signed-off-by: Benny Halevy <bhalevy@panasas.com>
Cc: Trond Myklebust <trond.myklebust@netapp.com>
[sunrpc: change idle timeout value for the backchannel]
Signed-off-by: Alexandros Batsakis <batsakis@netapp.com>
Signed-off-by: Benny Halevy <bhalevy@panasas.com>
Acked-by: Trond Myklebust <trond.myklebust@netapp.com>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>

1 files changed, 146 insertions, 0 deletions

diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 62438f3a914d..d9a2b815714e 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -32,6 +32,7 @@
 #include <linux/tcp.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/sched.h>
+#include <linux/sunrpc/svcsock.h>
 #include <linux/sunrpc/xprtsock.h>
 #include <linux/file.h>
 #ifdef CONFIG_NFS_V4_1
@@ -43,6 +44,7 @@
 #include <net/udp.h>
 #include <net/tcp.h>
 
+#include "sunrpc.h"
 /*
  * xprtsock tunables
  */
@@ -2098,6 +2100,134 @@ static void xs_tcp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
                         xprt->stat.bklog_u);
 }
 
+/*
+ * Allocate a bunch of pages for a scratch buffer for the rpc code. The reason
+ * we allocate pages instead doing a kmalloc like rpc_malloc is because we want
+ * to use the server side send routines.
+ */
+void *bc_malloc(struct rpc_task *task, size_t size)
+{
+        struct page *page;
+        struct rpc_buffer *buf;
+
+        BUG_ON(size > PAGE_SIZE - sizeof(struct rpc_buffer));
+        page = alloc_page(GFP_KERNEL);
+
+        if (!page)
+                return NULL;
+
+        buf = page_address(page);
+        buf->len = PAGE_SIZE;
+
+        return buf->data;
+}
+
+/*
+ * Free the space allocated in the bc_alloc routine
+ */
+void bc_free(void *buffer)
+{
+        struct rpc_buffer *buf;
+
+        if (!buffer)
+                return;
+
+        buf = container_of(buffer, struct rpc_buffer, data);
+        free_page((unsigned long)buf);
+}
+
+/*
+ * Use the svc_sock to send the callback. Must be called with svsk->sk_mutex
+ * held. Borrows heavily from svc_tcp_sendto and xs_tcp_send_request.
+ */
+static int bc_sendto(struct rpc_rqst *req)
+{
+        int len;
+        struct xdr_buf *xbufp = &req->rq_snd_buf;
+        struct rpc_xprt *xprt = req->rq_xprt;
+        struct sock_xprt *transport =
+                                container_of(xprt, struct sock_xprt, xprt);
+        struct socket *sock = transport->sock;
+        unsigned long headoff;
+        unsigned long tailoff;
+
+        /*
+         * Set up the rpc header and record marker stuff
+         */
+        xs_encode_tcp_record_marker(xbufp);
+
+        tailoff = (unsigned long)xbufp->tail[0].iov_base & ~PAGE_MASK;
+        headoff = (unsigned long)xbufp->head[0].iov_base & ~PAGE_MASK;
+        len = svc_send_common(sock, xbufp,
+                              virt_to_page(xbufp->head[0].iov_base), headoff,
+                              xbufp->tail[0].iov_base, tailoff);
+
+        if (len != xbufp->len) {
+                printk(KERN_NOTICE "Error sending entire callback!\n");
+                len = -EAGAIN;
+        }
+
+        return len;
+}
+
+/*
+ * The send routine. Borrows from svc_send
+ */
+static int bc_send_request(struct rpc_task *task)
+{
+        struct rpc_rqst *req = task->tk_rqstp;
+        struct svc_xprt *xprt;
+        struct svc_sock         *svsk;
+        u32                     len;
+
+        dprintk("sending request with xid: %08x\n", ntohl(req->rq_xid));
+        /*
+         * Get the server socket associated with this callback xprt
+         */
+        xprt = req->rq_xprt->bc_xprt;
+        svsk = container_of(xprt, struct svc_sock, sk_xprt);
+
+        /*
+         * Grab the mutex to serialize data as the connection is shared
+         * with the fore channel
+         */
+        if (!mutex_trylock(&xprt->xpt_mutex)) {
+                rpc_sleep_on(&xprt->xpt_bc_pending, task, NULL);
+                if (!mutex_trylock(&xprt->xpt_mutex))
+                        return -EAGAIN;
+                rpc_wake_up_queued_task(&xprt->xpt_bc_pending, task);
+        }
+        if (test_bit(XPT_DEAD, &xprt->xpt_flags))
+                len = -ENOTCONN;
+        else
+                len = bc_sendto(req);
+        mutex_unlock(&xprt->xpt_mutex);
+
+        if (len > 0)
+                len = 0;
+
+        return len;
+}
+
+/*
+ * The close routine. Since this is client initiated, we do nothing
+ */
+
+static void bc_close(struct rpc_xprt *xprt)
+{
+        return;
+}
+
+/*
+ * The xprt destroy routine. Again, because this connection is client
+ * initiated, we do nothing
+ */
+
+static void bc_destroy(struct rpc_xprt *xprt)
+{
+        return;
+}
+
 static struct rpc_xprt_ops xs_udp_ops = {
         .set_buffer_size        = xs_udp_set_buffer_size,
         .reserve_xprt           = xprt_reserve_xprt_cong,
@@ -2134,6 +2264,22 @@ static struct rpc_xprt_ops xs_tcp_ops = {
         .print_stats            = xs_tcp_print_stats,
 };
 
+/*
+ * The rpc_xprt_ops for the server backchannel
+ */
+
+static struct rpc_xprt_ops bc_tcp_ops = {
+        .reserve_xprt           = xprt_reserve_xprt,
+        .release_xprt           = xprt_release_xprt,
+        .buf_alloc              = bc_malloc,
+        .buf_free               = bc_free,
+        .send_request           = bc_send_request,
+        .set_retrans_timeout    = xprt_set_retrans_timeout_def,
+        .close                  = bc_close,
+        .destroy                = bc_destroy,
+        .print_stats            = xs_tcp_print_stats,
+};
+
 static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args,
                                       unsigned int slot_table_size)
 {