SUNRPC: Generalize the RPC buffer allocation API

xprtrdma needs to allocate the Call and Reply buffers separately.
TBH, the reliance on using a single buffer for the pair of XDR
buffers is transport implementation-specific.

Transports that want to allocate separate Call and Reply buffers
will ignore the "size" argument anyway.  Don't bother passing it.

The buf_alloc method can't return two pointers. Instead, make the
method's return value an error code, and set the rq_buffer pointer
in the method itself.

This gives call_allocate an opportunity to terminate an RPC instead
of looping forever when a permanent problem occurs. If a request is
just bogus, or the transport is in a state where it can't allocate
resources for any request, there needs to be a way to kill the RPC
right there and not loop.

This immediately fixes a rare problem in the backchannel send path,
which loops if the server happens to send a CB request whose
call+reply size is larger than a page (which it shouldn't do yet).

One more issue: looks like xprt_inject_disconnect was incorrectly
placed in the failure path in call_allocate. It needs to be in the
success path, as it is for other call-sites.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

2 files changed, 27 insertions, 16 deletions

diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index a2a7519b0f23..124688ba67e5 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -159,29 +159,30 @@ out_unmap:
 /* Server-side transport endpoint wants a whole page for its send
  * buffer. The client RPC code constructs the RPC header in this
  * buffer before it invokes ->send_request.
- *
- * Returns NULL if there was a temporary allocation failure.
  */
-static void *
-xprt_rdma_bc_allocate(struct rpc_task *task, size_t size)
+static int
+xprt_rdma_bc_allocate(struct rpc_task *task)
 {
 	struct rpc_rqst *rqst = task->tk_rqstp;
 	struct svc_xprt *sxprt = rqst->rq_xprt->bc_xprt;
+	size_t size = rqst->rq_callsize;
 	struct svcxprt_rdma *rdma;
 	struct page *page;
 
 	rdma = container_of(sxprt, struct svcxprt_rdma, sc_xprt);
 
-	/* Prevent an infinite loop: try to make this case work */
-	if (size > PAGE_SIZE)
+	if (size > PAGE_SIZE) {
 		WARN_ONCE(1, "svcrdma: large bc buffer request (size %zu)\n",
 			  size);
+		return -EINVAL;
+	}
 
 	page = alloc_page(RPCRDMA_DEF_GFP);
 	if (!page)
-		return NULL;
+		return -ENOMEM;
 
-	return page_address(page);
+	rqst->rq_buffer = page_address(page);
+	return 0;
 }
 
 static void
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index be95eced0726..daa7d4d43fd8 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -477,7 +477,15 @@ xprt_rdma_connect(struct rpc_xprt *xprt, struct rpc_task *task)
 	}
 }
 
-/*
+/**
+ * xprt_rdma_allocate - allocate transport resources for an RPC
+ * @task: RPC task
+ *
+ * Return values:
+ *        0:	Success; rq_buffer points to RPC buffer to use
+ *   ENOMEM:	Out of memory, call again later
+ *      EIO:	A permanent error occurred, do not retry
+ *
  * The RDMA allocate/free functions need the task structure as a place
  * to hide the struct rpcrdma_req, which is necessary for the actual send/recv
  * sequence.
@@ -486,11 +494,12 @@ xprt_rdma_connect(struct rpc_xprt *xprt, struct rpc_task *task)
  * (rq_send_buf and rq_rcv_buf are both part of a single contiguous buffer).
  * We may register rq_rcv_buf when using reply chunks.
  */
-static void *
-xprt_rdma_allocate(struct rpc_task *task, size_t size)
+static int
+xprt_rdma_allocate(struct rpc_task *task)
 {
-	struct rpc_xprt *xprt = task->tk_rqstp->rq_xprt;
-	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
+	struct rpc_rqst *rqst = task->tk_rqstp;
+	size_t size = rqst->rq_callsize + rqst->rq_rcvsize;
+	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(rqst->rq_xprt);
 	struct rpcrdma_regbuf *rb;
 	struct rpcrdma_req *req;
 	size_t min_size;
@@ -498,7 +507,7 @@ xprt_rdma_allocate(struct rpc_task *task, size_t size)
 
 	req = rpcrdma_buffer_get(&r_xprt->rx_buf);
 	if (req == NULL)
-		return NULL;
+		return -ENOMEM;
 
 	flags = RPCRDMA_DEF_GFP;
 	if (RPC_IS_SWAPPER(task))
@@ -515,7 +524,8 @@ out:
 	dprintk("RPC:       %s: size %zd, request 0x%p\n", __func__, size, req);
 	req->rl_connect_cookie = 0;	/* our reserved value */
 	req->rl_task = task;
-	return req->rl_sendbuf->rg_base;
+	rqst->rq_buffer = req->rl_sendbuf->rg_base;
+	return 0;
 
 out_rdmabuf:
 	min_size = r_xprt->rx_data.inline_wsize;
@@ -558,7 +568,7 @@ out_sendbuf:
 
 out_fail:
 	rpcrdma_buffer_put(req);
-	return NULL;
+	return -ENOMEM;
 }
 
 /*