Commit 467c9674 authored by Chuck Lever's avatar Chuck Lever Committed by Anna Schumaker
Browse files

xprtrdma: unmap all FMRs during transport disconnect 



When using RPCRDMA_MTHCAFMR memory registration, after a few
transport disconnect / reconnect cycles, ib_map_phys_fmr() starts to
return EINVAL because the provider has exhausted its map pool.

Make sure that all FMRs are unmapped during transport disconnect,
and that ->send_request remarshals them during an RPC retransmit.
This resets the transport's MRs to ensure that none are leaked
during a disconnect.

Signed-off-by: default avatarChuck Lever <chuck.lever@oracle.com>
Signed-off-by: default avatarAnna Schumaker <Anna.Schumaker@Netapp.com>
parent e7104a2a

net/sunrpc/xprtrdma/transport.c

+1 −1
Original line number Diff line number Diff line
@@ -599,7 +599,7 @@ xprt_rdma_send_request(struct rpc_task *task) 


	if (req->rl_niovs == 0)

		rc = rpcrdma_marshal_req(rqst);

	else if (r_xprt->rx_ia.ri_memreg_strategy == RPCRDMA_FRMR)

	else if (r_xprt->rx_ia.ri_memreg_strategy != RPCRDMA_ALLPHYSICAL)

		rc = rpcrdma_marshal_chunks(rqst, 0);

	if (rc < 0)

		goto failed_marshal;

net/sunrpc/xprtrdma/verbs.c

+41 −1
Original line number Diff line number Diff line
@@ -62,6 +62,7 @@ 
#endif



static void rpcrdma_reset_frmrs(struct rpcrdma_ia *);

static void rpcrdma_reset_fmrs(struct rpcrdma_ia *);



/*

 * internal functions
@@ -868,8 +869,19 @@ retry: 
		rpcrdma_ep_disconnect(ep, ia);

		rpcrdma_flush_cqs(ep);



		if (ia->ri_memreg_strategy == RPCRDMA_FRMR)

		switch (ia->ri_memreg_strategy) {

		case RPCRDMA_FRMR:

			rpcrdma_reset_frmrs(ia);

			break;

		case RPCRDMA_MTHCAFMR:

			rpcrdma_reset_fmrs(ia);

			break;

		case RPCRDMA_ALLPHYSICAL:

			break;

		default:

			rc = -EIO;

			goto out;

		}



		xprt = container_of(ia, struct rpcrdma_xprt, rx_ia);

		id = rpcrdma_create_id(xprt, ia,
@@ -1289,6 +1301,34 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf) 
	kfree(buf->rb_pool);

}



/* After a disconnect, unmap all FMRs.

 *

 * This is invoked only in the transport connect worker in order

 * to serialize with rpcrdma_register_fmr_external().

 */

static void

rpcrdma_reset_fmrs(struct rpcrdma_ia *ia)

{

	struct rpcrdma_xprt *r_xprt =

				container_of(ia, struct rpcrdma_xprt, rx_ia);

	struct rpcrdma_buffer *buf = &r_xprt->rx_buf;

	struct list_head *pos;

	struct rpcrdma_mw *r;

	LIST_HEAD(l);

	int rc;



	list_for_each(pos, &buf->rb_all) {

		r = list_entry(pos, struct rpcrdma_mw, mw_all);



		INIT_LIST_HEAD(&l);

		list_add(&r->r.fmr->list, &l);

		rc = ib_unmap_fmr(&l);

		if (rc)

			dprintk("RPC:       %s: ib_unmap_fmr failed %i\n",

				__func__, rc);

	}

}



/* After a disconnect, a flushed FAST_REG_MR can leave an FRMR in

 * an unusable state. Find FRMRs in this state and dereg / reg

 * each.  FRMRs that are VALID and attached to an rpcrdma_req are

CRA Git | Maintained and supported by SUSTech CRA and CCSE