When the client uses physical memory registration, each page in the payload gets its own array entry in the RPC/RDMA header's chunk list. Therefore, don't advertise a maximum payload size that would require more array entries than can fit in the RPC buffer where RPC/RDMA headers are built. BugLink: https://bugzilla.linux-nfs.org/show_bug.cgi?id=248 Signed-off-by: Chuck Lever <chuck.lever@xxxxxxxxxx> Tested-by: Steve Wise <swise@xxxxxxxxxxxxxxxxxxxxx> Tested-by: Shirley Ma <shirley.ma@xxxxxxxxxx> Tested-by: Devesh Sharma <devesh.sharma@xxxxxxxxxx> --- net/sunrpc/xprtrdma/transport.c | 4 +++- net/sunrpc/xprtrdma/verbs.c | 41 +++++++++++++++++++++++++++++++++++++++ net/sunrpc/xprtrdma/xprt_rdma.h | 1 + 3 files changed, 45 insertions(+), 1 deletion(-) diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 66f91f0..4185102 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -296,7 +296,6 @@ xprt_setup_rdma(struct xprt_create *args) xprt->resvport = 0; /* privileged port not needed */ xprt->tsh_size = 0; /* RPC-RDMA handles framing */ - xprt->max_payload = RPCRDMA_MAX_DATA_SEGS * PAGE_SIZE; xprt->ops = &xprt_rdma_procs; /* @@ -382,6 +381,9 @@ xprt_setup_rdma(struct xprt_create *args) new_ep->rep_xprt = xprt; xprt_rdma_format_addresses(xprt); + xprt->max_payload = rpcrdma_max_payload(new_xprt); + dprintk("RPC: %s: transport data payload maximum: %zu bytes\n", + __func__, xprt->max_payload); if (!try_module_get(THIS_MODULE)) goto out4; diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index cab742d..0d5187d 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1822,3 +1822,44 @@ rpcrdma_ep_post_recv(struct rpcrdma_ia *ia, rc); return rc; } + +/* Physical mapping means one Read/Write list entry per-page. + * All list entries must fit within an inline buffer + * + * NB: The server must return a Write list for NFS READ, + * which has the same constraint. Factor in the inline + * rsize as well. + */ +static size_t +rpcrdma_physical_max_payload(struct rpcrdma_xprt *r_xprt) +{ + struct rpcrdma_create_data_internal *cdata = &r_xprt->rx_data; + unsigned int inline_size, pages; + + inline_size = min_t(unsigned int, + cdata->inline_wsize, cdata->inline_rsize); + inline_size -= RPCRDMA_HDRLEN_MIN; + pages = inline_size / sizeof(struct rpcrdma_segment); + return pages << PAGE_SHIFT; +} + +static size_t +rpcrdma_mr_max_payload(struct rpcrdma_xprt *r_xprt) +{ + return RPCRDMA_MAX_DATA_SEGS << PAGE_SHIFT; +} + +size_t +rpcrdma_max_payload(struct rpcrdma_xprt *r_xprt) +{ + size_t result; + + switch (r_xprt->rx_ia.ri_memreg_strategy) { + case RPCRDMA_ALLPHYSICAL: + result = rpcrdma_physical_max_payload(r_xprt); + break; + default: + result = rpcrdma_mr_max_payload(r_xprt); + } + return result; +} diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 97ca516..f3d86b2 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -348,6 +348,7 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *); * RPC/RDMA protocol calls - xprtrdma/rpc_rdma.c */ int rpcrdma_marshal_req(struct rpc_rqst *); +size_t rpcrdma_max_payload(struct rpcrdma_xprt *); /* Temporary NFS request map cache. Created in svc_rdma.c */ extern struct kmem_cache *svc_rdma_map_cachep; -- To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
