This is a note to let you know that I've just added the patch titled xprtrdma: Per-connection pad optimization to the 4.10-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: xprtrdma-per-connection-pad-optimization.patch and it can be found in the queue-4.10 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. >From b5f0afbea4f2ea52c613ac2b06cb6de2ea18cb6d Mon Sep 17 00:00:00 2001 From: Chuck Lever <chuck.lever@xxxxxxxxxx> Date: Wed, 8 Feb 2017 16:59:54 -0500 Subject: xprtrdma: Per-connection pad optimization From: Chuck Lever <chuck.lever@xxxxxxxxxx> commit b5f0afbea4f2ea52c613ac2b06cb6de2ea18cb6d upstream. Pad optimization is changed by echoing into /proc/sys/sunrpc/rdma_pad_optimize. This is a global setting, affecting all RPC-over-RDMA connections to all servers. The marshaling code picks up that value and uses it for decisions about how to construct each RPC-over-RDMA frame. Having it change suddenly in mid-operation can result in unexpected failures. And some servers a client mounts might need chunk round-up, while others don't. So instead, copy the pad_optimize setting into each connection's rpcrdma_ia when the transport is created, and use the copy, which can't change during the life of the connection, instead. This also removes a hack: rpcrdma_convert_iovs was using the remote-invalidation-expected flag to predict when it could leave out Write chunk padding. This is because the Linux server handles implicit XDR padding on Write chunks correctly, and only Linux servers can set the connection's remote-invalidation-expected flag. It's more sensible to use the pad optimization setting instead. Fixes: 677eb17e94ed ("xprtrdma: Fix XDR tail buffer marshalling") Signed-off-by: Chuck Lever <chuck.lever@xxxxxxxxxx> Signed-off-by: Anna Schumaker <Anna.Schumaker@xxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- net/sunrpc/xprtrdma/rpc_rdma.c | 28 ++++++++++++++-------------- net/sunrpc/xprtrdma/verbs.c | 1 + net/sunrpc/xprtrdma/xprt_rdma.h | 1 + 3 files changed, 16 insertions(+), 14 deletions(-) --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -186,9 +186,9 @@ rpcrdma_convert_kvec(struct kvec *vec, s */ static int -rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos, - enum rpcrdma_chunktype type, struct rpcrdma_mr_seg *seg, - bool reminv_expected) +rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf, + unsigned int pos, enum rpcrdma_chunktype type, + struct rpcrdma_mr_seg *seg) { int len, n, p, page_base; struct page **ppages; @@ -229,14 +229,15 @@ rpcrdma_convert_iovs(struct xdr_buf *xdr /* When encoding a Read chunk, the tail iovec contains an * XDR pad and may be omitted. */ - if (type == rpcrdma_readch && xprt_rdma_pad_optimize) + if (type == rpcrdma_readch && r_xprt->rx_ia.ri_implicit_roundup) return n; - /* When encoding the Write list, some servers need to see an extra - * segment for odd-length Write chunks. The upper layer provides - * space in the tail iovec for this purpose. + /* When encoding a Write chunk, some servers need to see an + * extra segment for non-XDR-aligned Write chunks. The upper + * layer provides space in the tail iovec that may be used + * for this purpose. */ - if (type == rpcrdma_writech && reminv_expected) + if (type == rpcrdma_writech && r_xprt->rx_ia.ri_implicit_roundup) return n; if (xdrbuf->tail[0].iov_len) { @@ -291,7 +292,8 @@ rpcrdma_encode_read_list(struct rpcrdma_ if (rtype == rpcrdma_areadch) pos = 0; seg = req->rl_segments; - nsegs = rpcrdma_convert_iovs(&rqst->rq_snd_buf, pos, rtype, seg, false); + nsegs = rpcrdma_convert_iovs(r_xprt, &rqst->rq_snd_buf, pos, + rtype, seg); if (nsegs < 0) return ERR_PTR(nsegs); @@ -353,10 +355,9 @@ rpcrdma_encode_write_list(struct rpcrdma } seg = req->rl_segments; - nsegs = rpcrdma_convert_iovs(&rqst->rq_rcv_buf, + nsegs = rpcrdma_convert_iovs(r_xprt, &rqst->rq_rcv_buf, rqst->rq_rcv_buf.head[0].iov_len, - wtype, seg, - r_xprt->rx_ia.ri_reminv_expected); + wtype, seg); if (nsegs < 0) return ERR_PTR(nsegs); @@ -421,8 +422,7 @@ rpcrdma_encode_reply_chunk(struct rpcrdm } seg = req->rl_segments; - nsegs = rpcrdma_convert_iovs(&rqst->rq_rcv_buf, 0, wtype, seg, - r_xprt->rx_ia.ri_reminv_expected); + nsegs = rpcrdma_convert_iovs(r_xprt, &rqst->rq_rcv_buf, 0, wtype, seg); if (nsegs < 0) return ERR_PTR(nsegs); --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -208,6 +208,7 @@ rpcrdma_update_connect_private(struct rp /* Default settings for RPC-over-RDMA Version One */ r_xprt->rx_ia.ri_reminv_expected = false; + r_xprt->rx_ia.ri_implicit_roundup = xprt_rdma_pad_optimize; rsize = RPCRDMA_V1_DEF_INLINE_SIZE; wsize = RPCRDMA_V1_DEF_INLINE_SIZE; --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -75,6 +75,7 @@ struct rpcrdma_ia { unsigned int ri_max_inline_write; unsigned int ri_max_inline_read; bool ri_reminv_expected; + bool ri_implicit_roundup; enum ib_mr_type ri_mrtype; struct ib_qp_attr ri_qp_attr; struct ib_qp_init_attr ri_qp_init_attr; Patches currently in stable-queue which might be from chuck.lever@xxxxxxxxxx are queue-4.10/xprtrdma-disable-pad-optimization-by-default.patch queue-4.10/xprtrdma-fix-read-chunk-padding.patch queue-4.10/xprtrdma-reduce-required-number-of-send-sges.patch queue-4.10/nfsd-special-case-truncates-some-more.patch queue-4.10/xprtrdma-per-connection-pad-optimization.patch