From fedbb6b4ff341c1e2120f4ffbf367fd78ac3e8f3 Mon Sep 17 00:00:00 2001 From: Shmulik Ladkani Date: Wed, 29 Jun 2016 21:47:03 +0300 Subject: ipv4: Fix ip_skb_dst_mtu to use the sk passed by ip_finish_output ip_skb_dst_mtu uses skb->sk, assuming it is an AF_INET socket (e.g. it calls ip_sk_use_pmtu which casts sk as an inet_sk). However, in the case of UDP tunneling, the skb->sk is not necessarily an inet socket (could be AF_PACKET socket, or AF_UNSPEC if arriving from tun/tap). OTOH, the sk passed as an argument throughout IP stack's output path is the one which is of PMTU interest: - In case of local sockets, sk is same as skb->sk; - In case of a udp tunnel, sk is the tunneling socket. Fix, by passing ip_finish_output's sk to ip_skb_dst_mtu. This augments 7026b1ddb6 'netfilter: Pass socket pointer down through okfn().' Signed-off-by: Shmulik Ladkani Reviewed-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/bridge/br_netfilter_hooks.c | 2 +- net/ipv4/ip_output.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 2d25979..77e7f69 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -700,7 +700,7 @@ static int br_nf_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)) { - unsigned int mtu = ip_skb_dst_mtu(skb); + unsigned int mtu = ip_skb_dst_mtu(sk, skb); struct iphdr *iph = ip_hdr(skb); if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) || diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 124bf0a..4bd4921 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -271,7 +271,7 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk return dst_output(net, sk, skb); } #endif - mtu = ip_skb_dst_mtu(skb); + mtu = ip_skb_dst_mtu(sk, skb); if (skb_is_gso(skb)) return ip_finish_output_gso(net, sk, skb, mtu); @@ -541,7 +541,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, iph = ip_hdr(skb); - mtu = ip_skb_dst_mtu(skb); + mtu = ip_skb_dst_mtu(sk, skb); if (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size < mtu) mtu = IPCB(skb)->frag_max_size; -- cgit v1.1 From eb70db8756717b90c01ccc765fdefc4dd969fc74 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 1 Jul 2016 16:07:50 -0400 Subject: packet: Use symmetric hash for PACKET_FANOUT_HASH. People who use PACKET_FANOUT_HASH want a symmetric hash, meaning that they want packets going in both directions on a flow to hash to the same bucket. The core kernel SKB hash became non-symmetric when the ipv6 flow label and other entities were incorporated into the standard flow hash order to increase entropy. But there are no users of PACKET_FANOUT_HASH who want an assymetric hash, they all want a symmetric one. Therefore, use the flow dissector to compute a flat symmetric hash over only the protocol, addresses and ports. This hash does not get installed into and override the normal skb hash, so this change has no effect whatsoever on the rest of the stack. Reported-by: Eric Leblond Tested-by: Eric Leblond Signed-off-by: David S. Miller --- net/core/flow_dissector.c | 43 +++++++++++++++++++++++++++++++++++++++++++ net/packet/af_packet.c | 2 +- 2 files changed, 44 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index a669dea..61ad43f 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -651,6 +651,23 @@ void make_flow_keys_digest(struct flow_keys_digest *digest, } EXPORT_SYMBOL(make_flow_keys_digest); +static struct flow_dissector flow_keys_dissector_symmetric __read_mostly; + +u32 __skb_get_hash_symmetric(struct sk_buff *skb) +{ + struct flow_keys keys; + + __flow_hash_secret_init(); + + memset(&keys, 0, sizeof(keys)); + __skb_flow_dissect(skb, &flow_keys_dissector_symmetric, &keys, + NULL, 0, 0, 0, + FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); + + return __flow_hash_from_keys(&keys, hashrnd); +} +EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric); + /** * __skb_get_hash: calculate a flow hash * @skb: sk_buff to calculate flow hash from @@ -868,6 +885,29 @@ static const struct flow_dissector_key flow_keys_dissector_keys[] = { }, }; +static const struct flow_dissector_key flow_keys_dissector_symmetric_keys[] = { + { + .key_id = FLOW_DISSECTOR_KEY_CONTROL, + .offset = offsetof(struct flow_keys, control), + }, + { + .key_id = FLOW_DISSECTOR_KEY_BASIC, + .offset = offsetof(struct flow_keys, basic), + }, + { + .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, + .offset = offsetof(struct flow_keys, addrs.v4addrs), + }, + { + .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS, + .offset = offsetof(struct flow_keys, addrs.v6addrs), + }, + { + .key_id = FLOW_DISSECTOR_KEY_PORTS, + .offset = offsetof(struct flow_keys, ports), + }, +}; + static const struct flow_dissector_key flow_keys_buf_dissector_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, @@ -889,6 +929,9 @@ static int __init init_default_flow_dissectors(void) skb_flow_dissector_init(&flow_keys_dissector, flow_keys_dissector_keys, ARRAY_SIZE(flow_keys_dissector_keys)); + skb_flow_dissector_init(&flow_keys_dissector_symmetric, + flow_keys_dissector_symmetric_keys, + ARRAY_SIZE(flow_keys_dissector_symmetric_keys)); skb_flow_dissector_init(&flow_keys_buf_dissector, flow_keys_buf_dissector_keys, ARRAY_SIZE(flow_keys_buf_dissector_keys)); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 9bff6ef..9f0983f 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1341,7 +1341,7 @@ static unsigned int fanout_demux_hash(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { - return reciprocal_scale(skb_get_hash(skb), num); + return reciprocal_scale(__skb_get_hash_symmetric(skb), num); } static unsigned int fanout_demux_lb(struct packet_fanout *f, -- cgit v1.1 From 82a31b9231f02d9c1b7b290a46999d517b0d312a Mon Sep 17 00:00:00 2001 From: WANG Cong Date: Thu, 30 Jun 2016 10:15:22 -0700 Subject: net_sched: fix mirrored packets checksum Similar to commit 9b368814b336 ("net: fix bridge multicast packet checksum validation") we need to fixup the checksum for CHECKSUM_COMPLETE when pushing skb on RX path. Otherwise we get similar splats. Cc: Jamal Hadi Salim Cc: Tom Herbert Signed-off-by: Cong Wang Acked-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- net/core/skbuff.c | 18 ------------------ net/sched/act_mirred.c | 2 +- 2 files changed, 1 insertion(+), 19 deletions(-) (limited to 'net') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index f2b77e5..eb12d21 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3016,24 +3016,6 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page, EXPORT_SYMBOL_GPL(skb_append_pagefrags); /** - * skb_push_rcsum - push skb and update receive checksum - * @skb: buffer to update - * @len: length of data pulled - * - * This function performs an skb_push on the packet and updates - * the CHECKSUM_COMPLETE checksum. It should be used on - * receive path processing instead of skb_push unless you know - * that the checksum difference is zero (e.g., a valid IP header) - * or you are setting ip_summed to CHECKSUM_NONE. - */ -static unsigned char *skb_push_rcsum(struct sk_buff *skb, unsigned len) -{ - skb_push(skb, len); - skb_postpush_rcsum(skb, skb->data, len); - return skb->data; -} - -/** * skb_pull_rcsum - pull skb and update receive checksum * @skb: buffer to update * @len: length of data pulled diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 128942b..1f5bd6c 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -181,7 +181,7 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, if (!(at & AT_EGRESS)) { if (m->tcfm_ok_push) - skb_push(skb2, skb->mac_len); + skb_push_rcsum(skb2, skb->mac_len); } /* mirror is always swallowed */ -- cgit v1.1 From 55e77a3e8297581c919b45adcc4d0815b69afa84 Mon Sep 17 00:00:00 2001 From: Richard Alpe Date: Fri, 1 Jul 2016 11:11:21 +0200 Subject: tipc: fix nl compat regression for link statistics Fix incorrect use of nla_strlcpy() where the first NLA_HDRLEN bytes of the link name where left out. Making the output of tipc-config -ls look something like: Link statistics: dcast-link 1:data0-1.1.2:data0 1:data0-1.1.3:data0 Also, for the record, the patch that introduce this regression claims "Sending the whole object out can cause a leak". Which isn't very likely as this is a compat layer, where the data we are parsing is generated by us and we know the string to be NULL terminated. But you can of course never be to secure. Fixes: 5d2be1422e02 (tipc: fix an infoleak in tipc_nl_compat_link_dump) Signed-off-by: Richard Alpe Signed-off-by: David S. Miller --- net/tipc/netlink_compat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 3ad9fab..1fd4647 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -604,7 +604,7 @@ static int tipc_nl_compat_link_dump(struct tipc_nl_compat_msg *msg, link_info.dest = nla_get_flag(link[TIPC_NLA_LINK_DEST]); link_info.up = htonl(nla_get_flag(link[TIPC_NLA_LINK_UP])); - nla_strlcpy(link_info.str, nla_data(link[TIPC_NLA_LINK_NAME]), + nla_strlcpy(link_info.str, link[TIPC_NLA_LINK_NAME], TIPC_MAX_LINK_NAME); return tipc_add_tlv(msg->rep, TIPC_TLV_LINK_INFO, -- cgit v1.1 From 3dad5424adfb346c871847d467f97dcdca64ea97 Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Sun, 3 Jul 2016 10:54:54 +0200 Subject: RDS: fix rds_tcp_init() error path If register_pernet_subsys() fails, we shouldn't try to call unregister_pernet_subsys(). Fixes: 467fa15356 ("RDS-TCP: Support multiple RDS-TCP listen endpoints, one per netns.") Cc: stable@vger.kernel.org Cc: Sowmini Varadhan Cc: David S. Miller Signed-off-by: Vegard Nossum Acked-by: Sowmini Varadhan Acked-by: Santosh Shilimkar Signed-off-by: David S. Miller --- net/rds/tcp.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 74ee126..c8a7b4c 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -616,7 +616,7 @@ static int rds_tcp_init(void) ret = rds_tcp_recv_init(); if (ret) - goto out_slab; + goto out_pernet; ret = rds_trans_register(&rds_tcp_transport); if (ret) @@ -628,8 +628,9 @@ static int rds_tcp_init(void) out_recv: rds_tcp_recv_exit(); -out_slab: +out_pernet: unregister_pernet_subsys(&rds_tcp_net_ops); +out_slab: kmem_cache_destroy(rds_tcp_conn_slab); out: return ret; -- cgit v1.1 From ab58298cf459fcd4f588a401d36abf0bd2215b51 Mon Sep 17 00:00:00 2001 From: Vegard Nossum Date: Tue, 5 Jul 2016 21:12:53 +0200 Subject: net: fix decnet rtnexthop parsing dn_fib_count_nhs() could enter an infinite loop if nhp->rtnh_len == 0 (i.e. if userspace passes a malformed netlink message). Let's use the helpers from net/nexthop.h which take care of all this stuff. We can do exactly the same as e.g. fib_count_nexthops() and fib_get_nhs() from net/ipv4/fib_semantics.c. This fixes the softlockup for me. Cc: Thomas Graf Signed-off-by: Vegard Nossum Signed-off-by: David S. Miller --- net/decnet/dn_fib.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) (limited to 'net') diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index df48034..a796fc7 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -41,6 +41,7 @@ #include #include #include +#include #define RT_MIN_TABLE 1 @@ -150,14 +151,13 @@ static int dn_fib_count_nhs(const struct nlattr *attr) struct rtnexthop *nhp = nla_data(attr); int nhs = 0, nhlen = nla_len(attr); - while(nhlen >= (int)sizeof(struct rtnexthop)) { - if ((nhlen -= nhp->rtnh_len) < 0) - return 0; + while (rtnh_ok(nhp, nhlen)) { nhs++; - nhp = RTNH_NEXT(nhp); + nhp = rtnh_next(nhp, &nhlen); } - return nhs; + /* leftover implies invalid nexthop configuration, discard it */ + return nhlen > 0 ? 0 : nhs; } static int dn_fib_get_nhs(struct dn_fib_info *fi, const struct nlattr *attr, @@ -167,21 +167,24 @@ static int dn_fib_get_nhs(struct dn_fib_info *fi, const struct nlattr *attr, int nhlen = nla_len(attr); change_nexthops(fi) { - int attrlen = nhlen - sizeof(struct rtnexthop); - if (attrlen < 0 || (nhlen -= nhp->rtnh_len) < 0) + int attrlen; + + if (!rtnh_ok(nhp, nhlen)) return -EINVAL; nh->nh_flags = (r->rtm_flags&~0xFF) | nhp->rtnh_flags; nh->nh_oif = nhp->rtnh_ifindex; nh->nh_weight = nhp->rtnh_hops + 1; - if (attrlen) { + attrlen = rtnh_attrlen(nhp); + if (attrlen > 0) { struct nlattr *gw_attr; gw_attr = nla_find((struct nlattr *) (nhp + 1), attrlen, RTA_GATEWAY); nh->nh_gw = gw_attr ? nla_get_le16(gw_attr) : 0; } - nhp = RTNH_NEXT(nhp); + + nhp = rtnh_next(nhp, &nhlen); } endfor_nexthops(fi); return 0; -- cgit v1.1 From 903ce4abdf374e3365d93bcb3df56c62008835ba Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Tue, 5 Jul 2016 12:10:23 -0700 Subject: ipv6: Fix mem leak in rt6i_pcpu It was first reported and reproduced by Petr (thanks!) in https://bugzilla.kernel.org/show_bug.cgi?id=119581 free_percpu(rt->rt6i_pcpu) used to always happen in ip6_dst_destroy(). However, after fixing a deadlock bug in commit 9c7370a166b4 ("ipv6: Fix a potential deadlock when creating pcpu rt"), free_percpu() is not called before setting non_pcpu_rt->rt6i_pcpu to NULL. It is worth to note that rt6i_pcpu is protected by table->tb6_lock. kmemleak somehow did not report it. We nailed it down by observing the pcpu entries in /proc/vmallocinfo (first suggested by Hannes, thanks!). Signed-off-by: Martin KaFai Lau Fixes: 9c7370a166b4 ("ipv6: Fix a potential deadlock when creating pcpu rt") Reported-by: Petr Novopashenniy Tested-by: Petr Novopashenniy Acked-by: Hannes Frederic Sowa Cc: Hannes Frederic Sowa Cc: Petr Novopashenniy Signed-off-by: David S. Miller --- net/ipv6/ip6_fib.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 1bcef23..771be1f 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -177,6 +177,7 @@ static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) } } + free_percpu(non_pcpu_rt->rt6i_pcpu); non_pcpu_rt->rt6i_pcpu = NULL; } -- cgit v1.1 From 38f1932e60ba249660bbae585f61ef2dee3313a4 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:52:12 -0400 Subject: xprtrdma: Remove FMRs from the unmap list after unmapping ib_unmap_fmr() takes a list of FMRs to unmap. However, it does not remove the FMRs from this list as it processes them. Other ib_unmap_fmr() call sites are careful to remove FMRs from the list after ib_unmap_fmr() returns. Since commit 7c7a5390dc6c8 ("xprtrdma: Add ro_unmap_sync method for FMR") fmr_op_unmap_sync passes more than one FMR to ib_unmap_fmr(), but it didn't bother to remove the FMRs from that list once the call was complete. I've noticed some instability that could be related to list tangling by the new fmr_op_unmap_sync() logic. In an abundance of caution, add some defensive logic to clean up properly after ib_unmap_fmr(). Fixes: 7c7a5390dc6c8 ("xprtrdma: Add ro_unmap_sync method for FMR") Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/fmr_ops.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index 6326ebe..c748ff6 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -63,9 +63,12 @@ static int __fmr_unmap(struct rpcrdma_mw *mw) { LIST_HEAD(l); + int rc; list_add(&mw->fmr.fmr->list, &l); - return ib_unmap_fmr(&l); + rc = ib_unmap_fmr(&l); + list_del_init(&mw->fmr.fmr->list); + return rc; } /* Deferred reset of a single FMR. Generate a fresh rkey by @@ -267,7 +270,7 @@ fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) seg = &req->rl_segments[i]; mw = seg->rl_mw; - list_add(&mw->fmr.fmr->list, &unmap_list); + list_add_tail(&mw->fmr.fmr->list, &unmap_list); i += seg->mr_nsegs; } @@ -280,7 +283,9 @@ fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) */ for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) { seg = &req->rl_segments[i]; + mw = seg->rl_mw; + list_del_init(&mw->fmr.fmr->list); __fmr_dma_unmap(r_xprt, seg); rpcrdma_put_mw(r_xprt, seg->rl_mw); -- cgit v1.1 From 564471d2f2f1ddaf02119b8759813666db93abba Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:52:21 -0400 Subject: xprtrdma: Create common scatterlist fields in rpcrdma_mw Clean up: FMR is about to replace the rpcrdma_map_one code with scatterlists. Move the scatterlist fields out of the FRWR-specific union and into the generic part of rpcrdma_mw. One minor change: -EIO is now returned if FRWR registration fails. The RPC is terminated immediately, since the problem is likely due to a software bug, thus retrying likely won't help. Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/frwr_ops.c | 85 ++++++++++++++++++++--------------------- net/sunrpc/xprtrdma/xprt_rdma.h | 8 ++-- 2 files changed, 46 insertions(+), 47 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index c094754..f02ab80 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -125,17 +125,16 @@ __frwr_reset_mr(struct rpcrdma_ia *ia, struct rpcrdma_mw *r) } static void -__frwr_reset_and_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mw *mw) +__frwr_reset_and_unmap(struct rpcrdma_mw *mw) { + struct rpcrdma_xprt *r_xprt = mw->mw_xprt; struct rpcrdma_ia *ia = &r_xprt->rx_ia; - struct rpcrdma_frmr *f = &mw->frmr; int rc; rc = __frwr_reset_mr(ia, mw); - ib_dma_unmap_sg(ia->ri_device, f->fr_sg, f->fr_nents, f->fr_dir); + ib_dma_unmap_sg(ia->ri_device, mw->mw_sg, mw->mw_nents, mw->mw_dir); if (rc) return; - rpcrdma_put_mw(r_xprt, mw); } @@ -152,8 +151,7 @@ __frwr_recovery_worker(struct work_struct *work) struct rpcrdma_mw *r = container_of(work, struct rpcrdma_mw, mw_work); - __frwr_reset_and_unmap(r->mw_xprt, r); - return; + __frwr_reset_and_unmap(r); } /* A broken MR was discovered in a context that can't sleep. @@ -167,8 +165,7 @@ __frwr_queue_recovery(struct rpcrdma_mw *r) } static int -__frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, struct ib_device *device, - unsigned int depth) +__frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, unsigned int depth) { struct rpcrdma_frmr *f = &r->frmr; int rc; @@ -177,11 +174,11 @@ __frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, struct ib_device *device, if (IS_ERR(f->fr_mr)) goto out_mr_err; - f->fr_sg = kcalloc(depth, sizeof(*f->fr_sg), GFP_KERNEL); - if (!f->fr_sg) + r->mw_sg = kcalloc(depth, sizeof(*r->mw_sg), GFP_KERNEL); + if (!r->mw_sg) goto out_list_err; - sg_init_table(f->fr_sg, depth); + sg_init_table(r->mw_sg, depth); init_completion(&f->fr_linv_done); @@ -210,7 +207,7 @@ __frwr_release(struct rpcrdma_mw *r) if (rc) dprintk("RPC: %s: ib_dereg_mr status %i\n", __func__, rc); - kfree(r->frmr.fr_sg); + kfree(r->mw_sg); } static int @@ -350,7 +347,6 @@ static int frwr_op_init(struct rpcrdma_xprt *r_xprt) { struct rpcrdma_buffer *buf = &r_xprt->rx_buf; - struct ib_device *device = r_xprt->rx_ia.ri_device; unsigned int depth = r_xprt->rx_ia.ri_max_frmr_depth; struct ib_pd *pd = r_xprt->rx_ia.ri_pd; int i; @@ -372,7 +368,7 @@ frwr_op_init(struct rpcrdma_xprt *r_xprt) if (!r) return -ENOMEM; - rc = __frwr_init(r, pd, device, depth); + rc = __frwr_init(r, pd, depth); if (rc) { kfree(r); return rc; @@ -386,7 +382,7 @@ frwr_op_init(struct rpcrdma_xprt *r_xprt) return 0; } -/* Post a FAST_REG Work Request to register a memory region +/* Post a REG_MR Work Request to register a memory region * for remote access via RDMA READ or RDMA WRITE. */ static int @@ -394,8 +390,6 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, int nsegs, bool writing) { struct rpcrdma_ia *ia = &r_xprt->rx_ia; - struct ib_device *device = ia->ri_device; - enum dma_data_direction direction = rpcrdma_data_dir(writing); struct rpcrdma_mr_seg *seg1 = seg; struct rpcrdma_mw *mw; struct rpcrdma_frmr *frmr; @@ -421,15 +415,14 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, if (nsegs > ia->ri_max_frmr_depth) nsegs = ia->ri_max_frmr_depth; - for (i = 0; i < nsegs;) { if (seg->mr_page) - sg_set_page(&frmr->fr_sg[i], + sg_set_page(&mw->mw_sg[i], seg->mr_page, seg->mr_len, offset_in_page(seg->mr_offset)); else - sg_set_buf(&frmr->fr_sg[i], seg->mr_offset, + sg_set_buf(&mw->mw_sg[i], seg->mr_offset, seg->mr_len); ++seg; @@ -440,26 +433,20 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len)) break; } - frmr->fr_nents = i; - frmr->fr_dir = direction; - - dma_nents = ib_dma_map_sg(device, frmr->fr_sg, frmr->fr_nents, direction); - if (!dma_nents) { - pr_err("RPC: %s: failed to dma map sg %p sg_nents %u\n", - __func__, frmr->fr_sg, frmr->fr_nents); - return -ENOMEM; - } + mw->mw_nents = i; + mw->mw_dir = rpcrdma_data_dir(writing); - n = ib_map_mr_sg(mr, frmr->fr_sg, frmr->fr_nents, NULL, PAGE_SIZE); - if (unlikely(n != frmr->fr_nents)) { - pr_err("RPC: %s: failed to map mr %p (%u/%u)\n", - __func__, frmr->fr_mr, n, frmr->fr_nents); - rc = n < 0 ? n : -EINVAL; - goto out_senderr; - } + dma_nents = ib_dma_map_sg(ia->ri_device, + mw->mw_sg, mw->mw_nents, mw->mw_dir); + if (!dma_nents) + goto out_dmamap_err; + + n = ib_map_mr_sg(mr, mw->mw_sg, mw->mw_nents, NULL, PAGE_SIZE); + if (unlikely(n != mw->mw_nents)) + goto out_mapmr_err; dprintk("RPC: %s: Using frmr %p to map %u segments (%u bytes)\n", - __func__, mw, frmr->fr_nents, mr->length); + __func__, mw, mw->mw_nents, mr->length); key = (u8)(mr->rkey & 0x000000FF); ib_update_fast_reg_key(mr, ++key); @@ -484,13 +471,25 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, seg1->rl_mw = mw; seg1->mr_rkey = mr->rkey; seg1->mr_base = mr->iova; - seg1->mr_nsegs = frmr->fr_nents; + seg1->mr_nsegs = mw->mw_nents; seg1->mr_len = mr->length; - return frmr->fr_nents; + return mw->mw_nents; + +out_dmamap_err: + pr_err("rpcrdma: failed to dma map sg %p sg_nents %u\n", + mw->mw_sg, mw->mw_nents); + return -ENOMEM; + +out_mapmr_err: + pr_err("rpcrdma: failed to map mr %p (%u/%u)\n", + frmr->fr_mr, n, mw->mw_nents); + rc = n < 0 ? n : -EIO; + __frwr_queue_recovery(mw); + return rc; out_senderr: - dprintk("RPC: %s: ib_post_send status %i\n", __func__, rc); + pr_err("rpcrdma: ib_post_send status %i\n", rc); __frwr_queue_recovery(mw); return rc; } @@ -582,8 +581,8 @@ unmap: mw = seg->rl_mw; seg->rl_mw = NULL; - ib_dma_unmap_sg(ia->ri_device, f->fr_sg, f->fr_nents, - f->fr_dir); + ib_dma_unmap_sg(ia->ri_device, + mw->mw_sg, mw->mw_nents, mw->mw_dir); rpcrdma_put_mw(r_xprt, mw); i += seg->mr_nsegs; @@ -630,7 +629,7 @@ frwr_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, mw = seg->rl_mw; if (sync) - __frwr_reset_and_unmap(r_xprt, mw); + __frwr_reset_and_unmap(mw); else __frwr_queue_recovery(mw); diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 95cdc66..c53abd1 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -221,9 +221,6 @@ enum rpcrdma_frmr_state { }; struct rpcrdma_frmr { - struct scatterlist *fr_sg; - int fr_nents; - enum dma_data_direction fr_dir; struct ib_mr *fr_mr; struct ib_cqe fr_cqe; enum rpcrdma_frmr_state fr_state; @@ -240,13 +237,16 @@ struct rpcrdma_fmr { }; struct rpcrdma_mw { + struct list_head mw_list; + struct scatterlist *mw_sg; + int mw_nents; + enum dma_data_direction mw_dir; union { struct rpcrdma_fmr fmr; struct rpcrdma_frmr frmr; }; struct work_struct mw_work; struct rpcrdma_xprt *mw_xprt; - struct list_head mw_list; struct list_head mw_all; }; -- cgit v1.1 From d48b1d295079f5e45b5c38683b7be353af1b2bda Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:52:29 -0400 Subject: xprtrdma: Move init and release helpers Clean up: Moving these helpers in a separate patch makes later patches more readable. Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/fmr_ops.c | 118 ++++++++++++++++++++++++++--------------- net/sunrpc/xprtrdma/frwr_ops.c | 90 +++++++++++++++---------------- 2 files changed, 119 insertions(+), 89 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index c748ff6..d524584 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -35,6 +35,12 @@ /* Maximum scatter/gather per FMR */ #define RPCRDMA_MAX_FMR_SGES (64) +/* Access mode of externally registered pages */ +enum { + RPCRDMA_FMR_ACCESS_FLAGS = IB_ACCESS_REMOTE_WRITE | + IB_ACCESS_REMOTE_READ, +}; + static struct workqueue_struct *fmr_recovery_wq; #define FMR_RECOVERY_WQ_FLAGS (WQ_UNBOUND) @@ -60,6 +66,44 @@ fmr_destroy_recovery_wq(void) } static int +__fmr_init(struct rpcrdma_mw *mw, struct ib_pd *pd) +{ + static struct ib_fmr_attr fmr_attr = { + .max_pages = RPCRDMA_MAX_FMR_SGES, + .max_maps = 1, + .page_shift = PAGE_SHIFT + }; + + mw->fmr.physaddrs = kcalloc(RPCRDMA_MAX_FMR_SGES, + sizeof(u64), GFP_KERNEL); + if (!mw->fmr.physaddrs) + goto out_free; + + mw->mw_sg = kcalloc(RPCRDMA_MAX_FMR_SGES, + sizeof(*mw->mw_sg), GFP_KERNEL); + if (!mw->mw_sg) + goto out_free; + + sg_init_table(mw->mw_sg, RPCRDMA_MAX_FMR_SGES); + + mw->fmr.fmr = ib_alloc_fmr(pd, RPCRDMA_FMR_ACCESS_FLAGS, + &fmr_attr); + if (IS_ERR(mw->fmr.fmr)) + goto out_fmr_err; + + return 0; + +out_fmr_err: + dprintk("RPC: %s: ib_alloc_fmr returned %ld\n", __func__, + PTR_ERR(mw->fmr.fmr)); + +out_free: + kfree(mw->mw_sg); + kfree(mw->fmr.physaddrs); + return -ENOMEM; +} + +static int __fmr_unmap(struct rpcrdma_mw *mw) { LIST_HEAD(l); @@ -71,6 +115,30 @@ __fmr_unmap(struct rpcrdma_mw *mw) return rc; } +static void +__fmr_dma_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg) +{ + struct ib_device *device = r_xprt->rx_ia.ri_device; + int nsegs = seg->mr_nsegs; + + while (nsegs--) + rpcrdma_unmap_one(device, seg++); +} + +static void +__fmr_release(struct rpcrdma_mw *r) +{ + int rc; + + kfree(r->fmr.physaddrs); + kfree(r->mw_sg); + + rc = ib_dealloc_fmr(r->fmr.fmr); + if (rc) + pr_err("rpcrdma: final ib_dealloc_fmr for %p returned %i\n", + r, rc); +} + /* Deferred reset of a single FMR. Generate a fresh rkey by * replacing the MR. There's no recovery if this fails. */ @@ -119,12 +187,6 @@ static int fmr_op_init(struct rpcrdma_xprt *r_xprt) { struct rpcrdma_buffer *buf = &r_xprt->rx_buf; - int mr_access_flags = IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_READ; - struct ib_fmr_attr fmr_attr = { - .max_pages = RPCRDMA_MAX_FMR_SGES, - .max_maps = 1, - .page_shift = PAGE_SHIFT - }; struct ib_pd *pd = r_xprt->rx_ia.ri_pd; struct rpcrdma_mw *r; int i, rc; @@ -138,35 +200,22 @@ fmr_op_init(struct rpcrdma_xprt *r_xprt) i *= buf->rb_max_requests; /* one set for each RPC slot */ dprintk("RPC: %s: initalizing %d FMRs\n", __func__, i); - rc = -ENOMEM; while (i--) { r = kzalloc(sizeof(*r), GFP_KERNEL); if (!r) - goto out; - - r->fmr.physaddrs = kmalloc(RPCRDMA_MAX_FMR_SGES * - sizeof(u64), GFP_KERNEL); - if (!r->fmr.physaddrs) - goto out_free; + return -ENOMEM; - r->fmr.fmr = ib_alloc_fmr(pd, mr_access_flags, &fmr_attr); - if (IS_ERR(r->fmr.fmr)) - goto out_fmr_err; + rc = __fmr_init(r, pd); + if (rc) { + kfree(r); + return rc; + } r->mw_xprt = r_xprt; list_add(&r->mw_list, &buf->rb_mws); list_add(&r->mw_all, &buf->rb_all); } return 0; - -out_fmr_err: - rc = PTR_ERR(r->fmr.fmr); - dprintk("RPC: %s: ib_alloc_fmr status %i\n", __func__, rc); - kfree(r->fmr.physaddrs); -out_free: - kfree(r); -out: - return rc; } /* Use the ib_map_phys_fmr() verb to register a memory region @@ -235,16 +284,6 @@ out_maperr: return rc; } -static void -__fmr_dma_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg) -{ - struct ib_device *device = r_xprt->rx_ia.ri_device; - int nsegs = seg->mr_nsegs; - - while (nsegs--) - rpcrdma_unmap_one(device, seg++); -} - /* Invalidate all memory regions that were registered for "req". * * Sleeps until it is safe for the host CPU to access the @@ -337,18 +376,11 @@ static void fmr_op_destroy(struct rpcrdma_buffer *buf) { struct rpcrdma_mw *r; - int rc; while (!list_empty(&buf->rb_all)) { r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all); list_del(&r->mw_all); - kfree(r->fmr.physaddrs); - - rc = ib_dealloc_fmr(r->fmr.fmr); - if (rc) - dprintk("RPC: %s: ib_dealloc_fmr failed %i\n", - __func__, rc); - + __fmr_release(r); kfree(r); } } diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index f02ab80..9cd60bf0 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -99,6 +99,50 @@ frwr_destroy_recovery_wq(void) } static int +__frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, unsigned int depth) +{ + struct rpcrdma_frmr *f = &r->frmr; + int rc; + + f->fr_mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, depth); + if (IS_ERR(f->fr_mr)) + goto out_mr_err; + + r->mw_sg = kcalloc(depth, sizeof(*r->mw_sg), GFP_KERNEL); + if (!r->mw_sg) + goto out_list_err; + + sg_init_table(r->mw_sg, depth); + init_completion(&f->fr_linv_done); + return 0; + +out_mr_err: + rc = PTR_ERR(f->fr_mr); + dprintk("RPC: %s: ib_alloc_mr status %i\n", + __func__, rc); + return rc; + +out_list_err: + rc = -ENOMEM; + dprintk("RPC: %s: sg allocation failure\n", + __func__); + ib_dereg_mr(f->fr_mr); + return rc; +} + +static void +__frwr_release(struct rpcrdma_mw *r) +{ + int rc; + + rc = ib_dereg_mr(r->frmr.fr_mr); + if (rc) + pr_err("rpcrdma: final ib_dereg_mr for %p returned %i\n", + r, rc); + kfree(r->mw_sg); +} + +static int __frwr_reset_mr(struct rpcrdma_ia *ia, struct rpcrdma_mw *r) { struct rpcrdma_frmr *f = &r->frmr; @@ -165,52 +209,6 @@ __frwr_queue_recovery(struct rpcrdma_mw *r) } static int -__frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, unsigned int depth) -{ - struct rpcrdma_frmr *f = &r->frmr; - int rc; - - f->fr_mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, depth); - if (IS_ERR(f->fr_mr)) - goto out_mr_err; - - r->mw_sg = kcalloc(depth, sizeof(*r->mw_sg), GFP_KERNEL); - if (!r->mw_sg) - goto out_list_err; - - sg_init_table(r->mw_sg, depth); - - init_completion(&f->fr_linv_done); - - return 0; - -out_mr_err: - rc = PTR_ERR(f->fr_mr); - dprintk("RPC: %s: ib_alloc_mr status %i\n", - __func__, rc); - return rc; - -out_list_err: - rc = -ENOMEM; - dprintk("RPC: %s: sg allocation failure\n", - __func__); - ib_dereg_mr(f->fr_mr); - return rc; -} - -static void -__frwr_release(struct rpcrdma_mw *r) -{ - int rc; - - rc = ib_dereg_mr(r->frmr.fr_mr); - if (rc) - dprintk("RPC: %s: ib_dereg_mr status %i\n", - __func__, rc); - kfree(r->mw_sg); -} - -static int frwr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, struct rpcrdma_create_data_internal *cdata) { -- cgit v1.1 From 88975ebed5a82b7f0a16f22c81253fdd1ba15fce Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:52:37 -0400 Subject: xprtrdma: Rename fields in rpcrdma_fmr Clean up: Use the same naming convention used in other RPC/RDMA-related data structures. Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/fmr_ops.c | 34 +++++++++++++++++----------------- net/sunrpc/xprtrdma/xprt_rdma.h | 4 ++-- 2 files changed, 19 insertions(+), 19 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index d524584..b8a5533 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -74,9 +74,9 @@ __fmr_init(struct rpcrdma_mw *mw, struct ib_pd *pd) .page_shift = PAGE_SHIFT }; - mw->fmr.physaddrs = kcalloc(RPCRDMA_MAX_FMR_SGES, - sizeof(u64), GFP_KERNEL); - if (!mw->fmr.physaddrs) + mw->fmr.fm_physaddrs = kcalloc(RPCRDMA_MAX_FMR_SGES, + sizeof(u64), GFP_KERNEL); + if (!mw->fmr.fm_physaddrs) goto out_free; mw->mw_sg = kcalloc(RPCRDMA_MAX_FMR_SGES, @@ -86,20 +86,20 @@ __fmr_init(struct rpcrdma_mw *mw, struct ib_pd *pd) sg_init_table(mw->mw_sg, RPCRDMA_MAX_FMR_SGES); - mw->fmr.fmr = ib_alloc_fmr(pd, RPCRDMA_FMR_ACCESS_FLAGS, - &fmr_attr); - if (IS_ERR(mw->fmr.fmr)) + mw->fmr.fm_mr = ib_alloc_fmr(pd, RPCRDMA_FMR_ACCESS_FLAGS, + &fmr_attr); + if (IS_ERR(mw->fmr.fm_mr)) goto out_fmr_err; return 0; out_fmr_err: dprintk("RPC: %s: ib_alloc_fmr returned %ld\n", __func__, - PTR_ERR(mw->fmr.fmr)); + PTR_ERR(mw->fmr.fm_mr)); out_free: kfree(mw->mw_sg); - kfree(mw->fmr.physaddrs); + kfree(mw->fmr.fm_physaddrs); return -ENOMEM; } @@ -109,9 +109,9 @@ __fmr_unmap(struct rpcrdma_mw *mw) LIST_HEAD(l); int rc; - list_add(&mw->fmr.fmr->list, &l); + list_add(&mw->fmr.fm_mr->list, &l); rc = ib_unmap_fmr(&l); - list_del_init(&mw->fmr.fmr->list); + list_del_init(&mw->fmr.fm_mr->list); return rc; } @@ -130,10 +130,10 @@ __fmr_release(struct rpcrdma_mw *r) { int rc; - kfree(r->fmr.physaddrs); + kfree(r->fmr.fm_physaddrs); kfree(r->mw_sg); - rc = ib_dealloc_fmr(r->fmr.fmr); + rc = ib_dealloc_fmr(r->fmr.fm_mr); if (rc) pr_err("rpcrdma: final ib_dealloc_fmr for %p returned %i\n", r, rc); @@ -253,7 +253,7 @@ fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, nsegs = RPCRDMA_MAX_FMR_SGES; for (i = 0; i < nsegs;) { rpcrdma_map_one(device, seg, direction); - mw->fmr.physaddrs[i] = seg->mr_dma; + mw->fmr.fm_physaddrs[i] = seg->mr_dma; len += seg->mr_len; ++seg; ++i; @@ -263,13 +263,13 @@ fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, break; } - rc = ib_map_phys_fmr(mw->fmr.fmr, mw->fmr.physaddrs, + rc = ib_map_phys_fmr(mw->fmr.fm_mr, mw->fmr.fm_physaddrs, i, seg1->mr_dma); if (rc) goto out_maperr; seg1->rl_mw = mw; - seg1->mr_rkey = mw->fmr.fmr->rkey; + seg1->mr_rkey = mw->fmr.fm_mr->rkey; seg1->mr_base = seg1->mr_dma + pageoff; seg1->mr_nsegs = i; seg1->mr_len = len; @@ -309,7 +309,7 @@ fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) seg = &req->rl_segments[i]; mw = seg->rl_mw; - list_add_tail(&mw->fmr.fmr->list, &unmap_list); + list_add_tail(&mw->fmr.fm_mr->list, &unmap_list); i += seg->mr_nsegs; } @@ -324,7 +324,7 @@ fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) seg = &req->rl_segments[i]; mw = seg->rl_mw; - list_del_init(&mw->fmr.fmr->list); + list_del_init(&mw->fmr.fm_mr->list); __fmr_dma_unmap(r_xprt, seg); rpcrdma_put_mw(r_xprt, seg->rl_mw); diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index c53abd1..04696c0 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -232,8 +232,8 @@ struct rpcrdma_frmr { }; struct rpcrdma_fmr { - struct ib_fmr *fmr; - u64 *physaddrs; + struct ib_fmr *fm_mr; + u64 *fm_physaddrs; }; struct rpcrdma_mw { -- cgit v1.1 From fcdfb968a706b0e80b12832bc30387ee9e0a759e Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:52:45 -0400 Subject: xprtrdma: Use scatterlist for DMA mapping and unmapping under FMR The use of a scatterlist for handling DMA mapping and unmapping was recently introduced in frwr_ops.c in commit 4143f34e01e9 ("xprtrdma: Port to new memory registration API"). That commit did not make a similar update to xprtrdma's FMR support because the core ib_map_phys_fmr() and ib_unmap_fmr() APIs have not been changed to take a scatterlist argument. However, FMR still needs to do DMA mapping and unmapping. It appears that RDS, for example, uses a scatterlist for this, then builds the DMA addr array for the ib_map_phys_fmr call separately. I see that SRP also utilizes a scatterlist for DMA mapping. xprtrdma can do something similar. This modernization is used immediately to properly defer DMA unmapping during fmr_unmap_safe (a FIXME). It separates the DMA unmapping coordinates from the rl_segments array. This array, being part of an rpcrdma_req, is always re-used immediately when an RPC exits. A scatterlist is allocated in memory independent of the rl_segments array, so it can be preserved indefinitely (ie, until the MR invalidation and DMA unmapping can actually be done by a worker thread). The FRWR and FMR DMA mapping code are slightly different from each other now, and will diverge further when the "Check for holes" logic can be removed from FRWR (support for SG_GAP MRs). So I chose not to create helpers for the common-looking code. Fixes: ead3f26e359e ("xprtrdma: Add ro_unmap_safe memreg method") Suggested-by: Sagi Grimberg Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/fmr_ops.c | 96 +++++++++++++++++++++++++------------------ 1 file changed, 57 insertions(+), 39 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index b8a5533..df5fe17 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -116,13 +116,28 @@ __fmr_unmap(struct rpcrdma_mw *mw) } static void -__fmr_dma_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg) +__fmr_dma_unmap(struct rpcrdma_mw *mw) { - struct ib_device *device = r_xprt->rx_ia.ri_device; - int nsegs = seg->mr_nsegs; + struct rpcrdma_xprt *r_xprt = mw->mw_xprt; - while (nsegs--) - rpcrdma_unmap_one(device, seg++); + ib_dma_unmap_sg(r_xprt->rx_ia.ri_device, + mw->mw_sg, mw->mw_nents, mw->mw_dir); + rpcrdma_put_mw(r_xprt, mw); +} + +static void +__fmr_reset_and_unmap(struct rpcrdma_mw *mw) +{ + int rc; + + /* ORDER */ + rc = __fmr_unmap(mw); + if (rc) { + pr_warn("rpcrdma: ib_unmap_fmr status %d, fmr %p orphaned\n", + rc, mw); + return; + } + __fmr_dma_unmap(mw); } static void @@ -146,11 +161,9 @@ static void __fmr_recovery_worker(struct work_struct *work) { struct rpcrdma_mw *mw = container_of(work, struct rpcrdma_mw, - mw_work); - struct rpcrdma_xprt *r_xprt = mw->mw_xprt; + mw_work); - __fmr_unmap(mw); - rpcrdma_put_mw(r_xprt, mw); + __fmr_reset_and_unmap(mw); return; } @@ -225,12 +238,10 @@ static int fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, int nsegs, bool writing) { - struct rpcrdma_ia *ia = &r_xprt->rx_ia; - struct ib_device *device = ia->ri_device; - enum dma_data_direction direction = rpcrdma_data_dir(writing); struct rpcrdma_mr_seg *seg1 = seg; int len, pageoff, i, rc; struct rpcrdma_mw *mw; + u64 *dma_pages; mw = seg1->rl_mw; seg1->rl_mw = NULL; @@ -252,8 +263,14 @@ fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, if (nsegs > RPCRDMA_MAX_FMR_SGES) nsegs = RPCRDMA_MAX_FMR_SGES; for (i = 0; i < nsegs;) { - rpcrdma_map_one(device, seg, direction); - mw->fmr.fm_physaddrs[i] = seg->mr_dma; + if (seg->mr_page) + sg_set_page(&mw->mw_sg[i], + seg->mr_page, + seg->mr_len, + offset_in_page(seg->mr_offset)); + else + sg_set_buf(&mw->mw_sg[i], seg->mr_offset, + seg->mr_len); len += seg->mr_len; ++seg; ++i; @@ -262,25 +279,37 @@ fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len)) break; } + mw->mw_nents = i; + mw->mw_dir = rpcrdma_data_dir(writing); + + if (!ib_dma_map_sg(r_xprt->rx_ia.ri_device, + mw->mw_sg, mw->mw_nents, mw->mw_dir)) + goto out_dmamap_err; - rc = ib_map_phys_fmr(mw->fmr.fm_mr, mw->fmr.fm_physaddrs, - i, seg1->mr_dma); + for (i = 0, dma_pages = mw->fmr.fm_physaddrs; i < mw->mw_nents; i++) + dma_pages[i] = sg_dma_address(&mw->mw_sg[i]); + rc = ib_map_phys_fmr(mw->fmr.fm_mr, dma_pages, mw->mw_nents, + dma_pages[0]); if (rc) goto out_maperr; seg1->rl_mw = mw; seg1->mr_rkey = mw->fmr.fm_mr->rkey; - seg1->mr_base = seg1->mr_dma + pageoff; - seg1->mr_nsegs = i; + seg1->mr_base = dma_pages[0] + pageoff; + seg1->mr_nsegs = mw->mw_nents; seg1->mr_len = len; - return i; + return mw->mw_nents; + +out_dmamap_err: + pr_err("rpcrdma: failed to dma map sg %p sg_nents %u\n", + mw->mw_sg, mw->mw_nents); + return -ENOMEM; out_maperr: - dprintk("RPC: %s: ib_map_phys_fmr %u@0x%llx+%i (%d) status %i\n", - __func__, len, (unsigned long long)seg1->mr_dma, - pageoff, i, rc); - while (i--) - rpcrdma_unmap_one(device, --seg); + pr_err("rpcrdma: ib_map_phys_fmr %u@0x%llx+%i (%d) status %i\n", + len, (unsigned long long)dma_pages[0], + pageoff, mw->mw_nents, rc); + __fmr_dma_unmap(mw); return rc; } @@ -325,8 +354,7 @@ fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) mw = seg->rl_mw; list_del_init(&mw->fmr.fm_mr->list); - __fmr_dma_unmap(r_xprt, seg); - rpcrdma_put_mw(r_xprt, seg->rl_mw); + __fmr_dma_unmap(mw); i += seg->mr_nsegs; seg->mr_nsegs = 0; @@ -338,11 +366,6 @@ fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) /* Use a slow, safe mechanism to invalidate all memory regions * that were registered for "req". - * - * In the asynchronous case, DMA unmapping occurs first here - * because the rpcrdma_mr_seg is released immediately after this - * call. It's contents won't be available in __fmr_dma_unmap later. - * FIXME. */ static void fmr_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, @@ -356,15 +379,10 @@ fmr_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, seg = &req->rl_segments[i]; mw = seg->rl_mw; - if (sync) { - /* ORDER */ - __fmr_unmap(mw); - __fmr_dma_unmap(r_xprt, seg); - rpcrdma_put_mw(r_xprt, mw); - } else { - __fmr_dma_unmap(r_xprt, seg); + if (sync) + __fmr_reset_and_unmap(mw); + else __fmr_queue_recovery(mw); - } i += seg->mr_nsegs; seg->mr_nsegs = 0; -- cgit v1.1 From 505bbe64dd04b105c1377703252758ac56f92485 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:52:54 -0400 Subject: xprtrdma: Refactor MR recovery work queues I found that commit ead3f26e359e ("xprtrdma: Add ro_unmap_safe memreg method"), which introduces ro_unmap_safe, never wired up the FMR recovery worker. The FMR and FRWR recovery work queues both do the same thing. Instead of setting up separate individual work queues for this, schedule a delayed worker to deal with them, since recovering MRs is not performance-critical. Fixes: ead3f26e359e ("xprtrdma: Add ro_unmap_safe memreg method") Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/fmr_ops.c | 147 ++++++++++++++++------------------------ net/sunrpc/xprtrdma/frwr_ops.c | 82 ++++++---------------- net/sunrpc/xprtrdma/transport.c | 16 ++--- net/sunrpc/xprtrdma/verbs.c | 43 +++++++++++- net/sunrpc/xprtrdma/xprt_rdma.h | 13 ++-- 5 files changed, 135 insertions(+), 166 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index df5fe17..4837ced 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -19,13 +19,6 @@ * verb (fmr_op_unmap). */ -/* Transport recovery - * - * After a transport reconnect, fmr_op_map re-uses the MR already - * allocated for the RPC, but generates a fresh rkey then maps the - * MR again. This process is synchronous. - */ - #include "xprt_rdma.h" #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) @@ -41,30 +34,6 @@ enum { IB_ACCESS_REMOTE_READ, }; -static struct workqueue_struct *fmr_recovery_wq; - -#define FMR_RECOVERY_WQ_FLAGS (WQ_UNBOUND) - -int -fmr_alloc_recovery_wq(void) -{ - fmr_recovery_wq = alloc_workqueue("fmr_recovery", WQ_UNBOUND, 0); - return !fmr_recovery_wq ? -ENOMEM : 0; -} - -void -fmr_destroy_recovery_wq(void) -{ - struct workqueue_struct *wq; - - if (!fmr_recovery_wq) - return; - - wq = fmr_recovery_wq; - fmr_recovery_wq = NULL; - destroy_workqueue(wq); -} - static int __fmr_init(struct rpcrdma_mw *mw, struct ib_pd *pd) { @@ -116,65 +85,55 @@ __fmr_unmap(struct rpcrdma_mw *mw) } static void -__fmr_dma_unmap(struct rpcrdma_mw *mw) -{ - struct rpcrdma_xprt *r_xprt = mw->mw_xprt; - - ib_dma_unmap_sg(r_xprt->rx_ia.ri_device, - mw->mw_sg, mw->mw_nents, mw->mw_dir); - rpcrdma_put_mw(r_xprt, mw); -} - -static void -__fmr_reset_and_unmap(struct rpcrdma_mw *mw) -{ - int rc; - - /* ORDER */ - rc = __fmr_unmap(mw); - if (rc) { - pr_warn("rpcrdma: ib_unmap_fmr status %d, fmr %p orphaned\n", - rc, mw); - return; - } - __fmr_dma_unmap(mw); -} - -static void __fmr_release(struct rpcrdma_mw *r) { + LIST_HEAD(unmap_list); int rc; kfree(r->fmr.fm_physaddrs); kfree(r->mw_sg); + /* In case this one was left mapped, try to unmap it + * to prevent dealloc_fmr from failing with EBUSY + */ + rc = __fmr_unmap(r); + if (rc) + pr_err("rpcrdma: final ib_unmap_fmr for %p failed %i\n", + r, rc); + rc = ib_dealloc_fmr(r->fmr.fm_mr); if (rc) pr_err("rpcrdma: final ib_dealloc_fmr for %p returned %i\n", r, rc); } -/* Deferred reset of a single FMR. Generate a fresh rkey by - * replacing the MR. There's no recovery if this fails. +/* Reset of a single FMR. + * + * There's no recovery if this fails. The FMR is abandoned, but + * remains in rb_all. It will be cleaned up when the transport is + * destroyed. */ static void -__fmr_recovery_worker(struct work_struct *work) +fmr_op_recover_mr(struct rpcrdma_mw *mw) { - struct rpcrdma_mw *mw = container_of(work, struct rpcrdma_mw, - mw_work); + struct rpcrdma_xprt *r_xprt = mw->mw_xprt; + int rc; - __fmr_reset_and_unmap(mw); - return; -} + /* ORDER: invalidate first */ + rc = __fmr_unmap(mw); -/* A broken MR was discovered in a context that can't sleep. - * Defer recovery to the recovery worker. - */ -static void -__fmr_queue_recovery(struct rpcrdma_mw *mw) -{ - INIT_WORK(&mw->mw_work, __fmr_recovery_worker); - queue_work(fmr_recovery_wq, &mw->mw_work); + /* ORDER: then DMA unmap */ + ib_dma_unmap_sg(r_xprt->rx_ia.ri_device, + mw->mw_sg, mw->mw_nents, mw->mw_dir); + if (rc) { + pr_err("rpcrdma: FMR reset status %d, %p orphaned\n", + rc, mw); + r_xprt->rx_stats.mrs_orphaned++; + return; + } + + rpcrdma_put_mw(r_xprt, mw); + r_xprt->rx_stats.mrs_recovered++; } static int @@ -245,16 +204,11 @@ fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, mw = seg1->rl_mw; seg1->rl_mw = NULL; - if (!mw) { - mw = rpcrdma_get_mw(r_xprt); - if (!mw) - return -ENOMEM; - } else { - /* this is a retransmit; generate a fresh rkey */ - rc = __fmr_unmap(mw); - if (rc) - return rc; - } + if (mw) + rpcrdma_defer_mr_recovery(mw); + mw = rpcrdma_get_mw(r_xprt); + if (!mw) + return -ENOMEM; pageoff = offset_in_page(seg1->mr_offset); seg1->mr_offset -= pageoff; /* start of page */ @@ -309,7 +263,7 @@ out_maperr: pr_err("rpcrdma: ib_map_phys_fmr %u@0x%llx+%i (%d) status %i\n", len, (unsigned long long)dma_pages[0], pageoff, mw->mw_nents, rc); - __fmr_dma_unmap(mw); + rpcrdma_defer_mr_recovery(mw); return rc; } @@ -332,7 +286,7 @@ fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) /* ORDER: Invalidate all of the req's MRs first * * ib_unmap_fmr() is slow, so use a single call instead - * of one call per mapped MR. + * of one call per mapped FMR. */ for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) { seg = &req->rl_segments[i]; @@ -344,7 +298,7 @@ fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) } rc = ib_unmap_fmr(&unmap_list); if (rc) - pr_warn("%s: ib_unmap_fmr failed (%i)\n", __func__, rc); + goto out_reset; /* ORDER: Now DMA unmap all of the req's MRs, and return * them to the free MW list. @@ -354,7 +308,9 @@ fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) mw = seg->rl_mw; list_del_init(&mw->fmr.fm_mr->list); - __fmr_dma_unmap(mw); + ib_dma_unmap_sg(r_xprt->rx_ia.ri_device, + mw->mw_sg, mw->mw_nents, mw->mw_dir); + rpcrdma_put_mw(r_xprt, mw); i += seg->mr_nsegs; seg->mr_nsegs = 0; @@ -362,6 +318,20 @@ fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) } req->rl_nchunks = 0; + return; + +out_reset: + pr_err("rpcrdma: ib_unmap_fmr failed (%i)\n", rc); + + for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) { + seg = &req->rl_segments[i]; + mw = seg->rl_mw; + + list_del_init(&mw->fmr.fm_mr->list); + fmr_op_recover_mr(mw); + + i += seg->mr_nsegs; + } } /* Use a slow, safe mechanism to invalidate all memory regions @@ -380,9 +350,9 @@ fmr_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, mw = seg->rl_mw; if (sync) - __fmr_reset_and_unmap(mw); + fmr_op_recover_mr(mw); else - __fmr_queue_recovery(mw); + rpcrdma_defer_mr_recovery(mw); i += seg->mr_nsegs; seg->mr_nsegs = 0; @@ -407,6 +377,7 @@ const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops = { .ro_map = fmr_op_map, .ro_unmap_sync = fmr_op_unmap_sync, .ro_unmap_safe = fmr_op_unmap_safe, + .ro_recover_mr = fmr_op_recover_mr, .ro_open = fmr_op_open, .ro_maxpages = fmr_op_maxpages, .ro_init = fmr_op_init, diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 9cd60bf0..cbb2d05 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -73,31 +73,6 @@ # define RPCDBG_FACILITY RPCDBG_TRANS #endif -static struct workqueue_struct *frwr_recovery_wq; - -#define FRWR_RECOVERY_WQ_FLAGS (WQ_UNBOUND | WQ_MEM_RECLAIM) - -int -frwr_alloc_recovery_wq(void) -{ - frwr_recovery_wq = alloc_workqueue("frwr_recovery", - FRWR_RECOVERY_WQ_FLAGS, 0); - return !frwr_recovery_wq ? -ENOMEM : 0; -} - -void -frwr_destroy_recovery_wq(void) -{ - struct workqueue_struct *wq; - - if (!frwr_recovery_wq) - return; - - wq = frwr_recovery_wq; - frwr_recovery_wq = NULL; - destroy_workqueue(wq); -} - static int __frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, unsigned int depth) { @@ -168,8 +143,14 @@ __frwr_reset_mr(struct rpcrdma_ia *ia, struct rpcrdma_mw *r) return 0; } +/* Reset of a single FRMR. Generate a fresh rkey by replacing the MR. + * + * There's no recovery if this fails. The FRMR is abandoned, but + * remains in rb_all. It will be cleaned up when the transport is + * destroyed. + */ static void -__frwr_reset_and_unmap(struct rpcrdma_mw *mw) +frwr_op_recover_mr(struct rpcrdma_mw *mw) { struct rpcrdma_xprt *r_xprt = mw->mw_xprt; struct rpcrdma_ia *ia = &r_xprt->rx_ia; @@ -177,35 +158,15 @@ __frwr_reset_and_unmap(struct rpcrdma_mw *mw) rc = __frwr_reset_mr(ia, mw); ib_dma_unmap_sg(ia->ri_device, mw->mw_sg, mw->mw_nents, mw->mw_dir); - if (rc) + if (rc) { + pr_err("rpcrdma: FRMR reset status %d, %p orphaned\n", + rc, mw); + r_xprt->rx_stats.mrs_orphaned++; return; - rpcrdma_put_mw(r_xprt, mw); -} - -/* Deferred reset of a single FRMR. Generate a fresh rkey by - * replacing the MR. - * - * There's no recovery if this fails. The FRMR is abandoned, but - * remains in rb_all. It will be cleaned up when the transport is - * destroyed. - */ -static void -__frwr_recovery_worker(struct work_struct *work) -{ - struct rpcrdma_mw *r = container_of(work, struct rpcrdma_mw, - mw_work); - - __frwr_reset_and_unmap(r); -} + } -/* A broken MR was discovered in a context that can't sleep. - * Defer recovery to the recovery worker. - */ -static void -__frwr_queue_recovery(struct rpcrdma_mw *r) -{ - INIT_WORK(&r->mw_work, __frwr_recovery_worker); - queue_work(frwr_recovery_wq, &r->mw_work); + rpcrdma_put_mw(r_xprt, mw); + r_xprt->rx_stats.mrs_recovered++; } static int @@ -401,7 +362,7 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, seg1->rl_mw = NULL; do { if (mw) - __frwr_queue_recovery(mw); + rpcrdma_defer_mr_recovery(mw); mw = rpcrdma_get_mw(r_xprt); if (!mw) return -ENOMEM; @@ -483,12 +444,11 @@ out_mapmr_err: pr_err("rpcrdma: failed to map mr %p (%u/%u)\n", frmr->fr_mr, n, mw->mw_nents); rc = n < 0 ? n : -EIO; - __frwr_queue_recovery(mw); + rpcrdma_defer_mr_recovery(mw); return rc; out_senderr: - pr_err("rpcrdma: ib_post_send status %i\n", rc); - __frwr_queue_recovery(mw); + rpcrdma_defer_mr_recovery(mw); return rc; } @@ -627,9 +587,9 @@ frwr_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, mw = seg->rl_mw; if (sync) - __frwr_reset_and_unmap(mw); + frwr_op_recover_mr(mw); else - __frwr_queue_recovery(mw); + rpcrdma_defer_mr_recovery(mw); i += seg->mr_nsegs; seg->mr_nsegs = 0; @@ -642,9 +602,6 @@ frwr_op_destroy(struct rpcrdma_buffer *buf) { struct rpcrdma_mw *r; - /* Ensure stale MWs for "buf" are no longer in flight */ - flush_workqueue(frwr_recovery_wq); - while (!list_empty(&buf->rb_all)) { r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all); list_del(&r->mw_all); @@ -657,6 +614,7 @@ const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops = { .ro_map = frwr_op_map, .ro_unmap_sync = frwr_op_unmap_sync, .ro_unmap_safe = frwr_op_unmap_safe, + .ro_recover_mr = frwr_op_recover_mr, .ro_open = frwr_op_open, .ro_maxpages = frwr_op_maxpages, .ro_init = frwr_op_init, diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 99d2e5b..4c8e7f1 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -660,7 +660,7 @@ void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) xprt->stat.bad_xids, xprt->stat.req_u, xprt->stat.bklog_u); - seq_printf(seq, "%lu %lu %lu %llu %llu %llu %llu %lu %lu %lu %lu\n", + seq_printf(seq, "%lu %lu %lu %llu %llu %llu %llu %lu %lu %lu %lu ", r_xprt->rx_stats.read_chunk_count, r_xprt->rx_stats.write_chunk_count, r_xprt->rx_stats.reply_chunk_count, @@ -672,6 +672,9 @@ void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) r_xprt->rx_stats.failed_marshal_count, r_xprt->rx_stats.bad_reply_count, r_xprt->rx_stats.nomsg_call_count); + seq_printf(seq, "%lu %lu\n", + r_xprt->rx_stats.mrs_recovered, + r_xprt->rx_stats.mrs_orphaned); } static int @@ -741,7 +744,6 @@ void xprt_rdma_cleanup(void) __func__, rc); rpcrdma_destroy_wq(); - frwr_destroy_recovery_wq(); rc = xprt_unregister_transport(&xprt_rdma_bc); if (rc) @@ -753,20 +755,13 @@ int xprt_rdma_init(void) { int rc; - rc = frwr_alloc_recovery_wq(); - if (rc) - return rc; - rc = rpcrdma_alloc_wq(); - if (rc) { - frwr_destroy_recovery_wq(); + if (rc) return rc; - } rc = xprt_register_transport(&xprt_rdma); if (rc) { rpcrdma_destroy_wq(); - frwr_destroy_recovery_wq(); return rc; } @@ -774,7 +769,6 @@ int xprt_rdma_init(void) if (rc) { xprt_unregister_transport(&xprt_rdma); rpcrdma_destroy_wq(); - frwr_destroy_recovery_wq(); return rc; } diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index b044d98a..77a371d 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -777,6 +777,41 @@ rpcrdma_ep_disconnect(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) ib_drain_qp(ia->ri_id->qp); } +static void +rpcrdma_mr_recovery_worker(struct work_struct *work) +{ + struct rpcrdma_buffer *buf = container_of(work, struct rpcrdma_buffer, + rb_recovery_worker.work); + struct rpcrdma_mw *mw; + + spin_lock(&buf->rb_recovery_lock); + while (!list_empty(&buf->rb_stale_mrs)) { + mw = list_first_entry(&buf->rb_stale_mrs, + struct rpcrdma_mw, mw_list); + list_del_init(&mw->mw_list); + spin_unlock(&buf->rb_recovery_lock); + + dprintk("RPC: %s: recovering MR %p\n", __func__, mw); + mw->mw_xprt->rx_ia.ri_ops->ro_recover_mr(mw); + + spin_lock(&buf->rb_recovery_lock); + }; + spin_unlock(&buf->rb_recovery_lock); +} + +void +rpcrdma_defer_mr_recovery(struct rpcrdma_mw *mw) +{ + struct rpcrdma_xprt *r_xprt = mw->mw_xprt; + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + + spin_lock(&buf->rb_recovery_lock); + list_add(&mw->mw_list, &buf->rb_stale_mrs); + spin_unlock(&buf->rb_recovery_lock); + + schedule_delayed_work(&buf->rb_recovery_worker, 0); +} + struct rpcrdma_req * rpcrdma_create_req(struct rpcrdma_xprt *r_xprt) { @@ -837,8 +872,12 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) buf->rb_max_requests = r_xprt->rx_data.max_requests; buf->rb_bc_srv_max_requests = 0; - spin_lock_init(&buf->rb_lock); atomic_set(&buf->rb_credits, 1); + spin_lock_init(&buf->rb_lock); + spin_lock_init(&buf->rb_recovery_lock); + INIT_LIST_HEAD(&buf->rb_stale_mrs); + INIT_DELAYED_WORK(&buf->rb_recovery_worker, + rpcrdma_mr_recovery_worker); rc = ia->ri_ops->ro_init(r_xprt); if (rc) @@ -923,6 +962,8 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf) { struct rpcrdma_ia *ia = rdmab_to_ia(buf); + cancel_delayed_work_sync(&buf->rb_recovery_worker); + while (!list_empty(&buf->rb_recv_bufs)) { struct rpcrdma_rep *rep; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 04696c0..4e03037 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -245,7 +245,6 @@ struct rpcrdma_mw { struct rpcrdma_fmr fmr; struct rpcrdma_frmr frmr; }; - struct work_struct mw_work; struct rpcrdma_xprt *mw_xprt; struct list_head mw_all; }; @@ -341,6 +340,10 @@ struct rpcrdma_buffer { struct list_head rb_allreqs; u32 rb_bc_max_requests; + + spinlock_t rb_recovery_lock; /* protect rb_stale_mrs */ + struct list_head rb_stale_mrs; + struct delayed_work rb_recovery_worker; }; #define rdmab_to_ia(b) (&container_of((b), struct rpcrdma_xprt, rx_buf)->rx_ia) @@ -387,6 +390,8 @@ struct rpcrdma_stats { unsigned long bad_reply_count; unsigned long nomsg_call_count; unsigned long bcall_count; + unsigned long mrs_recovered; + unsigned long mrs_orphaned; }; /* @@ -400,6 +405,7 @@ struct rpcrdma_memreg_ops { struct rpcrdma_req *); void (*ro_unmap_safe)(struct rpcrdma_xprt *, struct rpcrdma_req *, bool); + void (*ro_recover_mr)(struct rpcrdma_mw *); int (*ro_open)(struct rpcrdma_ia *, struct rpcrdma_ep *, struct rpcrdma_create_data_internal *); @@ -477,6 +483,8 @@ void rpcrdma_buffer_put(struct rpcrdma_req *); void rpcrdma_recv_buffer_get(struct rpcrdma_req *); void rpcrdma_recv_buffer_put(struct rpcrdma_rep *); +void rpcrdma_defer_mr_recovery(struct rpcrdma_mw *); + struct rpcrdma_regbuf *rpcrdma_alloc_regbuf(struct rpcrdma_ia *, size_t, gfp_t); void rpcrdma_free_regbuf(struct rpcrdma_ia *, @@ -484,9 +492,6 @@ void rpcrdma_free_regbuf(struct rpcrdma_ia *, int rpcrdma_ep_post_extra_recv(struct rpcrdma_xprt *, unsigned int); -int frwr_alloc_recovery_wq(void); -void frwr_destroy_recovery_wq(void); - int rpcrdma_alloc_wq(void); void rpcrdma_destroy_wq(void); -- cgit v1.1 From 42fe28f607634841e870acf16b10469824594463 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:53:02 -0400 Subject: xprtrdma: Do not leak an MW during a DMA map failure Based on code audit. Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/fmr_ops.c | 1 + net/sunrpc/xprtrdma/frwr_ops.c | 1 + 2 files changed, 2 insertions(+) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index 4837ced..6c4527b 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -257,6 +257,7 @@ fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, out_dmamap_err: pr_err("rpcrdma: failed to dma map sg %p sg_nents %u\n", mw->mw_sg, mw->mw_nents); + rpcrdma_defer_mr_recovery(mw); return -ENOMEM; out_maperr: diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index cbb2d05..c9ead2b 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -438,6 +438,7 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, out_dmamap_err: pr_err("rpcrdma: failed to dma map sg %p sg_nents %u\n", mw->mw_sg, mw->mw_nents); + rpcrdma_defer_mr_recovery(mw); return -ENOMEM; out_mapmr_err: -- cgit v1.1 From 2dc3a69de0d6e7f4dba7dbf8eadd5c3ac34098c7 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:53:11 -0400 Subject: xprtrdma: Remove ALLPHYSICAL memory registration mode No HCA or RNIC in the kernel tree requires the use of ALLPHYSICAL. ALLPHYSICAL advertises in the clear on the network fabric an R_key that is good for all of the client's memory. No known exploit exists, but theoretically any user on the server can use that R_key on the client's QP to read or update any part of the client's memory. ALLPHYSICAL exposes the client to server bugs, including: o base/bounds errors causing data outside the i/o buffer to be accessed o RDMA access after reply causing data corruption and/or integrity fail ALLPHYSICAL can't protect application memory regions from server update after a local signal or soft timeout has terminated an RPC. ALLPHYSICAL chunks are no larger than a page. Special cases to handle small chunks and long chunk lists have been a source of implementation complexity and bugs. Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/Makefile | 2 +- net/sunrpc/xprtrdma/physical_ops.c | 122 ------------------------------------- net/sunrpc/xprtrdma/verbs.c | 15 ----- net/sunrpc/xprtrdma/xprt_rdma.h | 5 +- 4 files changed, 2 insertions(+), 142 deletions(-) delete mode 100644 net/sunrpc/xprtrdma/physical_ops.c (limited to 'net') diff --git a/net/sunrpc/xprtrdma/Makefile b/net/sunrpc/xprtrdma/Makefile index dc9f3b5..ef19fa4 100644 --- a/net/sunrpc/xprtrdma/Makefile +++ b/net/sunrpc/xprtrdma/Makefile @@ -1,7 +1,7 @@ obj-$(CONFIG_SUNRPC_XPRT_RDMA) += rpcrdma.o rpcrdma-y := transport.o rpc_rdma.o verbs.o \ - fmr_ops.o frwr_ops.o physical_ops.o \ + fmr_ops.o frwr_ops.o \ svc_rdma.o svc_rdma_backchannel.o svc_rdma_transport.o \ svc_rdma_marshal.o svc_rdma_sendto.o svc_rdma_recvfrom.o \ module.o diff --git a/net/sunrpc/xprtrdma/physical_ops.c b/net/sunrpc/xprtrdma/physical_ops.c deleted file mode 100644 index 3750596..0000000 --- a/net/sunrpc/xprtrdma/physical_ops.c +++ /dev/null @@ -1,122 +0,0 @@ -/* - * Copyright (c) 2015 Oracle. All rights reserved. - * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved. - */ - -/* No-op chunk preparation. All client memory is pre-registered. - * Sometimes referred to as ALLPHYSICAL mode. - * - * Physical registration is simple because all client memory is - * pre-registered and never deregistered. This mode is good for - * adapter bring up, but is considered not safe: the server is - * trusted not to abuse its access to client memory not involved - * in RDMA I/O. - */ - -#include "xprt_rdma.h" - -#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) -# define RPCDBG_FACILITY RPCDBG_TRANS -#endif - -static int -physical_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, - struct rpcrdma_create_data_internal *cdata) -{ - struct ib_mr *mr; - - /* Obtain an rkey to use for RPC data payloads. - */ - mr = ib_get_dma_mr(ia->ri_pd, - IB_ACCESS_LOCAL_WRITE | - IB_ACCESS_REMOTE_WRITE | - IB_ACCESS_REMOTE_READ); - if (IS_ERR(mr)) { - pr_err("%s: ib_get_dma_mr for failed with %lX\n", - __func__, PTR_ERR(mr)); - return -ENOMEM; - } - ia->ri_dma_mr = mr; - - rpcrdma_set_max_header_sizes(ia, cdata, min_t(unsigned int, - RPCRDMA_MAX_DATA_SEGS, - RPCRDMA_MAX_HDR_SEGS)); - return 0; -} - -/* PHYSICAL memory registration conveys one page per chunk segment. - */ -static size_t -physical_op_maxpages(struct rpcrdma_xprt *r_xprt) -{ - return min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS, - RPCRDMA_MAX_HDR_SEGS); -} - -static int -physical_op_init(struct rpcrdma_xprt *r_xprt) -{ - return 0; -} - -/* The client's physical memory is already exposed for - * remote access via RDMA READ or RDMA WRITE. - */ -static int -physical_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, - int nsegs, bool writing) -{ - struct rpcrdma_ia *ia = &r_xprt->rx_ia; - - rpcrdma_map_one(ia->ri_device, seg, rpcrdma_data_dir(writing)); - seg->mr_rkey = ia->ri_dma_mr->rkey; - seg->mr_base = seg->mr_dma; - return 1; -} - -/* DMA unmap all memory regions that were mapped for "req". - */ -static void -physical_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) -{ - struct ib_device *device = r_xprt->rx_ia.ri_device; - unsigned int i; - - for (i = 0; req->rl_nchunks; --req->rl_nchunks) - rpcrdma_unmap_one(device, &req->rl_segments[i++]); -} - -/* Use a slow, safe mechanism to invalidate all memory regions - * that were registered for "req". - * - * For physical memory registration, there is no good way to - * fence a single MR that has been advertised to the server. The - * client has already handed the server an R_key that cannot be - * invalidated and is shared by all MRs on this connection. - * Tearing down the PD might be the only safe choice, but it's - * not clear that a freshly acquired DMA R_key would be different - * than the one used by the PD that was just destroyed. - * FIXME. - */ -static void -physical_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, - bool sync) -{ - physical_op_unmap_sync(r_xprt, req); -} - -static void -physical_op_destroy(struct rpcrdma_buffer *buf) -{ -} - -const struct rpcrdma_memreg_ops rpcrdma_physical_memreg_ops = { - .ro_map = physical_op_map, - .ro_unmap_sync = physical_op_unmap_sync, - .ro_unmap_safe = physical_op_unmap_safe, - .ro_open = physical_op_open, - .ro_maxpages = physical_op_maxpages, - .ro_init = physical_op_init, - .ro_destroy = physical_op_destroy, - .ro_displayname = "physical", -}; diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 77a371d..5ee98e9 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -379,8 +379,6 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg) struct rpcrdma_ia *ia = &xprt->rx_ia; int rc; - ia->ri_dma_mr = NULL; - ia->ri_id = rpcrdma_create_id(xprt, ia, addr); if (IS_ERR(ia->ri_id)) { rc = PTR_ERR(ia->ri_id); @@ -418,9 +416,6 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg) case RPCRDMA_FRMR: ia->ri_ops = &rpcrdma_frwr_memreg_ops; break; - case RPCRDMA_ALLPHYSICAL: - ia->ri_ops = &rpcrdma_physical_memreg_ops; - break; case RPCRDMA_MTHCAFMR: ia->ri_ops = &rpcrdma_fmr_memreg_ops; break; @@ -585,8 +580,6 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, out2: ib_free_cq(sendcq); out1: - if (ia->ri_dma_mr) - ib_dereg_mr(ia->ri_dma_mr); return rc; } @@ -600,8 +593,6 @@ out1: void rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) { - int rc; - dprintk("RPC: %s: entering, connected is %d\n", __func__, ep->rep_connected); @@ -615,12 +606,6 @@ rpcrdma_ep_destroy(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia) ib_free_cq(ep->rep_attr.recv_cq); ib_free_cq(ep->rep_attr.send_cq); - - if (ia->ri_dma_mr) { - rc = ib_dereg_mr(ia->ri_dma_mr); - dprintk("RPC: %s: ib_dereg_mr returned %i\n", - __func__, rc); - } } /* diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 4e03037..bcb168e 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -68,7 +68,6 @@ struct rpcrdma_ia { struct ib_device *ri_device; struct rdma_cm_id *ri_id; struct ib_pd *ri_pd; - struct ib_mr *ri_dma_mr; struct completion ri_done; int ri_async_rc; unsigned int ri_max_frmr_depth; @@ -269,8 +268,7 @@ struct rpcrdma_mw { * NOTES: * o RPCRDMA_MAX_SEGS is the max number of addressible chunk elements we * marshal. The number needed varies depending on the iov lists that - * are passed to us, the memory registration mode we are in, and if - * physical addressing is used, the layout. + * are passed to us and the memory registration mode we are in. */ struct rpcrdma_mr_seg { /* chunk descriptors */ @@ -417,7 +415,6 @@ struct rpcrdma_memreg_ops { extern const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops; extern const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops; -extern const struct rpcrdma_memreg_ops rpcrdma_physical_memreg_ops; /* * RPCRDMA transport -- encapsulates the structures above for -- cgit v1.1 From a473018cfe0ef1e46c0ff9df3fa02afc23c9f1d2 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:53:19 -0400 Subject: xprtrdma: Remove rpcrdma_map_one() and friends Clean up: ALLPHYSICAL is gone and FMR has been converted to use scatterlists. There are no more users of these functions. This patch shrinks the size of struct rpcrdma_req by about 3500 bytes on x86_64. There is one of these structs for each RPC credit (128 credits per transport connection). Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/verbs.c | 8 -------- net/sunrpc/xprtrdma/xprt_rdma.h | 36 ------------------------------------ 2 files changed, 44 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 5ee98e9..b80e767f 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1086,14 +1086,6 @@ rpcrdma_recv_buffer_put(struct rpcrdma_rep *rep) * Wrappers for internal-use kmalloc memory registration, used by buffer code. */ -void -rpcrdma_mapping_error(struct rpcrdma_mr_seg *seg) -{ - dprintk("RPC: map_one: offset %p iova %llx len %zu\n", - seg->mr_offset, - (unsigned long long)seg->mr_dma, seg->mr_dmalen); -} - /** * rpcrdma_alloc_regbuf - kmalloc and register memory for SEND/RECV buffers * @ia: controlling rpcrdma_ia diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index bcb168e..f1b6f2f 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -277,9 +277,6 @@ struct rpcrdma_mr_seg { /* chunk descriptors */ u32 mr_rkey; /* registration result */ u32 mr_len; /* length of chunk or segment */ int mr_nsegs; /* number of segments in chunk or 0 */ - enum dma_data_direction mr_dir; /* segment mapping direction */ - dma_addr_t mr_dma; /* segment mapping address */ - size_t mr_dmalen; /* segment mapping length */ struct page *mr_page; /* owning page, if any */ char *mr_offset; /* kva if no page, else offset */ }; @@ -496,45 +493,12 @@ void rpcrdma_destroy_wq(void); * Wrappers for chunk registration, shared by read/write chunk code. */ -void rpcrdma_mapping_error(struct rpcrdma_mr_seg *); - static inline enum dma_data_direction rpcrdma_data_dir(bool writing) { return writing ? DMA_FROM_DEVICE : DMA_TO_DEVICE; } -static inline void -rpcrdma_map_one(struct ib_device *device, struct rpcrdma_mr_seg *seg, - enum dma_data_direction direction) -{ - seg->mr_dir = direction; - seg->mr_dmalen = seg->mr_len; - - if (seg->mr_page) - seg->mr_dma = ib_dma_map_page(device, - seg->mr_page, offset_in_page(seg->mr_offset), - seg->mr_dmalen, seg->mr_dir); - else - seg->mr_dma = ib_dma_map_single(device, - seg->mr_offset, - seg->mr_dmalen, seg->mr_dir); - - if (ib_dma_mapping_error(device, seg->mr_dma)) - rpcrdma_mapping_error(seg); -} - -static inline void -rpcrdma_unmap_one(struct ib_device *device, struct rpcrdma_mr_seg *seg) -{ - if (seg->mr_page) - ib_dma_unmap_page(device, - seg->mr_dma, seg->mr_dmalen, seg->mr_dir); - else - ib_dma_unmap_single(device, - seg->mr_dma, seg->mr_dmalen, seg->mr_dir); -} - /* * RPC/RDMA connection management calls - xprtrdma/rpc_rdma.c */ -- cgit v1.1 From b54054ca5590f59469437fc4a78a978edcb01c31 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:53:27 -0400 Subject: xprtrdma: Clean up device capability detection Clean up: Move device capability detection into memreg-specific source files. Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/fmr_ops.c | 11 +++++++++++ net/sunrpc/xprtrdma/frwr_ops.c | 17 ++++++++++++++++ net/sunrpc/xprtrdma/verbs.c | 43 ++++++++++++++--------------------------- net/sunrpc/xprtrdma/xprt_rdma.h | 2 ++ 4 files changed, 44 insertions(+), 29 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index 6c4527b..8b6ce8e 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -34,6 +34,17 @@ enum { IB_ACCESS_REMOTE_READ, }; +bool +fmr_is_supported(struct rpcrdma_ia *ia) +{ + if (!ia->ri_device->alloc_fmr) { + pr_info("rpcrdma: 'fmr' mode is not supported by device %s\n", + ia->ri_device->name); + return false; + } + return true; +} + static int __fmr_init(struct rpcrdma_mw *mw, struct ib_pd *pd) { diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index c9ead2b..fc2826b 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -73,6 +73,23 @@ # define RPCDBG_FACILITY RPCDBG_TRANS #endif +bool +frwr_is_supported(struct rpcrdma_ia *ia) +{ + struct ib_device_attr *attrs = &ia->ri_device->attrs; + + if (!(attrs->device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS)) + goto out_not_supported; + if (attrs->max_fast_reg_page_list_len == 0) + goto out_not_supported; + return true; + +out_not_supported: + pr_info("rpcrdma: 'frwr' mode is not supported by device %s\n", + ia->ri_device->name); + return false; +} + static int __frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, unsigned int depth) { diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index b80e767f..cd4c5f1 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -389,44 +389,29 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg) ia->ri_pd = ib_alloc_pd(ia->ri_device); if (IS_ERR(ia->ri_pd)) { rc = PTR_ERR(ia->ri_pd); - dprintk("RPC: %s: ib_alloc_pd() failed %i\n", - __func__, rc); + pr_err("rpcrdma: ib_alloc_pd() returned %d\n", rc); goto out2; } - if (memreg == RPCRDMA_FRMR) { - if (!(ia->ri_device->attrs.device_cap_flags & - IB_DEVICE_MEM_MGT_EXTENSIONS) || - (ia->ri_device->attrs.max_fast_reg_page_list_len == 0)) { - dprintk("RPC: %s: FRMR registration " - "not supported by HCA\n", __func__); - memreg = RPCRDMA_MTHCAFMR; - } - } - if (memreg == RPCRDMA_MTHCAFMR) { - if (!ia->ri_device->alloc_fmr) { - dprintk("RPC: %s: MTHCAFMR registration " - "not supported by HCA\n", __func__); - rc = -EINVAL; - goto out3; - } - } - switch (memreg) { case RPCRDMA_FRMR: - ia->ri_ops = &rpcrdma_frwr_memreg_ops; - break; + if (frwr_is_supported(ia)) { + ia->ri_ops = &rpcrdma_frwr_memreg_ops; + break; + } + /*FALLTHROUGH*/ case RPCRDMA_MTHCAFMR: - ia->ri_ops = &rpcrdma_fmr_memreg_ops; - break; + if (fmr_is_supported(ia)) { + ia->ri_ops = &rpcrdma_fmr_memreg_ops; + break; + } + /*FALLTHROUGH*/ default: - printk(KERN_ERR "RPC: Unsupported memory " - "registration mode: %d\n", memreg); - rc = -ENOMEM; + pr_err("rpcrdma: Unsupported memory registration mode: %d\n", + memreg); + rc = -EINVAL; goto out3; } - dprintk("RPC: %s: memory registration strategy is '%s'\n", - __func__, ia->ri_ops->ro_displayname); return 0; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index f1b6f2f..08d441d 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -446,6 +446,8 @@ extern int xprt_rdma_pad_optimize; */ int rpcrdma_ia_open(struct rpcrdma_xprt *, struct sockaddr *, int); void rpcrdma_ia_close(struct rpcrdma_ia *); +bool frwr_is_supported(struct rpcrdma_ia *); +bool fmr_is_supported(struct rpcrdma_ia *); /* * Endpoint calls - xprtrdma/verbs.c -- cgit v1.1 From 3d4cf35bd4fab56c3aa0ec4323fccb24970aaf79 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:53:35 -0400 Subject: xprtrdma: Reply buffer exhaustion can be catastrophic Not having an rpcrdma_rep at call_allocate time can be a problem. It means that send_request can't post a receive buffer to catch the RPC's reply. Possible consequences are RPC timeouts or even transport deadlock. Instead of allowing an RPC to proceed if an rpcrdma_rep is not available, return NULL to force call_allocate to wait and try again. Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/verbs.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index cd4c5f1..6fb73ff 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -871,7 +871,7 @@ rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) } INIT_LIST_HEAD(&buf->rb_recv_bufs); - for (i = 0; i < buf->rb_max_requests + 2; i++) { + for (i = 0; i < buf->rb_max_requests; i++) { struct rpcrdma_rep *rep; rep = rpcrdma_create_rep(r_xprt); @@ -989,8 +989,6 @@ rpcrdma_put_mw(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mw *mw) /* * Get a set of request/reply buffers. - * - * Reply buffer (if available) is attached to send buffer upon return. */ struct rpcrdma_req * rpcrdma_buffer_get(struct rpcrdma_buffer *buffers) @@ -1009,13 +1007,13 @@ rpcrdma_buffer_get(struct rpcrdma_buffer *buffers) out_reqbuf: spin_unlock(&buffers->rb_lock); - pr_warn("RPC: %s: out of request buffers\n", __func__); + pr_warn("rpcrdma: out of request buffers (%p)\n", buffers); return NULL; out_repbuf: + list_add(&req->rl_free, &buffers->rb_send_bufs); spin_unlock(&buffers->rb_lock); - pr_warn("RPC: %s: out of reply buffers\n", __func__); - req->rl_reply = NULL; - return req; + pr_warn("rpcrdma: out of reply buffers (%p)\n", buffers); + return NULL; } /* -- cgit v1.1 From 7a89f9c626e337ba6528d8a2829b228c933877fb Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:53:43 -0400 Subject: xprtrdma: Honor ->send_request API contract Commit c93c62231cf5 ("xprtrdma: Disconnect on registration failure") added a disconnect for some RPC marshaling failures. This is needed only in a handful of cases, but it was triggering for simple stuff like temporary resource shortages. Try to straighten this out. Fix up the lower layers so they don't return -ENOMEM or other error codes that the RPC client's FSM doesn't explicitly recognize. Also fix up the places in the send_request path that do want a disconnect. For example, when ib_post_send or ib_post_recv fail, this is a sign that there is a send or receive queue resource miscalculation. That should be rare, and is a sign of a software bug. But xprtrdma can recover: disconnect to reset the transport and start over. Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/fmr_ops.c | 6 +++--- net/sunrpc/xprtrdma/frwr_ops.c | 13 +++++++------ net/sunrpc/xprtrdma/rpc_rdma.c | 2 +- net/sunrpc/xprtrdma/transport.c | 20 +++++++++++++++----- net/sunrpc/xprtrdma/verbs.c | 22 +++++++++++++--------- 5 files changed, 39 insertions(+), 24 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index 8b6ce8e..aae4c37 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -219,7 +219,7 @@ fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, rpcrdma_defer_mr_recovery(mw); mw = rpcrdma_get_mw(r_xprt); if (!mw) - return -ENOMEM; + return -ENOBUFS; pageoff = offset_in_page(seg1->mr_offset); seg1->mr_offset -= pageoff; /* start of page */ @@ -269,14 +269,14 @@ out_dmamap_err: pr_err("rpcrdma: failed to dma map sg %p sg_nents %u\n", mw->mw_sg, mw->mw_nents); rpcrdma_defer_mr_recovery(mw); - return -ENOMEM; + return -EIO; out_maperr: pr_err("rpcrdma: ib_map_phys_fmr %u@0x%llx+%i (%d) status %i\n", len, (unsigned long long)dma_pages[0], pageoff, mw->mw_nents, rc); rpcrdma_defer_mr_recovery(mw); - return rc; + return -EIO; } /* Invalidate all memory regions that were registered for "req". diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index fc2826b..d7613db9 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -382,7 +382,7 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, rpcrdma_defer_mr_recovery(mw); mw = rpcrdma_get_mw(r_xprt); if (!mw) - return -ENOMEM; + return -ENOBUFS; } while (mw->frmr.fr_state != FRMR_IS_INVALID); frmr = &mw->frmr; frmr->fr_state = FRMR_IS_VALID; @@ -456,18 +456,18 @@ out_dmamap_err: pr_err("rpcrdma: failed to dma map sg %p sg_nents %u\n", mw->mw_sg, mw->mw_nents); rpcrdma_defer_mr_recovery(mw); - return -ENOMEM; + return -EIO; out_mapmr_err: pr_err("rpcrdma: failed to map mr %p (%u/%u)\n", frmr->fr_mr, n, mw->mw_nents); - rc = n < 0 ? n : -EIO; rpcrdma_defer_mr_recovery(mw); - return rc; + return -EIO; out_senderr: + pr_err("rpcrdma: FRMR registration ib_post_send returned %i\n", rc); rpcrdma_defer_mr_recovery(mw); - return rc; + return -ENOTCONN; } static struct ib_send_wr * @@ -569,7 +569,8 @@ unmap: return; reset_mrs: - pr_warn("%s: ib_post_send failed %i\n", __func__, rc); + pr_err("rpcrdma: FRMR invalidate ib_post_send returned %i\n", rc); + rdma_disconnect(ia->ri_id); /* Find and reset the MRs in the LOCAL_INV WRs that did not * get posted. This is synchronous, and slow. diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 35a8109..77e002f 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -251,7 +251,7 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos, /* alloc the pagelist for receiving buffer */ ppages[p] = alloc_page(GFP_ATOMIC); if (!ppages[p]) - return -ENOMEM; + return -EAGAIN; } seg[n].mr_page = ppages[p]; seg[n].mr_offset = (void *)(unsigned long) page_base; diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 4c8e7f1..be4dd2c 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -558,7 +558,6 @@ out_sendbuf: out_fail: rpcrdma_buffer_put(req); - r_xprt->rx_stats.failed_marshal_count++; return NULL; } @@ -590,8 +589,19 @@ xprt_rdma_free(void *buffer) rpcrdma_buffer_put(req); } -/* +/** + * xprt_rdma_send_request - marshal and send an RPC request + * @task: RPC task with an RPC message in rq_snd_buf + * + * Return values: + * 0: The request has been sent + * ENOTCONN: Caller needs to invoke connect logic then call again + * ENOBUFS: Call again later to send the request + * EIO: A permanent error occurred. The request was not sent, + * and don't try it again + * * send_request invokes the meat of RPC RDMA. It must do the following: + * * 1. Marshal the RPC request into an RPC RDMA request, which means * putting a header in front of data, and creating IOVs for RDMA * from those in the request. @@ -600,7 +610,6 @@ xprt_rdma_free(void *buffer) * the request (rpcrdma_ep_post). * 4. No partial sends are possible in the RPC-RDMA protocol (as in UDP). */ - static int xprt_rdma_send_request(struct rpc_task *task) { @@ -630,11 +639,12 @@ xprt_rdma_send_request(struct rpc_task *task) return 0; failed_marshal: - r_xprt->rx_stats.failed_marshal_count++; dprintk("RPC: %s: rpcrdma_marshal_req failed, status %i\n", __func__, rc); if (rc == -EIO) - return -EIO; + r_xprt->rx_stats.failed_marshal_count++; + if (rc != -ENOTCONN) + return rc; drop_connection: xprt_disconnect_done(xprt); return -ENOTCONN; /* implies disconnect */ diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 6fb73ff..db935ed 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1151,7 +1151,7 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia, if (rep) { rc = rpcrdma_ep_post_recv(ia, ep, rep); if (rc) - goto out; + return rc; req->rl_reply = NULL; } @@ -1176,10 +1176,12 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia, rc = ib_post_send(ia->ri_id->qp, &send_wr, &send_wr_fail); if (rc) - dprintk("RPC: %s: ib_post_send returned %i\n", __func__, - rc); -out: - return rc; + goto out_postsend_err; + return 0; + +out_postsend_err: + pr_err("rpcrdma: RDMA Send ib_post_send returned %i\n", rc); + return -ENOTCONN; } /* @@ -1204,11 +1206,13 @@ rpcrdma_ep_post_recv(struct rpcrdma_ia *ia, DMA_BIDIRECTIONAL); rc = ib_post_recv(ia->ri_id->qp, &recv_wr, &recv_wr_fail); - if (rc) - dprintk("RPC: %s: ib_post_recv returned %i\n", __func__, - rc); - return rc; + goto out_postrecv; + return 0; + +out_postrecv: + pr_err("rpcrdma: ib_post_recv returned %i\n", rc); + return -ENOTCONN; } /** -- cgit v1.1 From a54d4059e5f356c522aabfd38563ab6e64773263 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:53:52 -0400 Subject: xprtrdma: Chunk list encoders must not return zero Clean up, based on code audit: Remove the possibility that the chunk list XDR encoders can return zero, which would be interpreted as a NULL. Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/fmr_ops.c | 2 ++ net/sunrpc/xprtrdma/frwr_ops.c | 2 ++ net/sunrpc/xprtrdma/rpc_rdma.c | 6 +++--- 3 files changed, 7 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index aae4c37..bc5f4a1 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -246,6 +246,8 @@ fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, } mw->mw_nents = i; mw->mw_dir = rpcrdma_data_dir(writing); + if (i == 0) + goto out_dmamap_err; if (!ib_dma_map_sg(r_xprt->rx_ia.ri_device, mw->mw_sg, mw->mw_nents, mw->mw_dir)) diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index d7613db9..f3a06fa 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -411,6 +411,8 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, } mw->mw_nents = i; mw->mw_dir = rpcrdma_data_dir(writing); + if (i == 0) + goto out_dmamap_err; dma_nents = ib_dma_map_sg(ia->ri_device, mw->mw_sg, mw->mw_nents, mw->mw_dir); diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 77e002f..8fde0ab 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -329,7 +329,7 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt, do { n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, false); - if (n <= 0) + if (n < 0) return ERR_PTR(n); *iptr++ = xdr_one; /* item present */ @@ -397,7 +397,7 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, nchunks = 0; do { n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, true); - if (n <= 0) + if (n < 0) return ERR_PTR(n); iptr = xdr_encode_rdma_segment(iptr, seg); @@ -462,7 +462,7 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt, nchunks = 0; do { n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, true); - if (n <= 0) + if (n < 0) return ERR_PTR(n); iptr = xdr_encode_rdma_segment(iptr, seg); -- cgit v1.1 From e2ac236c0b65129f12fef358390f76cc3cacb865 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:54:00 -0400 Subject: xprtrdma: Allocate MRs on demand Frequent MR list exhaustion can impact I/O throughput, so enough MRs are always created during transport set-up to prevent running out. This means more MRs are created than most workloads need. Commit 94f58c58c0b4 ("xprtrdma: Allow Read list and Reply chunk simultaneously") introduced support for sending two chunk lists per RPC, which consumes more MRs per RPC. Instead of trying to provision more MRs, introduce a mechanism for allocating MRs on demand. A few MRs are allocated during transport set-up to kick things off. This significantly reduces the average number of MRs per transport while allowing the MR count to grow for workloads or devices that need more MRs. FRWR with mlx4 allocated almost 400 MRs per transport before this patch. Now it starts with 32. Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/fmr_ops.c | 64 +++------------------------ net/sunrpc/xprtrdma/frwr_ops.c | 64 +++------------------------ net/sunrpc/xprtrdma/transport.c | 5 ++- net/sunrpc/xprtrdma/verbs.c | 98 ++++++++++++++++++++++++++++++++++++++--- net/sunrpc/xprtrdma/xprt_rdma.h | 7 ++- 5 files changed, 114 insertions(+), 124 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index bc5f4a1..758cd1a 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -46,7 +46,7 @@ fmr_is_supported(struct rpcrdma_ia *ia) } static int -__fmr_init(struct rpcrdma_mw *mw, struct ib_pd *pd) +fmr_op_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mw *mw) { static struct ib_fmr_attr fmr_attr = { .max_pages = RPCRDMA_MAX_FMR_SGES, @@ -66,7 +66,7 @@ __fmr_init(struct rpcrdma_mw *mw, struct ib_pd *pd) sg_init_table(mw->mw_sg, RPCRDMA_MAX_FMR_SGES); - mw->fmr.fm_mr = ib_alloc_fmr(pd, RPCRDMA_FMR_ACCESS_FLAGS, + mw->fmr.fm_mr = ib_alloc_fmr(ia->ri_pd, RPCRDMA_FMR_ACCESS_FLAGS, &fmr_attr); if (IS_ERR(mw->fmr.fm_mr)) goto out_fmr_err; @@ -96,7 +96,7 @@ __fmr_unmap(struct rpcrdma_mw *mw) } static void -__fmr_release(struct rpcrdma_mw *r) +fmr_op_release_mr(struct rpcrdma_mw *r) { LIST_HEAD(unmap_list); int rc; @@ -116,13 +116,11 @@ __fmr_release(struct rpcrdma_mw *r) if (rc) pr_err("rpcrdma: final ib_dealloc_fmr for %p returned %i\n", r, rc); + + kfree(r); } /* Reset of a single FMR. - * - * There's no recovery if this fails. The FMR is abandoned, but - * remains in rb_all. It will be cleaned up when the transport is - * destroyed. */ static void fmr_op_recover_mr(struct rpcrdma_mw *mw) @@ -166,41 +164,6 @@ fmr_op_maxpages(struct rpcrdma_xprt *r_xprt) RPCRDMA_MAX_HDR_SEGS * RPCRDMA_MAX_FMR_SGES); } -static int -fmr_op_init(struct rpcrdma_xprt *r_xprt) -{ - struct rpcrdma_buffer *buf = &r_xprt->rx_buf; - struct ib_pd *pd = r_xprt->rx_ia.ri_pd; - struct rpcrdma_mw *r; - int i, rc; - - spin_lock_init(&buf->rb_mwlock); - INIT_LIST_HEAD(&buf->rb_mws); - INIT_LIST_HEAD(&buf->rb_all); - - i = max_t(int, RPCRDMA_MAX_DATA_SEGS / RPCRDMA_MAX_FMR_SGES, 1); - i += 2; /* head + tail */ - i *= buf->rb_max_requests; /* one set for each RPC slot */ - dprintk("RPC: %s: initalizing %d FMRs\n", __func__, i); - - while (i--) { - r = kzalloc(sizeof(*r), GFP_KERNEL); - if (!r) - return -ENOMEM; - - rc = __fmr_init(r, pd); - if (rc) { - kfree(r); - return rc; - } - - r->mw_xprt = r_xprt; - list_add(&r->mw_list, &buf->rb_mws); - list_add(&r->mw_all, &buf->rb_all); - } - return 0; -} - /* Use the ib_map_phys_fmr() verb to register a memory region * for remote access via RDMA READ or RDMA WRITE. */ @@ -374,19 +337,6 @@ fmr_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, } } -static void -fmr_op_destroy(struct rpcrdma_buffer *buf) -{ - struct rpcrdma_mw *r; - - while (!list_empty(&buf->rb_all)) { - r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all); - list_del(&r->mw_all); - __fmr_release(r); - kfree(r); - } -} - const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops = { .ro_map = fmr_op_map, .ro_unmap_sync = fmr_op_unmap_sync, @@ -394,7 +344,7 @@ const struct rpcrdma_memreg_ops rpcrdma_fmr_memreg_ops = { .ro_recover_mr = fmr_op_recover_mr, .ro_open = fmr_op_open, .ro_maxpages = fmr_op_maxpages, - .ro_init = fmr_op_init, - .ro_destroy = fmr_op_destroy, + .ro_init_mr = fmr_op_init_mr, + .ro_release_mr = fmr_op_release_mr, .ro_displayname = "fmr", }; diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index f3a06fa..e77776b 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -91,12 +91,13 @@ out_not_supported: } static int -__frwr_init(struct rpcrdma_mw *r, struct ib_pd *pd, unsigned int depth) +frwr_op_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mw *r) { + unsigned int depth = ia->ri_max_frmr_depth; struct rpcrdma_frmr *f = &r->frmr; int rc; - f->fr_mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, depth); + f->fr_mr = ib_alloc_mr(ia->ri_pd, IB_MR_TYPE_MEM_REG, depth); if (IS_ERR(f->fr_mr)) goto out_mr_err; @@ -123,7 +124,7 @@ out_list_err: } static void -__frwr_release(struct rpcrdma_mw *r) +frwr_op_release_mr(struct rpcrdma_mw *r) { int rc; @@ -132,6 +133,7 @@ __frwr_release(struct rpcrdma_mw *r) pr_err("rpcrdma: final ib_dereg_mr for %p returned %i\n", r, rc); kfree(r->mw_sg); + kfree(r); } static int @@ -319,45 +321,6 @@ frwr_wc_localinv_wake(struct ib_cq *cq, struct ib_wc *wc) complete_all(&frmr->fr_linv_done); } -static int -frwr_op_init(struct rpcrdma_xprt *r_xprt) -{ - struct rpcrdma_buffer *buf = &r_xprt->rx_buf; - unsigned int depth = r_xprt->rx_ia.ri_max_frmr_depth; - struct ib_pd *pd = r_xprt->rx_ia.ri_pd; - int i; - - spin_lock_init(&buf->rb_mwlock); - INIT_LIST_HEAD(&buf->rb_mws); - INIT_LIST_HEAD(&buf->rb_all); - - i = max_t(int, RPCRDMA_MAX_DATA_SEGS / depth, 1); - i += 2; /* head + tail */ - i *= buf->rb_max_requests; /* one set for each RPC slot */ - dprintk("RPC: %s: initalizing %d FRMRs\n", __func__, i); - - while (i--) { - struct rpcrdma_mw *r; - int rc; - - r = kzalloc(sizeof(*r), GFP_KERNEL); - if (!r) - return -ENOMEM; - - rc = __frwr_init(r, pd, depth); - if (rc) { - kfree(r); - return rc; - } - - r->mw_xprt = r_xprt; - list_add(&r->mw_list, &buf->rb_mws); - list_add(&r->mw_all, &buf->rb_all); - } - - return 0; -} - /* Post a REG_MR Work Request to register a memory region * for remote access via RDMA READ or RDMA WRITE. */ @@ -618,19 +581,6 @@ frwr_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, } } -static void -frwr_op_destroy(struct rpcrdma_buffer *buf) -{ - struct rpcrdma_mw *r; - - while (!list_empty(&buf->rb_all)) { - r = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all); - list_del(&r->mw_all); - __frwr_release(r); - kfree(r); - } -} - const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops = { .ro_map = frwr_op_map, .ro_unmap_sync = frwr_op_unmap_sync, @@ -638,7 +588,7 @@ const struct rpcrdma_memreg_ops rpcrdma_frwr_memreg_ops = { .ro_recover_mr = frwr_op_recover_mr, .ro_open = frwr_op_open, .ro_maxpages = frwr_op_maxpages, - .ro_init = frwr_op_init, - .ro_destroy = frwr_op_destroy, + .ro_init_mr = frwr_op_init_mr, + .ro_release_mr = frwr_op_release_mr, .ro_displayname = "frwr", }; diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index be4dd2c..b1dd42a 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -682,9 +682,10 @@ void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) r_xprt->rx_stats.failed_marshal_count, r_xprt->rx_stats.bad_reply_count, r_xprt->rx_stats.nomsg_call_count); - seq_printf(seq, "%lu %lu\n", + seq_printf(seq, "%lu %lu %lu\n", r_xprt->rx_stats.mrs_recovered, - r_xprt->rx_stats.mrs_orphaned); + r_xprt->rx_stats.mrs_orphaned, + r_xprt->rx_stats.mrs_allocated); } static int diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index db935ed..e8677ea 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -782,6 +782,55 @@ rpcrdma_defer_mr_recovery(struct rpcrdma_mw *mw) schedule_delayed_work(&buf->rb_recovery_worker, 0); } +static void +rpcrdma_create_mrs(struct rpcrdma_xprt *r_xprt) +{ + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + struct rpcrdma_ia *ia = &r_xprt->rx_ia; + unsigned int count; + LIST_HEAD(free); + LIST_HEAD(all); + + for (count = 0; count < 32; count++) { + struct rpcrdma_mw *mw; + int rc; + + mw = kzalloc(sizeof(*mw), GFP_KERNEL); + if (!mw) + break; + + rc = ia->ri_ops->ro_init_mr(ia, mw); + if (rc) { + kfree(mw); + break; + } + + mw->mw_xprt = r_xprt; + + list_add(&mw->mw_list, &free); + list_add(&mw->mw_all, &all); + } + + spin_lock(&buf->rb_mwlock); + list_splice(&free, &buf->rb_mws); + list_splice(&all, &buf->rb_all); + r_xprt->rx_stats.mrs_allocated += count; + spin_unlock(&buf->rb_mwlock); + + dprintk("RPC: %s: created %u MRs\n", __func__, count); +} + +static void +rpcrdma_mr_refresh_worker(struct work_struct *work) +{ + struct rpcrdma_buffer *buf = container_of(work, struct rpcrdma_buffer, + rb_refresh_worker.work); + struct rpcrdma_xprt *r_xprt = container_of(buf, struct rpcrdma_xprt, + rx_buf); + + rpcrdma_create_mrs(r_xprt); +} + struct rpcrdma_req * rpcrdma_create_req(struct rpcrdma_xprt *r_xprt) { @@ -837,21 +886,23 @@ int rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) { struct rpcrdma_buffer *buf = &r_xprt->rx_buf; - struct rpcrdma_ia *ia = &r_xprt->rx_ia; int i, rc; buf->rb_max_requests = r_xprt->rx_data.max_requests; buf->rb_bc_srv_max_requests = 0; atomic_set(&buf->rb_credits, 1); + spin_lock_init(&buf->rb_mwlock); spin_lock_init(&buf->rb_lock); spin_lock_init(&buf->rb_recovery_lock); + INIT_LIST_HEAD(&buf->rb_mws); + INIT_LIST_HEAD(&buf->rb_all); INIT_LIST_HEAD(&buf->rb_stale_mrs); + INIT_DELAYED_WORK(&buf->rb_refresh_worker, + rpcrdma_mr_refresh_worker); INIT_DELAYED_WORK(&buf->rb_recovery_worker, rpcrdma_mr_recovery_worker); - rc = ia->ri_ops->ro_init(r_xprt); - if (rc) - goto out; + rpcrdma_create_mrs(r_xprt); INIT_LIST_HEAD(&buf->rb_send_bufs); INIT_LIST_HEAD(&buf->rb_allreqs); @@ -927,6 +978,32 @@ rpcrdma_destroy_req(struct rpcrdma_ia *ia, struct rpcrdma_req *req) kfree(req); } +static void +rpcrdma_destroy_mrs(struct rpcrdma_buffer *buf) +{ + struct rpcrdma_xprt *r_xprt = container_of(buf, struct rpcrdma_xprt, + rx_buf); + struct rpcrdma_ia *ia = rdmab_to_ia(buf); + struct rpcrdma_mw *mw; + unsigned int count; + + count = 0; + spin_lock(&buf->rb_mwlock); + while (!list_empty(&buf->rb_all)) { + mw = list_entry(buf->rb_all.next, struct rpcrdma_mw, mw_all); + list_del(&mw->mw_all); + + spin_unlock(&buf->rb_mwlock); + ia->ri_ops->ro_release_mr(mw); + count++; + spin_lock(&buf->rb_mwlock); + } + spin_unlock(&buf->rb_mwlock); + r_xprt->rx_stats.mrs_allocated = 0; + + dprintk("RPC: %s: released %u MRs\n", __func__, count); +} + void rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf) { @@ -955,7 +1032,7 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf) } spin_unlock(&buf->rb_reqslock); - ia->ri_ops->ro_destroy(buf); + rpcrdma_destroy_mrs(buf); } struct rpcrdma_mw * @@ -973,8 +1050,17 @@ rpcrdma_get_mw(struct rpcrdma_xprt *r_xprt) spin_unlock(&buf->rb_mwlock); if (!mw) - pr_err("RPC: %s: no MWs available\n", __func__); + goto out_nomws; return mw; + +out_nomws: + dprintk("RPC: %s: no MWs available\n", __func__); + schedule_delayed_work(&buf->rb_refresh_worker, 0); + + /* Allow the reply handler and refresh worker to run */ + cond_resched(); + + return NULL; } void diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 08d441d..649d01d 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -339,6 +339,7 @@ struct rpcrdma_buffer { spinlock_t rb_recovery_lock; /* protect rb_stale_mrs */ struct list_head rb_stale_mrs; struct delayed_work rb_recovery_worker; + struct delayed_work rb_refresh_worker; }; #define rdmab_to_ia(b) (&container_of((b), struct rpcrdma_xprt, rx_buf)->rx_ia) @@ -387,6 +388,7 @@ struct rpcrdma_stats { unsigned long bcall_count; unsigned long mrs_recovered; unsigned long mrs_orphaned; + unsigned long mrs_allocated; }; /* @@ -405,8 +407,9 @@ struct rpcrdma_memreg_ops { struct rpcrdma_ep *, struct rpcrdma_create_data_internal *); size_t (*ro_maxpages)(struct rpcrdma_xprt *); - int (*ro_init)(struct rpcrdma_xprt *); - void (*ro_destroy)(struct rpcrdma_buffer *); + int (*ro_init_mr)(struct rpcrdma_ia *, + struct rpcrdma_mw *); + void (*ro_release_mr)(struct rpcrdma_mw *); const char *ro_displayname; }; -- cgit v1.1 From 2ffc871a574daa760ef4f7750e0a36187a45754a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:54:08 -0400 Subject: xprtrdma: Release orphaned MRs immediately Instead of leaving orphaned MRs to be released when the transport is destroyed, release them immediately. The MR free list can now be replenished if it becomes exhausted. Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/fmr_ops.c | 19 +++++++++++++------ net/sunrpc/xprtrdma/frwr_ops.c | 19 +++++++++++++------ 2 files changed, 26 insertions(+), 12 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index 758cd1a..6521dce 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -134,15 +134,22 @@ fmr_op_recover_mr(struct rpcrdma_mw *mw) /* ORDER: then DMA unmap */ ib_dma_unmap_sg(r_xprt->rx_ia.ri_device, mw->mw_sg, mw->mw_nents, mw->mw_dir); - if (rc) { - pr_err("rpcrdma: FMR reset status %d, %p orphaned\n", - rc, mw); - r_xprt->rx_stats.mrs_orphaned++; - return; - } + if (rc) + goto out_release; rpcrdma_put_mw(r_xprt, mw); r_xprt->rx_stats.mrs_recovered++; + return; + +out_release: + pr_err("rpcrdma: FMR reset failed (%d), %p released\n", rc, mw); + r_xprt->rx_stats.mrs_orphaned++; + + spin_lock(&r_xprt->rx_buf.rb_mwlock); + list_del(&mw->mw_all); + spin_unlock(&r_xprt->rx_buf.rb_mwlock); + + fmr_op_release_mr(mw); } static int diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index e77776b..f4c06c8 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -177,15 +177,22 @@ frwr_op_recover_mr(struct rpcrdma_mw *mw) rc = __frwr_reset_mr(ia, mw); ib_dma_unmap_sg(ia->ri_device, mw->mw_sg, mw->mw_nents, mw->mw_dir); - if (rc) { - pr_err("rpcrdma: FRMR reset status %d, %p orphaned\n", - rc, mw); - r_xprt->rx_stats.mrs_orphaned++; - return; - } + if (rc) + goto out_release; rpcrdma_put_mw(r_xprt, mw); r_xprt->rx_stats.mrs_recovered++; + return; + +out_release: + pr_err("rpcrdma: FRMR reset failed %d, %p release\n", rc, mw); + r_xprt->rx_stats.mrs_orphaned++; + + spin_lock(&r_xprt->rx_buf.rb_mwlock); + list_del(&mw->mw_all); + spin_unlock(&r_xprt->rx_buf.rb_mwlock); + + frwr_op_release_mr(mw); } static int -- cgit v1.1 From 9d6b0409788287b64d8401ffba2ce11a5a86a879 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:54:16 -0400 Subject: xprtrdma: Place registered MWs on a per-req list Instead of placing registered MWs sparsely into the rl_segments array, place these MWs on a per-req list. ro_unmap_{sync,safe} can then simply pull those MWs off the list instead of walking through the array. This change significantly reduces the size of struct rpcrdma_req by removing nsegs and rl_mw from every array element. As an additional clean-up, chunk co-ordinates are returned in the "*mw" output argument so they are no longer needed in every array element. Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/fmr_ops.c | 65 +++++++++++---------------------- net/sunrpc/xprtrdma/frwr_ops.c | 72 +++++++++++++----------------------- net/sunrpc/xprtrdma/rpc_rdma.c | 81 +++++++++++++++++++---------------------- net/sunrpc/xprtrdma/transport.c | 3 ++ net/sunrpc/xprtrdma/verbs.c | 1 + net/sunrpc/xprtrdma/xprt_rdma.h | 11 +++--- 6 files changed, 94 insertions(+), 139 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index 6521dce..21cb3b1 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -101,6 +101,10 @@ fmr_op_release_mr(struct rpcrdma_mw *r) LIST_HEAD(unmap_list); int rc; + /* Ensure MW is not on any rl_registered list */ + if (!list_empty(&r->mw_list)) + list_del(&r->mw_list); + kfree(r->fmr.fm_physaddrs); kfree(r->mw_sg); @@ -176,17 +180,13 @@ fmr_op_maxpages(struct rpcrdma_xprt *r_xprt) */ static int fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, - int nsegs, bool writing) + int nsegs, bool writing, struct rpcrdma_mw **out) { struct rpcrdma_mr_seg *seg1 = seg; int len, pageoff, i, rc; struct rpcrdma_mw *mw; u64 *dma_pages; - mw = seg1->rl_mw; - seg1->rl_mw = NULL; - if (mw) - rpcrdma_defer_mr_recovery(mw); mw = rpcrdma_get_mw(r_xprt); if (!mw) return -ENOBUFS; @@ -230,11 +230,11 @@ fmr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, if (rc) goto out_maperr; - seg1->rl_mw = mw; - seg1->mr_rkey = mw->fmr.fm_mr->rkey; - seg1->mr_base = dma_pages[0] + pageoff; - seg1->mr_nsegs = mw->mw_nents; - seg1->mr_len = len; + mw->mw_handle = mw->fmr.fm_mr->rkey; + mw->mw_length = len; + mw->mw_offset = dma_pages[0] + pageoff; + + *out = mw; return mw->mw_nents; out_dmamap_err: @@ -255,13 +255,13 @@ out_maperr: * * Sleeps until it is safe for the host CPU to access the * previously mapped memory regions. + * + * Caller ensures that req->rl_registered is not empty. */ static void fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) { - struct rpcrdma_mr_seg *seg; - unsigned int i, nchunks; - struct rpcrdma_mw *mw; + struct rpcrdma_mw *mw, *tmp; LIST_HEAD(unmap_list); int rc; @@ -272,14 +272,8 @@ fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) * ib_unmap_fmr() is slow, so use a single call instead * of one call per mapped FMR. */ - for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) { - seg = &req->rl_segments[i]; - mw = seg->rl_mw; - + list_for_each_entry(mw, &req->rl_registered, mw_list) list_add_tail(&mw->fmr.fm_mr->list, &unmap_list); - - i += seg->mr_nsegs; - } rc = ib_unmap_fmr(&unmap_list); if (rc) goto out_reset; @@ -287,34 +281,22 @@ fmr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) /* ORDER: Now DMA unmap all of the req's MRs, and return * them to the free MW list. */ - for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) { - seg = &req->rl_segments[i]; - mw = seg->rl_mw; - + list_for_each_entry_safe(mw, tmp, &req->rl_registered, mw_list) { + list_del_init(&mw->mw_list); list_del_init(&mw->fmr.fm_mr->list); ib_dma_unmap_sg(r_xprt->rx_ia.ri_device, mw->mw_sg, mw->mw_nents, mw->mw_dir); rpcrdma_put_mw(r_xprt, mw); - - i += seg->mr_nsegs; - seg->mr_nsegs = 0; - seg->rl_mw = NULL; } - req->rl_nchunks = 0; return; out_reset: pr_err("rpcrdma: ib_unmap_fmr failed (%i)\n", rc); - for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) { - seg = &req->rl_segments[i]; - mw = seg->rl_mw; - + list_for_each_entry_safe(mw, tmp, &req->rl_registered, mw_list) { list_del_init(&mw->fmr.fm_mr->list); fmr_op_recover_mr(mw); - - i += seg->mr_nsegs; } } @@ -325,22 +307,17 @@ static void fmr_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, bool sync) { - struct rpcrdma_mr_seg *seg; struct rpcrdma_mw *mw; - unsigned int i; - for (i = 0; req->rl_nchunks; req->rl_nchunks--) { - seg = &req->rl_segments[i]; - mw = seg->rl_mw; + while (!list_empty(&req->rl_registered)) { + mw = list_first_entry(&req->rl_registered, + struct rpcrdma_mw, mw_list); + list_del_init(&mw->mw_list); if (sync) fmr_op_recover_mr(mw); else rpcrdma_defer_mr_recovery(mw); - - i += seg->mr_nsegs; - seg->mr_nsegs = 0; - seg->rl_mw = NULL; } } diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index f4c06c8..892b5e1 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -128,6 +128,10 @@ frwr_op_release_mr(struct rpcrdma_mw *r) { int rc; + /* Ensure MW is not on any rl_registered list */ + if (!list_empty(&r->mw_list)) + list_del(&r->mw_list); + rc = ib_dereg_mr(r->frmr.fr_mr); if (rc) pr_err("rpcrdma: final ib_dereg_mr for %p returned %i\n", @@ -333,10 +337,9 @@ frwr_wc_localinv_wake(struct ib_cq *cq, struct ib_wc *wc) */ static int frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, - int nsegs, bool writing) + int nsegs, bool writing, struct rpcrdma_mw **out) { struct rpcrdma_ia *ia = &r_xprt->rx_ia; - struct rpcrdma_mr_seg *seg1 = seg; struct rpcrdma_mw *mw; struct rpcrdma_frmr *frmr; struct ib_mr *mr; @@ -345,8 +348,7 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, int rc, i, n, dma_nents; u8 key; - mw = seg1->rl_mw; - seg1->rl_mw = NULL; + mw = NULL; do { if (mw) rpcrdma_defer_mr_recovery(mw); @@ -416,12 +418,11 @@ frwr_op_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr_seg *seg, if (rc) goto out_senderr; - seg1->rl_mw = mw; - seg1->mr_rkey = mr->rkey; - seg1->mr_base = mr->iova; - seg1->mr_nsegs = mw->mw_nents; - seg1->mr_len = mr->length; + mw->mw_handle = mr->rkey; + mw->mw_length = mr->length; + mw->mw_offset = mr->iova; + *out = mw; return mw->mw_nents; out_dmamap_err: @@ -443,9 +444,8 @@ out_senderr: } static struct ib_send_wr * -__frwr_prepare_linv_wr(struct rpcrdma_mr_seg *seg) +__frwr_prepare_linv_wr(struct rpcrdma_mw *mw) { - struct rpcrdma_mw *mw = seg->rl_mw; struct rpcrdma_frmr *f = &mw->frmr; struct ib_send_wr *invalidate_wr; @@ -465,16 +465,16 @@ __frwr_prepare_linv_wr(struct rpcrdma_mr_seg *seg) * * Sleeps until it is safe for the host CPU to access the * previously mapped memory regions. + * + * Caller ensures that req->rl_registered is not empty. */ static void frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) { struct ib_send_wr *invalidate_wrs, *pos, *prev, *bad_wr; struct rpcrdma_ia *ia = &r_xprt->rx_ia; - struct rpcrdma_mr_seg *seg; - unsigned int i, nchunks; + struct rpcrdma_mw *mw, *tmp; struct rpcrdma_frmr *f; - struct rpcrdma_mw *mw; int rc; dprintk("RPC: %s: req %p\n", __func__, req); @@ -484,22 +484,18 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) * Chain the LOCAL_INV Work Requests and post them with * a single ib_post_send() call. */ + f = NULL; invalidate_wrs = pos = prev = NULL; - seg = NULL; - for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) { - seg = &req->rl_segments[i]; - - pos = __frwr_prepare_linv_wr(seg); + list_for_each_entry(mw, &req->rl_registered, mw_list) { + pos = __frwr_prepare_linv_wr(mw); if (!invalidate_wrs) invalidate_wrs = pos; else prev->next = pos; prev = pos; - - i += seg->mr_nsegs; + f = &mw->frmr; } - f = &seg->rl_mw->frmr; /* Strong send queue ordering guarantees that when the * last WR in the chain completes, all WRs in the chain @@ -524,20 +520,12 @@ frwr_op_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req) * them to the free MW list. */ unmap: - for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) { - seg = &req->rl_segments[i]; - mw = seg->rl_mw; - seg->rl_mw = NULL; - + list_for_each_entry_safe(mw, tmp, &req->rl_registered, mw_list) { + list_del_init(&mw->mw_list); ib_dma_unmap_sg(ia->ri_device, mw->mw_sg, mw->mw_nents, mw->mw_dir); rpcrdma_put_mw(r_xprt, mw); - - i += seg->mr_nsegs; - seg->mr_nsegs = 0; } - - req->rl_nchunks = 0; return; reset_mrs: @@ -547,17 +535,12 @@ reset_mrs: /* Find and reset the MRs in the LOCAL_INV WRs that did not * get posted. This is synchronous, and slow. */ - for (i = 0, nchunks = req->rl_nchunks; nchunks; nchunks--) { - seg = &req->rl_segments[i]; - mw = seg->rl_mw; + list_for_each_entry(mw, &req->rl_registered, mw_list) { f = &mw->frmr; - if (mw->frmr.fr_mr->rkey == bad_wr->ex.invalidate_rkey) { __frwr_reset_mr(ia, mw); bad_wr = bad_wr->next; } - - i += seg->mr_nsegs; } goto unmap; } @@ -569,22 +552,17 @@ static void frwr_op_unmap_safe(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, bool sync) { - struct rpcrdma_mr_seg *seg; struct rpcrdma_mw *mw; - unsigned int i; - for (i = 0; req->rl_nchunks; req->rl_nchunks--) { - seg = &req->rl_segments[i]; - mw = seg->rl_mw; + while (!list_empty(&req->rl_registered)) { + mw = list_first_entry(&req->rl_registered, + struct rpcrdma_mw, mw_list); + list_del_init(&mw->mw_list); if (sync) frwr_op_recover_mr(mw); else rpcrdma_defer_mr_recovery(mw); - - i += seg->mr_nsegs; - seg->mr_nsegs = 0; - seg->rl_mw = NULL; } } diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 8fde0ab..6d34c1f 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -286,11 +286,11 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos, } static inline __be32 * -xdr_encode_rdma_segment(__be32 *iptr, struct rpcrdma_mr_seg *seg) +xdr_encode_rdma_segment(__be32 *iptr, struct rpcrdma_mw *mw) { - *iptr++ = cpu_to_be32(seg->mr_rkey); - *iptr++ = cpu_to_be32(seg->mr_len); - return xdr_encode_hyper(iptr, seg->mr_base); + *iptr++ = cpu_to_be32(mw->mw_handle); + *iptr++ = cpu_to_be32(mw->mw_length); + return xdr_encode_hyper(iptr, mw->mw_offset); } /* XDR-encode the Read list. Supports encoding a list of read @@ -311,6 +311,7 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt, __be32 *iptr, enum rpcrdma_chunktype rtype) { struct rpcrdma_mr_seg *seg = req->rl_nextseg; + struct rpcrdma_mw *mw; unsigned int pos; int n, nsegs; @@ -328,9 +329,11 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt, return ERR_PTR(nsegs); do { - n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, false); + n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, + false, &mw); if (n < 0) return ERR_PTR(n); + list_add(&mw->mw_list, &req->rl_registered); *iptr++ = xdr_one; /* item present */ @@ -338,13 +341,12 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt, * have the same "position". */ *iptr++ = cpu_to_be32(pos); - iptr = xdr_encode_rdma_segment(iptr, seg); + iptr = xdr_encode_rdma_segment(iptr, mw); - dprintk("RPC: %5u %s: read segment pos %u " - "%d@0x%016llx:0x%08x (%s)\n", + dprintk("RPC: %5u %s: pos %u %u@0x%016llx:0x%08x (%s)\n", rqst->rq_task->tk_pid, __func__, pos, - seg->mr_len, (unsigned long long)seg->mr_base, - seg->mr_rkey, n < nsegs ? "more" : "last"); + mw->mw_length, (unsigned long long)mw->mw_offset, + mw->mw_handle, n < nsegs ? "more" : "last"); r_xprt->rx_stats.read_chunk_count++; req->rl_nchunks++; @@ -376,6 +378,7 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, enum rpcrdma_chunktype wtype) { struct rpcrdma_mr_seg *seg = req->rl_nextseg; + struct rpcrdma_mw *mw; int n, nsegs, nchunks; __be32 *segcount; @@ -396,17 +399,18 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, nchunks = 0; do { - n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, true); + n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, + true, &mw); if (n < 0) return ERR_PTR(n); + list_add(&mw->mw_list, &req->rl_registered); - iptr = xdr_encode_rdma_segment(iptr, seg); + iptr = xdr_encode_rdma_segment(iptr, mw); - dprintk("RPC: %5u %s: write segment " - "%d@0x016%llx:0x%08x (%s)\n", + dprintk("RPC: %5u %s: %u@0x016%llx:0x%08x (%s)\n", rqst->rq_task->tk_pid, __func__, - seg->mr_len, (unsigned long long)seg->mr_base, - seg->mr_rkey, n < nsegs ? "more" : "last"); + mw->mw_length, (unsigned long long)mw->mw_offset, + mw->mw_handle, n < nsegs ? "more" : "last"); r_xprt->rx_stats.write_chunk_count++; r_xprt->rx_stats.total_rdma_request += seg->mr_len; @@ -443,6 +447,7 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt, __be32 *iptr, enum rpcrdma_chunktype wtype) { struct rpcrdma_mr_seg *seg = req->rl_nextseg; + struct rpcrdma_mw *mw; int n, nsegs, nchunks; __be32 *segcount; @@ -461,17 +466,18 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt, nchunks = 0; do { - n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, true); + n = r_xprt->rx_ia.ri_ops->ro_map(r_xprt, seg, nsegs, + true, &mw); if (n < 0) return ERR_PTR(n); + list_add(&mw->mw_list, &req->rl_registered); - iptr = xdr_encode_rdma_segment(iptr, seg); + iptr = xdr_encode_rdma_segment(iptr, mw); - dprintk("RPC: %5u %s: reply segment " - "%d@0x%016llx:0x%08x (%s)\n", + dprintk("RPC: %5u %s: %u@0x%016llx:0x%08x (%s)\n", rqst->rq_task->tk_pid, __func__, - seg->mr_len, (unsigned long long)seg->mr_base, - seg->mr_rkey, n < nsegs ? "more" : "last"); + mw->mw_length, (unsigned long long)mw->mw_offset, + mw->mw_handle, n < nsegs ? "more" : "last"); r_xprt->rx_stats.reply_chunk_count++; r_xprt->rx_stats.total_rdma_request += seg->mr_len; @@ -690,10 +696,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) out_overflow: pr_err("rpcrdma: send overflow: hdrlen %zd rpclen %zu %s/%s\n", hdrlen, rpclen, transfertypes[rtype], transfertypes[wtype]); - /* Terminate this RPC. Chunks registered above will be - * released by xprt_release -> xprt_rmda_free . - */ - return -EIO; + iptr = ERR_PTR(-EIO); out_unmap: r_xprt->rx_ia.ri_ops->ro_unmap_safe(r_xprt, req, false); @@ -705,15 +708,13 @@ out_unmap: * RDMA'd by server. See map at rpcrdma_create_chunks()! :-) */ static int -rpcrdma_count_chunks(struct rpcrdma_rep *rep, unsigned int max, int wrchunk, __be32 **iptrp) +rpcrdma_count_chunks(struct rpcrdma_rep *rep, int wrchunk, __be32 **iptrp) { unsigned int i, total_len; struct rpcrdma_write_chunk *cur_wchunk; char *base = (char *)rdmab_to_msg(rep->rr_rdmabuf); i = be32_to_cpu(**iptrp); - if (i > max) - return -1; cur_wchunk = (struct rpcrdma_write_chunk *) (*iptrp + 1); total_len = 0; while (i--) { @@ -960,14 +961,13 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep) (headerp->rm_body.rm_chunks[1] == xdr_zero && headerp->rm_body.rm_chunks[2] != xdr_zero) || (headerp->rm_body.rm_chunks[1] != xdr_zero && - req->rl_nchunks == 0)) + list_empty(&req->rl_registered))) goto badheader; if (headerp->rm_body.rm_chunks[1] != xdr_zero) { /* count any expected write chunks in read reply */ /* start at write chunk array count */ iptr = &headerp->rm_body.rm_chunks[2]; - rdmalen = rpcrdma_count_chunks(rep, - req->rl_nchunks, 1, &iptr); + rdmalen = rpcrdma_count_chunks(rep, 1, &iptr); /* check for validity, and no reply chunk after */ if (rdmalen < 0 || *iptr++ != xdr_zero) goto badheader; @@ -997,11 +997,11 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep) if (headerp->rm_body.rm_chunks[0] != xdr_zero || headerp->rm_body.rm_chunks[1] != xdr_zero || headerp->rm_body.rm_chunks[2] != xdr_one || - req->rl_nchunks == 0) + list_empty(&req->rl_registered)) goto badheader; iptr = (__be32 *)((unsigned char *)headerp + RPCRDMA_HDRLEN_MIN); - rdmalen = rpcrdma_count_chunks(rep, req->rl_nchunks, 0, &iptr); + rdmalen = rpcrdma_count_chunks(rep, 0, &iptr); if (rdmalen < 0) goto badheader; r_xprt->rx_stats.total_rdma_reply += rdmalen; @@ -1014,14 +1014,9 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep) badheader: default: - dprintk("%s: invalid rpcrdma reply header (type %d):" - " chunks[012] == %d %d %d" - " expected chunks <= %d\n", - __func__, be32_to_cpu(headerp->rm_type), - headerp->rm_body.rm_chunks[0], - headerp->rm_body.rm_chunks[1], - headerp->rm_body.rm_chunks[2], - req->rl_nchunks); + dprintk("RPC: %5u %s: invalid rpcrdma reply (type %u)\n", + rqst->rq_task->tk_pid, __func__, + be32_to_cpu(headerp->rm_type)); status = -EIO; r_xprt->rx_stats.bad_reply_count++; break; @@ -1035,7 +1030,7 @@ out: * control: waking the next RPC waits until this RPC has * relinquished all its Send Queue entries. */ - if (req->rl_nchunks) + if (!list_empty(&req->rl_registered)) r_xprt->rx_ia.ri_ops->ro_unmap_sync(r_xprt, req); spin_lock_bh(&xprt->transport_lock); diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index b1dd42a..81f0e87 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -619,6 +619,9 @@ xprt_rdma_send_request(struct rpc_task *task) struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); int rc = 0; + /* On retransmit, remove any previously registered chunks */ + r_xprt->rx_ia.ri_ops->ro_unmap_safe(r_xprt, req, false); + rc = rpcrdma_marshal_req(rqst); if (rc < 0) goto failed_marshal; diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index e8677ea..a74d79d 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -847,6 +847,7 @@ rpcrdma_create_req(struct rpcrdma_xprt *r_xprt) spin_unlock(&buffer->rb_reqslock); req->rl_cqe.done = rpcrdma_wc_send; req->rl_buffer = &r_xprt->rx_buf; + INIT_LIST_HEAD(&req->rl_registered); return req; } diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 649d01d..f5d0511 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -245,6 +245,9 @@ struct rpcrdma_mw { struct rpcrdma_frmr frmr; }; struct rpcrdma_xprt *mw_xprt; + u32 mw_handle; + u32 mw_length; + u64 mw_offset; struct list_head mw_all; }; @@ -272,11 +275,7 @@ struct rpcrdma_mw { */ struct rpcrdma_mr_seg { /* chunk descriptors */ - struct rpcrdma_mw *rl_mw; /* registered MR */ - u64 mr_base; /* registration result */ - u32 mr_rkey; /* registration result */ u32 mr_len; /* length of chunk or segment */ - int mr_nsegs; /* number of segments in chunk or 0 */ struct page *mr_page; /* owning page, if any */ char *mr_offset; /* kva if no page, else offset */ }; @@ -294,6 +293,7 @@ struct rpcrdma_req { struct ib_sge rl_send_iov[RPCRDMA_MAX_IOVS]; struct rpcrdma_regbuf *rl_rdmabuf; struct rpcrdma_regbuf *rl_sendbuf; + struct list_head rl_registered; /* registered segments */ struct rpcrdma_mr_seg rl_segments[RPCRDMA_MAX_SEGS]; struct rpcrdma_mr_seg *rl_nextseg; @@ -397,7 +397,8 @@ struct rpcrdma_stats { struct rpcrdma_xprt; struct rpcrdma_memreg_ops { int (*ro_map)(struct rpcrdma_xprt *, - struct rpcrdma_mr_seg *, int, bool); + struct rpcrdma_mr_seg *, int, bool, + struct rpcrdma_mw **); void (*ro_unmap_sync)(struct rpcrdma_xprt *, struct rpcrdma_req *); void (*ro_unmap_safe)(struct rpcrdma_xprt *, -- cgit v1.1 From 5ab8142839c714ed5ac9a9de1846ab71f87a3ed7 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:54:25 -0400 Subject: xprtrdma: Chunk list encoders no longer share one rl_segments array Currently, all three chunk list encoders each use a portion of the one rl_segments array in rpcrdma_req. This is because the MWs for each chunk list were preserved in rl_segments so that ro_unmap could find and invalidate them after the RPC was complete. However, now that MWs are placed on a per-req linked list as they are registered, there is no longer any information in rpcrdma_mr_seg that is shared between ro_map and ro_unmap_{sync,safe}, and thus nothing in rl_segments needs to be preserved after rpcrdma_marshal_req is complete. Thus the rl_segments array can be used now just for the needs of each rpcrdma_convert_iovs call. Once each chunk list is encoded, the next chunk list encoder is free to re-use all of rl_segments. This means all three chunk lists in one RPC request can now each encode a full size data payload with no increase in the size of rl_segments. This is a key requirement for Kerberos support, since both the Call and Reply for a single RPC transaction are conveyed via Long messages (RDMA Read/Write). Both can be large. Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/rpc_rdma.c | 61 +++++++++++++++++++---------------------- net/sunrpc/xprtrdma/xprt_rdma.h | 36 +++++++++++------------- 2 files changed, 44 insertions(+), 53 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 6d34c1f..f60d229 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -196,8 +196,7 @@ rpcrdma_tail_pullup(struct xdr_buf *buf) * MR when they can. */ static int -rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg, - int n, int nsegs) +rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg, int n) { size_t page_offset; u32 remaining; @@ -206,7 +205,7 @@ rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg, base = vec->iov_base; page_offset = offset_in_page(base); remaining = vec->iov_len; - while (remaining && n < nsegs) { + while (remaining && n < RPCRDMA_MAX_SEGS) { seg[n].mr_page = NULL; seg[n].mr_offset = base; seg[n].mr_len = min_t(u32, PAGE_SIZE - page_offset, remaining); @@ -230,23 +229,23 @@ rpcrdma_convert_kvec(struct kvec *vec, struct rpcrdma_mr_seg *seg, static int rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos, - enum rpcrdma_chunktype type, struct rpcrdma_mr_seg *seg, int nsegs) + enum rpcrdma_chunktype type, struct rpcrdma_mr_seg *seg) { - int len, n = 0, p; - int page_base; + int len, n, p, page_base; struct page **ppages; + n = 0; if (pos == 0) { - n = rpcrdma_convert_kvec(&xdrbuf->head[0], seg, n, nsegs); - if (n == nsegs) - return -EIO; + n = rpcrdma_convert_kvec(&xdrbuf->head[0], seg, n); + if (n == RPCRDMA_MAX_SEGS) + goto out_overflow; } len = xdrbuf->page_len; ppages = xdrbuf->pages + (xdrbuf->page_base >> PAGE_SHIFT); page_base = xdrbuf->page_base & ~PAGE_MASK; p = 0; - while (len && n < nsegs) { + while (len && n < RPCRDMA_MAX_SEGS) { if (!ppages[p]) { /* alloc the pagelist for receiving buffer */ ppages[p] = alloc_page(GFP_ATOMIC); @@ -257,7 +256,7 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos, seg[n].mr_offset = (void *)(unsigned long) page_base; seg[n].mr_len = min_t(u32, PAGE_SIZE - page_base, len); if (seg[n].mr_len > PAGE_SIZE) - return -EIO; + goto out_overflow; len -= seg[n].mr_len; ++n; ++p; @@ -265,8 +264,8 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos, } /* Message overflows the seg array */ - if (len && n == nsegs) - return -EIO; + if (len && n == RPCRDMA_MAX_SEGS) + goto out_overflow; /* When encoding the read list, the tail is always sent inline */ if (type == rpcrdma_readch) @@ -277,12 +276,16 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos, * xdr pad bytes, saving the server an RDMA operation. */ if (xdrbuf->tail[0].iov_len < 4 && xprt_rdma_pad_optimize) return n; - n = rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, n, nsegs); - if (n == nsegs) - return -EIO; + n = rpcrdma_convert_kvec(&xdrbuf->tail[0], seg, n); + if (n == RPCRDMA_MAX_SEGS) + goto out_overflow; } return n; + +out_overflow: + pr_err("rpcrdma: segment array overflow\n"); + return -EIO; } static inline __be32 * @@ -310,7 +313,7 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, struct rpc_rqst *rqst, __be32 *iptr, enum rpcrdma_chunktype rtype) { - struct rpcrdma_mr_seg *seg = req->rl_nextseg; + struct rpcrdma_mr_seg *seg; struct rpcrdma_mw *mw; unsigned int pos; int n, nsegs; @@ -323,8 +326,8 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt, pos = rqst->rq_snd_buf.head[0].iov_len; if (rtype == rpcrdma_areadch) pos = 0; - nsegs = rpcrdma_convert_iovs(&rqst->rq_snd_buf, pos, rtype, seg, - RPCRDMA_MAX_SEGS - req->rl_nchunks); + seg = req->rl_segments; + nsegs = rpcrdma_convert_iovs(&rqst->rq_snd_buf, pos, rtype, seg); if (nsegs < 0) return ERR_PTR(nsegs); @@ -349,11 +352,9 @@ rpcrdma_encode_read_list(struct rpcrdma_xprt *r_xprt, mw->mw_handle, n < nsegs ? "more" : "last"); r_xprt->rx_stats.read_chunk_count++; - req->rl_nchunks++; seg += n; nsegs -= n; } while (nsegs); - req->rl_nextseg = seg; /* Finish Read list */ *iptr++ = xdr_zero; /* Next item not present */ @@ -377,7 +378,7 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, struct rpc_rqst *rqst, __be32 *iptr, enum rpcrdma_chunktype wtype) { - struct rpcrdma_mr_seg *seg = req->rl_nextseg; + struct rpcrdma_mr_seg *seg; struct rpcrdma_mw *mw; int n, nsegs, nchunks; __be32 *segcount; @@ -387,10 +388,10 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, return iptr; } + seg = req->rl_segments; nsegs = rpcrdma_convert_iovs(&rqst->rq_rcv_buf, rqst->rq_rcv_buf.head[0].iov_len, - wtype, seg, - RPCRDMA_MAX_SEGS - req->rl_nchunks); + wtype, seg); if (nsegs < 0) return ERR_PTR(nsegs); @@ -414,12 +415,10 @@ rpcrdma_encode_write_list(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, r_xprt->rx_stats.write_chunk_count++; r_xprt->rx_stats.total_rdma_request += seg->mr_len; - req->rl_nchunks++; nchunks++; seg += n; nsegs -= n; } while (nsegs); - req->rl_nextseg = seg; /* Update count of segments in this Write chunk */ *segcount = cpu_to_be32(nchunks); @@ -446,7 +445,7 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, struct rpc_rqst *rqst, __be32 *iptr, enum rpcrdma_chunktype wtype) { - struct rpcrdma_mr_seg *seg = req->rl_nextseg; + struct rpcrdma_mr_seg *seg; struct rpcrdma_mw *mw; int n, nsegs, nchunks; __be32 *segcount; @@ -456,8 +455,8 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt, return iptr; } - nsegs = rpcrdma_convert_iovs(&rqst->rq_rcv_buf, 0, wtype, seg, - RPCRDMA_MAX_SEGS - req->rl_nchunks); + seg = req->rl_segments; + nsegs = rpcrdma_convert_iovs(&rqst->rq_rcv_buf, 0, wtype, seg); if (nsegs < 0) return ERR_PTR(nsegs); @@ -481,12 +480,10 @@ rpcrdma_encode_reply_chunk(struct rpcrdma_xprt *r_xprt, r_xprt->rx_stats.reply_chunk_count++; r_xprt->rx_stats.total_rdma_request += seg->mr_len; - req->rl_nchunks++; nchunks++; seg += n; nsegs -= n; } while (nsegs); - req->rl_nextseg = seg; /* Update count of segments in the Reply chunk */ *segcount = cpu_to_be32(nchunks); @@ -656,8 +653,6 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) * send a Call message with a Position Zero Read chunk and a * regular Read chunk at the same time. */ - req->rl_nchunks = 0; - req->rl_nextseg = req->rl_segments; iptr = headerp->rm_body.rm_chunks; iptr = rpcrdma_encode_read_list(r_xprt, req, rqst, iptr, rtype); if (IS_ERR(iptr)) diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index f5d0511..670fad5 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -171,23 +171,14 @@ rdmab_to_msg(struct rpcrdma_regbuf *rb) * o recv buffer (posted to provider) * o ib_sge (also donated to provider) * o status of reply (length, success or not) - * o bookkeeping state to get run by tasklet (list, etc) + * o bookkeeping state to get run by reply handler (list, etc) * - * These are allocated during initialization, per-transport instance; - * however, the tasklet execution list itself is global, as it should - * always be pretty short. + * These are allocated during initialization, per-transport instance. * * N of these are associated with a transport instance, and stored in * struct rpcrdma_buffer. N is the max number of outstanding requests. */ -#define RPCRDMA_MAX_DATA_SEGS ((1 * 1024 * 1024) / PAGE_SIZE) - -/* data segments + head/tail for Call + head/tail for Reply */ -#define RPCRDMA_MAX_SEGS (RPCRDMA_MAX_DATA_SEGS + 4) - -struct rpcrdma_buffer; - struct rpcrdma_rep { struct ib_cqe rr_cqe; unsigned int rr_len; @@ -267,13 +258,18 @@ struct rpcrdma_mw { * of iovs for send operations. The reason is that the iovs passed to * ib_post_{send,recv} must not be modified until the work request * completes. - * - * NOTES: - * o RPCRDMA_MAX_SEGS is the max number of addressible chunk elements we - * marshal. The number needed varies depending on the iov lists that - * are passed to us and the memory registration mode we are in. */ +/* Maximum number of page-sized "segments" per chunk list to be + * registered or invalidated. Must handle a Reply chunk: + */ +enum { + RPCRDMA_MAX_IOV_SEGS = 3, + RPCRDMA_MAX_DATA_SEGS = ((1 * 1024 * 1024) / PAGE_SIZE) + 1, + RPCRDMA_MAX_SEGS = RPCRDMA_MAX_DATA_SEGS + + RPCRDMA_MAX_IOV_SEGS, +}; + struct rpcrdma_mr_seg { /* chunk descriptors */ u32 mr_len; /* length of chunk or segment */ struct page *mr_page; /* owning page, if any */ @@ -282,10 +278,10 @@ struct rpcrdma_mr_seg { /* chunk descriptors */ #define RPCRDMA_MAX_IOVS (2) +struct rpcrdma_buffer; struct rpcrdma_req { struct list_head rl_free; unsigned int rl_niovs; - unsigned int rl_nchunks; unsigned int rl_connect_cookie; struct rpc_task *rl_task; struct rpcrdma_buffer *rl_buffer; @@ -293,13 +289,13 @@ struct rpcrdma_req { struct ib_sge rl_send_iov[RPCRDMA_MAX_IOVS]; struct rpcrdma_regbuf *rl_rdmabuf; struct rpcrdma_regbuf *rl_sendbuf; - struct list_head rl_registered; /* registered segments */ - struct rpcrdma_mr_seg rl_segments[RPCRDMA_MAX_SEGS]; - struct rpcrdma_mr_seg *rl_nextseg; struct ib_cqe rl_cqe; struct list_head rl_all; bool rl_backchannel; + + struct list_head rl_registered; /* registered segments */ + struct rpcrdma_mr_seg rl_segments[RPCRDMA_MAX_SEGS]; }; static inline struct rpcrdma_req * -- cgit v1.1 From 80414abc2848f43690c8402a77d37710ad0020c2 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:54:33 -0400 Subject: xprtrdma: rpcrdma_inline_fixup() overruns the receive page list When the remaining length of an incoming reply is longer than the XDR buf's page_len, switch over to the tail iovec instead of copying more than page_len bytes into the page list. Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/rpc_rdma.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index f60d229..e3560c2 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -773,12 +773,17 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) page_base &= ~PAGE_MASK; if (copy_len && rqst->rq_rcv_buf.page_len) { - npages = PAGE_ALIGN(page_base + - rqst->rq_rcv_buf.page_len) >> PAGE_SHIFT; + int pagelist_len; + + pagelist_len = rqst->rq_rcv_buf.page_len; + if (pagelist_len > copy_len) + pagelist_len = copy_len; + npages = PAGE_ALIGN(page_base + pagelist_len) >> PAGE_SHIFT; for (; i < npages; i++) { curlen = PAGE_SIZE - page_base; - if (curlen > copy_len) - curlen = copy_len; + if (curlen > pagelist_len) + curlen = pagelist_len; + dprintk("RPC: %s: page %d" " srcp 0x%p len %d curlen %d\n", __func__, i, srcp, copy_len, curlen); @@ -788,7 +793,8 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) kunmap_atomic(destp); srcp += curlen; copy_len -= curlen; - if (copy_len == 0) + pagelist_len -= curlen; + if (!pagelist_len) break; page_base = 0; } -- cgit v1.1 From cb0ae1fbb2f5e0cec250ba19c0525dde2b6c0160 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:54:41 -0400 Subject: xprtrdma: Do not update {head, tail}.iov_len in rpcrdma_inline_fixup() While trying NFSv4.0/RDMA with sec=krb5p, I noticed small NFS READ operations failed. After the client unwrapped the NFS READ reply message, the NFS READ XDR decoder was not able to decode the reply. The message was "Server cheating in reply", with the reported number of received payload bytes being zero. Applications reported a read(2) that returned -1/EIO. The problem is rpcrdma_inline_fixup() sets the tail.iov_len to zero when the incoming reply fits entirely in the head iovec. The zero tail.iov_len confused xdr_buf_trim(), which then mangled the actual reply data instead of simply removing the trailing GSS checksum. As near as I can tell, RPC transports are not supposed to update the head.iov_len, page_len, or tail.iov_len fields in the receive XDR buffer when handling an incoming RPC reply message. These fields contain the length of each component of the XDR buffer, and hence the maximum number of bytes of reply data that can be stored in each XDR buffer component. I've concluded this because: - This is how xdr_partial_copy_from_skb() appears to behave - rpcrdma_inline_fixup() already does not alter page_len - call_decode() compares rq_private_buf and rq_rcv_buf and WARNs if they are not exactly the same Unfortunately, as soon as I tried the simple fix to just remove the line that sets tail.iov_len to zero, I saw that the logic that appends the implicit Write chunk pad inline depends on inline_fixup setting tail.iov_len to zero. To address this, re-organize the tail iovec handling logic to use the same approach as with the head iovec: simply point tail.iov_base to the correct bytes in the receive buffer. While I remember all this, write down the conclusion in documenting comments. Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/rpc_rdma.c | 61 +++++++++++++++++++++++------------------- 1 file changed, 33 insertions(+), 28 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index e3560c2..d018eb7 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -740,8 +740,16 @@ rpcrdma_count_chunks(struct rpcrdma_rep *rep, int wrchunk, __be32 **iptrp) return total_len; } -/* - * Scatter inline received data back into provided iov's. +/** + * rpcrdma_inline_fixup - Scatter inline received data into rqst's iovecs + * @rqst: controlling RPC request + * @srcp: points to RPC message payload in receive buffer + * @copy_len: remaining length of receive buffer content + * @pad: Write chunk pad bytes needed (zero for pure inline) + * + * The upper layer has set the maximum number of bytes it can + * receive in each component of rq_rcv_buf. These values are set in + * the head.iov_len, page_len, tail.iov_len, and buflen fields. */ static void rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) @@ -751,17 +759,19 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) struct page **ppages; int page_base; + /* The head iovec is redirected to the RPC reply message + * in the receive buffer, to avoid a memcopy. + */ + rqst->rq_rcv_buf.head[0].iov_base = srcp; + + /* The contents of the receive buffer that follow + * head.iov_len bytes are copied into the page list. + */ curlen = rqst->rq_rcv_buf.head[0].iov_len; - if (curlen > copy_len) { /* write chunk header fixup */ + if (curlen > copy_len) curlen = copy_len; - rqst->rq_rcv_buf.head[0].iov_len = curlen; - } - dprintk("RPC: %s: srcp 0x%p len %d hdrlen %d\n", __func__, srcp, copy_len, curlen); - - /* Shift pointer for first receive segment only */ - rqst->rq_rcv_buf.head[0].iov_base = srcp; srcp += curlen; copy_len -= curlen; @@ -798,28 +808,23 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) break; page_base = 0; } - } - if (copy_len && rqst->rq_rcv_buf.tail[0].iov_len) { - curlen = copy_len; - if (curlen > rqst->rq_rcv_buf.tail[0].iov_len) - curlen = rqst->rq_rcv_buf.tail[0].iov_len; - if (rqst->rq_rcv_buf.tail[0].iov_base != srcp) - memmove(rqst->rq_rcv_buf.tail[0].iov_base, srcp, curlen); - dprintk("RPC: %s: tail srcp 0x%p len %d curlen %d\n", - __func__, srcp, copy_len, curlen); - rqst->rq_rcv_buf.tail[0].iov_len = curlen; - copy_len -= curlen; ++i; - } else - rqst->rq_rcv_buf.tail[0].iov_len = 0; - - if (pad) { - /* implicit padding on terminal chunk */ - unsigned char *p = rqst->rq_rcv_buf.tail[0].iov_base; - while (pad--) - p[rqst->rq_rcv_buf.tail[0].iov_len++] = 0; + /* Implicit padding for the last segment in a Write + * chunk is inserted inline at the front of the tail + * iovec. The upper layer ignores the content of + * the pad. Simply ensure inline content in the tail + * that follows the Write chunk is properly aligned. + */ + if (pad) + srcp -= pad; } + /* The tail iovec is redirected to the remaining data + * in the receive buffer, to avoid a memcopy. + */ + if (copy_len || pad) + rqst->rq_rcv_buf.tail[0].iov_base = srcp; + if (copy_len) dprintk("RPC: %s: %d bytes in" " %d extra segments (%d lost)\n", -- cgit v1.1 From cfabe2c634e617765af39ea1cb2920bdcbc5bb7e Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:54:49 -0400 Subject: xprtrdma: Update only specific fields in private receive buffer Now that rpcrdma_inline_fixup() updates only two fields in rq_rcv_buf, a full memcpy of that structure to rq_private_buf is unwarranted. Updating rq_private_buf fields only where needed also better documents what is going on. Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/rpc_rdma.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index d018eb7..a0e811d 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -750,6 +750,11 @@ rpcrdma_count_chunks(struct rpcrdma_rep *rep, int wrchunk, __be32 **iptrp) * The upper layer has set the maximum number of bytes it can * receive in each component of rq_rcv_buf. These values are set in * the head.iov_len, page_len, tail.iov_len, and buflen fields. + * + * Unlike the TCP equivalent (xdr_partial_copy_from_skb), in + * many cases this function simply updates iov_base pointers in + * rq_rcv_buf to point directly to the received reply data, to + * avoid copying reply data. */ static void rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) @@ -763,6 +768,7 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) * in the receive buffer, to avoid a memcopy. */ rqst->rq_rcv_buf.head[0].iov_base = srcp; + rqst->rq_private_buf.head[0].iov_base = srcp; /* The contents of the receive buffer that follow * head.iov_len bytes are copied into the page list. @@ -822,16 +828,15 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) /* The tail iovec is redirected to the remaining data * in the receive buffer, to avoid a memcopy. */ - if (copy_len || pad) + if (copy_len || pad) { rqst->rq_rcv_buf.tail[0].iov_base = srcp; + rqst->rq_private_buf.tail[0].iov_base = srcp; + } if (copy_len) dprintk("RPC: %s: %d bytes in" " %d extra segments (%d lost)\n", __func__, olen, i, copy_len); - - /* TBD avoid a warning from call_decode() */ - rqst->rq_private_buf = rqst->rq_rcv_buf; } void -- cgit v1.1 From 64695bde6c289a62250eb0a078916703c8cf639a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:54:58 -0400 Subject: xprtrdma: Clean up fixup_copy_count accounting fixup_copy_count should count only the number of bytes copied to the page list. The head and tail are now always handled without a data copy. And the debugging at the end of rpcrdma_inline_fixup() is also no longer necessary, since copy_len will be non-zero when there is reply data in the tail (a normal and valid case). Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/rpc_rdma.c | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index a0e811d..dac2990 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -755,11 +755,14 @@ rpcrdma_count_chunks(struct rpcrdma_rep *rep, int wrchunk, __be32 **iptrp) * many cases this function simply updates iov_base pointers in * rq_rcv_buf to point directly to the received reply data, to * avoid copying reply data. + * + * Returns the count of bytes which had to be memcopied. */ -static void +static unsigned long rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) { - int i, npages, curlen, olen; + unsigned long fixup_copy_count; + int i, npages, curlen; char *destp; struct page **ppages; int page_base; @@ -781,13 +784,10 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) srcp += curlen; copy_len -= curlen; - olen = copy_len; - i = 0; - rpcx_to_rdmax(rqst->rq_xprt)->rx_stats.fixup_copy_count += olen; page_base = rqst->rq_rcv_buf.page_base; ppages = rqst->rq_rcv_buf.pages + (page_base >> PAGE_SHIFT); page_base &= ~PAGE_MASK; - + fixup_copy_count = 0; if (copy_len && rqst->rq_rcv_buf.page_len) { int pagelist_len; @@ -795,7 +795,7 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) if (pagelist_len > copy_len) pagelist_len = copy_len; npages = PAGE_ALIGN(page_base + pagelist_len) >> PAGE_SHIFT; - for (; i < npages; i++) { + for (i = 0; i < npages; i++) { curlen = PAGE_SIZE - page_base; if (curlen > pagelist_len) curlen = pagelist_len; @@ -809,6 +809,7 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) kunmap_atomic(destp); srcp += curlen; copy_len -= curlen; + fixup_copy_count += curlen; pagelist_len -= curlen; if (!pagelist_len) break; @@ -833,10 +834,7 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad) rqst->rq_private_buf.tail[0].iov_base = srcp; } - if (copy_len) - dprintk("RPC: %s: %d bytes in" - " %d extra segments (%d lost)\n", - __func__, olen, i, copy_len); + return fixup_copy_count; } void @@ -999,8 +997,10 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep) rep->rr_len -= RPCRDMA_HDRLEN_MIN; status = rep->rr_len; } - /* Fix up the rpc results for upper layer */ - rpcrdma_inline_fixup(rqst, (char *)iptr, rep->rr_len, rdmalen); + + r_xprt->rx_stats.fixup_copy_count += + rpcrdma_inline_fixup(rqst, (char *)iptr, rep->rr_len, + rdmalen); break; case rdma_nomsg: -- cgit v1.1 From 65b80179f9b8171b74625febf3457f41e792fa23 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:55:06 -0400 Subject: xprtrdma: No direct data placement with krb5i and krb5p Direct data placement is not allowed when using flavors that guarantee integrity or privacy. When such security flavors are in effect, don't allow the use of Read and Write chunks for moving individual data items. All messages larger than the inline threshold are sent via Long Call or Long Reply. On my systems (CX-3 Pro on FDR), for small I/O operations, the use of Long messages adds only around 5 usecs of latency in each direction. Note that when integrity or encryption is used, the host CPU touches every byte in these messages. Even if it could be used, data movement offload doesn't buy much in this case. Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/auth_gss/auth_gss.c | 2 ++ net/sunrpc/auth_gss/gss_krb5_mech.c | 2 ++ net/sunrpc/auth_gss/gss_mech_switch.c | 12 ++++++++++++ net/sunrpc/xprtrdma/rpc_rdma.c | 12 ++++++++++-- 4 files changed, 26 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index e64ae93..bca3537 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1017,6 +1017,8 @@ gss_create_new(struct rpc_auth_create_args *args, struct rpc_clnt *clnt) auth->au_rslack = GSS_VERF_SLACK >> 2; auth->au_ops = &authgss_ops; auth->au_flavor = flavor; + if (gss_pseudoflavor_to_datatouch(gss_auth->mech, flavor)) + auth->au_flags |= RPCAUTH_AUTH_DATATOUCH; atomic_set(&auth->au_count, 1); kref_init(&gss_auth->kref); diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 6542749..6059583 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -745,12 +745,14 @@ static struct pf_desc gss_kerberos_pfs[] = { .qop = GSS_C_QOP_DEFAULT, .service = RPC_GSS_SVC_INTEGRITY, .name = "krb5i", + .datatouch = true, }, [2] = { .pseudoflavor = RPC_AUTH_GSS_KRB5P, .qop = GSS_C_QOP_DEFAULT, .service = RPC_GSS_SVC_PRIVACY, .name = "krb5p", + .datatouch = true, }, }; diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c index 7063d85..5fec3ab 100644 --- a/net/sunrpc/auth_gss/gss_mech_switch.c +++ b/net/sunrpc/auth_gss/gss_mech_switch.c @@ -361,6 +361,18 @@ gss_pseudoflavor_to_service(struct gss_api_mech *gm, u32 pseudoflavor) } EXPORT_SYMBOL(gss_pseudoflavor_to_service); +bool +gss_pseudoflavor_to_datatouch(struct gss_api_mech *gm, u32 pseudoflavor) +{ + int i; + + for (i = 0; i < gm->gm_pf_num; i++) { + if (gm->gm_pfs[i].pseudoflavor == pseudoflavor) + return gm->gm_pfs[i].datatouch; + } + return false; +} + char * gss_service_to_auth_domain_name(struct gss_api_mech *gm, u32 service) { diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index dac2990..a47f170 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -570,6 +570,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) struct rpcrdma_req *req = rpcr_to_rdmar(rqst); enum rpcrdma_chunktype rtype, wtype; struct rpcrdma_msg *headerp; + bool ddp_allowed; ssize_t hdrlen; size_t rpclen; __be32 *iptr; @@ -586,6 +587,13 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) headerp->rm_credit = cpu_to_be32(r_xprt->rx_buf.rb_max_requests); headerp->rm_type = rdma_msg; + /* When the ULP employs a GSS flavor that guarantees integrity + * or privacy, direct data placement of individual data items + * is not allowed. + */ + ddp_allowed = !(rqst->rq_cred->cr_auth->au_flags & + RPCAUTH_AUTH_DATATOUCH); + /* * Chunks needed for results? * @@ -597,7 +605,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) */ if (rpcrdma_results_inline(r_xprt, rqst)) wtype = rpcrdma_noch; - else if (rqst->rq_rcv_buf.flags & XDRBUF_READ) + else if (ddp_allowed && rqst->rq_rcv_buf.flags & XDRBUF_READ) wtype = rpcrdma_writech; else wtype = rpcrdma_replych; @@ -620,7 +628,7 @@ rpcrdma_marshal_req(struct rpc_rqst *rqst) rtype = rpcrdma_noch; rpcrdma_inline_pullup(rqst); rpclen = rqst->rq_svec[0].iov_len; - } else if (rqst->rq_snd_buf.flags & XDRBUF_WRITE) { + } else if (ddp_allowed && rqst->rq_snd_buf.flags & XDRBUF_WRITE) { rtype = rpcrdma_readch; rpclen = rqst->rq_svec[0].iov_len; rpclen += rpcrdma_tail_pullup(&rqst->rq_snd_buf); -- cgit v1.1 From 0533b13072f4bf35738290d2cf9e299c7bc6c42a Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:55:14 -0400 Subject: svc: Avoid garbage replies when pc_func() returns rpc_drop_reply If an RPC program does not set vs_dispatch and pc_func() returns rpc_drop_reply, the server sends a reply anyway containing a single word containing the value RPC_DROP_REPLY (in network byte-order, of course). This is a nonsense RPC message. Fixes: 9e701c610923 ("svcrpc: simpler request dropping") Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/svc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index cc98528..87290a5 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1188,7 +1188,8 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) *statp = procp->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp); /* Encode reply */ - if (test_bit(RQ_DROPME, &rqstp->rq_flags)) { + if (*statp == rpc_drop_reply || + test_bit(RQ_DROPME, &rqstp->rq_flags)) { if (procp->pc_release) procp->pc_release(rqstp, NULL, rqstp->rq_resp); goto dropit; -- cgit v1.1 From a4e187d83d88eeaba6252aac0a2ffe5eaa73a818 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 29 Jun 2016 13:55:22 -0400 Subject: NFS: Don't drop CB requests with invalid principals Before commit 778be232a207 ("NFS do not find client in NFSv4 pg_authenticate"), the Linux callback server replied with RPC_AUTH_ERROR / RPC_AUTH_BADCRED, instead of dropping the CB request. Let's restore that behavior so the server has a chance to do something useful about it, and provide a warning that helps admins correct the problem. Fixes: 778be232a207 ("NFS do not find client in NFSv4 ...") Signed-off-by: Chuck Lever Tested-by: Steve Wise Signed-off-by: Anna Schumaker --- net/sunrpc/svc.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'net') diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 87290a5..c5b0cb4 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1194,6 +1194,11 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) procp->pc_release(rqstp, NULL, rqstp->rq_resp); goto dropit; } + if (*statp == rpc_autherr_badcred) { + if (procp->pc_release) + procp->pc_release(rqstp, NULL, rqstp->rq_resp); + goto err_bad_auth; + } if (*statp == rpc_success && (xdr = procp->pc_encode) && !xdr(rqstp, resv->iov_base+resv->iov_len, rqstp->rq_resp)) { -- cgit v1.1 From 53d7852307295b4576777618cbc2684bb191fb46 Mon Sep 17 00:00:00 2001 From: kbuild test robot Date: Sat, 16 Jul 2016 06:02:05 +0800 Subject: xprtrdma: fix semicolon.cocci warnings net/sunrpc/xprtrdma/verbs.c:798:2-3: Unneeded semicolon Remove unneeded semicolon. Generated by: scripts/coccinelle/misc/semicolon.cocci CC: Chuck Lever Signed-off-by: Fengguang Wu Reviewed-by: Chuck Lever Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/verbs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index a74d79d..536d0be 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -765,7 +765,7 @@ rpcrdma_mr_recovery_worker(struct work_struct *work) mw->mw_xprt->rx_ia.ri_ops->ro_recover_mr(mw); spin_lock(&buf->rb_recovery_lock); - }; + } spin_unlock(&buf->rb_recovery_lock); } -- cgit v1.1