diff options
Diffstat (limited to 'net')
37 files changed, 856 insertions, 533 deletions
diff --git a/net/compat.c b/net/compat.c index 6564720f32b7..485db8ee9b28 100644 --- a/net/compat.c +++ b/net/compat.c @@ -297,7 +297,7 @@ void scm_detach_fds_compat(struct msghdr *msg, struct scm_cookie *scm) int err = 0, i; for (i = 0; i < fdmax; i++) { - err = receive_fd_user(scm->fp->fp[i], cmsg_data + i, o_flags); + err = scm_recv_one_fd(scm->fp->fp[i], cmsg_data + i, o_flags); if (err < 0) break; } diff --git a/net/core/scm.c b/net/core/scm.c index 7dc47c17d863..db3f7cd519c2 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -325,7 +325,7 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) } for (i = 0; i < fdmax; i++) { - err = receive_fd_user(scm->fp->fp[i], cmsg_data + i, o_flags); + err = scm_recv_one_fd(scm->fp->fp[i], cmsg_data + i, o_flags); if (err < 0) break; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 12d22c0b8551..edbbef563d4d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -337,7 +337,7 @@ static struct sk_buff *napi_skb_cache_get(void) } skb = nc->skb_cache[--nc->skb_count]; - kasan_unpoison_object_data(skbuff_cache, skb); + kasan_mempool_unpoison_object(skb, kmem_cache_size(skbuff_cache)); return skb; } @@ -1345,13 +1345,15 @@ static void napi_skb_cache_put(struct sk_buff *skb) struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); u32 i; - kasan_poison_object_data(skbuff_cache, skb); + if (!kasan_mempool_poison_object(skb)) + return; + nc->skb_cache[nc->skb_count++] = skb; if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { for (i = NAPI_SKB_CACHE_HALF; i < NAPI_SKB_CACHE_SIZE; i++) - kasan_unpoison_object_data(skbuff_cache, - nc->skb_cache[i]); + kasan_mempool_unpoison_object(nc->skb_cache[i], + kmem_cache_size(skbuff_cache)); kmem_cache_free_bulk(skbuff_cache, NAPI_SKB_CACHE_HALF, nc->skb_cache + NAPI_SKB_CACHE_HALF); diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index f18ca02aa95a..c42ddd85ff1f 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -104,7 +104,7 @@ dns_resolver_preparse(struct key_preparsed_payload *prep) const struct dns_server_list_v1_header *v1; /* It may be a server list. */ - if (datalen <= sizeof(*v1)) + if (datalen < sizeof(*v1)) return -EINVAL; v1 = (const struct dns_server_list_v1_header *)data; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 9bdfdab906fe..3ff35f811765 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -52,6 +52,7 @@ #include <linux/if_arp.h> #include <linux/proc_fs.h> #include <linux/rcupdate.h> +#include <linux/rcupdate_wait.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/init.h> diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 1d6b80145efb..1baa484d2190 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1849,7 +1849,6 @@ static int receive_fallback_to_copy(struct sock *sk, { unsigned long copy_address = (unsigned long)zc->copybuf_address; struct msghdr msg = {}; - struct iovec iov; int err; zc->length = 0; @@ -1858,8 +1857,8 @@ static int receive_fallback_to_copy(struct sock *sk, if (copy_address != zc->copybuf_address) return -EINVAL; - err = import_single_range(ITER_DEST, (void __user *)copy_address, - inq, &iov, &msg.msg_iter); + err = import_ubuf(ITER_DEST, (void __user *)copy_address, inq, + &msg.msg_iter); if (err) return err; @@ -1886,14 +1885,13 @@ static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc, { unsigned long copy_address = (unsigned long)zc->copybuf_address; struct msghdr msg = {}; - struct iovec iov; int err; if (copy_address != zc->copybuf_address) return -EINVAL; - err = import_single_range(ITER_DEST, (void __user *)copy_address, - copylen, &iov, &msg.msg_iter); + err = import_ubuf(ITER_DEST, (void __user *)copy_address, copylen, + &msg.msg_iter); if (err) return err; err = skb_copy_datagram_msg(skb, *offset, &msg, copylen); diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index 26ab0e9612d8..21f7860e8fa1 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -4,6 +4,8 @@ #ifndef __IP_SET_BITMAP_IP_GEN_H #define __IP_SET_BITMAP_IP_GEN_H +#include <linux/rcupdate_wait.h> + #define mtype_do_test IPSET_TOKEN(MTYPE, _do_test) #define mtype_gc_test IPSET_TOKEN(MTYPE, _gc_test) #define mtype_is_filled IPSET_TOKEN(MTYPE, _is_filled) diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 7c2399541771..cbf80da9a01c 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -5,6 +5,7 @@ #define _IP_SET_HASH_GEN_H #include <linux/rcupdate.h> +#include <linux/rcupdate_wait.h> #include <linux/jhash.h> #include <linux/types.h> #include <linux/netfilter/nfnetlink.h> diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 9065da3cdd12..a743db073887 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -31,6 +31,7 @@ #include <linux/seq_file.h> #include <linux/jhash.h> #include <linux/random.h> +#include <linux/rcupdate_wait.h> #include <net/net_namespace.h> #include <net/ip_vs.h> diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index c5970ba416ae..f821ad2e19b3 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -21,6 +21,7 @@ #include <linux/interrupt.h> #include <linux/sysctl.h> #include <linux/list.h> +#include <linux/rcupdate_wait.h> #include <net/ip_vs.h> diff --git a/net/netlabel/netlabel_calipso.c b/net/netlabel/netlabel_calipso.c index f1d5b8465217..a07c2216d28b 100644 --- a/net/netlabel/netlabel_calipso.c +++ b/net/netlabel/netlabel_calipso.c @@ -54,6 +54,28 @@ static const struct nla_policy calipso_genl_policy[NLBL_CALIPSO_A_MAX + 1] = { [NLBL_CALIPSO_A_MTYPE] = { .type = NLA_U32 }, }; +static const struct netlbl_calipso_ops *calipso_ops; + +/** + * netlbl_calipso_ops_register - Register the CALIPSO operations + * @ops: ops to register + * + * Description: + * Register the CALIPSO packet engine operations. + * + */ +const struct netlbl_calipso_ops * +netlbl_calipso_ops_register(const struct netlbl_calipso_ops *ops) +{ + return xchg(&calipso_ops, ops); +} +EXPORT_SYMBOL(netlbl_calipso_ops_register); + +static const struct netlbl_calipso_ops *netlbl_calipso_ops_get(void) +{ + return READ_ONCE(calipso_ops); +} + /* NetLabel Command Handlers */ /** @@ -96,15 +118,18 @@ static int netlbl_calipso_add_pass(struct genl_info *info, * */ static int netlbl_calipso_add(struct sk_buff *skb, struct genl_info *info) - { int ret_val = -EINVAL; struct netlbl_audit audit_info; + const struct netlbl_calipso_ops *ops = netlbl_calipso_ops_get(); if (!info->attrs[NLBL_CALIPSO_A_DOI] || !info->attrs[NLBL_CALIPSO_A_MTYPE]) return -EINVAL; + if (!ops) + return -EOPNOTSUPP; + netlbl_netlink_auditinfo(&audit_info); switch (nla_get_u32(info->attrs[NLBL_CALIPSO_A_MTYPE])) { case CALIPSO_MAP_PASS: @@ -363,28 +388,6 @@ int __init netlbl_calipso_genl_init(void) return genl_register_family(&netlbl_calipso_gnl_family); } -static const struct netlbl_calipso_ops *calipso_ops; - -/** - * netlbl_calipso_ops_register - Register the CALIPSO operations - * @ops: ops to register - * - * Description: - * Register the CALIPSO packet engine operations. - * - */ -const struct netlbl_calipso_ops * -netlbl_calipso_ops_register(const struct netlbl_calipso_ops *ops) -{ - return xchg(&calipso_ops, ops); -} -EXPORT_SYMBOL(netlbl_calipso_ops_register); - -static const struct netlbl_calipso_ops *netlbl_calipso_ops_get(void) -{ - return READ_ONCE(calipso_ops); -} - /** * calipso_doi_add - Add a new DOI to the CALIPSO protocol engine * @doi_def: the DOI structure diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index fa8aec78f63d..465bfe5eb061 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -259,15 +259,61 @@ static int rxrpc_listen(struct socket *sock, int backlog) } /** + * rxrpc_kernel_lookup_peer - Obtain remote transport endpoint for an address + * @sock: The socket through which it will be accessed + * @srx: The network address + * @gfp: Allocation flags + * + * Lookup or create a remote transport endpoint record for the specified + * address and return it with a ref held. + */ +struct rxrpc_peer *rxrpc_kernel_lookup_peer(struct socket *sock, + struct sockaddr_rxrpc *srx, gfp_t gfp) +{ + struct rxrpc_sock *rx = rxrpc_sk(sock->sk); + int ret; + + ret = rxrpc_validate_address(rx, srx, sizeof(*srx)); + if (ret < 0) + return ERR_PTR(ret); + + return rxrpc_lookup_peer(rx->local, srx, gfp); +} +EXPORT_SYMBOL(rxrpc_kernel_lookup_peer); + +/** + * rxrpc_kernel_get_peer - Get a reference on a peer + * @peer: The peer to get a reference on. + * + * Get a record for the remote peer in a call. + */ +struct rxrpc_peer *rxrpc_kernel_get_peer(struct rxrpc_peer *peer) +{ + return peer ? rxrpc_get_peer(peer, rxrpc_peer_get_application) : NULL; +} +EXPORT_SYMBOL(rxrpc_kernel_get_peer); + +/** + * rxrpc_kernel_put_peer - Allow a kernel app to drop a peer reference + * @peer: The peer to drop a ref on + */ +void rxrpc_kernel_put_peer(struct rxrpc_peer *peer) +{ + rxrpc_put_peer(peer, rxrpc_peer_put_application); +} +EXPORT_SYMBOL(rxrpc_kernel_put_peer); + +/** * rxrpc_kernel_begin_call - Allow a kernel service to begin a call * @sock: The socket on which to make the call - * @srx: The address of the peer to contact + * @peer: The peer to contact * @key: The security context to use (defaults to socket setting) * @user_call_ID: The ID to use * @tx_total_len: Total length of data to transmit during the call (or -1) * @hard_timeout: The maximum lifespan of the call in sec * @gfp: The allocation constraints * @notify_rx: Where to send notifications instead of socket queue + * @service_id: The ID of the service to contact * @upgrade: Request service upgrade for call * @interruptibility: The call is interruptible, or can be canceled. * @debug_id: The debug ID for tracing to be assigned to the call @@ -280,13 +326,14 @@ static int rxrpc_listen(struct socket *sock, int backlog) * supplying @srx and @key. */ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, - struct sockaddr_rxrpc *srx, + struct rxrpc_peer *peer, struct key *key, unsigned long user_call_ID, s64 tx_total_len, u32 hard_timeout, gfp_t gfp, rxrpc_notify_rx_t notify_rx, + u16 service_id, bool upgrade, enum rxrpc_interruptibility interruptibility, unsigned int debug_id) @@ -295,13 +342,11 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, struct rxrpc_call_params p; struct rxrpc_call *call; struct rxrpc_sock *rx = rxrpc_sk(sock->sk); - int ret; _enter(",,%x,%lx", key_serial(key), user_call_ID); - ret = rxrpc_validate_address(rx, srx, sizeof(*srx)); - if (ret < 0) - return ERR_PTR(ret); + if (WARN_ON_ONCE(peer->local != rx->local)) + return ERR_PTR(-EIO); lock_sock(&rx->sk); @@ -319,12 +364,13 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, memset(&cp, 0, sizeof(cp)); cp.local = rx->local; + cp.peer = peer; cp.key = key; cp.security_level = rx->min_sec_level; cp.exclusive = false; cp.upgrade = upgrade; - cp.service_id = srx->srx_service; - call = rxrpc_new_client_call(rx, &cp, srx, &p, gfp, debug_id); + cp.service_id = service_id; + call = rxrpc_new_client_call(rx, &cp, &p, gfp, debug_id); /* The socket has been unlocked. */ if (!IS_ERR(call)) { call->notify_rx = notify_rx; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index e8e14c6f904d..2f8b39a614c3 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -68,6 +68,7 @@ struct rxrpc_net { atomic_t nr_calls; /* Count of allocated calls */ atomic_t nr_conns; + struct list_head bundle_proc_list; /* List of bundles for proc */ struct list_head conn_proc_list; /* List of conns in this namespace for proc */ struct list_head service_conns; /* Service conns in this namespace */ rwlock_t conn_lock; /* Lock for ->conn_proc_list, ->service_conns */ @@ -364,6 +365,7 @@ struct rxrpc_conn_proto { struct rxrpc_conn_parameters { struct rxrpc_local *local; /* Representation of local endpoint */ + struct rxrpc_peer *peer; /* Representation of remote endpoint */ struct key *key; /* Security details */ bool exclusive; /* T if conn is exclusive */ bool upgrade; /* T if service ID can be upgraded */ @@ -431,6 +433,7 @@ struct rxrpc_bundle { struct rxrpc_local *local; /* Representation of local endpoint */ struct rxrpc_peer *peer; /* Remote endpoint */ struct key *key; /* Security details */ + struct list_head proc_link; /* Link in net->bundle_proc_list */ const struct rxrpc_security *security; /* applied security module */ refcount_t ref; atomic_t active; /* Number of active users */ @@ -444,6 +447,7 @@ struct rxrpc_bundle { struct rb_node local_node; /* Node in local->client_conns */ struct list_head waiting_calls; /* Calls waiting for channels */ unsigned long avail_chans; /* Mask of available channels */ + unsigned int conn_ids[4]; /* Connection IDs. */ struct rxrpc_connection *conns[4]; /* The connections in the bundle (max 4) */ }; @@ -867,7 +871,6 @@ struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *, unsigned long struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *, gfp_t, unsigned int); struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *, struct rxrpc_conn_parameters *, - struct sockaddr_rxrpc *, struct rxrpc_call_params *, gfp_t, unsigned int); void rxrpc_start_call_timer(struct rxrpc_call *call); @@ -1167,6 +1170,7 @@ void rxrpc_put_peer(struct rxrpc_peer *, enum rxrpc_peer_trace); */ extern const struct seq_operations rxrpc_call_seq_ops; extern const struct seq_operations rxrpc_connection_seq_ops; +extern const struct seq_operations rxrpc_bundle_seq_ops; extern const struct seq_operations rxrpc_peer_seq_ops; extern const struct seq_operations rxrpc_local_seq_ops; diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index f10b37c14772..0943e54370ba 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -193,7 +193,6 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, * Allocate a new client call. */ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, - struct sockaddr_rxrpc *srx, struct rxrpc_conn_parameters *cp, struct rxrpc_call_params *p, gfp_t gfp, @@ -211,10 +210,12 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, now = ktime_get_real(); call->acks_latest_ts = now; call->cong_tstamp = now; - call->dest_srx = *srx; + call->dest_srx = cp->peer->srx; + call->dest_srx.srx_service = cp->service_id; call->interruptibility = p->interruptibility; call->tx_total_len = p->tx_total_len; call->key = key_get(cp->key); + call->peer = rxrpc_get_peer(cp->peer, rxrpc_peer_get_call); call->local = rxrpc_get_local(cp->local, rxrpc_local_get_call); call->security_level = cp->security_level; if (p->kernel) @@ -306,10 +307,6 @@ static int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp) _enter("{%d,%lx},", call->debug_id, call->user_call_ID); - call->peer = rxrpc_lookup_peer(local, &call->dest_srx, gfp); - if (!call->peer) - goto error; - ret = rxrpc_look_up_bundle(call, gfp); if (ret < 0) goto error; @@ -334,7 +331,6 @@ error: */ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, struct rxrpc_conn_parameters *cp, - struct sockaddr_rxrpc *srx, struct rxrpc_call_params *p, gfp_t gfp, unsigned int debug_id) @@ -349,13 +345,18 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, _enter("%p,%lx", rx, p->user_call_ID); + if (WARN_ON_ONCE(!cp->peer)) { + release_sock(&rx->sk); + return ERR_PTR(-EIO); + } + limiter = rxrpc_get_call_slot(p, gfp); if (!limiter) { release_sock(&rx->sk); return ERR_PTR(-ERESTARTSYS); } - call = rxrpc_alloc_client_call(rx, srx, cp, p, gfp, debug_id); + call = rxrpc_alloc_client_call(rx, cp, p, gfp, debug_id); if (IS_ERR(call)) { release_sock(&rx->sk); up(limiter); diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 1d95f8bc769f..3b9b267a4431 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -91,6 +91,10 @@ static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_call *call, atomic_set(&bundle->active, 1); INIT_LIST_HEAD(&bundle->waiting_calls); trace_rxrpc_bundle(bundle->debug_id, 1, rxrpc_bundle_new); + + write_lock(&bundle->local->rxnet->conn_lock); + list_add_tail(&bundle->proc_link, &bundle->local->rxnet->bundle_proc_list); + write_unlock(&bundle->local->rxnet->conn_lock); } return bundle; } @@ -109,6 +113,9 @@ static void rxrpc_free_bundle(struct rxrpc_bundle *bundle) { trace_rxrpc_bundle(bundle->debug_id, refcount_read(&bundle->ref), rxrpc_bundle_free); + write_lock(&bundle->local->rxnet->conn_lock); + list_del(&bundle->proc_link); + write_unlock(&bundle->local->rxnet->conn_lock); rxrpc_put_peer(bundle->peer, rxrpc_peer_put_bundle); key_put(bundle->key); kfree(bundle); @@ -338,6 +345,7 @@ static bool rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, old = bundle->conns[slot]; if (old) { bundle->conns[slot] = NULL; + bundle->conn_ids[slot] = 0; trace_rxrpc_client(old, -1, rxrpc_client_replace); rxrpc_put_connection(old, rxrpc_conn_put_noreuse); } @@ -351,6 +359,7 @@ static bool rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, rxrpc_activate_bundle(bundle); conn->bundle_shift = shift; bundle->conns[slot] = conn; + bundle->conn_ids[slot] = conn->debug_id; for (i = 0; i < RXRPC_MAXCALLS; i++) set_bit(shift + i, &bundle->avail_chans); return true; @@ -671,6 +680,7 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) if (bundle->conns[bindex] == conn) { _debug("clear slot %u", bindex); bundle->conns[bindex] = NULL; + bundle->conn_ids[bindex] = 0; for (i = 0; i < RXRPC_MAXCALLS; i++) clear_bit(conn->bundle_shift + i, &bundle->avail_chans); rxrpc_put_client_connection_id(bundle->local, conn); diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index 89ac05a711a4..39c908a3ca6e 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -25,7 +25,7 @@ struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *peer, struct rxrpc_conn_proto k; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rb_node *p; - unsigned int seq = 0; + unsigned int seq = 1; k.epoch = sp->hdr.epoch; k.cid = sp->hdr.cid & RXRPC_CIDMASK; @@ -35,6 +35,7 @@ struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *peer, * under just the RCU read lock, so we have to check for * changes. */ + seq++; /* 2 on the 1st/lockless path, otherwise odd */ read_seqbegin_or_lock(&peer->service_conn_lock, &seq); p = rcu_dereference_raw(peer->service_conns.rb_node); diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c index a0319c040c25..a4c135d0fbcc 100644 --- a/net/rxrpc/net_ns.c +++ b/net/rxrpc/net_ns.c @@ -45,6 +45,7 @@ static __net_init int rxrpc_init_net(struct net *net) atomic_set(&rxnet->nr_calls, 1); atomic_set(&rxnet->nr_conns, 1); + INIT_LIST_HEAD(&rxnet->bundle_proc_list); INIT_LIST_HEAD(&rxnet->conn_proc_list); INIT_LIST_HEAD(&rxnet->service_conns); rwlock_init(&rxnet->conn_lock); @@ -78,6 +79,9 @@ static __net_init int rxrpc_init_net(struct net *net) proc_create_net("conns", 0444, rxnet->proc_net, &rxrpc_connection_seq_ops, sizeof(struct seq_net_private)); + proc_create_net("bundles", 0444, rxnet->proc_net, + &rxrpc_bundle_seq_ops, + sizeof(struct seq_net_private)); proc_create_net("peers", 0444, rxnet->proc_net, &rxrpc_peer_seq_ops, sizeof(struct seq_net_private)); diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 8d7a715a0bb1..49dcda67a0d5 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -22,6 +22,8 @@ #include <net/ip6_route.h> #include "ar-internal.h" +static const struct sockaddr_rxrpc rxrpc_null_addr; + /* * Hash a peer key. */ @@ -457,39 +459,53 @@ void rxrpc_destroy_all_peers(struct rxrpc_net *rxnet) } /** - * rxrpc_kernel_get_peer - Get the peer address of a call + * rxrpc_kernel_get_call_peer - Get the peer address of a call * @sock: The socket on which the call is in progress. * @call: The call to query - * @_srx: Where to place the result * - * Get the address of the remote peer in a call. + * Get a record for the remote peer in a call. */ -void rxrpc_kernel_get_peer(struct socket *sock, struct rxrpc_call *call, - struct sockaddr_rxrpc *_srx) +struct rxrpc_peer *rxrpc_kernel_get_call_peer(struct socket *sock, struct rxrpc_call *call) { - *_srx = call->peer->srx; + return call->peer; } -EXPORT_SYMBOL(rxrpc_kernel_get_peer); +EXPORT_SYMBOL(rxrpc_kernel_get_call_peer); /** * rxrpc_kernel_get_srtt - Get a call's peer smoothed RTT - * @sock: The socket on which the call is in progress. - * @call: The call to query - * @_srtt: Where to store the SRTT value. + * @peer: The peer to query * - * Get the call's peer smoothed RTT in uS. + * Get the call's peer smoothed RTT in uS or UINT_MAX if we have no samples. */ -bool rxrpc_kernel_get_srtt(struct socket *sock, struct rxrpc_call *call, - u32 *_srtt) +unsigned int rxrpc_kernel_get_srtt(const struct rxrpc_peer *peer) { - struct rxrpc_peer *peer = call->peer; + return peer->rtt_count > 0 ? peer->srtt_us >> 3 : UINT_MAX; +} +EXPORT_SYMBOL(rxrpc_kernel_get_srtt); - if (peer->rtt_count == 0) { - *_srtt = 1000000; /* 1S */ - return false; - } +/** + * rxrpc_kernel_remote_srx - Get the address of a peer + * @peer: The peer to query + * + * Get a pointer to the address from a peer record. The caller is responsible + * for making sure that the address is not deallocated. + */ +const struct sockaddr_rxrpc *rxrpc_kernel_remote_srx(const struct rxrpc_peer *peer) +{ + return peer ? &peer->srx : &rxrpc_null_addr; +} +EXPORT_SYMBOL(rxrpc_kernel_remote_srx); - *_srtt = call->peer->srtt_us >> 3; - return true; +/** + * rxrpc_kernel_remote_addr - Get the peer transport address of a call + * @peer: The peer to query + * + * Get a pointer to the transport address from a peer record. The caller is + * responsible for making sure that the address is not deallocated. + */ +const struct sockaddr *rxrpc_kernel_remote_addr(const struct rxrpc_peer *peer) +{ + return (const struct sockaddr *) + (peer ? &peer->srx.transport : &rxrpc_null_addr.transport); } -EXPORT_SYMBOL(rxrpc_kernel_get_srtt); +EXPORT_SYMBOL(rxrpc_kernel_remote_addr); diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 682636d3b060..6c86cbb98d1d 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -199,6 +199,82 @@ const struct seq_operations rxrpc_connection_seq_ops = { }; /* + * generate a list of extant virtual bundles in /proc/net/rxrpc/bundles + */ +static void *rxrpc_bundle_seq_start(struct seq_file *seq, loff_t *_pos) + __acquires(rxnet->conn_lock) +{ + struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); + + read_lock(&rxnet->conn_lock); + return seq_list_start_head(&rxnet->bundle_proc_list, *_pos); +} + +static void *rxrpc_bundle_seq_next(struct seq_file *seq, void *v, + loff_t *pos) +{ + struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); + + return seq_list_next(v, &rxnet->bundle_proc_list, pos); +} + +static void rxrpc_bundle_seq_stop(struct seq_file *seq, void *v) + __releases(rxnet->conn_lock) +{ + struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); + + read_unlock(&rxnet->conn_lock); +} + +static int rxrpc_bundle_seq_show(struct seq_file *seq, void *v) +{ + struct rxrpc_bundle *bundle; + struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); + char lbuff[50], rbuff[50]; + + if (v == &rxnet->bundle_proc_list) { + seq_puts(seq, + "Proto Local " + " Remote " + " SvID Ref Act Flg Key |" + " Bundle Conn_0 Conn_1 Conn_2 Conn_3\n" + ); + return 0; + } + + bundle = list_entry(v, struct rxrpc_bundle, proc_link); + + sprintf(lbuff, "%pISpc", &bundle->local->srx.transport); + sprintf(rbuff, "%pISpc", &bundle->peer->srx.transport); + seq_printf(seq, + "UDP %-47.47s %-47.47s %4x %3u %3d" + " %c%c%c %08x | %08x %08x %08x %08x %08x\n", + lbuff, + rbuff, + bundle->service_id, + refcount_read(&bundle->ref), + atomic_read(&bundle->active), + bundle->try_upgrade ? 'U' : '-', + bundle->exclusive ? 'e' : '-', + bundle->upgrade ? 'u' : '-', + key_serial(bundle->key), + bundle->debug_id, + bundle->conn_ids[0], + bundle->conn_ids[1], + bundle->conn_ids[2], + bundle->conn_ids[3]); + + return 0; +} + +const struct seq_operations rxrpc_bundle_seq_ops = { + .start = rxrpc_bundle_seq_start, + .next = rxrpc_bundle_seq_next, + .stop = rxrpc_bundle_seq_stop, + .show = rxrpc_bundle_seq_show, +}; + +/* * generate a list of extant virtual peers in /proc/net/rxrpc/peers */ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v) diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 8e0b94714e84..5677d5690a02 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -572,6 +572,7 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, __acquires(&call->user_mutex) { struct rxrpc_conn_parameters cp; + struct rxrpc_peer *peer; struct rxrpc_call *call; struct key *key; @@ -584,21 +585,29 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, return ERR_PTR(-EDESTADDRREQ); } + peer = rxrpc_lookup_peer(rx->local, srx, GFP_KERNEL); + if (!peer) { + release_sock(&rx->sk); + return ERR_PTR(-ENOMEM); + } + key = rx->key; if (key && !rx->key->payload.data[0]) key = NULL; memset(&cp, 0, sizeof(cp)); cp.local = rx->local; + cp.peer = peer; cp.key = rx->key; cp.security_level = rx->min_sec_level; cp.exclusive = rx->exclusive | p->exclusive; cp.upgrade = p->upgrade; cp.service_id = srx->srx_service; - call = rxrpc_new_client_call(rx, &cp, srx, &p->call, GFP_KERNEL, + call = rxrpc_new_client_call(rx, &cp, &p->call, GFP_KERNEL, atomic_inc_return(&rxrpc_debug_id)); /* The socket is now unlocked */ + rxrpc_put_peer(peer, rxrpc_peer_put_application); _leave(" = %p\n", call); return call; } diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 89981dbe46c9..97704a9e84c7 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -844,7 +844,7 @@ long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev) goto out; /* the calculated number of cq entries fits to mlx5 cq allocation */ cqe_size_order = cache_line_size() == 128 ? 7 : 6; - smc_order = MAX_ORDER - cqe_size_order; + smc_order = MAX_PAGE_ORDER - cqe_size_order; if (SMC_MAX_CQE + 2 > (0x00000001 << smc_order) * PAGE_SIZE) cqattr.cqe = (0x00000001 << smc_order) * PAGE_SIZE - 2; smcibdev->roce_cq_send = ib_create_cq(smcibdev->ibdev, diff --git a/net/socket.c b/net/socket.c index 89d79205bf50..ed3df2f749bf 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2163,10 +2163,9 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, struct sockaddr_storage address; int err; struct msghdr msg; - struct iovec iov; int fput_needed; - err = import_single_range(ITER_SOURCE, buff, len, &iov, &msg.msg_iter); + err = import_ubuf(ITER_SOURCE, buff, len, &msg.msg_iter); if (unlikely(err)) return err; sock = sockfd_lookup_light(fd, &err, &fput_needed); @@ -2228,11 +2227,10 @@ int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags, .msg_name = addr ? (struct sockaddr *)&address : NULL, }; struct socket *sock; - struct iovec iov; int err, err2; int fput_needed; - err = import_single_range(ITER_DEST, ubuf, size, &iov, &msg.msg_iter); + err = import_ubuf(ITER_DEST, ubuf, size, &msg.msg_iter); if (unlikely(err)) return err; sock = sockfd_lookup_light(fd, &err, &fput_needed); diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 18734e70c5dd..24de94184700 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -866,14 +866,6 @@ svcauth_gss_unwrap_integ(struct svc_rqst *rqstp, u32 seq, struct gss_ctx *ctx) struct xdr_buf databody_integ; struct xdr_netobj checksum; - /* NFS READ normally uses splice to send data in-place. However - * the data in cache can change after the reply's MIC is computed - * but before the RPC reply is sent. To prevent the client from - * rejecting the server-computed MIC in this somewhat rare case, - * do not use splice with the GSS integrity service. - */ - clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); - /* Did we already verify the signature on the original pass through? */ if (rqstp->rq_deferred) return 0; @@ -948,8 +940,6 @@ svcauth_gss_unwrap_priv(struct svc_rqst *rqstp, u32 seq, struct gss_ctx *ctx) struct xdr_buf *buf = xdr->buf; unsigned int saved_len; - clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); - if (xdr_stream_decode_u32(xdr, &len) < 0) goto unwrap_failed; if (rqstp->rq_deferred) { @@ -2014,6 +2004,11 @@ svcauth_gss_domain_release(struct auth_domain *dom) call_rcu(&dom->rcu_head, svcauth_gss_domain_release_rcu); } +static rpc_authflavor_t svcauth_gss_pseudoflavor(struct svc_rqst *rqstp) +{ + return svcauth_gss_flavor(rqstp->rq_gssclient); +} + static struct auth_ops svcauthops_gss = { .name = "rpcsec_gss", .owner = THIS_MODULE, @@ -2022,6 +2017,7 @@ static struct auth_ops svcauthops_gss = { .release = svcauth_gss_release, .domain_release = svcauth_gss_domain_release, .set_client = svcauth_gss_set_client, + .pseudoflavor = svcauth_gss_pseudoflavor, }; static int rsi_cache_create_net(struct net *net) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index daa9582ec861..cda0935a68c9 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -287,8 +287,14 @@ static struct rpc_xprt *rpc_clnt_set_transport(struct rpc_clnt *clnt, static void rpc_clnt_set_nodename(struct rpc_clnt *clnt, const char *nodename) { - clnt->cl_nodelen = strlcpy(clnt->cl_nodename, - nodename, sizeof(clnt->cl_nodename)); + ssize_t copied; + + copied = strscpy(clnt->cl_nodename, + nodename, sizeof(clnt->cl_nodename)); + + clnt->cl_nodelen = copied < 0 + ? sizeof(clnt->cl_nodename) - 1 + : copied; } static int rpc_client_register(struct rpc_clnt *clnt, @@ -797,15 +803,24 @@ out_revert: } EXPORT_SYMBOL_GPL(rpc_switch_client_transport); -static -int _rpc_clnt_xprt_iter_init(struct rpc_clnt *clnt, struct rpc_xprt_iter *xpi, - void func(struct rpc_xprt_iter *xpi, struct rpc_xprt_switch *xps)) +static struct rpc_xprt_switch *rpc_clnt_xprt_switch_get(struct rpc_clnt *clnt) { struct rpc_xprt_switch *xps; rcu_read_lock(); xps = xprt_switch_get(rcu_dereference(clnt->cl_xpi.xpi_xpswitch)); rcu_read_unlock(); + + return xps; +} + +static +int _rpc_clnt_xprt_iter_init(struct rpc_clnt *clnt, struct rpc_xprt_iter *xpi, + void func(struct rpc_xprt_iter *xpi, struct rpc_xprt_switch *xps)) +{ + struct rpc_xprt_switch *xps; + + xps = rpc_clnt_xprt_switch_get(clnt); if (xps == NULL) return -EAGAIN; func(xpi, xps); @@ -1302,8 +1317,10 @@ static void call_bc_encode(struct rpc_task *task); * rpc_run_bc_task - Allocate a new RPC task for backchannel use, then run * rpc_execute against it * @req: RPC request + * @timeout: timeout values to use for this task */ -struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req) +struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req, + struct rpc_timeout *timeout) { struct rpc_task *task; struct rpc_task_setup task_setup_data = { @@ -1322,7 +1339,7 @@ struct rpc_task *rpc_run_bc_task(struct rpc_rqst *req) return task; } - xprt_init_bc_request(req, task); + xprt_init_bc_request(req, task, timeout); task->tk_action = call_bc_encode; atomic_inc(&task->tk_count); @@ -2206,9 +2223,7 @@ call_connect_status(struct rpc_task *task) struct rpc_xprt *saved = task->tk_xprt; struct rpc_xprt_switch *xps; - rcu_read_lock(); - xps = xprt_switch_get(rcu_dereference(clnt->cl_xpi.xpi_xpswitch)); - rcu_read_unlock(); + xps = rpc_clnt_xprt_switch_get(clnt); if (xps->xps_nxprts > 1) { long value; @@ -3116,7 +3131,6 @@ static int rpc_xprt_probe_trunked(struct rpc_clnt *clnt, struct rpc_xprt *xprt, struct rpc_add_xprt_test *data) { - struct rpc_xprt_switch *xps; struct rpc_xprt *main_xprt; int status = 0; @@ -3124,7 +3138,6 @@ static int rpc_xprt_probe_trunked(struct rpc_clnt *clnt, rcu_read_lock(); main_xprt = xprt_get(rcu_dereference(clnt->cl_xprt)); - xps = xprt_switch_get(rcu_dereference(clnt->cl_xpi.xpi_xpswitch)); status = rpc_cmp_addr_port((struct sockaddr *)&xprt->addr, (struct sockaddr *)&main_xprt->addr); rcu_read_unlock(); @@ -3135,7 +3148,6 @@ static int rpc_xprt_probe_trunked(struct rpc_clnt *clnt, status = rpc_clnt_add_xprt_helper(clnt, xprt, data); out: xprt_put(xprt); - xprt_switch_put(xps); return status; } @@ -3250,34 +3262,27 @@ rpc_set_connect_timeout(struct rpc_clnt *clnt, } EXPORT_SYMBOL_GPL(rpc_set_connect_timeout); -void rpc_clnt_xprt_switch_put(struct rpc_clnt *clnt) -{ - rcu_read_lock(); - xprt_switch_put(rcu_dereference(clnt->cl_xpi.xpi_xpswitch)); - rcu_read_unlock(); -} -EXPORT_SYMBOL_GPL(rpc_clnt_xprt_switch_put); - void rpc_clnt_xprt_set_online(struct rpc_clnt *clnt, struct rpc_xprt *xprt) { struct rpc_xprt_switch *xps; - rcu_read_lock(); - xps = rcu_dereference(clnt->cl_xpi.xpi_xpswitch); - rcu_read_unlock(); + xps = rpc_clnt_xprt_switch_get(clnt); xprt_set_online_locked(xprt, xps); + xprt_switch_put(xps); } void rpc_clnt_xprt_switch_add_xprt(struct rpc_clnt *clnt, struct rpc_xprt *xprt) { + struct rpc_xprt_switch *xps; + if (rpc_clnt_xprt_switch_has_addr(clnt, (const struct sockaddr *)&xprt->addr)) { return rpc_clnt_xprt_set_online(clnt, xprt); } - rcu_read_lock(); - rpc_xprt_switch_add_xprt(rcu_dereference(clnt->cl_xpi.xpi_xpswitch), - xprt); - rcu_read_unlock(); + + xps = rpc_clnt_xprt_switch_get(clnt); + rpc_xprt_switch_add_xprt(xps, xprt); + xprt_switch_put(xps); } EXPORT_SYMBOL_GPL(rpc_clnt_xprt_switch_add_xprt); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 3f2ea7a0496f..f60c93e5a25d 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -463,7 +463,6 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, return NULL; serv->sv_name = prog->pg_name; serv->sv_program = prog; - kref_init(&serv->sv_refcnt); serv->sv_stats = prog->pg_stats; if (bufsize > RPCSVC_MAXPAYLOAD) bufsize = RPCSVC_MAXPAYLOAD; @@ -564,11 +563,13 @@ EXPORT_SYMBOL_GPL(svc_create_pooled); * protect sv_permsocks and sv_tempsocks. */ void -svc_destroy(struct kref *ref) +svc_destroy(struct svc_serv **servp) { - struct svc_serv *serv = container_of(ref, struct svc_serv, sv_refcnt); + struct svc_serv *serv = *servp; unsigned int i; + *servp = NULL; + dprintk("svc: svc_destroy(%s)\n", serv->sv_program->pg_name); timer_shutdown_sync(&serv->sv_temptimer); @@ -675,7 +676,6 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node) if (!rqstp) return ERR_PTR(-ENOMEM); - svc_get(serv); spin_lock_bh(&serv->sv_lock); serv->sv_nrthreads += 1; spin_unlock_bh(&serv->sv_lock); @@ -935,11 +935,6 @@ svc_exit_thread(struct svc_rqst *rqstp) svc_rqst_free(rqstp); - svc_put(serv); - /* That svc_put() cannot be the last, because the thread - * waiting for SP_VICTIM_REMAINS to clear must hold - * a reference. So it is still safe to access pool. - */ clear_and_wake_up_bit(SP_VICTIM_REMAINS, &pool->sp_flags); } EXPORT_SYMBOL_GPL(svc_exit_thread); @@ -1305,8 +1300,6 @@ svc_process_common(struct svc_rqst *rqstp) int rc; __be32 *p; - /* Will be turned off by GSS integrity and privacy services */ - set_bit(RQ_SPLICE_OK, &rqstp->rq_flags); /* Will be turned off only when NFSv4 Sessions are used */ set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); clear_bit(RQ_DROPME, &rqstp->rq_flags); @@ -1557,6 +1550,7 @@ void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp) { struct rpc_task *task; int proc_error; + struct rpc_timeout timeout; /* Build the svc_rqst used by the common processing routine */ rqstp->rq_xid = req->rq_xid; @@ -1602,8 +1596,16 @@ void svc_process_bc(struct rpc_rqst *req, struct svc_rqst *rqstp) return; } /* Finally, send the reply synchronously */ + if (rqstp->bc_to_initval > 0) { + timeout.to_initval = rqstp->bc_to_initval; + timeout.to_retries = rqstp->bc_to_initval; + } else { + timeout.to_initval = req->rq_xprt->timeout->to_initval; + timeout.to_initval = req->rq_xprt->timeout->to_retries; + } memcpy(&req->rq_snd_buf, &rqstp->rq_res, sizeof(req->rq_snd_buf)); - task = rpc_run_bc_task(req); + task = rpc_run_bc_task(req, &timeout); + if (IS_ERR(task)) return; diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 1b71055fc391..b4a85a227bd7 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -1362,29 +1362,36 @@ int svc_xprt_names(struct svc_serv *serv, char *buf, const int buflen) } EXPORT_SYMBOL_GPL(svc_xprt_names); - /*----------------------------------------------------------------------------*/ static void *svc_pool_stats_start(struct seq_file *m, loff_t *pos) { unsigned int pidx = (unsigned int)*pos; - struct svc_serv *serv = m->private; + struct svc_info *si = m->private; dprintk("svc_pool_stats_start, *pidx=%u\n", pidx); + mutex_lock(si->mutex); + if (!pidx) return SEQ_START_TOKEN; - return (pidx > serv->sv_nrpools ? NULL : &serv->sv_pools[pidx-1]); + if (!si->serv) + return NULL; + return pidx > si->serv->sv_nrpools ? NULL + : &si->serv->sv_pools[pidx - 1]; } static void *svc_pool_stats_next(struct seq_file *m, void *p, loff_t *pos) { struct svc_pool *pool = p; - struct svc_serv *serv = m->private; + struct svc_info *si = m->private; + struct svc_serv *serv = si->serv; dprintk("svc_pool_stats_next, *pos=%llu\n", *pos); - if (p == SEQ_START_TOKEN) { + if (!serv) { + pool = NULL; + } else if (p == SEQ_START_TOKEN) { pool = &serv->sv_pools[0]; } else { unsigned int pidx = (pool - &serv->sv_pools[0]); @@ -1399,6 +1406,9 @@ static void *svc_pool_stats_next(struct seq_file *m, void *p, loff_t *pos) static void svc_pool_stats_stop(struct seq_file *m, void *p) { + struct svc_info *si = m->private; + + mutex_unlock(si->mutex); } static int svc_pool_stats_show(struct seq_file *m, void *p) @@ -1426,14 +1436,18 @@ static const struct seq_operations svc_pool_stats_seq_ops = { .show = svc_pool_stats_show, }; -int svc_pool_stats_open(struct svc_serv *serv, struct file *file) +int svc_pool_stats_open(struct svc_info *info, struct file *file) { + struct seq_file *seq; int err; err = seq_open(file, &svc_pool_stats_seq_ops); - if (!err) - ((struct seq_file *) file->private_data)->private = serv; - return err; + if (err) + return err; + seq = file->private_data; + seq->private = info; + + return 0; } EXPORT_SYMBOL(svc_pool_stats_open); diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index aa4429d0b810..1619211f0960 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -160,6 +160,22 @@ svc_auth_unregister(rpc_authflavor_t flavor) } EXPORT_SYMBOL_GPL(svc_auth_unregister); +/** + * svc_auth_flavor - return RPC transaction's RPC_AUTH flavor + * @rqstp: RPC transaction context + * + * Returns an RPC flavor or GSS pseudoflavor. + */ +rpc_authflavor_t svc_auth_flavor(struct svc_rqst *rqstp) +{ + struct auth_ops *aops = rqstp->rq_authop; + + if (!aops->pseudoflavor) + return aops->flavour; + return aops->pseudoflavor(rqstp); +} +EXPORT_SYMBOL_GPL(svc_auth_flavor); + /************************************************** * 'auth_domains' are stored in a hash table indexed by name. * When the last reference to an 'auth_domain' is dropped, diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 998687421fa6..bfb2f78523a8 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1049,18 +1049,14 @@ static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp) struct rpc_rqst *req = NULL; struct kvec *src, *dst; __be32 *p = (__be32 *)rqstp->rq_arg.head[0].iov_base; - __be32 xid; - __be32 calldir; - - xid = *p++; - calldir = *p; + __be32 xid = *p; if (!bc_xprt) return -EAGAIN; spin_lock(&bc_xprt->queue_lock); req = xprt_lookup_rqst(bc_xprt, xid); if (!req) - goto unlock_notfound; + goto unlock_eagain; memcpy(&req->rq_private_buf, &req->rq_rcv_buf, sizeof(struct xdr_buf)); /* @@ -1077,12 +1073,6 @@ static int receive_cb_reply(struct svc_sock *svsk, struct svc_rqst *rqstp) rqstp->rq_arg.len = 0; spin_unlock(&bc_xprt->queue_lock); return 0; -unlock_notfound: - printk(KERN_NOTICE - "%s: Got unrecognized reply: " - "calldir 0x%x xpt_bc_xprt %p xid %08x\n", - __func__, ntohl(calldir), - bc_xprt, ntohl(xid)); unlock_eagain: spin_unlock(&bc_xprt->queue_lock); return -EAGAIN; diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 2364c485540c..af13fdfa6672 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -651,9 +651,9 @@ static unsigned long xprt_abs_ktime_to_jiffies(ktime_t abstime) jiffies + nsecs_to_jiffies(-delta); } -static unsigned long xprt_calc_majortimeo(struct rpc_rqst *req) +static unsigned long xprt_calc_majortimeo(struct rpc_rqst *req, + const struct rpc_timeout *to) { - const struct rpc_timeout *to = req->rq_task->tk_client->cl_timeout; unsigned long majortimeo = req->rq_timeout; if (to->to_exponential) @@ -665,9 +665,10 @@ static unsigned long xprt_calc_majortimeo(struct rpc_rqst *req) return majortimeo; } -static void xprt_reset_majortimeo(struct rpc_rqst *req) +static void xprt_reset_majortimeo(struct rpc_rqst *req, + const struct rpc_timeout *to) { - req->rq_majortimeo += xprt_calc_majortimeo(req); + req->rq_majortimeo += xprt_calc_majortimeo(req, to); } static void xprt_reset_minortimeo(struct rpc_rqst *req) @@ -675,7 +676,8 @@ static void xprt_reset_minortimeo(struct rpc_rqst *req) req->rq_minortimeo += req->rq_timeout; } -static void xprt_init_majortimeo(struct rpc_task *task, struct rpc_rqst *req) +static void xprt_init_majortimeo(struct rpc_task *task, struct rpc_rqst *req, + const struct rpc_timeout *to) { unsigned long time_init; struct rpc_xprt *xprt = req->rq_xprt; @@ -684,8 +686,9 @@ static void xprt_init_majortimeo(struct rpc_task *task, struct rpc_rqst *req) time_init = jiffies; else time_init = xprt_abs_ktime_to_jiffies(task->tk_start); - req->rq_timeout = task->tk_client->cl_timeout->to_initval; - req->rq_majortimeo = time_init + xprt_calc_majortimeo(req); + + req->rq_timeout = to->to_initval; + req->rq_majortimeo = time_init + xprt_calc_majortimeo(req, to); req->rq_minortimeo = time_init + req->rq_timeout; } @@ -713,7 +716,7 @@ int xprt_adjust_timeout(struct rpc_rqst *req) } else { req->rq_timeout = to->to_initval; req->rq_retries = 0; - xprt_reset_majortimeo(req); + xprt_reset_majortimeo(req, to); /* Reset the RTT counters == "slow start" */ spin_lock(&xprt->transport_lock); rpc_init_rtt(req->rq_task->tk_client->cl_rtt, to->to_initval); @@ -1886,7 +1889,7 @@ xprt_request_init(struct rpc_task *task) req->rq_snd_buf.bvec = NULL; req->rq_rcv_buf.bvec = NULL; req->rq_release_snd_buf = NULL; - xprt_init_majortimeo(task, req); + xprt_init_majortimeo(task, req, task->tk_client->cl_timeout); trace_xprt_reserve(req); } @@ -1983,7 +1986,8 @@ void xprt_release(struct rpc_task *task) #ifdef CONFIG_SUNRPC_BACKCHANNEL void -xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task) +xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task, + const struct rpc_timeout *to) { struct xdr_buf *xbufp = &req->rq_snd_buf; @@ -1996,6 +2000,13 @@ xprt_init_bc_request(struct rpc_rqst *req, struct rpc_task *task) */ xbufp->len = xbufp->head[0].iov_len + xbufp->page_len + xbufp->tail[0].iov_len; + /* + * Backchannel Replies are sent with !RPC_TASK_SOFT and + * RPC_TASK_NO_RETRANS_TIMEOUT. The major timeout setting + * affects only how long each Reply waits to be sent when + * a transport connection cannot be established. + */ + xprt_init_majortimeo(task, req, to); } #endif diff --git a/net/sunrpc/xprtmultipath.c b/net/sunrpc/xprtmultipath.c index 701250b305db..720d3ba742ec 100644 --- a/net/sunrpc/xprtmultipath.c +++ b/net/sunrpc/xprtmultipath.c @@ -284,7 +284,7 @@ struct rpc_xprt *_xprt_switch_find_current_entry(struct list_head *head, if (cur == pos) found = true; if (found && ((find_active && xprt_is_active(pos)) || - (!find_active && xprt_is_active(pos)))) + (!find_active && !xprt_is_active(pos)))) return pos; } return NULL; @@ -336,8 +336,9 @@ struct rpc_xprt *xprt_iter_current_entry_offline(struct rpc_xprt_iter *xpi) xprt_switch_find_current_entry_offline); } -bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, - const struct sockaddr *sap) +static +bool __rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, + const struct sockaddr *sap) { struct list_head *head; struct rpc_xprt *pos; @@ -356,6 +357,18 @@ bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, return false; } +bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, + const struct sockaddr *sap) +{ + bool res; + + rcu_read_lock(); + res = __rpc_xprt_switch_has_addr(xps, sap); + rcu_read_unlock(); + + return res; +} + static struct rpc_xprt *xprt_switch_find_next_entry(struct list_head *head, const struct rpc_xprt *cur, bool check_active) diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index f0d5eeed4c88..f86970733eb0 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -256,28 +256,44 @@ out_err: return rc; } +struct workqueue_struct *svcrdma_wq; + void svc_rdma_cleanup(void) { - dprintk("SVCRDMA Module Removed, deregister RPC RDMA transport\n"); svc_unreg_xprt_class(&svc_rdma_class); svc_rdma_proc_cleanup(); + if (svcrdma_wq) { + struct workqueue_struct *wq = svcrdma_wq; + + svcrdma_wq = NULL; + destroy_workqueue(wq); + } + + dprintk("SVCRDMA Module Removed, deregister RPC RDMA transport\n"); } int svc_rdma_init(void) { + struct workqueue_struct *wq; int rc; - dprintk("SVCRDMA Module Init, register RPC RDMA transport\n"); - dprintk("\tsvcrdma_ord : %d\n", svcrdma_ord); - dprintk("\tmax_requests : %u\n", svcrdma_max_requests); - dprintk("\tmax_bc_requests : %u\n", svcrdma_max_bc_requests); - dprintk("\tmax_inline : %d\n", svcrdma_max_req_size); + wq = alloc_workqueue("svcrdma", WQ_UNBOUND, 0); + if (!wq) + return -ENOMEM; rc = svc_rdma_proc_init(); - if (rc) + if (rc) { + destroy_workqueue(wq); return rc; + } - /* Register RDMA with the SVC transport switch */ + svcrdma_wq = wq; svc_reg_xprt_class(&svc_rdma_class); + + dprintk("SVCRDMA Module Init, register RPC RDMA transport\n"); + dprintk("\tsvcrdma_ord : %d\n", svcrdma_ord); + dprintk("\tmax_requests : %u\n", svcrdma_max_requests); + dprintk("\tmax_bc_requests : %u\n", svcrdma_max_bc_requests); + dprintk("\tmax_inline : %d\n", svcrdma_max_req_size); return 0; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index 7420a2c990c7..c9be6778643b 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -76,15 +76,12 @@ static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma, struct rpc_rqst *rqst, struct svc_rdma_send_ctxt *sctxt) { - struct svc_rdma_recv_ctxt *rctxt; + struct svc_rdma_pcl empty_pcl; int ret; - rctxt = svc_rdma_recv_ctxt_get(rdma); - if (!rctxt) - return -EIO; - - ret = svc_rdma_map_reply_msg(rdma, sctxt, rctxt, &rqst->rq_snd_buf); - svc_rdma_recv_ctxt_put(rdma, rctxt); + pcl_init(&empty_pcl); + ret = svc_rdma_map_reply_msg(rdma, sctxt, &empty_pcl, &empty_pcl, + &rqst->rq_snd_buf); if (ret < 0) return -EIO; diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 3b05f90a3e50..d72953f29258 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -115,13 +115,6 @@ svc_rdma_next_recv_ctxt(struct list_head *list) rc_list); } -static void svc_rdma_recv_cid_init(struct svcxprt_rdma *rdma, - struct rpc_rdma_cid *cid) -{ - cid->ci_queue_id = rdma->sc_rq_cq->res.id; - cid->ci_completion_id = atomic_inc_return(&rdma->sc_completion_ids); -} - static struct svc_rdma_recv_ctxt * svc_rdma_recv_ctxt_alloc(struct svcxprt_rdma *rdma) { @@ -130,7 +123,7 @@ svc_rdma_recv_ctxt_alloc(struct svcxprt_rdma *rdma) dma_addr_t addr; void *buffer; - ctxt = kmalloc_node(sizeof(*ctxt), GFP_KERNEL, node); + ctxt = kzalloc_node(sizeof(*ctxt), GFP_KERNEL, node); if (!ctxt) goto fail0; buffer = kmalloc_node(rdma->sc_max_req_size, GFP_KERNEL, node); @@ -156,6 +149,7 @@ svc_rdma_recv_ctxt_alloc(struct svcxprt_rdma *rdma) ctxt->rc_recv_sge.length = rdma->sc_max_req_size; ctxt->rc_recv_sge.lkey = rdma->sc_pd->local_dma_lkey; ctxt->rc_recv_buf = buffer; + svc_rdma_cc_init(rdma, &ctxt->rc_cc); return ctxt; fail2: @@ -204,18 +198,11 @@ struct svc_rdma_recv_ctxt *svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma) node = llist_del_first(&rdma->sc_recv_ctxts); if (!node) - goto out_empty; - ctxt = llist_entry(node, struct svc_rdma_recv_ctxt, rc_node); + return NULL; -out: + ctxt = llist_entry(node, struct svc_rdma_recv_ctxt, rc_node); ctxt->rc_page_count = 0; return ctxt; - -out_empty: - ctxt = svc_rdma_recv_ctxt_alloc(rdma); - if (!ctxt) - return NULL; - goto out; } /** @@ -227,6 +214,13 @@ out_empty: void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma, struct svc_rdma_recv_ctxt *ctxt) { + svc_rdma_cc_release(rdma, &ctxt->rc_cc, DMA_FROM_DEVICE); + + /* @rc_page_count is normally zero here, but error flows + * can leave pages in @rc_pages. + */ + release_pages(ctxt->rc_pages, ctxt->rc_page_count); + pcl_free(&ctxt->rc_call_pcl); pcl_free(&ctxt->rc_read_pcl); pcl_free(&ctxt->rc_write_pcl); @@ -271,13 +265,13 @@ static bool svc_rdma_refresh_recvs(struct svcxprt_rdma *rdma, if (!ctxt) break; - trace_svcrdma_post_recv(ctxt); + trace_svcrdma_post_recv(&ctxt->rc_cid); ctxt->rc_recv_wr.next = recv_chain; recv_chain = &ctxt->rc_recv_wr; rdma->sc_pending_recvs++; } if (!recv_chain) - return false; + return true; ret = ib_post_recv(rdma->sc_qp, recv_chain, &bad_wr); if (ret) @@ -301,10 +295,27 @@ err_free: * svc_rdma_post_recvs - Post initial set of Recv WRs * @rdma: fresh svcxprt_rdma * - * Returns true if successful, otherwise false. + * Return values: + * %true: Receive Queue initialization successful + * %false: memory allocation or DMA error */ bool svc_rdma_post_recvs(struct svcxprt_rdma *rdma) { + unsigned int total; + + /* For each credit, allocate enough recv_ctxts for one + * posted Receive and one RPC in process. + */ + total = (rdma->sc_max_requests * 2) + rdma->sc_recv_batch; + while (total--) { + struct svc_rdma_recv_ctxt *ctxt; + + ctxt = svc_rdma_recv_ctxt_alloc(rdma); + if (!ctxt) + return false; + llist_add(&ctxt->rc_node, &rdma->sc_recv_ctxts); + } + return svc_rdma_refresh_recvs(rdma, rdma->sc_max_requests); } @@ -373,6 +384,10 @@ void svc_rdma_flush_recv_queues(struct svcxprt_rdma *rdma) { struct svc_rdma_recv_ctxt *ctxt; + while ((ctxt = svc_rdma_next_recv_ctxt(&rdma->sc_read_complete_q))) { + list_del(&ctxt->rc_list); + svc_rdma_recv_ctxt_put(rdma, ctxt); + } while ((ctxt = svc_rdma_next_recv_ctxt(&rdma->sc_rq_dto_q))) { list_del(&ctxt->rc_list); svc_rdma_recv_ctxt_put(rdma, ctxt); @@ -754,6 +769,122 @@ static bool svc_rdma_is_reverse_direction_reply(struct svc_xprt *xprt, return true; } +/* Finish constructing the RPC Call message in rqstp::rq_arg. + * + * The incoming RPC/RDMA message is an RDMA_MSG type message + * with a single Read chunk (only the upper layer data payload + * was conveyed via RDMA Read). + */ +static void svc_rdma_read_complete_one(struct svc_rqst *rqstp, + struct svc_rdma_recv_ctxt *ctxt) +{ + struct svc_rdma_chunk *chunk = pcl_first_chunk(&ctxt->rc_read_pcl); + struct xdr_buf *buf = &rqstp->rq_arg; + unsigned int length; + + /* Split the Receive buffer between the head and tail + * buffers at Read chunk's position. XDR roundup of the + * chunk is not included in either the pagelist or in + * the tail. + */ + buf->tail[0].iov_base = buf->head[0].iov_base + chunk->ch_position; + buf->tail[0].iov_len = buf->head[0].iov_len - chunk->ch_position; + buf->head[0].iov_len = chunk->ch_position; + + /* Read chunk may need XDR roundup (see RFC 8166, s. 3.4.5.2). + * + * If the client already rounded up the chunk length, the + * length does not change. Otherwise, the length of the page + * list is increased to include XDR round-up. + * + * Currently these chunks always start at page offset 0, + * thus the rounded-up length never crosses a page boundary. + */ + buf->pages = &rqstp->rq_pages[0]; + length = xdr_align_size(chunk->ch_length); + buf->page_len = length; + buf->len += length; + buf->buflen += length; +} + +/* Finish constructing the RPC Call message in rqstp::rq_arg. + * + * The incoming RPC/RDMA message is an RDMA_MSG type message + * with payload in multiple Read chunks and no PZRC. + */ +static void svc_rdma_read_complete_multiple(struct svc_rqst *rqstp, + struct svc_rdma_recv_ctxt *ctxt) +{ + struct xdr_buf *buf = &rqstp->rq_arg; + + buf->len += ctxt->rc_readbytes; + buf->buflen += ctxt->rc_readbytes; + + buf->head[0].iov_base = page_address(rqstp->rq_pages[0]); + buf->head[0].iov_len = min_t(size_t, PAGE_SIZE, ctxt->rc_readbytes); + buf->pages = &rqstp->rq_pages[1]; + buf->page_len = ctxt->rc_readbytes - buf->head[0].iov_len; +} + +/* Finish constructing the RPC Call message in rqstp::rq_arg. + * + * The incoming RPC/RDMA message is an RDMA_NOMSG type message + * (the RPC message body was conveyed via RDMA Read). + */ +static void svc_rdma_read_complete_pzrc(struct svc_rqst *rqstp, + struct svc_rdma_recv_ctxt *ctxt) +{ + struct xdr_buf *buf = &rqstp->rq_arg; + + buf->len += ctxt->rc_readbytes; + buf->buflen += ctxt->rc_readbytes; + + buf->head[0].iov_base = page_address(rqstp->rq_pages[0]); + buf->head[0].iov_len = min_t(size_t, PAGE_SIZE, ctxt->rc_readbytes); + buf->pages = &rqstp->rq_pages[1]; + buf->page_len = ctxt->rc_readbytes - buf->head[0].iov_len; +} + +static noinline void svc_rdma_read_complete(struct svc_rqst *rqstp, + struct svc_rdma_recv_ctxt *ctxt) +{ + unsigned int i; + + /* Transfer the Read chunk pages into @rqstp.rq_pages, replacing + * the rq_pages that were already allocated for this rqstp. + */ + release_pages(rqstp->rq_respages, ctxt->rc_page_count); + for (i = 0; i < ctxt->rc_page_count; i++) + rqstp->rq_pages[i] = ctxt->rc_pages[i]; + + /* Update @rqstp's result send buffer to start after the + * last page in the RDMA Read payload. + */ + rqstp->rq_respages = &rqstp->rq_pages[ctxt->rc_page_count]; + rqstp->rq_next_page = rqstp->rq_respages + 1; + + /* Prevent svc_rdma_recv_ctxt_put() from releasing the + * pages in ctxt::rc_pages a second time. + */ + ctxt->rc_page_count = 0; + + /* Finish constructing the RPC Call message. The exact + * procedure for that depends on what kind of RPC/RDMA + * chunks were provided by the client. + */ + rqstp->rq_arg = ctxt->rc_saved_arg; + if (pcl_is_empty(&ctxt->rc_call_pcl)) { + if (ctxt->rc_read_pcl.cl_count == 1) + svc_rdma_read_complete_one(rqstp, ctxt); + else + svc_rdma_read_complete_multiple(rqstp, ctxt); + } else { + svc_rdma_read_complete_pzrc(rqstp, ctxt); + } + + trace_svcrdma_read_finished(&ctxt->rc_cid); +} + /** * svc_rdma_recvfrom - Receive an RPC call * @rqstp: request structure into which to receive an RPC Call @@ -798,8 +929,15 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) rqstp->rq_xprt_ctxt = NULL; - ctxt = NULL; spin_lock(&rdma_xprt->sc_rq_dto_lock); + ctxt = svc_rdma_next_recv_ctxt(&rdma_xprt->sc_read_complete_q); + if (ctxt) { + list_del(&ctxt->rc_list); + spin_unlock(&rdma_xprt->sc_rq_dto_lock); + svc_xprt_received(xprt); + svc_rdma_read_complete(rqstp, ctxt); + goto complete; + } ctxt = svc_rdma_next_recv_ctxt(&rdma_xprt->sc_rq_dto_q); if (ctxt) list_del(&ctxt->rc_list); @@ -831,12 +969,10 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) svc_rdma_get_inv_rkey(rdma_xprt, ctxt); if (!pcl_is_empty(&ctxt->rc_read_pcl) || - !pcl_is_empty(&ctxt->rc_call_pcl)) { - ret = svc_rdma_process_read_list(rdma_xprt, rqstp, ctxt); - if (ret < 0) - goto out_readfail; - } + !pcl_is_empty(&ctxt->rc_call_pcl)) + goto out_readlist; +complete: rqstp->rq_xprt_ctxt = ctxt; rqstp->rq_prot = IPPROTO_MAX; svc_xprt_copy_addrs(rqstp, xprt); @@ -848,12 +984,23 @@ out_err: svc_rdma_recv_ctxt_put(rdma_xprt, ctxt); return 0; -out_readfail: - if (ret == -EINVAL) - svc_rdma_send_error(rdma_xprt, ctxt, ret); - svc_rdma_recv_ctxt_put(rdma_xprt, ctxt); - svc_xprt_deferred_close(xprt); - return -ENOTCONN; +out_readlist: + /* This @rqstp is about to be recycled. Save the work + * already done constructing the Call message in rq_arg + * so it can be restored when the RDMA Reads have + * completed. + */ + ctxt->rc_saved_arg = rqstp->rq_arg; + + ret = svc_rdma_process_read_list(rdma_xprt, rqstp, ctxt); + if (ret < 0) { + if (ret == -EINVAL) + svc_rdma_send_error(rdma_xprt, ctxt, ret); + svc_rdma_recv_ctxt_put(rdma_xprt, ctxt); + svc_xprt_deferred_close(xprt); + return ret; + } + return 0; out_backchannel: svc_rdma_handle_bc_reply(rqstp, ctxt); diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index e460e25a1d6d..c00fcce61d1e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -39,6 +39,7 @@ struct svc_rdma_rw_ctxt { struct list_head rw_list; struct rdma_rw_ctx rw_ctx; unsigned int rw_nents; + unsigned int rw_first_sgl_nents; struct sg_table rw_sg_table; struct scatterlist rw_first_sgl[]; }; @@ -53,6 +54,8 @@ svc_rdma_next_ctxt(struct list_head *list) static struct svc_rdma_rw_ctxt * svc_rdma_get_rw_ctxt(struct svcxprt_rdma *rdma, unsigned int sges) { + struct ib_device *dev = rdma->sc_cm_id->device; + unsigned int first_sgl_nents = dev->attrs.max_send_sge; struct svc_rdma_rw_ctxt *ctxt; struct llist_node *node; @@ -62,32 +65,33 @@ svc_rdma_get_rw_ctxt(struct svcxprt_rdma *rdma, unsigned int sges) if (node) { ctxt = llist_entry(node, struct svc_rdma_rw_ctxt, rw_node); } else { - ctxt = kmalloc_node(struct_size(ctxt, rw_first_sgl, SG_CHUNK_SIZE), - GFP_KERNEL, ibdev_to_node(rdma->sc_cm_id->device)); + ctxt = kmalloc_node(struct_size(ctxt, rw_first_sgl, first_sgl_nents), + GFP_KERNEL, ibdev_to_node(dev)); if (!ctxt) goto out_noctx; INIT_LIST_HEAD(&ctxt->rw_list); + ctxt->rw_first_sgl_nents = first_sgl_nents; } ctxt->rw_sg_table.sgl = ctxt->rw_first_sgl; if (sg_alloc_table_chained(&ctxt->rw_sg_table, sges, ctxt->rw_sg_table.sgl, - SG_CHUNK_SIZE)) + first_sgl_nents)) goto out_free; return ctxt; out_free: kfree(ctxt); out_noctx: - trace_svcrdma_no_rwctx_err(rdma, sges); + trace_svcrdma_rwctx_empty(rdma, sges); return NULL; } static void __svc_rdma_put_rw_ctxt(struct svc_rdma_rw_ctxt *ctxt, struct llist_head *list) { - sg_free_table_chained(&ctxt->rw_sg_table, SG_CHUNK_SIZE); + sg_free_table_chained(&ctxt->rw_sg_table, ctxt->rw_first_sgl_nents); llist_add(&ctxt->rw_node, list); } @@ -135,57 +139,40 @@ static int svc_rdma_rw_ctx_init(struct svcxprt_rdma *rdma, ctxt->rw_sg_table.sgl, ctxt->rw_nents, 0, offset, handle, direction); if (unlikely(ret < 0)) { + trace_svcrdma_dma_map_rw_err(rdma, offset, handle, + ctxt->rw_nents, ret); svc_rdma_put_rw_ctxt(rdma, ctxt); - trace_svcrdma_dma_map_rw_err(rdma, ctxt->rw_nents, ret); } return ret; } -/* A chunk context tracks all I/O for moving one Read or Write - * chunk. This is a set of rdma_rw's that handle data movement - * for all segments of one chunk. - * - * These are small, acquired with a single allocator call, and - * no more than one is needed per chunk. They are allocated on - * demand, and not cached. +/** + * svc_rdma_cc_init - Initialize an svc_rdma_chunk_ctxt + * @rdma: controlling transport instance + * @cc: svc_rdma_chunk_ctxt to be initialized */ -struct svc_rdma_chunk_ctxt { - struct rpc_rdma_cid cc_cid; - struct ib_cqe cc_cqe; - struct svcxprt_rdma *cc_rdma; - struct list_head cc_rwctxts; - ktime_t cc_posttime; - int cc_sqecount; - enum ib_wc_status cc_status; - struct completion cc_done; -}; - -static void svc_rdma_cc_cid_init(struct svcxprt_rdma *rdma, - struct rpc_rdma_cid *cid) +void svc_rdma_cc_init(struct svcxprt_rdma *rdma, + struct svc_rdma_chunk_ctxt *cc) { - cid->ci_queue_id = rdma->sc_sq_cq->res.id; - cid->ci_completion_id = atomic_inc_return(&rdma->sc_completion_ids); -} + struct rpc_rdma_cid *cid = &cc->cc_cid; -static void svc_rdma_cc_init(struct svcxprt_rdma *rdma, - struct svc_rdma_chunk_ctxt *cc) -{ - svc_rdma_cc_cid_init(rdma, &cc->cc_cid); - cc->cc_rdma = rdma; + if (unlikely(!cid->ci_completion_id)) + svc_rdma_send_cid_init(rdma, cid); INIT_LIST_HEAD(&cc->cc_rwctxts); cc->cc_sqecount = 0; } -/* - * The consumed rw_ctx's are cleaned and placed on a local llist so - * that only one atomic llist operation is needed to put them all - * back on the free list. +/** + * svc_rdma_cc_release - Release resources held by a svc_rdma_chunk_ctxt + * @rdma: controlling transport instance + * @cc: svc_rdma_chunk_ctxt to be released + * @dir: DMA direction */ -static void svc_rdma_cc_release(struct svc_rdma_chunk_ctxt *cc, - enum dma_data_direction dir) +void svc_rdma_cc_release(struct svcxprt_rdma *rdma, + struct svc_rdma_chunk_ctxt *cc, + enum dma_data_direction dir) { - struct svcxprt_rdma *rdma = cc->cc_rdma; struct llist_node *first, *last; struct svc_rdma_rw_ctxt *ctxt; LLIST_HEAD(free); @@ -215,6 +202,8 @@ static void svc_rdma_cc_release(struct svc_rdma_chunk_ctxt *cc, * - Stores arguments for the SGL constructor functions */ struct svc_rdma_write_info { + struct svcxprt_rdma *wi_rdma; + const struct svc_rdma_chunk *wi_chunk; /* write state of this chunk */ @@ -227,6 +216,7 @@ struct svc_rdma_write_info { unsigned int wi_next_off; struct svc_rdma_chunk_ctxt wi_cc; + struct work_struct wi_work; }; static struct svc_rdma_write_info * @@ -235,25 +225,33 @@ svc_rdma_write_info_alloc(struct svcxprt_rdma *rdma, { struct svc_rdma_write_info *info; - info = kmalloc_node(sizeof(*info), GFP_KERNEL, + info = kzalloc_node(sizeof(*info), GFP_KERNEL, ibdev_to_node(rdma->sc_cm_id->device)); if (!info) return info; + info->wi_rdma = rdma; info->wi_chunk = chunk; - info->wi_seg_off = 0; - info->wi_seg_no = 0; svc_rdma_cc_init(rdma, &info->wi_cc); info->wi_cc.cc_cqe.done = svc_rdma_write_done; return info; } -static void svc_rdma_write_info_free(struct svc_rdma_write_info *info) +static void svc_rdma_write_info_free_async(struct work_struct *work) { - svc_rdma_cc_release(&info->wi_cc, DMA_TO_DEVICE); + struct svc_rdma_write_info *info; + + info = container_of(work, struct svc_rdma_write_info, wi_work); + svc_rdma_cc_release(info->wi_rdma, &info->wi_cc, DMA_TO_DEVICE); kfree(info); } +static void svc_rdma_write_info_free(struct svc_rdma_write_info *info) +{ + INIT_WORK(&info->wi_work, svc_rdma_write_info_free_async); + queue_work(svcrdma_wq, &info->wi_work); +} + /** * svc_rdma_write_done - Write chunk completion * @cq: controlling Completion Queue @@ -263,16 +261,16 @@ static void svc_rdma_write_info_free(struct svc_rdma_write_info *info) */ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc) { + struct svcxprt_rdma *rdma = cq->cq_context; struct ib_cqe *cqe = wc->wr_cqe; struct svc_rdma_chunk_ctxt *cc = container_of(cqe, struct svc_rdma_chunk_ctxt, cc_cqe); - struct svcxprt_rdma *rdma = cc->cc_rdma; struct svc_rdma_write_info *info = container_of(cc, struct svc_rdma_write_info, wi_cc); switch (wc->status) { case IB_WC_SUCCESS: - trace_svcrdma_wc_write(wc, &cc->cc_cid); + trace_svcrdma_wc_write(&cc->cc_cid); break; case IB_WC_WR_FLUSH_ERR: trace_svcrdma_wc_write_flush(wc, &cc->cc_cid); @@ -289,39 +287,6 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc) svc_rdma_write_info_free(info); } -/* State for pulling a Read chunk. - */ -struct svc_rdma_read_info { - struct svc_rqst *ri_rqst; - struct svc_rdma_recv_ctxt *ri_readctxt; - unsigned int ri_pageno; - unsigned int ri_pageoff; - unsigned int ri_totalbytes; - - struct svc_rdma_chunk_ctxt ri_cc; -}; - -static struct svc_rdma_read_info * -svc_rdma_read_info_alloc(struct svcxprt_rdma *rdma) -{ - struct svc_rdma_read_info *info; - - info = kmalloc_node(sizeof(*info), GFP_KERNEL, - ibdev_to_node(rdma->sc_cm_id->device)); - if (!info) - return info; - - svc_rdma_cc_init(rdma, &info->ri_cc); - info->ri_cc.cc_cqe.done = svc_rdma_wc_read_done; - return info; -} - -static void svc_rdma_read_info_free(struct svc_rdma_read_info *info) -{ - svc_rdma_cc_release(&info->ri_cc, DMA_FROM_DEVICE); - kfree(info); -} - /** * svc_rdma_wc_read_done - Handle completion of an RDMA Read ctx * @cq: controlling Completion Queue @@ -330,17 +295,27 @@ static void svc_rdma_read_info_free(struct svc_rdma_read_info *info) */ static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc) { + struct svcxprt_rdma *rdma = cq->cq_context; struct ib_cqe *cqe = wc->wr_cqe; struct svc_rdma_chunk_ctxt *cc = container_of(cqe, struct svc_rdma_chunk_ctxt, cc_cqe); - struct svc_rdma_read_info *info; + struct svc_rdma_recv_ctxt *ctxt; + svc_rdma_wake_send_waiters(rdma, cc->cc_sqecount); + + ctxt = container_of(cc, struct svc_rdma_recv_ctxt, rc_cc); switch (wc->status) { case IB_WC_SUCCESS: - info = container_of(cc, struct svc_rdma_read_info, ri_cc); - trace_svcrdma_wc_read(wc, &cc->cc_cid, info->ri_totalbytes, + trace_svcrdma_wc_read(wc, &cc->cc_cid, ctxt->rc_readbytes, cc->cc_posttime); - break; + + spin_lock(&rdma->sc_rq_dto_lock); + list_add_tail(&ctxt->rc_list, &rdma->sc_read_complete_q); + /* the unlock pairs with the smp_rmb in svc_xprt_ready */ + set_bit(XPT_DATA, &rdma->sc_xprt.xpt_flags); + spin_unlock(&rdma->sc_rq_dto_lock); + svc_xprt_enqueue(&rdma->sc_xprt); + return; case IB_WC_WR_FLUSH_ERR: trace_svcrdma_wc_read_flush(wc, &cc->cc_cid); break; @@ -348,10 +323,13 @@ static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc) trace_svcrdma_wc_read_err(wc, &cc->cc_cid); } - svc_rdma_wake_send_waiters(cc->cc_rdma, cc->cc_sqecount); - cc->cc_status = wc->status; - complete(&cc->cc_done); - return; + /* The RDMA Read has flushed, so the incoming RPC message + * cannot be constructed and must be dropped. Signal the + * loss to the client by closing the connection. + */ + svc_rdma_cc_release(rdma, cc, DMA_FROM_DEVICE); + svc_rdma_recv_ctxt_put(rdma, ctxt); + svc_xprt_deferred_close(&rdma->sc_xprt); } /* @@ -360,9 +338,9 @@ static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc) * even if one or more WRs are flushed. This is true when posting * an rdma_rw_ctx or when posting a single signaled WR. */ -static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc) +static int svc_rdma_post_chunk_ctxt(struct svcxprt_rdma *rdma, + struct svc_rdma_chunk_ctxt *cc) { - struct svcxprt_rdma *rdma = cc->cc_rdma; struct ib_send_wr *first_wr; const struct ib_send_wr *bad_wr; struct list_head *tmp; @@ -396,14 +374,14 @@ static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc) } percpu_counter_inc(&svcrdma_stat_sq_starve); - trace_svcrdma_sq_full(rdma); + trace_svcrdma_sq_full(rdma, &cc->cc_cid); atomic_add(cc->cc_sqecount, &rdma->sc_sq_avail); wait_event(rdma->sc_send_wait, atomic_read(&rdma->sc_sq_avail) > cc->cc_sqecount); - trace_svcrdma_sq_retry(rdma); + trace_svcrdma_sq_retry(rdma, &cc->cc_cid); } while (1); - trace_svcrdma_sq_post_err(rdma, ret); + trace_svcrdma_sq_post_err(rdma, &cc->cc_cid, ret); svc_xprt_deferred_close(&rdma->sc_xprt); /* If even one was posted, there will be a completion. */ @@ -473,7 +451,7 @@ svc_rdma_build_writes(struct svc_rdma_write_info *info, unsigned int remaining) { struct svc_rdma_chunk_ctxt *cc = &info->wi_cc; - struct svcxprt_rdma *rdma = cc->cc_rdma; + struct svcxprt_rdma *rdma = info->wi_rdma; const struct svc_rdma_segment *seg; struct svc_rdma_rw_ctxt *ctxt; int ret; @@ -516,7 +494,7 @@ svc_rdma_build_writes(struct svc_rdma_write_info *info, return 0; out_overflow: - trace_svcrdma_small_wrch_err(rdma, remaining, info->wi_seg_no, + trace_svcrdma_small_wrch_err(&cc->cc_cid, remaining, info->wi_seg_no, info->wi_chunk->ch_segcount); return -E2BIG; } @@ -633,7 +611,7 @@ int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, goto out_err; trace_svcrdma_post_write_chunk(&cc->cc_cid, cc->cc_sqecount); - ret = svc_rdma_post_chunk_ctxt(cc); + ret = svc_rdma_post_chunk_ctxt(rdma, cc); if (ret < 0) goto out_err; return xdr->len; @@ -680,7 +658,7 @@ int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma, goto out_err; trace_svcrdma_post_reply_chunk(&cc->cc_cid, cc->cc_sqecount); - ret = svc_rdma_post_chunk_ctxt(cc); + ret = svc_rdma_post_chunk_ctxt(rdma, cc); if (ret < 0) goto out_err; @@ -693,7 +671,8 @@ out_err: /** * svc_rdma_build_read_segment - Build RDMA Read WQEs to pull one RDMA segment - * @info: context for ongoing I/O + * @rqstp: RPC transaction context + * @head: context for ongoing I/O * @segment: co-ordinates of remote memory to be read * * Returns: @@ -702,20 +681,20 @@ out_err: * %-ENOMEM: allocating a local resources failed * %-EIO: a DMA mapping error occurred */ -static int svc_rdma_build_read_segment(struct svc_rdma_read_info *info, +static int svc_rdma_build_read_segment(struct svc_rqst *rqstp, + struct svc_rdma_recv_ctxt *head, const struct svc_rdma_segment *segment) { - struct svc_rdma_recv_ctxt *head = info->ri_readctxt; - struct svc_rdma_chunk_ctxt *cc = &info->ri_cc; - struct svc_rqst *rqstp = info->ri_rqst; + struct svcxprt_rdma *rdma = svc_rdma_rqst_rdma(rqstp); + struct svc_rdma_chunk_ctxt *cc = &head->rc_cc; unsigned int sge_no, seg_len, len; struct svc_rdma_rw_ctxt *ctxt; struct scatterlist *sg; int ret; len = segment->rs_length; - sge_no = PAGE_ALIGN(info->ri_pageoff + len) >> PAGE_SHIFT; - ctxt = svc_rdma_get_rw_ctxt(cc->cc_rdma, sge_no); + sge_no = PAGE_ALIGN(head->rc_pageoff + len) >> PAGE_SHIFT; + ctxt = svc_rdma_get_rw_ctxt(rdma, sge_no); if (!ctxt) return -ENOMEM; ctxt->rw_nents = sge_no; @@ -723,29 +702,27 @@ static int svc_rdma_build_read_segment(struct svc_rdma_read_info *info, sg = ctxt->rw_sg_table.sgl; for (sge_no = 0; sge_no < ctxt->rw_nents; sge_no++) { seg_len = min_t(unsigned int, len, - PAGE_SIZE - info->ri_pageoff); + PAGE_SIZE - head->rc_pageoff); - if (!info->ri_pageoff) + if (!head->rc_pageoff) head->rc_page_count++; - sg_set_page(sg, rqstp->rq_pages[info->ri_pageno], - seg_len, info->ri_pageoff); + sg_set_page(sg, rqstp->rq_pages[head->rc_curpage], + seg_len, head->rc_pageoff); sg = sg_next(sg); - info->ri_pageoff += seg_len; - if (info->ri_pageoff == PAGE_SIZE) { - info->ri_pageno++; - info->ri_pageoff = 0; + head->rc_pageoff += seg_len; + if (head->rc_pageoff == PAGE_SIZE) { + head->rc_curpage++; + head->rc_pageoff = 0; } len -= seg_len; - /* Safety check */ - if (len && - &rqstp->rq_pages[info->ri_pageno + 1] > rqstp->rq_page_end) + if (len && ((head->rc_curpage + 1) > ARRAY_SIZE(rqstp->rq_pages))) goto out_overrun; } - ret = svc_rdma_rw_ctx_init(cc->cc_rdma, ctxt, segment->rs_offset, + ret = svc_rdma_rw_ctx_init(rdma, ctxt, segment->rs_offset, segment->rs_handle, DMA_FROM_DEVICE); if (ret < 0) return -EIO; @@ -756,13 +733,14 @@ static int svc_rdma_build_read_segment(struct svc_rdma_read_info *info, return 0; out_overrun: - trace_svcrdma_page_overrun_err(cc->cc_rdma, rqstp, info->ri_pageno); + trace_svcrdma_page_overrun_err(&cc->cc_cid, head->rc_curpage); return -EINVAL; } /** * svc_rdma_build_read_chunk - Build RDMA Read WQEs to pull one RDMA chunk - * @info: context for ongoing I/O + * @rqstp: RPC transaction context + * @head: context for ongoing I/O * @chunk: Read chunk to pull * * Return values: @@ -771,7 +749,8 @@ out_overrun: * %-ENOMEM: allocating a local resources failed * %-EIO: a DMA mapping error occurred */ -static int svc_rdma_build_read_chunk(struct svc_rdma_read_info *info, +static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp, + struct svc_rdma_recv_ctxt *head, const struct svc_rdma_chunk *chunk) { const struct svc_rdma_segment *segment; @@ -779,56 +758,56 @@ static int svc_rdma_build_read_chunk(struct svc_rdma_read_info *info, ret = -EINVAL; pcl_for_each_segment(segment, chunk) { - ret = svc_rdma_build_read_segment(info, segment); + ret = svc_rdma_build_read_segment(rqstp, head, segment); if (ret < 0) break; - info->ri_totalbytes += segment->rs_length; + head->rc_readbytes += segment->rs_length; } return ret; } /** * svc_rdma_copy_inline_range - Copy part of the inline content into pages - * @info: context for RDMA Reads + * @rqstp: RPC transaction context + * @head: context for ongoing I/O * @offset: offset into the Receive buffer of region to copy * @remaining: length of region to copy * * Take a page at a time from rqstp->rq_pages and copy the inline * content from the Receive buffer into that page. Update - * info->ri_pageno and info->ri_pageoff so that the next RDMA Read + * head->rc_curpage and head->rc_pageoff so that the next RDMA Read * result will land contiguously with the copied content. * * Return values: * %0: Inline content was successfully copied * %-EINVAL: offset or length was incorrect */ -static int svc_rdma_copy_inline_range(struct svc_rdma_read_info *info, +static int svc_rdma_copy_inline_range(struct svc_rqst *rqstp, + struct svc_rdma_recv_ctxt *head, unsigned int offset, unsigned int remaining) { - struct svc_rdma_recv_ctxt *head = info->ri_readctxt; unsigned char *dst, *src = head->rc_recv_buf; - struct svc_rqst *rqstp = info->ri_rqst; unsigned int page_no, numpages; - numpages = PAGE_ALIGN(info->ri_pageoff + remaining) >> PAGE_SHIFT; + numpages = PAGE_ALIGN(head->rc_pageoff + remaining) >> PAGE_SHIFT; for (page_no = 0; page_no < numpages; page_no++) { unsigned int page_len; page_len = min_t(unsigned int, remaining, - PAGE_SIZE - info->ri_pageoff); + PAGE_SIZE - head->rc_pageoff); - if (!info->ri_pageoff) + if (!head->rc_pageoff) head->rc_page_count++; - dst = page_address(rqstp->rq_pages[info->ri_pageno]); - memcpy(dst + info->ri_pageno, src + offset, page_len); + dst = page_address(rqstp->rq_pages[head->rc_curpage]); + memcpy(dst + head->rc_curpage, src + offset, page_len); - info->ri_totalbytes += page_len; - info->ri_pageoff += page_len; - if (info->ri_pageoff == PAGE_SIZE) { - info->ri_pageno++; - info->ri_pageoff = 0; + head->rc_readbytes += page_len; + head->rc_pageoff += page_len; + if (head->rc_pageoff == PAGE_SIZE) { + head->rc_curpage++; + head->rc_pageoff = 0; } remaining -= page_len; offset += page_len; @@ -839,7 +818,8 @@ static int svc_rdma_copy_inline_range(struct svc_rdma_read_info *info, /** * svc_rdma_read_multiple_chunks - Construct RDMA Reads to pull data item Read chunks - * @info: context for RDMA Reads + * @rqstp: RPC transaction context + * @head: context for ongoing I/O * * The chunk data lands in rqstp->rq_arg as a series of contiguous pages, * like an incoming TCP call. @@ -851,11 +831,11 @@ static int svc_rdma_copy_inline_range(struct svc_rdma_read_info *info, * %-ENOTCONN: posting failed (connection is lost), * %-EIO: rdma_rw initialization failed (DMA mapping, etc). */ -static noinline int svc_rdma_read_multiple_chunks(struct svc_rdma_read_info *info) +static noinline int +svc_rdma_read_multiple_chunks(struct svc_rqst *rqstp, + struct svc_rdma_recv_ctxt *head) { - struct svc_rdma_recv_ctxt *head = info->ri_readctxt; const struct svc_rdma_pcl *pcl = &head->rc_read_pcl; - struct xdr_buf *buf = &info->ri_rqst->rq_arg; struct svc_rdma_chunk *chunk, *next; unsigned int start, length; int ret; @@ -863,12 +843,12 @@ static noinline int svc_rdma_read_multiple_chunks(struct svc_rdma_read_info *inf start = 0; chunk = pcl_first_chunk(pcl); length = chunk->ch_position; - ret = svc_rdma_copy_inline_range(info, start, length); + ret = svc_rdma_copy_inline_range(rqstp, head, start, length); if (ret < 0) return ret; pcl_for_each_chunk(chunk, pcl) { - ret = svc_rdma_build_read_chunk(info, chunk); + ret = svc_rdma_build_read_chunk(rqstp, head, chunk); if (ret < 0) return ret; @@ -877,31 +857,21 @@ static noinline int svc_rdma_read_multiple_chunks(struct svc_rdma_read_info *inf break; start += length; - length = next->ch_position - info->ri_totalbytes; - ret = svc_rdma_copy_inline_range(info, start, length); + length = next->ch_position - head->rc_readbytes; + ret = svc_rdma_copy_inline_range(rqstp, head, start, length); if (ret < 0) return ret; } start += length; length = head->rc_byte_len - start; - ret = svc_rdma_copy_inline_range(info, start, length); - if (ret < 0) - return ret; - - buf->len += info->ri_totalbytes; - buf->buflen += info->ri_totalbytes; - - buf->head[0].iov_base = page_address(info->ri_rqst->rq_pages[0]); - buf->head[0].iov_len = min_t(size_t, PAGE_SIZE, info->ri_totalbytes); - buf->pages = &info->ri_rqst->rq_pages[1]; - buf->page_len = info->ri_totalbytes - buf->head[0].iov_len; - return 0; + return svc_rdma_copy_inline_range(rqstp, head, start, length); } /** * svc_rdma_read_data_item - Construct RDMA Reads to pull data item Read chunks - * @info: context for RDMA Reads + * @rqstp: RPC transaction context + * @head: context for ongoing I/O * * The chunk data lands in the page list of rqstp->rq_arg.pages. * @@ -916,50 +886,17 @@ static noinline int svc_rdma_read_multiple_chunks(struct svc_rdma_read_info *inf * %-ENOTCONN: posting failed (connection is lost), * %-EIO: rdma_rw initialization failed (DMA mapping, etc). */ -static int svc_rdma_read_data_item(struct svc_rdma_read_info *info) +static int svc_rdma_read_data_item(struct svc_rqst *rqstp, + struct svc_rdma_recv_ctxt *head) { - struct svc_rdma_recv_ctxt *head = info->ri_readctxt; - struct xdr_buf *buf = &info->ri_rqst->rq_arg; - struct svc_rdma_chunk *chunk; - unsigned int length; - int ret; - - chunk = pcl_first_chunk(&head->rc_read_pcl); - ret = svc_rdma_build_read_chunk(info, chunk); - if (ret < 0) - goto out; - - /* Split the Receive buffer between the head and tail - * buffers at Read chunk's position. XDR roundup of the - * chunk is not included in either the pagelist or in - * the tail. - */ - buf->tail[0].iov_base = buf->head[0].iov_base + chunk->ch_position; - buf->tail[0].iov_len = buf->head[0].iov_len - chunk->ch_position; - buf->head[0].iov_len = chunk->ch_position; - - /* Read chunk may need XDR roundup (see RFC 8166, s. 3.4.5.2). - * - * If the client already rounded up the chunk length, the - * length does not change. Otherwise, the length of the page - * list is increased to include XDR round-up. - * - * Currently these chunks always start at page offset 0, - * thus the rounded-up length never crosses a page boundary. - */ - buf->pages = &info->ri_rqst->rq_pages[0]; - length = xdr_align_size(chunk->ch_length); - buf->page_len = length; - buf->len += length; - buf->buflen += length; - -out: - return ret; + return svc_rdma_build_read_chunk(rqstp, head, + pcl_first_chunk(&head->rc_read_pcl)); } /** - * svc_rdma_read_chunk_range - Build RDMA Read WQEs for portion of a chunk - * @info: context for RDMA Reads + * svc_rdma_read_chunk_range - Build RDMA Read WRs for portion of a chunk + * @rqstp: RPC transaction context + * @head: context for ongoing I/O * @chunk: parsed Call chunk to pull * @offset: offset of region to pull * @length: length of region to pull @@ -971,7 +908,8 @@ out: * %-ENOTCONN: posting failed (connection is lost), * %-EIO: rdma_rw initialization failed (DMA mapping, etc). */ -static int svc_rdma_read_chunk_range(struct svc_rdma_read_info *info, +static int svc_rdma_read_chunk_range(struct svc_rqst *rqstp, + struct svc_rdma_recv_ctxt *head, const struct svc_rdma_chunk *chunk, unsigned int offset, unsigned int length) { @@ -991,11 +929,11 @@ static int svc_rdma_read_chunk_range(struct svc_rdma_read_info *info, dummy.rs_length = min_t(u32, length, segment->rs_length) - offset; dummy.rs_offset = segment->rs_offset + offset; - ret = svc_rdma_build_read_segment(info, &dummy); + ret = svc_rdma_build_read_segment(rqstp, head, &dummy); if (ret < 0) break; - info->ri_totalbytes += dummy.rs_length; + head->rc_readbytes += dummy.rs_length; length -= dummy.rs_length; offset = 0; } @@ -1004,7 +942,8 @@ static int svc_rdma_read_chunk_range(struct svc_rdma_read_info *info, /** * svc_rdma_read_call_chunk - Build RDMA Read WQEs to pull a Long Message - * @info: context for RDMA Reads + * @rqstp: RPC transaction context + * @head: context for ongoing I/O * * Return values: * %0: RDMA Read WQEs were successfully built @@ -1013,9 +952,9 @@ static int svc_rdma_read_chunk_range(struct svc_rdma_read_info *info, * %-ENOTCONN: posting failed (connection is lost), * %-EIO: rdma_rw initialization failed (DMA mapping, etc). */ -static int svc_rdma_read_call_chunk(struct svc_rdma_read_info *info) +static int svc_rdma_read_call_chunk(struct svc_rqst *rqstp, + struct svc_rdma_recv_ctxt *head) { - struct svc_rdma_recv_ctxt *head = info->ri_readctxt; const struct svc_rdma_chunk *call_chunk = pcl_first_chunk(&head->rc_call_pcl); const struct svc_rdma_pcl *pcl = &head->rc_read_pcl; @@ -1024,17 +963,18 @@ static int svc_rdma_read_call_chunk(struct svc_rdma_read_info *info) int ret; if (pcl_is_empty(pcl)) - return svc_rdma_build_read_chunk(info, call_chunk); + return svc_rdma_build_read_chunk(rqstp, head, call_chunk); start = 0; chunk = pcl_first_chunk(pcl); length = chunk->ch_position; - ret = svc_rdma_read_chunk_range(info, call_chunk, start, length); + ret = svc_rdma_read_chunk_range(rqstp, head, call_chunk, + start, length); if (ret < 0) return ret; pcl_for_each_chunk(chunk, pcl) { - ret = svc_rdma_build_read_chunk(info, chunk); + ret = svc_rdma_build_read_chunk(rqstp, head, chunk); if (ret < 0) return ret; @@ -1043,8 +983,8 @@ static int svc_rdma_read_call_chunk(struct svc_rdma_read_info *info) break; start += length; - length = next->ch_position - info->ri_totalbytes; - ret = svc_rdma_read_chunk_range(info, call_chunk, + length = next->ch_position - head->rc_readbytes; + ret = svc_rdma_read_chunk_range(rqstp, head, call_chunk, start, length); if (ret < 0) return ret; @@ -1052,12 +992,14 @@ static int svc_rdma_read_call_chunk(struct svc_rdma_read_info *info) start += length; length = call_chunk->ch_length - start; - return svc_rdma_read_chunk_range(info, call_chunk, start, length); + return svc_rdma_read_chunk_range(rqstp, head, call_chunk, + start, length); } /** * svc_rdma_read_special - Build RDMA Read WQEs to pull a Long Message - * @info: context for RDMA Reads + * @rqstp: RPC transaction context + * @head: context for ongoing I/O * * The start of the data lands in the first page just after the * Transport header, and the rest lands in rqstp->rq_arg.pages. @@ -1073,25 +1015,31 @@ static int svc_rdma_read_call_chunk(struct svc_rdma_read_info *info) * %-ENOTCONN: posting failed (connection is lost), * %-EIO: rdma_rw initialization failed (DMA mapping, etc). */ -static noinline int svc_rdma_read_special(struct svc_rdma_read_info *info) +static noinline int svc_rdma_read_special(struct svc_rqst *rqstp, + struct svc_rdma_recv_ctxt *head) { - struct xdr_buf *buf = &info->ri_rqst->rq_arg; - int ret; - - ret = svc_rdma_read_call_chunk(info); - if (ret < 0) - goto out; - - buf->len += info->ri_totalbytes; - buf->buflen += info->ri_totalbytes; + return svc_rdma_read_call_chunk(rqstp, head); +} - buf->head[0].iov_base = page_address(info->ri_rqst->rq_pages[0]); - buf->head[0].iov_len = min_t(size_t, PAGE_SIZE, info->ri_totalbytes); - buf->pages = &info->ri_rqst->rq_pages[1]; - buf->page_len = info->ri_totalbytes - buf->head[0].iov_len; +/* Pages under I/O have been copied to head->rc_pages. Ensure that + * svc_xprt_release() does not put them when svc_rdma_recvfrom() + * returns. This has to be done after all Read WRs are constructed + * to properly handle a page that happens to be part of I/O on behalf + * of two different RDMA segments. + * + * Note: if the subsequent post_send fails, these pages have already + * been moved to head->rc_pages and thus will be cleaned up by + * svc_rdma_recv_ctxt_put(). + */ +static void svc_rdma_clear_rqst_pages(struct svc_rqst *rqstp, + struct svc_rdma_recv_ctxt *head) +{ + unsigned int i; -out: - return ret; + for (i = 0; i < head->rc_page_count; i++) { + head->rc_pages[i] = rqstp->rq_pages[i]; + rqstp->rq_pages[i] = NULL; + } } /** @@ -1121,49 +1069,27 @@ int svc_rdma_process_read_list(struct svcxprt_rdma *rdma, struct svc_rqst *rqstp, struct svc_rdma_recv_ctxt *head) { - struct svc_rdma_read_info *info; - struct svc_rdma_chunk_ctxt *cc; + struct svc_rdma_chunk_ctxt *cc = &head->rc_cc; int ret; - info = svc_rdma_read_info_alloc(rdma); - if (!info) - return -ENOMEM; - cc = &info->ri_cc; - info->ri_rqst = rqstp; - info->ri_readctxt = head; - info->ri_pageno = 0; - info->ri_pageoff = 0; - info->ri_totalbytes = 0; + cc->cc_cqe.done = svc_rdma_wc_read_done; + cc->cc_sqecount = 0; + head->rc_pageoff = 0; + head->rc_curpage = 0; + head->rc_readbytes = 0; if (pcl_is_empty(&head->rc_call_pcl)) { if (head->rc_read_pcl.cl_count == 1) - ret = svc_rdma_read_data_item(info); + ret = svc_rdma_read_data_item(rqstp, head); else - ret = svc_rdma_read_multiple_chunks(info); + ret = svc_rdma_read_multiple_chunks(rqstp, head); } else - ret = svc_rdma_read_special(info); + ret = svc_rdma_read_special(rqstp, head); + svc_rdma_clear_rqst_pages(rqstp, head); if (ret < 0) - goto out_err; + return ret; trace_svcrdma_post_read_chunk(&cc->cc_cid, cc->cc_sqecount); - init_completion(&cc->cc_done); - ret = svc_rdma_post_chunk_ctxt(cc); - if (ret < 0) - goto out_err; - - ret = 1; - wait_for_completion(&cc->cc_done); - if (cc->cc_status != IB_WC_SUCCESS) - ret = -EIO; - - /* rq_respages starts after the last arg page */ - rqstp->rq_respages = &rqstp->rq_pages[head->rc_page_count]; - rqstp->rq_next_page = rqstp->rq_respages + 1; - - /* Ensure svc_rdma_recv_ctxt_put() does not try to release pages */ - head->rc_page_count = 0; - -out_err: - svc_rdma_read_info_free(info); - return ret; + ret = svc_rdma_post_chunk_ctxt(rdma, cc); + return ret < 0 ? ret : 1; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index c6644cca52c5..1a49b7f02041 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -113,13 +113,6 @@ static void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc); -static void svc_rdma_send_cid_init(struct svcxprt_rdma *rdma, - struct rpc_rdma_cid *cid) -{ - cid->ci_queue_id = rdma->sc_sq_cq->res.id; - cid->ci_completion_id = atomic_inc_return(&rdma->sc_completion_ids); -} - static struct svc_rdma_send_ctxt * svc_rdma_send_ctxt_alloc(struct svcxprt_rdma *rdma) { @@ -129,7 +122,7 @@ svc_rdma_send_ctxt_alloc(struct svcxprt_rdma *rdma) void *buffer; int i; - ctxt = kmalloc_node(struct_size(ctxt, sc_sges, rdma->sc_max_send_sges), + ctxt = kzalloc_node(struct_size(ctxt, sc_sges, rdma->sc_max_send_sges), GFP_KERNEL, node); if (!ctxt) goto fail0; @@ -143,6 +136,7 @@ svc_rdma_send_ctxt_alloc(struct svcxprt_rdma *rdma) svc_rdma_send_cid_init(rdma, &ctxt->sc_cid); + ctxt->sc_rdma = rdma; ctxt->sc_send_wr.next = NULL; ctxt->sc_send_wr.wr_cqe = &ctxt->sc_cqe; ctxt->sc_send_wr.sg_list = ctxt->sc_sges; @@ -200,10 +194,11 @@ struct svc_rdma_send_ctxt *svc_rdma_send_ctxt_get(struct svcxprt_rdma *rdma) spin_lock(&rdma->sc_send_lock); node = llist_del_first(&rdma->sc_send_ctxts); + spin_unlock(&rdma->sc_send_lock); if (!node) goto out_empty; + ctxt = llist_entry(node, struct svc_rdma_send_ctxt, sc_node); - spin_unlock(&rdma->sc_send_lock); out: rpcrdma_set_xdrlen(&ctxt->sc_hdrbuf, 0); @@ -216,22 +211,14 @@ out: return ctxt; out_empty: - spin_unlock(&rdma->sc_send_lock); ctxt = svc_rdma_send_ctxt_alloc(rdma); if (!ctxt) return NULL; goto out; } -/** - * svc_rdma_send_ctxt_put - Return send_ctxt to free list - * @rdma: controlling svcxprt_rdma - * @ctxt: object to return to the free list - * - * Pages left in sc_pages are DMA unmapped and released. - */ -void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma, - struct svc_rdma_send_ctxt *ctxt) +static void svc_rdma_send_ctxt_release(struct svcxprt_rdma *rdma, + struct svc_rdma_send_ctxt *ctxt) { struct ib_device *device = rdma->sc_cm_id->device; unsigned int i; @@ -243,18 +230,40 @@ void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma, * remains mapped until @ctxt is destroyed. */ for (i = 1; i < ctxt->sc_send_wr.num_sge; i++) { + trace_svcrdma_dma_unmap_page(&ctxt->sc_cid, + ctxt->sc_sges[i].addr, + ctxt->sc_sges[i].length); ib_dma_unmap_page(device, ctxt->sc_sges[i].addr, ctxt->sc_sges[i].length, DMA_TO_DEVICE); - trace_svcrdma_dma_unmap_page(rdma, - ctxt->sc_sges[i].addr, - ctxt->sc_sges[i].length); } llist_add(&ctxt->sc_node, &rdma->sc_send_ctxts); } +static void svc_rdma_send_ctxt_put_async(struct work_struct *work) +{ + struct svc_rdma_send_ctxt *ctxt; + + ctxt = container_of(work, struct svc_rdma_send_ctxt, sc_work); + svc_rdma_send_ctxt_release(ctxt->sc_rdma, ctxt); +} + +/** + * svc_rdma_send_ctxt_put - Return send_ctxt to free list + * @rdma: controlling svcxprt_rdma + * @ctxt: object to return to the free list + * + * Pages left in sc_pages are DMA unmapped and released. + */ +void svc_rdma_send_ctxt_put(struct svcxprt_rdma *rdma, + struct svc_rdma_send_ctxt *ctxt) +{ + INIT_WORK(&ctxt->sc_work, svc_rdma_send_ctxt_put_async); + queue_work(svcrdma_wq, &ctxt->sc_work); +} + /** * svc_rdma_wake_send_waiters - manage Send Queue accounting * @rdma: controlling transport @@ -289,7 +298,7 @@ static void svc_rdma_wc_send(struct ib_cq *cq, struct ib_wc *wc) if (unlikely(wc->status != IB_WC_SUCCESS)) goto flushed; - trace_svcrdma_wc_send(wc, &ctxt->sc_cid); + trace_svcrdma_wc_send(&ctxt->sc_cid); svc_rdma_send_ctxt_put(rdma, ctxt); return; @@ -327,13 +336,13 @@ int svc_rdma_send(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt) while (1) { if ((atomic_dec_return(&rdma->sc_sq_avail) < 0)) { percpu_counter_inc(&svcrdma_stat_sq_starve); - trace_svcrdma_sq_full(rdma); + trace_svcrdma_sq_full(rdma, &ctxt->sc_cid); atomic_inc(&rdma->sc_sq_avail); wait_event(rdma->sc_send_wait, atomic_read(&rdma->sc_sq_avail) > 1); if (test_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags)) return -ENOTCONN; - trace_svcrdma_sq_retry(rdma); + trace_svcrdma_sq_retry(rdma, &ctxt->sc_cid); continue; } @@ -344,7 +353,7 @@ int svc_rdma_send(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *ctxt) return 0; } - trace_svcrdma_sq_post_err(rdma, ret); + trace_svcrdma_sq_post_err(rdma, &ctxt->sc_cid, ret); svc_xprt_deferred_close(&rdma->sc_xprt); wake_up(&rdma->sc_send_wait); return ret; @@ -534,14 +543,14 @@ static int svc_rdma_page_dma_map(void *data, struct page *page, if (ib_dma_mapping_error(dev, dma_addr)) goto out_maperr; - trace_svcrdma_dma_map_page(rdma, dma_addr, len); + trace_svcrdma_dma_map_page(&ctxt->sc_cid, dma_addr, len); ctxt->sc_sges[ctxt->sc_cur_sge_no].addr = dma_addr; ctxt->sc_sges[ctxt->sc_cur_sge_no].length = len; ctxt->sc_send_wr.num_sge++; return 0; out_maperr: - trace_svcrdma_dma_map_err(rdma, dma_addr, len); + trace_svcrdma_dma_map_err(&ctxt->sc_cid, dma_addr, len); return -EIO; } @@ -653,7 +662,7 @@ static int svc_rdma_xb_count_sges(const struct xdr_buf *xdr, * svc_rdma_pull_up_needed - Determine whether to use pull-up * @rdma: controlling transport * @sctxt: send_ctxt for the Send WR - * @rctxt: Write and Reply chunks provided by client + * @write_pcl: Write chunk list provided by client * @xdr: xdr_buf containing RPC message to transmit * * Returns: @@ -662,7 +671,7 @@ static int svc_rdma_xb_count_sges(const struct xdr_buf *xdr, */ static bool svc_rdma_pull_up_needed(const struct svcxprt_rdma *rdma, const struct svc_rdma_send_ctxt *sctxt, - const struct svc_rdma_recv_ctxt *rctxt, + const struct svc_rdma_pcl *write_pcl, const struct xdr_buf *xdr) { /* Resources needed for the transport header */ @@ -672,7 +681,7 @@ static bool svc_rdma_pull_up_needed(const struct svcxprt_rdma *rdma, }; int ret; - ret = pcl_process_nonpayloads(&rctxt->rc_write_pcl, xdr, + ret = pcl_process_nonpayloads(write_pcl, xdr, svc_rdma_xb_count_sges, &args); if (ret < 0) return false; @@ -728,7 +737,7 @@ static int svc_rdma_xb_linearize(const struct xdr_buf *xdr, * svc_rdma_pull_up_reply_msg - Copy Reply into a single buffer * @rdma: controlling transport * @sctxt: send_ctxt for the Send WR; xprt hdr is already prepared - * @rctxt: Write and Reply chunks provided by client + * @write_pcl: Write chunk list provided by client * @xdr: prepared xdr_buf containing RPC message * * The device is not capable of sending the reply directly. @@ -743,7 +752,7 @@ static int svc_rdma_xb_linearize(const struct xdr_buf *xdr, */ static int svc_rdma_pull_up_reply_msg(const struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *sctxt, - const struct svc_rdma_recv_ctxt *rctxt, + const struct svc_rdma_pcl *write_pcl, const struct xdr_buf *xdr) { struct svc_rdma_pullup_data args = { @@ -751,7 +760,7 @@ static int svc_rdma_pull_up_reply_msg(const struct svcxprt_rdma *rdma, }; int ret; - ret = pcl_process_nonpayloads(&rctxt->rc_write_pcl, xdr, + ret = pcl_process_nonpayloads(write_pcl, xdr, svc_rdma_xb_linearize, &args); if (ret < 0) return ret; @@ -764,7 +773,8 @@ static int svc_rdma_pull_up_reply_msg(const struct svcxprt_rdma *rdma, /* svc_rdma_map_reply_msg - DMA map the buffer holding RPC message * @rdma: controlling transport * @sctxt: send_ctxt for the Send WR - * @rctxt: Write and Reply chunks provided by client + * @write_pcl: Write chunk list provided by client + * @reply_pcl: Reply chunk provided by client * @xdr: prepared xdr_buf containing RPC message * * Returns: @@ -776,7 +786,8 @@ static int svc_rdma_pull_up_reply_msg(const struct svcxprt_rdma *rdma, */ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, struct svc_rdma_send_ctxt *sctxt, - const struct svc_rdma_recv_ctxt *rctxt, + const struct svc_rdma_pcl *write_pcl, + const struct svc_rdma_pcl *reply_pcl, const struct xdr_buf *xdr) { struct svc_rdma_map_data args = { @@ -789,18 +800,18 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, sctxt->sc_sges[0].length = sctxt->sc_hdrbuf.len; /* If there is a Reply chunk, nothing follows the transport - * header, and we're done here. + * header, so there is nothing to map. */ - if (!pcl_is_empty(&rctxt->rc_reply_pcl)) + if (!pcl_is_empty(reply_pcl)) return 0; /* For pull-up, svc_rdma_send() will sync the transport header. * No additional DMA mapping is necessary. */ - if (svc_rdma_pull_up_needed(rdma, sctxt, rctxt, xdr)) - return svc_rdma_pull_up_reply_msg(rdma, sctxt, rctxt, xdr); + if (svc_rdma_pull_up_needed(rdma, sctxt, write_pcl, xdr)) + return svc_rdma_pull_up_reply_msg(rdma, sctxt, write_pcl, xdr); - return pcl_process_nonpayloads(&rctxt->rc_write_pcl, xdr, + return pcl_process_nonpayloads(write_pcl, xdr, svc_rdma_xb_dma_map, &args); } @@ -848,7 +859,8 @@ static int svc_rdma_send_reply_msg(struct svcxprt_rdma *rdma, { int ret; - ret = svc_rdma_map_reply_msg(rdma, sctxt, rctxt, &rqstp->rq_res); + ret = svc_rdma_map_reply_msg(rdma, sctxt, &rctxt->rc_write_pcl, + &rctxt->rc_reply_pcl, &rqstp->rq_res); if (ret < 0) return ret; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 2abd895046ee..4f27325ace4a 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -125,6 +125,9 @@ static void qp_event_handler(struct ib_event *event, void *context) static struct svcxprt_rdma *svc_rdma_create_xprt(struct svc_serv *serv, struct net *net, int node) { + static struct lock_class_key svcrdma_rwctx_lock; + static struct lock_class_key svcrdma_sctx_lock; + static struct lock_class_key svcrdma_dto_lock; struct svcxprt_rdma *cma_xprt; cma_xprt = kzalloc_node(sizeof(*cma_xprt), GFP_KERNEL, node); @@ -134,6 +137,7 @@ static struct svcxprt_rdma *svc_rdma_create_xprt(struct svc_serv *serv, svc_xprt_init(net, &svc_rdma_class, &cma_xprt->sc_xprt, serv); INIT_LIST_HEAD(&cma_xprt->sc_accept_q); INIT_LIST_HEAD(&cma_xprt->sc_rq_dto_q); + INIT_LIST_HEAD(&cma_xprt->sc_read_complete_q); init_llist_head(&cma_xprt->sc_send_ctxts); init_llist_head(&cma_xprt->sc_recv_ctxts); init_llist_head(&cma_xprt->sc_rw_ctxts); @@ -141,8 +145,11 @@ static struct svcxprt_rdma *svc_rdma_create_xprt(struct svc_serv *serv, spin_lock_init(&cma_xprt->sc_lock); spin_lock_init(&cma_xprt->sc_rq_dto_lock); + lockdep_set_class(&cma_xprt->sc_rq_dto_lock, &svcrdma_dto_lock); spin_lock_init(&cma_xprt->sc_send_lock); + lockdep_set_class(&cma_xprt->sc_send_lock, &svcrdma_sctx_lock); spin_lock_init(&cma_xprt->sc_rw_ctxt_lock); + lockdep_set_class(&cma_xprt->sc_rw_ctxt_lock, &svcrdma_rwctx_lock); /* * Note that this implies that the underlying transport support @@ -391,37 +398,35 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) dev = newxprt->sc_cm_id->device; newxprt->sc_port_num = newxprt->sc_cm_id->port_num; - /* Qualify the transport resource defaults with the - * capabilities of this particular device */ + newxprt->sc_max_req_size = svcrdma_max_req_size; + newxprt->sc_max_requests = svcrdma_max_requests; + newxprt->sc_max_bc_requests = svcrdma_max_bc_requests; + newxprt->sc_recv_batch = RPCRDMA_MAX_RECV_BATCH; + newxprt->sc_fc_credits = cpu_to_be32(newxprt->sc_max_requests); + + /* Qualify the transport's resource defaults with the + * capabilities of this particular device. + */ + /* Transport header, head iovec, tail iovec */ newxprt->sc_max_send_sges = 3; /* Add one SGE per page list entry */ newxprt->sc_max_send_sges += (svcrdma_max_req_size / PAGE_SIZE) + 1; if (newxprt->sc_max_send_sges > dev->attrs.max_send_sge) newxprt->sc_max_send_sges = dev->attrs.max_send_sge; - newxprt->sc_max_req_size = svcrdma_max_req_size; - newxprt->sc_max_requests = svcrdma_max_requests; - newxprt->sc_max_bc_requests = svcrdma_max_bc_requests; - newxprt->sc_recv_batch = RPCRDMA_MAX_RECV_BATCH; rq_depth = newxprt->sc_max_requests + newxprt->sc_max_bc_requests + newxprt->sc_recv_batch; if (rq_depth > dev->attrs.max_qp_wr) { - pr_warn("svcrdma: reducing receive depth to %d\n", - dev->attrs.max_qp_wr); rq_depth = dev->attrs.max_qp_wr; newxprt->sc_recv_batch = 1; newxprt->sc_max_requests = rq_depth - 2; newxprt->sc_max_bc_requests = 2; } - newxprt->sc_fc_credits = cpu_to_be32(newxprt->sc_max_requests); ctxts = rdma_rw_mr_factor(dev, newxprt->sc_port_num, RPCSVC_MAXPAGES); ctxts *= newxprt->sc_max_requests; newxprt->sc_sq_depth = rq_depth + ctxts; - if (newxprt->sc_sq_depth > dev->attrs.max_qp_wr) { - pr_warn("svcrdma: reducing send depth to %d\n", - dev->attrs.max_qp_wr); + if (newxprt->sc_sq_depth > dev->attrs.max_qp_wr) newxprt->sc_sq_depth = dev->attrs.max_qp_wr; - } atomic_set(&newxprt->sc_sq_avail, newxprt->sc_sq_depth); newxprt->sc_pd = ib_alloc_pd(dev, 0); @@ -451,8 +456,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) qp_attr.qp_type = IB_QPT_RC; qp_attr.send_cq = newxprt->sc_sq_cq; qp_attr.recv_cq = newxprt->sc_rq_cq; - dprintk("svcrdma: newxprt->sc_cm_id=%p, newxprt->sc_pd=%p\n", - newxprt->sc_cm_id, newxprt->sc_pd); dprintk(" cap.max_send_wr = %d, cap.max_recv_wr = %d\n", qp_attr.cap.max_send_wr, qp_attr.cap.max_recv_wr); dprintk(" cap.max_send_sge = %d, cap.max_recv_sge = %d\n", @@ -506,7 +509,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) } #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) - dprintk("svcrdma: new connection %p accepted:\n", newxprt); + dprintk("svcrdma: new connection accepted on device %s:\n", dev->name); sap = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.src_addr; dprintk(" local address : %pIS:%u\n", sap, rpc_get_port(sap)); sap = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.dst_addr; @@ -547,6 +550,7 @@ static void __svc_rdma_free(struct work_struct *work) /* This blocks until the Completion Queues are empty */ if (rdma->sc_qp && !IS_ERR(rdma->sc_qp)) ib_drain_qp(rdma->sc_qp); + flush_workqueue(svcrdma_wq); svc_rdma_flush_recv_queues(rdma); diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 28c0771c4e8c..4f8d7efa469f 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1364,7 +1364,7 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, int needed, bool temp) } rep->rr_cid.ci_queue_id = ep->re_attr.recv_cq->res.id; - trace_xprtrdma_post_recv(rep); + trace_xprtrdma_post_recv(&rep->rr_cid); rep->rr_recv_wr.next = wr; wr = &rep->rr_recv_wr; --needed; |