From 10f4e765879e514e1ce7f52ed26603047af196e2 Mon Sep 17 00:00:00 2001 From: wenxu Date: Thu, 10 Jan 2019 14:51:35 +0800 Subject: netfilter: nft_flow_offload: fix interaction with vrf slave device In the forward chain, the iif is changed from slave device to master vrf device. Thus, flow offload does not find a match on the lower slave device. This patch uses the cached route, ie. dst->dev, to update the iif and oif fields in the flow entry. After this patch, the following example works fine: # ip addr add dev eth0 1.1.1.1/24 # ip addr add dev eth1 10.0.0.1/24 # ip link add user1 type vrf table 1 # ip l set user1 up # ip l set dev eth0 master user1 # ip l set dev eth1 master user1 # nft add table firewall # nft add flowtable f fb1 { hook ingress priority 0 \; devices = { eth0, eth1 } \; } # nft add chain f ftb-all {type filter hook forward priority 0 \; policy accept \; } # nft add rule f ftb-all ct zone 1 ip protocol tcp flow offload @fb1 # nft add rule f ftb-all ct zone 1 ip protocol udp flow offload @fb1 Signed-off-by: wenxu Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_flow_table.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 7d5cda7ce32a..3e370cb36263 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -84,7 +84,6 @@ struct flow_offload { struct nf_flow_route { struct { struct dst_entry *dst; - int ifindex; } tuple[FLOW_OFFLOAD_DIR_MAX]; }; -- cgit v1.2.3 From f97f4dd8b3bb9d0993d2491e0f22024c68109184 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 9 Jan 2019 09:57:39 +0000 Subject: net: ipv4: Fix memory leak in network namespace dismantle IPv4 routing tables are flushed in two cases: 1. In response to events in the netdev and inetaddr notification chains 2. When a network namespace is being dismantled In both cases only routes associated with a dead nexthop group are flushed. However, a nexthop group will only be marked as dead in case it is populated with actual nexthops using a nexthop device. This is not the case when the route in question is an error route (e.g., 'blackhole', 'unreachable'). Therefore, when a network namespace is being dismantled such routes are not flushed and leaked [1]. To reproduce: # ip netns add blue # ip -n blue route add unreachable 192.0.2.0/24 # ip netns del blue Fix this by not skipping error routes that are not marked with RTNH_F_DEAD when flushing the routing tables. To prevent the flushing of such routes in case #1, add a parameter to fib_table_flush() that indicates if the table is flushed as part of namespace dismantle or not. Note that this problem does not exist in IPv6 since error routes are associated with the loopback device. [1] unreferenced object 0xffff888066650338 (size 56): comm "ip", pid 1206, jiffies 4294786063 (age 26.235s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 b0 1c 62 61 80 88 ff ff ..........ba.... e8 8b a1 64 80 88 ff ff 00 07 00 08 fe 00 00 00 ...d............ backtrace: [<00000000856ed27d>] inet_rtm_newroute+0x129/0x220 [<00000000fcdfc00a>] rtnetlink_rcv_msg+0x397/0xa20 [<00000000cb85801a>] netlink_rcv_skb+0x132/0x380 [<00000000ebc991d2>] netlink_unicast+0x4c0/0x690 [<0000000014f62875>] netlink_sendmsg+0x929/0xe10 [<00000000bac9d967>] sock_sendmsg+0xc8/0x110 [<00000000223e6485>] ___sys_sendmsg+0x77a/0x8f0 [<000000002e94f880>] __sys_sendmsg+0xf7/0x250 [<00000000ccb1fa72>] do_syscall_64+0x14d/0x610 [<00000000ffbe3dae>] entry_SYSCALL_64_after_hwframe+0x49/0xbe [<000000003a8b605b>] 0xffffffffffffffff unreferenced object 0xffff888061621c88 (size 48): comm "ip", pid 1206, jiffies 4294786063 (age 26.235s) hex dump (first 32 bytes): 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk 6b 6b 6b 6b 6b 6b 6b 6b d8 8e 26 5f 80 88 ff ff kkkkkkkk..&_.... backtrace: [<00000000733609e3>] fib_table_insert+0x978/0x1500 [<00000000856ed27d>] inet_rtm_newroute+0x129/0x220 [<00000000fcdfc00a>] rtnetlink_rcv_msg+0x397/0xa20 [<00000000cb85801a>] netlink_rcv_skb+0x132/0x380 [<00000000ebc991d2>] netlink_unicast+0x4c0/0x690 [<0000000014f62875>] netlink_sendmsg+0x929/0xe10 [<00000000bac9d967>] sock_sendmsg+0xc8/0x110 [<00000000223e6485>] ___sys_sendmsg+0x77a/0x8f0 [<000000002e94f880>] __sys_sendmsg+0xf7/0x250 [<00000000ccb1fa72>] do_syscall_64+0x14d/0x610 [<00000000ffbe3dae>] entry_SYSCALL_64_after_hwframe+0x49/0xbe [<000000003a8b605b>] 0xffffffffffffffff Fixes: 8cced9eff1d4 ("[NETNS]: Enable routing configuration in non-initial namespace.") Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip_fib.h | 2 +- net/ipv4/fib_frontend.c | 4 ++-- net/ipv4/fib_trie.c | 15 ++++++++++++--- 3 files changed, 15 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index c5969762a8f4..9c8214d2116d 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -241,7 +241,7 @@ int fib_table_delete(struct net *, struct fib_table *, struct fib_config *, struct netlink_ext_ack *extack); int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb, struct fib_dump_filter *filter); -int fib_table_flush(struct net *net, struct fib_table *table); +int fib_table_flush(struct net *net, struct fib_table *table, bool flush_all); struct fib_table *fib_trie_unmerge(struct fib_table *main_tb); void fib_table_flush_external(struct fib_table *table); void fib_free_table(struct fib_table *tb); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 6df95be96311..fe4f6a624238 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -203,7 +203,7 @@ static void fib_flush(struct net *net) struct fib_table *tb; hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) - flushed += fib_table_flush(net, tb); + flushed += fib_table_flush(net, tb, false); } if (flushed) @@ -1463,7 +1463,7 @@ static void ip_fib_net_exit(struct net *net) hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) { hlist_del(&tb->tb_hlist); - fib_table_flush(net, tb); + fib_table_flush(net, tb, true); fib_free_table(tb); } } diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 237c9f72b265..a573e37e0615 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1856,7 +1856,7 @@ void fib_table_flush_external(struct fib_table *tb) } /* Caller must hold RTNL. */ -int fib_table_flush(struct net *net, struct fib_table *tb) +int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *pn = t->kv; @@ -1904,8 +1904,17 @@ int fib_table_flush(struct net *net, struct fib_table *tb) hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { struct fib_info *fi = fa->fa_info; - if (!fi || !(fi->fib_flags & RTNH_F_DEAD) || - tb->tb_id != fa->tb_id) { + if (!fi || tb->tb_id != fa->tb_id || + (!(fi->fib_flags & RTNH_F_DEAD) && + !fib_props[fa->fa_type].error)) { + slen = fa->fa_slen; + continue; + } + + /* Do not flush error routes if network namespace is + * not being dismantled + */ + if (!flush_all && fib_props[fa->fa_type].error) { slen = fa->fa_slen; continue; } -- cgit v1.2.3 From e122d845a01ece2ddd28b2f125ef2db66b8b627a Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 10 Jan 2019 16:59:13 +0000 Subject: Revert "rxrpc: Allow failed client calls to be retried" The changes introduced to allow rxrpc calls to be retried creates an issue when it comes to refcounting afs_call structs. The problem is that when rxrpc_send_data() queues the last packet for an asynchronous call, the following sequence can occur: (1) The notify_end_tx callback is invoked which causes the state in the afs_call to be changed from AFS_CALL_CL_REQUESTING or AFS_CALL_SV_REPLYING. (2) afs_deliver_to_call() can then process event notifications from rxrpc on the async_work queue. (3) Delivery of events, such as an abort from the server, can cause the afs_call state to be changed to AFS_CALL_COMPLETE on async_work. (4) For an asynchronous call, afs_process_async_call() notes that the call is complete and tried to clean up all the refs on async_work. (5) rxrpc_send_data() might return the amount of data transferred (success) or an error - which could in turn reflect a local error or a received error. Synchronising the clean up after rxrpc_kernel_send_data() returns an error with the asynchronous cleanup is then tricky to get right. Mostly revert commit c038a58ccfd6704d4d7d60ed3d6a0fca13cf13a4. The two API functions the original commit added aren't currently used. This makes rxrpc_kernel_send_data() always return successfully if it queued the data it was given. Note that this doesn't affect synchronous calls since their Rx notification function merely pokes a wait queue and does not refcounting. The asynchronous call notification function *has* to do refcounting and pass a ref over the work item to avoid the need to sync the workqueue in call cleanup. Signed-off-by: David Howells Signed-off-by: David S. Miller --- Documentation/networking/rxrpc.txt | 45 ------------------ include/net/af_rxrpc.h | 16 ------- net/rxrpc/af_rxrpc.c | 70 --------------------------- net/rxrpc/ar-internal.h | 19 +++++--- net/rxrpc/call_object.c | 97 -------------------------------------- net/rxrpc/conn_client.c | 5 +- net/rxrpc/sendmsg.c | 24 +++++----- 7 files changed, 24 insertions(+), 252 deletions(-) (limited to 'include') diff --git a/Documentation/networking/rxrpc.txt b/Documentation/networking/rxrpc.txt index c9d052e0cf51..2df5894353d6 100644 --- a/Documentation/networking/rxrpc.txt +++ b/Documentation/networking/rxrpc.txt @@ -1000,51 +1000,6 @@ The kernel interface functions are as follows: size should be set when the call is begun. tx_total_len may not be less than zero. - (*) Check to see the completion state of a call so that the caller can assess - whether it needs to be retried. - - enum rxrpc_call_completion { - RXRPC_CALL_SUCCEEDED, - RXRPC_CALL_REMOTELY_ABORTED, - RXRPC_CALL_LOCALLY_ABORTED, - RXRPC_CALL_LOCAL_ERROR, - RXRPC_CALL_NETWORK_ERROR, - }; - - int rxrpc_kernel_check_call(struct socket *sock, struct rxrpc_call *call, - enum rxrpc_call_completion *_compl, - u32 *_abort_code); - - On return, -EINPROGRESS will be returned if the call is still ongoing; if - it is finished, *_compl will be set to indicate the manner of completion, - *_abort_code will be set to any abort code that occurred. 0 will be - returned on a successful completion, -ECONNABORTED will be returned if the - client failed due to a remote abort and anything else will return an - appropriate error code. - - The caller should look at this information to decide if it's worth - retrying the call. - - (*) Retry a client call. - - int rxrpc_kernel_retry_call(struct socket *sock, - struct rxrpc_call *call, - struct sockaddr_rxrpc *srx, - struct key *key); - - This attempts to partially reinitialise a call and submit it again while - reusing the original call's Tx queue to avoid the need to repackage and - re-encrypt the data to be sent. call indicates the call to retry, srx the - new address to send it to and key the encryption key to use for signing or - encrypting the packets. - - For this to work, the first Tx data packet must still be in the transmit - queue, and currently this is only permitted for local and network errors - and the call must not have been aborted. Any partially constructed Tx - packet is left as is and can continue being filled afterwards. - - It returns 0 if the call was requeued and an error otherwise. - (*) Get call RTT. u64 rxrpc_kernel_get_rtt(struct socket *sock, struct rxrpc_call *call); diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index 1adefe42c0a6..2bfb87eb98ce 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -20,18 +20,6 @@ struct sock; struct socket; struct rxrpc_call; -/* - * Call completion condition (state == RXRPC_CALL_COMPLETE). - */ -enum rxrpc_call_completion { - RXRPC_CALL_SUCCEEDED, /* - Normal termination */ - RXRPC_CALL_REMOTELY_ABORTED, /* - call aborted by peer */ - RXRPC_CALL_LOCALLY_ABORTED, /* - call aborted locally on error or close */ - RXRPC_CALL_LOCAL_ERROR, /* - call failed due to local error */ - RXRPC_CALL_NETWORK_ERROR, /* - call terminated by network error */ - NR__RXRPC_CALL_COMPLETIONS -}; - /* * Debug ID counter for tracing. */ @@ -73,10 +61,6 @@ int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t, rxrpc_user_attach_call_t, unsigned long, gfp_t, unsigned int); void rxrpc_kernel_set_tx_length(struct socket *, struct rxrpc_call *, s64); -int rxrpc_kernel_retry_call(struct socket *, struct rxrpc_call *, - struct sockaddr_rxrpc *, struct key *); -int rxrpc_kernel_check_call(struct socket *, struct rxrpc_call *, - enum rxrpc_call_completion *, u32 *); u32 rxrpc_kernel_check_life(const struct socket *, const struct rxrpc_call *); void rxrpc_kernel_probe_life(struct socket *, struct rxrpc_call *); u32 rxrpc_kernel_get_epoch(struct socket *, struct rxrpc_call *); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index a2522f9d71e2..96f2952bbdfd 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -418,76 +418,6 @@ u32 rxrpc_kernel_get_epoch(struct socket *sock, struct rxrpc_call *call) } EXPORT_SYMBOL(rxrpc_kernel_get_epoch); -/** - * rxrpc_kernel_check_call - Check a call's state - * @sock: The socket the call is on - * @call: The call to check - * @_compl: Where to store the completion state - * @_abort_code: Where to store any abort code - * - * Allow a kernel service to query the state of a call and find out the manner - * of its termination if it has completed. Returns -EINPROGRESS if the call is - * still going, 0 if the call finished successfully, -ECONNABORTED if the call - * was aborted and an appropriate error if the call failed in some other way. - */ -int rxrpc_kernel_check_call(struct socket *sock, struct rxrpc_call *call, - enum rxrpc_call_completion *_compl, u32 *_abort_code) -{ - if (call->state != RXRPC_CALL_COMPLETE) - return -EINPROGRESS; - smp_rmb(); - *_compl = call->completion; - *_abort_code = call->abort_code; - return call->error; -} -EXPORT_SYMBOL(rxrpc_kernel_check_call); - -/** - * rxrpc_kernel_retry_call - Allow a kernel service to retry a call - * @sock: The socket the call is on - * @call: The call to retry - * @srx: The address of the peer to contact - * @key: The security context to use (defaults to socket setting) - * - * Allow a kernel service to try resending a client call that failed due to a - * network error to a new address. The Tx queue is maintained intact, thereby - * relieving the need to re-encrypt any request data that has already been - * buffered. - */ -int rxrpc_kernel_retry_call(struct socket *sock, struct rxrpc_call *call, - struct sockaddr_rxrpc *srx, struct key *key) -{ - struct rxrpc_conn_parameters cp; - struct rxrpc_sock *rx = rxrpc_sk(sock->sk); - int ret; - - _enter("%d{%d}", call->debug_id, atomic_read(&call->usage)); - - if (!key) - key = rx->key; - if (key && !key->payload.data[0]) - key = NULL; /* a no-security key */ - - memset(&cp, 0, sizeof(cp)); - cp.local = rx->local; - cp.key = key; - cp.security_level = 0; - cp.exclusive = false; - cp.service_id = srx->srx_service; - - mutex_lock(&call->user_mutex); - - ret = rxrpc_prepare_call_for_retry(rx, call); - if (ret == 0) - ret = rxrpc_retry_client_call(rx, call, &cp, srx, GFP_KERNEL); - - mutex_unlock(&call->user_mutex); - rxrpc_put_peer(cp.peer); - _leave(" = %d", ret); - return ret; -} -EXPORT_SYMBOL(rxrpc_kernel_retry_call); - /** * rxrpc_kernel_new_call_notification - Get notifications of new calls * @sock: The socket to intercept received messages on diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index bc628acf4f4f..4b1a534d290a 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -476,7 +476,6 @@ enum rxrpc_call_flag { RXRPC_CALL_EXPOSED, /* The call was exposed to the world */ RXRPC_CALL_RX_LAST, /* Received the last packet (at rxtx_top) */ RXRPC_CALL_TX_LAST, /* Last packet in Tx buffer (at rxtx_top) */ - RXRPC_CALL_TX_LASTQ, /* Last packet has been queued */ RXRPC_CALL_SEND_PING, /* A ping will need to be sent */ RXRPC_CALL_PINGING, /* Ping in process */ RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ @@ -517,6 +516,18 @@ enum rxrpc_call_state { NR__RXRPC_CALL_STATES }; +/* + * Call completion condition (state == RXRPC_CALL_COMPLETE). + */ +enum rxrpc_call_completion { + RXRPC_CALL_SUCCEEDED, /* - Normal termination */ + RXRPC_CALL_REMOTELY_ABORTED, /* - call aborted by peer */ + RXRPC_CALL_LOCALLY_ABORTED, /* - call aborted locally on error or close */ + RXRPC_CALL_LOCAL_ERROR, /* - call failed due to local error */ + RXRPC_CALL_NETWORK_ERROR, /* - call terminated by network error */ + NR__RXRPC_CALL_COMPLETIONS +}; + /* * Call Tx congestion management modes. */ @@ -761,15 +772,9 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *, struct sockaddr_rxrpc *, struct rxrpc_call_params *, gfp_t, unsigned int); -int rxrpc_retry_client_call(struct rxrpc_sock *, - struct rxrpc_call *, - struct rxrpc_conn_parameters *, - struct sockaddr_rxrpc *, - gfp_t); void rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_call *, struct sk_buff *); void rxrpc_release_call(struct rxrpc_sock *, struct rxrpc_call *); -int rxrpc_prepare_call_for_retry(struct rxrpc_sock *, struct rxrpc_call *); void rxrpc_release_calls_on_socket(struct rxrpc_sock *); bool __rxrpc_queue_call(struct rxrpc_call *); bool rxrpc_queue_call(struct rxrpc_call *); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 8f1a8f85b1f9..8aa2937b069f 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -324,48 +324,6 @@ error: return ERR_PTR(ret); } -/* - * Retry a call to a new address. It is expected that the Tx queue of the call - * will contain data previously packaged for an old call. - */ -int rxrpc_retry_client_call(struct rxrpc_sock *rx, - struct rxrpc_call *call, - struct rxrpc_conn_parameters *cp, - struct sockaddr_rxrpc *srx, - gfp_t gfp) -{ - const void *here = __builtin_return_address(0); - int ret; - - /* Set up or get a connection record and set the protocol parameters, - * including channel number and call ID. - */ - ret = rxrpc_connect_call(rx, call, cp, srx, gfp); - if (ret < 0) - goto error; - - trace_rxrpc_call(call, rxrpc_call_connected, atomic_read(&call->usage), - here, NULL); - - rxrpc_start_call_timer(call); - - _net("CALL new %d on CONN %d", call->debug_id, call->conn->debug_id); - - if (!test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) - rxrpc_queue_call(call); - - _leave(" = 0"); - return 0; - -error: - rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, - RX_CALL_DEAD, ret); - trace_rxrpc_call(call, rxrpc_call_error, atomic_read(&call->usage), - here, ERR_PTR(ret)); - _leave(" = %d", ret); - return ret; -} - /* * Set up an incoming call. call->conn points to the connection. * This is called in BH context and isn't allowed to fail. @@ -533,61 +491,6 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) _leave(""); } -/* - * Prepare a kernel service call for retry. - */ -int rxrpc_prepare_call_for_retry(struct rxrpc_sock *rx, struct rxrpc_call *call) -{ - const void *here = __builtin_return_address(0); - int i; - u8 last = 0; - - _enter("{%d,%d}", call->debug_id, atomic_read(&call->usage)); - - trace_rxrpc_call(call, rxrpc_call_release, atomic_read(&call->usage), - here, (const void *)call->flags); - - ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); - ASSERTCMP(call->completion, !=, RXRPC_CALL_REMOTELY_ABORTED); - ASSERTCMP(call->completion, !=, RXRPC_CALL_LOCALLY_ABORTED); - ASSERT(list_empty(&call->recvmsg_link)); - - del_timer_sync(&call->timer); - - _debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, call->conn); - - if (call->conn) - rxrpc_disconnect_call(call); - - if (rxrpc_is_service_call(call) || - !call->tx_phase || - call->tx_hard_ack != 0 || - call->rx_hard_ack != 0 || - call->rx_top != 0) - return -EINVAL; - - call->state = RXRPC_CALL_UNINITIALISED; - call->completion = RXRPC_CALL_SUCCEEDED; - call->call_id = 0; - call->cid = 0; - call->cong_cwnd = 0; - call->cong_extra = 0; - call->cong_ssthresh = 0; - call->cong_mode = 0; - call->cong_dup_acks = 0; - call->cong_cumul_acks = 0; - call->acks_lowest_nak = 0; - - for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++) { - last |= call->rxtx_annotations[i]; - call->rxtx_annotations[i] &= RXRPC_TX_ANNO_LAST; - call->rxtx_annotations[i] |= RXRPC_TX_ANNO_RETRANS; - } - - _leave(" = 0"); - return 0; -} - /* * release all the calls associated with a socket */ diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 521189f4b666..b2adfa825363 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -562,10 +562,7 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, clear_bit(RXRPC_CONN_FINAL_ACK_0 + channel, &conn->flags); write_lock_bh(&call->state_lock); - if (!test_bit(RXRPC_CALL_TX_LASTQ, &call->flags)) - call->state = RXRPC_CALL_CLIENT_SEND_REQUEST; - else - call->state = RXRPC_CALL_CLIENT_AWAIT_REPLY; + call->state = RXRPC_CALL_CLIENT_SEND_REQUEST; write_unlock_bh(&call->state_lock); rxrpc_see_call(call); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index be01f9c5d963..46c9312085b1 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -169,10 +169,8 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, ASSERTCMP(seq, ==, call->tx_top + 1); - if (last) { + if (last) annotation |= RXRPC_TX_ANNO_LAST; - set_bit(RXRPC_CALL_TX_LASTQ, &call->flags); - } /* We have to set the timestamp before queueing as the retransmit * algorithm can see the packet as soon as we queue it. @@ -386,6 +384,11 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, call->tx_total_len -= copy; } + /* check for the far side aborting the call or a network error + * occurring */ + if (call->state == RXRPC_CALL_COMPLETE) + goto call_terminated; + /* add the packet to the send queue if it's now full */ if (sp->remain <= 0 || (msg_data_left(msg) == 0 && !more)) { @@ -425,16 +428,6 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, notify_end_tx); skb = NULL; } - - /* Check for the far side aborting the call or a network error - * occurring. If this happens, save any packet that was under - * construction so that in the case of a network error, the - * call can be retried or redirected. - */ - if (call->state == RXRPC_CALL_COMPLETE) { - ret = call->error; - goto out; - } } while (msg_data_left(msg) > 0); success: @@ -444,6 +437,11 @@ out: _leave(" = %d", ret); return ret; +call_terminated: + rxrpc_free_skb(skb, rxrpc_skb_tx_freed); + _leave(" = %d", call->error); + return call->error; + maybe_error: if (copied) goto success; -- cgit v1.2.3 From f275ee0fa3a06eb87edc229749cf1eb18f0663fa Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Thu, 10 Jan 2019 21:24:13 +0100 Subject: IN_BADCLASS: fix macro to actually work Commit 65cab850f0ee ("net: Allow class-e address assignment via ifconfig ioctl") modified the IN_BADCLASS macro a bit, but unfortunatly one too many '(' characters were added to the line, making any code that used it, not build properly. Also, the macro now compares an unsigned with a signed value, which isn't ok, so fix that up by making both types match properly. Reported-by: Christopher Ferris Fixes: 65cab850f0ee ("net: Allow class-e address assignment via ifconfig ioctl") Cc: Dave Taht Signed-off-by: Greg Kroah-Hartman Signed-off-by: David S. Miller --- include/uapi/linux/in.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index f6052e70bf40..a55cb8b10165 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -268,7 +268,7 @@ struct sockaddr_in { #define IN_MULTICAST(a) IN_CLASSD(a) #define IN_MULTICAST_NET 0xe0000000 -#define IN_BADCLASS(a) ((((long int) (a) ) == 0xffffffff) +#define IN_BADCLASS(a) (((long int) (a) ) == (long int)0xffffffff) #define IN_EXPERIMENTAL(a) IN_BADCLASS((a)) #define IN_CLASSE(a) ((((long int) (a)) & 0xf0000000) == 0xf0000000) -- cgit v1.2.3 From 9e857a40dc4eba15a739b4194d7db873d82c28a0 Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Tue, 15 Jan 2019 16:55:30 +0100 Subject: net: phy: Add missing features to PHY drivers The bcm87xx and micrel driver has PHYs which are missing the .features value. Add them. The bcm87xx is a 10G FEC only PHY. Add the needed features definition of this PHY. Fixes: 719655a14971 ("net: phy: Replace phy driver features u32 with link_mode bitmap") Reported-by: Scott Wood Reported-by: Camelia Groza Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/bcm87xx.c | 2 ++ drivers/net/phy/micrel.c | 1 + drivers/net/phy/phy_device.c | 12 ++++++++++++ include/linux/phy.h | 2 ++ 4 files changed, 17 insertions(+) (limited to 'include') diff --git a/drivers/net/phy/bcm87xx.c b/drivers/net/phy/bcm87xx.c index 1b350183bffb..a271239748f2 100644 --- a/drivers/net/phy/bcm87xx.c +++ b/drivers/net/phy/bcm87xx.c @@ -197,6 +197,7 @@ static struct phy_driver bcm87xx_driver[] = { .phy_id = PHY_ID_BCM8706, .phy_id_mask = 0xffffffff, .name = "Broadcom BCM8706", + .features = PHY_10GBIT_FEC_FEATURES, .config_init = bcm87xx_config_init, .config_aneg = bcm87xx_config_aneg, .read_status = bcm87xx_read_status, @@ -208,6 +209,7 @@ static struct phy_driver bcm87xx_driver[] = { .phy_id = PHY_ID_BCM8727, .phy_id_mask = 0xffffffff, .name = "Broadcom BCM8727", + .features = PHY_10GBIT_FEC_FEATURES, .config_init = bcm87xx_config_init, .config_aneg = bcm87xx_config_aneg, .read_status = bcm87xx_read_status, diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 7828d17f0662..b1f959935f50 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -1099,6 +1099,7 @@ static struct phy_driver ksphy_driver[] = { .phy_id = PHY_ID_KSZ8873MLL, .phy_id_mask = MICREL_PHY_ID_MASK, .name = "Micrel KSZ8873MLL Switch", + .features = PHY_BASIC_FEATURES, .config_init = kszphy_config_init, .config_aneg = ksz8873mll_config_aneg, .read_status = ksz8873mll_read_status, diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 51990002d495..bf3ce48a1e5d 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -61,6 +61,9 @@ EXPORT_SYMBOL_GPL(phy_gbit_all_ports_features); __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init; EXPORT_SYMBOL_GPL(phy_10gbit_features); +__ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_fec_features) __ro_after_init; +EXPORT_SYMBOL_GPL(phy_10gbit_fec_features); + static const int phy_basic_ports_array[] = { ETHTOOL_LINK_MODE_Autoneg_BIT, ETHTOOL_LINK_MODE_TP_BIT, @@ -109,6 +112,11 @@ const int phy_10gbit_features_array[1] = { }; EXPORT_SYMBOL_GPL(phy_10gbit_features_array); +const int phy_10gbit_fec_features_array[1] = { + ETHTOOL_LINK_MODE_10000baseR_FEC_BIT, +}; +EXPORT_SYMBOL_GPL(phy_10gbit_fec_features_array); + __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init; EXPORT_SYMBOL_GPL(phy_10gbit_full_features); @@ -191,6 +199,10 @@ static void features_init(void) linkmode_set_bit_array(phy_10gbit_full_features_array, ARRAY_SIZE(phy_10gbit_full_features_array), phy_10gbit_full_features); + /* 10G FEC only */ + linkmode_set_bit_array(phy_10gbit_fec_features_array, + ARRAY_SIZE(phy_10gbit_fec_features_array), + phy_10gbit_fec_features); } void phy_device_free(struct phy_device *phydev) diff --git a/include/linux/phy.h b/include/linux/phy.h index 3b051f761450..55114657a577 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -48,6 +48,7 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_fibre_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_all_ports_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init; +extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_fec_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init; #define PHY_BASIC_FEATURES ((unsigned long *)&phy_basic_features) @@ -56,6 +57,7 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_ini #define PHY_GBIT_FIBRE_FEATURES ((unsigned long *)&phy_gbit_fibre_features) #define PHY_GBIT_ALL_PORTS_FEATURES ((unsigned long *)&phy_gbit_all_ports_features) #define PHY_10GBIT_FEATURES ((unsigned long *)&phy_10gbit_features) +#define PHY_10GBIT_FEC_FEATURES ((unsigned long *)&phy_10gbit_fec_features) #define PHY_10GBIT_FULL_FEATURES ((unsigned long *)&phy_10gbit_full_features) extern const int phy_10_100_features_array[4]; -- cgit v1.2.3 From 6c57f0458022298e4da1729c67bd33ce41c14e7a Mon Sep 17 00:00:00 2001 From: Ross Lagerwall Date: Thu, 17 Jan 2019 15:34:38 +0000 Subject: net: Fix usage of pskb_trim_rcsum In certain cases, pskb_trim_rcsum() may change skb pointers. Reinitialize header pointers afterwards to avoid potential use-after-frees. Add a note in the documentation of pskb_trim_rcsum(). Found by KASAN. Signed-off-by: Ross Lagerwall Signed-off-by: David S. Miller --- drivers/net/ppp/pppoe.c | 1 + include/linux/skbuff.h | 1 + net/bridge/br_netfilter_ipv6.c | 1 + net/bridge/netfilter/nft_reject_bridge.c | 1 + net/ipv4/ip_input.c | 1 + 5 files changed, 5 insertions(+) (limited to 'include') diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 62dc564b251d..f22639f0116a 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -445,6 +445,7 @@ static int pppoe_rcv(struct sk_buff *skb, struct net_device *dev, if (pskb_trim_rcsum(skb, len)) goto drop; + ph = pppoe_hdr(skb); pn = pppoe_pernet(dev_net(dev)); /* Note that get_item does a sock_hold(), so sk_pppox(po) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 93f56fddd92a..95d25b010a25 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3218,6 +3218,7 @@ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len); * * This is exactly the same as pskb_trim except that it ensures the * checksum of received packets are still valid after the operation. + * It can change skb pointers. */ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index 94039f588f1d..564710f88f93 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/net/bridge/br_netfilter_ipv6.c @@ -131,6 +131,7 @@ int br_validate_ipv6(struct net *net, struct sk_buff *skb) IPSTATS_MIB_INDISCARDS); goto drop; } + hdr = ipv6_hdr(skb); } if (hdr->nexthdr == NEXTHDR_HOP && br_nf_check_hbh_len(skb)) goto drop; diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index 08cbed7d940e..419e8edf23ba 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -229,6 +229,7 @@ static bool reject6_br_csum_ok(struct sk_buff *skb, int hook) pskb_trim_rcsum(skb, ntohs(ip6h->payload_len) + sizeof(*ip6h))) return false; + ip6h = ipv6_hdr(skb); thoff = ipv6_skip_exthdr(skb, ((u8*)(ip6h+1) - skb->data), &proto, &fo); if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0) return false; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 26921f6b3b92..51d8efba6de2 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -488,6 +488,7 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net) goto drop; } + iph = ip_hdr(skb); skb->transport_header = skb->network_header + iph->ihl*4; /* Remove any debris in the socket control block */ -- cgit v1.2.3 From 3e64cf7a435ed0500e3adaa8aada2272d3ae8abc Mon Sep 17 00:00:00 2001 From: Camelia Groza Date: Thu, 17 Jan 2019 14:22:36 +0200 Subject: net: phy: phy driver features are mandatory Since phy driver features became a link_mode bitmap, phy drivers that don't have a list of features configured will cause the kernel to crash when probed. Prevent the phy driver from registering if the features field is missing. Fixes: 719655a14971 ("net: phy: Replace phy driver features u32 with link_mode bitmap") Reported-by: Scott Wood Signed-off-by: Camelia Groza Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 5 +++++ include/linux/phy.h | 4 ++-- 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index bf3ce48a1e5d..46c86725a693 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -2255,6 +2255,11 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner) { int retval; + if (WARN_ON(!new_driver->features)) { + pr_err("%s: Driver features are missing\n", new_driver->name); + return -EINVAL; + } + new_driver->mdiodrv.flags |= MDIO_DEVICE_IS_PHY; new_driver->mdiodrv.driver.name = new_driver->name; new_driver->mdiodrv.driver.bus = &mdio_bus_type; diff --git a/include/linux/phy.h b/include/linux/phy.h index 55114657a577..ef20aeea10cc 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -469,8 +469,8 @@ struct phy_device { * only works for PHYs with IDs which match this field * name: The friendly name of this PHY type * phy_id_mask: Defines the important bits of the phy_id - * features: A list of features (speed, duplex, etc) supported - * by this PHY + * features: A mandatory list of features (speed, duplex, etc) + * supported by this PHY * flags: A bitfield defining certain other features this PHY * supports (like interrupts) * -- cgit v1.2.3