From 9f460ae31c4435fd022c443a6029352217a16ac1 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Tue, 18 May 2021 21:00:27 +0200 Subject: batman-adv: Avoid WARN_ON timing related checks The soft/batadv interface for a queued OGM can be changed during the time the OGM was queued for transmission and when the OGM is actually transmitted by the worker. But WARN_ON must be used to denote kernel bugs and not to print simple warnings. A warning can simply be printed using pr_warn. Reported-by: Tetsuo Handa Reported-by: syzbot+c0b807de416427ff3dd1@syzkaller.appspotmail.com Fixes: ef0a937f7a14 ("batman-adv: consider outgoing interface in OGM sending") Signed-off-by: Sven Eckelmann Signed-off-by: Simon Wunderlich --- net/batman-adv/bat_iv_ogm.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 789f257be24f..fc8be49010b9 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -409,8 +409,10 @@ static void batadv_iv_ogm_emit(struct batadv_forw_packet *forw_packet) if (WARN_ON(!forw_packet->if_outgoing)) return; - if (WARN_ON(forw_packet->if_outgoing->soft_iface != soft_iface)) + if (forw_packet->if_outgoing->soft_iface != soft_iface) { + pr_warn("%s: soft interface switch for queued OGM\n", __func__); return; + } if (forw_packet->if_incoming->if_status != BATADV_IF_ACTIVE) return; -- cgit v1.2.3 From e877a88d1f069edced4160792f42c2a8e2dba942 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 17 May 2021 09:59:10 +1000 Subject: SUNRPC in case of backlog, hand free slots directly to waiting task If sunrpc.tcp_max_slot_table_entries is small and there are tasks on the backlog queue, then when a request completes it is freed and the first task on the queue is woken. The expectation is that it will wake and claim that request. However if it was a sync task and the waiting process was killed at just that moment, it will wake and NOT claim the request. As long as TASK_CONGESTED remains set, requests can only be claimed by tasks woken from the backlog, and they are woken only as requests are freed, so when a task doesn't claim a request, no other task can ever get that request until TASK_CONGESTED is cleared. Each time this happens the number of available requests is decreased by one. With a sufficiently high workload and sufficiently low setting of max_slot (16 in the case where this was seen), TASK_CONGESTED can remain set for an extended period, and the above scenario (of a process being killed just as its task was woken) can repeat until no requests can be allocated. Then traffic stops. This patch addresses the problem by introducing a positive handover of a request from a completing task to a backlog task - the request is never freed when there is a backlog. When a task is woken it might not already have a request attached in which case it is *not* freed (as with current code) but is initialised (if needed) and used. If it isn't used it will eventually be freed by rpc_exit_task(). xprt_release() is enhanced to be able to correctly release an uninitialised request. Fixes: ba60eb25ff6b ("SUNRPC: Fix a livelock problem in the xprt->backlog queue") Signed-off-by: NeilBrown Signed-off-by: Trond Myklebust --- net/sunrpc/clnt.c | 7 ------ net/sunrpc/xprt.c | 68 ++++++++++++++++++++++++++++++++++++++----------------- 2 files changed, 47 insertions(+), 28 deletions(-) (limited to 'net') diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index f555d335e910..42623d6b8f0e 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1677,13 +1677,6 @@ call_reserveresult(struct rpc_task *task) return; } - /* - * Even though there was an error, we may have acquired - * a request slot somehow. Make sure not to leak it. - */ - if (task->tk_rqstp) - xprt_release(task); - switch (status) { case -ENOMEM: rpc_delay(task, HZ >> 2); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index e5b5a960a69b..5b3981fd3783 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -70,6 +70,7 @@ static void xprt_init(struct rpc_xprt *xprt, struct net *net); static __be32 xprt_alloc_xid(struct rpc_xprt *xprt); static void xprt_destroy(struct rpc_xprt *xprt); +static void xprt_request_init(struct rpc_task *task); static DEFINE_SPINLOCK(xprt_list_lock); static LIST_HEAD(xprt_list); @@ -1612,10 +1613,26 @@ static void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task) rpc_sleep_on(&xprt->backlog, task, NULL); } -static void xprt_wake_up_backlog(struct rpc_xprt *xprt) +static bool __xprt_set_rq(struct rpc_task *task, void *data) { - if (rpc_wake_up_next(&xprt->backlog) == NULL) + struct rpc_rqst *req = data; + + if (task->tk_rqstp == NULL) { + memset(req, 0, sizeof(*req)); /* mark unused */ + task->tk_status = -EAGAIN; + task->tk_rqstp = req; + return true; + } + return false; +} + +static bool xprt_wake_up_backlog(struct rpc_xprt *xprt, struct rpc_rqst *req) +{ + if (rpc_wake_up_first(&xprt->backlog, __xprt_set_rq, req) == NULL) { clear_bit(XPRT_CONGESTED, &xprt->state); + return false; + } + return true; } static bool xprt_throttle_congested(struct rpc_xprt *xprt, struct rpc_task *task) @@ -1703,11 +1720,11 @@ EXPORT_SYMBOL_GPL(xprt_alloc_slot); void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req) { spin_lock(&xprt->reserve_lock); - if (!xprt_dynamic_free_slot(xprt, req)) { + if (!xprt_wake_up_backlog(xprt, req) && + !xprt_dynamic_free_slot(xprt, req)) { memset(req, 0, sizeof(*req)); /* mark unused */ list_add(&req->rq_list, &xprt->free); } - xprt_wake_up_backlog(xprt); spin_unlock(&xprt->reserve_lock); } EXPORT_SYMBOL_GPL(xprt_free_slot); @@ -1795,6 +1812,10 @@ xprt_request_init(struct rpc_task *task) struct rpc_xprt *xprt = task->tk_xprt; struct rpc_rqst *req = task->tk_rqstp; + if (req->rq_task) + /* Already initialized */ + return; + req->rq_task = task; req->rq_xprt = xprt; req->rq_buffer = NULL; @@ -1855,8 +1876,10 @@ void xprt_retry_reserve(struct rpc_task *task) struct rpc_xprt *xprt = task->tk_xprt; task->tk_status = 0; - if (task->tk_rqstp != NULL) + if (task->tk_rqstp != NULL) { + xprt_request_init(task); return; + } task->tk_status = -EAGAIN; xprt_do_reserve(xprt, task); @@ -1881,23 +1904,26 @@ void xprt_release(struct rpc_task *task) } xprt = req->rq_xprt; - xprt_request_dequeue_xprt(task); - spin_lock(&xprt->transport_lock); - xprt->ops->release_xprt(xprt, task); - if (xprt->ops->release_request) - xprt->ops->release_request(task); - xprt_schedule_autodisconnect(xprt); - spin_unlock(&xprt->transport_lock); - if (req->rq_buffer) - xprt->ops->buf_free(task); - xdr_free_bvec(&req->rq_rcv_buf); - xdr_free_bvec(&req->rq_snd_buf); - if (req->rq_cred != NULL) - put_rpccred(req->rq_cred); - task->tk_rqstp = NULL; - if (req->rq_release_snd_buf) - req->rq_release_snd_buf(req); + if (xprt) { + xprt_request_dequeue_xprt(task); + spin_lock(&xprt->transport_lock); + xprt->ops->release_xprt(xprt, task); + if (xprt->ops->release_request) + xprt->ops->release_request(task); + xprt_schedule_autodisconnect(xprt); + spin_unlock(&xprt->transport_lock); + if (req->rq_buffer) + xprt->ops->buf_free(task); + xdr_free_bvec(&req->rq_rcv_buf); + xdr_free_bvec(&req->rq_snd_buf); + if (req->rq_cred != NULL) + put_rpccred(req->rq_cred); + if (req->rq_release_snd_buf) + req->rq_release_snd_buf(req); + } else + xprt = task->tk_xprt; + task->tk_rqstp = NULL; if (likely(!bc_prealloc(req))) xprt->ops->free_slot(xprt, req); else -- cgit v1.2.3 From d275880abce9ac66cb842af828fbc2b1ba8082a0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 17 May 2021 08:50:11 -0400 Subject: SUNRPC: Fix Oops in xs_tcp_send_request() when transport is disconnected If a disconnection occurs while we're trying to reply to a server callback, then we may end up calling xs_tcp_send_request() with a NULL value for transport->inet, which trips up the call to tcp_sock_set_cork(). Fixes: d737e5d41870 ("SUNRPC: Set TCP_CORK until the transmit queue is empty") Cc: stable@vger.kernel.org Signed-off-by: Trond Myklebust --- net/sunrpc/xprtsock.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net') diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 47aa47a2b07c..316d04945587 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1010,6 +1010,8 @@ static int xs_tcp_send_request(struct rpc_rqst *req) kernel_sock_shutdown(transport->sock, SHUT_RDWR); return -ENOTCONN; } + if (!transport->inet) + return -ENOTCONN; xs_pktdump("packet data:", req->rq_svec->iov_base, -- cgit v1.2.3 From e86be3a04bc4aeaf12f93af35f08f8d4385bcd98 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 25 May 2021 18:43:38 -0400 Subject: SUNRPC: More fixes for backlog congestion Ensure that we fix the XPRT_CONGESTED starvation issue for RDMA as well as socket based transports. Ensure we always initialise the request after waking up from the backlog list. Fixes: e877a88d1f06 ("SUNRPC in case of backlog, hand free slots directly to waiting task") Signed-off-by: Trond Myklebust --- include/linux/sunrpc/xprt.h | 2 ++ net/sunrpc/xprt.c | 58 ++++++++++++++++++++--------------------- net/sunrpc/xprtrdma/transport.c | 12 ++++----- net/sunrpc/xprtrdma/verbs.c | 18 ++++++++++--- net/sunrpc/xprtrdma/xprt_rdma.h | 1 + 5 files changed, 52 insertions(+), 39 deletions(-) (limited to 'net') diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index d81fe8b364d0..61b622e334ee 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -368,6 +368,8 @@ struct rpc_xprt * xprt_alloc(struct net *net, size_t size, unsigned int num_prealloc, unsigned int max_req); void xprt_free(struct rpc_xprt *); +void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task); +bool xprt_wake_up_backlog(struct rpc_xprt *xprt, struct rpc_rqst *req); static inline int xprt_enable_swap(struct rpc_xprt *xprt) diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 5b3981fd3783..3509a7f139b9 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1607,11 +1607,18 @@ xprt_transmit(struct rpc_task *task) spin_unlock(&xprt->queue_lock); } -static void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task) +static void xprt_complete_request_init(struct rpc_task *task) +{ + if (task->tk_rqstp) + xprt_request_init(task); +} + +void xprt_add_backlog(struct rpc_xprt *xprt, struct rpc_task *task) { set_bit(XPRT_CONGESTED, &xprt->state); - rpc_sleep_on(&xprt->backlog, task, NULL); + rpc_sleep_on(&xprt->backlog, task, xprt_complete_request_init); } +EXPORT_SYMBOL_GPL(xprt_add_backlog); static bool __xprt_set_rq(struct rpc_task *task, void *data) { @@ -1619,14 +1626,13 @@ static bool __xprt_set_rq(struct rpc_task *task, void *data) if (task->tk_rqstp == NULL) { memset(req, 0, sizeof(*req)); /* mark unused */ - task->tk_status = -EAGAIN; task->tk_rqstp = req; return true; } return false; } -static bool xprt_wake_up_backlog(struct rpc_xprt *xprt, struct rpc_rqst *req) +bool xprt_wake_up_backlog(struct rpc_xprt *xprt, struct rpc_rqst *req) { if (rpc_wake_up_first(&xprt->backlog, __xprt_set_rq, req) == NULL) { clear_bit(XPRT_CONGESTED, &xprt->state); @@ -1634,6 +1640,7 @@ static bool xprt_wake_up_backlog(struct rpc_xprt *xprt, struct rpc_rqst *req) } return true; } +EXPORT_SYMBOL_GPL(xprt_wake_up_backlog); static bool xprt_throttle_congested(struct rpc_xprt *xprt, struct rpc_task *task) { @@ -1643,7 +1650,7 @@ static bool xprt_throttle_congested(struct rpc_xprt *xprt, struct rpc_task *task goto out; spin_lock(&xprt->reserve_lock); if (test_bit(XPRT_CONGESTED, &xprt->state)) { - rpc_sleep_on(&xprt->backlog, task, NULL); + xprt_add_backlog(xprt, task); ret = true; } spin_unlock(&xprt->reserve_lock); @@ -1812,10 +1819,6 @@ xprt_request_init(struct rpc_task *task) struct rpc_xprt *xprt = task->tk_xprt; struct rpc_rqst *req = task->tk_rqstp; - if (req->rq_task) - /* Already initialized */ - return; - req->rq_task = task; req->rq_xprt = xprt; req->rq_buffer = NULL; @@ -1876,10 +1879,8 @@ void xprt_retry_reserve(struct rpc_task *task) struct rpc_xprt *xprt = task->tk_xprt; task->tk_status = 0; - if (task->tk_rqstp != NULL) { - xprt_request_init(task); + if (task->tk_rqstp != NULL) return; - } task->tk_status = -EAGAIN; xprt_do_reserve(xprt, task); @@ -1904,24 +1905,21 @@ void xprt_release(struct rpc_task *task) } xprt = req->rq_xprt; - if (xprt) { - xprt_request_dequeue_xprt(task); - spin_lock(&xprt->transport_lock); - xprt->ops->release_xprt(xprt, task); - if (xprt->ops->release_request) - xprt->ops->release_request(task); - xprt_schedule_autodisconnect(xprt); - spin_unlock(&xprt->transport_lock); - if (req->rq_buffer) - xprt->ops->buf_free(task); - xdr_free_bvec(&req->rq_rcv_buf); - xdr_free_bvec(&req->rq_snd_buf); - if (req->rq_cred != NULL) - put_rpccred(req->rq_cred); - if (req->rq_release_snd_buf) - req->rq_release_snd_buf(req); - } else - xprt = task->tk_xprt; + xprt_request_dequeue_xprt(task); + spin_lock(&xprt->transport_lock); + xprt->ops->release_xprt(xprt, task); + if (xprt->ops->release_request) + xprt->ops->release_request(task); + xprt_schedule_autodisconnect(xprt); + spin_unlock(&xprt->transport_lock); + if (req->rq_buffer) + xprt->ops->buf_free(task); + xdr_free_bvec(&req->rq_rcv_buf); + xdr_free_bvec(&req->rq_snd_buf); + if (req->rq_cred != NULL) + put_rpccred(req->rq_cred); + if (req->rq_release_snd_buf) + req->rq_release_snd_buf(req); task->tk_rqstp = NULL; if (likely(!bc_prealloc(req))) diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 09953597d055..19a49d26b1e4 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -520,9 +520,8 @@ xprt_rdma_alloc_slot(struct rpc_xprt *xprt, struct rpc_task *task) return; out_sleep: - set_bit(XPRT_CONGESTED, &xprt->state); - rpc_sleep_on(&xprt->backlog, task, NULL); task->tk_status = -EAGAIN; + xprt_add_backlog(xprt, task); } /** @@ -537,10 +536,11 @@ xprt_rdma_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *rqst) struct rpcrdma_xprt *r_xprt = container_of(xprt, struct rpcrdma_xprt, rx_xprt); - memset(rqst, 0, sizeof(*rqst)); - rpcrdma_buffer_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst)); - if (unlikely(!rpc_wake_up_next(&xprt->backlog))) - clear_bit(XPRT_CONGESTED, &xprt->state); + rpcrdma_reply_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst)); + if (!xprt_wake_up_backlog(xprt, rqst)) { + memset(rqst, 0, sizeof(*rqst)); + rpcrdma_buffer_put(&r_xprt->rx_buf, rpcr_to_rdmar(rqst)); + } } static bool rpcrdma_check_regbuf(struct rpcrdma_xprt *r_xprt, diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 1e965a380896..649c23518ec0 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1200,6 +1200,20 @@ rpcrdma_mr_get(struct rpcrdma_xprt *r_xprt) return mr; } +/** + * rpcrdma_reply_put - Put reply buffers back into pool + * @buffers: buffer pool + * @req: object to return + * + */ +void rpcrdma_reply_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req) +{ + if (req->rl_reply) { + rpcrdma_rep_put(buffers, req->rl_reply); + req->rl_reply = NULL; + } +} + /** * rpcrdma_buffer_get - Get a request buffer * @buffers: Buffer pool from which to obtain a buffer @@ -1228,9 +1242,7 @@ rpcrdma_buffer_get(struct rpcrdma_buffer *buffers) */ void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req) { - if (req->rl_reply) - rpcrdma_rep_put(buffers, req->rl_reply); - req->rl_reply = NULL; + rpcrdma_reply_put(buffers, req); spin_lock(&buffers->rb_lock); list_add(&req->rl_list, &buffers->rb_send_bufs); diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 436ad7312614..5d231d94e944 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -479,6 +479,7 @@ struct rpcrdma_req *rpcrdma_buffer_get(struct rpcrdma_buffer *); void rpcrdma_buffer_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req); void rpcrdma_rep_put(struct rpcrdma_buffer *buf, struct rpcrdma_rep *rep); +void rpcrdma_reply_put(struct rpcrdma_buffer *buffers, struct rpcrdma_req *req); bool rpcrdma_regbuf_realloc(struct rpcrdma_regbuf *rb, size_t size, gfp_t flags); -- cgit v1.2.3 From ae605ee9830840f14566a3b1cde27fa8096dbdd4 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 26 May 2021 15:35:20 -0400 Subject: xprtrdma: Revert 586a0787ce35 Commit 9ed5af268e88 ("SUNRPC: Clean up the handling of page padding in rpc_prepare_reply_pages()") [Dec 2020] affects RPC Replies that have a data payload (i.e., Write chunks). rpcrdma_prepare_readch(), as its name suggests, sets up Read chunks which are data payloads within RPC Calls. Those payloads are constructed by xdr_write_pages(), which continues to stuff the call buffer's tail kvec with the payload's XDR roundup. Thus removing the tail buffer logic in rpcrdma_prepare_readch() was the wrong thing to do. Fixes: 586a0787ce35 ("xprtrdma: Clean up rpcrdma_prepare_readch()") Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- net/sunrpc/xprtrdma/rpc_rdma.c | 27 ++++++++++++++++++--------- 1 file changed, 18 insertions(+), 9 deletions(-) (limited to 'net') diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 649f7d8b9733..c335c1361564 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -628,8 +628,9 @@ out_mapping_err: return false; } -/* The tail iovec might not reside in the same page as the - * head iovec. +/* The tail iovec may include an XDR pad for the page list, + * as well as additional content, and may not reside in the + * same page as the head iovec. */ static bool rpcrdma_prepare_tail_iov(struct rpcrdma_req *req, struct xdr_buf *xdr, @@ -747,19 +748,27 @@ static bool rpcrdma_prepare_readch(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req, struct xdr_buf *xdr) { - struct kvec *tail = &xdr->tail[0]; - if (!rpcrdma_prepare_head_iov(r_xprt, req, xdr->head[0].iov_len)) return false; - /* If there is a Read chunk, the page list is handled + /* If there is a Read chunk, the page list is being handled * via explicit RDMA, and thus is skipped here. */ - if (tail->iov_len) { - if (!rpcrdma_prepare_tail_iov(req, xdr, - offset_in_page(tail->iov_base), - tail->iov_len)) + /* Do not include the tail if it is only an XDR pad */ + if (xdr->tail[0].iov_len > 3) { + unsigned int page_base, len; + + /* If the content in the page list is an odd length, + * xdr_write_pages() adds a pad at the beginning of + * the tail iovec. Force the tail's non-pad content to + * land at the next XDR position in the Send message. + */ + page_base = offset_in_page(xdr->tail[0].iov_base); + len = xdr->tail[0].iov_len; + page_base += len & 3; + len -= len & 3; + if (!rpcrdma_prepare_tail_iov(req, xdr, page_base, len)) return false; kref_get(&req->rl_kref); } -- cgit v1.2.3 From 0ee4d55534f82a0624701d0bb9fc2304d4529086 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 17 May 2021 16:47:17 +0200 Subject: mac80211: remove warning in ieee80211_get_sband() Syzbot reports that it's possible to hit this from userspace, by trying to add a station before any other connection setup has been done. Instead of trying to catch this in some other way simply remove the warning, that will appropriately reject the call from userspace. Reported-by: syzbot+7716dbc401d9a437890d@syzkaller.appspotmail.com Link: https://lore.kernel.org/r/20210517164715.f537da276d17.Id05f40ec8761d6a8cc2df87f1aa09c651988a586@changeid Signed-off-by: Johannes Berg --- net/mac80211/ieee80211_i.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 214404a558fb..648696b49f89 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1442,7 +1442,7 @@ ieee80211_get_sband(struct ieee80211_sub_if_data *sdata) rcu_read_lock(); chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf); - if (WARN_ON_ONCE(!chanctx_conf)) { + if (!chanctx_conf) { rcu_read_unlock(); return NULL; } -- cgit v1.2.3 From a64b6a25dd9f984ed05fade603a00e2eae787d2f Mon Sep 17 00:00:00 2001 From: Du Cheng Date: Wed, 28 Apr 2021 14:39:41 +0800 Subject: cfg80211: call cfg80211_leave_ocb when switching away from OCB If the userland switches back-and-forth between NL80211_IFTYPE_OCB and NL80211_IFTYPE_ADHOC via send_msg(NL80211_CMD_SET_INTERFACE), there is a chance where the cleanup cfg80211_leave_ocb() is not called. This leads to initialization of in-use memory (e.g. init u.ibss while in-use by u.ocb) due to a shared struct/union within ieee80211_sub_if_data: struct ieee80211_sub_if_data { ... union { struct ieee80211_if_ap ap; struct ieee80211_if_vlan vlan; struct ieee80211_if_managed mgd; struct ieee80211_if_ibss ibss; // <- shares address struct ieee80211_if_mesh mesh; struct ieee80211_if_ocb ocb; // <- shares address struct ieee80211_if_mntr mntr; struct ieee80211_if_nan nan; } u; ... } Therefore add handling of otype == NL80211_IFTYPE_OCB, during cfg80211_change_iface() to perform cleanup when leaving OCB mode. link to syzkaller bug: https://syzkaller.appspot.com/bug?id=0612dbfa595bf4b9b680ff7b4948257b8e3732d5 Reported-by: syzbot+105896fac213f26056f9@syzkaller.appspotmail.com Signed-off-by: Du Cheng Link: https://lore.kernel.org/r/20210428063941.105161-1-ducheng2@gmail.com Signed-off-by: Johannes Berg --- net/wireless/util.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net') diff --git a/net/wireless/util.c b/net/wireless/util.c index 7ec021a610ae..18dba3d7c638 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1059,6 +1059,9 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, case NL80211_IFTYPE_MESH_POINT: /* mesh should be handled? */ break; + case NL80211_IFTYPE_OCB: + cfg80211_leave_ocb(rdev, dev); + break; default: break; } -- cgit v1.2.3 From e298aa358f0ca658406d524b6639fe389cb6e11e Mon Sep 17 00:00:00 2001 From: Du Cheng Date: Mon, 10 May 2021 12:16:49 +0800 Subject: mac80211: fix skb length check in ieee80211_scan_rx() Replace hard-coded compile-time constants for header length check with dynamic determination based on the frame type. Otherwise, we hit a validation WARN_ON in cfg80211 later. Fixes: cd418ba63f0c ("mac80211: convert S1G beacon to scan results") Reported-by: syzbot+405843667e93b9790fc1@syzkaller.appspotmail.com Signed-off-by: Du Cheng Link: https://lore.kernel.org/r/20210510041649.589754-1-ducheng2@gmail.com [style fixes, reword commit message] Signed-off-by: Johannes Berg --- net/mac80211/scan.c | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index d4cc9ac2d703..6b50cb5e0e3c 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -251,13 +251,24 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb) struct ieee80211_mgmt *mgmt = (void *)skb->data; struct ieee80211_bss *bss; struct ieee80211_channel *channel; + size_t min_hdr_len = offsetof(struct ieee80211_mgmt, + u.probe_resp.variable); + + if (!ieee80211_is_probe_resp(mgmt->frame_control) && + !ieee80211_is_beacon(mgmt->frame_control) && + !ieee80211_is_s1g_beacon(mgmt->frame_control)) + return; if (ieee80211_is_s1g_beacon(mgmt->frame_control)) { - if (skb->len < 15) - return; - } else if (skb->len < 24 || - (!ieee80211_is_probe_resp(mgmt->frame_control) && - !ieee80211_is_beacon(mgmt->frame_control))) + if (ieee80211_is_s1g_short_beacon(mgmt->frame_control)) + min_hdr_len = offsetof(struct ieee80211_ext, + u.s1g_short_beacon.variable); + else + min_hdr_len = offsetof(struct ieee80211_ext, + u.s1g_beacon); + } + + if (skb->len < min_hdr_len) return; sdata1 = rcu_dereference(local->scan_sdata); -- cgit v1.2.3 From bddc0c411a45d3718ac535a070f349be8eca8d48 Mon Sep 17 00:00:00 2001 From: Mathy Vanhoef Date: Sun, 30 May 2021 15:32:26 +0200 Subject: mac80211: Fix NULL ptr deref for injected rate info The commit cb17ed29a7a5 ("mac80211: parse radiotap header when selecting Tx queue") moved the code to validate the radiotap header from ieee80211_monitor_start_xmit to ieee80211_parse_tx_radiotap. This made is possible to share more code with the new Tx queue selection code for injected frames. But at the same time, it now required the call of ieee80211_parse_tx_radiotap at the beginning of functions which wanted to handle the radiotap header. And this broke the rate parser for radiotap header parser. The radiotap parser for rates is operating most of the time only on the data in the actual radiotap header. But for the 802.11a/b/g rates, it must also know the selected band from the chandef information. But this information is only written to the ieee80211_tx_info at the end of the ieee80211_monitor_start_xmit - long after ieee80211_parse_tx_radiotap was already called. The info->band information was therefore always 0 (NL80211_BAND_2GHZ) when the parser code tried to access it. For a 5GHz only device, injecting a frame with 802.11a rates would cause a NULL pointer dereference because local->hw.wiphy->bands[NL80211_BAND_2GHZ] would most likely have been NULL when the radiotap parser searched for the correct rate index of the driver. Cc: stable@vger.kernel.org Reported-by: Ben Greear Fixes: cb17ed29a7a5 ("mac80211: parse radiotap header when selecting Tx queue") Signed-off-by: Mathy Vanhoef [sven@narfation.org: added commit message] Signed-off-by: Sven Eckelmann Link: https://lore.kernel.org/r/20210530133226.40587-1-sven@narfation.org Signed-off-by: Johannes Berg --- include/net/mac80211.h | 7 ++++++- net/mac80211/tx.c | 52 ++++++++++++++++++++++++++++++++++---------------- 2 files changed, 42 insertions(+), 17 deletions(-) (limited to 'net') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index e7c59b4e2c44..e89530d0d9c6 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -6392,7 +6392,12 @@ bool ieee80211_tx_prepare_skb(struct ieee80211_hw *hw, /** * ieee80211_parse_tx_radiotap - Sanity-check and parse the radiotap header - * of injected frames + * of injected frames. + * + * To accurately parse and take into account rate and retransmission fields, + * you must initialize the chandef field in the ieee80211_tx_info structure + * of the skb before calling this function. + * * @skb: packet injected by userspace * @dev: the &struct device of this 802.11 device */ diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 0b719f3d2dec..2651498d05e8 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2014,6 +2014,26 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, ieee80211_tx(sdata, sta, skb, false); } +static bool ieee80211_validate_radiotap_len(struct sk_buff *skb) +{ + struct ieee80211_radiotap_header *rthdr = + (struct ieee80211_radiotap_header *)skb->data; + + /* check for not even having the fixed radiotap header part */ + if (unlikely(skb->len < sizeof(struct ieee80211_radiotap_header))) + return false; /* too short to be possibly valid */ + + /* is it a header version we can trust to find length from? */ + if (unlikely(rthdr->it_version)) + return false; /* only version 0 is supported */ + + /* does the skb contain enough to deliver on the alleged length? */ + if (unlikely(skb->len < ieee80211_get_radiotap_len(skb->data))) + return false; /* skb too short for claimed rt header extent */ + + return true; +} + bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, struct net_device *dev) { @@ -2022,8 +2042,6 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, struct ieee80211_radiotap_header *rthdr = (struct ieee80211_radiotap_header *) skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - struct ieee80211_supported_band *sband = - local->hw.wiphy->bands[info->band]; int ret = ieee80211_radiotap_iterator_init(&iterator, rthdr, skb->len, NULL); u16 txflags; @@ -2036,17 +2054,8 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, u8 vht_mcs = 0, vht_nss = 0; int i; - /* check for not even having the fixed radiotap header part */ - if (unlikely(skb->len < sizeof(struct ieee80211_radiotap_header))) - return false; /* too short to be possibly valid */ - - /* is it a header version we can trust to find length from? */ - if (unlikely(rthdr->it_version)) - return false; /* only version 0 is supported */ - - /* does the skb contain enough to deliver on the alleged length? */ - if (unlikely(skb->len < ieee80211_get_radiotap_len(skb->data))) - return false; /* skb too short for claimed rt header extent */ + if (!ieee80211_validate_radiotap_len(skb)) + return false; info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT | IEEE80211_TX_CTL_DONTFRAG; @@ -2186,6 +2195,9 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, return false; if (rate_found) { + struct ieee80211_supported_band *sband = + local->hw.wiphy->bands[info->band]; + info->control.flags |= IEEE80211_TX_CTRL_RATE_INJECT; for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) { @@ -2199,7 +2211,7 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb, } else if (rate_flags & IEEE80211_TX_RC_VHT_MCS) { ieee80211_rate_set_vht(info->control.rates, vht_mcs, vht_nss); - } else { + } else if (sband) { for (i = 0; i < sband->n_bitrates; i++) { if (rate * 5 != sband->bitrates[i].bitrate) continue; @@ -2236,8 +2248,8 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, info->flags = IEEE80211_TX_CTL_REQ_TX_STATUS | IEEE80211_TX_CTL_INJECTED; - /* Sanity-check and process the injection radiotap header */ - if (!ieee80211_parse_tx_radiotap(skb, dev)) + /* Sanity-check the length of the radiotap header */ + if (!ieee80211_validate_radiotap_len(skb)) goto fail; /* we now know there is a radiotap header with a length we can use */ @@ -2351,6 +2363,14 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, ieee80211_select_queue_80211(sdata, skb, hdr); skb_set_queue_mapping(skb, ieee80211_ac_from_tid(skb->priority)); + /* + * Process the radiotap header. This will now take into account the + * selected chandef above to accurately set injection rates and + * retransmissions. + */ + if (!ieee80211_parse_tx_radiotap(skb, dev)) + goto fail_rcu; + /* remove the injection radiotap header */ skb_pull(skb, len_rthdr); -- cgit v1.2.3 From 51c96a561f244e25a4a2afc7a48b92b4adf8050d Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sun, 6 Jun 2021 17:24:22 +0300 Subject: ethtool: Fix NULL pointer dereference during module EEPROM dump When get_module_eeprom_by_page() is not implemented by the driver, NULL pointer dereference can occur [1]. Fix by testing if get_module_eeprom_by_page() is implemented instead of get_module_info(). [1] BUG: kernel NULL pointer dereference, address: 0000000000000000 [...] CPU: 0 PID: 251 Comm: ethtool Not tainted 5.13.0-rc3-custom-00940-g3822d0670c9d #989 Call Trace: eeprom_prepare_data+0x101/0x2d0 ethnl_default_doit+0xc2/0x290 genl_family_rcv_msg_doit+0xdc/0x140 genl_rcv_msg+0xd7/0x1d0 netlink_rcv_skb+0x49/0xf0 genl_rcv+0x1f/0x30 netlink_unicast+0x1f6/0x2c0 netlink_sendmsg+0x1f9/0x400 __sys_sendto+0xe1/0x130 __x64_sys_sendto+0x1b/0x20 do_syscall_64+0x3a/0x70 entry_SYSCALL_64_after_hwframe+0x44/0xae Fixes: c97a31f66ebc ("ethtool: wire in generic SFP module access") Signed-off-by: Ido Schimmel Acked-by: Moshe Shemesh Signed-off-by: David S. Miller --- net/ethtool/eeprom.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/ethtool/eeprom.c b/net/ethtool/eeprom.c index 2a6733a6449a..5d38e90895ac 100644 --- a/net/ethtool/eeprom.c +++ b/net/ethtool/eeprom.c @@ -95,7 +95,7 @@ static int get_module_eeprom_by_page(struct net_device *dev, if (dev->sfp_bus) return sfp_get_module_eeprom_by_page(dev->sfp_bus, page_data, extack); - if (ops->get_module_info) + if (ops->get_module_eeprom_by_page) return ops->get_module_eeprom_by_page(dev, page_data, extack); return -EOPNOTSUPP; -- cgit v1.2.3 From a47c397bb29fce1751dc755246a2c8deeca5e38f Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Mon, 7 Jun 2021 21:46:23 +0300 Subject: revert "net: kcm: fix memory leak in kcm_sendmsg" In commit c47cc304990a ("net: kcm: fix memory leak in kcm_sendmsg") I misunderstood the root case of the memory leak and came up with completely broken fix. So, simply revert this commit to avoid GPF reported by syzbot. Im so sorry for this situation. Fixes: c47cc304990a ("net: kcm: fix memory leak in kcm_sendmsg") Reported-by: syzbot+65badd5e74ec62cb67dc@syzkaller.appspotmail.com Signed-off-by: Pavel Skripkin Signed-off-by: David S. Miller --- net/kcm/kcmsock.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'net') diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 1c572c8daced..6201965bd822 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1066,11 +1066,6 @@ out_error: goto partial_message; } - if (skb_has_frag_list(head)) { - kfree_skb_list(skb_shinfo(head)->frag_list); - skb_shinfo(head)->frag_list = NULL; - } - if (head != kcm->seq_skb) kfree_skb(head); -- cgit v1.2.3 From 7a6b1ab7475fd6478eeaf5c9d1163e7a18125c8f Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 7 Jun 2021 11:35:30 -0600 Subject: neighbour: allow NUD_NOARP entries to be forced GCed IFF_POINTOPOINT interfaces use NUD_NOARP entries for IPv6. It's possible to fill up the neighbour table with enough entries that it will overflow for valid connections after that. This behaviour is more prevalent after commit 58956317c8de ("neighbor: Improve garbage collection") is applied, as it prevents removal from entries that are not NUD_FAILED, unless they are more than 5s old. Fixes: 58956317c8de (neighbor: Improve garbage collection) Reported-by: Kasper Dupont Signed-off-by: Thadeu Lima de Souza Cascardo Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/core/neighbour.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 98f20efbfadf..bf774575ad71 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -238,6 +238,7 @@ static int neigh_forced_gc(struct neigh_table *tbl) write_lock(&n->lock); if ((n->nud_state == NUD_FAILED) || + (n->nud_state == NUD_NOARP) || (tbl->is_multicast && tbl->is_multicast(n->primary_key)) || time_after(tref, n->updated)) -- cgit v1.2.3 From d5befb224edbe53056c2c18999d630dafb4a08b9 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 17 May 2021 16:03:23 +0200 Subject: mac80211: fix deadlock in AP/VLAN handling Syzbot reports that when you have AP_VLAN interfaces that are up and close the AP interface they belong to, we get a deadlock. No surprise - since we dev_close() them with the wiphy mutex held, which goes back into the netdev notifier in cfg80211 and tries to acquire the wiphy mutex there. To fix this, we need to do two things: 1) prevent changing iftype while AP_VLANs are up, we can't easily fix this case since cfg80211 already calls us with the wiphy mutex held, but change_interface() is relatively rare in drivers anyway, so changing iftype isn't used much (and userspace has to fall back to down/change/up anyway) 2) pull the dev_close() loop over VLANs out of the wiphy mutex section in the normal stop case Cc: stable@vger.kernel.org Reported-by: syzbot+452ea4fbbef700ff0a56@syzkaller.appspotmail.com Fixes: a05829a7222e ("cfg80211: avoid holding the RTNL when calling the driver") Link: https://lore.kernel.org/r/20210517160322.9b8f356c0222.I392cb0e2fa5a1a94cf2e637555d702c7e512c1ff@changeid Signed-off-by: Johannes Berg --- net/mac80211/iface.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) (limited to 'net') diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 2e2f73a4aa73..137fa4c50e07 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -476,14 +476,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do GFP_KERNEL); } - /* APs need special treatment */ if (sdata->vif.type == NL80211_IFTYPE_AP) { - struct ieee80211_sub_if_data *vlan, *tmpsdata; - - /* down all dependent devices, that is VLANs */ - list_for_each_entry_safe(vlan, tmpsdata, &sdata->u.ap.vlans, - u.vlan.list) - dev_close(vlan->dev); WARN_ON(!list_empty(&sdata->u.ap.vlans)); } else if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { /* remove all packets in parent bc_buf pointing to this dev */ @@ -641,6 +634,15 @@ static int ieee80211_stop(struct net_device *dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + /* close all dependent VLAN interfaces before locking wiphy */ + if (sdata->vif.type == NL80211_IFTYPE_AP) { + struct ieee80211_sub_if_data *vlan, *tmpsdata; + + list_for_each_entry_safe(vlan, tmpsdata, &sdata->u.ap.vlans, + u.vlan.list) + dev_close(vlan->dev); + } + wiphy_lock(sdata->local->hw.wiphy); ieee80211_do_stop(sdata, true); wiphy_unlock(sdata->local->hw.wiphy); @@ -1591,6 +1593,9 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata, switch (sdata->vif.type) { case NL80211_IFTYPE_AP: + if (!list_empty(&sdata->u.ap.vlans)) + return -EBUSY; + break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_ADHOC: case NL80211_IFTYPE_OCB: -- cgit v1.2.3 From d612c3f3fae221e7ea736d196581c2217304bbbc Mon Sep 17 00:00:00 2001 From: Nanyong Sun Date: Tue, 8 Jun 2021 09:51:58 +0800 Subject: net: ipv4: fix memory leak in netlbl_cipsov4_add_std Reported by syzkaller: BUG: memory leak unreferenced object 0xffff888105df7000 (size 64): comm "syz-executor842", pid 360, jiffies 4294824824 (age 22.546s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000e67ed558>] kmalloc include/linux/slab.h:590 [inline] [<00000000e67ed558>] kzalloc include/linux/slab.h:720 [inline] [<00000000e67ed558>] netlbl_cipsov4_add_std net/netlabel/netlabel_cipso_v4.c:145 [inline] [<00000000e67ed558>] netlbl_cipsov4_add+0x390/0x2340 net/netlabel/netlabel_cipso_v4.c:416 [<0000000006040154>] genl_family_rcv_msg_doit.isra.0+0x20e/0x320 net/netlink/genetlink.c:739 [<00000000204d7a1c>] genl_family_rcv_msg net/netlink/genetlink.c:783 [inline] [<00000000204d7a1c>] genl_rcv_msg+0x2bf/0x4f0 net/netlink/genetlink.c:800 [<00000000c0d6a995>] netlink_rcv_skb+0x134/0x3d0 net/netlink/af_netlink.c:2504 [<00000000d78b9d2c>] genl_rcv+0x24/0x40 net/netlink/genetlink.c:811 [<000000009733081b>] netlink_unicast_kernel net/netlink/af_netlink.c:1314 [inline] [<000000009733081b>] netlink_unicast+0x4a0/0x6a0 net/netlink/af_netlink.c:1340 [<00000000d5fd43b8>] netlink_sendmsg+0x789/0xc70 net/netlink/af_netlink.c:1929 [<000000000a2d1e40>] sock_sendmsg_nosec net/socket.c:654 [inline] [<000000000a2d1e40>] sock_sendmsg+0x139/0x170 net/socket.c:674 [<00000000321d1969>] ____sys_sendmsg+0x658/0x7d0 net/socket.c:2350 [<00000000964e16bc>] ___sys_sendmsg+0xf8/0x170 net/socket.c:2404 [<000000001615e288>] __sys_sendmsg+0xd3/0x190 net/socket.c:2433 [<000000004ee8b6a5>] do_syscall_64+0x37/0x90 arch/x86/entry/common.c:47 [<00000000171c7cee>] entry_SYSCALL_64_after_hwframe+0x44/0xae The memory of doi_def->map.std pointing is allocated in netlbl_cipsov4_add_std, but no place has freed it. It should be freed in cipso_v4_doi_free which frees the cipso DOI resource. Fixes: 96cb8e3313c7a ("[NetLabel]: CIPSOv4 and Unlabeled packet integration") Reported-by: Hulk Robot Signed-off-by: Nanyong Sun Acked-by: Paul Moore Signed-off-by: David S. Miller --- net/ipv4/cipso_ipv4.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index bfaf327e9d12..e0480c6cebaa 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -472,6 +472,7 @@ void cipso_v4_doi_free(struct cipso_v4_doi *doi_def) kfree(doi_def->map.std->lvl.local); kfree(doi_def->map.std->cat.cipso); kfree(doi_def->map.std->cat.local); + kfree(doi_def->map.std); break; } kfree(doi_def); -- cgit v1.2.3 From 5ac6b198d7e312bd10ebe7d58c64690dc59cc49a Mon Sep 17 00:00:00 2001 From: Zheng Yongjun Date: Tue, 8 Jun 2021 09:53:15 +0800 Subject: net: ipv4: Remove unneed BUG() function When 'nla_parse_nested_deprecated' failed, it's no need to BUG() here, return -EINVAL is ok. Signed-off-by: Zheng Yongjun Signed-off-by: David S. Miller --- net/ipv4/devinet.c | 2 +- net/ipv6/addrconf.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 2e35f68da40a..1c6429c353a9 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1989,7 +1989,7 @@ static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla, return -EAFNOSUPPORT; if (nla_parse_nested_deprecated(tb, IFLA_INET_MAX, nla, NULL, NULL) < 0) - BUG(); + return -EINVAL; if (tb[IFLA_INET_CONF]) { nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index b0ef65eb9bd2..701eb82acd1c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5827,7 +5827,7 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla, return -EAFNOSUPPORT; if (nla_parse_nested_deprecated(tb, IFLA_INET6_MAX, nla, NULL, NULL) < 0) - BUG(); + return -EINVAL; if (tb[IFLA_INET6_TOKEN]) { err = inet6_set_iftoken(idev, nla_data(tb[IFLA_INET6_TOKEN]), -- cgit v1.2.3 From d439aa33a9b917cfbca8a528f13367aff974aeb7 Mon Sep 17 00:00:00 2001 From: gushengxian Date: Mon, 7 Jun 2021 19:19:32 -0700 Subject: net: appletalk: fix the usage of preposition The preposition "for" should be changed to preposition "of". Signed-off-by: gushengxian Signed-off-by: David S. Miller --- net/appletalk/aarp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c index be18af481d7d..c7236daa2415 100644 --- a/net/appletalk/aarp.c +++ b/net/appletalk/aarp.c @@ -768,7 +768,7 @@ static int aarp_rcv(struct sk_buff *skb, struct net_device *dev, if (a && a->status & ATIF_PROBE) { a->status |= ATIF_PROBE_FAIL; /* - * we do not respond to probe or request packets for + * we do not respond to probe or request packets of * this address while we are probing this address */ goto unlock; -- cgit v1.2.3 From 49bfcbfd989a8f1f23e705759a6bb099de2cff9f Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Tue, 8 Jun 2021 11:06:41 +0300 Subject: net: rds: fix memory leak in rds_recvmsg Syzbot reported memory leak in rds. The problem was in unputted refcount in case of error. int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int msg_flags) { ... if (!rds_next_incoming(rs, &inc)) { ... } After this "if" inc refcount incremented and if (rds_cmsg_recv(inc, msg, rs)) { ret = -EFAULT; goto out; } ... out: return ret; } in case of rds_cmsg_recv() fail the refcount won't be decremented. And it's easy to see from ftrace log, that rds_inc_addref() don't have rds_inc_put() pair in rds_recvmsg() after rds_cmsg_recv() 1) | rds_recvmsg() { 1) 3.721 us | rds_inc_addref(); 1) 3.853 us | rds_message_inc_copy_to_user(); 1) + 10.395 us | rds_cmsg_recv(); 1) + 34.260 us | } Fixes: bdbe6fbc6a2f ("RDS: recv.c") Reported-and-tested-by: syzbot+5134cdf021c4ed5aaa5f@syzkaller.appspotmail.com Signed-off-by: Pavel Skripkin Reviewed-by: Håkon Bugge Acked-by: Santosh Shilimkar Signed-off-by: David S. Miller --- net/rds/recv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/rds/recv.c b/net/rds/recv.c index 4db109fb6ec2..5b426dc3634d 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -714,7 +714,7 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, if (rds_cmsg_recv(inc, msg, rs)) { ret = -EFAULT; - goto out; + break; } rds_recvmsg_zcookie(rs, msg); -- cgit v1.2.3 From adaed1b9daf5a045be71e923e04b5069d2bee664 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 8 Jun 2021 11:32:27 +0200 Subject: mac80211: fix 'reset' debugfs locking cfg80211 now calls suspend/resume with the wiphy lock held, and while there's a problem with that needing to be fixed, we should do the same in debugfs. Cc: stable@vger.kernel.org Fixes: a05829a7222e ("cfg80211: avoid holding the RTNL when calling the driver") Link: https://lore.kernel.org/r/20210608113226.14020430e449.I78e19db0a55a8295a376e15ac4cf77dbb4c6fb51@changeid Signed-off-by: Johannes Berg --- net/mac80211/debugfs.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 9245c0421bda..b5ff61b6448a 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -4,7 +4,7 @@ * * Copyright 2007 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright (C) 2018 - 2019 Intel Corporation + * Copyright (C) 2018 - 2019, 2021 Intel Corporation */ #include @@ -389,8 +389,10 @@ static ssize_t reset_write(struct file *file, const char __user *user_buf, struct ieee80211_local *local = file->private_data; rtnl_lock(); + wiphy_lock(local->hw.wiphy); __ieee80211_suspend(&local->hw, NULL); __ieee80211_resume(&local->hw); + wiphy_unlock(local->hw.wiphy); rtnl_unlock(); return count; -- cgit v1.2.3 From 43076c1e074359f11c85d7d1b85ede1bbb8ee6b9 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 8 Jun 2021 11:32:28 +0200 Subject: cfg80211: fix phy80211 symlink creation When I moved around the code here, I neglected that we could still call register_netdev() or similar without the wiphy mutex held, which then calls cfg80211_register_wdev() - that's also done from cfg80211_register_netdevice(), but the phy80211 symlink creation was only there. Now, the symlink isn't needed for a *pure* wdev, but a netdev not registered via cfg80211_register_wdev() should still have the symlink, so move the creation to the right place. Cc: stable@vger.kernel.org Fixes: 2fe8ef106238 ("cfg80211: change netdev registration/unregistration semantics") Link: https://lore.kernel.org/r/20210608113226.a5dc4c1e488c.Ia42fe663cefe47b0883af78c98f284c5555bbe5d@changeid Signed-off-by: Johannes Berg --- net/wireless/core.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) (limited to 'net') diff --git a/net/wireless/core.c b/net/wireless/core.c index 6fbf7537faf5..8d0883e81093 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1340,6 +1340,11 @@ void cfg80211_register_wdev(struct cfg80211_registered_device *rdev, rdev->devlist_generation++; wdev->registered = true; + if (wdev->netdev && + sysfs_create_link(&wdev->netdev->dev.kobj, &rdev->wiphy.dev.kobj, + "phy80211")) + pr_err("failed to add phy80211 symlink to netdev!\n"); + nl80211_notify_iface(rdev, wdev, NL80211_CMD_NEW_INTERFACE); } @@ -1365,14 +1370,6 @@ int cfg80211_register_netdevice(struct net_device *dev) if (ret) goto out; - if (sysfs_create_link(&dev->dev.kobj, &rdev->wiphy.dev.kobj, - "phy80211")) { - pr_err("failed to add phy80211 symlink to netdev!\n"); - unregister_netdevice(dev); - ret = -EINVAL; - goto out; - } - cfg80211_register_wdev(rdev, wdev); ret = 0; out: -- cgit v1.2.3 From 65bec836da8394b1d56bdec2c478dcac21cf12a4 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 8 Jun 2021 11:32:29 +0200 Subject: cfg80211: shut down interfaces on failed resume If resume fails, we should shut down all interfaces as the hardware is probably dead. This was/is already done now in mac80211, but we need to change that due to locking issues, so move it here and do it without the wiphy lock held. Cc: stable@vger.kernel.org Fixes: 2fe8ef106238 ("cfg80211: change netdev registration/unregistration semantics") Link: https://lore.kernel.org/r/20210608113226.d564ca69de7c.I2e3c3e5d410b72a4f63bade4fb075df041b3d92f@changeid Signed-off-by: Johannes Berg --- net/wireless/sysfs.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net') diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c index 9b959e3b09c6..0c3f05c9be27 100644 --- a/net/wireless/sysfs.c +++ b/net/wireless/sysfs.c @@ -133,6 +133,10 @@ static int wiphy_resume(struct device *dev) if (rdev->wiphy.registered && rdev->ops->resume) ret = rdev_resume(rdev); wiphy_unlock(&rdev->wiphy); + + if (ret) + cfg80211_shutdown_all_interfaces(&rdev->wiphy); + rtnl_unlock(); return ret; -- cgit v1.2.3 From f5baf287f5da5641099ad5c809b3b4ebfc08506d Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 8 Jun 2021 11:32:30 +0200 Subject: mac80211: move interface shutdown out of wiphy lock When reconfiguration fails, we shut down everything, but we cannot call cfg80211_shutdown_all_interfaces() with the wiphy mutex held. Since cfg80211 now calls it on resume errors, we only need to do likewise for where we call reconfig (whether directly or indirectly), but not under the wiphy lock. Cc: stable@vger.kernel.org Fixes: 2fe8ef106238 ("cfg80211: change netdev registration/unregistration semantics") Link: https://lore.kernel.org/r/20210608113226.78233c80f548.Iecc104aceb89f0568f50e9670a9cb191a1c8887b@changeid Signed-off-by: Johannes Berg --- net/mac80211/debugfs.c | 7 ++++++- net/mac80211/main.c | 7 ++++++- net/mac80211/util.c | 2 -- 3 files changed, 12 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index b5ff61b6448a..fc34ae2b604c 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -387,12 +387,17 @@ static ssize_t reset_write(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { struct ieee80211_local *local = file->private_data; + int ret; rtnl_lock(); wiphy_lock(local->hw.wiphy); __ieee80211_suspend(&local->hw, NULL); - __ieee80211_resume(&local->hw); + ret = __ieee80211_resume(&local->hw); wiphy_unlock(local->hw.wiphy); + + if (ret) + cfg80211_shutdown_all_interfaces(local->hw.wiphy); + rtnl_unlock(); return count; diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 62145e5f9628..f33a3acd7f96 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -252,6 +252,7 @@ static void ieee80211_restart_work(struct work_struct *work) struct ieee80211_local *local = container_of(work, struct ieee80211_local, restart_work); struct ieee80211_sub_if_data *sdata; + int ret; /* wait for scan work complete */ flush_workqueue(local->workqueue); @@ -301,8 +302,12 @@ static void ieee80211_restart_work(struct work_struct *work) /* wait for all packet processing to be done */ synchronize_net(); - ieee80211_reconfig(local); + ret = ieee80211_reconfig(local); wiphy_unlock(local->hw.wiphy); + + if (ret) + cfg80211_shutdown_all_interfaces(local->hw.wiphy); + rtnl_unlock(); } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 0a0481f5af48..93d96a4f9c3e 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2178,8 +2178,6 @@ static void ieee80211_handle_reconfig_failure(struct ieee80211_local *local) list_for_each_entry(ctx, &local->chanctx_list, list) ctx->driver_present = false; mutex_unlock(&local->chanctx_mtx); - - cfg80211_shutdown_all_interfaces(local->hw.wiphy); } static void ieee80211_assign_chanctx(struct ieee80211_local *local, -- cgit v1.2.3 From a9799541ca34652d9996e45f80e8e03144c12949 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 9 Jun 2021 16:13:06 +0200 Subject: mac80211: drop multicast fragments These are not permitted by the spec, just drop them. Link: https://lore.kernel.org/r/20210609161305.23def022b750.Ibd6dd3cdce573dae262fcdc47f8ac52b883a9c50@changeid Signed-off-by: Johannes Berg --- net/mac80211/rx.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'net') diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 1bb43edd47b6..af0ef456eb0f 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2240,17 +2240,15 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) sc = le16_to_cpu(hdr->seq_ctrl); frag = sc & IEEE80211_SCTL_FRAG; - if (is_multicast_ether_addr(hdr->addr1)) { - I802_DEBUG_INC(rx->local->dot11MulticastReceivedFrameCount); - goto out_no_led; - } - if (rx->sta) cache = &rx->sta->frags; if (likely(!ieee80211_has_morefrags(fc) && frag == 0)) goto out; + if (is_multicast_ether_addr(hdr->addr1)) + return RX_DROP_MONITOR; + I802_DEBUG_INC(rx->local->rx_handlers_fragments); if (skb_linearize(rx->skb)) @@ -2376,7 +2374,6 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) out: ieee80211_led_rx(rx->local); - out_no_led: if (rx->sta) rx->sta->rx_stats.packets++; return RX_CONTINUE; -- cgit v1.2.3 From ad9f151e560b016b6ad3280b48e42fa11e1a5440 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Fri, 4 Jun 2021 03:07:28 +0200 Subject: netfilter: nf_tables: initialize set before expression setup nft_set_elem_expr_alloc() needs an initialized set if expression sets on the NFT_EXPR_GC flag. Move set fields initialization before expression setup. [4512935.019450] ================================================================== [4512935.019456] BUG: KASAN: null-ptr-deref in nft_set_elem_expr_alloc+0x84/0xd0 [nf_tables] [4512935.019487] Read of size 8 at addr 0000000000000070 by task nft/23532 [4512935.019494] CPU: 1 PID: 23532 Comm: nft Not tainted 5.12.0-rc4+ #48 [...] [4512935.019502] Call Trace: [4512935.019505] dump_stack+0x89/0xb4 [4512935.019512] ? nft_set_elem_expr_alloc+0x84/0xd0 [nf_tables] [4512935.019536] ? nft_set_elem_expr_alloc+0x84/0xd0 [nf_tables] [4512935.019560] kasan_report.cold.12+0x5f/0xd8 [4512935.019566] ? nft_set_elem_expr_alloc+0x84/0xd0 [nf_tables] [4512935.019590] nft_set_elem_expr_alloc+0x84/0xd0 [nf_tables] [4512935.019615] nf_tables_newset+0xc7f/0x1460 [nf_tables] Reported-by: syzbot+ce96ca2b1d0b37c6422d@syzkaller.appspotmail.com Fixes: 65038428b2c6 ("netfilter: nf_tables: allow to specify stateful expression in set definition") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 85 ++++++++++++++++++++++--------------------- 1 file changed, 43 insertions(+), 42 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 72bc759179ef..bf4d6ec9fc55 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4364,13 +4364,45 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, err = nf_tables_set_alloc_name(&ctx, set, name); kfree(name); if (err < 0) - goto err_set_alloc_name; + goto err_set_name; + + udata = NULL; + if (udlen) { + udata = set->data + size; + nla_memcpy(udata, nla[NFTA_SET_USERDATA], udlen); + } + + INIT_LIST_HEAD(&set->bindings); + INIT_LIST_HEAD(&set->catchall_list); + set->table = table; + write_pnet(&set->net, net); + set->ops = ops; + set->ktype = ktype; + set->klen = desc.klen; + set->dtype = dtype; + set->objtype = objtype; + set->dlen = desc.dlen; + set->flags = flags; + set->size = desc.size; + set->policy = policy; + set->udlen = udlen; + set->udata = udata; + set->timeout = timeout; + set->gc_int = gc_int; + + set->field_count = desc.field_count; + for (i = 0; i < desc.field_count; i++) + set->field_len[i] = desc.field_len[i]; + + err = ops->init(set, &desc, nla); + if (err < 0) + goto err_set_init; if (nla[NFTA_SET_EXPR]) { expr = nft_set_elem_expr_alloc(&ctx, set, nla[NFTA_SET_EXPR]); if (IS_ERR(expr)) { err = PTR_ERR(expr); - goto err_set_alloc_name; + goto err_set_expr_alloc; } set->exprs[0] = expr; set->num_exprs++; @@ -4381,75 +4413,44 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info, if (!(flags & NFT_SET_EXPR)) { err = -EINVAL; - goto err_set_alloc_name; + goto err_set_expr_alloc; } i = 0; nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) { if (i == NFT_SET_EXPR_MAX) { err = -E2BIG; - goto err_set_init; + goto err_set_expr_alloc; } if (nla_type(tmp) != NFTA_LIST_ELEM) { err = -EINVAL; - goto err_set_init; + goto err_set_expr_alloc; } expr = nft_set_elem_expr_alloc(&ctx, set, tmp); if (IS_ERR(expr)) { err = PTR_ERR(expr); - goto err_set_init; + goto err_set_expr_alloc; } set->exprs[i++] = expr; set->num_exprs++; } } - udata = NULL; - if (udlen) { - udata = set->data + size; - nla_memcpy(udata, nla[NFTA_SET_USERDATA], udlen); - } - - INIT_LIST_HEAD(&set->bindings); - INIT_LIST_HEAD(&set->catchall_list); - set->table = table; - write_pnet(&set->net, net); - set->ops = ops; - set->ktype = ktype; - set->klen = desc.klen; - set->dtype = dtype; - set->objtype = objtype; - set->dlen = desc.dlen; - set->flags = flags; - set->size = desc.size; - set->policy = policy; - set->udlen = udlen; - set->udata = udata; - set->timeout = timeout; - set->gc_int = gc_int; set->handle = nf_tables_alloc_handle(table); - set->field_count = desc.field_count; - for (i = 0; i < desc.field_count; i++) - set->field_len[i] = desc.field_len[i]; - - err = ops->init(set, &desc, nla); - if (err < 0) - goto err_set_init; - err = nft_trans_set_add(&ctx, NFT_MSG_NEWSET, set); if (err < 0) - goto err_set_trans; + goto err_set_expr_alloc; list_add_tail_rcu(&set->list, &table->sets); table->use++; return 0; -err_set_trans: - ops->destroy(set); -err_set_init: +err_set_expr_alloc: for (i = 0; i < set->num_exprs; i++) nft_expr_destroy(&ctx, set->exprs[i]); -err_set_alloc_name: + + ops->destroy(set); +err_set_init: kfree(set->name); err_set_name: kvfree(set); -- cgit v1.2.3 From 12f36e9bf678a81d030ca1b693dcda62b55af7c5 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 8 Jun 2021 13:48:18 +0200 Subject: netfilter: nft_fib_ipv6: skip ipv6 packets from any to link-local The ip6tables rpfilter match has an extra check to skip packets with "::" source address. Extend this to ipv6 fib expression. Else ipv6 duplicate address detection packets will fail rpf route check -- lookup returns -ENETUNREACH. While at it, extend the prerouting check to also cover the ingress hook. Closes: https://bugzilla.netfilter.org/show_bug.cgi?id=1543 Fixes: f6d0cbcf09c5 ("netfilter: nf_tables: add fib expression") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/ipv6/netfilter/nft_fib_ipv6.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index e204163c7036..92f3235fa287 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -135,6 +135,17 @@ void nft_fib6_eval_type(const struct nft_expr *expr, struct nft_regs *regs, } EXPORT_SYMBOL_GPL(nft_fib6_eval_type); +static bool nft_fib_v6_skip_icmpv6(const struct sk_buff *skb, u8 next, const struct ipv6hdr *iph) +{ + if (likely(next != IPPROTO_ICMPV6)) + return false; + + if (ipv6_addr_type(&iph->saddr) != IPV6_ADDR_ANY) + return false; + + return ipv6_addr_type(&iph->daddr) & IPV6_ADDR_LINKLOCAL; +} + void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { @@ -163,10 +174,13 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif, iph); - if (nft_hook(pkt) == NF_INET_PRE_ROUTING && - nft_fib_is_loopback(pkt->skb, nft_in(pkt))) { - nft_fib_store_result(dest, priv, nft_in(pkt)); - return; + if (nft_hook(pkt) == NF_INET_PRE_ROUTING || + nft_hook(pkt) == NF_INET_INGRESS) { + if (nft_fib_is_loopback(pkt->skb, nft_in(pkt)) || + nft_fib_v6_skip_icmpv6(pkt->skb, pkt->tprot, iph)) { + nft_fib_store_result(dest, priv, nft_in(pkt)); + return; + } } *dest = 0; -- cgit v1.2.3 From 80ec82e3d2c1fab42eeb730aaa7985494a963d3f Mon Sep 17 00:00:00 2001 From: Austin Kim Date: Wed, 9 Jun 2021 03:34:25 +0100 Subject: net: ethtool: clear heap allocations for ethtool function Several ethtool functions leave heap uncleared (potentially) by drivers. This will leave the unused portion of heap unchanged and might copy the full contents back to userspace. Signed-off-by: Austin Kim Signed-off-by: David S. Miller --- net/ethtool/ioctl.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 3fa7a394eabf..baa5d10043cb 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1421,7 +1421,7 @@ static int ethtool_get_any_eeprom(struct net_device *dev, void __user *useraddr, if (eeprom.offset + eeprom.len > total_len) return -EINVAL; - data = kmalloc(PAGE_SIZE, GFP_USER); + data = kzalloc(PAGE_SIZE, GFP_USER); if (!data) return -ENOMEM; @@ -1486,7 +1486,7 @@ static int ethtool_set_eeprom(struct net_device *dev, void __user *useraddr) if (eeprom.offset + eeprom.len > ops->get_eeprom_len(dev)) return -EINVAL; - data = kmalloc(PAGE_SIZE, GFP_USER); + data = kzalloc(PAGE_SIZE, GFP_USER); if (!data) return -ENOMEM; @@ -1765,7 +1765,7 @@ static int ethtool_self_test(struct net_device *dev, char __user *useraddr) return -EFAULT; test.len = test_len; - data = kmalloc_array(test_len, sizeof(u64), GFP_USER); + data = kcalloc(test_len, sizeof(u64), GFP_USER); if (!data) return -ENOMEM; @@ -2293,7 +2293,7 @@ static int ethtool_get_tunable(struct net_device *dev, void __user *useraddr) ret = ethtool_tunable_valid(&tuna); if (ret) return ret; - data = kmalloc(tuna.len, GFP_USER); + data = kzalloc(tuna.len, GFP_USER); if (!data) return -ENOMEM; ret = ops->get_tunable(dev, &tuna, data); @@ -2485,7 +2485,7 @@ static int get_phy_tunable(struct net_device *dev, void __user *useraddr) ret = ethtool_phy_tunable_valid(&tuna); if (ret) return ret; - data = kmalloc(tuna.len, GFP_USER); + data = kzalloc(tuna.len, GFP_USER); if (!data) return -ENOMEM; if (phy_drv_tunable) { -- cgit v1.2.3 From dcd01eeac14486b56a790f5cce9b823440ba5b34 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 9 Jun 2021 00:59:45 -0700 Subject: inet: annotate data race in inet_send_prepare() and inet_dgram_connect() Both functions are known to be racy when reading inet_num as we do not want to grab locks for the common case the socket has been bound already. The race is resolved in inet_autobind() by reading again inet_num under the socket lock. syzbot reported: BUG: KCSAN: data-race in inet_send_prepare / udp_lib_get_port write to 0xffff88812cba150e of 2 bytes by task 24135 on cpu 0: udp_lib_get_port+0x4b2/0xe20 net/ipv4/udp.c:308 udp_v6_get_port+0x5e/0x70 net/ipv6/udp.c:89 inet_autobind net/ipv4/af_inet.c:183 [inline] inet_send_prepare+0xd0/0x210 net/ipv4/af_inet.c:807 inet6_sendmsg+0x29/0x80 net/ipv6/af_inet6.c:639 sock_sendmsg_nosec net/socket.c:654 [inline] sock_sendmsg net/socket.c:674 [inline] ____sys_sendmsg+0x360/0x4d0 net/socket.c:2350 ___sys_sendmsg net/socket.c:2404 [inline] __sys_sendmmsg+0x315/0x4b0 net/socket.c:2490 __do_sys_sendmmsg net/socket.c:2519 [inline] __se_sys_sendmmsg net/socket.c:2516 [inline] __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2516 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff88812cba150e of 2 bytes by task 24132 on cpu 1: inet_send_prepare+0x21/0x210 net/ipv4/af_inet.c:806 inet6_sendmsg+0x29/0x80 net/ipv6/af_inet6.c:639 sock_sendmsg_nosec net/socket.c:654 [inline] sock_sendmsg net/socket.c:674 [inline] ____sys_sendmsg+0x360/0x4d0 net/socket.c:2350 ___sys_sendmsg net/socket.c:2404 [inline] __sys_sendmmsg+0x315/0x4b0 net/socket.c:2490 __do_sys_sendmmsg net/socket.c:2519 [inline] __se_sys_sendmmsg net/socket.c:2516 [inline] __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2516 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x0000 -> 0x9db4 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 24132 Comm: syz-executor.2 Not tainted 5.13.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- net/ipv4/af_inet.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index f17870ee558b..2f94d221c00e 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -575,7 +575,7 @@ int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, return err; } - if (!inet_sk(sk)->inet_num && inet_autobind(sk)) + if (data_race(!inet_sk(sk)->inet_num) && inet_autobind(sk)) return -EAGAIN; return sk->sk_prot->connect(sk, uaddr, addr_len); } @@ -803,7 +803,7 @@ int inet_send_prepare(struct sock *sk) sock_rps_record_flow(sk); /* We may need to bind the socket. */ - if (!inet_sk(sk)->inet_num && !sk->sk_prot->no_autobind && + if (data_race(!inet_sk(sk)->inet_num) && !sk->sk_prot->no_autobind && inet_autobind(sk)) return -EAGAIN; -- cgit v1.2.3 From a8b897c7bcd47f4147d066e22cc01d1026d7640e Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 9 Jun 2021 11:49:01 +0200 Subject: udp: fix race between close() and udp_abort() Kaustubh reported and diagnosed a panic in udp_lib_lookup(). The root cause is udp_abort() racing with close(). Both racing functions acquire the socket lock, but udp{v6}_destroy_sock() release it before performing destructive actions. We can't easily extend the socket lock scope to avoid the race, instead use the SOCK_DEAD flag to prevent udp_abort from doing any action when the critical race happens. Diagnosed-and-tested-by: Kaustubh Pandey Fixes: 5d77dca82839 ("net: diag: support SOCK_DESTROY for UDP sockets") Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- net/ipv4/udp.c | 10 ++++++++++ net/ipv6/udp.c | 3 +++ 2 files changed, 13 insertions(+) (limited to 'net') diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 15f5504adf5b..1307ad0d3b9e 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2607,6 +2607,9 @@ void udp_destroy_sock(struct sock *sk) { struct udp_sock *up = udp_sk(sk); bool slow = lock_sock_fast(sk); + + /* protects from races with udp_abort() */ + sock_set_flag(sk, SOCK_DEAD); udp_flush_pending_frames(sk); unlock_sock_fast(sk, slow); if (static_branch_unlikely(&udp_encap_needed_key)) { @@ -2857,10 +2860,17 @@ int udp_abort(struct sock *sk, int err) { lock_sock(sk); + /* udp{v6}_destroy_sock() sets it under the sk lock, avoid racing + * with close() + */ + if (sock_flag(sk, SOCK_DEAD)) + goto out; + sk->sk_err = err; sk->sk_error_report(sk); __udp_disconnect(sk, 0); +out: release_sock(sk); return 0; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 199b080d418a..3fcd86f4dfdc 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1598,6 +1598,9 @@ void udpv6_destroy_sock(struct sock *sk) { struct udp_sock *up = udp_sk(sk); lock_sock(sk); + + /* protects from races with udp_abort() */ + sock_set_flag(sk, SOCK_DEAD); udp_v6_flush_pending_frames(sk); release_sock(sk); -- cgit v1.2.3 From d2e381c4963663bca6f30c3b996fa4dbafe8fcb5 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 9 Jun 2021 14:17:53 +0300 Subject: rtnetlink: Fix regression in bridge VLAN configuration Cited commit started returning errors when notification info is not filled by the bridge driver, resulting in the following regression: # ip link add name br1 type bridge vlan_filtering 1 # bridge vlan add dev br1 vid 555 self pvid untagged RTNETLINK answers: Invalid argument As long as the bridge driver does not fill notification info for the bridge device itself, an empty notification should not be considered as an error. This is explained in commit 59ccaaaa49b5 ("bridge: dont send notification when skb->len == 0 in rtnl_bridge_notify"). Fix by removing the error and add a comment to avoid future bugs. Fixes: a8db57c1d285 ("rtnetlink: Fix missing error code in rtnl_bridge_notify()") Signed-off-by: Ido Schimmel Reviewed-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 3e84279c4123..ec931b080156 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -4842,10 +4842,12 @@ static int rtnl_bridge_notify(struct net_device *dev) if (err < 0) goto errout; - if (!skb->len) { - err = -EINVAL; + /* Notification info is only filled for bridge ports, not the bridge + * device itself. Therefore, a zero notification length is valid and + * should not result in an error. + */ + if (!skb->len) goto errout; - } rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); return 0; -- cgit v1.2.3 From 13c62f5371e3eb4fc3400cfa26e64ca75f888008 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Wed, 9 Jun 2021 11:23:56 -0300 Subject: net/sched: act_ct: handle DNAT tuple collision This this the counterpart of 8aa7b526dc0b ("openvswitch: handle DNAT tuple collision") for act_ct. From that commit changelog: """ With multiple DNAT rules it's possible that after destination translation the resulting tuples collide. ... Netfilter handles this case by allocating a null binding for SNAT at egress by default. Perform the same operation in openvswitch for DNAT if no explicit SNAT is requested by the user and allocate a null binding for SNAT for packets in the "original" direction. """ Fixes: 95219afbb980 ("act_ct: support asymmetric conntrack") Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: David S. Miller --- net/sched/act_ct.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) (limited to 'net') diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 18edd9ad1410..a656baa321fe 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -904,14 +904,19 @@ static int tcf_ct_act_nat(struct sk_buff *skb, } err = ct_nat_execute(skb, ct, ctinfo, range, maniptype); - if (err == NF_ACCEPT && - ct->status & IPS_SRC_NAT && ct->status & IPS_DST_NAT) { - if (maniptype == NF_NAT_MANIP_SRC) - maniptype = NF_NAT_MANIP_DST; - else - maniptype = NF_NAT_MANIP_SRC; - - err = ct_nat_execute(skb, ct, ctinfo, range, maniptype); + if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) { + if (ct->status & IPS_SRC_NAT) { + if (maniptype == NF_NAT_MANIP_SRC) + maniptype = NF_NAT_MANIP_DST; + else + maniptype = NF_NAT_MANIP_SRC; + + err = ct_nat_execute(skb, ct, ctinfo, range, + maniptype); + } else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { + err = ct_nat_execute(skb, ct, ctinfo, NULL, + NF_NAT_MANIP_SRC); + } } return err; #else -- cgit v1.2.3 From 3bdd5ee0ec8c14131d560da492e6df452c6fdd75 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Wed, 9 Jun 2021 18:41:57 -0400 Subject: skbuff: fix incorrect msg_zerocopy copy notifications msg_zerocopy signals if a send operation required copying with a flag in serr->ee.ee_code. This field can be incorrect as of the below commit, as a result of both structs uarg and serr pointing into the same skb->cb[]. uarg->zerocopy must be read before skb->cb[] is reinitialized to hold serr. Similar to other fields len, hi and lo, use a local variable to temporarily hold the value. This was not a problem before, when the value was passed as a function argument. Fixes: 75518851a2a0 ("skbuff: Push status and refcounts into sock_zerocopy_callback") Reported-by: Talal Ahmad Signed-off-by: Willem de Bruijn Acked-by: Soheil Hassas Yeganeh Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/skbuff.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 3ad22870298c..bbc3b4b62032 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1253,6 +1253,7 @@ static void __msg_zerocopy_callback(struct ubuf_info *uarg) struct sock *sk = skb->sk; struct sk_buff_head *q; unsigned long flags; + bool is_zerocopy; u32 lo, hi; u16 len; @@ -1267,6 +1268,7 @@ static void __msg_zerocopy_callback(struct ubuf_info *uarg) len = uarg->len; lo = uarg->id; hi = uarg->id + len - 1; + is_zerocopy = uarg->zerocopy; serr = SKB_EXT_ERR(skb); memset(serr, 0, sizeof(*serr)); @@ -1274,7 +1276,7 @@ static void __msg_zerocopy_callback(struct ubuf_info *uarg) serr->ee.ee_origin = SO_EE_ORIGIN_ZEROCOPY; serr->ee.ee_data = hi; serr->ee.ee_info = lo; - if (!uarg->zerocopy) + if (!is_zerocopy) serr->ee.ee_code |= SO_EE_CODE_ZEROCOPY_COPIED; q = &sk->sk_error_queue; -- cgit v1.2.3 From 9d44fa3e50cc91691896934d106c86e4027e61ca Mon Sep 17 00:00:00 2001 From: Zheng Yongjun Date: Thu, 10 Jun 2021 09:41:36 +0800 Subject: ping: Check return value of function 'ping_queue_rcv_skb' Function 'ping_queue_rcv_skb' not always return success, which will also return fail. If not check the wrong return value of it, lead to function `ping_rcv` return success. Signed-off-by: Zheng Yongjun Signed-off-by: David S. Miller --- net/ipv4/ping.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 1c9f71a37258..95a718397fd1 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -954,6 +954,7 @@ bool ping_rcv(struct sk_buff *skb) struct sock *sk; struct net *net = dev_net(skb->dev); struct icmphdr *icmph = icmp_hdr(skb); + bool rc = false; /* We assume the packet has already been checked by icmp_rcv */ @@ -968,14 +969,15 @@ bool ping_rcv(struct sk_buff *skb) struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); pr_debug("rcv on socket %p\n", sk); - if (skb2) - ping_queue_rcv_skb(sk, skb2); + if (skb2 && !ping_queue_rcv_skb(sk, skb2)) + rc = true; sock_put(sk); - return true; } - pr_debug("no socket, dropping\n"); - return false; + if (!rc) + pr_debug("no socket, dropping\n"); + + return rc; } EXPORT_SYMBOL_GPL(ping_rcv); -- cgit v1.2.3 From 58e2071742e38f29f051b709a5cca014ba51166f Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Thu, 10 Jun 2021 15:04:10 +0300 Subject: net: bridge: fix vlan tunnel dst null pointer dereference This patch fixes a tunnel_dst null pointer dereference due to lockless access in the tunnel egress path. When deleting a vlan tunnel the tunnel_dst pointer is set to NULL without waiting a grace period (i.e. while it's still usable) and packets egressing are dereferencing it without checking. Use READ/WRITE_ONCE to annotate the lockless use of tunnel_id, use RCU for accessing tunnel_dst and make sure it is read only once and checked in the egress path. The dst is already properly RCU protected so we don't need to do anything fancy than to make sure tunnel_id and tunnel_dst are read only once and checked in the egress path. Cc: stable@vger.kernel.org Fixes: 11538d039ac6 ("bridge: vlan dst_metadata hooks in ingress and egress paths") Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/bridge/br_private.h | 4 ++-- net/bridge/br_vlan_tunnel.c | 38 ++++++++++++++++++++++++-------------- 2 files changed, 26 insertions(+), 16 deletions(-) (limited to 'net') diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 7ce8a77cc6b6..e013d33f1c7c 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -90,8 +90,8 @@ struct bridge_mcast_stats { #endif struct br_tunnel_info { - __be64 tunnel_id; - struct metadata_dst *tunnel_dst; + __be64 tunnel_id; + struct metadata_dst __rcu *tunnel_dst; }; /* private vlan flags */ diff --git a/net/bridge/br_vlan_tunnel.c b/net/bridge/br_vlan_tunnel.c index 0d3a8c01552e..03de461a0d44 100644 --- a/net/bridge/br_vlan_tunnel.c +++ b/net/bridge/br_vlan_tunnel.c @@ -41,26 +41,33 @@ static struct net_bridge_vlan *br_vlan_tunnel_lookup(struct rhashtable *tbl, br_vlan_tunnel_rht_params); } +static void vlan_tunnel_info_release(struct net_bridge_vlan *vlan) +{ + struct metadata_dst *tdst = rtnl_dereference(vlan->tinfo.tunnel_dst); + + WRITE_ONCE(vlan->tinfo.tunnel_id, 0); + RCU_INIT_POINTER(vlan->tinfo.tunnel_dst, NULL); + dst_release(&tdst->dst); +} + void vlan_tunnel_info_del(struct net_bridge_vlan_group *vg, struct net_bridge_vlan *vlan) { - if (!vlan->tinfo.tunnel_dst) + if (!rcu_access_pointer(vlan->tinfo.tunnel_dst)) return; rhashtable_remove_fast(&vg->tunnel_hash, &vlan->tnode, br_vlan_tunnel_rht_params); - vlan->tinfo.tunnel_id = 0; - dst_release(&vlan->tinfo.tunnel_dst->dst); - vlan->tinfo.tunnel_dst = NULL; + vlan_tunnel_info_release(vlan); } static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg, struct net_bridge_vlan *vlan, u32 tun_id) { - struct metadata_dst *metadata = NULL; + struct metadata_dst *metadata = rtnl_dereference(vlan->tinfo.tunnel_dst); __be64 key = key32_to_tunnel_id(cpu_to_be32(tun_id)); int err; - if (vlan->tinfo.tunnel_dst) + if (metadata) return -EEXIST; metadata = __ip_tun_set_dst(0, 0, 0, 0, 0, TUNNEL_KEY, @@ -69,8 +76,8 @@ static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg, return -EINVAL; metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_BRIDGE; - vlan->tinfo.tunnel_dst = metadata; - vlan->tinfo.tunnel_id = key; + rcu_assign_pointer(vlan->tinfo.tunnel_dst, metadata); + WRITE_ONCE(vlan->tinfo.tunnel_id, key); err = rhashtable_lookup_insert_fast(&vg->tunnel_hash, &vlan->tnode, br_vlan_tunnel_rht_params); @@ -79,9 +86,7 @@ static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg, return 0; out: - dst_release(&vlan->tinfo.tunnel_dst->dst); - vlan->tinfo.tunnel_dst = NULL; - vlan->tinfo.tunnel_id = 0; + vlan_tunnel_info_release(vlan); return err; } @@ -182,12 +187,15 @@ int br_handle_ingress_vlan_tunnel(struct sk_buff *skb, int br_handle_egress_vlan_tunnel(struct sk_buff *skb, struct net_bridge_vlan *vlan) { + struct metadata_dst *tunnel_dst; + __be64 tunnel_id; int err; - if (!vlan || !vlan->tinfo.tunnel_id) + if (!vlan) return 0; - if (unlikely(!skb_vlan_tag_present(skb))) + tunnel_id = READ_ONCE(vlan->tinfo.tunnel_id); + if (!tunnel_id || unlikely(!skb_vlan_tag_present(skb))) return 0; skb_dst_drop(skb); @@ -195,7 +203,9 @@ int br_handle_egress_vlan_tunnel(struct sk_buff *skb, if (err) return err; - skb_dst_set(skb, dst_clone(&vlan->tinfo.tunnel_dst->dst)); + tunnel_dst = rcu_dereference(vlan->tinfo.tunnel_dst); + if (tunnel_dst) + skb_dst_set(skb, dst_clone(&tunnel_dst->dst)); return 0; } -- cgit v1.2.3 From cfc579f9d89af4ada58c69b03bcaa4887840f3b3 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Thu, 10 Jun 2021 15:04:11 +0300 Subject: net: bridge: fix vlan tunnel dst refcnt when egressing The egress tunnel code uses dst_clone() and directly sets the result which is wrong because the entry might have 0 refcnt or be already deleted, causing number of problems. It also triggers the WARN_ON() in dst_hold()[1] when a refcnt couldn't be taken. Fix it by using dst_hold_safe() and checking if a reference was actually taken before setting the dst. [1] dmesg WARN_ON log and following refcnt errors WARNING: CPU: 5 PID: 38 at include/net/dst.h:230 br_handle_egress_vlan_tunnel+0x10b/0x134 [bridge] Modules linked in: 8021q garp mrp bridge stp llc bonding ipv6 virtio_net CPU: 5 PID: 38 Comm: ksoftirqd/5 Kdump: loaded Tainted: G W 5.13.0-rc3+ #360 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.14.0-1.fc33 04/01/2014 RIP: 0010:br_handle_egress_vlan_tunnel+0x10b/0x134 [bridge] Code: e8 85 bc 01 e1 45 84 f6 74 90 45 31 f6 85 db 48 c7 c7 a0 02 19 a0 41 0f 94 c6 31 c9 31 d2 44 89 f6 e8 64 bc 01 e1 85 db 75 02 <0f> 0b 31 c9 31 d2 44 89 f6 48 c7 c7 70 02 19 a0 e8 4b bc 01 e1 49 RSP: 0018:ffff8881003d39e8 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffffffffa01902a0 RBP: ffff8881040c6700 R08: 0000000000000000 R09: 0000000000000001 R10: 2ce93d0054fe0d00 R11: 54fe0d00000e0000 R12: ffff888109515000 R13: 0000000000000000 R14: 0000000000000001 R15: 0000000000000401 FS: 0000000000000000(0000) GS:ffff88822bf40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f42ba70f030 CR3: 0000000109926000 CR4: 00000000000006e0 Call Trace: br_handle_vlan+0xbc/0xca [bridge] __br_forward+0x23/0x164 [bridge] deliver_clone+0x41/0x48 [bridge] br_handle_frame_finish+0x36f/0x3aa [bridge] ? skb_dst+0x2e/0x38 [bridge] ? br_handle_ingress_vlan_tunnel+0x3e/0x1c8 [bridge] ? br_handle_frame_finish+0x3aa/0x3aa [bridge] br_handle_frame+0x2c3/0x377 [bridge] ? __skb_pull+0x33/0x51 ? vlan_do_receive+0x4f/0x36a ? br_handle_frame_finish+0x3aa/0x3aa [bridge] __netif_receive_skb_core+0x539/0x7c6 ? __list_del_entry_valid+0x16e/0x1c2 __netif_receive_skb_list_core+0x6d/0xd6 netif_receive_skb_list_internal+0x1d9/0x1fa gro_normal_list+0x22/0x3e dev_gro_receive+0x55b/0x600 ? detach_buf_split+0x58/0x140 napi_gro_receive+0x94/0x12e virtnet_poll+0x15d/0x315 [virtio_net] __napi_poll+0x2c/0x1c9 net_rx_action+0xe6/0x1fb __do_softirq+0x115/0x2d8 run_ksoftirqd+0x18/0x20 smpboot_thread_fn+0x183/0x19c ? smpboot_unregister_percpu_thread+0x66/0x66 kthread+0x10a/0x10f ? kthread_mod_delayed_work+0xb6/0xb6 ret_from_fork+0x22/0x30 ---[ end trace 49f61b07f775fd2b ]--- dst_release: dst:00000000c02d677a refcnt:-1 dst_release underflow Cc: stable@vger.kernel.org Fixes: 11538d039ac6 ("bridge: vlan dst_metadata hooks in ingress and egress paths") Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- net/bridge/br_vlan_tunnel.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/bridge/br_vlan_tunnel.c b/net/bridge/br_vlan_tunnel.c index 03de461a0d44..01017448ebde 100644 --- a/net/bridge/br_vlan_tunnel.c +++ b/net/bridge/br_vlan_tunnel.c @@ -204,8 +204,8 @@ int br_handle_egress_vlan_tunnel(struct sk_buff *skb, return err; tunnel_dst = rcu_dereference(vlan->tinfo.tunnel_dst); - if (tunnel_dst) - skb_dst_set(skb, dst_clone(&tunnel_dst->dst)); + if (tunnel_dst && dst_hold_safe(&tunnel_dst->dst)) + skb_dst_set(skb, &tunnel_dst->dst); return 0; } -- cgit v1.2.3 From d1b5bee4c8be01585033be9b3a8878789285285f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 10 Jun 2021 09:00:12 -0700 Subject: net/packet: annotate data race in packet_sendmsg() There is a known race in packet_sendmsg(), addressed in commit 32d3182cd2cd ("net/packet: fix race in tpacket_snd()") Now we have data_race(), we can use it to avoid a future KCSAN warning, as syzbot loves stressing af_packet sockets :) Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/packet/af_packet.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ae906eb4b269..74e6e45a8e84 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3034,10 +3034,13 @@ static int packet_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); - if (po->tx_ring.pg_vec) + /* Reading tx_ring.pg_vec without holding pg_vec_lock is racy. + * tpacket_snd() will redo the check safely. + */ + if (data_race(po->tx_ring.pg_vec)) return tpacket_snd(po, msg); - else - return packet_snd(sock, msg, len); + + return packet_snd(sock, msg, len); } /* -- cgit v1.2.3 From 5fc177ab759418c9537433e63301096e733fb915 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Thu, 10 Jun 2021 19:40:29 +0300 Subject: netfilter: synproxy: Fix out of bounds when parsing TCP options The TCP option parser in synproxy (synproxy_parse_options) could read one byte out of bounds. When the length is 1, the execution flow gets into the loop, reads one byte of the opcode, and if the opcode is neither TCPOPT_EOL nor TCPOPT_NOP, it reads one more byte, which exceeds the length of 1. This fix is inspired by commit 9609dad263f8 ("ipv4: tcp_input: fix stack out of bounds when parsing TCP options."). v2 changes: Added an early return when length < 0 to avoid calling skb_header_pointer with negative length. Cc: Young Xiao <92siuyang@gmail.com> Fixes: 48b1de4c110a ("netfilter: add SYNPROXY core/target") Signed-off-by: Maxim Mikityanskiy Reviewed-by: Florian Westphal Signed-off-by: David S. Miller --- net/netfilter/nf_synproxy_core.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'net') diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index b100c04a0e43..3d6d49420db8 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -31,6 +31,9 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, int length = (th->doff * 4) - sizeof(*th); u8 buf[40], *ptr; + if (unlikely(length < 0)) + return false; + ptr = skb_header_pointer(skb, doff + sizeof(*th), length, buf); if (ptr == NULL) return false; @@ -47,6 +50,8 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, length--; continue; default: + if (length < 2) + return true; opsize = *ptr++; if (opsize < 2) return true; -- cgit v1.2.3 From 07718be265680dcf496347d475ce1a5442f55ad7 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Thu, 10 Jun 2021 19:40:30 +0300 Subject: mptcp: Fix out of bounds when parsing TCP options The TCP option parser in mptcp (mptcp_get_options) could read one byte out of bounds. When the length is 1, the execution flow gets into the loop, reads one byte of the opcode, and if the opcode is neither TCPOPT_EOL nor TCPOPT_NOP, it reads one more byte, which exceeds the length of 1. This fix is inspired by commit 9609dad263f8 ("ipv4: tcp_input: fix stack out of bounds when parsing TCP options."). Cc: Young Xiao <92siuyang@gmail.com> Fixes: cec37a6e41aa ("mptcp: Handle MP_CAPABLE options for outgoing connections") Signed-off-by: Maxim Mikityanskiy Reviewed-by: Mat Martineau Signed-off-by: David S. Miller --- net/mptcp/options.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net') diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 6b825fb3fa83..9b263f27ce9b 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -356,6 +356,8 @@ void mptcp_get_options(const struct sk_buff *skb, length--; continue; default: + if (length < 2) + return; opsize = *ptr++; if (opsize < 2) /* "silly options" */ return; -- cgit v1.2.3 From ba91c49dedbde758ba0b72f57ac90b06ddf8e548 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Thu, 10 Jun 2021 19:40:31 +0300 Subject: sch_cake: Fix out of bounds when parsing TCP options and header The TCP option parser in cake qdisc (cake_get_tcpopt and cake_tcph_may_drop) could read one byte out of bounds. When the length is 1, the execution flow gets into the loop, reads one byte of the opcode, and if the opcode is neither TCPOPT_EOL nor TCPOPT_NOP, it reads one more byte, which exceeds the length of 1. This fix is inspired by commit 9609dad263f8 ("ipv4: tcp_input: fix stack out of bounds when parsing TCP options."). v2 changes: Added doff validation in cake_get_tcphdr to avoid parsing garbage as TCP header. Although it wasn't strictly an out-of-bounds access (memory was allocated), garbage values could be read where CAKE expected the TCP header if doff was smaller than 5. Cc: Young Xiao <92siuyang@gmail.com> Fixes: 8b7138814f29 ("sch_cake: Add optional ACK filter") Signed-off-by: Maxim Mikityanskiy Acked-by: Toke Høiland-Jørgensen Signed-off-by: David S. Miller --- net/sched/sch_cake.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 7d37638ee1c7..5c15968b5155 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -943,7 +943,7 @@ static struct tcphdr *cake_get_tcphdr(const struct sk_buff *skb, } tcph = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); - if (!tcph) + if (!tcph || tcph->doff < 5) return NULL; return skb_header_pointer(skb, offset, @@ -967,6 +967,8 @@ static const void *cake_get_tcpopt(const struct tcphdr *tcph, length--; continue; } + if (length < 2) + break; opsize = *ptr++; if (opsize < 2 || opsize > length) break; @@ -1104,6 +1106,8 @@ static bool cake_tcph_may_drop(const struct tcphdr *tcph, length--; continue; } + if (length < 2) + break; opsize = *ptr++; if (opsize < 2 || opsize > length) break; -- cgit v1.2.3 From 72f961320d5d15bfcb26dbe3edaa3f7d25fd2c8a Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 10 Jun 2021 15:59:40 -0700 Subject: mptcp: try harder to borrow memory from subflow under pressure If the host is under sever memory pressure, and RX forward memory allocation for the msk fails, we try to borrow the required memory from the ingress subflow. The current attempt is a bit flaky: if skb->truesize is less than SK_MEM_QUANTUM, the ssk will not release any memory, and the next schedule will fail again. Instead, directly move the required amount of pages from the ssk to the msk, if available Fixes: 9c3f94e1681b ("mptcp: add missing memory scheduling in the rx path") Signed-off-by: Paolo Abeni Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- net/mptcp/protocol.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'net') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 5edc686faff1..534cf500521d 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -280,11 +280,13 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, /* try to fetch required memory from subflow */ if (!sk_rmem_schedule(sk, skb, skb->truesize)) { - if (ssk->sk_forward_alloc < skb->truesize) - goto drop; - __sk_mem_reclaim(ssk, skb->truesize); - if (!sk_rmem_schedule(sk, skb, skb->truesize)) + int amount = sk_mem_pages(skb->truesize) << SK_MEM_QUANTUM_SHIFT; + + if (ssk->sk_forward_alloc < amount) goto drop; + + ssk->sk_forward_alloc -= amount; + sk->sk_forward_alloc += amount; } /* the skb map_seq accounts for the skb offset: -- cgit v1.2.3 From 99d1055ce2469dca3dd14be0991ff8133e25e3d0 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 10 Jun 2021 15:59:41 -0700 Subject: mptcp: wake-up readers only for in sequence data Currently we rely on the subflow->data_avail field, which is subject to races: ssk1 skb len = 500 DSS(seq=1, len=1000, off=0) # data_avail == MPTCP_SUBFLOW_DATA_AVAIL ssk2 skb len = 500 DSS(seq = 501, len=1000) # data_avail == MPTCP_SUBFLOW_DATA_AVAIL ssk1 skb len = 500 DSS(seq = 1, len=1000, off =500) # still data_avail == MPTCP_SUBFLOW_DATA_AVAIL, # as the skb is covered by a pre-existing map, # which was in-sequence at reception time. Instead we can explicitly check if some has been received in-sequence, propagating the info from __mptcp_move_skbs_from_subflow(). Additionally add the 'ONCE' annotation to the 'data_avail' memory access, as msk will read it outside the subflow socket lock. Fixes: 648ef4b88673 ("mptcp: Implement MPTCP receive path") Signed-off-by: Paolo Abeni Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- net/mptcp/protocol.c | 33 ++++++++++++--------------------- net/mptcp/protocol.h | 1 - net/mptcp/subflow.c | 23 +++++++++-------------- 3 files changed, 21 insertions(+), 36 deletions(-) (limited to 'net') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 534cf500521d..f6e62a6dc9fb 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -670,15 +670,13 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) /* In most cases we will be able to lock the mptcp socket. If its already * owned, we need to defer to the work queue to avoid ABBA deadlock. */ -static void move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) +static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) { struct sock *sk = (struct sock *)msk; unsigned int moved = 0; if (inet_sk_state_load(sk) == TCP_CLOSE) - return; - - mptcp_data_lock(sk); + return false; __mptcp_move_skbs_from_subflow(msk, ssk, &moved); __mptcp_ofo_queue(msk); @@ -690,7 +688,7 @@ static void move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) */ if (mptcp_pending_data_fin(sk, NULL)) mptcp_schedule_work(sk); - mptcp_data_unlock(sk); + return moved > 0; } void mptcp_data_ready(struct sock *sk, struct sock *ssk) @@ -698,7 +696,6 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct mptcp_sock *msk = mptcp_sk(sk); int sk_rbuf, ssk_rbuf; - bool wake; /* The peer can send data while we are shutting down this * subflow at msk destruction time, but we must avoid enqueuing @@ -707,28 +704,22 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) if (unlikely(subflow->disposable)) return; - /* move_skbs_to_msk below can legitly clear the data_avail flag, - * but we will need later to properly woke the reader, cache its - * value - */ - wake = subflow->data_avail == MPTCP_SUBFLOW_DATA_AVAIL; - if (wake) - set_bit(MPTCP_DATA_READY, &msk->flags); - ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf); sk_rbuf = READ_ONCE(sk->sk_rcvbuf); if (unlikely(ssk_rbuf > sk_rbuf)) sk_rbuf = ssk_rbuf; - /* over limit? can't append more skbs to msk */ + /* over limit? can't append more skbs to msk, Also, no need to wake-up*/ if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) - goto wake; - - move_skbs_to_msk(msk, ssk); + return; -wake: - if (wake) + /* Wake-up the reader only for in-sequence data */ + mptcp_data_lock(sk); + if (move_skbs_to_msk(msk, ssk)) { + set_bit(MPTCP_DATA_READY, &msk->flags); sk->sk_data_ready(sk); + } + mptcp_data_unlock(sk); } static bool mptcp_do_flush_join_list(struct mptcp_sock *msk) @@ -860,7 +851,7 @@ static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk) sock_owned_by_me(sk); mptcp_for_each_subflow(msk, subflow) { - if (subflow->data_avail) + if (READ_ONCE(subflow->data_avail)) return mptcp_subflow_tcp_sock(subflow); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 0c6f99c67345..385796f0ef19 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -362,7 +362,6 @@ mptcp_subflow_rsk(const struct request_sock *rsk) enum mptcp_data_avail { MPTCP_SUBFLOW_NODATA, MPTCP_SUBFLOW_DATA_AVAIL, - MPTCP_SUBFLOW_OOO_DATA }; struct mptcp_delegated_action { diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index ef3d037f984a..ebb898acd65a 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1000,7 +1000,7 @@ static bool subflow_check_data_avail(struct sock *ssk) struct sk_buff *skb; if (!skb_peek(&ssk->sk_receive_queue)) - subflow->data_avail = 0; + WRITE_ONCE(subflow->data_avail, 0); if (subflow->data_avail) return true; @@ -1039,18 +1039,13 @@ static bool subflow_check_data_avail(struct sock *ssk) ack_seq = mptcp_subflow_get_mapped_dsn(subflow); pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack, ack_seq); - if (ack_seq == old_ack) { - subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL; - break; - } else if (after64(ack_seq, old_ack)) { - subflow->data_avail = MPTCP_SUBFLOW_OOO_DATA; - break; + if (unlikely(before64(ack_seq, old_ack))) { + mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq); + continue; } - /* only accept in-sequence mapping. Old values are spurious - * retransmission - */ - mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq); + WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); + break; } return true; @@ -1070,7 +1065,7 @@ fallback: subflow->reset_transient = 0; subflow->reset_reason = MPTCP_RST_EMPTCP; tcp_send_active_reset(ssk, GFP_ATOMIC); - subflow->data_avail = 0; + WRITE_ONCE(subflow->data_avail, 0); return false; } @@ -1080,7 +1075,7 @@ fallback: subflow->map_seq = READ_ONCE(msk->ack_seq); subflow->map_data_len = skb->len; subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq - subflow->ssn_offset; - subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL; + WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); return true; } @@ -1092,7 +1087,7 @@ bool mptcp_subflow_data_available(struct sock *sk) if (subflow->map_valid && mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) { subflow->map_valid = 0; - subflow->data_avail = 0; + WRITE_ONCE(subflow->data_avail, 0); pr_debug("Done with mapping: seq=%u data_len=%u", subflow->map_subflow_seq, -- cgit v1.2.3 From 61e710227e97172355d5f150d5c78c64175d9fb2 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 10 Jun 2021 15:59:42 -0700 Subject: mptcp: do not warn on bad input from the network warn_bad_map() produces a kernel WARN on bad input coming from the network. Use pr_debug() to avoid spamming the system log. Additionally, when the right bound check fails, warn_bad_map() reports the wrong ssn value, let's fix it. Fixes: 648ef4b88673 ("mptcp: Implement MPTCP receive path") Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/107 Signed-off-by: Paolo Abeni Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- net/mptcp/subflow.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'net') diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index ebb898acd65a..e05e05ec9687 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -784,10 +784,10 @@ static u64 expand_seq(u64 old_seq, u16 old_data_len, u64 seq) return seq | ((old_seq + old_data_len + 1) & GENMASK_ULL(63, 32)); } -static void warn_bad_map(struct mptcp_subflow_context *subflow, u32 ssn) +static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn) { - WARN_ONCE(1, "Bad mapping: ssn=%d map_seq=%d map_data_len=%d", - ssn, subflow->map_subflow_seq, subflow->map_data_len); + pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d", + ssn, subflow->map_subflow_seq, subflow->map_data_len); } static bool skb_is_fully_mapped(struct sock *ssk, struct sk_buff *skb) @@ -812,13 +812,13 @@ static bool validate_mapping(struct sock *ssk, struct sk_buff *skb) /* Mapping covers data later in the subflow stream, * currently unsupported. */ - warn_bad_map(subflow, ssn); + dbg_bad_map(subflow, ssn); return false; } if (unlikely(!before(ssn, subflow->map_subflow_seq + subflow->map_data_len))) { /* Mapping does covers past subflow data, invalid */ - warn_bad_map(subflow, ssn + skb->len); + dbg_bad_map(subflow, ssn); return false; } return true; -- cgit v1.2.3 From 499ada5073361c631f2a3c4a8aed44d53b6f82ec Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 10 Jun 2021 15:59:44 -0700 Subject: mptcp: fix soft lookup in subflow_error_report() Maxim reported a soft lookup in subflow_error_report(): watchdog: BUG: soft lockup - CPU#0 stuck for 22s! [swapper/0:0] RIP: 0010:native_queued_spin_lock_slowpath RSP: 0018:ffffa859c0003bc0 EFLAGS: 00000202 RAX: 0000000000000101 RBX: 0000000000000001 RCX: 0000000000000000 RDX: ffff9195c2772d88 RSI: 0000000000000000 RDI: ffff9195c2772d88 RBP: ffff9195c2772d00 R08: 00000000000067b0 R09: c6e31da9eb1e44f4 R10: ffff9195ef379700 R11: ffff9195edb50710 R12: ffff9195c2772d88 R13: ffff9195f500e3d0 R14: ffff9195ef379700 R15: ffff9195ef379700 FS: 0000000000000000(0000) GS:ffff91961f400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000c000407000 CR3: 0000000002988000 CR4: 00000000000006f0 Call Trace: _raw_spin_lock_bh subflow_error_report mptcp_subflow_data_available __mptcp_move_skbs_from_subflow mptcp_data_ready tcp_data_queue tcp_rcv_established tcp_v4_do_rcv tcp_v4_rcv ip_protocol_deliver_rcu ip_local_deliver_finish __netif_receive_skb_one_core netif_receive_skb rtl8139_poll 8139too __napi_poll net_rx_action __do_softirq __irq_exit_rcu common_interrupt The calling function - mptcp_subflow_data_available() - can be invoked from different contexts: - plain ssk socket lock - ssk socket lock + mptcp_data_lock - ssk socket lock + mptcp_data_lock + msk socket lock. Since subflow_error_report() tries to acquire the mptcp_data_lock, the latter two call chains will cause soft lookup. This change addresses the issue moving the error reporting call to outer functions, where the held locks list is known and the we can acquire only the needed one. Reported-by: Maxim Galaganov Fixes: 15cc10453398 ("mptcp: deliver ssk errors to msk") Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/199 Signed-off-by: Paolo Abeni Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- net/mptcp/protocol.c | 9 +++++++ net/mptcp/subflow.c | 75 +++++++++++++++++++++++++++------------------------- 2 files changed, 48 insertions(+), 36 deletions(-) (limited to 'net') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index f6e62a6dc9fb..632350018fb6 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -680,6 +680,12 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) __mptcp_move_skbs_from_subflow(msk, ssk, &moved); __mptcp_ofo_queue(msk); + if (unlikely(ssk->sk_err)) { + if (!sock_owned_by_user(sk)) + __mptcp_error_report(sk); + else + set_bit(MPTCP_ERROR_REPORT, &msk->flags); + } /* If the moves have caught up with the DATA_FIN sequence number * it's time to ack the DATA_FIN and change socket state, but @@ -1948,6 +1954,9 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk) done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved); mptcp_data_unlock(sk); tcp_cleanup_rbuf(ssk, moved); + + if (unlikely(ssk->sk_err)) + __mptcp_error_report(sk); unlock_sock_fast(ssk, slowpath); } while (!done); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index e05e05ec9687..be1de4084196 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1060,7 +1060,6 @@ fallback: * subflow_error_report() will introduce the appropriate barriers */ ssk->sk_err = EBADMSG; - ssk->sk_error_report(ssk); tcp_set_state(ssk, TCP_CLOSE); subflow->reset_transient = 0; subflow->reset_reason = MPTCP_RST_EMPTCP; @@ -1115,41 +1114,6 @@ void mptcp_space(const struct sock *ssk, int *space, int *full_space) *full_space = tcp_full_space(sk); } -static void subflow_data_ready(struct sock *sk) -{ - struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - u16 state = 1 << inet_sk_state_load(sk); - struct sock *parent = subflow->conn; - struct mptcp_sock *msk; - - msk = mptcp_sk(parent); - if (state & TCPF_LISTEN) { - /* MPJ subflow are removed from accept queue before reaching here, - * avoid stray wakeups - */ - if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue)) - return; - - set_bit(MPTCP_DATA_READY, &msk->flags); - parent->sk_data_ready(parent); - return; - } - - WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable && - !subflow->mp_join && !(state & TCPF_CLOSE)); - - if (mptcp_subflow_data_available(sk)) - mptcp_data_ready(parent, sk); -} - -static void subflow_write_space(struct sock *ssk) -{ - struct sock *sk = mptcp_subflow_ctx(ssk)->conn; - - mptcp_propagate_sndbuf(sk, ssk); - mptcp_write_space(sk); -} - void __mptcp_error_report(struct sock *sk) { struct mptcp_subflow_context *subflow; @@ -1190,6 +1154,43 @@ static void subflow_error_report(struct sock *ssk) mptcp_data_unlock(sk); } +static void subflow_data_ready(struct sock *sk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + u16 state = 1 << inet_sk_state_load(sk); + struct sock *parent = subflow->conn; + struct mptcp_sock *msk; + + msk = mptcp_sk(parent); + if (state & TCPF_LISTEN) { + /* MPJ subflow are removed from accept queue before reaching here, + * avoid stray wakeups + */ + if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue)) + return; + + set_bit(MPTCP_DATA_READY, &msk->flags); + parent->sk_data_ready(parent); + return; + } + + WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable && + !subflow->mp_join && !(state & TCPF_CLOSE)); + + if (mptcp_subflow_data_available(sk)) + mptcp_data_ready(parent, sk); + else if (unlikely(sk->sk_err)) + subflow_error_report(sk); +} + +static void subflow_write_space(struct sock *ssk) +{ + struct sock *sk = mptcp_subflow_ctx(ssk)->conn; + + mptcp_propagate_sndbuf(sk, ssk); + mptcp_write_space(sk); +} + static struct inet_connection_sock_af_ops * subflow_default_af_ops(struct sock *sk) { @@ -1500,6 +1501,8 @@ static void subflow_state_change(struct sock *sk) */ if (mptcp_subflow_data_available(sk)) mptcp_data_ready(parent, sk); + else if (unlikely(sk->sk_err)) + subflow_error_report(sk); subflow_sched_work_if_closed(mptcp_sk(parent), sk); -- cgit v1.2.3 From ea6932d70e223e02fea3ae20a4feff05d7c1ea9a Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Fri, 11 Jun 2021 22:29:59 +0800 Subject: net: make get_net_ns return error if NET_NS is disabled There is a panic in socket ioctl cmd SIOCGSKNS when NET_NS is not enabled. The reason is that nsfs tries to access ns->ops but the proc_ns_operations is not implemented in this case. [7.670023] Unable to handle kernel NULL pointer dereference at virtual address 00000010 [7.670268] pgd = 32b54000 [7.670544] [00000010] *pgd=00000000 [7.671861] Internal error: Oops: 5 [#1] SMP ARM [7.672315] Modules linked in: [7.672918] CPU: 0 PID: 1 Comm: systemd Not tainted 5.13.0-rc3-00375-g6799d4f2da49 #16 [7.673309] Hardware name: Generic DT based system [7.673642] PC is at nsfs_evict+0x24/0x30 [7.674486] LR is at clear_inode+0x20/0x9c The same to tun SIOCGSKNS command. To fix this problem, we make get_net_ns() return -EINVAL when NET_NS is disabled. Meanwhile move it to right place net/core/net_namespace.c. Signed-off-by: Changbin Du Fixes: c62cce2caee5 ("net: add an ioctl to get a socket network namespace") Cc: Cong Wang Cc: Jakub Kicinski Cc: David Laight Cc: Christian Brauner Suggested-by: Jakub Kicinski Acked-by: Christian Brauner Signed-off-by: David S. Miller --- include/linux/socket.h | 2 -- include/net/net_namespace.h | 7 +++++++ net/core/net_namespace.c | 12 ++++++++++++ net/socket.c | 13 ------------- 4 files changed, 19 insertions(+), 15 deletions(-) (limited to 'net') diff --git a/include/linux/socket.h b/include/linux/socket.h index b8fc5c53ba6f..0d8e3dcb7f88 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -438,6 +438,4 @@ extern int __sys_socketpair(int family, int type, int protocol, int __user *usockvec); extern int __sys_shutdown_sock(struct socket *sock, int how); extern int __sys_shutdown(int fd, int how); - -extern struct ns_common *get_net_ns(struct ns_common *ns); #endif /* _LINUX_SOCKET_H */ diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index fa5887143f0d..6412d7833d97 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -184,6 +184,8 @@ struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns, void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid); void net_ns_barrier(void); + +struct ns_common *get_net_ns(struct ns_common *ns); #else /* CONFIG_NET_NS */ #include #include @@ -203,6 +205,11 @@ static inline void net_ns_get_ownership(const struct net *net, } static inline void net_ns_barrier(void) {} + +static inline struct ns_common *get_net_ns(struct ns_common *ns) +{ + return ERR_PTR(-EINVAL); +} #endif /* CONFIG_NET_NS */ diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 43b6ac4c4439..cc8dafb25d61 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -641,6 +641,18 @@ void __put_net(struct net *net) } EXPORT_SYMBOL_GPL(__put_net); +/** + * get_net_ns - increment the refcount of the network namespace + * @ns: common namespace (net) + * + * Returns the net's common namespace. + */ +struct ns_common *get_net_ns(struct ns_common *ns) +{ + return &get_net(container_of(ns, struct net, ns))->ns; +} +EXPORT_SYMBOL_GPL(get_net_ns); + struct net *get_net_ns_by_fd(int fd) { struct file *file; diff --git a/net/socket.c b/net/socket.c index 27e3e7d53f8e..4f2c6d2795d0 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1072,19 +1072,6 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, * what to do with it - that's up to the protocol still. */ -/** - * get_net_ns - increment the refcount of the network namespace - * @ns: common namespace (net) - * - * Returns the net's common namespace. - */ - -struct ns_common *get_net_ns(struct ns_common *ns) -{ - return &get_net(container_of(ns, struct net, ns))->ns; -} -EXPORT_SYMBOL_GPL(get_net_ns); - static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) { struct socket *sock; -- cgit v1.2.3 From 4f667b8e049e716a0533fc927f50310fe6e40d22 Mon Sep 17 00:00:00 2001 From: Tyson Moore Date: Sat, 12 Jun 2021 02:54:11 -0400 Subject: sch_cake: revise docs for RFC 8622 LE PHB support Commit b8392808eb3fc28e ("sch_cake: add RFC 8622 LE PHB support to CAKE diffserv handling") added the LE mark to the Bulk tin. Update the comments to reflect the change. Signed-off-by: Tyson Moore Acked-by: Toke Høiland-Jørgensen Signed-off-by: David S. Miller --- net/sched/sch_cake.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'net') diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 5c15968b5155..951542843cab 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -2342,7 +2342,7 @@ static int cake_config_precedence(struct Qdisc *sch) /* List of known Diffserv codepoints: * - * Least Effort (CS1) + * Least Effort (CS1, LE) * Best Effort (CS0) * Max Reliability & LLT "Lo" (TOS1) * Max Throughput (TOS2) @@ -2364,7 +2364,7 @@ static int cake_config_precedence(struct Qdisc *sch) * Total 25 codepoints. */ -/* List of traffic classes in RFC 4594: +/* List of traffic classes in RFC 4594, updated by RFC 8622: * (roughly descending order of contended priority) * (roughly ascending order of uncontended throughput) * @@ -2379,7 +2379,7 @@ static int cake_config_precedence(struct Qdisc *sch) * Ops, Admin, Management (CS2,TOS1) - eg. ssh * Standard Service (CS0 & unrecognised codepoints) * High Throughput Data (AF1x,TOS2) - eg. web traffic - * Low Priority Data (CS1) - eg. BitTorrent + * Low Priority Data (CS1,LE) - eg. BitTorrent * Total 12 traffic classes. */ @@ -2395,7 +2395,7 @@ static int cake_config_diffserv8(struct Qdisc *sch) * Video Streaming (AF4x, AF3x, CS3) * Bog Standard (CS0 etc.) * High Throughput (AF1x, TOS2) - * Background Traffic (CS1) + * Background Traffic (CS1, LE) * * Total 8 traffic classes. */ @@ -2439,7 +2439,7 @@ static int cake_config_diffserv4(struct Qdisc *sch) * Latency Sensitive (CS7, CS6, EF, VA, CS5, CS4) * Streaming Media (AF4x, AF3x, CS3, AF2x, TOS4, CS2, TOS1) * Best Effort (CS0, AF1x, TOS2, and those not specified) - * Background Traffic (CS1) + * Background Traffic (CS1, LE) * * Total 4 traffic classes. */ @@ -2477,7 +2477,7 @@ static int cake_config_diffserv4(struct Qdisc *sch) static int cake_config_diffserv3(struct Qdisc *sch) { /* Simplified Diffserv structure with 3 tins. - * Low Priority (CS1) + * Low Priority (CS1, LE) * Best Effort * Latency Sensitive (TOS4, VA, EF, CS6, CS7) */ -- cgit v1.2.3 From e175aef902697826d344ce3a12189329848fe898 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 11 Jun 2021 18:49:48 -0700 Subject: ethtool: strset: fix message length calculation Outer nest for ETHTOOL_A_STRSET_STRINGSETS is not accounted for. This may result in ETHTOOL_MSG_STRSET_GET producing a warning like: calculated message payload length (684) not sufficient WARNING: CPU: 0 PID: 30967 at net/ethtool/netlink.c:369 ethnl_default_doit+0x87a/0xa20 and a splat. As usually with such warnings three conditions must be met for the warning to trigger: - there must be no skb size rounding up (e.g. reply_size of 684); - string set must be per-device (so that the header gets populated); - the device name must be at least 12 characters long. all in all with current user space it looks like reading priv flags is the only place this could potentially happen. Or with syzbot :) Reported-by: syzbot+59aa77b92d06cd5a54f2@syzkaller.appspotmail.com Fixes: 71921690f974 ("ethtool: provide string sets with STRSET_GET request") Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- net/ethtool/strset.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net') diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c index b3029fff715d..2d51b7ab4dc5 100644 --- a/net/ethtool/strset.c +++ b/net/ethtool/strset.c @@ -353,6 +353,8 @@ static int strset_reply_size(const struct ethnl_req_info *req_base, int len = 0; int ret; + len += nla_total_size(0); /* ETHTOOL_A_STRSET_STRINGSETS */ + for (i = 0; i < ETH_SS_COUNT; i++) { const struct strset_info *set_info = &data->sets[i]; -- cgit v1.2.3 From b87b04f5019e821c8c6c7761f258402e43500a1f Mon Sep 17 00:00:00 2001 From: David Ahern Date: Sat, 12 Jun 2021 18:24:59 -0600 Subject: ipv4: Fix device used for dst_alloc with local routes Oliver reported a use case where deleting a VRF device can hang waiting for the refcnt to drop to 0. The root cause is that the dst is allocated against the VRF device but cached on the loopback device. The use case (added to the selftests) has an implicit VRF crossing due to the ordering of the FIB rules (lookup local is before the l3mdev rule, but the problem occurs even if the FIB rules are re-ordered with local after l3mdev because the VRF table does not have a default route to terminate the lookup). The end result is is that the FIB lookup returns the loopback device as the nexthop, but the ingress device is in a VRF. The mismatch causes the dst alloc against the VRF device but then cached on the loopback. The fix is to bring the trick used for IPv6 (see ip6_rt_get_dev_rcu): pick the dst alloc device based the fib lookup result but with checks that the result has a nexthop device (e.g., not an unreachable or prohibit entry). Fixes: f5a0aab84b74 ("net: ipv4: dst for local input routes should use l3mdev if relevant") Reported-by: Oliver Herms Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/route.c | 15 ++++++++++++++- tools/testing/selftests/net/fib_tests.sh | 25 +++++++++++++++++++++++++ 2 files changed, 39 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f6787c55f6ab..6a36ac98476f 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2056,6 +2056,19 @@ martian_source: return err; } +/* get device for dst_alloc with local routes */ +static struct net_device *ip_rt_get_dev(struct net *net, + const struct fib_result *res) +{ + struct fib_nh_common *nhc = res->fi ? res->nhc : NULL; + struct net_device *dev = NULL; + + if (nhc) + dev = l3mdev_master_dev_rcu(nhc->nhc_dev); + + return dev ? : net->loopback_dev; +} + /* * NOTE. We drop all the packets that has local source * addresses, because every properly looped back packet @@ -2212,7 +2225,7 @@ local_input: } } - rth = rt_dst_alloc(l3mdev_master_dev_rcu(dev) ? : net->loopback_dev, + rth = rt_dst_alloc(ip_rt_get_dev(net, res), flags | RTCF_LOCAL, res->type, IN_DEV_ORCONF(in_dev, NOPOLICY), false); if (!rth) diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 76d9487fb03c..5abe92d55b69 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -1384,12 +1384,37 @@ ipv4_rt_replace() ipv4_rt_replace_mpath } +# checks that cached input route on VRF port is deleted +# when VRF is deleted +ipv4_local_rt_cache() +{ + run_cmd "ip addr add 10.0.0.1/32 dev lo" + run_cmd "ip netns add test-ns" + run_cmd "ip link add veth-outside type veth peer name veth-inside" + run_cmd "ip link add vrf-100 type vrf table 1100" + run_cmd "ip link set veth-outside master vrf-100" + run_cmd "ip link set veth-inside netns test-ns" + run_cmd "ip link set veth-outside up" + run_cmd "ip link set vrf-100 up" + run_cmd "ip route add 10.1.1.1/32 dev veth-outside table 1100" + run_cmd "ip netns exec test-ns ip link set veth-inside up" + run_cmd "ip netns exec test-ns ip addr add 10.1.1.1/32 dev veth-inside" + run_cmd "ip netns exec test-ns ip route add 10.0.0.1/32 dev veth-inside" + run_cmd "ip netns exec test-ns ip route add default via 10.0.0.1" + run_cmd "ip netns exec test-ns ping 10.0.0.1 -c 1 -i 1" + run_cmd "ip link delete vrf-100" + + # if we do not hang test is a success + log_test $? 0 "Cached route removed from VRF port device" +} + ipv4_route_test() { route_setup ipv4_rt_add ipv4_rt_replace + ipv4_local_rt_cache route_cleanup } -- cgit v1.2.3 From ad9d24c9429e2159d1e279dc3a83191ccb4daf1d Mon Sep 17 00:00:00 2001 From: Pavel Skripkin Date: Mon, 14 Jun 2021 15:06:50 +0300 Subject: net: qrtr: fix OOB Read in qrtr_endpoint_post Syzbot reported slab-out-of-bounds Read in qrtr_endpoint_post. The problem was in wrong _size_ type: if (len != ALIGN(size, 4) + hdrlen) goto err; If size from qrtr_hdr is 4294967293 (0xfffffffd), the result of ALIGN(size, 4) will be 0. In case of len == hdrlen and size == 4294967293 in header this check won't fail and skb_put_data(skb, data + hdrlen, size); will read out of bound from data, which is hdrlen allocated block. Fixes: 194ccc88297a ("net: qrtr: Support decoding incoming v2 packets") Reported-and-tested-by: syzbot+1917d778024161609247@syzkaller.appspotmail.com Signed-off-by: Pavel Skripkin Reviewed-by: Bjorn Andersson Signed-off-by: David S. Miller --- net/qrtr/qrtr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index c0477bec09bd..f2efaa4225f9 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -436,7 +436,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) struct qrtr_sock *ipc; struct sk_buff *skb; struct qrtr_cb *cb; - unsigned int size; + size_t size; unsigned int ver; size_t hdrlen; -- cgit v1.2.3 From 995fca15b73ff8f92888cc2d5d95f17ffdac74ba Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Mon, 14 Jun 2021 10:46:44 -0700 Subject: Bluetooth: SMP: Fix crash when receiving new connection when debug is enabled When receiving a new connection pchan->conn won't be initialized so the code cannot use bt_dev_dbg as the pointer to hci_dev won't be accessible. Fixes: 2e1614f7d61e4 ("Bluetooth: SMP: Convert BT_ERR/BT_DBG to bt_dev_err/bt_dev_dbg") Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Marcel Holtmann --- net/bluetooth/smp.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 372e3b25aaa4..7dd51da73845 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -3229,7 +3229,7 @@ static inline struct l2cap_chan *smp_new_conn_cb(struct l2cap_chan *pchan) { struct l2cap_chan *chan; - bt_dev_dbg(pchan->conn->hcon->hdev, "pchan %p", pchan); + BT_DBG("pchan %p", pchan); chan = l2cap_chan_create(); if (!chan) @@ -3250,7 +3250,7 @@ static inline struct l2cap_chan *smp_new_conn_cb(struct l2cap_chan *pchan) */ atomic_set(&chan->nesting, L2CAP_NESTING_SMP); - bt_dev_dbg(pchan->conn->hcon->hdev, "created chan %p", chan); + BT_DBG("created chan %p", chan); return chan; } @@ -3354,7 +3354,7 @@ static void smp_del_chan(struct l2cap_chan *chan) { struct smp_dev *smp; - bt_dev_dbg(chan->conn->hcon->hdev, "chan %p", chan); + BT_DBG("chan %p", chan); smp = chan->data; if (smp) { -- cgit v1.2.3 From e34492dea68d4f09e9989e518fc76cd41909d707 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Tue, 15 Jun 2021 07:52:43 +0800 Subject: net: inline function get_net_ns_by_fd if NET_NS is disabled The function get_net_ns_by_fd() could be inlined when NET_NS is not enabled. Signed-off-by: Changbin Du Signed-off-by: David S. Miller --- include/net/net_namespace.h | 7 ++++++- net/core/net_namespace.c | 8 +------- 2 files changed, 7 insertions(+), 8 deletions(-) (limited to 'net') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 6412d7833d97..bdc0459a595e 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -186,6 +186,7 @@ void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid); void net_ns_barrier(void); struct ns_common *get_net_ns(struct ns_common *ns); +struct net *get_net_ns_by_fd(int fd); #else /* CONFIG_NET_NS */ #include #include @@ -210,13 +211,17 @@ static inline struct ns_common *get_net_ns(struct ns_common *ns) { return ERR_PTR(-EINVAL); } + +static inline struct net *get_net_ns_by_fd(int fd) +{ + return ERR_PTR(-EINVAL); +} #endif /* CONFIG_NET_NS */ extern struct list_head net_namespace_list; struct net *get_net_ns_by_pid(pid_t pid); -struct net *get_net_ns_by_fd(int fd); #ifdef CONFIG_SYSCTL void ipx_register_sysctl(void); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index cc8dafb25d61..9b5a767eddd5 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -672,14 +672,8 @@ struct net *get_net_ns_by_fd(int fd) fput(file); return net; } - -#else -struct net *get_net_ns_by_fd(int fd) -{ - return ERR_PTR(-EINVAL); -} -#endif EXPORT_SYMBOL_GPL(get_net_ns_by_fd); +#endif struct net *get_net_ns_by_pid(pid_t pid) { -- cgit v1.2.3 From 2030043e616cab40f510299f09b636285e0a3678 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Fri, 21 May 2021 13:57:20 +0200 Subject: can: j1939: fix Use-after-Free, hold skb ref while in use This patch fixes a Use-after-Free found by the syzbot. The problem is that a skb is taken from the per-session skb queue, without incrementing the ref count. This leads to a Use-after-Free if the skb is taken concurrently from the session queue due to a CTS. Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol") Link: https://lore.kernel.org/r/20210521115720.7533-1-o.rempel@pengutronix.de Cc: Hillf Danton Cc: linux-stable Reported-by: syzbot+220c1a29987a9a490903@syzkaller.appspotmail.com Reported-by: syzbot+45199c1b73b4013525cf@syzkaller.appspotmail.com Signed-off-by: Oleksij Rempel Signed-off-by: Marc Kleine-Budde --- net/can/j1939/transport.c | 54 +++++++++++++++++++++++++++++++++++------------ 1 file changed, 40 insertions(+), 14 deletions(-) (limited to 'net') diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index e09d087ba240..c3946c355882 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -330,6 +330,9 @@ static void j1939_session_skb_drop_old(struct j1939_session *session) if ((do_skcb->offset + do_skb->len) < offset_start) { __skb_unlink(do_skb, &session->skb_queue); + /* drop ref taken in j1939_session_skb_queue() */ + skb_unref(do_skb); + kfree_skb(do_skb); } spin_unlock_irqrestore(&session->skb_queue.lock, flags); @@ -349,12 +352,13 @@ void j1939_session_skb_queue(struct j1939_session *session, skcb->flags |= J1939_ECU_LOCAL_SRC; + skb_get(skb); skb_queue_tail(&session->skb_queue, skb); } static struct -sk_buff *j1939_session_skb_find_by_offset(struct j1939_session *session, - unsigned int offset_start) +sk_buff *j1939_session_skb_get_by_offset(struct j1939_session *session, + unsigned int offset_start) { struct j1939_priv *priv = session->priv; struct j1939_sk_buff_cb *do_skcb; @@ -371,6 +375,10 @@ sk_buff *j1939_session_skb_find_by_offset(struct j1939_session *session, skb = do_skb; } } + + if (skb) + skb_get(skb); + spin_unlock_irqrestore(&session->skb_queue.lock, flags); if (!skb) @@ -381,12 +389,12 @@ sk_buff *j1939_session_skb_find_by_offset(struct j1939_session *session, return skb; } -static struct sk_buff *j1939_session_skb_find(struct j1939_session *session) +static struct sk_buff *j1939_session_skb_get(struct j1939_session *session) { unsigned int offset_start; offset_start = session->pkt.dpo * 7; - return j1939_session_skb_find_by_offset(session, offset_start); + return j1939_session_skb_get_by_offset(session, offset_start); } /* see if we are receiver @@ -776,7 +784,7 @@ static int j1939_session_tx_dat(struct j1939_session *session) int ret = 0; u8 dat[8]; - se_skb = j1939_session_skb_find_by_offset(session, session->pkt.tx * 7); + se_skb = j1939_session_skb_get_by_offset(session, session->pkt.tx * 7); if (!se_skb) return -ENOBUFS; @@ -801,7 +809,8 @@ static int j1939_session_tx_dat(struct j1939_session *session) netdev_err_once(priv->ndev, "%s: 0x%p: requested data outside of queued buffer: offset %i, len %i, pkt.tx: %i\n", __func__, session, skcb->offset, se_skb->len , session->pkt.tx); - return -EOVERFLOW; + ret = -EOVERFLOW; + goto out_free; } if (!len) { @@ -835,6 +844,12 @@ static int j1939_session_tx_dat(struct j1939_session *session) if (pkt_done) j1939_tp_set_rxtimeout(session, 250); + out_free: + if (ret) + kfree_skb(se_skb); + else + consume_skb(se_skb); + return ret; } @@ -1007,7 +1022,7 @@ static int j1939_xtp_txnext_receiver(struct j1939_session *session) static int j1939_simple_txnext(struct j1939_session *session) { struct j1939_priv *priv = session->priv; - struct sk_buff *se_skb = j1939_session_skb_find(session); + struct sk_buff *se_skb = j1939_session_skb_get(session); struct sk_buff *skb; int ret; @@ -1015,8 +1030,10 @@ static int j1939_simple_txnext(struct j1939_session *session) return 0; skb = skb_clone(se_skb, GFP_ATOMIC); - if (!skb) - return -ENOMEM; + if (!skb) { + ret = -ENOMEM; + goto out_free; + } can_skb_set_owner(skb, se_skb->sk); @@ -1024,12 +1041,18 @@ static int j1939_simple_txnext(struct j1939_session *session) ret = j1939_send_one(priv, skb); if (ret) - return ret; + goto out_free; j1939_sk_errqueue(session, J1939_ERRQUEUE_SCHED); j1939_sk_queue_activate_next(session); - return 0; + out_free: + if (ret) + kfree_skb(se_skb); + else + consume_skb(se_skb); + + return ret; } static bool j1939_session_deactivate_locked(struct j1939_session *session) @@ -1170,9 +1193,10 @@ static void j1939_session_completed(struct j1939_session *session) struct sk_buff *skb; if (!session->transmission) { - skb = j1939_session_skb_find(session); + skb = j1939_session_skb_get(session); /* distribute among j1939 receivers */ j1939_sk_recv(session->priv, skb); + consume_skb(skb); } j1939_session_deactivate_activate_next(session); @@ -1744,7 +1768,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, { struct j1939_priv *priv = session->priv; struct j1939_sk_buff_cb *skcb; - struct sk_buff *se_skb; + struct sk_buff *se_skb = NULL; const u8 *dat; u8 *tpdat; int offset; @@ -1786,7 +1810,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, goto out_session_cancel; } - se_skb = j1939_session_skb_find_by_offset(session, packet * 7); + se_skb = j1939_session_skb_get_by_offset(session, packet * 7); if (!se_skb) { netdev_warn(priv->ndev, "%s: 0x%p: no skb found\n", __func__, session); @@ -1848,11 +1872,13 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, j1939_tp_set_rxtimeout(session, 250); } session->last_cmd = 0xff; + consume_skb(se_skb); j1939_session_put(session); return; out_session_cancel: + kfree_skb(se_skb); j1939_session_timers_cancel(session); j1939_session_cancel(session, J1939_XTP_ABORT_FAULT); j1939_session_put(session); -- cgit v1.2.3 From 8d0caedb759683041d9db82069937525999ada53 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Sat, 5 Jun 2021 19:26:35 +0900 Subject: can: bcm/raw/isotp: use per module netdevice notifier syzbot is reporting hung task at register_netdevice_notifier() [1] and unregister_netdevice_notifier() [2], for cleanup_net() might perform time consuming operations while CAN driver's raw/bcm/isotp modules are calling {register,unregister}_netdevice_notifier() on each socket. Change raw/bcm/isotp modules to call register_netdevice_notifier() from module's __init function and call unregister_netdevice_notifier() from module's __exit function, as with gw/j1939 modules are doing. Link: https://syzkaller.appspot.com/bug?id=391b9498827788b3cc6830226d4ff5be87107c30 [1] Link: https://syzkaller.appspot.com/bug?id=1724d278c83ca6e6df100a2e320c10d991cf2bce [2] Link: https://lore.kernel.org/r/54a5f451-05ed-f977-8534-79e7aa2bcc8f@i-love.sakura.ne.jp Cc: linux-stable Reported-by: syzbot Reported-by: syzbot Reviewed-by: Kirill Tkhai Tested-by: syzbot Tested-by: Oliver Hartkopp Signed-off-by: Tetsuo Handa Signed-off-by: Marc Kleine-Budde --- net/can/bcm.c | 59 ++++++++++++++++++++++++++++++++++++++++++------------ net/can/isotp.c | 61 ++++++++++++++++++++++++++++++++++++++++++++------------ net/can/raw.c | 62 ++++++++++++++++++++++++++++++++++++++++++++------------- 3 files changed, 142 insertions(+), 40 deletions(-) (limited to 'net') diff --git a/net/can/bcm.c b/net/can/bcm.c index 909b9e684e04..f00176b2a6c3 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -125,7 +125,7 @@ struct bcm_sock { struct sock sk; int bound; int ifindex; - struct notifier_block notifier; + struct list_head notifier; struct list_head rx_ops; struct list_head tx_ops; unsigned long dropped_usr_msgs; @@ -133,6 +133,10 @@ struct bcm_sock { char procname [32]; /* inode number in decimal with \0 */ }; +static LIST_HEAD(bcm_notifier_list); +static DEFINE_SPINLOCK(bcm_notifier_lock); +static struct bcm_sock *bcm_busy_notifier; + static inline struct bcm_sock *bcm_sk(const struct sock *sk) { return (struct bcm_sock *)sk; @@ -1378,20 +1382,15 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) /* * notification handler for netdevice status changes */ -static int bcm_notifier(struct notifier_block *nb, unsigned long msg, - void *ptr) +static void bcm_notify(struct bcm_sock *bo, unsigned long msg, + struct net_device *dev) { - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct bcm_sock *bo = container_of(nb, struct bcm_sock, notifier); struct sock *sk = &bo->sk; struct bcm_op *op; int notify_enodev = 0; if (!net_eq(dev_net(dev), sock_net(sk))) - return NOTIFY_DONE; - - if (dev->type != ARPHRD_CAN) - return NOTIFY_DONE; + return; switch (msg) { @@ -1426,7 +1425,28 @@ static int bcm_notifier(struct notifier_block *nb, unsigned long msg, sk->sk_error_report(sk); } } +} +static int bcm_notifier(struct notifier_block *nb, unsigned long msg, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + if (dev->type != ARPHRD_CAN) + return NOTIFY_DONE; + if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) + return NOTIFY_DONE; + if (unlikely(bcm_busy_notifier)) /* Check for reentrant bug. */ + return NOTIFY_DONE; + + spin_lock(&bcm_notifier_lock); + list_for_each_entry(bcm_busy_notifier, &bcm_notifier_list, notifier) { + spin_unlock(&bcm_notifier_lock); + bcm_notify(bcm_busy_notifier, msg, dev); + spin_lock(&bcm_notifier_lock); + } + bcm_busy_notifier = NULL; + spin_unlock(&bcm_notifier_lock); return NOTIFY_DONE; } @@ -1446,9 +1466,9 @@ static int bcm_init(struct sock *sk) INIT_LIST_HEAD(&bo->rx_ops); /* set notifier */ - bo->notifier.notifier_call = bcm_notifier; - - register_netdevice_notifier(&bo->notifier); + spin_lock(&bcm_notifier_lock); + list_add_tail(&bo->notifier, &bcm_notifier_list); + spin_unlock(&bcm_notifier_lock); return 0; } @@ -1471,7 +1491,14 @@ static int bcm_release(struct socket *sock) /* remove bcm_ops, timer, rx_unregister(), etc. */ - unregister_netdevice_notifier(&bo->notifier); + spin_lock(&bcm_notifier_lock); + while (bcm_busy_notifier == bo) { + spin_unlock(&bcm_notifier_lock); + schedule_timeout_uninterruptible(1); + spin_lock(&bcm_notifier_lock); + } + list_del(&bo->notifier); + spin_unlock(&bcm_notifier_lock); lock_sock(sk); @@ -1692,6 +1719,10 @@ static struct pernet_operations canbcm_pernet_ops __read_mostly = { .exit = canbcm_pernet_exit, }; +static struct notifier_block canbcm_notifier = { + .notifier_call = bcm_notifier +}; + static int __init bcm_module_init(void) { int err; @@ -1705,12 +1736,14 @@ static int __init bcm_module_init(void) } register_pernet_subsys(&canbcm_pernet_ops); + register_netdevice_notifier(&canbcm_notifier); return 0; } static void __exit bcm_module_exit(void) { can_proto_unregister(&bcm_can_proto); + unregister_netdevice_notifier(&canbcm_notifier); unregister_pernet_subsys(&canbcm_pernet_ops); } diff --git a/net/can/isotp.c b/net/can/isotp.c index 253b24417c8e..be6183f8ca11 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -143,10 +143,14 @@ struct isotp_sock { u32 force_tx_stmin; u32 force_rx_stmin; struct tpcon rx, tx; - struct notifier_block notifier; + struct list_head notifier; wait_queue_head_t wait; }; +static LIST_HEAD(isotp_notifier_list); +static DEFINE_SPINLOCK(isotp_notifier_lock); +static struct isotp_sock *isotp_busy_notifier; + static inline struct isotp_sock *isotp_sk(const struct sock *sk) { return (struct isotp_sock *)sk; @@ -1013,7 +1017,14 @@ static int isotp_release(struct socket *sock) /* wait for complete transmission of current pdu */ wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); - unregister_netdevice_notifier(&so->notifier); + spin_lock(&isotp_notifier_lock); + while (isotp_busy_notifier == so) { + spin_unlock(&isotp_notifier_lock); + schedule_timeout_uninterruptible(1); + spin_lock(&isotp_notifier_lock); + } + list_del(&so->notifier); + spin_unlock(&isotp_notifier_lock); lock_sock(sk); @@ -1317,21 +1328,16 @@ static int isotp_getsockopt(struct socket *sock, int level, int optname, return 0; } -static int isotp_notifier(struct notifier_block *nb, unsigned long msg, - void *ptr) +static void isotp_notify(struct isotp_sock *so, unsigned long msg, + struct net_device *dev) { - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct isotp_sock *so = container_of(nb, struct isotp_sock, notifier); struct sock *sk = &so->sk; if (!net_eq(dev_net(dev), sock_net(sk))) - return NOTIFY_DONE; - - if (dev->type != ARPHRD_CAN) - return NOTIFY_DONE; + return; if (so->ifindex != dev->ifindex) - return NOTIFY_DONE; + return; switch (msg) { case NETDEV_UNREGISTER: @@ -1357,7 +1363,28 @@ static int isotp_notifier(struct notifier_block *nb, unsigned long msg, sk->sk_error_report(sk); break; } +} +static int isotp_notifier(struct notifier_block *nb, unsigned long msg, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + if (dev->type != ARPHRD_CAN) + return NOTIFY_DONE; + if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) + return NOTIFY_DONE; + if (unlikely(isotp_busy_notifier)) /* Check for reentrant bug. */ + return NOTIFY_DONE; + + spin_lock(&isotp_notifier_lock); + list_for_each_entry(isotp_busy_notifier, &isotp_notifier_list, notifier) { + spin_unlock(&isotp_notifier_lock); + isotp_notify(isotp_busy_notifier, msg, dev); + spin_lock(&isotp_notifier_lock); + } + isotp_busy_notifier = NULL; + spin_unlock(&isotp_notifier_lock); return NOTIFY_DONE; } @@ -1394,8 +1421,9 @@ static int isotp_init(struct sock *sk) init_waitqueue_head(&so->wait); - so->notifier.notifier_call = isotp_notifier; - register_netdevice_notifier(&so->notifier); + spin_lock(&isotp_notifier_lock); + list_add_tail(&so->notifier, &isotp_notifier_list); + spin_unlock(&isotp_notifier_lock); return 0; } @@ -1442,6 +1470,10 @@ static const struct can_proto isotp_can_proto = { .prot = &isotp_proto, }; +static struct notifier_block canisotp_notifier = { + .notifier_call = isotp_notifier +}; + static __init int isotp_module_init(void) { int err; @@ -1451,6 +1483,8 @@ static __init int isotp_module_init(void) err = can_proto_register(&isotp_can_proto); if (err < 0) pr_err("can: registration of isotp protocol failed\n"); + else + register_netdevice_notifier(&canisotp_notifier); return err; } @@ -1458,6 +1492,7 @@ static __init int isotp_module_init(void) static __exit void isotp_module_exit(void) { can_proto_unregister(&isotp_can_proto); + unregister_netdevice_notifier(&canisotp_notifier); } module_init(isotp_module_init); diff --git a/net/can/raw.c b/net/can/raw.c index 139d9471ddcf..ac96fc210025 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -83,7 +83,7 @@ struct raw_sock { struct sock sk; int bound; int ifindex; - struct notifier_block notifier; + struct list_head notifier; int loopback; int recv_own_msgs; int fd_frames; @@ -95,6 +95,10 @@ struct raw_sock { struct uniqframe __percpu *uniq; }; +static LIST_HEAD(raw_notifier_list); +static DEFINE_SPINLOCK(raw_notifier_lock); +static struct raw_sock *raw_busy_notifier; + /* Return pointer to store the extra msg flags for raw_recvmsg(). * We use the space of one unsigned int beyond the 'struct sockaddr_can' * in skb->cb. @@ -263,21 +267,16 @@ static int raw_enable_allfilters(struct net *net, struct net_device *dev, return err; } -static int raw_notifier(struct notifier_block *nb, - unsigned long msg, void *ptr) +static void raw_notify(struct raw_sock *ro, unsigned long msg, + struct net_device *dev) { - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct raw_sock *ro = container_of(nb, struct raw_sock, notifier); struct sock *sk = &ro->sk; if (!net_eq(dev_net(dev), sock_net(sk))) - return NOTIFY_DONE; - - if (dev->type != ARPHRD_CAN) - return NOTIFY_DONE; + return; if (ro->ifindex != dev->ifindex) - return NOTIFY_DONE; + return; switch (msg) { case NETDEV_UNREGISTER: @@ -305,7 +304,28 @@ static int raw_notifier(struct notifier_block *nb, sk->sk_error_report(sk); break; } +} + +static int raw_notifier(struct notifier_block *nb, unsigned long msg, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + if (dev->type != ARPHRD_CAN) + return NOTIFY_DONE; + if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) + return NOTIFY_DONE; + if (unlikely(raw_busy_notifier)) /* Check for reentrant bug. */ + return NOTIFY_DONE; + spin_lock(&raw_notifier_lock); + list_for_each_entry(raw_busy_notifier, &raw_notifier_list, notifier) { + spin_unlock(&raw_notifier_lock); + raw_notify(raw_busy_notifier, msg, dev); + spin_lock(&raw_notifier_lock); + } + raw_busy_notifier = NULL; + spin_unlock(&raw_notifier_lock); return NOTIFY_DONE; } @@ -334,9 +354,9 @@ static int raw_init(struct sock *sk) return -ENOMEM; /* set notifier */ - ro->notifier.notifier_call = raw_notifier; - - register_netdevice_notifier(&ro->notifier); + spin_lock(&raw_notifier_lock); + list_add_tail(&ro->notifier, &raw_notifier_list); + spin_unlock(&raw_notifier_lock); return 0; } @@ -351,7 +371,14 @@ static int raw_release(struct socket *sock) ro = raw_sk(sk); - unregister_netdevice_notifier(&ro->notifier); + spin_lock(&raw_notifier_lock); + while (raw_busy_notifier == ro) { + spin_unlock(&raw_notifier_lock); + schedule_timeout_uninterruptible(1); + spin_lock(&raw_notifier_lock); + } + list_del(&ro->notifier); + spin_unlock(&raw_notifier_lock); lock_sock(sk); @@ -889,6 +916,10 @@ static const struct can_proto raw_can_proto = { .prot = &raw_proto, }; +static struct notifier_block canraw_notifier = { + .notifier_call = raw_notifier +}; + static __init int raw_module_init(void) { int err; @@ -898,6 +929,8 @@ static __init int raw_module_init(void) err = can_proto_register(&raw_can_proto); if (err < 0) pr_err("can: registration of raw protocol failed\n"); + else + register_netdevice_notifier(&canraw_notifier); return err; } @@ -905,6 +938,7 @@ static __init int raw_module_init(void) static __exit void raw_module_exit(void) { can_proto_unregister(&raw_can_proto); + unregister_netdevice_notifier(&canraw_notifier); } module_init(raw_module_init); -- cgit v1.2.3 From 5e87ddbe3942e27e939bdc02deb8579b0cbd8ecc Mon Sep 17 00:00:00 2001 From: Norbert Slusarek Date: Sat, 12 Jun 2021 22:18:54 +0200 Subject: can: bcm: fix infoleak in struct bcm_msg_head On 64-bit systems, struct bcm_msg_head has an added padding of 4 bytes between struct members count and ival1. Even though all struct members are initialized, the 4-byte hole will contain data from the kernel stack. This patch zeroes out struct bcm_msg_head before usage, preventing infoleaks to userspace. Fixes: ffd980f976e7 ("[CAN]: Add broadcast manager (bcm) protocol") Link: https://lore.kernel.org/r/trinity-7c1b2e82-e34f-4885-8060-2cd7a13769ce-1623532166177@3c-app-gmx-bs52 Cc: linux-stable Signed-off-by: Norbert Slusarek Acked-by: Oliver Hartkopp Signed-off-by: Marc Kleine-Budde --- net/can/bcm.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net') diff --git a/net/can/bcm.c b/net/can/bcm.c index f00176b2a6c3..f3e4d9528fa3 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -406,6 +406,7 @@ static enum hrtimer_restart bcm_tx_timeout_handler(struct hrtimer *hrtimer) if (!op->count && (op->flags & TX_COUNTEVT)) { /* create notification to user */ + memset(&msg_head, 0, sizeof(msg_head)); msg_head.opcode = TX_EXPIRED; msg_head.flags = op->flags; msg_head.count = op->count; @@ -443,6 +444,7 @@ static void bcm_rx_changed(struct bcm_op *op, struct canfd_frame *data) /* this element is not throttled anymore */ data->flags &= (BCM_CAN_FLAGS_MASK|RX_RECV); + memset(&head, 0, sizeof(head)); head.opcode = RX_CHANGED; head.flags = op->flags; head.count = op->count; @@ -564,6 +566,7 @@ static enum hrtimer_restart bcm_rx_timeout_handler(struct hrtimer *hrtimer) } /* create notification to user */ + memset(&msg_head, 0, sizeof(msg_head)); msg_head.opcode = RX_TIMEOUT; msg_head.flags = op->flags; msg_head.count = op->count; -- cgit v1.2.3 From d8e2973029b8b2ce477b564824431f3385c77083 Mon Sep 17 00:00:00 2001 From: Chengyang Fan Date: Wed, 16 Jun 2021 17:59:25 +0800 Subject: net: ipv4: fix memory leak in ip_mc_add1_src BUG: memory leak unreferenced object 0xffff888101bc4c00 (size 32): comm "syz-executor527", pid 360, jiffies 4294807421 (age 19.329s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 01 00 00 00 00 00 00 00 ac 14 14 bb 00 00 02 00 ................ backtrace: [<00000000f17c5244>] kmalloc include/linux/slab.h:558 [inline] [<00000000f17c5244>] kzalloc include/linux/slab.h:688 [inline] [<00000000f17c5244>] ip_mc_add1_src net/ipv4/igmp.c:1971 [inline] [<00000000f17c5244>] ip_mc_add_src+0x95f/0xdb0 net/ipv4/igmp.c:2095 [<000000001cb99709>] ip_mc_source+0x84c/0xea0 net/ipv4/igmp.c:2416 [<0000000052cf19ed>] do_ip_setsockopt net/ipv4/ip_sockglue.c:1294 [inline] [<0000000052cf19ed>] ip_setsockopt+0x114b/0x30c0 net/ipv4/ip_sockglue.c:1423 [<00000000477edfbc>] raw_setsockopt+0x13d/0x170 net/ipv4/raw.c:857 [<00000000e75ca9bb>] __sys_setsockopt+0x158/0x270 net/socket.c:2117 [<00000000bdb993a8>] __do_sys_setsockopt net/socket.c:2128 [inline] [<00000000bdb993a8>] __se_sys_setsockopt net/socket.c:2125 [inline] [<00000000bdb993a8>] __x64_sys_setsockopt+0xba/0x150 net/socket.c:2125 [<000000006a1ffdbd>] do_syscall_64+0x40/0x80 arch/x86/entry/common.c:47 [<00000000b11467c4>] entry_SYSCALL_64_after_hwframe+0x44/0xae In commit 24803f38a5c0 ("igmp: do not remove igmp souce list info when set link down"), the ip_mc_clear_src() in ip_mc_destroy_dev() was removed, because it was also called in igmpv3_clear_delrec(). Rough callgraph: inetdev_destroy -> ip_mc_destroy_dev -> igmpv3_clear_delrec -> ip_mc_clear_src -> RCU_INIT_POINTER(dev->ip_ptr, NULL) However, ip_mc_clear_src() called in igmpv3_clear_delrec() doesn't release in_dev->mc_list->sources. And RCU_INIT_POINTER() assigns the NULL to dev->ip_ptr. As a result, in_dev cannot be obtained through inetdev_by_index() and then in_dev->mc_list->sources cannot be released by ip_mc_del1_src() in the sock_close. Rough call sequence goes like: sock_close -> __sock_release -> inet_release -> ip_mc_drop_socket -> inetdev_by_index -> ip_mc_leave_src -> ip_mc_del_src -> ip_mc_del1_src So we still need to call ip_mc_clear_src() in ip_mc_destroy_dev() to free in_dev->mc_list->sources. Fixes: 24803f38a5c0 ("igmp: do not remove igmp souce list info ...") Reported-by: Hulk Robot Signed-off-by: Chengyang Fan Acked-by: Hangbin Liu Signed-off-by: David S. Miller --- net/ipv4/igmp.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net') diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 7b272bbed2b4..6b3c558a4f23 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1801,6 +1801,7 @@ void ip_mc_destroy_dev(struct in_device *in_dev) while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) { in_dev->mc_list = i->next_rcu; in_dev->mc_count--; + ip_mc_clear_src(i); ip_ma_put(i); } } -- cgit v1.2.3 From c7d2ef5dd4b03ed0ee1d13bc0c55f9cf62d49bd6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 16 Jun 2021 06:42:01 -0700 Subject: net/packet: annotate accesses to po->bind tpacket_snd(), packet_snd(), packet_getname() and packet_seq_show() can read po->num without holding a lock. This means other threads can change po->num at the same time. KCSAN complained about this known fact [1] Add READ_ONCE()/WRITE_ONCE() to address the issue. [1] BUG: KCSAN: data-race in packet_do_bind / packet_sendmsg write to 0xffff888131a0dcc0 of 2 bytes by task 24714 on cpu 0: packet_do_bind+0x3ab/0x7e0 net/packet/af_packet.c:3181 packet_bind+0xc3/0xd0 net/packet/af_packet.c:3255 __sys_bind+0x200/0x290 net/socket.c:1637 __do_sys_bind net/socket.c:1648 [inline] __se_sys_bind net/socket.c:1646 [inline] __x64_sys_bind+0x3d/0x50 net/socket.c:1646 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff888131a0dcc0 of 2 bytes by task 24719 on cpu 1: packet_snd net/packet/af_packet.c:2899 [inline] packet_sendmsg+0x317/0x3570 net/packet/af_packet.c:3040 sock_sendmsg_nosec net/socket.c:654 [inline] sock_sendmsg net/socket.c:674 [inline] ____sys_sendmsg+0x360/0x4d0 net/socket.c:2350 ___sys_sendmsg net/socket.c:2404 [inline] __sys_sendmsg+0x1ed/0x270 net/socket.c:2433 __do_sys_sendmsg net/socket.c:2442 [inline] __se_sys_sendmsg net/socket.c:2440 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2440 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x0000 -> 0x1200 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 24719 Comm: syz-executor.5 Not tainted 5.13.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- net/packet/af_packet.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'net') diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 74e6e45a8e84..e91a36bdd1ab 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2683,7 +2683,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) } if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); - proto = po->num; + proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) @@ -2896,7 +2896,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); - proto = po->num; + proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) @@ -3171,7 +3171,7 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, /* prevents packet_notifier() from calling * register_prot_hook() */ - po->num = 0; + WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, true); rcu_read_lock(); dev_curr = po->prot_hook.dev; @@ -3181,7 +3181,7 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, } BUG_ON(po->running); - po->num = proto; + WRITE_ONCE(po->num, proto); po->prot_hook.type = proto; if (unlikely(unlisted)) { @@ -3526,7 +3526,7 @@ static int packet_getname(struct socket *sock, struct sockaddr *uaddr, sll->sll_family = AF_PACKET; sll->sll_ifindex = po->ifindex; - sll->sll_protocol = po->num; + sll->sll_protocol = READ_ONCE(po->num); sll->sll_pkttype = 0; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), po->ifindex); @@ -4414,7 +4414,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, was_running = po->running; num = po->num; if (was_running) { - po->num = 0; + WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, false); } spin_unlock(&po->bind_lock); @@ -4449,7 +4449,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, spin_lock(&po->bind_lock); if (was_running) { - po->num = num; + WRITE_ONCE(po->num, num); register_prot_hook(sk); } spin_unlock(&po->bind_lock); @@ -4619,7 +4619,7 @@ static int packet_seq_show(struct seq_file *seq, void *v) s, refcount_read(&s->sk_refcnt), s->sk_type, - ntohs(po->num), + ntohs(READ_ONCE(po->num)), po->ifindex, po->running, atomic_read(&s->sk_rmem_alloc), -- cgit v1.2.3 From e032f7c9c7cefffcfb79b9fc16c53011d2d9d11f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 16 Jun 2021 06:42:02 -0700 Subject: net/packet: annotate accesses to po->ifindex Like prior patch, we need to annotate lockless accesses to po->ifindex For instance, packet_getname() is reading po->ifindex (twice) while another thread is able to change po->ifindex. KCSAN reported: BUG: KCSAN: data-race in packet_do_bind / packet_getname write to 0xffff888143ce3cbc of 4 bytes by task 25573 on cpu 1: packet_do_bind+0x420/0x7e0 net/packet/af_packet.c:3191 packet_bind+0xc3/0xd0 net/packet/af_packet.c:3255 __sys_bind+0x200/0x290 net/socket.c:1637 __do_sys_bind net/socket.c:1648 [inline] __se_sys_bind net/socket.c:1646 [inline] __x64_sys_bind+0x3d/0x50 net/socket.c:1646 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff888143ce3cbc of 4 bytes by task 25578 on cpu 0: packet_getname+0x5b/0x1a0 net/packet/af_packet.c:3525 __sys_getsockname+0x10e/0x1a0 net/socket.c:1887 __do_sys_getsockname net/socket.c:1902 [inline] __se_sys_getsockname net/socket.c:1899 [inline] __x64_sys_getsockname+0x3e/0x50 net/socket.c:1899 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x00000000 -> 0x00000001 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 25578 Comm: syz-executor.5 Not tainted 5.13.0-rc6-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- net/packet/af_packet.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'net') diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index e91a36bdd1ab..330ba68828e7 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3187,11 +3187,11 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, if (unlikely(unlisted)) { dev_put(dev); po->prot_hook.dev = NULL; - po->ifindex = -1; + WRITE_ONCE(po->ifindex, -1); packet_cached_dev_reset(po); } else { po->prot_hook.dev = dev; - po->ifindex = dev ? dev->ifindex : 0; + WRITE_ONCE(po->ifindex, dev ? dev->ifindex : 0); packet_cached_dev_assign(po, dev); } } @@ -3505,7 +3505,7 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, uaddr->sa_family = AF_PACKET; memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data)); rcu_read_lock(); - dev = dev_get_by_index_rcu(sock_net(sk), pkt_sk(sk)->ifindex); + dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) strlcpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data)); rcu_read_unlock(); @@ -3520,16 +3520,18 @@ static int packet_getname(struct socket *sock, struct sockaddr *uaddr, struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); DECLARE_SOCKADDR(struct sockaddr_ll *, sll, uaddr); + int ifindex; if (peer) return -EOPNOTSUPP; + ifindex = READ_ONCE(po->ifindex); sll->sll_family = AF_PACKET; - sll->sll_ifindex = po->ifindex; + sll->sll_ifindex = ifindex; sll->sll_protocol = READ_ONCE(po->num); sll->sll_pkttype = 0; rcu_read_lock(); - dev = dev_get_by_index_rcu(sock_net(sk), po->ifindex); + dev = dev_get_by_index_rcu(sock_net(sk), ifindex); if (dev) { sll->sll_hatype = dev->type; sll->sll_halen = dev->addr_len; @@ -4108,7 +4110,7 @@ static int packet_notifier(struct notifier_block *this, } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); - po->ifindex = -1; + WRITE_ONCE(po->ifindex, -1); if (po->prot_hook.dev) dev_put(po->prot_hook.dev); po->prot_hook.dev = NULL; @@ -4620,7 +4622,7 @@ static int packet_seq_show(struct seq_file *seq, void *v) refcount_read(&s->sk_refcnt), s->sk_type, ntohs(READ_ONCE(po->num)), - po->ifindex, + READ_ONCE(po->ifindex), po->running, atomic_read(&s->sk_rmem_alloc), from_kuid_munged(seq_user_ns(seq), sock_i_uid(s)), -- cgit v1.2.3 From a494bd642d9120648b06bb7d28ce6d05f55a7819 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 16 Jun 2021 07:47:15 -0700 Subject: net/af_unix: fix a data-race in unix_dgram_sendmsg / unix_release_sock While unix_may_send(sk, osk) is called while osk is locked, it appears unix_release_sock() can overwrite unix_peer() after this lock has been released, making KCSAN unhappy. Changing unix_release_sock() to access/change unix_peer() before lock is released should fix this issue. BUG: KCSAN: data-race in unix_dgram_sendmsg / unix_release_sock write to 0xffff88810465a338 of 8 bytes by task 20852 on cpu 1: unix_release_sock+0x4ed/0x6e0 net/unix/af_unix.c:558 unix_release+0x2f/0x50 net/unix/af_unix.c:859 __sock_release net/socket.c:599 [inline] sock_close+0x6c/0x150 net/socket.c:1258 __fput+0x25b/0x4e0 fs/file_table.c:280 ____fput+0x11/0x20 fs/file_table.c:313 task_work_run+0xae/0x130 kernel/task_work.c:164 tracehook_notify_resume include/linux/tracehook.h:189 [inline] exit_to_user_mode_loop kernel/entry/common.c:175 [inline] exit_to_user_mode_prepare+0x156/0x190 kernel/entry/common.c:209 __syscall_exit_to_user_mode_work kernel/entry/common.c:291 [inline] syscall_exit_to_user_mode+0x20/0x40 kernel/entry/common.c:302 do_syscall_64+0x56/0x90 arch/x86/entry/common.c:57 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff88810465a338 of 8 bytes by task 20888 on cpu 0: unix_may_send net/unix/af_unix.c:189 [inline] unix_dgram_sendmsg+0x923/0x1610 net/unix/af_unix.c:1712 sock_sendmsg_nosec net/socket.c:654 [inline] sock_sendmsg net/socket.c:674 [inline] ____sys_sendmsg+0x360/0x4d0 net/socket.c:2350 ___sys_sendmsg net/socket.c:2404 [inline] __sys_sendmmsg+0x315/0x4b0 net/socket.c:2490 __do_sys_sendmmsg net/socket.c:2519 [inline] __se_sys_sendmmsg net/socket.c:2516 [inline] __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2516 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0xffff888167905400 -> 0x0000000000000000 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 20888 Comm: syz-executor.0 Not tainted 5.13.0-rc5-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- net/unix/af_unix.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'net') diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 5a31307ceb76..5d1192ceb139 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -535,12 +535,14 @@ static void unix_release_sock(struct sock *sk, int embrion) u->path.mnt = NULL; state = sk->sk_state; sk->sk_state = TCP_CLOSE; + + skpair = unix_peer(sk); + unix_peer(sk) = NULL; + unix_state_unlock(sk); wake_up_interruptible_all(&u->peer_wait); - skpair = unix_peer(sk); - if (skpair != NULL) { if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) { unix_state_lock(skpair); @@ -555,7 +557,6 @@ static void unix_release_sock(struct sock *sk, int embrion) unix_dgram_peer_wake_disconnect(sk, skpair); sock_put(skpair); /* It may now die */ - unix_peer(sk) = NULL; } /* Try to flush out this socket. Throw out buffers at least */ -- cgit v1.2.3 From 1236af327af476731aa548dfcbbefb1a3ec6726a Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Thu, 17 Jun 2021 12:38:54 +0200 Subject: mac80211: minstrel_ht: fix sample time check We need to skip sampling if the next sample time is after jiffies, not before. This patch fixes an issue where in some cases only very little sampling (or none at all) is performed, leading to really bad data rates Fixes: 80d55154b2f8 ("mac80211: minstrel_ht: significantly redesign the rate probing strategy") Cc: stable@vger.kernel.org Signed-off-by: Felix Fietkau Link: https://lore.kernel.org/r/20210617103854.61875-1-nbd@nbd.name Signed-off-by: Johannes Berg --- net/mac80211/rc80211_minstrel_ht.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 6487b05da6fa..a6f3fb4a9197 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -1514,7 +1514,7 @@ minstrel_ht_get_rate(void *priv, struct ieee80211_sta *sta, void *priv_sta, (info->control.flags & IEEE80211_TX_CTRL_PORT_CTRL_PROTO)) return; - if (time_is_before_jiffies(mi->sample_time)) + if (time_is_after_jiffies(mi->sample_time)) return; mi->sample_time = jiffies + MINSTREL_SAMPLE_INTERVAL; -- cgit v1.2.3 From b5642479b0f7168fe16d156913533fe65ab4f8d5 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 18 Jun 2021 13:41:29 +0300 Subject: cfg80211: make certificate generation more robust If all net/wireless/certs/*.hex files are deleted, the build will hang at this point since the 'cat' command will have no arguments. Do "echo | cat - ..." so that even if the "..." part is empty, the whole thing won't hang. Cc: stable@vger.kernel.org Signed-off-by: Johannes Berg Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20210618133832.c989056c3664.Ic3b77531d00b30b26dcd69c64e55ae2f60c3f31e@changeid Signed-off-by: Johannes Berg --- net/wireless/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/wireless/Makefile b/net/wireless/Makefile index 2eee93985ab0..af590ae606b6 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -28,7 +28,7 @@ $(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.hex) @$(kecho) " GEN $@" @(echo '#include "reg.h"'; \ echo 'const u8 shipped_regdb_certs[] = {'; \ - cat $^ ; \ + echo | cat - $^ ; \ echo '};'; \ echo 'unsigned int shipped_regdb_certs_len = sizeof(shipped_regdb_certs);'; \ ) > $@ -- cgit v1.2.3 From 0288e5e16a2e18f0b7e61a2b70d9037fc6e4abeb Mon Sep 17 00:00:00 2001 From: Avraham Stern Date: Fri, 18 Jun 2021 13:41:31 +0300 Subject: cfg80211: avoid double free of PMSR request If cfg80211_pmsr_process_abort() moves all the PMSR requests that need to be freed into a local list before aborting and freeing them. As a result, it is possible that cfg80211_pmsr_complete() will run in parallel and free the same PMSR request. Fix it by freeing the request in cfg80211_pmsr_complete() only if it is still in the original pmsr list. Cc: stable@vger.kernel.org Fixes: 9bb7e0f24e7e ("cfg80211: add peer measurement with FTM initiator API") Signed-off-by: Avraham Stern Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20210618133832.1fbef57e269a.I00294bebdb0680b892f8d1d5c871fd9dbe785a5e@changeid Signed-off-by: Johannes Berg --- net/wireless/pmsr.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index 6bdd96408022..d245968b74cb 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -334,6 +334,7 @@ void cfg80211_pmsr_complete(struct wireless_dev *wdev, gfp_t gfp) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + struct cfg80211_pmsr_request *tmp, *prev, *to_free = NULL; struct sk_buff *msg; void *hdr; @@ -364,9 +365,20 @@ free_msg: nlmsg_free(msg); free_request: spin_lock_bh(&wdev->pmsr_lock); - list_del(&req->list); + /* + * cfg80211_pmsr_process_abort() may have already moved this request + * to the free list, and will free it later. In this case, don't free + * it here. + */ + list_for_each_entry_safe(tmp, prev, &wdev->pmsr_list, list) { + if (tmp == req) { + list_del(&req->list); + to_free = req; + break; + } + } spin_unlock_bh(&wdev->pmsr_lock); - kfree(req); + kfree(to_free); } EXPORT_SYMBOL_GPL(cfg80211_pmsr_complete); -- cgit v1.2.3 From bbc6f03ff26e7b71d6135a7b78ce40e7dee3d86a Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 18 Jun 2021 13:41:49 +0300 Subject: mac80211: reset profile_periodicity/ema_ap Apparently we never clear these values, so they'll remain set since the setting of them is conditional. Clear the values in the relevant other cases. Signed-off-by: Johannes Berg Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20210618133832.316e32d136a9.I2a12e51814258e1e1b526103894f4b9f19a91c8d@changeid Signed-off-by: Johannes Berg --- net/mac80211/mlme.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'net') diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 2480bd0577bb..3f2aad2e7436 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -4062,10 +4062,14 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, if (elems.mbssid_config_ie) bss_conf->profile_periodicity = elems.mbssid_config_ie->profile_periodicity; + else + bss_conf->profile_periodicity = 0; if (elems.ext_capab_len >= 11 && (elems.ext_capab[10] & WLAN_EXT_CAPA11_EMA_SUPPORT)) bss_conf->ema_ap = true; + else + bss_conf->ema_ap = false; /* continue assoc process */ ifmgd->assoc_data->timeout = jiffies; @@ -5802,12 +5806,16 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata, beacon_ies->data, beacon_ies->len); if (elem && elem->datalen >= 3) sdata->vif.bss_conf.profile_periodicity = elem->data[2]; + else + sdata->vif.bss_conf.profile_periodicity = 0; elem = cfg80211_find_elem(WLAN_EID_EXT_CAPABILITY, beacon_ies->data, beacon_ies->len); if (elem && elem->datalen >= 11 && (elem->data[10] & WLAN_EXT_CAPA11_EMA_SUPPORT)) sdata->vif.bss_conf.ema_ap = true; + else + sdata->vif.bss_conf.ema_ap = false; } else { assoc_data->timeout = jiffies; assoc_data->timeout_started = true; -- cgit v1.2.3 From 652e8363bbc7d149fa194a5cbf30b1001c0274b0 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Fri, 18 Jun 2021 13:41:45 +0300 Subject: mac80211: handle various extensible elements correctly Various elements are parsed with a requirement to have an exact size, when really we should only check that they have the minimum size that we need. Check only that and therefore ignore any additional data that they might carry. Signed-off-by: Johannes Berg Signed-off-by: Luca Coelho Link: https://lore.kernel.org/r/iwlwifi.20210618133832.cd101f8040a4.Iadf0e9b37b100c6c6e79c7b298cc657c2be9151a@changeid Signed-off-by: Johannes Berg --- net/mac80211/util.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'net') diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 93d96a4f9c3e..060059ef9668 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -947,7 +947,7 @@ static void ieee80211_parse_extension_element(u32 *crc, switch (elem->data[0]) { case WLAN_EID_EXT_HE_MU_EDCA: - if (len == sizeof(*elems->mu_edca_param_set)) { + if (len >= sizeof(*elems->mu_edca_param_set)) { elems->mu_edca_param_set = data; if (crc) *crc = crc32_be(*crc, (void *)elem, @@ -968,7 +968,7 @@ static void ieee80211_parse_extension_element(u32 *crc, } break; case WLAN_EID_EXT_UORA: - if (len == 1) + if (len >= 1) elems->uora_element = data; break; case WLAN_EID_EXT_MAX_CHANNEL_SWITCH_TIME: @@ -976,7 +976,7 @@ static void ieee80211_parse_extension_element(u32 *crc, elems->max_channel_switch_time = data; break; case WLAN_EID_EXT_MULTIPLE_BSSID_CONFIGURATION: - if (len == sizeof(*elems->mbssid_config_ie)) + if (len >= sizeof(*elems->mbssid_config_ie)) elems->mbssid_config_ie = data; break; case WLAN_EID_EXT_HE_SPR: @@ -985,7 +985,7 @@ static void ieee80211_parse_extension_element(u32 *crc, elems->he_spr = data; break; case WLAN_EID_EXT_HE_6GHZ_CAPA: - if (len == sizeof(*elems->he_6ghz_capa)) + if (len >= sizeof(*elems->he_6ghz_capa)) elems->he_6ghz_capa = data; break; } @@ -1074,14 +1074,14 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, switch (id) { case WLAN_EID_LINK_ID: - if (elen + 2 != sizeof(struct ieee80211_tdls_lnkie)) { + if (elen + 2 < sizeof(struct ieee80211_tdls_lnkie)) { elem_parse_failed = true; break; } elems->lnk_id = (void *)(pos - 2); break; case WLAN_EID_CHAN_SWITCH_TIMING: - if (elen != sizeof(struct ieee80211_ch_switch_timing)) { + if (elen < sizeof(struct ieee80211_ch_switch_timing)) { elem_parse_failed = true; break; } @@ -1244,7 +1244,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, elems->sec_chan_offs = (void *)pos; break; case WLAN_EID_CHAN_SWITCH_PARAM: - if (elen != + if (elen < sizeof(*elems->mesh_chansw_params_ie)) { elem_parse_failed = true; break; @@ -1253,7 +1253,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, break; case WLAN_EID_WIDE_BW_CHANNEL_SWITCH: if (!action || - elen != sizeof(*elems->wide_bw_chansw_ie)) { + elen < sizeof(*elems->wide_bw_chansw_ie)) { elem_parse_failed = true; break; } @@ -1272,7 +1272,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, ie = cfg80211_find_ie(WLAN_EID_WIDE_BW_CHANNEL_SWITCH, pos, elen); if (ie) { - if (ie[1] == sizeof(*elems->wide_bw_chansw_ie)) + if (ie[1] >= sizeof(*elems->wide_bw_chansw_ie)) elems->wide_bw_chansw_ie = (void *)(ie + 2); else @@ -1316,7 +1316,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, elems->cisco_dtpc_elem = pos; break; case WLAN_EID_ADDBA_EXT: - if (elen != sizeof(struct ieee80211_addba_ext_ie)) { + if (elen < sizeof(struct ieee80211_addba_ext_ie)) { elem_parse_failed = true; break; } @@ -1342,7 +1342,7 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, elem, elems); break; case WLAN_EID_S1G_CAPABILITIES: - if (elen == sizeof(*elems->s1g_capab)) + if (elen >= sizeof(*elems->s1g_capab)) elems->s1g_capab = (void *)pos; else elem_parse_failed = true; -- cgit v1.2.3 From 321827477360934dc040e9d3c626bf1de6c3ab3c Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Fri, 18 Jun 2021 13:04:35 +0200 Subject: icmp: don't send out ICMP messages with a source address of 0.0.0.0 When constructing ICMP response messages, the kernel will try to pick a suitable source address for the outgoing packet. However, if no IPv4 addresses are configured on the system at all, this will fail and we end up producing an ICMP message with a source address of 0.0.0.0. This can happen on a box routing IPv4 traffic via v6 nexthops, for instance. Since 0.0.0.0 is not generally routable on the internet, there's a good chance that such ICMP messages will never make it back to the sender of the original packet that the ICMP message was sent in response to. This, in turn, can create connectivity and PMTUd problems for senders. Fortunately, RFC7600 reserves a dummy address to be used as a source for ICMP messages (192.0.0.8/32), so let's teach the kernel to substitute that address as a last resort if the regular source address selection procedure fails. Below is a quick example reproducing this issue with network namespaces: ip netns add ns0 ip l add type veth peer netns ns0 ip l set dev veth0 up ip a add 10.0.0.1/24 dev veth0 ip a add fc00:dead:cafe:42::1/64 dev veth0 ip r add 10.1.0.0/24 via inet6 fc00:dead:cafe:42::2 ip -n ns0 l set dev veth0 up ip -n ns0 a add fc00:dead:cafe:42::2/64 dev veth0 ip -n ns0 r add 10.0.0.0/24 via inet6 fc00:dead:cafe:42::1 ip netns exec ns0 sysctl -w net.ipv4.icmp_ratelimit=0 ip netns exec ns0 sysctl -w net.ipv4.ip_forward=1 tcpdump -tpni veth0 -c 2 icmp & ping -w 1 10.1.0.1 > /dev/null tcpdump: verbose output suppressed, use -v[v]... for full protocol decode listening on veth0, link-type EN10MB (Ethernet), snapshot length 262144 bytes IP 10.0.0.1 > 10.1.0.1: ICMP echo request, id 29, seq 1, length 64 IP 0.0.0.0 > 10.0.0.1: ICMP net 10.1.0.1 unreachable, length 92 2 packets captured 2 packets received by filter 0 packets dropped by kernel With this patch the above capture changes to: IP 10.0.0.1 > 10.1.0.1: ICMP echo request, id 31127, seq 1, length 64 IP 192.0.0.8 > 10.0.0.1: ICMP net 10.1.0.1 unreachable, length 92 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: Juliusz Chroboczek Reviewed-by: David Ahern Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: David S. Miller --- include/uapi/linux/in.h | 3 +++ net/ipv4/icmp.c | 7 +++++++ 2 files changed, 10 insertions(+) (limited to 'net') diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index 7d6687618d80..d1b327036ae4 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -289,6 +289,9 @@ struct sockaddr_in { /* Address indicating an error return. */ #define INADDR_NONE ((unsigned long int) 0xffffffff) +/* Dummy address for src of ICMP replies if no real address is set (RFC7600). */ +#define INADDR_DUMMY ((unsigned long int) 0xc0000008) + /* Network number for local host loopback. */ #define IN_LOOPBACKNET 127 diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 7b6931a4d775..752e392083e6 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -759,6 +759,13 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, icmp_param.data_len = room; icmp_param.head_len = sizeof(struct icmphdr); + /* if we don't have a source address at this point, fall back to the + * dummy address instead of sending out a packet with a source address + * of 0.0.0.0 + */ + if (!fl4.saddr) + fl4.saddr = htonl(INADDR_DUMMY); + icmp_push_reply(&icmp_param, &fl4, &ipc, &rt); ende: ip_rt_put(rt); -- cgit v1.2.3