From: Xin Long lucien.xin@gmail.com
[ Upstream commit c7a42eb49212f93a800560662d17d5293960d3c3 ]
We need a similar fix for ipv6 as Commit 0761680d5215 ("net: ipv4: fix listify ip_rcv_finish in case of forwarding") does for ipv4.
This issue can be reprocuded by syzbot since Commit 323ebb61e32b ("net: use listified RX for handling GRO_NORMAL skbs") on net-next. The call trace was:
kernel BUG at include/linux/skbuff.h:2225! RIP: 0010:__skb_pull include/linux/skbuff.h:2225 [inline] RIP: 0010:skb_pull+0xea/0x110 net/core/skbuff.c:1902 Call Trace: sctp_inq_pop+0x2f1/0xd80 net/sctp/inqueue.c:202 sctp_endpoint_bh_rcv+0x184/0x8d0 net/sctp/endpointola.c:385 sctp_inq_push+0x1e4/0x280 net/sctp/inqueue.c:80 sctp_rcv+0x2807/0x3590 net/sctp/input.c:256 sctp6_rcv+0x17/0x30 net/sctp/ipv6.c:1049 ip6_protocol_deliver_rcu+0x2fe/0x1660 net/ipv6/ip6_input.c:397 ip6_input_finish+0x84/0x170 net/ipv6/ip6_input.c:438 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip6_input+0xe4/0x3f0 net/ipv6/ip6_input.c:447 dst_input include/net/dst.h:442 [inline] ip6_sublist_rcv_finish+0x98/0x1e0 net/ipv6/ip6_input.c:84 ip6_list_rcv_finish net/ipv6/ip6_input.c:118 [inline] ip6_sublist_rcv+0x80c/0xcf0 net/ipv6/ip6_input.c:282 ipv6_list_rcv+0x373/0x4b0 net/ipv6/ip6_input.c:316 __netif_receive_skb_list_ptype net/core/dev.c:5049 [inline] __netif_receive_skb_list_core+0x5fc/0x9d0 net/core/dev.c:5097 __netif_receive_skb_list net/core/dev.c:5149 [inline] netif_receive_skb_list_internal+0x7eb/0xe60 net/core/dev.c:5244 gro_normal_list.part.0+0x1e/0xb0 net/core/dev.c:5757 gro_normal_list net/core/dev.c:5755 [inline] gro_normal_one net/core/dev.c:5769 [inline] napi_frags_finish net/core/dev.c:5782 [inline] napi_gro_frags+0xa6a/0xea0 net/core/dev.c:5855 tun_get_user+0x2e98/0x3fa0 drivers/net/tun.c:1974 tun_chr_write_iter+0xbd/0x156 drivers/net/tun.c:2020
Fixes: d8269e2cbf90 ("net: ipv6: listify ipv6_rcv() and ip6_rcv_finish()") Fixes: 323ebb61e32b ("net: use listified RX for handling GRO_NORMAL skbs") Reported-by: syzbot+eb349eeee854e389c36d@syzkaller.appspotmail.com Reported-by: syzbot+4a0643a653ac375612d1@syzkaller.appspotmail.com Signed-off-by: Xin Long lucien.xin@gmail.com Acked-by: Edward Cree ecree@solarflare.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/ip6_input.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index a593aaf257483..2bb0b66181a74 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -80,8 +80,10 @@ static void ip6_sublist_rcv_finish(struct list_head *head) { struct sk_buff *skb, *next;
- list_for_each_entry_safe(skb, next, head, list) + list_for_each_entry_safe(skb, next, head, list) { + skb_list_del_init(skb); dst_input(skb); + } }
static void ip6_list_rcv_finish(struct net *net, struct sock *sk,
From: Eric Dumazet edumazet@google.com
[ Upstream commit 159d2c7d8106177bd9a986fd005a311fe0d11285 ]
qdisc_root() use from netem_enqueue() triggers a lockdep warning.
__dev_queue_xmit() uses rcu_read_lock_bh() which is not equivalent to rcu_read_lock() + local_bh_disable_bh as far as lockdep is concerned.
WARNING: suspicious RCU usage 5.3.0-rc7+ #0 Not tainted ----------------------------- include/net/sch_generic.h:492 suspicious rcu_dereference_check() usage!
other info that might help us debug this:
rcu_scheduler_active = 2, debug_locks = 1 3 locks held by syz-executor427/8855: #0: 00000000b5525c01 (rcu_read_lock_bh){....}, at: lwtunnel_xmit_redirect include/net/lwtunnel.h:92 [inline] #0: 00000000b5525c01 (rcu_read_lock_bh){....}, at: ip_finish_output2+0x2dc/0x2570 net/ipv4/ip_output.c:214 #1: 00000000b5525c01 (rcu_read_lock_bh){....}, at: __dev_queue_xmit+0x20a/0x3650 net/core/dev.c:3804 #2: 00000000364bae92 (&(&sch->q.lock)->rlock){+.-.}, at: spin_lock include/linux/spinlock.h:338 [inline] #2: 00000000364bae92 (&(&sch->q.lock)->rlock){+.-.}, at: __dev_xmit_skb net/core/dev.c:3502 [inline] #2: 00000000364bae92 (&(&sch->q.lock)->rlock){+.-.}, at: __dev_queue_xmit+0x14b8/0x3650 net/core/dev.c:3838
stack backtrace: CPU: 0 PID: 8855 Comm: syz-executor427 Not tainted 5.3.0-rc7+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x172/0x1f0 lib/dump_stack.c:113 lockdep_rcu_suspicious+0x153/0x15d kernel/locking/lockdep.c:5357 qdisc_root include/net/sch_generic.h:492 [inline] netem_enqueue+0x1cfb/0x2d80 net/sched/sch_netem.c:479 __dev_xmit_skb net/core/dev.c:3527 [inline] __dev_queue_xmit+0x15d2/0x3650 net/core/dev.c:3838 dev_queue_xmit+0x18/0x20 net/core/dev.c:3902 neigh_hh_output include/net/neighbour.h:500 [inline] neigh_output include/net/neighbour.h:509 [inline] ip_finish_output2+0x1726/0x2570 net/ipv4/ip_output.c:228 __ip_finish_output net/ipv4/ip_output.c:308 [inline] __ip_finish_output+0x5fc/0xb90 net/ipv4/ip_output.c:290 ip_finish_output+0x38/0x1f0 net/ipv4/ip_output.c:318 NF_HOOK_COND include/linux/netfilter.h:294 [inline] ip_mc_output+0x292/0xf40 net/ipv4/ip_output.c:417 dst_output include/net/dst.h:436 [inline] ip_local_out+0xbb/0x190 net/ipv4/ip_output.c:125 ip_send_skb+0x42/0xf0 net/ipv4/ip_output.c:1555 udp_send_skb.isra.0+0x6b2/0x1160 net/ipv4/udp.c:887 udp_sendmsg+0x1e96/0x2820 net/ipv4/udp.c:1174 inet_sendmsg+0x9e/0xe0 net/ipv4/af_inet.c:807 sock_sendmsg_nosec net/socket.c:637 [inline] sock_sendmsg+0xd7/0x130 net/socket.c:657 ___sys_sendmsg+0x3e2/0x920 net/socket.c:2311 __sys_sendmmsg+0x1bf/0x4d0 net/socket.c:2413 __do_sys_sendmmsg net/socket.c:2442 [inline] __se_sys_sendmmsg net/socket.c:2439 [inline] __x64_sys_sendmmsg+0x9d/0x100 net/socket.c:2439 do_syscall_64+0xfd/0x6a0 arch/x86/entry/common.c:296 entry_SYSCALL_64_after_hwframe+0x49/0xbe
Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/sch_generic.h | 5 +++++ net/sched/sch_netem.c | 2 +- 2 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 6b6b01234dd9d..58b1fbc884a7a 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -520,6 +520,11 @@ static inline struct Qdisc *qdisc_root(const struct Qdisc *qdisc) return q; }
+static inline struct Qdisc *qdisc_root_bh(const struct Qdisc *qdisc) +{ + return rcu_dereference_bh(qdisc->dev_queue->qdisc); +} + static inline struct Qdisc *qdisc_root_sleeping(const struct Qdisc *qdisc) { return qdisc->dev_queue->qdisc_sleeping; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index f5cb35e550f8d..0e44039e729c7 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -476,7 +476,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, * skb will be queued. */ if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) { - struct Qdisc *rootq = qdisc_root(sch); + struct Qdisc *rootq = qdisc_root_bh(sch); u32 dupsave = q->duplicate; /* prevent duplicating a dup... */
q->duplicate = 0;
From: Vlad Buslov vladbu@mellanox.com
[ Upstream commit e3ae1f96accd21405715fe9c56b4d83bc7d96d44 ]
Recent changes that removed rtnl dependency from rules update path of tc also made tcf_block_put() function sleeping. This function is called from ops->destroy() of several Qdisc implementations, which in turn is called by qdisc_put(). Some Qdiscs call qdisc_put() while holding sch tree spinlock, which results sleeping-while-atomic BUG.
Steps to reproduce for sfb:
tc qdisc add dev ens1f0 handle 1: root sfb tc qdisc add dev ens1f0 parent 1:10 handle 50: sfq perturb 10 tc qdisc change dev ens1f0 root handle 1: sfb
Resulting dmesg:
[ 7265.938717] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:909 [ 7265.940152] in_atomic(): 1, irqs_disabled(): 0, pid: 28579, name: tc [ 7265.941455] INFO: lockdep is turned off. [ 7265.942744] CPU: 11 PID: 28579 Comm: tc Tainted: G W 5.3.0-rc8+ #721 [ 7265.944065] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 7265.945396] Call Trace: [ 7265.946709] dump_stack+0x85/0xc0 [ 7265.947994] ___might_sleep.cold+0xac/0xbc [ 7265.949282] __mutex_lock+0x5b/0x960 [ 7265.950543] ? tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 7265.951803] ? tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 7265.953022] tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 7265.954248] tcf_block_put_ext.part.0+0x21/0x50 [ 7265.955478] tcf_block_put+0x50/0x70 [ 7265.956694] sfq_destroy+0x15/0x50 [sch_sfq] [ 7265.957898] qdisc_destroy+0x5f/0x160 [ 7265.959099] sfb_change+0x175/0x330 [sch_sfb] [ 7265.960304] tc_modify_qdisc+0x324/0x840 [ 7265.961503] rtnetlink_rcv_msg+0x170/0x4b0 [ 7265.962692] ? netlink_deliver_tap+0x95/0x400 [ 7265.963876] ? rtnl_dellink+0x2d0/0x2d0 [ 7265.965064] netlink_rcv_skb+0x49/0x110 [ 7265.966251] netlink_unicast+0x171/0x200 [ 7265.967427] netlink_sendmsg+0x224/0x3f0 [ 7265.968595] sock_sendmsg+0x5e/0x60 [ 7265.969753] ___sys_sendmsg+0x2ae/0x330 [ 7265.970916] ? ___sys_recvmsg+0x159/0x1f0 [ 7265.972074] ? do_wp_page+0x9c/0x790 [ 7265.973233] ? __handle_mm_fault+0xcd3/0x19e0 [ 7265.974407] __sys_sendmsg+0x59/0xa0 [ 7265.975591] do_syscall_64+0x5c/0xb0 [ 7265.976753] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 7265.977938] RIP: 0033:0x7f229069f7b8 [ 7265.979117] Code: 89 02 48 c7 c0 ff ff ff ff eb bb 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 8d 05 65 8f 0c 00 8b 00 85 c0 75 17 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 58 c3 0f 1f 80 00 00 00 00 48 83 ec 28 89 5 4 [ 7265.981681] RSP: 002b:00007ffd7ed2d158 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 7265.983001] RAX: ffffffffffffffda RBX: 000000005d813ca1 RCX: 00007f229069f7b8 [ 7265.984336] RDX: 0000000000000000 RSI: 00007ffd7ed2d1c0 RDI: 0000000000000003 [ 7265.985682] RBP: 0000000000000000 R08: 0000000000000001 R09: 000000000165c9a0 [ 7265.987021] R10: 0000000000404eda R11: 0000000000000246 R12: 0000000000000001 [ 7265.988309] R13: 000000000047f640 R14: 0000000000000000 R15: 0000000000000000
In sfb_change() function use qdisc_purge_queue() instead of qdisc_tree_flush_backlog() to properly reset old child Qdisc and save pointer to it into local temporary variable. Put reference to Qdisc after sch tree lock is released in order not to call potentially sleeping cls API in atomic section. This is safe to do because Qdisc has already been reset by qdisc_purge_queue() inside sch tree lock critical section.
Reported-by: syzbot+ac54455281db908c581e@syzkaller.appspotmail.com Fixes: c266f64dbfa2 ("net: sched: protect block state with mutex") Suggested-by: Cong Wang xiyou.wangcong@gmail.com Signed-off-by: Vlad Buslov vladbu@mellanox.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/sch_sfb.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 1dff8506a7155..d448fe3068e5b 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -488,7 +488,7 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct sfb_sched_data *q = qdisc_priv(sch); - struct Qdisc *child; + struct Qdisc *child, *old; struct nlattr *tb[TCA_SFB_MAX + 1]; const struct tc_sfb_qopt *ctl = &sfb_default_ops; u32 limit; @@ -518,8 +518,8 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt, qdisc_hash_add(child, true); sch_tree_lock(sch);
- qdisc_tree_flush_backlog(q->qdisc); - qdisc_put(q->qdisc); + qdisc_purge_queue(q->qdisc); + old = q->qdisc; q->qdisc = child;
q->rehash_interval = msecs_to_jiffies(ctl->rehash_interval); @@ -542,6 +542,7 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt, sfb_init_perturbation(1, q);
sch_tree_unlock(sch); + qdisc_put(old);
return 0; }
From: David Howells dhowells@redhat.com
[ Upstream commit c48fc11b69e95007109206311b0187a3090591f3 ]
When sendmsg() finds a call to continue on with, if the call is in an inappropriate state, it doesn't release the ref it just got on that call before returning an error.
This causes the following symptom to show up with kasan:
BUG: KASAN: use-after-free in rxrpc_send_keepalive+0x8a2/0x940 net/rxrpc/output.c:635 Read of size 8 at addr ffff888064219698 by task kworker/0:3/11077
where line 635 is:
whdr.epoch = htonl(peer->local->rxnet->epoch);
The local endpoint (which cannot be pinned by the call) has been released, but not the peer (which is pinned by the call).
Fix this by releasing the call in the error path.
Fixes: 37411cad633f ("rxrpc: Fix potential NULL-pointer exception") Reported-by: syzbot+d850c266e3df14da1d31@syzkaller.appspotmail.com Signed-off-by: David Howells dhowells@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/rxrpc/sendmsg.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 6a1547b270fef..22f51a7e356ee 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -661,6 +661,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) case RXRPC_CALL_SERVER_PREALLOC: case RXRPC_CALL_SERVER_SECURING: case RXRPC_CALL_SERVER_ACCEPTING: + rxrpc_put_call(call, rxrpc_call_put); ret = -EBUSY; goto error_release_sock; default:
From: David Howells dhowells@redhat.com
[ Upstream commit 55f6c98e3674ce16038a1949c3f9ca5a9a99f289 ]
rxrpc_put_peer() calls trace_rxrpc_peer() after it has done the decrement of the refcount - which looks at the debug_id in the peer record. But unless the refcount was reduced to zero, we no longer have the right to look in the record and, indeed, it may be deleted by some other thread.
Fix this by getting the debug_id out before decrementing the refcount and then passing that into the tracepoint.
This can cause the following symptoms:
BUG: KASAN: use-after-free in __rxrpc_put_peer net/rxrpc/peer_object.c:411 [inline] BUG: KASAN: use-after-free in rxrpc_put_peer+0x685/0x6a0 net/rxrpc/peer_object.c:435 Read of size 8 at addr ffff888097ec0058 by task syz-executor823/24216
Fixes: 1159d4b496f5 ("rxrpc: Add a tracepoint to track rxrpc_peer refcounting") Reported-by: syzbot+b9be979c55f2bea8ed30@syzkaller.appspotmail.com Signed-off-by: David Howells dhowells@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/trace/events/rxrpc.h | 6 +++--- net/rxrpc/peer_object.c | 11 +++++++---- 2 files changed, 10 insertions(+), 7 deletions(-)
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index edc5c887a44c8..45556fe771c36 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -519,10 +519,10 @@ TRACE_EVENT(rxrpc_local, );
TRACE_EVENT(rxrpc_peer, - TP_PROTO(struct rxrpc_peer *peer, enum rxrpc_peer_trace op, + TP_PROTO(unsigned int peer_debug_id, enum rxrpc_peer_trace op, int usage, const void *where),
- TP_ARGS(peer, op, usage, where), + TP_ARGS(peer_debug_id, op, usage, where),
TP_STRUCT__entry( __field(unsigned int, peer ) @@ -532,7 +532,7 @@ TRACE_EVENT(rxrpc_peer, ),
TP_fast_assign( - __entry->peer = peer->debug_id; + __entry->peer = peer_debug_id; __entry->op = op; __entry->usage = usage; __entry->where = where; diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 9c3ac96f71cbf..b700b7ecaa3d8 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -382,7 +382,7 @@ struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *peer) int n;
n = atomic_inc_return(&peer->usage); - trace_rxrpc_peer(peer, rxrpc_peer_got, n, here); + trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, n, here); return peer; }
@@ -396,7 +396,7 @@ struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer) if (peer) { int n = atomic_fetch_add_unless(&peer->usage, 1, 0); if (n > 0) - trace_rxrpc_peer(peer, rxrpc_peer_got, n + 1, here); + trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, n + 1, here); else peer = NULL; } @@ -426,11 +426,13 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer) void rxrpc_put_peer(struct rxrpc_peer *peer) { const void *here = __builtin_return_address(0); + unsigned int debug_id; int n;
if (peer) { + debug_id = peer->debug_id; n = atomic_dec_return(&peer->usage); - trace_rxrpc_peer(peer, rxrpc_peer_put, n, here); + trace_rxrpc_peer(debug_id, rxrpc_peer_put, n, here); if (n == 0) __rxrpc_put_peer(peer); } @@ -443,10 +445,11 @@ void rxrpc_put_peer(struct rxrpc_peer *peer) void rxrpc_put_peer_locked(struct rxrpc_peer *peer) { const void *here = __builtin_return_address(0); + unsigned int debug_id = peer->debug_id; int n;
n = atomic_dec_return(&peer->usage); - trace_rxrpc_peer(peer, rxrpc_peer_put, n, here); + trace_rxrpc_peer(debug_id, rxrpc_peer_put, n, here); if (n == 0) { hash_del_rcu(&peer->hash_link); list_del_init(&peer->keepalive_link);
From: David Howells dhowells@redhat.com
[ Upstream commit 9ebeddef58c41bd700419cdcece24cf64ce32276 ]
The rxrpc_peer record needs to hold a reference on the rxrpc_local record it points as the peer is used as a base to access information in the rxrpc_local record.
This can cause problems in __rxrpc_put_peer(), where we need the network namespace pointer, and in rxrpc_send_keepalive(), where we need to access the UDP socket, leading to symptoms like:
BUG: KASAN: use-after-free in __rxrpc_put_peer net/rxrpc/peer_object.c:411 [inline] BUG: KASAN: use-after-free in rxrpc_put_peer+0x685/0x6a0 net/rxrpc/peer_object.c:435 Read of size 8 at addr ffff888097ec0058 by task syz-executor823/24216
Fix this by taking a ref on the local record for the peer record.
Fixes: ace45bec6d77 ("rxrpc: Fix firewall route keepalive") Fixes: 2baec2c3f854 ("rxrpc: Support network namespacing") Reported-by: syzbot+b9be979c55f2bea8ed30@syzkaller.appspotmail.com Signed-off-by: David Howells dhowells@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/rxrpc/peer_object.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index b700b7ecaa3d8..64830d8c1fdb5 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -216,7 +216,7 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) peer = kzalloc(sizeof(struct rxrpc_peer), gfp); if (peer) { atomic_set(&peer->usage, 1); - peer->local = local; + peer->local = rxrpc_get_local(local); INIT_HLIST_HEAD(&peer->error_targets); peer->service_conns = RB_ROOT; seqlock_init(&peer->service_conn_lock); @@ -307,7 +307,6 @@ void rxrpc_new_incoming_peer(struct rxrpc_sock *rx, struct rxrpc_local *local, unsigned long hash_key;
hash_key = rxrpc_peer_hash_key(local, &peer->srx); - peer->local = local; rxrpc_init_peer(rx, peer, hash_key);
spin_lock(&rxnet->peer_hash_lock); @@ -417,6 +416,7 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer) list_del_init(&peer->keepalive_link); spin_unlock_bh(&rxnet->peer_hash_lock);
+ rxrpc_put_local(peer->local); kfree_rcu(peer, rcu); }
@@ -453,6 +453,7 @@ void rxrpc_put_peer_locked(struct rxrpc_peer *peer) if (n == 0) { hash_del_rcu(&peer->hash_link); list_del_init(&peer->keepalive_link); + rxrpc_put_local(peer->local); kfree_rcu(peer, rcu); } }
From: Eric Biggers ebiggers@google.com
[ Upstream commit c6ee11c39fcc1fb55130748990a8f199e76263b4 ]
syzbot reported:
BUG: memory leak unreferenced object 0xffff888116270800 (size 224): comm "syz-executor641", pid 7047, jiffies 4294947360 (age 13.860s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 20 e1 2a 81 88 ff ff 00 40 3d 2a 81 88 ff ff . .*.....@=*.... backtrace: [<000000004d41b4cc>] kmemleak_alloc_recursive include/linux/kmemleak.h:55 [inline] [<000000004d41b4cc>] slab_post_alloc_hook mm/slab.h:439 [inline] [<000000004d41b4cc>] slab_alloc_node mm/slab.c:3269 [inline] [<000000004d41b4cc>] kmem_cache_alloc_node+0x153/0x2a0 mm/slab.c:3579 [<00000000506a5965>] __alloc_skb+0x6e/0x210 net/core/skbuff.c:198 [<000000001ba5a161>] alloc_skb include/linux/skbuff.h:1058 [inline] [<000000001ba5a161>] alloc_skb_with_frags+0x5f/0x250 net/core/skbuff.c:5327 [<0000000047d9c78b>] sock_alloc_send_pskb+0x269/0x2a0 net/core/sock.c:2225 [<000000003828fe54>] sock_alloc_send_skb+0x32/0x40 net/core/sock.c:2242 [<00000000e34d94f9>] llc_ui_sendmsg+0x10a/0x540 net/llc/af_llc.c:933 [<00000000de2de3fb>] sock_sendmsg_nosec net/socket.c:652 [inline] [<00000000de2de3fb>] sock_sendmsg+0x54/0x70 net/socket.c:671 [<000000008fe16e7a>] __sys_sendto+0x148/0x1f0 net/socket.c:1964 [...]
The bug is that llc_sap_state_process() always takes an extra reference to the skb, but sometimes neither llc_sap_next_state() nor llc_sap_state_process() itself drops this reference.
Fix it by changing llc_sap_next_state() to never consume a reference to the skb, rather than sometimes do so and sometimes not. Then remove the extra skb_get() and kfree_skb() from llc_sap_state_process().
Reported-by: syzbot+6bf095f9becf5efef645@syzkaller.appspotmail.com Reported-by: syzbot+31c16aa4202dace3812e@syzkaller.appspotmail.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Biggers ebiggers@google.com Signed-off-by: Jakub Kicinski jakub.kicinski@netronome.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/llc/llc_s_ac.c | 12 +++++++++--- net/llc/llc_sap.c | 23 ++++++++--------------- 2 files changed, 17 insertions(+), 18 deletions(-)
diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c index a94bd56bcac6f..7ae4cc684d3ab 100644 --- a/net/llc/llc_s_ac.c +++ b/net/llc/llc_s_ac.c @@ -58,8 +58,10 @@ int llc_sap_action_send_ui(struct llc_sap *sap, struct sk_buff *skb) ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_ui_cmd(skb); rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); - if (likely(!rc)) + if (likely(!rc)) { + skb_get(skb); rc = dev_queue_xmit(skb); + } return rc; }
@@ -81,8 +83,10 @@ int llc_sap_action_send_xid_c(struct llc_sap *sap, struct sk_buff *skb) ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_xid_cmd(skb, LLC_XID_NULL_CLASS_2, 0); rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); - if (likely(!rc)) + if (likely(!rc)) { + skb_get(skb); rc = dev_queue_xmit(skb); + } return rc; }
@@ -135,8 +139,10 @@ int llc_sap_action_send_test_c(struct llc_sap *sap, struct sk_buff *skb) ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_test_cmd(skb); rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); - if (likely(!rc)) + if (likely(!rc)) { + skb_get(skb); rc = dev_queue_xmit(skb); + } return rc; }
diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index a7f7b8ff47292..be419062e19a6 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -197,29 +197,22 @@ static int llc_sap_next_state(struct llc_sap *sap, struct sk_buff *skb) * After executing actions of the event, upper layer will be indicated * if needed(on receiving an UI frame). sk can be null for the * datalink_proto case. + * + * This function always consumes a reference to the skb. */ static void llc_sap_state_process(struct llc_sap *sap, struct sk_buff *skb) { struct llc_sap_state_ev *ev = llc_sap_ev(skb);
- /* - * We have to hold the skb, because llc_sap_next_state - * will kfree it in the sending path and we need to - * look at the skb->cb, where we encode llc_sap_state_ev. - */ - skb_get(skb); ev->ind_cfm_flag = 0; llc_sap_next_state(sap, skb); - if (ev->ind_cfm_flag == LLC_IND) { - if (skb->sk->sk_state == TCP_LISTEN) - kfree_skb(skb); - else { - llc_save_primitive(skb->sk, skb, ev->prim);
- /* queue skb to the user. */ - if (sock_queue_rcv_skb(skb->sk, skb)) - kfree_skb(skb); - } + if (ev->ind_cfm_flag == LLC_IND && skb->sk->sk_state != TCP_LISTEN) { + llc_save_primitive(skb->sk, skb, ev->prim); + + /* queue skb to the user. */ + if (sock_queue_rcv_skb(skb->sk, skb) == 0) + return; } kfree_skb(skb); }
From: Eric Biggers ebiggers@google.com
[ Upstream commit b74555de21acd791f12c4a1aeaf653dd7ac21133 ]
syzbot reported:
BUG: memory leak unreferenced object 0xffff88811eb3de00 (size 224): comm "syz-executor559", pid 7315, jiffies 4294943019 (age 10.300s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 a0 38 24 81 88 ff ff 00 c0 f2 15 81 88 ff ff ..8$............ backtrace: [<000000008d1c66a1>] kmemleak_alloc_recursive include/linux/kmemleak.h:55 [inline] [<000000008d1c66a1>] slab_post_alloc_hook mm/slab.h:439 [inline] [<000000008d1c66a1>] slab_alloc_node mm/slab.c:3269 [inline] [<000000008d1c66a1>] kmem_cache_alloc_node+0x153/0x2a0 mm/slab.c:3579 [<00000000447d9496>] __alloc_skb+0x6e/0x210 net/core/skbuff.c:198 [<000000000cdbf82f>] alloc_skb include/linux/skbuff.h:1058 [inline] [<000000000cdbf82f>] llc_alloc_frame+0x66/0x110 net/llc/llc_sap.c:54 [<000000002418b52e>] llc_conn_ac_send_sabme_cmd_p_set_x+0x2f/0x140 net/llc/llc_c_ac.c:777 [<000000001372ae17>] llc_exec_conn_trans_actions net/llc/llc_conn.c:475 [inline] [<000000001372ae17>] llc_conn_service net/llc/llc_conn.c:400 [inline] [<000000001372ae17>] llc_conn_state_process+0x1ac/0x640 net/llc/llc_conn.c:75 [<00000000f27e53c1>] llc_establish_connection+0x110/0x170 net/llc/llc_if.c:109 [<00000000291b2ca0>] llc_ui_connect+0x10e/0x370 net/llc/af_llc.c:477 [<000000000f9c740b>] __sys_connect+0x11d/0x170 net/socket.c:1840 [...]
The bug is that most callers of llc_conn_send_pdu() assume it consumes a reference to the skb, when actually due to commit b85ab56c3f81 ("llc: properly handle dev_queue_xmit() return value") it doesn't.
Revert most of that commit, and instead make the few places that need llc_conn_send_pdu() to *not* consume a reference call skb_get() before.
Fixes: b85ab56c3f81 ("llc: properly handle dev_queue_xmit() return value") Reported-by: syzbot+6b825a6494a04cc0e3f7@syzkaller.appspotmail.com Signed-off-by: Eric Biggers ebiggers@google.com Signed-off-by: Jakub Kicinski jakub.kicinski@netronome.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/llc_conn.h | 2 +- net/llc/llc_c_ac.c | 8 ++++++-- net/llc/llc_conn.c | 32 +++++++++----------------------- 3 files changed, 16 insertions(+), 26 deletions(-)
diff --git a/include/net/llc_conn.h b/include/net/llc_conn.h index df528a6235487..ea985aa7a6c5e 100644 --- a/include/net/llc_conn.h +++ b/include/net/llc_conn.h @@ -104,7 +104,7 @@ void llc_sk_reset(struct sock *sk);
/* Access to a connection */ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb); -int llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb); +void llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb); void llc_conn_rtn_pdu(struct sock *sk, struct sk_buff *skb); void llc_conn_resend_i_pdu_as_cmd(struct sock *sk, u8 nr, u8 first_p_bit); void llc_conn_resend_i_pdu_as_rsp(struct sock *sk, u8 nr, u8 first_f_bit); diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c index 4d78375f9872d..647c0554d04cd 100644 --- a/net/llc/llc_c_ac.c +++ b/net/llc/llc_c_ac.c @@ -372,6 +372,7 @@ int llc_conn_ac_send_i_cmd_p_set_1(struct sock *sk, struct sk_buff *skb) llc_pdu_init_as_i_cmd(skb, 1, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { + skb_get(skb); llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } @@ -389,7 +390,8 @@ static int llc_conn_ac_send_i_cmd_p_set_0(struct sock *sk, struct sk_buff *skb) llc_pdu_init_as_i_cmd(skb, 0, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { - rc = llc_conn_send_pdu(sk, skb); + skb_get(skb); + llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } return rc; @@ -406,6 +408,7 @@ int llc_conn_ac_send_i_xxx_x_set_0(struct sock *sk, struct sk_buff *skb) llc_pdu_init_as_i_cmd(skb, 0, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { + skb_get(skb); llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } @@ -916,7 +919,8 @@ static int llc_conn_ac_send_i_rsp_f_set_ackpf(struct sock *sk, llc_pdu_init_as_i_cmd(skb, llc->ack_pf, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { - rc = llc_conn_send_pdu(sk, skb); + skb_get(skb); + llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } return rc; diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 4ff89cb7c86f7..ed2aca12460ca 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -30,7 +30,7 @@ #endif
static int llc_find_offset(int state, int ev_type); -static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *skb); +static void llc_conn_send_pdus(struct sock *sk); static int llc_conn_service(struct sock *sk, struct sk_buff *skb); static int llc_exec_conn_trans_actions(struct sock *sk, struct llc_conn_state_trans *trans, @@ -193,11 +193,11 @@ int llc_conn_state_process(struct sock *sk, struct sk_buff *skb) return rc; }
-int llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb) +void llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb) { /* queue PDU to send to MAC layer */ skb_queue_tail(&sk->sk_write_queue, skb); - return llc_conn_send_pdus(sk, skb); + llc_conn_send_pdus(sk); }
/** @@ -255,7 +255,7 @@ void llc_conn_resend_i_pdu_as_cmd(struct sock *sk, u8 nr, u8 first_p_bit) if (howmany_resend > 0) llc->vS = (llc->vS + 1) % LLC_2_SEQ_NBR_MODULO; /* any PDUs to re-send are queued up; start sending to MAC */ - llc_conn_send_pdus(sk, NULL); + llc_conn_send_pdus(sk); out:; }
@@ -296,7 +296,7 @@ void llc_conn_resend_i_pdu_as_rsp(struct sock *sk, u8 nr, u8 first_f_bit) if (howmany_resend > 0) llc->vS = (llc->vS + 1) % LLC_2_SEQ_NBR_MODULO; /* any PDUs to re-send are queued up; start sending to MAC */ - llc_conn_send_pdus(sk, NULL); + llc_conn_send_pdus(sk); out:; }
@@ -340,16 +340,12 @@ int llc_conn_remove_acked_pdus(struct sock *sk, u8 nr, u16 *how_many_unacked) /** * llc_conn_send_pdus - Sends queued PDUs * @sk: active connection - * @hold_skb: the skb held by caller, or NULL if does not care * - * Sends queued pdus to MAC layer for transmission. When @hold_skb is - * NULL, always return 0. Otherwise, return 0 if @hold_skb is sent - * successfully, or 1 for failure. + * Sends queued pdus to MAC layer for transmission. */ -static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *hold_skb) +static void llc_conn_send_pdus(struct sock *sk) { struct sk_buff *skb; - int ret = 0;
while ((skb = skb_dequeue(&sk->sk_write_queue)) != NULL) { struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); @@ -361,20 +357,10 @@ static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *hold_skb) skb_queue_tail(&llc_sk(sk)->pdu_unack_q, skb); if (!skb2) break; - dev_queue_xmit(skb2); - } else { - bool is_target = skb == hold_skb; - int rc; - - if (is_target) - skb_get(skb); - rc = dev_queue_xmit(skb); - if (is_target) - ret = rc; + skb = skb2; } + dev_queue_xmit(skb); } - - return ret; }
/**
From: Johan Hovold johan@kernel.org
[ Upstream commit 6af3aa57a0984e061f61308fe181a9a12359fecc ]
The driver would fail to deregister and its class device and free related resources on late probe errors.
Reported-by: syzbot+cb035c75c03dbe34b796@syzkaller.appspotmail.com Fixes: 32ecc75ded72 ("NFC: pn533: change order operations in dev registation") Signed-off-by: Johan Hovold johan@kernel.org Signed-off-by: Jakub Kicinski jakub.kicinski@netronome.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nfc/pn533/usb.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c index c5289eaf17eef..e897e4d768ef7 100644 --- a/drivers/nfc/pn533/usb.c +++ b/drivers/nfc/pn533/usb.c @@ -547,18 +547,25 @@ static int pn533_usb_probe(struct usb_interface *interface,
rc = pn533_finalize_setup(priv); if (rc) - goto error; + goto err_deregister;
usb_set_intfdata(interface, phy);
return 0;
+err_deregister: + pn533_unregister_device(phy->priv); error: + usb_kill_urb(phy->in_urb); + usb_kill_urb(phy->out_urb); + usb_kill_urb(phy->ack_urb); + usb_free_urb(phy->in_urb); usb_free_urb(phy->out_urb); usb_free_urb(phy->ack_urb); usb_put_dev(phy->udev); kfree(in_buf); + kfree(phy->ack_buffer);
return rc; }
From: Eric Dumazet edumazet@google.com
[ Upstream commit a7137534b597b7c303203e6bc3ed87e87a273bb8 ]
syzbot got a NULL dereference in bond_update_slave_arr() [1], happening after a failure to allocate bond->slave_arr
A workqueue (bond_slave_arr_handler) is supposed to retry the allocation later, but if the slave is removed before the workqueue had a chance to complete, bond->slave_arr can still be NULL.
[1]
Failed to build slave-array. kasan: CONFIG_KASAN_INLINE enabled kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] SMP KASAN PTI Modules linked in: Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:bond_update_slave_arr.cold+0xc6/0x198 drivers/net/bonding/bond_main.c:4039 RSP: 0018:ffff88018fe33678 EFLAGS: 00010246 RAX: dffffc0000000000 RBX: 0000000000000000 RCX: ffffc9000290b000 RDX: 0000000000000000 RSI: ffffffff82b63037 RDI: ffff88019745ea20 RBP: ffff88018fe33760 R08: ffff880170754280 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 R13: ffff88019745ea00 R14: 0000000000000000 R15: ffff88018fe338b0 FS: 00007febd837d700(0000) GS:ffff8801dad00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000004540a0 CR3: 00000001c242e005 CR4: 00000000001626f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: [<ffffffff82b5b45e>] __bond_release_one+0x43e/0x500 drivers/net/bonding/bond_main.c:1923 [<ffffffff82b5b966>] bond_release drivers/net/bonding/bond_main.c:2039 [inline] [<ffffffff82b5b966>] bond_do_ioctl+0x416/0x870 drivers/net/bonding/bond_main.c:3562 [<ffffffff83ae25f4>] dev_ifsioc+0x6f4/0x940 net/core/dev_ioctl.c:328 [<ffffffff83ae2e58>] dev_ioctl+0x1b8/0xc70 net/core/dev_ioctl.c:495 [<ffffffff83995ffd>] sock_do_ioctl+0x1bd/0x300 net/socket.c:1088 [<ffffffff83996a80>] sock_ioctl+0x300/0x5d0 net/socket.c:1196 [<ffffffff81b124db>] vfs_ioctl fs/ioctl.c:47 [inline] [<ffffffff81b124db>] file_ioctl fs/ioctl.c:501 [inline] [<ffffffff81b124db>] do_vfs_ioctl+0xacb/0x1300 fs/ioctl.c:688 [<ffffffff81b12dc6>] SYSC_ioctl fs/ioctl.c:705 [inline] [<ffffffff81b12dc6>] SyS_ioctl+0xb6/0xe0 fs/ioctl.c:696 [<ffffffff8101ccc8>] do_syscall_64+0x528/0x770 arch/x86/entry/common.c:305 [<ffffffff84400091>] entry_SYSCALL_64_after_hwframe+0x42/0xb7
Fixes: ee6377147409 ("bonding: Simplify the xmit function for modes that use xmit_hash") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Cc: Mahesh Bandewar maheshb@google.com Signed-off-by: Jakub Kicinski jakub.kicinski@netronome.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/bonding/bond_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 931d9d9356869..21d8fcc83c9ce 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4039,7 +4039,7 @@ int bond_update_slave_arr(struct bonding *bond, struct slave *skipslave) * this to-be-skipped slave to send a packet out. */ old_arr = rtnl_dereference(bond->slave_arr); - for (idx = 0; idx < old_arr->count; idx++) { + for (idx = 0; old_arr != NULL && idx < old_arr->count; idx++) { if (skipslave == old_arr->arr[idx]) { old_arr->arr[idx] = old_arr->arr[old_arr->count-1];
From: Eric Dumazet edumazet@google.com
[ Upstream commit e37542ba111f3974dc622ae0a21c1787318de500 ]
As hinted by KCSAN, we need at least one READ_ONCE() to prevent a compiler optimization.
More details on : https://github.com/google/ktsan/wiki/READ_ONCE-and-WRITE_ONCE#it-may-improve...
sysbot report : BUG: KCSAN: data-race in __nf_ct_refresh_acct / __nf_ct_refresh_acct
read to 0xffff888123eb4f08 of 4 bytes by interrupt on cpu 0: __nf_ct_refresh_acct+0xd4/0x1b0 net/netfilter/nf_conntrack_core.c:1796 nf_ct_refresh_acct include/net/netfilter/nf_conntrack.h:201 [inline] nf_conntrack_tcp_packet+0xd40/0x3390 net/netfilter/nf_conntrack_proto_tcp.c:1161 nf_conntrack_handle_packet net/netfilter/nf_conntrack_core.c:1633 [inline] nf_conntrack_in+0x410/0xaa0 net/netfilter/nf_conntrack_core.c:1727 ipv4_conntrack_in+0x27/0x40 net/netfilter/nf_conntrack_proto.c:178 nf_hook_entry_hookfn include/linux/netfilter.h:135 [inline] nf_hook_slow+0x83/0x160 net/netfilter/core.c:512 nf_hook include/linux/netfilter.h:260 [inline] NF_HOOK include/linux/netfilter.h:303 [inline] ip_rcv+0x12f/0x1a0 net/ipv4/ip_input.c:523 __netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:5004 __netif_receive_skb+0x37/0xf0 net/core/dev.c:5118 netif_receive_skb_internal+0x59/0x190 net/core/dev.c:5208 napi_skb_finish net/core/dev.c:5671 [inline] napi_gro_receive+0x28f/0x330 net/core/dev.c:5704 receive_buf+0x284/0x30b0 drivers/net/virtio_net.c:1061 virtnet_receive drivers/net/virtio_net.c:1323 [inline] virtnet_poll+0x436/0x7d0 drivers/net/virtio_net.c:1428 napi_poll net/core/dev.c:6352 [inline] net_rx_action+0x3ae/0xa50 net/core/dev.c:6418 __do_softirq+0x115/0x33f kernel/softirq.c:292
write to 0xffff888123eb4f08 of 4 bytes by task 7191 on cpu 1: __nf_ct_refresh_acct+0xfb/0x1b0 net/netfilter/nf_conntrack_core.c:1797 nf_ct_refresh_acct include/net/netfilter/nf_conntrack.h:201 [inline] nf_conntrack_tcp_packet+0xd40/0x3390 net/netfilter/nf_conntrack_proto_tcp.c:1161 nf_conntrack_handle_packet net/netfilter/nf_conntrack_core.c:1633 [inline] nf_conntrack_in+0x410/0xaa0 net/netfilter/nf_conntrack_core.c:1727 ipv4_conntrack_local+0xbe/0x130 net/netfilter/nf_conntrack_proto.c:200 nf_hook_entry_hookfn include/linux/netfilter.h:135 [inline] nf_hook_slow+0x83/0x160 net/netfilter/core.c:512 nf_hook include/linux/netfilter.h:260 [inline] __ip_local_out+0x1f7/0x2b0 net/ipv4/ip_output.c:114 ip_local_out+0x31/0x90 net/ipv4/ip_output.c:123 __ip_queue_xmit+0x3a8/0xa40 net/ipv4/ip_output.c:532 ip_queue_xmit+0x45/0x60 include/net/ip.h:236 __tcp_transmit_skb+0xdeb/0x1cd0 net/ipv4/tcp_output.c:1158 __tcp_send_ack+0x246/0x300 net/ipv4/tcp_output.c:3685 tcp_send_ack+0x34/0x40 net/ipv4/tcp_output.c:3691 tcp_cleanup_rbuf+0x130/0x360 net/ipv4/tcp.c:1575
Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 7191 Comm: syz-fuzzer Not tainted 5.3.0+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Fixes: cc16921351d8 ("netfilter: conntrack: avoid same-timeout update") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Cc: Jozsef Kadlecsik kadlec@netfilter.org Cc: Florian Westphal fw@strlen.de Acked-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Jakub Kicinski jakub.kicinski@netronome.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_conntrack_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 81a8ef42b88d3..56b1cf82ed3aa 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1793,8 +1793,8 @@ void __nf_ct_refresh_acct(struct nf_conn *ct, if (nf_ct_is_confirmed(ct)) extra_jiffies += nfct_time_stamp;
- if (ct->timeout != extra_jiffies) - ct->timeout = extra_jiffies; + if (READ_ONCE(ct->timeout) != extra_jiffies) + WRITE_ONCE(ct->timeout, extra_jiffies); acct: if (do_acct) nf_ct_acct_update(ct, ctinfo, skb->len);
From: Mahesh Bandewar maheshb@google.com
[ Upstream commit b0818f80c8c1bc215bba276bd61c216014fab23b ]
While invalidating the dst, we assign backhole_netdev instead of loopback device. However, this device does not have idev pointer and hence no ip6_ptr even if IPv6 is enabled. Possibly this has triggered the syzbot reported crash.
The syzbot report does not have reproducer, however, this is the only device that doesn't have matching idev created.
Crash instruction is :
static inline bool ip6_ignore_linkdown(const struct net_device *dev) { const struct inet6_dev *idev = __in6_dev_get(dev);
return !!idev->cnf.ignore_routes_with_linkdown; <= crash }
Also ipv6 always assumes presence of idev and never checks for it being NULL (as does the above referenced code). So adding a idev for the blackhole_netdev to avoid this class of crashes in the future.
Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/addrconf.c | 7 ++++++- net/ipv6/route.c | 15 ++++++--------- 2 files changed, 12 insertions(+), 10 deletions(-)
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 34ccef18b40e6..4c87594d1389d 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -6996,7 +6996,7 @@ static struct rtnl_af_ops inet6_ops __read_mostly = {
int __init addrconf_init(void) { - struct inet6_dev *idev; + struct inet6_dev *idev, *bdev; int i, err;
err = ipv6_addr_label_init(); @@ -7036,10 +7036,14 @@ int __init addrconf_init(void) */ rtnl_lock(); idev = ipv6_add_dev(init_net.loopback_dev); + bdev = ipv6_add_dev(blackhole_netdev); rtnl_unlock(); if (IS_ERR(idev)) { err = PTR_ERR(idev); goto errlo; + } else if (IS_ERR(bdev)) { + err = PTR_ERR(bdev); + goto errlo; }
ip6_route_init_special_entries(); @@ -7124,6 +7128,7 @@ void addrconf_cleanup(void) addrconf_ifdown(dev, 1); } addrconf_ifdown(init_net.loopback_dev, 2); + addrconf_ifdown(blackhole_netdev, 2);
/* * Check hash table. diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 546088e508151..23164ac42826e 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -155,10 +155,9 @@ void rt6_uncached_list_del(struct rt6_info *rt)
static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev) { - struct net_device *loopback_dev = net->loopback_dev; int cpu;
- if (dev == loopback_dev) + if (dev == net->loopback_dev) return;
for_each_possible_cpu(cpu) { @@ -171,7 +170,7 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev) struct net_device *rt_dev = rt->dst.dev;
if (rt_idev->dev == dev) { - rt->rt6i_idev = in6_dev_get(loopback_dev); + rt->rt6i_idev = in6_dev_get(blackhole_netdev); in6_dev_put(rt_idev); }
@@ -386,13 +385,11 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, { struct rt6_info *rt = (struct rt6_info *)dst; struct inet6_dev *idev = rt->rt6i_idev; - struct net_device *loopback_dev = - dev_net(dev)->loopback_dev;
- if (idev && idev->dev != loopback_dev) { - struct inet6_dev *loopback_idev = in6_dev_get(loopback_dev); - if (loopback_idev) { - rt->rt6i_idev = loopback_idev; + if (idev && idev->dev != dev_net(dev)->loopback_dev) { + struct inet6_dev *ibdev = in6_dev_get(blackhole_netdev); + if (ibdev) { + rt->rt6i_idev = ibdev; in6_dev_put(idev); } }
On Fri, Oct 25, 2019 at 09:54:44AM -0400, Sasha Levin wrote:
From: Mahesh Bandewar maheshb@google.com
[ Upstream commit b0818f80c8c1bc215bba276bd61c216014fab23b ]
While invalidating the dst, we assign backhole_netdev instead of loopback device. However, this device does not have idev pointer and hence no ip6_ptr even if IPv6 is enabled. Possibly this has triggered the syzbot reported crash.
The syzbot report does not have reproducer, however, this is the only device that doesn't have matching idev created.
Crash instruction is :
static inline bool ip6_ignore_linkdown(const struct net_device *dev) { const struct inet6_dev *idev = __in6_dev_get(dev);
return !!idev->cnf.ignore_routes_with_linkdown; <= crash}
Also ipv6 always assumes presence of idev and never checks for it being NULL (as does the above referenced code). So adding a idev for the blackhole_netdev to avoid this class of crashes in the future.
Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org
I've dropped this patch.
From: Valentin Vidic vvidic@valentin-vidic.from.hr
[ Upstream commit 77b6d09f4ae66d42cd63b121af67780ae3d1a5e9 ]
Make sure res does not contain random value if the call to sr_read_cmd fails for some reason.
Reported-by: syzbot+f1842130bbcfb335bac1@syzkaller.appspotmail.com Signed-off-by: Valentin Vidic vvidic@valentin-vidic.from.hr Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/sr9800.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c index 35f39f23d8814..8f8c9ede88c26 100644 --- a/drivers/net/usb/sr9800.c +++ b/drivers/net/usb/sr9800.c @@ -336,7 +336,7 @@ static void sr_set_multicast(struct net_device *net) static int sr_mdio_read(struct net_device *net, int phy_id, int loc) { struct usbnet *dev = netdev_priv(net); - __le16 res; + __le16 res = 0;
mutex_lock(&dev->phy_mutex); sr_set_sw_mii(dev);
From: Quinn Tran qutran@marvell.com
[ Upstream commit d376dbda187317d06d3a2d495b43a7983e4a3250 ]
[ 17.177276] qla2xxx 0000:05:00.0: DMA-API: device driver frees DMA memory with different size [device address=0x00000006198b0000] [map size=32784 bytes] [unmap size=8208 bytes] [ 17.177390] RIP: 0010:check_unmap+0x7a2/0x1750 [ 17.177425] Call Trace: [ 17.177438] debug_dma_free_coherent+0x1b5/0x2d5 [ 17.177470] dma_free_attrs+0x7f/0x140 [ 17.177489] qla24xx_sp_unmap+0x1e2/0x610 [qla2xxx] [ 17.177509] qla24xx_async_gnnft_done+0x9c6/0x17d0 [qla2xxx] [ 17.177535] qla2x00_do_work+0x514/0x2200 [qla2xxx]
Fixes: b5f3bc39a0e8 ("scsi: qla2xxx: Fix inconsistent DMA mem alloc/free") Signed-off-by: Quinn Tran qutran@marvell.com Signed-off-by: Himanshu Madhani hmadhani@marvell.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/qla2xxx/qla_gs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index 9f58e591666da..ebf223cfebbc5 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -4152,7 +4152,7 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp) rspsz, &sp->u.iocb_cmd.u.ctarg.rsp_dma, GFP_KERNEL); - sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt); + sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = rspsz; if (!sp->u.iocb_cmd.u.ctarg.rsp) { ql_log(ql_log_warn, vha, 0xffff, "Failed to allocate ct_sns request.\n");
From: Chandan Rajendra chandan@linux.ibm.com
[ Upstream commit 547b9ad698b434eadca46319cb47e5875b55ef03 ]
When executing generic/388 on a ppc64le machine, we notice the following call trace,
VFS: brelse: Trying to free free buffer WARNING: CPU: 0 PID: 6637 at /root/repos/linux/fs/buffer.c:1195 __brelse+0x84/0xc0
Call Trace: __brelse+0x80/0xc0 (unreliable) invalidate_bh_lru+0x78/0xc0 on_each_cpu_mask+0xa8/0x130 on_each_cpu_cond_mask+0x130/0x170 invalidate_bh_lrus+0x44/0x60 invalidate_bdev+0x38/0x70 ext4_put_super+0x294/0x560 generic_shutdown_super+0xb0/0x170 kill_block_super+0x38/0xb0 deactivate_locked_super+0xa4/0xf0 cleanup_mnt+0x164/0x1d0 task_work_run+0x110/0x160 do_notify_resume+0x414/0x460 ret_from_except_lite+0x70/0x74
The warning happens because flush_descriptor() drops bh reference it does not own. The bh reference acquired by jbd2_journal_get_descriptor_buffer() is owned by the log_bufs list and gets released when this list is processed. The reference for doing IO is only acquired in write_dirty_buffer() later in flush_descriptor().
Reported-by: Harish Sriram harish@linux.ibm.com Reviewed-by: Jan Kara jack@suse.cz Signed-off-by: Chandan Rajendra chandan@linux.ibm.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- fs/jbd2/revoke.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c index 69b9bc329964f..f08073d7bbf57 100644 --- a/fs/jbd2/revoke.c +++ b/fs/jbd2/revoke.c @@ -638,10 +638,8 @@ static void flush_descriptor(journal_t *journal, { jbd2_journal_revoke_header_t *header;
- if (is_journal_aborted(journal)) { - put_bh(descriptor); + if (is_journal_aborted(journal)) return; - }
header = (jbd2_journal_revoke_header_t *)descriptor->b_data; header->r_count = cpu_to_be32(offset);
From: Florian Westphal fw@strlen.de
[ Upstream commit 105333435b4f3b21ffc325f32fae17719310db64 ]
seen during boot: BUG: spinlock bad magic on CPU#2, swapper/0/1 lock: nf_connlabels_lock+0x0/0x60, .magic: 00000000, .owner: <none>/-1, .owner_cpu: 0 Call Trace: do_raw_spin_lock+0x14e/0x1b0 nf_connlabels_get+0x15/0x40 ct_init_net+0xc4/0x270 ops_init+0x56/0x1c0 register_pernet_operations+0x1c8/0x350 register_pernet_subsys+0x1f/0x40 tcf_register_action+0x7c/0x1a0 do_one_initcall+0x13d/0x2d9
Problem is that ct action init function can run before connlabels_init(). Lock has not been initialised yet.
Fix it by using a static initialiser.
Fixes: b57dc7c13ea9 ("net/sched: Introduce action ct") Signed-off-by: Florian Westphal fw@strlen.de Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_conntrack_labels.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/net/netfilter/nf_conntrack_labels.c b/net/netfilter/nf_conntrack_labels.c index 74b8113f7aebe..d1c6b2a2e7bd1 100644 --- a/net/netfilter/nf_conntrack_labels.c +++ b/net/netfilter/nf_conntrack_labels.c @@ -11,7 +11,7 @@ #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_labels.h>
-static spinlock_t nf_connlabels_lock; +static __read_mostly DEFINE_SPINLOCK(nf_connlabels_lock);
static int replace_u32(u32 *address, u32 mask, u32 new) { @@ -89,7 +89,6 @@ int nf_conntrack_labels_init(void) { BUILD_BUG_ON(NF_CT_LABELS_MAX_SIZE / sizeof(long) >= U8_MAX);
- spin_lock_init(&nf_connlabels_lock); return nf_ct_extend_register(&labels_extend); }
From: Hans de Goede hdegoede@redhat.com
[ Upstream commit 1e296b5be40d309a1585c14bc55da6ff6a29ecf0 ]
tcpm_register_port() will call some of the fusb302 code's callbacks wich in turn will call fusb302_log(). So we need to call fusb302_debugfs_init() before we call tcpm_register_port().
This fixes the following warning, which was caused by the logbuffer_lock not yet being initialized (which is done by fusb302_debugfs_init):
DEBUG_LOCKS_WARN_ON(lock->magic != lock) WARNING: CPU: 0 PID: 1306 at kernel/locking/mutex.c:912 __mutex_lock+0x978/0x9a0 Modules linked in: fusb302(+) tcpm pi3usb30532 typec bq24190_charger snd_soc_sst_cht_bsw_rt5645 mei_hdcp dwc3 intel_rapl_msr udc_core ulpi gpio_keys intel_powerclamp coretemp kvm_intel brcmfmac kvm brcmutil joydev cfg80211 wdat_wdt irqbypass pcspkr intel_cstate extcon_intel_cht_wc i2c_cht_wc(E) snd_intel_sst_acpi snd_intel_sst_core snd_soc_rt5645 snd_soc_sst_atom_hifi2_platform snd_soc_acpi_intel_match snd_soc_rl6231 snd_soc_acpi intel_xhci_usb_role_switch roles hci_uart snd_soc_core btqca mei_txe btrtl processor_thermal_device mei snd_hdmi_lpe_audio lpc_ich snd_compress btbcm intel_rapl_common ac97_bus dwc3_pci snd_pcm_dmaengine intel_soc_dts_iosf btintel snd_seq bluetooth snd_seq_device snd_pcm intel_cht_int33fe_musb snd_timer intel_cht_int33fe_typec intel_hid intel_cht_int33fe_common sparse_keymap snd ecdh_generic goodix rfkill soundcore ecc spi_pxa2xx_platform max17042_battery dw_dmac int3406_thermal dptf_power acpi_pad soc_button_array int3400_thermal int3403_thermal gpd_pocket_fan intel_int0002_vgpio int340x_thermal_zone acpi_thermal_rel dm_crypt mmc_block i915 crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel i2c_algo_bit drm_kms_helper drm video sdhci_acpi sdhci mmc_core pwm_lpss_platform pwm_lpss i2c_dev CPU: 0 PID: 1306 Comm: systemd-udevd Tainted: G E 5.3.0-rc4+ #83 Hardware name: Default string Default string/Default string, BIOS 5.11 06/28/2017 RIP: 0010:__mutex_lock+0x978/0x9a0 Code: c0 0f 84 26 f7 ff ff 44 8b 05 24 25 c8 00 45 85 c0 0f 85 16 f7 ff ff 48 c7 c6 da 55 2f ae 48 c7 c7 98 8c 2d ae e8 a0 f9 5c ff <0f> 0b e9 fc f6 ff ff 4c 89 f0 4d 89 fe 49 89 c7 e9 cf fa ff ff e8 RSP: 0018:ffffb7a8c0523800 EFLAGS: 00010286 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000002 RSI: 0000000000000001 RDI: 0000000000000246 RBP: ffffb7a8c05238c0 R08: 0000000000000000 R09: 0000000000000000 R10: ffffb7a8c0523648 R11: 0000000000000030 R12: 0000000000000000 R13: ffffb7a8c0523990 R14: ffff9bf22f70c028 R15: ffff9bf22f70c360 FS: 00007f39ca234940(0000) GS:ffff9bf237400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f1f108481a0 CR3: 0000000271f28000 CR4: 00000000001006f0 Call Trace: ? find_held_lock+0x39/0x90 ? _fusb302_log+0x81/0x1d0 [fusb302] ? vsnprintf+0x3aa/0x4f0 ? _fusb302_log+0x81/0x1d0 [fusb302] _fusb302_log+0x81/0x1d0 [fusb302] ...
Reviewed-by: Guenter Roeck linux@roeck-us.net Reviewed-by: Heikki Krogerus heikki.krogerus@linux.intel.com Signed-off-by: Hans de Goede hdegoede@redhat.com Link: https://lore.kernel.org/r/20190817184340.64086-3-hdegoede@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/usb/typec/tcpm/fusb302.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/usb/typec/tcpm/fusb302.c b/drivers/usb/typec/tcpm/fusb302.c index c524088246ee3..2030ff8541783 100644 --- a/drivers/usb/typec/tcpm/fusb302.c +++ b/drivers/usb/typec/tcpm/fusb302.c @@ -1753,6 +1753,7 @@ static int fusb302_probe(struct i2c_client *client, INIT_WORK(&chip->irq_work, fusb302_irq_work); INIT_DELAYED_WORK(&chip->bc_lvl_handler, fusb302_bc_lvl_handler_work); init_tcpc_dev(&chip->tcpc_dev); + fusb302_debugfs_init(chip);
if (client->irq) { chip->gpio_int_n_irq = client->irq; @@ -1778,7 +1779,6 @@ static int fusb302_probe(struct i2c_client *client, goto tcpm_unregister_port; } enable_irq_wake(chip->gpio_int_n_irq); - fusb302_debugfs_init(chip); i2c_set_clientdata(client, chip);
return ret; @@ -1786,6 +1786,7 @@ static int fusb302_probe(struct i2c_client *client, tcpm_unregister_port: tcpm_unregister_port(chip->tcpm_port); destroy_workqueue: + fusb302_debugfs_exit(chip); destroy_workqueue(chip->wq);
return ret;
From: Chao Yu yuchao0@huawei.com
[ Upstream commit 04f9287ab395a5a279db44fb39de69b23640abb9 ]
============================================================================= BUG discard_cmd (Tainted: G B OE ): Objects remaining in discard_cmd on __kmem_cache_shutdown() -----------------------------------------------------------------------------
INFO: Slab 0xffffe1ac481d22c0 objects=36 used=2 fp=0xffff936b4748bf50 flags=0x2ffff0000000100 Call Trace: dump_stack+0x63/0x87 slab_err+0xa1/0xb0 __kmem_cache_shutdown+0x183/0x390 shutdown_cache+0x14/0x110 kmem_cache_destroy+0x195/0x1c0 f2fs_destroy_segment_manager_caches+0x21/0x40 [f2fs] exit_f2fs_fs+0x35/0x641 [f2fs] SyS_delete_module+0x155/0x230 ? vtime_user_exit+0x29/0x70 do_syscall_64+0x6e/0x160 entry_SYSCALL64_slow_path+0x25/0x25
INFO: Object 0xffff936b4748b000 @offset=0 INFO: Object 0xffff936b4748b070 @offset=112 kmem_cache_destroy discard_cmd: Slab cache still has objects Call Trace: dump_stack+0x63/0x87 kmem_cache_destroy+0x1b4/0x1c0 f2fs_destroy_segment_manager_caches+0x21/0x40 [f2fs] exit_f2fs_fs+0x35/0x641 [f2fs] SyS_delete_module+0x155/0x230 do_syscall_64+0x6e/0x160 entry_SYSCALL64_slow_path+0x25/0x25
Recovery can cache discard commands, so in error path of fill_super(), we need give a chance to handle them, otherwise it will lead to leak of discard_cmd slab cache.
Signed-off-by: Chao Yu yuchao0@huawei.com Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/f2fs/segment.c | 7 +++++++ 1 file changed, 7 insertions(+)
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index a661ac32e829e..a1ece0caad788 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -2084,6 +2084,13 @@ static void destroy_discard_cmd_control(struct f2fs_sb_info *sbi)
f2fs_stop_discard_thread(sbi);
+ /* + * Recovery can cache discard commands, so in error path of + * fill_super(), it needs to give a chance to handle them. + */ + if (unlikely(atomic_read(&dcc->discard_cmd_cnt))) + f2fs_issue_discard_timeout(sbi); + kvfree(dcc); SM_I(sbi)->dcc_info = NULL; }
From: Dag Moxnes dag.moxnes@oracle.com
[ Upstream commit bf1867db9b850fff2dd54a1a117a684a10b8cd90 ]
Add the RDMA cookie and RX timestamp to the usercopy whitelist.
After the introduction of hardened usercopy whitelisting (https://lwn.net/Articles/727322/), a warning is displayed when the RDMA cookie or RX timestamp is copied to userspace:
kernel: WARNING: CPU: 3 PID: 5750 at mm/usercopy.c:81 usercopy_warn+0x8e/0xa6 [...] kernel: Call Trace: kernel: __check_heap_object+0xb8/0x11b kernel: __check_object_size+0xe3/0x1bc kernel: put_cmsg+0x95/0x115 kernel: rds_recvmsg+0x43d/0x620 [rds] kernel: sock_recvmsg+0x43/0x4a kernel: ___sys_recvmsg+0xda/0x1e6 kernel: ? __handle_mm_fault+0xcae/0xf79 kernel: __sys_recvmsg+0x51/0x8a kernel: SyS_recvmsg+0x12/0x1c kernel: do_syscall_64+0x79/0x1ae
When the whitelisting feature was introduced, the memory for the RDMA cookie and RX timestamp in RDS was not added to the whitelist, causing the warning above.
Signed-off-by: Dag Moxnes dag.moxnes@oracle.com Tested-by: Jenny jenny.x.xu@oracle.com Acked-by: Santosh Shilimkar santosh.shilimkar@oracle.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/rds/ib_recv.c | 11 ++++++++--- net/rds/rds.h | 9 +++++++-- net/rds/recv.c | 22 ++++++++++++---------- 3 files changed, 27 insertions(+), 15 deletions(-)
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 3cae88cbdaa02..fecd0abdc7e8e 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -1038,9 +1038,14 @@ int rds_ib_recv_init(void) si_meminfo(&si); rds_ib_sysctl_max_recv_allocation = si.totalram / 3 * PAGE_SIZE / RDS_FRAG_SIZE;
- rds_ib_incoming_slab = kmem_cache_create("rds_ib_incoming", - sizeof(struct rds_ib_incoming), - 0, SLAB_HWCACHE_ALIGN, NULL); + rds_ib_incoming_slab = + kmem_cache_create_usercopy("rds_ib_incoming", + sizeof(struct rds_ib_incoming), + 0, SLAB_HWCACHE_ALIGN, + offsetof(struct rds_ib_incoming, + ii_inc.i_usercopy), + sizeof(struct rds_inc_usercopy), + NULL); if (!rds_ib_incoming_slab) goto out;
diff --git a/net/rds/rds.h b/net/rds/rds.h index f0066d1684993..e792a67dd5788 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -271,6 +271,12 @@ struct rds_ext_header_rdma_dest { #define RDS_MSG_RX_END 2 #define RDS_MSG_RX_CMSG 3
+/* The following values are whitelisted for usercopy */ +struct rds_inc_usercopy { + rds_rdma_cookie_t rdma_cookie; + ktime_t rx_tstamp; +}; + struct rds_incoming { refcount_t i_refcount; struct list_head i_item; @@ -280,8 +286,7 @@ struct rds_incoming { unsigned long i_rx_jiffies; struct in6_addr i_saddr;
- rds_rdma_cookie_t i_rdma_cookie; - ktime_t i_rx_tstamp; + struct rds_inc_usercopy i_usercopy; u64 i_rx_lat_trace[RDS_RX_MAX_TRACES]; };
diff --git a/net/rds/recv.c b/net/rds/recv.c index a42ba7fa06d5d..c8404971d5ab3 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -47,8 +47,8 @@ void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn, INIT_LIST_HEAD(&inc->i_item); inc->i_conn = conn; inc->i_saddr = *saddr; - inc->i_rdma_cookie = 0; - inc->i_rx_tstamp = ktime_set(0, 0); + inc->i_usercopy.rdma_cookie = 0; + inc->i_usercopy.rx_tstamp = ktime_set(0, 0);
memset(inc->i_rx_lat_trace, 0, sizeof(inc->i_rx_lat_trace)); } @@ -62,8 +62,8 @@ void rds_inc_path_init(struct rds_incoming *inc, struct rds_conn_path *cp, inc->i_conn = cp->cp_conn; inc->i_conn_path = cp; inc->i_saddr = *saddr; - inc->i_rdma_cookie = 0; - inc->i_rx_tstamp = ktime_set(0, 0); + inc->i_usercopy.rdma_cookie = 0; + inc->i_usercopy.rx_tstamp = ktime_set(0, 0); } EXPORT_SYMBOL_GPL(rds_inc_path_init);
@@ -186,7 +186,7 @@ static void rds_recv_incoming_exthdrs(struct rds_incoming *inc, struct rds_sock case RDS_EXTHDR_RDMA_DEST: /* We ignore the size for now. We could stash it * somewhere and use it for error checking. */ - inc->i_rdma_cookie = rds_rdma_make_cookie( + inc->i_usercopy.rdma_cookie = rds_rdma_make_cookie( be32_to_cpu(buffer.rdma_dest.h_rdma_rkey), be32_to_cpu(buffer.rdma_dest.h_rdma_offset));
@@ -380,7 +380,7 @@ void rds_recv_incoming(struct rds_connection *conn, struct in6_addr *saddr, be32_to_cpu(inc->i_hdr.h_len), inc->i_hdr.h_dport); if (sock_flag(sk, SOCK_RCVTSTAMP)) - inc->i_rx_tstamp = ktime_get_real(); + inc->i_usercopy.rx_tstamp = ktime_get_real(); rds_inc_addref(inc); inc->i_rx_lat_trace[RDS_MSG_RX_END] = local_clock(); list_add_tail(&inc->i_item, &rs->rs_recv_queue); @@ -540,16 +540,18 @@ static int rds_cmsg_recv(struct rds_incoming *inc, struct msghdr *msg, { int ret = 0;
- if (inc->i_rdma_cookie) { + if (inc->i_usercopy.rdma_cookie) { ret = put_cmsg(msg, SOL_RDS, RDS_CMSG_RDMA_DEST, - sizeof(inc->i_rdma_cookie), &inc->i_rdma_cookie); + sizeof(inc->i_usercopy.rdma_cookie), + &inc->i_usercopy.rdma_cookie); if (ret) goto out; }
- if ((inc->i_rx_tstamp != 0) && + if ((inc->i_usercopy.rx_tstamp != 0) && sock_flag(rds_rs_to_sk(rs), SOCK_RCVTSTAMP)) { - struct __kernel_old_timeval tv = ns_to_kernel_old_timeval(inc->i_rx_tstamp); + struct __kernel_old_timeval tv = + ns_to_kernel_old_timeval(inc->i_usercopy.rx_tstamp);
if (!sock_flag(rds_rs_to_sk(rs), SOCK_TSTAMP_NEW)) { ret = put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD,
From: Arun Easi aeasi@marvell.com
[ Upstream commit 47aeee5549cf9326656a8f9190960dfd35c101e2 ]
Driver was attempting to print cdb[0], which is not set for resets coming from SCSI ioctls. Check for cmd_len before accessing cmnd.
Crash info: [84790.864747] BUG: unable to handle kernel NULL pointer dereference at (null) [84790.864783] IP: qedf_initiate_tmf+0x7a/0x6e0 [qedf] [84790.865204] Call Trace: [84790.865246] scsi_try_target_reset+0x2b/0x90 [scsi_mod] [84790.865266] scsi_ioctl_reset+0x20f/0x2a0 [scsi_mod] [84790.865284] scsi_ioctl+0x131/0x3a0 [scsi_mod]
Signed-off-by: Arun Easi aeasi@marvell.com Signed-off-by: Saurav Kashyap skashyap@marvell.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/qedf/qedf_io.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/scsi/qedf/qedf_io.c b/drivers/scsi/qedf/qedf_io.c index d881e822f92cf..56756a5700867 100644 --- a/drivers/scsi/qedf/qedf_io.c +++ b/drivers/scsi/qedf/qedf_io.c @@ -2363,8 +2363,8 @@ int qedf_initiate_tmf(struct scsi_cmnd *sc_cmd, u8 tm_flags)
QEDF_ERR(NULL, "tm_flags 0x%x sc_cmd %p op = 0x%02x target_id = 0x%x lun=%d\n", - tm_flags, sc_cmd, sc_cmd->cmnd[0], rport->scsi_target_id, - (int)sc_cmd->device->lun); + tm_flags, sc_cmd, sc_cmd->cmd_len ? sc_cmd->cmnd[0] : 0xff, + rport->scsi_target_id, (int)sc_cmd->device->lun);
if (!rdata || !kref_get_unless_zero(&rdata->kref)) { QEDF_ERR(NULL, "stale rport\n");
From: Lorenzo Bianconi lorenzo@kernel.org
[ Upstream commit e1aa1a1db3b01c9890e82cf065cee99962ba1ed9 ]
Fix following lockdep warning disabling bh in ath_dynack_node_init/ath_dynack_node_deinit
[ 75.955878] -------------------------------- [ 75.955880] inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. [ 75.955884] swapper/0/0 [HC0[0]:SC1[3]:HE1:SE0] takes: [ 75.955888] 00000000792a7ee0 (&(&da->qlock)->rlock){+.?.}, at: ath_dynack_sample_ack_ts+0x4d/0xa0 [ath9k_hw] [ 75.955905] {SOFTIRQ-ON-W} state was registered at: [ 75.955912] lock_acquire+0x9a/0x160 [ 75.955917] _raw_spin_lock+0x2c/0x70 [ 75.955927] ath_dynack_node_init+0x2a/0x60 [ath9k_hw] [ 75.955934] ath9k_sta_state+0xec/0x160 [ath9k] [ 75.955976] drv_sta_state+0xb2/0x740 [mac80211] [ 75.956008] sta_info_insert_finish+0x21a/0x420 [mac80211] [ 75.956039] sta_info_insert_rcu+0x12b/0x2c0 [mac80211] [ 75.956069] sta_info_insert+0x7/0x70 [mac80211] [ 75.956093] ieee80211_prep_connection+0x42e/0x730 [mac80211] [ 75.956120] ieee80211_mgd_auth.cold+0xb9/0x15c [mac80211] [ 75.956152] cfg80211_mlme_auth+0x143/0x350 [cfg80211] [ 75.956169] nl80211_authenticate+0x25e/0x2b0 [cfg80211] [ 75.956172] genl_family_rcv_msg+0x198/0x400 [ 75.956174] genl_rcv_msg+0x42/0x90 [ 75.956176] netlink_rcv_skb+0x35/0xf0 [ 75.956178] genl_rcv+0x1f/0x30 [ 75.956180] netlink_unicast+0x154/0x200 [ 75.956182] netlink_sendmsg+0x1bf/0x3d0 [ 75.956186] ___sys_sendmsg+0x2c2/0x2f0 [ 75.956187] __sys_sendmsg+0x44/0x80 [ 75.956190] do_syscall_64+0x55/0x1a0 [ 75.956192] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 75.956194] irq event stamp: 2357092 [ 75.956196] hardirqs last enabled at (2357092): [<ffffffff818c62de>] _raw_spin_unlock_irqrestore+0x3e/0x50 [ 75.956199] hardirqs last disabled at (2357091): [<ffffffff818c60b1>] _raw_spin_lock_irqsave+0x11/0x80 [ 75.956202] softirqs last enabled at (2357072): [<ffffffff8106dc09>] irq_enter+0x59/0x60 [ 75.956204] softirqs last disabled at (2357073): [<ffffffff8106dcbe>] irq_exit+0xae/0xc0 [ 75.956206] other info that might help us debug this: [ 75.956207] Possible unsafe locking scenario:
[ 75.956208] CPU0 [ 75.956209] ---- [ 75.956210] lock(&(&da->qlock)->rlock); [ 75.956213] <Interrupt> [ 75.956214] lock(&(&da->qlock)->rlock); [ 75.956216] *** DEADLOCK ***
[ 75.956217] 1 lock held by swapper/0/0: [ 75.956219] #0: 000000003bb5675c (&(&sc->sc_pcu_lock)->rlock){+.-.}, at: ath9k_tasklet+0x55/0x240 [ath9k] [ 75.956225] stack backtrace: [ 75.956228] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.3.0-rc1-wdn+ #13 [ 75.956229] Hardware name: Dell Inc. Studio XPS 1340/0K183D, BIOS A11 09/08/2009 [ 75.956231] Call Trace: [ 75.956233] <IRQ> [ 75.956236] dump_stack+0x67/0x90 [ 75.956239] mark_lock+0x4c1/0x640 [ 75.956242] ? check_usage_backwards+0x130/0x130 [ 75.956245] ? sched_clock_local+0x12/0x80 [ 75.956247] __lock_acquire+0x484/0x7a0 [ 75.956250] ? __lock_acquire+0x3b9/0x7a0 [ 75.956252] lock_acquire+0x9a/0x160 [ 75.956259] ? ath_dynack_sample_ack_ts+0x4d/0xa0 [ath9k_hw] [ 75.956262] _raw_spin_lock_bh+0x34/0x80 [ 75.956268] ? ath_dynack_sample_ack_ts+0x4d/0xa0 [ath9k_hw] [ 75.956275] ath_dynack_sample_ack_ts+0x4d/0xa0 [ath9k_hw] [ 75.956280] ath_rx_tasklet+0xd09/0xe90 [ath9k] [ 75.956286] ath9k_tasklet+0x102/0x240 [ath9k] [ 75.956288] tasklet_action_common.isra.0+0x6d/0x170 [ 75.956291] __do_softirq+0xcc/0x425 [ 75.956294] irq_exit+0xae/0xc0 [ 75.956296] do_IRQ+0x8a/0x110 [ 75.956298] common_interrupt+0xf/0xf [ 75.956300] </IRQ> [ 75.956303] RIP: 0010:cpuidle_enter_state+0xb2/0x400 [ 75.956308] RSP: 0018:ffffffff82203e70 EFLAGS: 00000202 ORIG_RAX: ffffffffffffffd7 [ 75.956310] RAX: ffffffff82219800 RBX: ffffffff822bd0a0 RCX: 0000000000000000 [ 75.956312] RDX: 0000000000000046 RSI: 0000000000000006 RDI: ffffffff82219800 [ 75.956314] RBP: ffff888155a01c00 R08: 00000011af51aabe R09: 0000000000000000 [ 75.956315] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000002 [ 75.956317] R13: 00000011af51aabe R14: 0000000000000003 R15: ffffffff82219800 [ 75.956321] cpuidle_enter+0x24/0x40 [ 75.956323] do_idle+0x1ac/0x220 [ 75.956326] cpu_startup_entry+0x14/0x20 [ 75.956329] start_kernel+0x482/0x489 [ 75.956332] secondary_startup_64+0xa4/0xb0
Fixes: c774d57fd47c ("ath9k: add dynamic ACK timeout estimation") Signed-off-by: Lorenzo Bianconi lorenzo@kernel.org Tested-by: Koen Vandeputte koen.vandeputte@ncentric.com Signed-off-by: Kalle Valo kvalo@codeaurora.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/ath/ath9k/dynack.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/wireless/ath/ath9k/dynack.c b/drivers/net/wireless/ath/ath9k/dynack.c index f112fa5b2eacf..1ccf20d8c1607 100644 --- a/drivers/net/wireless/ath/ath9k/dynack.c +++ b/drivers/net/wireless/ath/ath9k/dynack.c @@ -298,9 +298,9 @@ void ath_dynack_node_init(struct ath_hw *ah, struct ath_node *an)
an->ackto = ackto;
- spin_lock(&da->qlock); + spin_lock_bh(&da->qlock); list_add_tail(&an->list, &da->nodes); - spin_unlock(&da->qlock); + spin_unlock_bh(&da->qlock); } EXPORT_SYMBOL(ath_dynack_node_init);
@@ -314,9 +314,9 @@ void ath_dynack_node_deinit(struct ath_hw *ah, struct ath_node *an) { struct ath_dynack *da = &ah->dynack;
- spin_lock(&da->qlock); + spin_lock_bh(&da->qlock); list_del(&an->list); - spin_unlock(&da->qlock); + spin_unlock_bh(&da->qlock); } EXPORT_SYMBOL(ath_dynack_node_deinit);
From: Filipe Manana fdmanana@suse.com
[ Upstream commit 7764d56baa844d7f6206394f21a0e8c1f303c476 ]
If we are able to load an existing inode cache off disk, we set the state of the cache to BTRFS_CACHE_FINISHED, but we don't wake up any one waiting for the cache to be available. This means that anyone waiting for the cache to be available, waiting on the condition that either its state is BTRFS_CACHE_FINISHED or its available free space is greather than zero, can hang forever.
This could be observed running fstests with MOUNT_OPTIONS="-o inode_cache", in particular test case generic/161 triggered it very frequently for me, producing a trace like the following:
[63795.739712] BTRFS info (device sdc): enabling inode map caching [63795.739714] BTRFS info (device sdc): disk space caching is enabled [63795.739716] BTRFS info (device sdc): has skinny extents [64036.653886] INFO: task btrfs-transacti:3917 blocked for more than 120 seconds. [64036.654079] Not tainted 5.2.0-rc4-btrfs-next-50 #1 [64036.654143] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [64036.654232] btrfs-transacti D 0 3917 2 0x80004000 [64036.654239] Call Trace: [64036.654258] ? __schedule+0x3ae/0x7b0 [64036.654271] schedule+0x3a/0xb0 [64036.654325] btrfs_commit_transaction+0x978/0xae0 [btrfs] [64036.654339] ? remove_wait_queue+0x60/0x60 [64036.654395] transaction_kthread+0x146/0x180 [btrfs] [64036.654450] ? btrfs_cleanup_transaction+0x620/0x620 [btrfs] [64036.654456] kthread+0x103/0x140 [64036.654464] ? kthread_create_worker_on_cpu+0x70/0x70 [64036.654476] ret_from_fork+0x3a/0x50 [64036.654504] INFO: task xfs_io:3919 blocked for more than 120 seconds. [64036.654568] Not tainted 5.2.0-rc4-btrfs-next-50 #1 [64036.654617] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [64036.654685] xfs_io D 0 3919 3633 0x00000000 [64036.654691] Call Trace: [64036.654703] ? __schedule+0x3ae/0x7b0 [64036.654716] schedule+0x3a/0xb0 [64036.654756] btrfs_find_free_ino+0xa9/0x120 [btrfs] [64036.654764] ? remove_wait_queue+0x60/0x60 [64036.654809] btrfs_create+0x72/0x1f0 [btrfs] [64036.654822] lookup_open+0x6bc/0x790 [64036.654849] path_openat+0x3bc/0xc00 [64036.654854] ? __lock_acquire+0x331/0x1cb0 [64036.654869] do_filp_open+0x99/0x110 [64036.654884] ? __alloc_fd+0xee/0x200 [64036.654895] ? do_raw_spin_unlock+0x49/0xc0 [64036.654909] ? do_sys_open+0x132/0x220 [64036.654913] do_sys_open+0x132/0x220 [64036.654926] do_syscall_64+0x60/0x1d0 [64036.654933] entry_SYSCALL_64_after_hwframe+0x49/0xbe
Fix this by adding a wake_up() call right after setting the cache state to BTRFS_CACHE_FINISHED, at start_caching(), when we are able to load the cache from disk.
Fixes: 82d5902d9c681b ("Btrfs: Support reading/writing on disk free ino cache") Reviewed-by: Nikolay Borisov nborisov@suse.com Signed-off-by: Filipe Manana fdmanana@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/btrfs/inode-map.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index 2e8bb402050b9..84b2c9ee52a74 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -146,6 +146,7 @@ static void start_caching(struct btrfs_root *root) spin_lock(&root->ino_cache_lock); root->ino_cache_state = BTRFS_CACHE_FINISHED; spin_unlock(&root->ino_cache_lock); + wake_up(&root->ino_cache_wait); return; }
From: Filipe Manana fdmanana@suse.com
[ Upstream commit 29d47d00e0ae61668ee0c5d90bef2893c8abbafa ]
If we failed to allocate the data extent(s) for the inode space cache, we were bailing out without releasing the previously reserved metadata. This was triggering the following warnings when unmounting a filesystem:
$ cat -n fs/btrfs/inode.c (...) 9268 void btrfs_destroy_inode(struct inode *inode) 9269 { (...) 9276 WARN_ON(BTRFS_I(inode)->block_rsv.reserved); 9277 WARN_ON(BTRFS_I(inode)->block_rsv.size); (...) 9281 WARN_ON(BTRFS_I(inode)->csum_bytes); 9282 WARN_ON(BTRFS_I(inode)->defrag_bytes); (...)
Several fstests test cases triggered this often, such as generic/083, generic/102, generic/172, generic/269 and generic/300 at least, producing stack traces like the following in dmesg/syslog:
[82039.079546] WARNING: CPU: 2 PID: 13167 at fs/btrfs/inode.c:9276 btrfs_destroy_inode+0x203/0x270 [btrfs] (...) [82039.081543] CPU: 2 PID: 13167 Comm: umount Tainted: G W 5.2.0-rc4-btrfs-next-50 #1 [82039.081912] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.2-0-gf9626ccb91-prebuilt.qemu-project.org 04/01/2014 [82039.082673] RIP: 0010:btrfs_destroy_inode+0x203/0x270 [btrfs] (...) [82039.083913] RSP: 0018:ffffac0b426a7d30 EFLAGS: 00010206 [82039.084320] RAX: ffff8ddf77691158 RBX: ffff8dde29b34660 RCX: 0000000000000002 [82039.084736] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8dde29b34660 [82039.085156] RBP: ffff8ddf5fbec000 R08: 0000000000000000 R09: 0000000000000000 [82039.085578] R10: ffffac0b426a7c90 R11: ffffffffb9aad768 R12: ffffac0b426a7db0 [82039.086000] R13: ffff8ddf5fbec0a0 R14: dead000000000100 R15: 0000000000000000 [82039.086416] FS: 00007f8db96d12c0(0000) GS:ffff8de036b00000(0000) knlGS:0000000000000000 [82039.086837] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [82039.087253] CR2: 0000000001416108 CR3: 00000002315cc001 CR4: 00000000003606e0 [82039.087672] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [82039.088089] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [82039.088504] Call Trace: [82039.088918] destroy_inode+0x3b/0x70 [82039.089340] btrfs_free_fs_root+0x16/0xa0 [btrfs] [82039.089768] btrfs_free_fs_roots+0xd8/0x160 [btrfs] [82039.090183] ? wait_for_completion+0x65/0x1a0 [82039.090607] close_ctree+0x172/0x370 [btrfs] [82039.091021] generic_shutdown_super+0x6c/0x110 [82039.091427] kill_anon_super+0xe/0x30 [82039.091832] btrfs_kill_super+0x12/0xa0 [btrfs] [82039.092233] deactivate_locked_super+0x3a/0x70 [82039.092636] cleanup_mnt+0x3b/0x80 [82039.093039] task_work_run+0x93/0xc0 [82039.093457] exit_to_usermode_loop+0xfa/0x100 [82039.093856] do_syscall_64+0x162/0x1d0 [82039.094244] entry_SYSCALL_64_after_hwframe+0x49/0xbe [82039.094634] RIP: 0033:0x7f8db8fbab37 (...) [82039.095876] RSP: 002b:00007ffdce35b468 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6 [82039.096290] RAX: 0000000000000000 RBX: 0000560d20b00060 RCX: 00007f8db8fbab37 [82039.096700] RDX: 0000000000000001 RSI: 0000000000000000 RDI: 0000560d20b00240 [82039.097110] RBP: 0000560d20b00240 R08: 0000560d20b00270 R09: 0000000000000015 [82039.097522] R10: 00000000000006b4 R11: 0000000000000246 R12: 00007f8db94bce64 [82039.097937] R13: 0000000000000000 R14: 0000000000000000 R15: 00007ffdce35b6f0 [82039.098350] irq event stamp: 0 [82039.098750] hardirqs last enabled at (0): [<0000000000000000>] 0x0 [82039.099150] hardirqs last disabled at (0): [<ffffffffb7884ff2>] copy_process.part.33+0x7f2/0x1f00 [82039.099545] softirqs last enabled at (0): [<ffffffffb7884ff2>] copy_process.part.33+0x7f2/0x1f00 [82039.099925] softirqs last disabled at (0): [<0000000000000000>] 0x0 [82039.100292] ---[ end trace f2521afa616ddccc ]--- [82039.100707] WARNING: CPU: 2 PID: 13167 at fs/btrfs/inode.c:9277 btrfs_destroy_inode+0x1ac/0x270 [btrfs] (...) [82039.103050] CPU: 2 PID: 13167 Comm: umount Tainted: G W 5.2.0-rc4-btrfs-next-50 #1 [82039.103428] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.2-0-gf9626ccb91-prebuilt.qemu-project.org 04/01/2014 [82039.104203] RIP: 0010:btrfs_destroy_inode+0x1ac/0x270 [btrfs] (...) [82039.105461] RSP: 0018:ffffac0b426a7d30 EFLAGS: 00010206 [82039.105866] RAX: ffff8ddf77691158 RBX: ffff8dde29b34660 RCX: 0000000000000002 [82039.106270] RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8dde29b34660 [82039.106673] RBP: ffff8ddf5fbec000 R08: 0000000000000000 R09: 0000000000000000 [82039.107078] R10: ffffac0b426a7c90 R11: ffffffffb9aad768 R12: ffffac0b426a7db0 [82039.107487] R13: ffff8ddf5fbec0a0 R14: dead000000000100 R15: 0000000000000000 [82039.107894] FS: 00007f8db96d12c0(0000) GS:ffff8de036b00000(0000) knlGS:0000000000000000 [82039.108309] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [82039.108723] CR2: 0000000001416108 CR3: 00000002315cc001 CR4: 00000000003606e0 [82039.109146] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [82039.109567] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [82039.109989] Call Trace: [82039.110405] destroy_inode+0x3b/0x70 [82039.110830] btrfs_free_fs_root+0x16/0xa0 [btrfs] [82039.111257] btrfs_free_fs_roots+0xd8/0x160 [btrfs] [82039.111675] ? wait_for_completion+0x65/0x1a0 [82039.112101] close_ctree+0x172/0x370 [btrfs] [82039.112519] generic_shutdown_super+0x6c/0x110 [82039.112988] kill_anon_super+0xe/0x30 [82039.113439] btrfs_kill_super+0x12/0xa0 [btrfs] [82039.113861] deactivate_locked_super+0x3a/0x70 [82039.114278] cleanup_mnt+0x3b/0x80 [82039.114685] task_work_run+0x93/0xc0 [82039.115083] exit_to_usermode_loop+0xfa/0x100 [82039.115476] do_syscall_64+0x162/0x1d0 [82039.115863] entry_SYSCALL_64_after_hwframe+0x49/0xbe [82039.116254] RIP: 0033:0x7f8db8fbab37 (...) [82039.117463] RSP: 002b:00007ffdce35b468 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6 [82039.117882] RAX: 0000000000000000 RBX: 0000560d20b00060 RCX: 00007f8db8fbab37 [82039.118330] RDX: 0000000000000001 RSI: 0000000000000000 RDI: 0000560d20b00240 [82039.118743] RBP: 0000560d20b00240 R08: 0000560d20b00270 R09: 0000000000000015 [82039.119159] R10: 00000000000006b4 R11: 0000000000000246 R12: 00007f8db94bce64 [82039.119574] R13: 0000000000000000 R14: 0000000000000000 R15: 00007ffdce35b6f0 [82039.119987] irq event stamp: 0 [82039.120387] hardirqs last enabled at (0): [<0000000000000000>] 0x0 [82039.120787] hardirqs last disabled at (0): [<ffffffffb7884ff2>] copy_process.part.33+0x7f2/0x1f00 [82039.121182] softirqs last enabled at (0): [<ffffffffb7884ff2>] copy_process.part.33+0x7f2/0x1f00 [82039.121563] softirqs last disabled at (0): [<0000000000000000>] 0x0 [82039.121933] ---[ end trace f2521afa616ddccd ]--- [82039.122353] WARNING: CPU: 2 PID: 13167 at fs/btrfs/inode.c:9278 btrfs_destroy_inode+0x1bc/0x270 [btrfs] (...) [82039.124606] CPU: 2 PID: 13167 Comm: umount Tainted: G W 5.2.0-rc4-btrfs-next-50 #1 [82039.125008] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.2-0-gf9626ccb91-prebuilt.qemu-project.org 04/01/2014 [82039.125801] RIP: 0010:btrfs_destroy_inode+0x1bc/0x270 [btrfs] (...) [82039.126998] RSP: 0018:ffffac0b426a7d30 EFLAGS: 00010202 [82039.127399] RAX: ffff8ddf77691158 RBX: ffff8dde29b34660 RCX: 0000000000000002 [82039.127803] RDX: 0000000000000001 RSI: 0000000000000001 RDI: ffff8dde29b34660 [82039.128206] RBP: ffff8ddf5fbec000 R08: 0000000000000000 R09: 0000000000000000 [82039.128611] R10: ffffac0b426a7c90 R11: ffffffffb9aad768 R12: ffffac0b426a7db0 [82039.129020] R13: ffff8ddf5fbec0a0 R14: dead000000000100 R15: 0000000000000000 [82039.129428] FS: 00007f8db96d12c0(0000) GS:ffff8de036b00000(0000) knlGS:0000000000000000 [82039.129846] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [82039.130261] CR2: 0000000001416108 CR3: 00000002315cc001 CR4: 00000000003606e0 [82039.130684] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [82039.131142] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [82039.131561] Call Trace: [82039.131990] destroy_inode+0x3b/0x70 [82039.132417] btrfs_free_fs_root+0x16/0xa0 [btrfs] [82039.132844] btrfs_free_fs_roots+0xd8/0x160 [btrfs] [82039.133262] ? wait_for_completion+0x65/0x1a0 [82039.133688] close_ctree+0x172/0x370 [btrfs] [82039.134157] generic_shutdown_super+0x6c/0x110 [82039.134575] kill_anon_super+0xe/0x30 [82039.134997] btrfs_kill_super+0x12/0xa0 [btrfs] [82039.135415] deactivate_locked_super+0x3a/0x70 [82039.135832] cleanup_mnt+0x3b/0x80 [82039.136239] task_work_run+0x93/0xc0 [82039.136637] exit_to_usermode_loop+0xfa/0x100 [82039.137029] do_syscall_64+0x162/0x1d0 [82039.137418] entry_SYSCALL_64_after_hwframe+0x49/0xbe [82039.137812] RIP: 0033:0x7f8db8fbab37 (...) [82039.139059] RSP: 002b:00007ffdce35b468 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6 [82039.139475] RAX: 0000000000000000 RBX: 0000560d20b00060 RCX: 00007f8db8fbab37 [82039.139890] RDX: 0000000000000001 RSI: 0000000000000000 RDI: 0000560d20b00240 [82039.140302] RBP: 0000560d20b00240 R08: 0000560d20b00270 R09: 0000000000000015 [82039.140719] R10: 00000000000006b4 R11: 0000000000000246 R12: 00007f8db94bce64 [82039.141138] R13: 0000000000000000 R14: 0000000000000000 R15: 00007ffdce35b6f0 [82039.141597] irq event stamp: 0 [82039.142043] hardirqs last enabled at (0): [<0000000000000000>] 0x0 [82039.142443] hardirqs last disabled at (0): [<ffffffffb7884ff2>] copy_process.part.33+0x7f2/0x1f00 [82039.142839] softirqs last enabled at (0): [<ffffffffb7884ff2>] copy_process.part.33+0x7f2/0x1f00 [82039.143220] softirqs last disabled at (0): [<0000000000000000>] 0x0 [82039.143588] ---[ end trace f2521afa616ddcce ]--- [82039.167472] WARNING: CPU: 3 PID: 13167 at fs/btrfs/extent-tree.c:10120 btrfs_free_block_groups+0x30d/0x460 [btrfs] (...) [82039.173800] CPU: 3 PID: 13167 Comm: umount Tainted: G W 5.2.0-rc4-btrfs-next-50 #1 [82039.174847] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.11.2-0-gf9626ccb91-prebuilt.qemu-project.org 04/01/2014 [82039.177031] RIP: 0010:btrfs_free_block_groups+0x30d/0x460 [btrfs] (...) [82039.180397] RSP: 0018:ffffac0b426a7dd8 EFLAGS: 00010206 [82039.181574] RAX: ffff8de010a1db40 RBX: ffff8de010a1db40 RCX: 0000000000170014 [82039.182711] RDX: ffff8ddff4380040 RSI: ffff8de010a1da58 RDI: 0000000000000246 [82039.183817] RBP: ffff8ddf5fbec000 R08: 0000000000000000 R09: 0000000000000000 [82039.184925] R10: ffff8de036404380 R11: ffffffffb8a5ea00 R12: ffff8de010a1b2b8 [82039.186090] R13: ffff8de010a1b2b8 R14: 0000000000000000 R15: dead000000000100 [82039.187208] FS: 00007f8db96d12c0(0000) GS:ffff8de036b80000(0000) knlGS:0000000000000000 [82039.188345] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [82039.189481] CR2: 00007fb044005170 CR3: 00000002315cc006 CR4: 00000000003606e0 [82039.190674] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [82039.191829] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [82039.192978] Call Trace: [82039.194160] close_ctree+0x19a/0x370 [btrfs] [82039.195315] generic_shutdown_super+0x6c/0x110 [82039.196486] kill_anon_super+0xe/0x30 [82039.197645] btrfs_kill_super+0x12/0xa0 [btrfs] [82039.198696] deactivate_locked_super+0x3a/0x70 [82039.199619] cleanup_mnt+0x3b/0x80 [82039.200559] task_work_run+0x93/0xc0 [82039.201505] exit_to_usermode_loop+0xfa/0x100 [82039.202436] do_syscall_64+0x162/0x1d0 [82039.203339] entry_SYSCALL_64_after_hwframe+0x49/0xbe [82039.204091] RIP: 0033:0x7f8db8fbab37 (...) [82039.206360] RSP: 002b:00007ffdce35b468 EFLAGS: 00000246 ORIG_RAX: 00000000000000a6 [82039.207132] RAX: 0000000000000000 RBX: 0000560d20b00060 RCX: 00007f8db8fbab37 [82039.207906] RDX: 0000000000000001 RSI: 0000000000000000 RDI: 0000560d20b00240 [82039.208621] RBP: 0000560d20b00240 R08: 0000560d20b00270 R09: 0000000000000015 [82039.209285] R10: 00000000000006b4 R11: 0000000000000246 R12: 00007f8db94bce64 [82039.209984] R13: 0000000000000000 R14: 0000000000000000 R15: 00007ffdce35b6f0 [82039.210642] irq event stamp: 0 [82039.211306] hardirqs last enabled at (0): [<0000000000000000>] 0x0 [82039.211971] hardirqs last disabled at (0): [<ffffffffb7884ff2>] copy_process.part.33+0x7f2/0x1f00 [82039.212643] softirqs last enabled at (0): [<ffffffffb7884ff2>] copy_process.part.33+0x7f2/0x1f00 [82039.213304] softirqs last disabled at (0): [<0000000000000000>] 0x0 [82039.213875] ---[ end trace f2521afa616ddccf ]---
Fix this by releasing the reserved metadata on failure to allocate data extent(s) for the inode cache.
Fixes: 69fe2d75dd91d0 ("btrfs: make the delalloc block rsv per inode") Signed-off-by: Filipe Manana fdmanana@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/btrfs/inode-map.c | 1 + 1 file changed, 1 insertion(+)
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index 84b2c9ee52a74..45db4fb4b9599 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -486,6 +486,7 @@ int btrfs_save_ino_cache(struct btrfs_root *root, prealloc, prealloc, &alloc_hint); if (ret) { btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc, true); + btrfs_delalloc_release_metadata(BTRFS_I(inode), prealloc, true); goto out_put; }
From: Zhihao Cheng chengzhihao1@huawei.com
[ Upstream commit 8615b94f029a4fb4306d3512aaf1c45f5fc24d4b ]
Running stress test io_paral (A pressure ubi test in mtd-utils) on an UBI device with fewer PEBs (fastmap enabled) may cause ENOSPC errors and make UBI device read-only, but there are still free PEBs on the UBI device. This problem can be easily reproduced by performing the following steps on a 2-core machine: $ modprobe nandsim first_id_byte=0x20 second_id_byte=0x33 parts=80 $ modprobe ubi mtd="0,0" fm_autoconvert $ ./io_paral /dev/ubi0
We may see the following verbose: (output) [io_paral] update_volume():108: failed to write 380 bytes at offset 95920 of volume 2 [io_paral] update_volume():109: update: 97088 bytes [io_paral] write_thread():227: function pwrite() failed with error 28 (No space left on device) [io_paral] write_thread():229: cannot write 15872 bytes to offs 31744, wrote -1 (dmesg) ubi0 error: ubi_wl_get_peb [ubi]: Unable to get a free PEB from user WL pool ubi0 warning: ubi_eba_write_leb [ubi]: switch to read-only mode CPU: 0 PID: 2027 Comm: io_paral Not tainted 5.3.0-rc2-00001-g5986cd0 #9 ubi0 warning: try_write_vid_and_data [ubi]: failed to write VID header to LEB 2:5, PEB 18 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0 -0-ga698c8995f-prebuilt.qemu.org 04/01/2014 Call Trace: dump_stack+0x85/0xba ubi_eba_write_leb+0xa1e/0xa40 [ubi] vol_cdev_write+0x307/0x520 [ubi] vfs_write+0xfa/0x280 ksys_pwrite64+0xc5/0xe0 __x64_sys_pwrite64+0x22/0x30 do_syscall_64+0xbf/0x440
In function ubi_wl_get_peb, the operation of filling the pool (ubi_update_fastmap) with free PEBs and fetching a free PEB from the pool is not atomic. After thread A filling the pool with free PEB, free PEB may be taken away by thread B. When thread A checks the expression again, the condition is still unsatisfactory. At this time, there may still be free PEBs on UBI that can be filled into the pool.
This patch increases the number of attempts to obtain PEB. An extreme case (No free PEBs left after creating test volumes) has been tested on different type of machines for 100 times. The biggest number of attempts are shown below:
x86_64 arm64 2-core 4 4 4-core 8 4 8-core 4 4
Signed-off-by: Zhihao Cheng chengzhihao1@huawei.com Signed-off-by: Richard Weinberger richard@nod.at Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/mtd/ubi/fastmap-wl.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/mtd/ubi/fastmap-wl.c b/drivers/mtd/ubi/fastmap-wl.c index d9e2e3a6e105f..c44c8470247e1 100644 --- a/drivers/mtd/ubi/fastmap-wl.c +++ b/drivers/mtd/ubi/fastmap-wl.c @@ -196,7 +196,7 @@ static int produce_free_peb(struct ubi_device *ubi) */ int ubi_wl_get_peb(struct ubi_device *ubi) { - int ret, retried = 0; + int ret, attempts = 0; struct ubi_fm_pool *pool = &ubi->fm_pool; struct ubi_fm_pool *wl_pool = &ubi->fm_wl_pool;
@@ -221,12 +221,12 @@ int ubi_wl_get_peb(struct ubi_device *ubi)
if (pool->used == pool->size) { spin_unlock(&ubi->wl_lock); - if (retried) { + attempts++; + if (attempts == 10) { ubi_err(ubi, "Unable to get a free PEB from user WL pool"); ret = -ENOSPC; goto out; } - retried = 1; up_read(&ubi->fm_eba_sem); ret = produce_free_peb(ubi); if (ret < 0) {
From: Vlad Buslov vladbu@mellanox.com
[ Upstream commit 4ce70b4aed5752332b268909336b351721965dc4 ]
Recent changes that removed rtnl dependency from rules update path of tc also made tcf_block_put() function sleeping. This function is called from ops->destroy() of several Qdisc implementations, which in turn is called by qdisc_put(). Some Qdiscs call qdisc_put() while holding sch tree spinlock, which results sleeping-while-atomic BUG.
Steps to reproduce for htb:
tc qdisc add dev ens1f0 root handle 1: htb default 12 tc class add dev ens1f0 parent 1: classid 1:1 htb rate 100kbps ceil 100kbps tc qdisc add dev ens1f0 parent 1:1 handle 40: sfq perturb 10 tc class add dev ens1f0 parent 1:1 classid 1:2 htb rate 100kbps ceil 100kbps
Resulting dmesg:
[ 4791.148551] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:909 [ 4791.151354] in_atomic(): 1, irqs_disabled(): 0, pid: 27273, name: tc [ 4791.152805] INFO: lockdep is turned off. [ 4791.153605] CPU: 19 PID: 27273 Comm: tc Tainted: G W 5.3.0-rc8+ #721 [ 4791.154336] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 4791.155075] Call Trace: [ 4791.155803] dump_stack+0x85/0xc0 [ 4791.156529] ___might_sleep.cold+0xac/0xbc [ 4791.157251] __mutex_lock+0x5b/0x960 [ 4791.157966] ? console_unlock+0x363/0x5d0 [ 4791.158676] ? tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 4791.159395] ? tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 4791.160103] tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 4791.160815] tcf_block_put_ext.part.0+0x21/0x50 [ 4791.161530] tcf_block_put+0x50/0x70 [ 4791.162233] sfq_destroy+0x15/0x50 [sch_sfq] [ 4791.162936] qdisc_destroy+0x5f/0x160 [ 4791.163642] htb_change_class.cold+0x5df/0x69d [sch_htb] [ 4791.164505] tc_ctl_tclass+0x19d/0x480 [ 4791.165360] rtnetlink_rcv_msg+0x170/0x4b0 [ 4791.166191] ? netlink_deliver_tap+0x95/0x400 [ 4791.166907] ? rtnl_dellink+0x2d0/0x2d0 [ 4791.167625] netlink_rcv_skb+0x49/0x110 [ 4791.168345] netlink_unicast+0x171/0x200 [ 4791.169058] netlink_sendmsg+0x224/0x3f0 [ 4791.169771] sock_sendmsg+0x5e/0x60 [ 4791.170475] ___sys_sendmsg+0x2ae/0x330 [ 4791.171183] ? ___sys_recvmsg+0x159/0x1f0 [ 4791.171894] ? do_wp_page+0x9c/0x790 [ 4791.172595] ? __handle_mm_fault+0xcd3/0x19e0 [ 4791.173309] __sys_sendmsg+0x59/0xa0 [ 4791.174024] do_syscall_64+0x5c/0xb0 [ 4791.174725] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 4791.175435] RIP: 0033:0x7f0aa41497b8 [ 4791.176129] Code: 89 02 48 c7 c0 ff ff ff ff eb bb 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 8d 05 65 8f 0c 00 8b 00 85 c0 75 17 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 58 c3 0f 1f 80 00 00 00 00 48 83 ec 28 89 5 4 [ 4791.177532] RSP: 002b:00007fff4e37d588 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 4791.178243] RAX: ffffffffffffffda RBX: 000000005d8132f7 RCX: 00007f0aa41497b8 [ 4791.178947] RDX: 0000000000000000 RSI: 00007fff4e37d5f0 RDI: 0000000000000003 [ 4791.179662] RBP: 0000000000000000 R08: 0000000000000001 R09: 00000000020149a0 [ 4791.180382] R10: 0000000000404eda R11: 0000000000000246 R12: 0000000000000001 [ 4791.181100] R13: 000000000047f640 R14: 0000000000000000 R15: 0000000000000000
In htb_change_class() function save parent->leaf.q to local temporary variable and put reference to it after sch tree lock is released in order not to call potentially sleeping cls API in atomic section. This is safe to do because Qdisc has already been reset by qdisc_purge_queue() inside sch tree lock critical section.
Fixes: c266f64dbfa2 ("net: sched: protect block state with mutex") Signed-off-by: Vlad Buslov vladbu@mellanox.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/sch_htb.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 7bcf20ef91453..8184c87da8bec 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1302,6 +1302,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, struct htb_class *cl = (struct htb_class *)*arg, *parent; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_HTB_MAX + 1]; + struct Qdisc *parent_qdisc = NULL; struct tc_htb_opt *hopt; u64 rate64, ceil64; int warn = 0; @@ -1401,7 +1402,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (parent && !parent->level) { /* turn parent into inner node */ qdisc_purge_queue(parent->leaf.q); - qdisc_put(parent->leaf.q); + parent_qdisc = parent->leaf.q; if (parent->prio_activity) htb_deactivate(q, parent);
@@ -1480,6 +1481,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, cl->cbuffer = PSCHED_TICKS2NS(hopt->cbuffer);
sch_tree_unlock(sch); + qdisc_put(parent_qdisc);
if (warn) pr_warn("HTB: quantum of class %X is %s. Consider r2q change.\n",
From: Vlad Buslov vladbu@mellanox.com
[ Upstream commit c2999f7fb05b87da4060e38150c70fa46794d82b ]
Recent changes that removed rtnl dependency from rules update path of tc also made tcf_block_put() function sleeping. This function is called from ops->destroy() of several Qdisc implementations, which in turn is called by qdisc_put(). Some Qdiscs call qdisc_put() while holding sch tree spinlock, which results sleeping-while-atomic BUG.
Steps to reproduce for multiq:
tc qdisc add dev ens1f0 root handle 1: multiq tc qdisc add dev ens1f0 parent 1:10 handle 50: sfq perturb 10 ethtool -L ens1f0 combined 2 tc qdisc change dev ens1f0 root handle 1: multiq
Resulting dmesg:
[ 5539.419344] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:909 [ 5539.420945] in_atomic(): 1, irqs_disabled(): 0, pid: 27658, name: tc [ 5539.422435] INFO: lockdep is turned off. [ 5539.423904] CPU: 21 PID: 27658 Comm: tc Tainted: G W 5.3.0-rc8+ #721 [ 5539.425400] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 5539.426911] Call Trace: [ 5539.428380] dump_stack+0x85/0xc0 [ 5539.429823] ___might_sleep.cold+0xac/0xbc [ 5539.431262] __mutex_lock+0x5b/0x960 [ 5539.432682] ? tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 5539.434103] ? __nla_validate_parse+0x51/0x840 [ 5539.435493] ? tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 5539.436903] tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 5539.438327] tcf_block_put_ext.part.0+0x21/0x50 [ 5539.439752] tcf_block_put+0x50/0x70 [ 5539.441165] sfq_destroy+0x15/0x50 [sch_sfq] [ 5539.442570] qdisc_destroy+0x5f/0x160 [ 5539.444000] multiq_tune+0x14a/0x420 [sch_multiq] [ 5539.445421] tc_modify_qdisc+0x324/0x840 [ 5539.446841] rtnetlink_rcv_msg+0x170/0x4b0 [ 5539.448269] ? netlink_deliver_tap+0x95/0x400 [ 5539.449691] ? rtnl_dellink+0x2d0/0x2d0 [ 5539.451116] netlink_rcv_skb+0x49/0x110 [ 5539.452522] netlink_unicast+0x171/0x200 [ 5539.453914] netlink_sendmsg+0x224/0x3f0 [ 5539.455304] sock_sendmsg+0x5e/0x60 [ 5539.456686] ___sys_sendmsg+0x2ae/0x330 [ 5539.458071] ? ___sys_recvmsg+0x159/0x1f0 [ 5539.459461] ? do_wp_page+0x9c/0x790 [ 5539.460846] ? __handle_mm_fault+0xcd3/0x19e0 [ 5539.462263] __sys_sendmsg+0x59/0xa0 [ 5539.463661] do_syscall_64+0x5c/0xb0 [ 5539.465044] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 5539.466454] RIP: 0033:0x7f1fe08177b8 [ 5539.467863] Code: 89 02 48 c7 c0 ff ff ff ff eb bb 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 8d 05 65 8f 0c 00 8b 00 85 c0 75 17 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 58 c3 0f 1f 80 00 00 00 00 48 83 ec 28 89 5 4 [ 5539.470906] RSP: 002b:00007ffe812de5d8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 5539.472483] RAX: ffffffffffffffda RBX: 000000005d8135e3 RCX: 00007f1fe08177b8 [ 5539.474069] RDX: 0000000000000000 RSI: 00007ffe812de640 RDI: 0000000000000003 [ 5539.475655] RBP: 0000000000000000 R08: 0000000000000001 R09: 000000000182e9b0 [ 5539.477203] R10: 0000000000404eda R11: 0000000000000246 R12: 0000000000000001 [ 5539.478699] R13: 000000000047f640 R14: 0000000000000000 R15: 0000000000000000
Rearrange locking in multiq_tune() in following ways:
- In loop that removes Qdiscs from disabled queues, call qdisc_purge_queue() instead of qdisc_tree_flush_backlog() on Qdisc that is being destroyed. Save the Qdisc in temporary allocated array and call qdisc_put() on each element of the array after sch tree lock is released. This is safe to do because Qdiscs have already been reset by qdisc_purge_queue() inside sch tree lock critical section.
- Do the same change for second loop that initializes Qdiscs for newly enabled queues in multiq_tune() function. Since sch tree lock is obtained and released on each iteration of this loop, just call qdisc_put() directly outside of critical section. Don't verify that old Qdisc is not noop_qdisc before releasing reference to it because such check is already performed by qdisc_put*() functions.
Fixes: c266f64dbfa2 ("net: sched: protect block state with mutex") Signed-off-by: Vlad Buslov vladbu@mellanox.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/sch_multiq.c | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-)
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index e1087746f6a29..b2b7fdb06fc62 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -174,7 +174,8 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, { struct multiq_sched_data *q = qdisc_priv(sch); struct tc_multiq_qopt *qopt; - int i; + struct Qdisc **removed; + int i, n_removed = 0;
if (!netif_is_multiqueue(qdisc_dev(sch))) return -EOPNOTSUPP; @@ -185,6 +186,11 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt,
qopt->bands = qdisc_dev(sch)->real_num_tx_queues;
+ removed = kmalloc(sizeof(*removed) * (q->max_bands - q->bands), + GFP_KERNEL); + if (!removed) + return -ENOMEM; + sch_tree_lock(sch); q->bands = qopt->bands; for (i = q->bands; i < q->max_bands; i++) { @@ -192,13 +198,17 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, struct Qdisc *child = q->queues[i];
q->queues[i] = &noop_qdisc; - qdisc_tree_flush_backlog(child); - qdisc_put(child); + qdisc_purge_queue(child); + removed[n_removed++] = child; } }
sch_tree_unlock(sch);
+ for (i = 0; i < n_removed; i++) + qdisc_put(removed[i]); + kfree(removed); + for (i = 0; i < q->bands; i++) { if (q->queues[i] == &noop_qdisc) { struct Qdisc *child, *old; @@ -213,11 +223,10 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt, if (child != &noop_qdisc) qdisc_hash_add(child, true);
- if (old != &noop_qdisc) { - qdisc_tree_flush_backlog(old); - qdisc_put(old); - } + if (old != &noop_qdisc) + qdisc_purge_queue(old); sch_tree_unlock(sch); + qdisc_put(old); } } }
From: Krishnamraju Eraparaju krishna2@chelsio.com
[ Upstream commit df791c54d627bae53c9be3be40a69594c55de487 ]
In siw_qp_llp_write_space(), 'sock' members should be accessed with sk_callback_lock held, otherwise, it could race with siw_sk_restore_upcalls(). And this could cause "NULL deref" panic. Below panic is due to the NULL cep returned from sk_to_cep(sk):
Call Trace: <IRQ> siw_qp_llp_write_space+0x11/0x40 [siw] tcp_check_space+0x4c/0xf0 tcp_rcv_established+0x52b/0x630 tcp_v4_do_rcv+0xf4/0x1e0 tcp_v4_rcv+0x9b8/0xab0 ip_protocol_deliver_rcu+0x2c/0x1c0 ip_local_deliver_finish+0x44/0x50 ip_local_deliver+0x6b/0xf0 ? ip_protocol_deliver_rcu+0x1c0/0x1c0 ip_rcv+0x52/0xd0 ? ip_rcv_finish_core.isra.14+0x390/0x390 __netif_receive_skb_one_core+0x83/0xa0 netif_receive_skb_internal+0x73/0xb0 napi_gro_frags+0x1ff/0x2b0 t4_ethrx_handler+0x4a7/0x740 [cxgb4] process_responses+0x2c9/0x590 [cxgb4] ? t4_sge_intr_msix+0x1d/0x30 [cxgb4] ? handle_irq_event_percpu+0x51/0x70 ? handle_irq_event+0x41/0x60 ? handle_edge_irq+0x97/0x1a0 napi_rx_handler+0x14/0xe0 [cxgb4] net_rx_action+0x2af/0x410 __do_softirq+0xda/0x2a8 do_softirq_own_stack+0x2a/0x40 </IRQ> do_softirq+0x50/0x60 __local_bh_enable_ip+0x50/0x60 ip_finish_output2+0x18f/0x520 ip_output+0x6e/0xf0 ? __ip_finish_output+0x1f0/0x1f0 __ip_queue_xmit+0x14f/0x3d0 ? __slab_alloc+0x4b/0x58 __tcp_transmit_skb+0x57d/0xa60 tcp_write_xmit+0x23b/0xfd0 __tcp_push_pending_frames+0x2e/0xf0 tcp_sendmsg_locked+0x939/0xd50 tcp_sendmsg+0x27/0x40 sock_sendmsg+0x57/0x80 siw_tx_hdt+0x894/0xb20 [siw] ? find_busiest_group+0x3e/0x5b0 ? common_interrupt+0xa/0xf ? common_interrupt+0xa/0xf ? common_interrupt+0xa/0xf siw_qp_sq_process+0xf1/0xe60 [siw] ? __wake_up_common_lock+0x87/0xc0 siw_sq_resume+0x33/0xe0 [siw] siw_run_sq+0xac/0x190 [siw] ? remove_wait_queue+0x60/0x60 kthread+0xf8/0x130 ? siw_sq_resume+0xe0/0xe0 [siw] ? kthread_bind+0x10/0x10 ret_from_fork+0x35/0x40
Fixes: f29dd55b0236 ("rdma/siw: queue pair methods") Link: https://lore.kernel.org/r/20190923101112.32685-1-krishna2@chelsio.com Signed-off-by: Krishnamraju Eraparaju krishna2@chelsio.com Reviewed-by: Bernard Metzler bmt@zurich.ibm.com Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/sw/siw/siw_qp.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-)
diff --git a/drivers/infiniband/sw/siw/siw_qp.c b/drivers/infiniband/sw/siw/siw_qp.c index 430314c8abd94..52d402f39df93 100644 --- a/drivers/infiniband/sw/siw/siw_qp.c +++ b/drivers/infiniband/sw/siw/siw_qp.c @@ -182,12 +182,19 @@ void siw_qp_llp_close(struct siw_qp *qp) */ void siw_qp_llp_write_space(struct sock *sk) { - struct siw_cep *cep = sk_to_cep(sk); + struct siw_cep *cep;
- cep->sk_write_space(sk); + read_lock(&sk->sk_callback_lock); + + cep = sk_to_cep(sk); + if (cep) { + cep->sk_write_space(sk);
- if (!test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) - (void)siw_sq_start(cep->qp); + if (!test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) + (void)siw_sq_start(cep->qp); + } + + read_unlock(&sk->sk_callback_lock); }
static int siw_qp_readq_init(struct siw_qp *qp, int irq_size, int orq_size)
From: Bart Van Assche bvanassche@acm.org
[ Upstream commit b66f31efbdad95ec274345721d99d1d835e6de01 ]
This patch fixes the lock inversion complaint:
============================================ WARNING: possible recursive locking detected 5.3.0-rc7-dbg+ #1 Not tainted -------------------------------------------- kworker/u16:6/171 is trying to acquire lock: 00000000035c6e6c (&id_priv->handler_mutex){+.+.}, at: rdma_destroy_id+0x78/0x4a0 [rdma_cm]
but task is already holding lock: 00000000bc7c307d (&id_priv->handler_mutex){+.+.}, at: iw_conn_req_handler+0x151/0x680 [rdma_cm]
other info that might help us debug this: Possible unsafe locking scenario:
CPU0 ---- lock(&id_priv->handler_mutex); lock(&id_priv->handler_mutex);
*** DEADLOCK ***
May be due to missing lock nesting notation
3 locks held by kworker/u16:6/171: #0: 00000000e2eaa773 ((wq_completion)iw_cm_wq){+.+.}, at: process_one_work+0x472/0xac0 #1: 000000001efd357b ((work_completion)(&work->work)#3){+.+.}, at: process_one_work+0x476/0xac0 #2: 00000000bc7c307d (&id_priv->handler_mutex){+.+.}, at: iw_conn_req_handler+0x151/0x680 [rdma_cm]
stack backtrace: CPU: 3 PID: 171 Comm: kworker/u16:6 Not tainted 5.3.0-rc7-dbg+ #1 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 Workqueue: iw_cm_wq cm_work_handler [iw_cm] Call Trace: dump_stack+0x8a/0xd6 __lock_acquire.cold+0xe1/0x24d lock_acquire+0x106/0x240 __mutex_lock+0x12e/0xcb0 mutex_lock_nested+0x1f/0x30 rdma_destroy_id+0x78/0x4a0 [rdma_cm] iw_conn_req_handler+0x5c9/0x680 [rdma_cm] cm_work_handler+0xe62/0x1100 [iw_cm] process_one_work+0x56d/0xac0 worker_thread+0x7a/0x5d0 kthread+0x1bc/0x210 ret_from_fork+0x24/0x30
This is not a bug as there are actually two lock classes here.
Link: https://lore.kernel.org/r/20190930231707.48259-3-bvanassche@acm.org Fixes: de910bd92137 ("RDMA/cma: Simplify locking needed for serialization of callbacks") Signed-off-by: Bart Van Assche bvanassche@acm.org Reviewed-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/core/cma.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index a68d0ccf67a43..2e48b59926c19 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -2396,9 +2396,10 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id, conn_id->cm_id.iw = NULL; cma_exch(conn_id, RDMA_CM_DESTROYING); mutex_unlock(&conn_id->handler_mutex); + mutex_unlock(&listen_id->handler_mutex); cma_deref_id(conn_id); rdma_destroy_id(&conn_id->id); - goto out; + return ret; }
mutex_unlock(&conn_id->handler_mutex);
From: David Ahern dsahern@gmail.com
[ Upstream commit a3ce2a21bb8969ae27917281244fa91bf5f286d7 ]
Rajendra reported a kernel panic when a link was taken down:
[ 6870.263084] BUG: unable to handle kernel NULL pointer dereference at 00000000000000a8 [ 6870.271856] IP: [<ffffffff8efc5764>] __ipv6_ifa_notify+0x154/0x290
<snip>
[ 6870.570501] Call Trace: [ 6870.573238] [<ffffffff8efc58c6>] ? ipv6_ifa_notify+0x26/0x40 [ 6870.579665] [<ffffffff8efc98ec>] ? addrconf_dad_completed+0x4c/0x2c0 [ 6870.586869] [<ffffffff8efe70c6>] ? ipv6_dev_mc_inc+0x196/0x260 [ 6870.593491] [<ffffffff8efc9c6a>] ? addrconf_dad_work+0x10a/0x430 [ 6870.600305] [<ffffffff8f01ade4>] ? __switch_to_asm+0x34/0x70 [ 6870.606732] [<ffffffff8ea93a7a>] ? process_one_work+0x18a/0x430 [ 6870.613449] [<ffffffff8ea93d6d>] ? worker_thread+0x4d/0x490 [ 6870.619778] [<ffffffff8ea93d20>] ? process_one_work+0x430/0x430 [ 6870.626495] [<ffffffff8ea99dd9>] ? kthread+0xd9/0xf0 [ 6870.632145] [<ffffffff8f01ade4>] ? __switch_to_asm+0x34/0x70 [ 6870.638573] [<ffffffff8ea99d00>] ? kthread_park+0x60/0x60 [ 6870.644707] [<ffffffff8f01ae77>] ? ret_from_fork+0x57/0x70 [ 6870.650936] Code: 31 c0 31 d2 41 b9 20 00 08 02 b9 09 00 00 0
addrconf_dad_work is kicked to be scheduled when a device is brought up. There is a race between addrcond_dad_work getting scheduled and taking the rtnl lock and a process taking the link down (under rtnl). The latter removes the host route from the inet6_addr as part of addrconf_ifdown which is run for NETDEV_DOWN. The former attempts to use the host route in ipv6_ifa_notify. If the down event removes the host route due to the race to the rtnl, then the BUG listed above occurs.
This scenario does not occur when the ipv6 address is not kept (net.ipv6.conf.all.keep_addr_on_down = 0) as addrconf_ifdown sets the state of the ifp to DEAD. Handle when the addresses are kept by checking IF_READY which is reset by addrconf_ifdown.
The 'dead' flag for an inet6_addr is set only under rtnl, in addrconf_ifdown and it means the device is getting removed (or IPv6 is disabled). The interesting cases for changing the idev flag are addrconf_notify (NETDEV_UP and NETDEV_CHANGE) and addrconf_ifdown (reset the flag). The former does not have the idev lock - only rtnl; the latter has both. Based on that the existing dead + IF_READY check can be moved to right after the rtnl_lock in addrconf_dad_work.
Fixes: f1705ec197e7 ("net: ipv6: Make address flushing on ifdown optional") Reported-by: Rajendra Dendukuri rajendra.dendukuri@broadcom.com Signed-off-by: David Ahern dsahern@gmail.com Reviewed-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/addrconf.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 4c87594d1389d..10093b8dd5483 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4032,6 +4032,12 @@ static void addrconf_dad_work(struct work_struct *w)
rtnl_lock();
+ /* check if device was taken down before this delayed work + * function could be canceled + */ + if (idev->dead || !(idev->if_flags & IF_READY)) + goto out; + spin_lock_bh(&ifp->lock); if (ifp->state == INET6_IFADDR_STATE_PREDAD) { action = DAD_BEGIN; @@ -4077,11 +4083,6 @@ static void addrconf_dad_work(struct work_struct *w) goto out;
write_lock_bh(&idev->lock); - if (idev->dead || !(idev->if_flags & IF_READY)) { - write_unlock_bh(&idev->lock); - goto out; - } - spin_lock(&ifp->lock); if (ifp->state == INET6_IFADDR_STATE_DEAD) { spin_unlock(&ifp->lock);
From: Mika Westerberg mika.westerberg@linux.intel.com
[ Upstream commit a2b90f11217790ec0964ba9c93a4abb369758c26 ]
A removable block device, such as NVMe or SSD connected over Thunderbolt can be hot-removed any time including when the system is suspended. When device is hot-removed during suspend and the system gets resumed, kernel first resumes devices and then thaws the userspace including freezable workqueues. What happens in that case is that the NVMe driver notices that the device is unplugged and removes it from the system. This ends up calling bdi_unregister() for the gendisk which then schedules wb_workfn() to be run one more time.
However, since the bdi_wq is still frozen flush_delayed_work() call in wb_shutdown() blocks forever halting system resume process. User sees this as hang as nothing is happening anymore.
Triggering sysrq-w reveals this:
Workqueue: nvme-wq nvme_remove_dead_ctrl_work [nvme] Call Trace: ? __schedule+0x2c5/0x630 ? wait_for_completion+0xa4/0x120 schedule+0x3e/0xc0 schedule_timeout+0x1c9/0x320 ? resched_curr+0x1f/0xd0 ? wait_for_completion+0xa4/0x120 wait_for_completion+0xc3/0x120 ? wake_up_q+0x60/0x60 __flush_work+0x131/0x1e0 ? flush_workqueue_prep_pwqs+0x130/0x130 bdi_unregister+0xb9/0x130 del_gendisk+0x2d2/0x2e0 nvme_ns_remove+0xed/0x110 [nvme_core] nvme_remove_namespaces+0x96/0xd0 [nvme_core] nvme_remove+0x5b/0x160 [nvme] pci_device_remove+0x36/0x90 device_release_driver_internal+0xdf/0x1c0 nvme_remove_dead_ctrl_work+0x14/0x30 [nvme] process_one_work+0x1c2/0x3f0 worker_thread+0x48/0x3e0 kthread+0x100/0x140 ? current_work+0x30/0x30 ? kthread_park+0x80/0x80 ret_from_fork+0x35/0x40
This is not limited to NVMes so exactly same issue can be reproduced by hot-removing SSD (over Thunderbolt) while the system is suspended.
Prevent this from happening by removing WQ_FREEZABLE from bdi_wq.
Reported-by: AceLan Kao acelan.kao@canonical.com Link: https://marc.info/?l=linux-kernel&m=138695698516487 Link: https://bugzilla.kernel.org/show_bug.cgi?id=204385 Link: https://lore.kernel.org/lkml/20191002122136.GD2819@lahna.fi.intel.com/#t Acked-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Mika Westerberg mika.westerberg@linux.intel.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- mm/backing-dev.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/mm/backing-dev.c b/mm/backing-dev.c index e8e89158adec6..553372b39178c 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -236,8 +236,8 @@ static int __init default_bdi_init(void) { int err;
- bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_FREEZABLE | - WQ_UNBOUND | WQ_SYSFS, 0); + bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_UNBOUND | + WQ_SYSFS, 0); if (!bdi_wq) return -ENOMEM;
From: Xin Long lucien.xin@gmail.com
[ Upstream commit 819be8108fded0b9e710bbbf81193e52f7bab2f7 ]
This patch is to fix a NULL-ptr deref in selinux_socket_connect_helper:
[...] kasan: GPF could be caused by NULL-ptr deref or user memory access [...] RIP: 0010:selinux_socket_connect_helper+0x94/0x460 [...] Call Trace: [...] selinux_sctp_bind_connect+0x16a/0x1d0 [...] security_sctp_bind_connect+0x58/0x90 [...] sctp_process_asconf+0xa52/0xfd0 [sctp] [...] sctp_sf_do_asconf+0x785/0x980 [sctp] [...] sctp_do_sm+0x175/0x5a0 [sctp] [...] sctp_assoc_bh_rcv+0x285/0x5b0 [sctp] [...] sctp_backlog_rcv+0x482/0x910 [sctp] [...] __release_sock+0x11e/0x310 [...] release_sock+0x4f/0x180 [...] sctp_accept+0x3f9/0x5a0 [sctp] [...] inet_accept+0xe7/0x720
It was caused by that the 'newsk' sk_socket was not set before going to security sctp hook when processing asconf chunk with SCTP_PARAM_ADD_IP or SCTP_PARAM_SET_PRIMARY:
inet_accept()-> sctp_accept(): lock_sock(): lock listening 'sk' do_softirq(): sctp_rcv(): <-- [1] asconf chunk arrives and enqueued in 'sk' backlog sctp_sock_migrate(): set asoc's sk to 'newsk' release_sock(): sctp_backlog_rcv(): lock 'newsk' sctp_process_asconf() <-- [2] unlock 'newsk' sock_graft(): set sk_socket <-- [3]
As it shows, at [1] the asconf chunk would be put into the listening 'sk' backlog, as accept() was holding its sock lock. Then at [2] asconf would get processed with 'newsk' as asoc's sk had been set to 'newsk'. However, 'newsk' sk_socket is not set until [3], while selinux_sctp_bind_connect() would deref it, then kernel crashed.
Here to fix it by adding the chunk to sk_backlog until newsk sk_socket is set when .accept() is done.
Note that sk->sk_socket can be NULL when the sock is closed, so SOCK_DEAD flag is also needed to check in sctp_newsk_ready().
Thanks to Ondrej for reviewing the code.
Fixes: d452930fd3b9 ("selinux: Add SCTP support") Reported-by: Ying Xu yinxu@redhat.com Suggested-by: Marcelo Ricardo Leitner marcelo.leitner@gmail.com Signed-off-by: Xin Long lucien.xin@gmail.com Acked-by: Marcelo Ricardo Leitner marcelo.leitner@gmail.com Acked-by: Neil Horman nhorman@tuxdriver.com Signed-off-by: Jakub Kicinski jakub.kicinski@netronome.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/sctp/sctp.h | 5 +++++ net/sctp/input.c | 12 +++++++++--- 2 files changed, 14 insertions(+), 3 deletions(-)
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 5d60f13d2347b..3ab5c6bbb90bd 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -610,4 +610,9 @@ static inline __u32 sctp_min_frag_point(struct sctp_sock *sp, __u16 datasize) return sctp_mtu_payload(sp, SCTP_DEFAULT_MINSEGMENT, datasize); }
+static inline bool sctp_newsk_ready(const struct sock *sk) +{ + return sock_flag(sk, SOCK_DEAD) || sk->sk_socket; +} + #endif /* __net_sctp_h__ */ diff --git a/net/sctp/input.c b/net/sctp/input.c index 1008cdc44dd61..156e24ad54ea4 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -243,7 +243,7 @@ int sctp_rcv(struct sk_buff *skb) bh_lock_sock(sk); }
- if (sock_owned_by_user(sk)) { + if (sock_owned_by_user(sk) || !sctp_newsk_ready(sk)) { if (sctp_add_backlog(sk, skb)) { bh_unlock_sock(sk); sctp_chunk_free(chunk); @@ -321,7 +321,7 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) local_bh_disable(); bh_lock_sock(sk);
- if (sock_owned_by_user(sk)) { + if (sock_owned_by_user(sk) || !sctp_newsk_ready(sk)) { if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) sctp_chunk_free(chunk); else @@ -336,7 +336,13 @@ int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb) if (backloged) return 0; } else { - sctp_inq_push(inqueue, chunk); + if (!sctp_newsk_ready(sk)) { + if (!sk_add_backlog(sk, skb, sk->sk_rcvbuf)) + return 0; + sctp_chunk_free(chunk); + } else { + sctp_inq_push(inqueue, chunk); + } }
done:
From: Takashi Iwai tiwai@suse.de
[ Upstream commit ee5f85d9290fe25d460bd320b7fe073075d72d33 ]
The call of snd_hdac_bus_add_device() is needed only for registering the codec onto the bus caddr_tbl[] that is referred essentially only in the unsol event handler. That is, the reason of this call and the release by the counter-part function snd_hdac_bus_remove_device() is just to assure that the unsol event gets notified to the codec.
But the current implementation of the unsol notification wouldn't work properly when the codec is still in a premature init state. So this patch tries to work around it by delaying the caddr_tbl[] registration at the point of snd_hdac_device_register().
Also, the order of snd_hdac_bus_remove_device() and device_del() calls are shuffled to make sure that the unsol event is masked before deleting the device.
BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=204565 Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/hda/hdac_device.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-)
diff --git a/sound/hda/hdac_device.c b/sound/hda/hdac_device.c index b26cc93e7e103..033bcef8751a8 100644 --- a/sound/hda/hdac_device.c +++ b/sound/hda/hdac_device.c @@ -61,10 +61,6 @@ int snd_hdac_device_init(struct hdac_device *codec, struct hdac_bus *bus, pm_runtime_get_noresume(&codec->dev); atomic_set(&codec->in_pm, 0);
- err = snd_hdac_bus_add_device(bus, codec); - if (err < 0) - goto error; - /* fill parameters */ codec->vendor_id = snd_hdac_read_parm(codec, AC_NODE_ROOT, AC_PAR_VENDOR_ID); @@ -143,15 +139,22 @@ int snd_hdac_device_register(struct hdac_device *codec) err = device_add(&codec->dev); if (err < 0) return err; + err = snd_hdac_bus_add_device(codec->bus, codec); + if (err < 0) + goto error; mutex_lock(&codec->widget_lock); err = hda_widget_sysfs_init(codec); mutex_unlock(&codec->widget_lock); - if (err < 0) { - device_del(&codec->dev); - return err; - } + if (err < 0) + goto error_remove;
return 0; + + error_remove: + snd_hdac_bus_remove_device(codec->bus, codec); + error: + device_del(&codec->dev); + return err; } EXPORT_SYMBOL_GPL(snd_hdac_device_register);
@@ -165,8 +168,8 @@ void snd_hdac_device_unregister(struct hdac_device *codec) mutex_lock(&codec->widget_lock); hda_widget_sysfs_exit(codec); mutex_unlock(&codec->widget_lock); - device_del(&codec->dev); snd_hdac_bus_remove_device(codec->bus, codec); + device_del(&codec->dev); } } EXPORT_SYMBOL_GPL(snd_hdac_device_unregister);
From: Jian-Hong Pan jian-hong@endlessm.com
[ Upstream commit 19ea025e1d28c629b369c3532a85b3df478cc5c6 ]
Kingston NVME SSD with firmware version E8FK11.T has no interrupt after resume with actions related to suspend to idle. This patch applied NVME_QUIRK_SIMPLE_SUSPEND quirk to fix this issue.
Fixes: d916b1be94b6 ("nvme-pci: use host managed power state for suspend") Buglink: https://bugzilla.kernel.org/show_bug.cgi?id=204887 Signed-off-by: Jian-Hong Pan jian-hong@endlessm.com Signed-off-by: Sagi Grimberg sagi@grimberg.me Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/core.c | 10 ++++++++++ 1 file changed, 10 insertions(+)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index d3d6b7bd69033..079da1c613f04 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2267,6 +2267,16 @@ static const struct nvme_core_quirk_entry core_quirks[] = { .vid = 0x14a4, .fr = "22301111", .quirks = NVME_QUIRK_SIMPLE_SUSPEND, + }, + { + /* + * This Kingston E8FK11.T firmware version has no interrupt + * after resume with actions related to suspend to idle + * https://bugzilla.kernel.org/show_bug.cgi?id=204887 + */ + .vid = 0x2646, + .fr = "E8FK11.T", + .quirks = NVME_QUIRK_SIMPLE_SUSPEND, } };
linux-stable-mirror@lists.linaro.org
-
Sasha Levin