linux-stable.git/net, branch v5.4.99

net/qrtr: restrict user-controlled length in qrtr_tun_write_iter()

2021-02-17T09:35:19+00:00

commit 2a80c15812372e554474b1dba0b1d8e467af295d upstream.

syzbot found WARNING in qrtr_tun_write_iter [1] when write_iter length
exceeds KMALLOC_MAX_SIZE causing order >= MAX_ORDER condition.

Additionally, there is no check for 0 length write.

[1]
WARNING: mm/page_alloc.c:5011
[..]
Call Trace:
 alloc_pages_current+0x18c/0x2a0 mm/mempolicy.c:2267
 alloc_pages include/linux/gfp.h:547 [inline]
 kmalloc_order+0x2e/0xb0 mm/slab_common.c:837
 kmalloc_order_trace+0x14/0x120 mm/slab_common.c:853
 kmalloc include/linux/slab.h:557 [inline]
 kzalloc include/linux/slab.h:682 [inline]
 qrtr_tun_write_iter+0x8a/0x180 net/qrtr/tun.c:83
 call_write_iter include/linux/fs.h:1901 [inline]

Reported-by: syzbot+c2a7e5c5211605a90865@syzkaller.appspotmail.com
Signed-off-by: Sabyrzhan Tasbolatov 
Link: https://lore.kernel.org/r/20210202092059.1361381-1-snovitoll@gmail.com
Signed-off-by: Jakub Kicinski 
Signed-off-by: Greg Kroah-Hartman

net/rds: restrict iovecs length for RDS_CMSG_RDMA_ARGS

2021-02-17T09:35:19+00:00

commit a11148e6fcce2ae53f47f0a442d098d860b4f7db upstream.

syzbot found WARNING in rds_rdma_extra_size [1] when RDS_CMSG_RDMA_ARGS
control message is passed with user-controlled
0x40001 bytes of args->nr_local, causing order >= MAX_ORDER condition.

The exact value 0x40001 can be checked with UIO_MAXIOV which is 0x400.
So for kcalloc() 0x400 iovecs with sizeof(struct rds_iovec) = 0x10
is the closest limit, with 0x10 leftover.

Same condition is currently done in rds_cmsg_rdma_args().

[1] WARNING: mm/page_alloc.c:5011
[..]
Call Trace:
 alloc_pages_current+0x18c/0x2a0 mm/mempolicy.c:2267
 alloc_pages include/linux/gfp.h:547 [inline]
 kmalloc_order+0x2e/0xb0 mm/slab_common.c:837
 kmalloc_order_trace+0x14/0x120 mm/slab_common.c:853
 kmalloc_array include/linux/slab.h:592 [inline]
 kcalloc include/linux/slab.h:621 [inline]
 rds_rdma_extra_size+0xb2/0x3b0 net/rds/rdma.c:568
 rds_rm_size net/rds/send.c:928 [inline]

Reported-by: syzbot+1bd2b07f93745fa38425@syzkaller.appspotmail.com
Signed-off-by: Sabyrzhan Tasbolatov 
Acked-by: Santosh Shilimkar 
Link: https://lore.kernel.org/r/20210201203233.1324704-1-snovitoll@gmail.com
Signed-off-by: Jakub Kicinski 
Signed-off-by: Greg Kroah-Hartman

vsock: fix locking in vsock_shutdown()

2021-02-17T09:35:19+00:00

commit 1c5fae9c9a092574398a17facc31c533791ef232 upstream.

In vsock_shutdown() we touched some socket fields without holding the
socket lock, such as 'state' and 'sk_flags'.

Also, after the introduction of multi-transport, we are accessing
'vsk->transport' in vsock_send_shutdown() without holding the lock
and this call can be made while the connection is in progress, so
the transport can change in the meantime.

To avoid issues, we hold the socket lock when we enter in
vsock_shutdown() and release it when we leave.

Among the transports that implement the 'shutdown' callback, only
hyperv_transport acquired the lock. Since the caller now holds it,
we no longer take it.

Fixes: d021c344051a ("VSOCK: Introduce VM Sockets")
Signed-off-by: Stefano Garzarella 
Signed-off-by: David S. Miller 
Signed-off-by: Greg Kroah-Hartman

vsock/virtio: update credit only if socket is not closed

2021-02-17T09:35:19+00:00

commit ce7536bc7398e2ae552d2fabb7e0e371a9f1fe46 upstream.

If the socket is closed or is being released, some resources used by
virtio_transport_space_update() such as 'vsk->trans' may be released.

To avoid a use after free bug we should only update the available credit
when we are sure the socket is still open and we have the lock held.

Fixes: 06a8fc78367d ("VSOCK: Introduce virtio_vsock_common.ko")
Signed-off-by: Stefano Garzarella 
Acked-by: Michael S. Tsirkin 
Link: https://lore.kernel.org/r/20210208144454.84438-1-sgarzare@redhat.com
Signed-off-by: Jakub Kicinski 
Signed-off-by: Greg Kroah-Hartman

net/vmw_vsock: improve locking in vsock_connect_timeout()

2021-02-17T09:35:19+00:00

commit 3d0bc44d39bca615b72637e340317b7899b7f911 upstream.

A possible locking issue in vsock_connect_timeout() was recognized by
Eric Dumazet which might cause a null pointer dereference in
vsock_transport_cancel_pkt(). This patch assures that
vsock_transport_cancel_pkt() will be called within the lock, so a race
condition won't occur which could result in vsk->transport to be set to NULL.

Fixes: 380feae0def7 ("vsock: cancel packets when failing to connect")
Reported-by: Eric Dumazet 
Signed-off-by: Norbert Slusarek 
Reviewed-by: Stefano Garzarella 
Link: https://lore.kernel.org/r/trinity-f8e0937a-cf0e-4d80-a76e-d9a958ba3ef1-1612535522360@3c-app-gmx-bap12
Signed-off-by: Jakub Kicinski 
Signed-off-by: Greg Kroah-Hartman

net: fix iteration for sctp transport seq_files

2021-02-17T09:35:19+00:00

commit af8085f3a4712c57d0dd415ad543bac85780375c upstream.

The sctp transport seq_file iterators take a reference to the transport
in the ->start and ->next functions and releases the reference in the
->show function.  The preferred handling for such resources is to
release them in the subsequent ->next or ->stop function call.

Since Commit 1f4aace60b0e ("fs/seq_file.c: simplify seq_file iteration
code and interface") there is no guarantee that ->show will be called
after ->next, so this function can now leak references.

So move the sctp_transport_put() call to ->next and ->stop.

Fixes: 1f4aace60b0e ("fs/seq_file.c: simplify seq_file iteration code and interface")
Reported-by: Xin Long 
Signed-off-by: NeilBrown 
Acked-by: Marcelo Ricardo Leitner 
Signed-off-by: Jakub Kicinski 
Signed-off-by: Greg Kroah-Hartman

net: gro: do not keep too many GRO packets in napi->rx_list

2021-02-17T09:35:19+00:00

commit 8dc1c444df193701910f5e80b5d4caaf705a8fb0 upstream.

Commit c80794323e82 ("net: Fix packet reordering caused by GRO and
listified RX cooperation") had the unfortunate effect of adding
latencies in common workloads.

Before the patch, GRO packets were immediately passed to
upper stacks.

After the patch, we can accumulate quite a lot of GRO
packets (depdending on NAPI budget).

My fix is counting in napi->rx_count number of segments
instead of number of logical packets.

Fixes: c80794323e82 ("net: Fix packet reordering caused by GRO and listified RX cooperation")
Signed-off-by: Eric Dumazet 
Bisected-by: John Sperbeck 
Tested-by: Jian Yang 
Cc: Maxim Mikityanskiy 
Reviewed-by: Saeed Mahameed 
Reviewed-by: Edward Cree 
Reviewed-by: Alexander Lobakin 
Link: https://lore.kernel.org/r/20210204213146.4192368-1-eric.dumazet@gmail.com
Signed-off-by: Jakub Kicinski 
Signed-off-by: Greg Kroah-Hartman

net: dsa: call teardown method on probe failure

2021-02-17T09:35:19+00:00

commit 8fd54a73b7cda11548154451bdb4bde6d8ff74c7 upstream.

Since teardown is supposed to undo the effects of the setup method, it
should be called in the error path for dsa_switch_setup, not just in
dsa_switch_teardown.

Fixes: 5e3f847a02aa ("net: dsa: Add teardown callback for drivers")
Signed-off-by: Vladimir Oltean 
Reviewed-by: Andrew Lunn 
Reviewed-by: Florian Fainelli 
Link: https://lore.kernel.org/r/20210204163351.2929670-1-vladimir.oltean@nxp.com
Signed-off-by: Jakub Kicinski 
Signed-off-by: Greg Kroah-Hartman

udp: fix skb_copy_and_csum_datagram with odd segment sizes

2021-02-17T09:35:19+00:00

commit 52cbd23a119c6ebf40a527e53f3402d2ea38eccb upstream.

When iteratively computing a checksum with csum_block_add, track the
offset "pos" to correctly rotate in csum_block_add when offset is odd.

The open coded implementation of skb_copy_and_csum_datagram did this.
With the switch to __skb_datagram_iter calling csum_and_copy_to_iter,
pos was reinitialized to 0 on each call.

Bring back the pos by passing it along with the csum to the callback.

Changes v1->v2
  - pass csum value, instead of csump pointer (Alexander Duyck)

Link: https://lore.kernel.org/netdev/20210128152353.GB27281@optiplex/
Fixes: 950fcaecd5cc ("datagram: consolidate datagram copy to iter helpers")
Reported-by: Oliver Graute 
Signed-off-by: Willem de Bruijn 
Reviewed-by: Alexander Duyck 
Reviewed-by: Eric Dumazet 
Link: https://lore.kernel.org/r/20210203192952.1849843-1-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski 
Signed-off-by: Greg Kroah-Hartman

rxrpc: Fix clearance of Tx/Rx ring when releasing a call

2021-02-17T09:35:18+00:00

commit 7b5eab57cac45e270a0ad624ba157c5b30b3d44d upstream.

At the end of rxrpc_release_call(), rxrpc_cleanup_ring() is called to clear
the Rx/Tx skbuff ring, but this doesn't lock the ring whilst it's accessing
it.  Unfortunately, rxrpc_resend() might be trying to retransmit a packet
concurrently with this - and whilst it does lock the ring, this isn't
protection against rxrpc_cleanup_call().

Fix this by removing the call to rxrpc_cleanup_ring() from
rxrpc_release_call().  rxrpc_cleanup_ring() will be called again anyway
from rxrpc_cleanup_call().  The earlier call is just an optimisation to
recycle skbuffs more quickly.

Alternative solutions include rxrpc_release_call() could try to cancel the
work item or wait for it to complete or rxrpc_cleanup_ring() could lock
when accessing the ring (which would require a bh lock).

This can produce a report like the following:

  BUG: KASAN: use-after-free in rxrpc_send_data_packet+0x19b4/0x1e70 net/rxrpc/output.c:372
  Read of size 4 at addr ffff888011606e04 by task kworker/0:0/5
  ...
  Workqueue: krxrpcd rxrpc_process_call
  Call Trace:
   ...
   kasan_report.cold+0x79/0xd5 mm/kasan/report.c:413
   rxrpc_send_data_packet+0x19b4/0x1e70 net/rxrpc/output.c:372
   rxrpc_resend net/rxrpc/call_event.c:266 [inline]
   rxrpc_process_call+0x1634/0x1f60 net/rxrpc/call_event.c:412
   process_one_work+0x98d/0x15f0 kernel/workqueue.c:2275
   ...

  Allocated by task 2318:
   ...
   sock_alloc_send_pskb+0x793/0x920 net/core/sock.c:2348
   rxrpc_send_data+0xb51/0x2bf0 net/rxrpc/sendmsg.c:358
   rxrpc_do_sendmsg+0xc03/0x1350 net/rxrpc/sendmsg.c:744
   rxrpc_sendmsg+0x420/0x630 net/rxrpc/af_rxrpc.c:560
   ...

  Freed by task 2318:
   ...
   kfree_skb+0x140/0x3f0 net/core/skbuff.c:704
   rxrpc_free_skb+0x11d/0x150 net/rxrpc/skbuff.c:78
   rxrpc_cleanup_ring net/rxrpc/call_object.c:485 [inline]
   rxrpc_release_call+0x5dd/0x860 net/rxrpc/call_object.c:552
   rxrpc_release_calls_on_socket+0x21c/0x300 net/rxrpc/call_object.c:579
   rxrpc_release_sock net/rxrpc/af_rxrpc.c:885 [inline]
   rxrpc_release+0x263/0x5a0 net/rxrpc/af_rxrpc.c:916
   __sock_release+0xcd/0x280 net/socket.c:597
   ...

  The buggy address belongs to the object at ffff888011606dc0
   which belongs to the cache skbuff_head_cache of size 232

Fixes: 248f219cb8bc ("rxrpc: Rewrite the data and ack handling code")
Reported-by: syzbot+174de899852504e4a74a@syzkaller.appspotmail.com
Reported-by: syzbot+3d1c772efafd3c38d007@syzkaller.appspotmail.com
Signed-off-by: David Howells 
cc: Hillf Danton 
Link: https://lore.kernel.org/r/161234207610.653119.5287360098400436976.stgit@warthog.procyon.org.uk
Signed-off-by: Jakub Kicinski 
Signed-off-by: Greg Kroah-Hartman