linux-toradex.git/net/smc/smc_cdc.h, branch v6.9

net/smc: fix kernel panic caused by race of smc_sock

2021-12-28T12:42:45+00:00

A crash occurs when smc_cdc_tx_handler() tries to access smc_sock
but smc_release() has already freed it.

[ 4570.695099] BUG: unable to handle page fault for address: 000000002eae9e88
[ 4570.696048] #PF: supervisor write access in kernel mode
[ 4570.696728] #PF: error_code(0x0002) - not-present page
[ 4570.697401] PGD 0 P4D 0
[ 4570.697716] Oops: 0002 [#1] PREEMPT SMP NOPTI
[ 4570.698228] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.16.0-rc4+ #111
[ 4570.699013] Hardware name: Alibaba Cloud Alibaba Cloud ECS, BIOS 8c24b4c 04/0
[ 4570.699933] RIP: 0010:_raw_spin_lock+0x1a/0x30
<...>
[ 4570.711446] Call Trace:
[ 4570.711746]  
[ 4570.711992]  smc_cdc_tx_handler+0x41/0xc0
[ 4570.712470]  smc_wr_tx_tasklet_fn+0x213/0x560
[ 4570.712981]  ? smc_cdc_tx_dismisser+0x10/0x10
[ 4570.713489]  tasklet_action_common.isra.17+0x66/0x140
[ 4570.714083]  __do_softirq+0x123/0x2f4
[ 4570.714521]  irq_exit_rcu+0xc4/0xf0
[ 4570.714934]  common_interrupt+0xba/0xe0

Though smc_cdc_tx_handler() checked the existence of smc connection,
smc_release() may have already dismissed and released the smc socket
before smc_cdc_tx_handler() further visits it.

smc_cdc_tx_handler()           |smc_release()
if (!conn)                     |
                               |
                               |smc_cdc_tx_dismiss_slots()
                               |      smc_cdc_tx_dismisser()
                               |
                               |sock_put(&smc->sk) <- last sock_put,
                               |                      smc_sock freed
bh_lock_sock(&smc->sk) (panic) |

To make sure we won't receive any CDC messages after we free the
smc_sock, add a refcount on the smc_connection for inflight CDC
message(posted to the QP but haven't received related CQE), and
don't release the smc_connection until all the inflight CDC messages
haven been done, for both success or failed ones.

Using refcount on CDC messages brings another problem: when the link
is going to be destroyed, smcr_link_clear() will reset the QP, which
then remove all the pending CQEs related to the QP in the CQ. To make
sure all the CQEs will always come back so the refcount on the
smc_connection can always reach 0, smc_ib_modify_qp_reset() was replaced
by smc_ib_modify_qp_error().
And remove the timeout in smc_wr_tx_wait_no_pending_sends() since we
need to wait for all pending WQEs done, or we may encounter use-after-
free when handling CQEs.

For IB device removal routine, we need to wait for all the QPs on that
device been destroyed before we can destroy CQs on the device, or
the refcount on smc_connection won't reach 0 and smc_sock cannot be
released.

Fixes: 5f08318f617b ("smc: connection data control (CDC)")
Reported-by: Wen Gu 
Signed-off-by: Dust Li 
Signed-off-by: David S. Miller

net/smc: pre-fetch send buffer outside of send_lock

2020-05-31T01:12:25+00:00

Pre-fetch send buffer for the CDC validation message before entering the
send_lock. Without that the send call might fail with -EBUSY because
there are no free buffers and waiting for buffers is not possible under
send_lock.

Signed-off-by: Karsten Graul 
Reviewed-by: Ursula Braun 
Signed-off-by: David S. Miller

net/smc: remove unused inline function smc_curs_read

2020-05-05T19:56:52+00:00

commit bac6de7b6370 ("net/smc: eliminate cursor read and write calls")
left behind this.

Signed-off-by: YueHaibing 
Signed-off-by: Karsten Graul 
Signed-off-by: David S. Miller

net/smc: send failover validation message

2020-05-04T17:54:39+00:00

When a connection is switched to a new link then a link validation
message must be sent to the peer over the new link, containing the
sequence number of the last CDC message that was sent over the old link.
The peer will validate if this sequence number is the same or lower then
the number he received, and abort the connection if messages were lost.
Add smcr_cdc_msg_send_validation() to send the message validation
message and call it when a connection was switched in
smc_switch_cursor().

Signed-off-by: Karsten Graul 
Reviewed-by: Ursula Braun 
Signed-off-by: David S. Miller

net/smc: switch connections to alternate link

2020-05-04T17:54:39+00:00

Add smc_switch_conns() to switch all connections from a link that is
going down. Find an other link to switch the connections to, and
switch each connection to the new link. smc_switch_cursor() updates the
cursors of a connection to the state of the last successfully sent CDC
message. When there is no link to switch to, terminate the link group.
Call smc_switch_conns() when a link is going down.
And with the possibility that links of connections can switch adapt CDC
and TX functions to detect and handle link switches.

Signed-off-by: Karsten Graul 
Reviewed-by: Ursula Braun 
Signed-off-by: David S. Miller

Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

2019-02-15T20:38:38+00:00

The netfilter conflicts were rather simple overlapping
changes.

However, the cls_tcindex.c stuff was a bit more complex.

On the 'net' side, Cong is fixing several races and memory
leaks.  Whilst on the 'net-next' side we have Vlad adding
the rtnl-ness support.

What I've decided to do, in order to resolve this, is revert the
conversion over to using a workqueue that Cong did, bringing us back
to pure RCU.  I did it this way because I believe that either Cong's
races don't apply with have Vlad did things, or Cong will have to
implement the race fix slightly differently.

Signed-off-by: David S. Miller

net/smc: fix byte_order for rx_curs_confirmed

2019-02-09T06:33:25+00:00

The recent change in the rx_curs_confirmed assignment disregards
byte order, which causes problems on little endian architectures.
This patch fixes it.

Fixes: b8649efad879 ("net/smc: fix sender_free computation") (net-tree)
Signed-off-by: Ursula Braun 
Signed-off-by: David S. Miller

Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

2019-02-08T23:00:17+00:00

An ipvlan bug fix in 'net' conflicted with the abstraction away
of the IPV6 specific support in 'net-next'.

Similarly, a bug fix for mlx5 in 'net' conflicted with the flow
action conversion in 'net-next'.

Signed-off-by: David S. Miller

net/smc: use smc_curs_copy() for SMC-D

2019-02-08T02:06:18+00:00

SMC already provides a wrapper for atomic64 calls to be
architecture independent. Use this wrapper for SMC-D as well.

Reported-by: Jens Remus 
Signed-off-by: Ursula Braun 
Signed-off-by: David S. Miller

net/smc: fix sender_free computation

2019-02-04T17:11:19+00:00

In some scenarios a separate consumer cursor update is necessary.
The decision is made in smc_tx_consumer_cursor_update(). The
sender_free computation could be wrong:

The rx confirmed cursor is always smaller than or equal to the
rx producer cursor. The parameters in the smc_curs_diff() call
have to be exchanged, otherwise sender_free might even be negative.

And if more data arrives local_rx_ctrl.prod might be updated, enabling
a cursor difference between local_rx_ctrl.prod and rx confirmed cursor
larger than the RMB size. This case is not covered by smc_curs_diff().
Thus function smc_curs_diff_large() is introduced here.

If a recvmsg() is processed in parallel, local_tx_ctrl.cons might
change during smc_cdc_msg_send. Make sure rx_curs_confirmed is updated
with the actually sent local_tx_ctrl.cons value.

Fixes: e82f2e31f559 ("net/smc: optimize consumer cursor updates")
Signed-off-by: Ursula Braun 
Signed-off-by: David S. Miller