diff options
author | Dust Li <dust.li@linux.alibaba.com> | 2021-12-28 17:03:25 +0800 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2021-12-28 12:42:45 +0000 |
commit | 349d43127dac00c15231e8ffbcaabd70f7b0e544 (patch) | |
tree | 7dc9d1354ef88f560485ae6e2ecf701b55ec9645 /net/smc/smc_wr.c | |
parent | 90cee52f2e780345d3629e278291aea5ac74f40f (diff) |
net/smc: fix kernel panic caused by race of smc_sock
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] <IRQ>
[ 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 <guwen@linux.alibaba.com>
Signed-off-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/smc/smc_wr.c')
-rw-r--r-- | net/smc/smc_wr.c | 41 |
1 files changed, 3 insertions, 38 deletions
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index df1dc225cbab..c6cfdea8b71b 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -62,13 +62,9 @@ static inline bool smc_wr_is_tx_pend(struct smc_link *link) } /* wait till all pending tx work requests on the given link are completed */ -int smc_wr_tx_wait_no_pending_sends(struct smc_link *link) +void smc_wr_tx_wait_no_pending_sends(struct smc_link *link) { - if (wait_event_timeout(link->wr_tx_wait, !smc_wr_is_tx_pend(link), - SMC_WR_TX_WAIT_PENDING_TIME)) - return 0; - else /* timeout */ - return -EPIPE; + wait_event(link->wr_tx_wait, !smc_wr_is_tx_pend(link)); } static inline int smc_wr_tx_find_pending_index(struct smc_link *link, u64 wr_id) @@ -87,7 +83,6 @@ static inline void smc_wr_tx_process_cqe(struct ib_wc *wc) struct smc_wr_tx_pend pnd_snd; struct smc_link *link; u32 pnd_snd_idx; - int i; link = wc->qp->qp_context; @@ -128,14 +123,6 @@ static inline void smc_wr_tx_process_cqe(struct ib_wc *wc) } if (wc->status) { - for_each_set_bit(i, link->wr_tx_mask, link->wr_tx_cnt) { - /* clear full struct smc_wr_tx_pend including .priv */ - memset(&link->wr_tx_pends[i], 0, - sizeof(link->wr_tx_pends[i])); - memset(&link->wr_tx_bufs[i], 0, - sizeof(link->wr_tx_bufs[i])); - clear_bit(i, link->wr_tx_mask); - } if (link->lgr->smc_version == SMC_V2) { memset(link->wr_tx_v2_pend, 0, sizeof(*link->wr_tx_v2_pend)); @@ -421,25 +408,6 @@ int smc_wr_reg_send(struct smc_link *link, struct ib_mr *mr) return rc; } -void smc_wr_tx_dismiss_slots(struct smc_link *link, u8 wr_tx_hdr_type, - smc_wr_tx_filter filter, - smc_wr_tx_dismisser dismisser, - unsigned long data) -{ - struct smc_wr_tx_pend_priv *tx_pend; - struct smc_wr_rx_hdr *wr_tx; - int i; - - for_each_set_bit(i, link->wr_tx_mask, link->wr_tx_cnt) { - wr_tx = (struct smc_wr_rx_hdr *)&link->wr_tx_bufs[i]; - if (wr_tx->type != wr_tx_hdr_type) - continue; - tx_pend = &link->wr_tx_pends[i].priv; - if (filter(tx_pend, data)) - dismisser(tx_pend); - } -} - /****************************** receive queue ********************************/ int smc_wr_rx_register_handler(struct smc_wr_rx_handler *handler) @@ -675,10 +643,7 @@ void smc_wr_free_link(struct smc_link *lnk) smc_wr_wakeup_reg_wait(lnk); smc_wr_wakeup_tx_wait(lnk); - if (smc_wr_tx_wait_no_pending_sends(lnk)) - memset(lnk->wr_tx_mask, 0, - BITS_TO_LONGS(SMC_WR_BUF_CNT) * - sizeof(*lnk->wr_tx_mask)); + smc_wr_tx_wait_no_pending_sends(lnk); wait_event(lnk->wr_reg_wait, (!atomic_read(&lnk->wr_reg_refcnt))); wait_event(lnk->wr_tx_wait, (!atomic_read(&lnk->wr_tx_refcnt))); |