diff options
author | Jakub Kicinski <kuba@kernel.org> | 2023-07-20 03:04:40 +0200 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2023-07-21 05:09:13 +0200 |
commit | 2b56b3d9924160d84c37d085628525666e3b1cea (patch) | |
tree | 97eaeaaedfd419060ec1785752a2dc9e5a004c17 /drivers/net/ethernet/broadcom/bnxt/bnxt.c | |
parent | eth: bnxt: take the bit to set as argument of bnxt_queue_sp_work() (diff) | |
download | linux-2b56b3d9924160d84c37d085628525666e3b1cea.tar.xz linux-2b56b3d9924160d84c37d085628525666e3b1cea.zip |
eth: bnxt: handle invalid Tx completions more gracefully
Invalid Tx completions should never happen (tm) but when they do
they crash the host, because driver blindly trusts that there is
a valid skb pointer on the ring.
The completions I've seen appear to be some form of FW / HW
miscalculation or staleness, they have typical (small) values
(<100), but they are most often higher than number of queued
descriptors. They usually happen after boot.
Instead of crashing, print a warning and schedule a reset.
Link: https://lore.kernel.org/r/20230720010440.1967136-4-kuba@kernel.org
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'drivers/net/ethernet/broadcom/bnxt/bnxt.c')
-rw-r--r-- | drivers/net/ethernet/broadcom/bnxt/bnxt.c | 25 |
1 files changed, 24 insertions, 1 deletions
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 7b545d2a98b4..a3bbd13c070f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -331,6 +331,22 @@ static void bnxt_sched_reset_rxr(struct bnxt *bp, struct bnxt_rx_ring_info *rxr) rxr->rx_next_cons = 0xffff; } +void bnxt_sched_reset_txr(struct bnxt *bp, struct bnxt_tx_ring_info *txr, + int idx) +{ + struct bnxt_napi *bnapi = txr->bnapi; + + if (bnapi->tx_fault) + return; + + netdev_err(bp->dev, "Invalid Tx completion (ring:%d tx_pkts:%d cons:%u prod:%u i:%d)", + txr->txq_index, bnapi->tx_pkts, + txr->tx_cons, txr->tx_prod, idx); + WARN_ON_ONCE(1); + bnapi->tx_fault = 1; + bnxt_queue_sp_work(bp, BNXT_RESET_TASK_SP_EVENT); +} + const u16 bnxt_lhint_arr[] = { TX_BD_FLAGS_LHINT_512_AND_SMALLER, TX_BD_FLAGS_LHINT_512_TO_1023, @@ -690,6 +706,11 @@ static void bnxt_tx_int(struct bnxt *bp, struct bnxt_napi *bnapi, int nr_pkts) skb = tx_buf->skb; tx_buf->skb = NULL; + if (unlikely(!skb)) { + bnxt_sched_reset_txr(bp, txr, i); + return; + } + tx_bytes += skb->len; if (tx_buf->is_push) { @@ -2576,7 +2597,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, static void __bnxt_poll_work_done(struct bnxt *bp, struct bnxt_napi *bnapi) { - if (bnapi->tx_pkts) { + if (bnapi->tx_pkts && !bnapi->tx_fault) { bnapi->tx_int(bp, bnapi, bnapi->tx_pkts); bnapi->tx_pkts = 0; } @@ -9429,6 +9450,8 @@ static void bnxt_enable_napi(struct bnxt *bp) struct bnxt_napi *bnapi = bp->bnapi[i]; struct bnxt_cp_ring_info *cpr; + bnapi->tx_fault = 0; + cpr = &bnapi->cp_ring; if (bnapi->in_reset) cpr->sw_stats.rx.rx_resets++; |