Re: [PATCH v2 net-next] net: core: use listified Rx for GRO_NORMAL in napi_gro_receive()

From: Alexander Lobakin
Date: Wed Nov 27 2019 - 02:47:45 EST


David Miller wrote 27.11.2019 02:57:
From: Alexander Lobakin <alobakin@xxxxxxxx>
Date: Mon, 25 Nov 2019 15:02:24 +0300

Paolo Abeni wrote 25.11.2019 14:42:
For -net, I *think* something as dumb and hacky as the following could
possibly work:
----
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index 4bba6b8a863c..df82fad96cbb 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -1527,7 +1527,7 @@ static void iwl_pcie_rx_handle(struct iwl_trans
*trans, int queue)
iwl_pcie_rxq_alloc_rbs(trans, GFP_ATOMIC, rxq);
if (rxq->napi.poll)
- napi_gro_flush(&rxq->napi, false);
+ napi_complete_done(&rxq->napi, 0);
iwl_pcie_rxq_restock(trans, rxq);
}
---

napi_complete_done(napi, 0) has an equivalent static inline
napi_complete(napi). I'm not sure it will work without any issues
as iwlwifi doesn't _really_ turn NAPI into scheduling state.

I'm not very familiar with iwlwifi, but as a work around manual
napi_gro_flush() you can also manually flush napi->rx_list to
prevent packets from stalling:

diff -Naur a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c 2019-11-25
--- 14:55:03.610355230 +0300
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c 2019-11-25
14:57:29.399556868 +0300
...

Thanks to everyone for looking into this.

Can I get some kind of fix in the next 24 hours? I want to send a quick
follow-on pull request to Linus to deal with all of the fallout, and in
particular fix this regression.

If Intel guys and others will agree, I'll send a patch which will add
manual napi->rx_list flushing in iwlwifi driver in about ~2-3 hours.

Anyway, this driver should get a proper NAPI in future releases to
prevent problems like this one.

Thanks!

Regards,
á á á á á á