Re: [PATCH v2 net-next] net: core: use listified Rx for GRO_NORMAL in napi_gro_receive()
From: David Miller <davem@davemloft.net>
Date: 2019-11-26 23:57:49
Also in:
linux-wireless, lkml
Possibly related (same subject, not in this thread)
- 2020-06-25 · Re: [PATCH v2 net-next] net: core: use listified Rx for GRO_NORMAL in napi_gro_receive() · Edward Cree <hidden>
- 2020-06-24 · Re: [PATCH v2 net-next] net: core: use listified Rx for GRO_NORMAL in napi_gro_receive() · "Jason A. Donenfeld" <Jason@zx2c4.com>
- 2020-06-24 · Re: [PATCH v2 net-next] net: core: use listified Rx for GRO_NORMAL in napi_gro_receive() · "Jason A. Donenfeld" <Jason@zx2c4.com>
- 2019-11-25 · Re: [PATCH v2 net-next] net: core: use listified Rx for GRO_NORMAL in napi_gro_receive() · Nicholas Johnson <hidden>
- 2019-11-25 · Re: [PATCH v2 net-next] net: core: use listified Rx for GRO_NORMAL in napi_gro_receive() · Kalle Valo <hidden>
From: Alexander Lobakin <redacted> Date: Mon, 25 Nov 2019 15:02:24 +0300
quoted hunk ↗ jump to hunk
Paolo Abeni wrote 25.11.2019 14:42:quoted
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.cb/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 2019-11-2514:57:29.399556868 +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. Thanks!