[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ZmmbFWJNb/s+UFNq@boxer>
Date: Wed, 12 Jun 2024 14:56:53 +0200
From: Maciej Fijalkowski <maciej.fijalkowski@...el.com>
To: Kurt Kanzenbach <kurt@...utronix.de>
CC: Jesse Brandeburg <jesse.brandeburg@...el.com>, Tony Nguyen
<anthony.l.nguyen@...el.com>, "David S. Miller" <davem@...emloft.net>, "Eric
Dumazet" <edumazet@...gle.com>, Jakub Kicinski <kuba@...nel.org>, Paolo Abeni
<pabeni@...hat.com>, Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
Vinicius Costa Gomes <vinicius.gomes@...el.com>,
<intel-wired-lan@...ts.osuosl.org>, <netdev@...r.kernel.org>
Subject: Re: [PATCH iwl-next] igc: Get rid of spurious interrupts
On Wed, Jun 12, 2024 at 11:24:53AM +0200, Kurt Kanzenbach wrote:
> When running the igc with XDP/ZC in busy polling mode with deferral of hard
> interrupts, interrupts still happen from time to time. That is caused by
> the igc task watchdog which triggers Rx interrupts periodically.
>
> That mechanism has been introduced to overcome skb/memory allocation
> failures [1]. So the Rx clean functions stop processing the Rx ring in case
> of such failure. The task watchdog triggers Rx interrupts periodically in
> the hope that memory became available in the mean time.
>
> The current behavior is undesirable for real time applications, because the
> driver induced Rx interrupts trigger also the softirq processing. However,
> all real time packets should be processed by the application which uses the
> busy polling method.
>
> Therefore, only trigger the Rx interrupts in case of real allocation
> failures. Introduce a new flag for signaling that condition.
>
> [1] - https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git/commit/?id=3be507547e6177e5c808544bd6a2efa2c7f1d436
>
> Signed-off-by: Kurt Kanzenbach <kurt@...utronix.de>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@...el.com>
> ---
> drivers/net/ethernet/intel/igc/igc.h | 1 +
> drivers/net/ethernet/intel/igc/igc_main.c | 24 ++++++++++++++++++++----
> 2 files changed, 21 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
> index 8b14c029eda1..7bfe5030e2c0 100644
> --- a/drivers/net/ethernet/intel/igc/igc.h
> +++ b/drivers/net/ethernet/intel/igc/igc.h
> @@ -682,6 +682,7 @@ enum igc_ring_flags_t {
> IGC_RING_FLAG_TX_DETECT_HANG,
> IGC_RING_FLAG_AF_XDP_ZC,
> IGC_RING_FLAG_TX_HWTSTAMP,
> + IGC_RING_FLAG_RX_ALLOC_FAILED,
> };
>
> #define ring_uses_large_buffer(ring) \
> diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
> index 305e05294a26..e666739dfac7 100644
> --- a/drivers/net/ethernet/intel/igc/igc_main.c
> +++ b/drivers/net/ethernet/intel/igc/igc_main.c
> @@ -2192,6 +2192,7 @@ static bool igc_alloc_mapped_page(struct igc_ring *rx_ring,
> page = dev_alloc_pages(igc_rx_pg_order(rx_ring));
> if (unlikely(!page)) {
> rx_ring->rx_stats.alloc_failed++;
> + set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
> return false;
> }
>
> @@ -2208,6 +2209,7 @@ static bool igc_alloc_mapped_page(struct igc_ring *rx_ring,
> __free_page(page);
>
> rx_ring->rx_stats.alloc_failed++;
> + set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
> return false;
> }
>
> @@ -2659,6 +2661,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
> if (!skb) {
> rx_ring->rx_stats.alloc_failed++;
> rx_buffer->pagecnt_bias++;
> + set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
> break;
> }
>
> @@ -2739,6 +2742,7 @@ static void igc_dispatch_skb_zc(struct igc_q_vector *q_vector,
> skb = igc_construct_skb_zc(ring, xdp);
> if (!skb) {
> ring->rx_stats.alloc_failed++;
> + set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &ring->flags);
> return;
> }
>
> @@ -5811,11 +5815,23 @@ static void igc_watchdog_task(struct work_struct *work)
> if (adapter->flags & IGC_FLAG_HAS_MSIX) {
> u32 eics = 0;
>
> - for (i = 0; i < adapter->num_q_vectors; i++)
> - eics |= adapter->q_vector[i]->eims_value;
> - wr32(IGC_EICS, eics);
> + for (i = 0; i < adapter->num_q_vectors; i++) {
> + struct igc_ring *rx_ring = adapter->rx_ring[i];
> +
> + if (test_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags)) {
> + eics |= adapter->q_vector[i]->eims_value;
> + clear_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
> + }
> + }
> + if (eics)
> + wr32(IGC_EICS, eics);
> } else {
> - wr32(IGC_ICS, IGC_ICS_RXDMT0);
> + struct igc_ring *rx_ring = adapter->rx_ring[0];
> +
> + if (test_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags)) {
> + clear_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
> + wr32(IGC_ICS, IGC_ICS_RXDMT0);
> + }
> }
>
> igc_ptp_tx_hang(adapter);
>
> ---
> base-commit: bb678f01804ccaa861b012b2b9426d69673d8a84
> change-id: 20240611-igc_irq-ccc1c8bc6890
>
> Best regards,
> --
> Kurt Kanzenbach <kurt@...utronix.de>
>
Powered by blists - more mailing lists