From: Magnus Karlsson <magnus.karlsson@intel.com> To: magnus.karlsson@intel.com, bjorn.topel@intel.com, intel-wired-lan@lists.osuosl.org Cc: maciej.fijalkowski@intel.com, maciejromanfijalkowski@gmail.com, netdev@vger.kernel.org Subject: [PATCH net 1/2] i40e: need_wakeup flag might not be set for Tx Date: Fri, 8 Nov 2019 20:58:09 +0100 [thread overview] Message-ID: <1573243090-2721-1-git-send-email-magnus.karlsson@intel.com> (raw) The need_wakeup flag for Tx might not be set for AF_XDP sockets that are only used to send packets. This happens if there is at least one outstanding packet that has not been completed by the hardware and we get that corresponding completion (which will not generate an interrupt since interrupts are disabled in the napi poll loop) between the time we stopped processing the Tx completions and interrupts are enabled again. In this case, the need_wakeup flag will have been cleared at the end of the Tx completion processing as we believe we will get an interrupt from the outstanding completion at a later point in time. But if this completion interrupt occurs before interrupts are enable, we lose it and should at that point really have set the need_wakeup flag since there are no more outstanding completions that can generate an interrupt to continue the processing. When this happens, user space will see a Tx queue need_wakeup of 0 and skip issuing a syscall, which means will never get into the Tx processing again and we have a deadlock. This patch introduces a quick fix for this issue by just setting the need_wakeup flag for Tx to 1 all the time. I am working on a proper fix for this that will toggle the flag appropriately, but it is more challenging than I anticipated and I am afraid that this patch will not be completed before the merge window closes, therefore this easier fix for now. This fix has a negative performance impact in the range of 0% to 4%. Towards the higher end of the scale if you have driver and application on the same core and issue a lot of packets, and towards no negative impact if you use two cores, lower transmission speeds and/or a workload that also receives packets. Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com> --- drivers/net/ethernet/intel/i40e/i40e_xsk.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index a05dfec..d07e1a8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -689,8 +689,6 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget) i40e_xdp_ring_update_tail(xdp_ring); xsk_umem_consume_tx_done(xdp_ring->xsk_umem); - if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_umem)) - xsk_clear_tx_need_wakeup(xdp_ring->xsk_umem); } return !!budget && work_done; @@ -769,12 +767,8 @@ bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi, i40e_update_tx_stats(tx_ring, completed_frames, total_bytes); out_xmit: - if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) { - if (tx_ring->next_to_clean == tx_ring->next_to_use) - xsk_set_tx_need_wakeup(tx_ring->xsk_umem); - else - xsk_clear_tx_need_wakeup(tx_ring->xsk_umem); - } + if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) + xsk_set_tx_need_wakeup(tx_ring->xsk_umem); xmit_done = i40e_xmit_zc(tx_ring, budget); -- 2.7.4
WARNING: multiple messages have this Message-ID (diff)
From: Magnus Karlsson <magnus.karlsson@intel.com> To: intel-wired-lan@osuosl.org Subject: [Intel-wired-lan] [PATCH net 1/2] i40e: need_wakeup flag might not be set for Tx Date: Fri, 8 Nov 2019 20:58:09 +0100 [thread overview] Message-ID: <1573243090-2721-1-git-send-email-magnus.karlsson@intel.com> (raw) The need_wakeup flag for Tx might not be set for AF_XDP sockets that are only used to send packets. This happens if there is at least one outstanding packet that has not been completed by the hardware and we get that corresponding completion (which will not generate an interrupt since interrupts are disabled in the napi poll loop) between the time we stopped processing the Tx completions and interrupts are enabled again. In this case, the need_wakeup flag will have been cleared at the end of the Tx completion processing as we believe we will get an interrupt from the outstanding completion at a later point in time. But if this completion interrupt occurs before interrupts are enable, we lose it and should at that point really have set the need_wakeup flag since there are no more outstanding completions that can generate an interrupt to continue the processing. When this happens, user space will see a Tx queue need_wakeup of 0 and skip issuing a syscall, which means will never get into the Tx processing again and we have a deadlock. This patch introduces a quick fix for this issue by just setting the need_wakeup flag for Tx to 1 all the time. I am working on a proper fix for this that will toggle the flag appropriately, but it is more challenging than I anticipated and I am afraid that this patch will not be completed before the merge window closes, therefore this easier fix for now. This fix has a negative performance impact in the range of 0% to 4%. Towards the higher end of the scale if you have driver and application on the same core and issue a lot of packets, and towards no negative impact if you use two cores, lower transmission speeds and/or a workload that also receives packets. Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com> --- drivers/net/ethernet/intel/i40e/i40e_xsk.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index a05dfec..d07e1a8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -689,8 +689,6 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget) i40e_xdp_ring_update_tail(xdp_ring); xsk_umem_consume_tx_done(xdp_ring->xsk_umem); - if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_umem)) - xsk_clear_tx_need_wakeup(xdp_ring->xsk_umem); } return !!budget && work_done; @@ -769,12 +767,8 @@ bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi, i40e_update_tx_stats(tx_ring, completed_frames, total_bytes); out_xmit: - if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) { - if (tx_ring->next_to_clean == tx_ring->next_to_use) - xsk_set_tx_need_wakeup(tx_ring->xsk_umem); - else - xsk_clear_tx_need_wakeup(tx_ring->xsk_umem); - } + if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) + xsk_set_tx_need_wakeup(tx_ring->xsk_umem); xmit_done = i40e_xmit_zc(tx_ring, budget); -- 2.7.4
next reply other threads:[~2019-11-08 19:58 UTC|newest] Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top 2019-11-08 19:58 Magnus Karlsson [this message] 2019-11-08 19:58 ` [Intel-wired-lan] [PATCH net 1/2] i40e: need_wakeup flag might not be set for Tx Magnus Karlsson 2019-11-08 19:58 ` [PATCH net 2/2] ixgbe: " Magnus Karlsson 2019-11-08 19:58 ` [Intel-wired-lan] " Magnus Karlsson 2019-11-09 0:02 ` Bowers, AndrewX 2019-11-09 0:02 ` Bowers, AndrewX 2019-11-08 22:11 ` [PATCH net 1/2] i40e: " David Miller 2019-11-08 22:11 ` [Intel-wired-lan] " David Miller 2019-11-08 22:46 ` Jeff Kirsher 2019-11-08 22:46 ` [Intel-wired-lan] " Jeff Kirsher 2019-11-09 0:01 ` Bowers, AndrewX 2019-11-09 0:01 ` Bowers, AndrewX 2019-11-25 15:24 ` Maxim Mikityanskiy 2019-11-25 15:24 ` [Intel-wired-lan] " Maxim Mikityanskiy 2019-11-25 16:44 ` Magnus Karlsson 2019-11-25 16:44 ` Magnus Karlsson
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=1573243090-2721-1-git-send-email-magnus.karlsson@intel.com \ --to=magnus.karlsson@intel.com \ --cc=bjorn.topel@intel.com \ --cc=intel-wired-lan@lists.osuosl.org \ --cc=maciej.fijalkowski@intel.com \ --cc=maciejromanfijalkowski@gmail.com \ --cc=netdev@vger.kernel.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.