summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorMagnus Karlsson <magnus.karlsson@intel.com>2019-11-08 22:58:09 +0300
committerJeff Kirsher <jeffrey.t.kirsher@intel.com>2019-11-09 03:11:48 +0300
commit705639572e8c096b12fcbff64a5c67db5b2d6ac0 (patch)
tree97ae39989e0c49f9ee25e256c07a9c9b3f0f4508
parent6acab13bdf2adda250b2a4d648fd4b49f1d0f14c (diff)
downloadlinux-705639572e8c096b12fcbff64a5c67db5b2d6ac0.tar.xz
i40e: need_wakeup flag might not be set for Tx
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> Tested-by: Andrew Bowers <andrewx.bowers@intel.com> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_xsk.c10
1 files 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 a05dfecdd9b4..d07e1a890428 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);