Re: [Intel-wired-lan] [iwl-next PATCH v4 2/3] idpf: convert workqueues to unbound

On Mon, Dec 16, 2024 at 1:11 PM Alexander Lobakin wrote: > > From: Brian Vazquez > Date: Mon, 16 Dec 2024 16:27:34 + > > > From: Marco Leogrande > > > > When a workqueue is created with `WQ_UNBOUND`, its work items are > > served by special worker-pools,

Re: [Intel-wired-lan] [iwl-next PATCH v3 3/3] idpf: add more info during virtchnl transaction time out

Thanks for the feedback, I will address it in the next version. On Fri, Dec 13, 2024 at 4:36 AM Paul Menzel wrote: > > Dear Brian, dear Manoj, > > > Thank you for your patch. > > Am 13.12.24 um 00:33 schrieb Brian Vazquez: > > From: Manoj Vishwanathan > > > &

[Intel-wired-lan] [iwl-next PATCH v4 2/3] idpf: convert workqueues to unbound

, keeping everything else equal, the maximum delay I could see was `6us`. Fixes: 0fe45467a104 ("idpf: add create vport and netdev configuration") Signed-off-by: Marco Leogrande Signed-off-by: Manoj Vishwanathan Signed-off-by: Brian Vazquez Reviewed-by: Jacob Keller Reviewed-by: Pavan K

[Intel-wired-lan] [iwl-next PATCH v4 0/3] IDPF Virtchnl: Enhance error reporting & fix locking/workqueue issues

This patch series addresses several IDPF virtchnl issues: * Improved error reporting for better diagnostics. * Fixed locking sequence in virtchnl message handling to avoid potential race conditions. * Converted idpf workqueues to unbound to prevent virtchnl processing delays under heavy load. P

[Intel-wired-lan] [iwl-next PATCH v4 3/3] idpf: add more info during virtchnl transaction timeout/salt mismatch

timeout:6ms) --- before it was: --- (op 5015, 6ms) --- Signed-off-by: Manoj Vishwanathan Signed-off-by: Brian Vazquez Reviewed-by: Jacob Keller Reviewed-by: Pavan Kumar Linga Reviewed-by: Paul Menzel --- drivers/net/ethernet/intel/idpf

[Intel-wired-lan] [iwl-next PATCH v4 1/3] idpf: Acquire the lock before accessing the xn->salt

Signed-off-by: Brian Vazquez Reviewed-by: Jacob Keller Reviewed-by: Pavan Kumar Linga --- drivers/net/ethernet/intel/idpf/idpf_virtchnl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_

[Intel-wired-lan] [iwl-next PATCH v3 2/3] idpf: convert workqueues to unbound

, keeping everything else equal, the maximum delay I could see was `6us`. Fixes: 0fe45467a104 ("idpf: add create vport and netdev configuration") Signed-off-by: Marco Leogrande Signed-off-by: Manoj Vishwanathan Signed-off-by: Brian Vazquez Reviewed-by: Jacob Keller Reviewed-by: Pavan K

[Intel-wired-lan] [iwl-next PATCH v3 1/3] idpf: Acquire the lock before accessing the xn->salt

Signed-off-by: Brian Vazquez Reviewed-by: Jacob Keller Reviewed-by: Pavan Kumar Linga --- drivers/net/ethernet/intel/idpf/idpf_virtchnl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_

[Intel-wired-lan] [iwl-next PATCH v3 0/3] IDPF Virtchnl: Enhance error reporting & fix locking/workqueue issues

This patch series addresses several IDPF virtchnl issues: * Improved error reporting for better diagnostics. * Fixed locking sequence in virtchnl message handling to avoid potential race conditions. * Converted idpf workqueues to unbound to prevent virtchnl processing delays under heavy load. P

[Intel-wired-lan] [iwl-next PATCH v3 3/3] idpf: add more info during virtchnl transaction time out

timeout:6ms) --- Signed-off-by: Manoj Vishwanathan Signed-off-by: Brian Vazquez Reviewed-by: Jacob Keller Reviewed-by: Pavan Kumar Linga --- drivers/net/ethernet/intel/idpf/idpf_virtchnl.c | 13 + 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a

Re: [Intel-wired-lan] [iwl-net PATCH v2] idpf: fix a race in txq wakeup

On Thu, May 1, 2025 at 11:16 AM Simon Horman wrote: > > On Mon, Apr 28, 2025 at 07:55:32PM +, Brian Vazquez wrote: > > Add a helper function to correctly handle the lockless > > synchronization when the sender needs to block. The paradigm is > > >

[Intel-wired-lan] [iwl-net PATCH v3] idpf: fix a race in txq wakeup

th1 -s 100 -6 -d $IP -m $MAC \ -p 1-1 -t 16 -n 0 -v -x -c 64 Fixes: 6818c4d5b3c2 ("idpf: add splitq start_xmit") Reviewed-by: Jacob Keller Reviewed-by: Madhu Chittim Signed-off-by: Josh Hay Signed-off-by: Brian Vazquez Signed-off-by: Luigi Rizzo --- v3: - Fix typo in commi

[Intel-wired-lan] [iwl-next PATCH] idpf: fix a race in txq wakeup

ueue.sh -i eth1 -s 100 -6 -d $IP -m $MAC \ -p 1-1 -t 16 -n 0 -v -x -c 64 Signed-off-by: Josh Hay Signed-off-by: Brian Vazquez Signed-off-by: Luigi Rizzo --- .../ethernet/intel/idpf/idpf_singleq_txrx.c | 9 ++-- drivers/net/ethernet/intel/idpf/idpf_txrx.c | 44 +++

[Intel-wired-lan] [iwl-net PATCH v2] idpf: fix a race in txq wakeup

th1 -s 100 -6 -d $IP -m $MAC \ -p 1-1 -t 16 -n 0 -v -x -c 64 Fixes: 6818c4d5b3c2 ("idpf: add splitq start_xmit") Signed-off-by: Josh Hay Signed-off-by: Brian Vazquez Signed-off-by: Luigi Rizzo --- v2: - Fix typos - Fix RCT in singleq function - No inline in c files

Re: [Intel-wired-lan] [iwl-next PATCH] idpf: fix a race in txq wakeup

Thanks for the quick review Tony! On Fri, Apr 25, 2025 at 6:41 PM Tony Nguyen wrote: > > On 4/25/2025 10:54 AM, Brian Vazquez wrote: > > Should this be a bug fix going to iwl-net/net? If yes, you'll need to > add a Fixes: as well > Correct, will send to iwl-net the

Re: [Intel-wired-lan] [PATCH net 0/5] idpf: replace Tx flow scheduling buffer ring with buffer pool

O Mon, Jun 30, 2025 at 06:22:11PM +0200, Paul Menzel wrote: > Dear Josh, > > > Am 30.06.25 um 18:08 schrieb Hay, Joshua A: > > > > Am 25.06.25 um 18:11 schrieb Joshua Hay: > > > > This series fixes a stability issue in the flow scheduling Tx send/clean > > > > path that results in a Tx timeout.