On Wed, Jul 14, 2021 at 08:56:41AM -0400, Nitesh Lal wrote:

On Wed, Jul 14, 2021 at 8:03 AM Leon Romanovsky [off-list ref] wrote:

quoted

On Tue, Jul 13, 2021 at 05:14:54PM -0400, Nitesh Narayan Lal wrote:

quoted

The driver uses irq_set_affinity_hint() to update the affinity_hint mask
that is consumed by the userspace to distribute the interrupts and to apply
the provided mask as the affinity for its interrupts. However,
irq_set_affinity_hint() applying the provided cpumask as an affinity for
the interrupt is an undocumented side effect.

To remove this side effect irq_set_affinity_hint() has been marked
as deprecated and new interfaces have been introduced. Hence, replace the
irq_set_affinity_hint() with the new interface irq_set_affinity_and_hint()
where the provided mask needs to be applied as the affinity and
affinity_hint pointer needs to be set and replace with
irq_update_affinity_hint() where only affinity_hint needs to be updated.

Signed-off-by: Nitesh Narayan Lal <redacted>
---
 drivers/infiniband/hw/irdma/hw.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c
index 7afb8a6a0526..7f13a051d4de 100644
--- a/drivers/infiniband/hw/irdma/hw.c
+++ b/drivers/infiniband/hw/irdma/hw.c

@@ -537,7 +537,7 @@ static void irdma_destroy_irq(struct irdma_pci_f *rf,
      struct irdma_sc_dev *dev = &rf->sc_dev;

      dev->irq_ops->irdma_dis_irq(dev, msix_vec->idx);
-     irq_set_affinity_hint(msix_vec->irq, NULL);
+     irq_update_affinity_hint(msix_vec->irq, NULL);
      free_irq(msix_vec->irq, dev_id);
 }

@@ -1087,7 +1087,7 @@ irdma_cfg_ceq_vector(struct irdma_pci_f *rf, struct irdma_ceq *iwceq,
      }
      cpumask_clear(&msix_vec->mask);
      cpumask_set_cpu(msix_vec->cpu_affinity, &msix_vec->mask);
-     irq_set_affinity_hint(msix_vec->irq, &msix_vec->mask);
+     irq_set_affinity_and_hint(msix_vec->irq, &msix_vec->mask);

I think that it needs to be irq_update_affinity_hint().

Ah! I got a little confused from our last conversation about mlx5.

IIUC mlx5 sub-function use case uses irdma (?) and that's why I thought
that perhaps we would also want to define the affinity here from the beginning.

mlx5 is connected to mlx5_ib/mlx5_vdpa e.t.c.

Not sure about that, but I think that only mlx5 implements SIOV model.

In any case, I will make the change and re-post.

--
Thanks
Nitesh