i40e: initialize our affinity_mask based on cpu_possible_mask
On older kernels a call to irq_set_affinity_hint does not guarantee that
the IRQ affinity will be set. If nothing else on the system sets the IRQ
affinity this can result in a bug in the i40e_napi_poll() routine where
we notice that our interrupt fired on the "wrong" CPU according to our
internal affinity_mask variable.
This results in a bug where we continuously tell NAPI to stop polling to
move the interrupt to a new CPU, but the CPU never changes because our
affinity mask does not match the actual mask setup for the IRQ.
The root problem is a mismatched affinity mask value. So lets initialize
the value to cpu_possible_mask instead. This ensures that prior to the
first time we get an IRQ affinity notification we'll have the mask set
to include every possible CPU.
We use cpu_possible_mask instead of cpu_online_mask since the former is
almost certainly never going to change, while the later might change
after we've made a copy.
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 7366e7c..6498da8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -2881,7 +2881,7 @@ static void i40e_config_xps_tx_ring(struct i40e_ring *ring)
if ((vsi->tc_config.numtc <= 1) &&
!test_and_set_bit(__I40E_TX_XPS_INIT_DONE, &ring->state)) {
netif_set_xps_queue(ring->netdev,
- &ring->q_vector->affinity_mask,
+ get_cpu_mask(ring->q_vector->v_idx),
ring->queue_index);
}
@@ -3506,8 +3506,10 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename)
q_vector->affinity_notify.notify = i40e_irq_affinity_notify;
q_vector->affinity_notify.release = i40e_irq_affinity_release;
irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify);
- /* assign the mask for this irq */
- irq_set_affinity_hint(irq_num, &q_vector->affinity_mask);
+ /* get_cpu_mask returns a static constant mask with
+ * a permanent lifetime so it's ok to use here.
+ */
+ irq_set_affinity_hint(irq_num, get_cpu_mask(q_vector->v_idx));
}
vsi->irqs_ready = true;
@@ -4289,7 +4291,7 @@ static void i40e_vsi_free_irq(struct i40e_vsi *vsi)
/* clear the affinity notifier in the IRQ descriptor */
irq_set_affinity_notifier(irq_num, NULL);
- /* clear the affinity_mask in the IRQ descriptor */
+ /* remove our suggested affinity mask for this IRQ */
irq_set_affinity_hint(irq_num, NULL);
synchronize_irq(irq_num);
free_irq(irq_num, vsi->q_vectors[i]);
@@ -8235,7 +8237,7 @@ static int i40e_vsi_alloc_q_vector(struct i40e_vsi *vsi, int v_idx, int cpu)
q_vector->vsi = vsi;
q_vector->v_idx = v_idx;
- cpumask_set_cpu(cpu, &q_vector->affinity_mask);
+ cpumask_copy(&q_vector->affinity_mask, cpu_possible_mask);
if (vsi->netdev)
netif_napi_add(vsi->netdev, &q_vector->napi,