[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20230208153905.109912-1-pawel.chmielewski@intel.com>
Date: Wed, 8 Feb 2023 16:39:05 +0100
From: Pawel Chmielewski <pawel.chmielewski@...el.com>
To: yury.norov@...il.com
Cc: Jonathan.Cameron@...wei.com, andriy.shevchenko@...ux.intel.com,
baohua@...nel.org, bristot@...hat.com, bsegall@...gle.com,
davem@...emloft.net, dietmar.eggemann@....com, gal@...dia.com,
gregkh@...uxfoundation.org, hca@...ux.ibm.com,
jacob.e.keller@...el.com, jesse.brandeburg@...el.com,
jgg@...dia.com, juri.lelli@...hat.com, kuba@...nel.org,
leonro@...dia.com, linux-crypto@...r.kernel.org,
linux-kernel@...r.kernel.org, linux-rdma@...r.kernel.org,
linux@...musvillemoes.dk, mgorman@...e.de, mingo@...hat.com,
netdev@...r.kernel.org, peter@...jl.ca, peterz@...radead.org,
rostedt@...dmis.org, saeedm@...dia.com, tariqt@...dia.com,
tony.luck@...el.com, torvalds@...ux-foundation.org,
ttoukan.linux@...il.com, vincent.guittot@...aro.org,
vschneid@...hat.com,
Pawel Chmielewski <pawel.chmielewski@...el.com>
Subject: [PATCH 1/1] ice: Change assigning method of the CPU affinity masks
With the introduction of sched_numa_hop_mask() and
for_each_numa_hop_mask(), the affinity masks for queue vectors can be
conveniently set by preferring the CPUs that are closest to the NUMA node
of the parent PCI device.
Signed-off-by: Pawel Chmielewski <pawel.chmielewski@...el.com>
---
drivers/net/ethernet/intel/ice/ice_base.c | 17 ++++++++++++++---
1 file changed, 14 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index e864634d66bc..fd3550d15c9e 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -122,8 +122,6 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, u16 v_idx)
if (vsi->type == ICE_VSI_VF)
goto out;
/* only set affinity_mask if the CPU is online */
- if (cpu_online(v_idx))
- cpumask_set_cpu(v_idx, &q_vector->affinity_mask);
/* This will not be called in the driver load path because the netdev
* will not be created yet. All other cases with register the NAPI
@@ -659,8 +657,10 @@ int ice_vsi_wait_one_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx)
*/
int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi)
{
+ cpumask_t *aff_mask, *last_aff_mask = cpu_none_mask;
struct device *dev = ice_pf_to_dev(vsi->back);
- u16 v_idx;
+ int numa_node = dev->numa_node;
+ u16 v_idx, cpu = 0;
int err;
if (vsi->q_vectors[0]) {
@@ -674,6 +674,17 @@ int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi)
goto err_out;
}
+ v_idx = 0;
+ for_each_numa_hop_mask(aff_mask, numa_node) {
+ for_each_cpu_andnot(cpu, aff_mask, last_aff_mask)
+ if (v_idx < vsi->num_q_vectors) {
+ if (cpu_online(cpu))
+ cpumask_set_cpu(cpu, &vsi->q_vectors[v_idx]->affinity_mask);
+ v_idx++;
+ }
+ last_aff_mask = aff_mask;
+ }
+
return 0;
err_out:
--
2.37.3
Powered by blists - more mailing lists