summaryrefslogtreecommitdiff
path: root/drivers/hv
diff options
context:
space:
mode:
authorK. Y. Srinivasan <kys@exchange.microsoft.com>2016-09-02 15:58:23 +0300
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2016-09-02 18:22:51 +0300
commit509879bdb30b8e12bd0b3cb0bc8429f01478df4b (patch)
treea2e9e25f47bec693795bd9493bdcce91bd61e38f /drivers/hv
parentbb08d431a914984dee278e0e0482a2e6d620a482 (diff)
downloadlinux-509879bdb30b8e12bd0b3cb0bc8429f01478df4b.tar.xz
Drivers: hv: Introduce a policy for controlling channel affinity
Introduce a mechanism to control how channels will be affinitized. We will support two policies: 1. HV_BALANCED: All performance critical channels will be dstributed evenly amongst all the available NUMA nodes. Once the Node is assigned, we will assign the CPU based on a simple round robin scheme. 2. HV_LOCALIZED: Only the primary channels are distributed across all NUMA nodes. Sub-channels will be in the same NUMA node as the primary channel. This is the current behaviour. The default policy will be the HV_BALANCED as it can minimize the remote memory access on NUMA machines with applications that span NUMA nodes. Signed-off-by: K. Y. Srinivasan <kys@microsoft.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'drivers/hv')
-rw-r--r--drivers/hv/channel_mgmt.c68
1 files changed, 39 insertions, 29 deletions
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index d8b64ba45b1d..bbd812e87511 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -356,8 +356,9 @@ void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
* We need to free the bit for init_vp_index() to work in the case
* of sub-channel, when we reload drivers like hv_netvsc.
*/
- cpumask_clear_cpu(channel->target_cpu,
- &primary_channel->alloced_cpus_in_node);
+ if (channel->affinity_policy == HV_LOCALIZED)
+ cpumask_clear_cpu(channel->target_cpu,
+ &primary_channel->alloced_cpus_in_node);
vmbus_release_relid(relid);
@@ -548,17 +549,17 @@ static void init_vp_index(struct vmbus_channel *channel, u16 dev_type)
}
/*
- * We distribute primary channels evenly across all the available
- * NUMA nodes and within the assigned NUMA node we will assign the
- * first available CPU to the primary channel.
- * The sub-channels will be assigned to the CPUs available in the
- * NUMA node evenly.
+ * Based on the channel affinity policy, we will assign the NUMA
+ * nodes.
*/
- if (!primary) {
+
+ if ((channel->affinity_policy == HV_BALANCED) || (!primary)) {
while (true) {
next_node = next_numa_node_id++;
- if (next_node == nr_node_ids)
+ if (next_node == nr_node_ids) {
next_node = next_numa_node_id = 0;
+ continue;
+ }
if (cpumask_empty(cpumask_of_node(next_node)))
continue;
break;
@@ -582,15 +583,17 @@ static void init_vp_index(struct vmbus_channel *channel, u16 dev_type)
cur_cpu = -1;
- /*
- * Normally Hyper-V host doesn't create more subchannels than there
- * are VCPUs on the node but it is possible when not all present VCPUs
- * on the node are initialized by guest. Clear the alloced_cpus_in_node
- * to start over.
- */
- if (cpumask_equal(&primary->alloced_cpus_in_node,
- cpumask_of_node(primary->numa_node)))
- cpumask_clear(&primary->alloced_cpus_in_node);
+ if (primary->affinity_policy == HV_LOCALIZED) {
+ /*
+ * Normally Hyper-V host doesn't create more subchannels
+ * than there are VCPUs on the node but it is possible when not
+ * all present VCPUs on the node are initialized by guest.
+ * Clear the alloced_cpus_in_node to start over.
+ */
+ if (cpumask_equal(&primary->alloced_cpus_in_node,
+ cpumask_of_node(primary->numa_node)))
+ cpumask_clear(&primary->alloced_cpus_in_node);
+ }
while (true) {
cur_cpu = cpumask_next(cur_cpu, &available_mask);
@@ -601,17 +604,24 @@ static void init_vp_index(struct vmbus_channel *channel, u16 dev_type)
continue;
}
- /*
- * NOTE: in the case of sub-channel, we clear the sub-channel
- * related bit(s) in primary->alloced_cpus_in_node in
- * hv_process_channel_removal(), so when we reload drivers
- * like hv_netvsc in SMP guest, here we're able to re-allocate
- * bit from primary->alloced_cpus_in_node.
- */
- if (!cpumask_test_cpu(cur_cpu,
- &primary->alloced_cpus_in_node)) {
- cpumask_set_cpu(cur_cpu,
- &primary->alloced_cpus_in_node);
+ if (primary->affinity_policy == HV_LOCALIZED) {
+ /*
+ * NOTE: in the case of sub-channel, we clear the
+ * sub-channel related bit(s) in
+ * primary->alloced_cpus_in_node in
+ * hv_process_channel_removal(), so when we
+ * reload drivers like hv_netvsc in SMP guest, here
+ * we're able to re-allocate
+ * bit from primary->alloced_cpus_in_node.
+ */
+ if (!cpumask_test_cpu(cur_cpu,
+ &primary->alloced_cpus_in_node)) {
+ cpumask_set_cpu(cur_cpu,
+ &primary->alloced_cpus_in_node);
+ cpumask_set_cpu(cur_cpu, alloced_mask);
+ break;
+ }
+ } else {
cpumask_set_cpu(cur_cpu, alloced_mask);
break;
}