diff options
Diffstat (limited to '0035-xen-sched-setup-dom0-vCPUs-affinity-only-once.patch')
| -rw-r--r-- | 0035-xen-sched-setup-dom0-vCPUs-affinity-only-once.patch | 123 |
1 files changed, 123 insertions, 0 deletions
diff --git a/0035-xen-sched-setup-dom0-vCPUs-affinity-only-once.patch b/0035-xen-sched-setup-dom0-vCPUs-affinity-only-once.patch new file mode 100644 index 0000000..0dfb3b4 --- /dev/null +++ b/0035-xen-sched-setup-dom0-vCPUs-affinity-only-once.patch @@ -0,0 +1,123 @@ +From 1e31848cdd8d2ff3cb76f364f04f9771f9b3a8b1 Mon Sep 17 00:00:00 2001 +From: Dario Faggioli <dfaggioli@suse.com> +Date: Mon, 15 Aug 2022 15:41:25 +0200 +Subject: [PATCH 35/67] xen/sched: setup dom0 vCPUs affinity only once + +Right now, affinity for dom0 vCPUs is setup in two steps. This is a +problem as, at least in Credit2, unit_insert() sees and uses the +"intermediate" affinity, and place the vCPUs on CPUs where they cannot +be run. And this in turn results in boot hangs, if the "dom0_nodes" +parameter is used. + +Fix this by setting up the affinity properly once and for all, in +sched_init_vcpu() called by create_vcpu(). + +Note that, unless a soft-affinity is explicitly specified for dom0 (by +using the relaxed mode of "dom0_nodes") we set it to the default, which +is all CPUs, instead of computing it basing on hard affinity (if any). +This is because hard and soft affinity should be considered as +independent user controlled properties. In fact, if we dor derive dom0's +soft-affinity from its boot-time hard-affinity, such computed value will +continue to be used even if later the user changes the hard-affinity. +And this could result in the vCPUs behaving differently than what the +user wanted and expects. + +Fixes: dafd936dddbd ("Make credit2 the default scheduler") +Reported-by: Olaf Hering <ohering@suse.de> +Signed-off-by: Dario Faggioli <dfaggioli@suse.com> +Reviewed-by: Jan Beulich <jbeulich@suse.com> +master commit: c79e4d209be3ed2a6b8e97c35944786ed2a66b94 +master date: 2022-08-11 11:46:22 +0200 +--- + xen/common/sched/core.c | 63 +++++++++++++++++++++++++---------------- + 1 file changed, 39 insertions(+), 24 deletions(-) + +diff --git a/xen/common/sched/core.c b/xen/common/sched/core.c +index 8f4b1ca10d1c..f07bd2681fcb 100644 +--- a/xen/common/sched/core.c ++++ b/xen/common/sched/core.c +@@ -571,12 +571,46 @@ int sched_init_vcpu(struct vcpu *v) + return 1; + } + +- /* +- * Initialize affinity settings. The idler, and potentially +- * domain-0 VCPUs, are pinned onto their respective physical CPUs. +- */ +- if ( is_idle_domain(d) || (is_hardware_domain(d) && opt_dom0_vcpus_pin) ) ++ if ( is_idle_domain(d) ) ++ { ++ /* Idle vCPUs are always pinned onto their respective pCPUs */ + sched_set_affinity(unit, cpumask_of(processor), &cpumask_all); ++ } ++ else if ( pv_shim && v->vcpu_id == 0 ) ++ { ++ /* ++ * PV-shim: vcpus are pinned 1:1. Initially only 1 cpu is online, ++ * others will be dealt with when onlining them. This avoids pinning ++ * a vcpu to a not yet online cpu here. ++ */ ++ sched_set_affinity(unit, cpumask_of(0), cpumask_of(0)); ++ } ++ else if ( is_hardware_domain(d) && opt_dom0_vcpus_pin ) ++ { ++ /* ++ * If dom0_vcpus_pin is specified, dom0 vCPUs are pinned 1:1 to ++ * their respective pCPUs too. ++ */ ++ sched_set_affinity(unit, cpumask_of(processor), &cpumask_all); ++ } ++#ifdef CONFIG_X86 ++ else if ( d->domain_id == 0 ) ++ { ++ /* ++ * In absence of dom0_vcpus_pin instead, the hard and soft affinity of ++ * dom0 is controlled by the (x86 only) dom0_nodes parameter. At this ++ * point it has been parsed and decoded into the dom0_cpus mask. ++ * ++ * Note that we always honor what user explicitly requested, for both ++ * hard and soft affinity, without doing any dynamic computation of ++ * either of them. ++ */ ++ if ( !dom0_affinity_relaxed ) ++ sched_set_affinity(unit, &dom0_cpus, &cpumask_all); ++ else ++ sched_set_affinity(unit, &cpumask_all, &dom0_cpus); ++ } ++#endif + else + sched_set_affinity(unit, &cpumask_all, &cpumask_all); + +@@ -3386,29 +3420,10 @@ void wait(void) + void __init sched_setup_dom0_vcpus(struct domain *d) + { + unsigned int i; +- struct sched_unit *unit; + + for ( i = 1; i < d->max_vcpus; i++ ) + vcpu_create(d, i); + +- /* +- * PV-shim: vcpus are pinned 1:1. +- * Initially only 1 cpu is online, others will be dealt with when +- * onlining them. This avoids pinning a vcpu to a not yet online cpu here. +- */ +- if ( pv_shim ) +- sched_set_affinity(d->vcpu[0]->sched_unit, +- cpumask_of(0), cpumask_of(0)); +- else +- { +- for_each_sched_unit ( d, unit ) +- { +- if ( !opt_dom0_vcpus_pin && !dom0_affinity_relaxed ) +- sched_set_affinity(unit, &dom0_cpus, NULL); +- sched_set_affinity(unit, NULL, &dom0_cpus); +- } +- } +- + domain_update_node_affinity(d); + } + #endif +-- +2.37.3 + |