summaryrefslogtreecommitdiffstats
path: root/virt/kvm/kvm_main.c
diff options
context:
space:
mode:
authorChristian Borntraeger <borntraeger@de.ibm.com>2014-01-16 13:44:20 +0100
committerPaolo Bonzini <pbonzini@redhat.com>2014-05-05 16:29:11 +0200
commit719d93cd5f5c5c8775b7a38192069e8e1d1ac46e (patch)
treee6d7703b4b69acf92db962fbe96d9f7c380484c8 /virt/kvm/kvm_main.c
parent57b5981cd38cbca3554c5e663b2361d9adea70c2 (diff)
downloadlinux-stable-719d93cd5f5c5c8775b7a38192069e8e1d1ac46e.tar.gz
linux-stable-719d93cd5f5c5c8775b7a38192069e8e1d1ac46e.tar.bz2
linux-stable-719d93cd5f5c5c8775b7a38192069e8e1d1ac46e.zip
kvm/irqchip: Speed up KVM_SET_GSI_ROUTING
When starting lots of dataplane devices the bootup takes very long on Christian's s390 with irqfd patches. With larger setups he is even able to trigger some timeouts in some components. Turns out that the KVM_SET_GSI_ROUTING ioctl takes very long (strace claims up to 0.1 sec) when having multiple CPUs. This is caused by the synchronize_rcu and the HZ=100 of s390. By changing the code to use a private srcu we can speed things up. This patch reduces the boot time till mounting root from 8 to 2 seconds on my s390 guest with 100 disks. Uses of hlist_for_each_entry_rcu, hlist_add_head_rcu, hlist_del_init_rcu are fine because they do not have lockdep checks (hlist_for_each_entry_rcu uses rcu_dereference_raw rather than rcu_dereference, and write-sides do not do rcu lockdep at all). Note that we're hardly relying on the "sleepable" part of srcu. We just want SRCU's faster detection of grace periods. Testing was done by Andrew Theurer using netperf tests STREAM, MAERTS and RR. The difference between results "before" and "after" the patch has mean -0.2% and standard deviation 0.6%. Using a paired t-test on the data points says that there is a 2.5% probability that the patch is the cause of the performance difference (rather than a random fluctuation). (Restricting the t-test to RR, which is the most likely to be affected, changes the numbers to respectively -0.3% mean, 0.7% stdev, and 8% probability that the numbers actually say something about the patch. The probability increases mostly because there are fewer data points). Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Michael S. Tsirkin <mst@redhat.com> Tested-by: Christian Borntraeger <borntraeger@de.ibm.com> # s390 Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Diffstat (limited to 'virt/kvm/kvm_main.c')
-rw-r--r--virt/kvm/kvm_main.c16
1 files changed, 10 insertions, 6 deletions
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index fa70c6e642b4..95b4c2b3906a 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -457,11 +457,11 @@ static struct kvm *kvm_create_vm(unsigned long type)
r = kvm_arch_init_vm(kvm, type);
if (r)
- goto out_err_nodisable;
+ goto out_err_no_disable;
r = hardware_enable_all();
if (r)
- goto out_err_nodisable;
+ goto out_err_no_disable;
#ifdef CONFIG_HAVE_KVM_IRQCHIP
INIT_HLIST_HEAD(&kvm->mask_notifier_list);
@@ -473,10 +473,12 @@ static struct kvm *kvm_create_vm(unsigned long type)
r = -ENOMEM;
kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
if (!kvm->memslots)
- goto out_err_nosrcu;
+ goto out_err_no_srcu;
kvm_init_memslots_id(kvm);
if (init_srcu_struct(&kvm->srcu))
- goto out_err_nosrcu;
+ goto out_err_no_srcu;
+ if (init_srcu_struct(&kvm->irq_srcu))
+ goto out_err_no_irq_srcu;
for (i = 0; i < KVM_NR_BUSES; i++) {
kvm->buses[i] = kzalloc(sizeof(struct kvm_io_bus),
GFP_KERNEL);
@@ -505,10 +507,12 @@ static struct kvm *kvm_create_vm(unsigned long type)
return kvm;
out_err:
+ cleanup_srcu_struct(&kvm->irq_srcu);
+out_err_no_irq_srcu:
cleanup_srcu_struct(&kvm->srcu);
-out_err_nosrcu:
+out_err_no_srcu:
hardware_disable_all();
-out_err_nodisable:
+out_err_no_disable:
for (i = 0; i < KVM_NR_BUSES; i++)
kfree(kvm->buses[i]);
kfree(kvm->memslots);