Implement the module parameter for enable/disable of the feature
globally. Also implement the ioctls for enable/disable of the feature
per guest.
TODO: Documentation for the ioctls and kvm module parameters.
Co-developed-by: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>
Signed-off-by: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>
Signed-off-by: Vineeth Pillai (Google) <vineeth@xxxxxxxxxxxxxxx>
---
arch/x86/kvm/x86.c | 8 +++--
include/linux/kvm_host.h | 34 +++++++++++++++++-
include/uapi/linux/kvm.h | 5 +++
virt/kvm/kvm_main.c | 76 +++++++++++++++++++++++++++++++++++++---
4 files changed, 116 insertions(+), 7 deletions(-)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8c15c6ff352e..4fb73833fc68 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9949,8 +9949,12 @@ static void record_vcpu_boost_status(struct kvm_vcpu *vcpu)
void kvm_set_vcpu_boosted(struct kvm_vcpu *vcpu, bool boosted)
{
- kvm_arch_vcpu_set_boost_status(&vcpu->arch,
- boosted ? VCPU_BOOST_BOOSTED : VCPU_BOOST_NORMAL);
+ enum kvm_vcpu_boost_state boost_status = VCPU_BOOST_DISABLED;
+
+ if (kvm_pv_sched_enabled(vcpu->kvm))
+ boost_status = boosted ? VCPU_BOOST_BOOSTED : VCPU_BOOST_NORMAL;
+
+ kvm_arch_vcpu_set_boost_status(&vcpu->arch, boost_status);
kvm_make_request(KVM_REQ_VCPU_BOOST_UPDATE, vcpu);
}
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index f76680fbc60d..07f60a27025c 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -807,6 +807,9 @@ struct kvm {
struct notifier_block pm_notifier;
#endif
char stats_id[KVM_STATS_NAME_SIZE];
+#ifdef CONFIG_PARAVIRT_SCHED_KVM
+ bool pv_sched_enabled;
+#endif
};
#define kvm_err(fmt, ...) \
@@ -2292,9 +2295,38 @@ static inline void kvm_account_pgtable_pages(void *virt, int nr)
void kvm_set_vcpu_boosted(struct kvm_vcpu *vcpu, bool boosted);
int kvm_vcpu_set_sched(struct kvm_vcpu *vcpu, bool boost);
+DECLARE_STATIC_KEY_FALSE(kvm_pv_sched);
+
+static inline bool kvm_pv_sched_enabled(struct kvm *kvm)
+{
+ if (static_branch_unlikely(&kvm_pv_sched))
+ return kvm->pv_sched_enabled;
+
+ return false;
+}
+
+static inline void kvm_set_pv_sched_enabled(struct kvm *kvm, bool enabled)
+{
+ unsigned long i;
+ struct kvm_vcpu *vcpu;
+
+ kvm->pv_sched_enabled = enabled;
+ /*
+ * After setting vcpu_sched_enabled, we need to update each vcpu's
+ * state(VCPU_BOOST_{DISABLED,NORMAL}) so that guest knows about the
+ * update.
+ * When disabling, we would also need to unboost vcpu threads
+ * if already boosted.
+ * XXX: this can race, needs locking!
+ */
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ kvm_vcpu_set_sched(vcpu, false);
+}
+
static inline bool kvm_vcpu_sched_enabled(struct kvm_vcpu *vcpu)
{
- return kvm_arch_vcpu_pv_sched_enabled(&vcpu->arch);
+ return kvm_pv_sched_enabled(vcpu->kvm) &&
+ kvm_arch_vcpu_pv_sched_enabled(&vcpu->arch);
}
static inline void kvm_vcpu_kick_boost(struct kvm_vcpu *vcpu)
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index f089ab290978..4beaeaa3e78f 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1192,6 +1192,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_COUNTER_OFFSET 227
#define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228
#define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229
+#define KVM_CAP_PV_SCHED 600
#ifdef KVM_CAP_IRQ_ROUTING
@@ -2249,4 +2250,8 @@ struct kvm_s390_zpci_op {
/* flags for kvm_s390_zpci_op->u.reg_aen.flags */
#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0)
+/* Available with KVM_CAP_PV_SCHED */
+#define KVM_SET_PV_SCHED_ENABLED _IOW(KVMIO, 0xe0, int)
+#define KVM_GET_PV_SCHED_ENABLED _IOR(KVMIO, 0xe1, int)
+
#endif /* __LINUX_KVM_H */
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 0dd8b84ed073..d17cd28d5a92 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -99,6 +99,52 @@ unsigned int halt_poll_ns_shrink;
module_param(halt_poll_ns_shrink, uint, 0644);
EXPORT_SYMBOL_GPL(halt_poll_ns_shrink);
+#ifdef CONFIG_PARAVIRT_SCHED_KVM
+__read_mostly DEFINE_STATIC_KEY_FALSE(kvm_pv_sched);
+EXPORT_SYMBOL_GPL(kvm_pv_sched);
+
+static int set_kvm_pv_sched(const char *val, const struct kernel_param *cp)
+{
+ struct kvm *kvm;
+ char *s = strstrip((char *)val);
+ bool new_val, old_val = static_key_enabled(&kvm_pv_sched);
+
+ if (!strcmp(s, "0"))
+ new_val = 0;
+ else if (!strcmp(s, "1"))
+ new_val = 1;
+ else
+ return -EINVAL;
+
+ if (old_val != new_val) {
+ if (new_val)
+ static_branch_enable(&kvm_pv_sched);
+ else
+ static_branch_disable(&kvm_pv_sched);
+
+ mutex_lock(&kvm_lock);
+ list_for_each_entry(kvm, &vm_list, vm_list)
+ kvm_set_pv_sched_enabled(kvm, !old_val);
+ mutex_unlock(&kvm_lock);
+ }
+
+ return 0;
+}
+
+static int get_kvm_pv_sched(char *buf, const struct kernel_param *cp)
+{
+ return sprintf(buf, "%s\n",
+ static_key_enabled(&kvm_pv_sched) ? "1" : "0");
+}
+
+static const struct kernel_param_ops kvm_pv_sched_ops = {
+ .set = set_kvm_pv_sched,
+ .get = get_kvm_pv_sched
+};
+
+module_param_cb(kvm_pv_sched, &kvm_pv_sched_ops, NULL, 0644);
+#endif
+
/*
* Ordering of locks:
*
@@ -1157,6 +1203,9 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
+#ifdef CONFIG_PARAVIRT_SCHED_KVM
+ kvm->pv_sched_enabled = true;
+#endif
/*
* Force subsequent debugfs file creations to fail if the VM directory
* is not created (by kvm_create_vm_debugfs()).
@@ -3635,11 +3684,15 @@ int kvm_vcpu_set_sched(struct kvm_vcpu *vcpu, bool boost)
struct task_struct *vcpu_task = NULL;
/*
- * We can ignore the request if a boost request comes
- * when we are already boosted or an unboost request
- * when we are already unboosted.
+ * If the feature is disabled and we receive a boost request,
+ * we can ignore the request and set VCPU_BOOST_DISABLED for the
+ * guest to see(kvm_set_vcpu_boosted).
+ * Similarly, we can ignore the request if a boost request comes
+ * when we are already boosted or an unboost request when we are
+ * already unboosted.
*/
- if (__can_ignore_set_sched(vcpu, boost))
+ if ((!kvm_vcpu_sched_enabled(vcpu) && boost) ||
+ __can_ignore_set_sched(vcpu, boost))
goto set_boost_status;
if (boost) {
@@ -4591,6 +4644,9 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
case KVM_CAP_CHECK_EXTENSION_VM:
case KVM_CAP_ENABLE_CAP_VM:
case KVM_CAP_HALT_POLL:
+#ifdef CONFIG_PARAVIRT_SCHED_KVM
+ case KVM_CAP_PV_SCHED:
+#endif
return 1;
#ifdef CONFIG_KVM_MMIO
case KVM_CAP_COALESCED_MMIO:
@@ -5018,6 +5074,18 @@ static long kvm_vm_ioctl(struct file *filp,
case KVM_GET_STATS_FD:
r = kvm_vm_ioctl_get_stats_fd(kvm);
break;
+#ifdef CONFIG_PARAVIRT_SCHED_KVM
+ case KVM_SET_PV_SCHED_ENABLED:
+ r = -EINVAL;
+ if (arg == 0 || arg == 1) {
+ kvm_set_pv_sched_enabled(kvm, arg);
+ r = 0;
+ }
+ break;
+ case KVM_GET_PV_SCHED_ENABLED:
+ r = kvm->pv_sched_enabled;
+ break;
+#endif
default:
r = kvm_arch_vm_ioctl(filp, ioctl, arg);
}
--
2.43.0
