Rather than calling cond_resched() in kvmppc_run_core() before doing
the post-processing for the vcpus that we have just run (that is,
calling kvmppc_handle_exit_hv(), kvmppc_set_timer(), etc.), we now do
that post-processing before calling cond_resched(), and that post-
processing is moved out into its own function, post_guest_process().
The reschedule point is now in kvmppc_run_vcpu() and we define a new
vcore state, VCORE_PREEMPT, to indicate that that the vcore's runner
task is runnable but not running. (Doing the reschedule with the
vcore in VCORE_INACTIVE state would be bad because there are potentially
other vcpus waiting for the runner in kvmppc_wait_for_exec() which
then wouldn't get woken up.)
Also, we make use of the handy cond_resched_lock() function, which
unlocks and relocks vc->lock for us around the reschedule.
Signed-off-by: Paul Mackerras <paulus@xxxxxxxxx>
---
arch/powerpc/include/asm/kvm_host.h | 5 +-
arch/powerpc/kvm/book3s_hv.c | 92 +++++++++++++++++++++----------------
2 files changed, 55 insertions(+), 42 deletions(-)
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index ec4cf37..7b327e5 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -304,8 +304,9 @@ struct kvmppc_vcore {
/* Values for vcore_state */
#define VCORE_INACTIVE 0
#define VCORE_SLEEPING 1
-#define VCORE_RUNNING 2
-#define VCORE_EXITING 3
+#define VCORE_PREEMPT 2
+#define VCORE_RUNNING 3
+#define VCORE_EXITING 4
/*
* Struct used to manage memory for a virtual processor area
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 15598be..bd16b03 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1855,15 +1855,50 @@ static void prepare_threads(struct kvmppc_vcore *vc)
}
}
+static void post_guest_process(struct kvmppc_vcore *vc)
+{
+ u64 now;
+ long ret;
+ struct kvm_vcpu *vcpu, *vnext;
+
+ now = get_tb();
+ list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
+ arch.run_list) {
+ /* cancel pending dec exception if dec is positive */
+ if (now < vcpu->arch.dec_expires &&
+ kvmppc_core_pending_dec(vcpu))
+ kvmppc_core_dequeue_dec(vcpu);
+
+ trace_kvm_guest_exit(vcpu);
+
+ ret = RESUME_GUEST;
+ if (vcpu->arch.trap)
+ ret = kvmppc_handle_exit_hv(vcpu->arch.kvm_run, vcpu,
+ vcpu->arch.run_task);
+
+ vcpu->arch.ret = ret;
+ vcpu->arch.trap = 0;
+
+ if (vcpu->arch.ceded) {
+ if (!is_kvmppc_resume_guest(ret))
+ kvmppc_end_cede(vcpu);
+ else
+ kvmppc_set_timer(vcpu);
+ }
+ if (!is_kvmppc_resume_guest(vcpu->arch.ret)) {
+ kvmppc_remove_runnable(vc, vcpu);
+ wake_up(&vcpu->arch.cpu_run);
+ }
+ }
+}
+
/*
* Run a set of guest threads on a physical core.
* Called with vc->lock held.
*/
static void kvmppc_run_core(struct kvmppc_vcore *vc)
{
- struct kvm_vcpu *vcpu, *vnext;
- long ret;
- u64 now;
+ struct kvm_vcpu *vcpu;
int i;
int srcu_idx;
@@ -1895,8 +1930,11 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
*/
if ((threads_per_core > 1) &&
((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
- list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
+ list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
vcpu->arch.ret = -EBUSY;
+ kvmppc_remove_runnable(vc, vcpu);
+ wake_up(&vcpu->arch.cpu_run);
+ }
goto out;
}
@@ -1952,44 +1990,12 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
kvm_guest_exit();
preempt_enable();
- cond_resched();
spin_lock(&vc->lock);
- now = get_tb();
- list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
- /* cancel pending dec exception if dec is positive */
- if (now < vcpu->arch.dec_expires &&
- kvmppc_core_pending_dec(vcpu))
- kvmppc_core_dequeue_dec(vcpu);
-
- trace_kvm_guest_exit(vcpu);
-
- ret = RESUME_GUEST;
- if (vcpu->arch.trap)
- ret = kvmppc_handle_exit_hv(vcpu->arch.kvm_run, vcpu,
- vcpu->arch.run_task);
-
- vcpu->arch.ret = ret;
- vcpu->arch.trap = 0;
-
- if (vcpu->arch.ceded) {
- if (!is_kvmppc_resume_guest(ret))
- kvmppc_end_cede(vcpu);
- else
- kvmppc_set_timer(vcpu);
- }
- }
+ post_guest_process(vc);
out:
vc->vcore_state = VCORE_INACTIVE;
- list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
- arch.run_list) {
- if (!is_kvmppc_resume_guest(vcpu->arch.ret)) {
- kvmppc_remove_runnable(vc, vcpu);
- wake_up(&vcpu->arch.cpu_run);
- }
- }
-
trace_kvmppc_run_core(vc, 1);
}
@@ -2111,7 +2117,6 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
}
if (!vc->n_runnable || vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
break;
- vc->runner = vcpu;
n_ceded = 0;
list_for_each_entry(v, &vc->runnable_threads, arch.run_list) {
if (!v->arch.pending_exceptions)
@@ -2119,10 +2124,17 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
else
v->arch.ceded = 0;
}
- if (n_ceded == vc->n_runnable)
+ vc->runner = vcpu;
+ if (n_ceded == vc->n_runnable) {
kvmppc_vcore_blocked(vc);
- else
+ } else if (should_resched()) {
+ vc->vcore_state = VCORE_PREEMPT;
+ /* Let something else run */
+ cond_resched_lock(&vc->lock);
+ vc->vcore_state = VCORE_INACTIVE;
+ } else {
kvmppc_run_core(vc);
+ }
vc->runner = NULL;
}
--
2.1.4
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
