powerpc/kvm/book3s_hv: Use threads_per_subcore in KVM

To support split core on POWER8 we need to modify various parts of the
KVM code to use threads_per_subcore instead of threads_per_core. On
systems that do not support split core threads_per_subcore ==
threads_per_core and these changes are a nop.

We use threads_per_subcore as the value reported by KVM_CAP_PPC_SMT.
This communicates to userspace that guests can only be created with
a value of threads_per_core that is less than or equal to the current
threads_per_subcore. This ensures that guests can only be created with a
thread configuration that we are able to run given the current split
core mode.

Although threads_per_subcore can change during the life of the system,
the commit that enables that will ensure that threads_per_subcore does
not change during the life of a KVM VM.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Michael Neuling <mikey@neuling.org>
Acked-by: Alexander Graf <agraf@suse.de>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index d7b74f888ad8fcd3770a1190840e4e68bae11ed8..5e86f28c9d2f490cba11dd6d311371e80ae60dd8 100644 (file)
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1266,7 +1266,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
        int core;
        struct kvmppc_vcore *vcore;
 
-       core = id / threads_per_core;
+       core = id / threads_per_subcore;
        if (core >= KVM_MAX_VCORES)
                goto out;
 
@@ -1305,7 +1305,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
                        init_waitqueue_head(&vcore->wq);
                        vcore->preempt_tb = TB_NIL;
                        vcore->lpcr = kvm->arch.lpcr;
-                       vcore->first_vcpuid = core * threads_per_core;
+                       vcore->first_vcpuid = core * threads_per_subcore;
                        vcore->kvm = kvm;
                }
                kvm->arch.vcores[core] = vcore;
@@ -1495,16 +1495,19 @@ static void kvmppc_wait_for_nap(struct kvmppc_vcore *vc)
 static int on_primary_thread(void)
 {
        int cpu = smp_processor_id();
-       int thr = cpu_thread_in_core(cpu);
+       int thr;
 
-       if (thr)
+       /* Are we on a primary subcore? */
+       if (cpu_thread_in_subcore(cpu))
                return 0;
-       while (++thr < threads_per_core)
+
+       thr = 0;
+       while (++thr < threads_per_subcore)
                if (cpu_online(cpu + thr))
                        return 0;
 
        /* Grab all hw threads so they can't go into the kernel */
-       for (thr = 1; thr < threads_per_core; ++thr) {
+       for (thr = 1; thr < threads_per_subcore; ++thr) {
                if (kvmppc_grab_hwthread(cpu + thr)) {
                        /* Couldn't grab one; let the others go */
                        do {
@@ -1563,15 +1566,18 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
        }
 
        /*
-        * Make sure we are running on thread 0, and that
-        * secondary threads are offline.
+        * Make sure we are running on primary threads, and that secondary
+        * threads are offline.  Also check if the number of threads in this
+        * guest are greater than the current system threads per guest.
         */
-       if (threads_per_core > 1 && !on_primary_thread()) {
+       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)
                        vcpu->arch.ret = -EBUSY;
                goto out;
        }
 
+
        vc->pcpu = smp_processor_id();
        list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
                kvmppc_start_thread(vcpu);
@@ -1599,7 +1605,7 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
        /* wait for secondary threads to finish writing their state to memory */
        if (vc->nap_count < vc->n_woken)
                kvmppc_wait_for_nap(vc);
-       for (i = 0; i < threads_per_core; ++i)
+       for (i = 0; i < threads_per_subcore; ++i)
                kvmppc_release_hwthread(vc->pcpu + i);
        /* prevent other vcpu threads from doing kvmppc_start_thread() now */
        vc->vcore_state = VCORE_EXITING;

diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 3cf541a53e2aef14a00e467e0c4daec16c255e7a..27919a8715cf33287c27413e7e843bd66e4284da 100644 (file)
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -384,7 +384,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
        case KVM_CAP_PPC_SMT:
                if (hv_enabled)
-                       r = threads_per_core;
+                       r = threads_per_subcore;
                else
                        r = 0;
                break;