KVM: PPC: Book3S HV: Make use of unused threads when running guests

When running a virtual core of a guest that is configured with fewer
threads per core than the physical cores have, the extra physical
threads are currently unused.  This makes it possible to use them to
run one or more other virtual cores from the same guest when certain
conditions are met.  This applies on POWER7, and on POWER8 to guests
with one thread per virtual core.  (It doesn't apply to POWER8 guests
with multiple threads per vcore because they require a 1-1 virtual to
physical thread mapping in order to be able to use msgsndp and the
TIR.)

The idea is that we maintain a list of preempted vcores for each
physical cpu (i.e. each core, since the host runs single-threaded).
Then, when a vcore is about to run, it checks to see if there are
any vcores on the list for its physical cpu that could be
piggybacked onto this vcore's execution.  If so, those additional
vcores are put into state VCORE_PIGGYBACK and their runnable VCPU
threads are started as well as the original vcore, which is called
the master vcore.

After the vcores have exited the guest, the extra ones are put back
onto the preempted list if any of their VCPUs are still runnable and
not idle.

This means that vcpu->arch.ptid is no longer necessarily the same as
the physical thread that the vcpu runs on.  In order to make it easier
for code that wants to send an IPI to know which CPU to target, we
now store that in a new field in struct vcpu_arch, called thread_cpu.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

arch/powerpc/include/asm/kvm_host.h

@@ -278,7 +278,9 @@ struct kvmppc_vcore {
 	u16 last_cpu;
 	u8 vcore_state;
 	u8 in_guest;
+	struct kvmppc_vcore *master_vcore;
 	struct list_head runnable_threads;
+	struct list_head preempt_list;
 	spinlock_t lock;
 	wait_queue_head_t wq;
 	spinlock_t stoltb_lock;	/* protects stolen_tb and preempt_tb */
@@ -300,12 +302,18 @@ struct kvmppc_vcore {
 #define VCORE_EXIT_MAP(vc)	((vc)->entry_exit_map >> 8)
 #define VCORE_IS_EXITING(vc)	(VCORE_EXIT_MAP(vc) != 0)
 
-/* Values for vcore_state */
+/*
+ * Values for vcore_state.
+ * Note that these are arranged such that lower values
+ * (< VCORE_SLEEPING) don't require stolen time accounting
+ * on load/unload, and higher values do.
+ */
 #define VCORE_INACTIVE	0
-#define VCORE_SLEEPING	1
-#define VCORE_PREEMPT	2
-#define VCORE_RUNNING	3
-#define VCORE_EXITING	4
+#define VCORE_PREEMPT	1
+#define VCORE_PIGGYBACK	2
+#define VCORE_SLEEPING	3
+#define VCORE_RUNNING	4
+#define VCORE_EXITING	5
 
 /*
  * Struct used to manage memory for a virtual processor area
@@ -619,6 +627,7 @@ struct kvm_vcpu_arch {
 	int trap;
 	int state;
 	int ptid;
+	int thread_cpu;
 	bool timer_running;
 	wait_queue_head_t cpu_run;
 

arch/powerpc/kernel/asm-offsets.c

@@ -512,6 +512,8 @@ int main(void)
 	DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa.pinned_addr));
 	DEFINE(VCPU_VPA_DIRTY, offsetof(struct kvm_vcpu, arch.vpa.dirty));
 	DEFINE(VCPU_HEIR, offsetof(struct kvm_vcpu, arch.emul_inst));
+	DEFINE(VCPU_CPU, offsetof(struct kvm_vcpu, cpu));
+	DEFINE(VCPU_THREAD_CPU, offsetof(struct kvm_vcpu, arch.thread_cpu));
 #endif
 #ifdef CONFIG_PPC_BOOK3S
 	DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id));

arch/powerpc/kvm/book3s_hv_builtin.c

@@ -110,14 +110,15 @@ void __init kvm_cma_reserve(void)
 long int kvmppc_rm_h_confer(struct kvm_vcpu *vcpu, int target,
 			    unsigned int yield_count)
 {
-	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	struct kvmppc_vcore *vc = local_paca->kvm_hstate.kvm_vcore;
+	int ptid = local_paca->kvm_hstate.ptid;
 	int threads_running;
 	int threads_ceded;
 	int threads_conferring;
 	u64 stop = get_tb() + 10 * tb_ticks_per_usec;
 	int rv = H_SUCCESS; /* => don't yield */
 
-	set_bit(vcpu->arch.ptid, &vc->conferring_threads);
+	set_bit(ptid, &vc->conferring_threads);
 	while ((get_tb() < stop) && !VCORE_IS_EXITING(vc)) {
 		threads_running = VCORE_ENTRY_MAP(vc);
 		threads_ceded = vc->napping_threads;
@@ -127,7 +128,7 @@ long int kvmppc_rm_h_confer(struct kvm_vcpu *vcpu, int target,
 			break;
 		}
 	}
-	clear_bit(vcpu->arch.ptid, &vc->conferring_threads);
+	clear_bit(ptid, &vc->conferring_threads);
 	return rv;
 }
 

arch/powerpc/kvm/book3s_hv_rm_xics.c

@@ -67,14 +67,12 @@ static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu,
 	}
 
 	/* Check if the core is loaded, if not, too hard */
-	cpu = vcpu->cpu;
+	cpu = vcpu->arch.thread_cpu;
 	if (cpu < 0 || cpu >= nr_cpu_ids) {
 		this_icp->rm_action |= XICS_RM_KICK_VCPU;
 		this_icp->rm_kick_target = vcpu;
 		return;
 	}
-	/* In SMT cpu will always point to thread 0, we adjust it */
-	cpu += vcpu->arch.ptid;
 
 	smp_mb();
 	kvmhv_rm_send_ipi(cpu);

arch/powerpc/kvm/book3s_hv_rmhandlers.S

@@ -1176,6 +1176,11 @@ mc_cont:
 	ld	r9, HSTATE_KVM_VCPU(r13)
 	lwz	r12, VCPU_TRAP(r9)
 
+	/* Stop others sending VCPU interrupts to this physical CPU */
+	li	r0, -1
+	stw	r0, VCPU_CPU(r9)
+	stw	r0, VCPU_THREAD_CPU(r9)
+
 	/* Save guest CTRL register, set runlatch to 1 */
 	mfspr	r6,SPRN_CTRLF
 	stw	r6,VCPU_CTRL(r9)