Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull more kvm updates from Paolo Bonzini:
 "ARM:
   - Full debug support for arm64
   - Active state switching for timer interrupts
   - Lazy FP/SIMD save/restore for arm64
   - Generic ARMv8 target

  PPC:
   - Book3S: A few bug fixes
   - Book3S: Allow micro-threading on POWER8

  x86:
   - Compiler warnings

  Generic:
   - Adaptive polling for guest halt"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (49 commits)
  kvm: irqchip: fix memory leak
  kvm: move new trace event outside #ifdef CONFIG_KVM_ASYNC_PF
  KVM: trace kvm_halt_poll_ns grow/shrink
  KVM: dynamic halt-polling
  KVM: make halt_poll_ns per-vCPU
  Silence compiler warning in arch/x86/kvm/emulate.c
  kvm: compile process_smi_save_seg_64() only for x86_64
  KVM: x86: avoid uninitialized variable warning
  KVM: PPC: Book3S: Fix typo in top comment about locking
  KVM: PPC: Book3S: Fix size of the PSPB register
  KVM: PPC: Book3S HV: Exit on H_DOORBELL if HOST_IPI is set
  KVM: PPC: Book3S HV: Fix race in starting secondary threads
  KVM: PPC: Book3S: correct width in XER handling
  KVM: PPC: Book3S HV: Fix preempted vcore stolen time calculation
  KVM: PPC: Book3S HV: Fix preempted vcore list locking
  KVM: PPC: Book3S HV: Implement H_CLEAR_REF and H_CLEAR_MOD
  KVM: PPC: Book3S HV: Fix bug in dirty page tracking
  KVM: PPC: Book3S HV: Fix race in reading change bit when removing HPTE
  KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8
  KVM: PPC: Book3S HV: Make use of unused threads when running guests
  ...

17 files changed, 899 insertions, 134 deletions

diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 3caec2c42105..c2024ac9d4e8 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -74,14 +74,14 @@ config KVM_BOOK3S_64
 	  If unsure, say N.
 
 config KVM_BOOK3S_64_HV
-	tristate "KVM support for POWER7 and PPC970 using hypervisor mode in host"
+	tristate "KVM for POWER7 and later using hypervisor mode in host"
 	depends on KVM_BOOK3S_64 && PPC_POWERNV
 	select KVM_BOOK3S_HV_POSSIBLE
 	select MMU_NOTIFIER
 	select CMA
 	---help---
 	  Support running unmodified book3s_64 guest kernels in
-	  virtual machines on POWER7 and PPC970 processors that have
+	  virtual machines on POWER7 and newer processors that have
 	  hypervisor mode available to the host.
 
 	  If you say Y here, KVM will use the hardware virtualization
@@ -89,8 +89,8 @@ config KVM_BOOK3S_64_HV
 	  guest operating systems will run at full hardware speed
 	  using supervisor and user modes.  However, this also means
 	  that KVM is not usable under PowerVM (pHyp), is only usable
-	  on POWER7 (or later) processors and PPC970-family processors,
-	  and cannot emulate a different processor from the host processor.
+	  on POWER7 or later processors, and cannot emulate a
+	  different processor from the host processor.
 
 	  If unsure, say N.
 
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 6d6398f4d632..d75bf325f54a 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -240,7 +240,8 @@ void kvmppc_core_queue_inst_storage(struct kvm_vcpu *vcpu, ulong flags)
 	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_INST_STORAGE);
 }
 
-int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority)
+static int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu,
+					 unsigned int priority)
 {
 	int deliver = 1;
 	int vec = 0;
diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index 2035d16a9262..d5c9bfeb0c9c 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -26,6 +26,7 @@
 #include <asm/machdep.h>
 #include <asm/mmu_context.h>
 #include <asm/hw_irq.h>
+#include "book3s.h"
 
 /* #define DEBUG_MMU */
 /* #define DEBUG_SR */
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index b982d925c710..79ad35abd196 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -28,6 +28,7 @@
 #include <asm/mmu_context.h>
 #include <asm/hw_irq.h>
 #include "trace_pr.h"
+#include "book3s.h"
 
 #define PTE_SIZE 12
 
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index dab68b7af3f2..1f9c0a17f445 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -761,6 +761,8 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
 			/* Harvest R and C */
 			rcbits = be64_to_cpu(hptep[1]) & (HPTE_R_R | HPTE_R_C);
 			*rmapp |= rcbits << KVMPPC_RMAP_RC_SHIFT;
+			if (rcbits & HPTE_R_C)
+				kvmppc_update_rmap_change(rmapp, psize);
 			if (rcbits & ~rev[i].guest_rpte) {
 				rev[i].guest_rpte = ptel | rcbits;
 				note_hpte_modification(kvm, &rev[i]);
@@ -927,8 +929,12 @@ static int kvm_test_clear_dirty_npages(struct kvm *kvm, unsigned long *rmapp)
  retry:
 	lock_rmap(rmapp);
 	if (*rmapp & KVMPPC_RMAP_CHANGED) {
-		*rmapp &= ~KVMPPC_RMAP_CHANGED;
+		long change_order = (*rmapp & KVMPPC_RMAP_CHG_ORDER)
+			>> KVMPPC_RMAP_CHG_SHIFT;
+		*rmapp &= ~(KVMPPC_RMAP_CHANGED | KVMPPC_RMAP_CHG_ORDER);
 		npages_dirty = 1;
+		if (change_order > PAGE_SHIFT)
+			npages_dirty = 1ul << (change_order - PAGE_SHIFT);
 	}
 	if (!(*rmapp & KVMPPC_RMAP_PRESENT)) {
 		unlock_rmap(rmapp);
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index 5a2bc4b0dfe5..2afdb9c0937d 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -23,6 +23,7 @@
 #include <asm/reg.h>
 #include <asm/switch_to.h>
 #include <asm/time.h>
+#include "book3s.h"
 
 #define OP_19_XOP_RFID		18
 #define OP_19_XOP_RFI		50
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index a9f753fb73a8..9754e6815e52 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -81,6 +81,12 @@ static DECLARE_BITMAP(default_enabled_hcalls, MAX_HCALL_OPCODE/4 + 1);
 #define MPP_BUFFER_ORDER	3
 #endif
 
+static int dynamic_mt_modes = 6;
+module_param(dynamic_mt_modes, int, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(dynamic_mt_modes, "Set of allowed dynamic micro-threading modes: 0 (= none), 2, 4, or 6 (= 2 or 4)");
+static int target_smt_mode;
+module_param(target_smt_mode, int, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(target_smt_mode, "Target threads per core (0 = max)");
 
 static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
@@ -114,7 +120,7 @@ static bool kvmppc_ipi_thread(int cpu)
 
 static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 {
-	int cpu = vcpu->cpu;
+	int cpu;
 	wait_queue_head_t *wqp;
 
 	wqp = kvm_arch_vcpu_wq(vcpu);
@@ -123,10 +129,11 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 		++vcpu->stat.halt_wakeup;
 	}
 
-	if (kvmppc_ipi_thread(cpu + vcpu->arch.ptid))
+	if (kvmppc_ipi_thread(vcpu->arch.thread_cpu))
 		return;
 
 	/* CPU points to the first thread of the core */
+	cpu = vcpu->cpu;
 	if (cpu >= 0 && cpu < nr_cpu_ids && cpu_online(cpu))
 		smp_send_reschedule(cpu);
 }
@@ -164,6 +171,27 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
  * they should never fail.)
  */
 
+static void kvmppc_core_start_stolen(struct kvmppc_vcore *vc)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&vc->stoltb_lock, flags);
+	vc->preempt_tb = mftb();
+	spin_unlock_irqrestore(&vc->stoltb_lock, flags);
+}
+
+static void kvmppc_core_end_stolen(struct kvmppc_vcore *vc)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&vc->stoltb_lock, flags);
+	if (vc->preempt_tb != TB_NIL) {
+		vc->stolen_tb += mftb() - vc->preempt_tb;
+		vc->preempt_tb = TB_NIL;
+	}
+	spin_unlock_irqrestore(&vc->stoltb_lock, flags);
+}
+
 static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu)
 {
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
@@ -175,14 +203,9 @@ static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu)
 	 * vcpu, and once it is set to this vcpu, only this task
 	 * ever sets it to NULL.
 	 */
-	if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE) {
-		spin_lock_irqsave(&vc->stoltb_lock, flags);
-		if (vc->preempt_tb != TB_NIL) {
-			vc->stolen_tb += mftb() - vc->preempt_tb;
-			vc->preempt_tb = TB_NIL;
-		}
-		spin_unlock_irqrestore(&vc->stoltb_lock, flags);
-	}
+	if (vc->runner == vcpu && vc->vcore_state >= VCORE_SLEEPING)
+		kvmppc_core_end_stolen(vc);
+
 	spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
 	if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST &&
 	    vcpu->arch.busy_preempt != TB_NIL) {
@@ -197,11 +220,9 @@ static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu)
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
 	unsigned long flags;
 
-	if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE) {
-		spin_lock_irqsave(&vc->stoltb_lock, flags);
-		vc->preempt_tb = mftb();
-		spin_unlock_irqrestore(&vc->stoltb_lock, flags);
-	}
+	if (vc->runner == vcpu && vc->vcore_state >= VCORE_SLEEPING)
+		kvmppc_core_start_stolen(vc);
+
 	spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
 	if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST)
 		vcpu->arch.busy_preempt = mftb();
@@ -214,12 +235,12 @@ static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
 	kvmppc_end_cede(vcpu);
 }
 
-void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr)
+static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr)
 {
 	vcpu->arch.pvr = pvr;
 }
 
-int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
+static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
 {
 	unsigned long pcr = 0;
 	struct kvmppc_vcore *vc = vcpu->arch.vcore;
@@ -259,7 +280,7 @@ int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
 	return 0;
 }
 
-void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
+static void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
 {
 	int r;
 
@@ -292,7 +313,7 @@ void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
 	       vcpu->arch.last_inst);
 }
 
-struct kvm_vcpu *kvmppc_find_vcpu(struct kvm *kvm, int id)
+static struct kvm_vcpu *kvmppc_find_vcpu(struct kvm *kvm, int id)
 {
 	int r;
 	struct kvm_vcpu *v, *ret = NULL;
@@ -641,7 +662,8 @@ static int kvm_arch_vcpu_yield_to(struct kvm_vcpu *target)
 
 	spin_lock(&vcore->lock);
 	if (target->arch.state == KVMPPC_VCPU_RUNNABLE &&
-	    vcore->vcore_state != VCORE_INACTIVE)
+	    vcore->vcore_state != VCORE_INACTIVE &&
+	    vcore->runner)
 		target = vcore->runner;
 	spin_unlock(&vcore->lock);
 
@@ -1431,6 +1453,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
 	vcore->lpcr = kvm->arch.lpcr;
 	vcore->first_vcpuid = core * threads_per_subcore;
 	vcore->kvm = kvm;
+	INIT_LIST_HEAD(&vcore->preempt_list);
 
 	vcore->mpp_buffer_is_valid = false;
 
@@ -1655,6 +1678,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
 	spin_unlock(&vcore->lock);
 	vcpu->arch.vcore = vcore;
 	vcpu->arch.ptid = vcpu->vcpu_id - vcore->first_vcpuid;
+	vcpu->arch.thread_cpu = -1;
 
 	vcpu->arch.cpu_type = KVM_CPU_3S_64;
 	kvmppc_sanity_check(vcpu);
@@ -1749,6 +1773,7 @@ static int kvmppc_grab_hwthread(int cpu)
 
 	/* Ensure the thread won't go into the kernel if it wakes */
 	tpaca->kvm_hstate.kvm_vcpu = NULL;
+	tpaca->kvm_hstate.kvm_vcore = NULL;
 	tpaca->kvm_hstate.napping = 0;
 	smp_wmb();
 	tpaca->kvm_hstate.hwthread_req = 1;
@@ -1780,26 +1805,32 @@ static void kvmppc_release_hwthread(int cpu)
 	tpaca = &paca[cpu];
 	tpaca->kvm_hstate.hwthread_req = 0;
 	tpaca->kvm_hstate.kvm_vcpu = NULL;
+	tpaca->kvm_hstate.kvm_vcore = NULL;
+	tpaca->kvm_hstate.kvm_split_mode = NULL;
 }
 
-static void kvmppc_start_thread(struct kvm_vcpu *vcpu)
+static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc)
 {
 	int cpu;
 	struct paca_struct *tpaca;
-	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	struct kvmppc_vcore *mvc = vc->master_vcore;
 
-	if (vcpu->arch.timer_running) {
-		hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
-		vcpu->arch.timer_running = 0;
+	cpu = vc->pcpu;
+	if (vcpu) {
+		if (vcpu->arch.timer_running) {
+			hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
+			vcpu->arch.timer_running = 0;
+		}
+		cpu += vcpu->arch.ptid;
+		vcpu->cpu = mvc->pcpu;
+		vcpu->arch.thread_cpu = cpu;
 	}
-	cpu = vc->pcpu + vcpu->arch.ptid;
 	tpaca = &paca[cpu];
-	tpaca->kvm_hstate.kvm_vcore = vc;
-	tpaca->kvm_hstate.ptid = vcpu->arch.ptid;
-	vcpu->cpu = vc->pcpu;
-	/* Order stores to hstate.kvm_vcore etc. before store to kvm_vcpu */
-	smp_wmb();
 	tpaca->kvm_hstate.kvm_vcpu = vcpu;
+	tpaca->kvm_hstate.ptid = cpu - mvc->pcpu;
+	/* Order stores to hstate.kvm_vcpu etc. before store to kvm_vcore */
+	smp_wmb();
+	tpaca->kvm_hstate.kvm_vcore = mvc;
 	if (cpu != smp_processor_id())
 		kvmppc_ipi_thread(cpu);
 }
@@ -1812,12 +1843,12 @@ static void kvmppc_wait_for_nap(void)
 	for (loops = 0; loops < 1000000; ++loops) {
 		/*
 		 * Check if all threads are finished.
-		 * We set the vcpu pointer when starting a thread
+		 * We set the vcore pointer when starting a thread
 		 * and the thread clears it when finished, so we look
-		 * for any threads that still have a non-NULL vcpu ptr.
+		 * for any threads that still have a non-NULL vcore ptr.
 		 */
 		for (i = 1; i < threads_per_subcore; ++i)
-			if (paca[cpu + i].kvm_hstate.kvm_vcpu)
+			if (paca[cpu + i].kvm_hstate.kvm_vcore)
 				break;
 		if (i == threads_per_subcore) {
 			HMT_medium();
@@ -1827,7 +1858,7 @@ static void kvmppc_wait_for_nap(void)
 	}
 	HMT_medium();
 	for (i = 1; i < threads_per_subcore; ++i)
-		if (paca[cpu + i].kvm_hstate.kvm_vcpu)
+		if (paca[cpu + i].kvm_hstate.kvm_vcore)
 			pr_err("KVM: CPU %d seems to be stuck\n", cpu + i);
 }
 
@@ -1890,6 +1921,278 @@ static void kvmppc_start_restoring_l2_cache(const struct kvmppc_vcore *vc)
 	mtspr(SPRN_MPPR, mpp_addr | PPC_MPPR_FETCH_WHOLE_TABLE);
 }
 
+/*
+ * A list of virtual cores for each physical CPU.
+ * These are vcores that could run but their runner VCPU tasks are
+ * (or may be) preempted.
+ */
+struct preempted_vcore_list {
+	struct list_head	list;
+	spinlock_t		lock;
+};
+
+static DEFINE_PER_CPU(struct preempted_vcore_list, preempted_vcores);
+
+static void init_vcore_lists(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct preempted_vcore_list *lp = &per_cpu(preempted_vcores, cpu);
+		spin_lock_init(&lp->lock);
+		INIT_LIST_HEAD(&lp->list);
+	}
+}
+
+static void kvmppc_vcore_preempt(struct kvmppc_vcore *vc)
+{
+	struct preempted_vcore_list *lp = this_cpu_ptr(&preempted_vcores);
+
+	vc->vcore_state = VCORE_PREEMPT;
+	vc->pcpu = smp_processor_id();
+	if (vc->num_threads < threads_per_subcore) {
+		spin_lock(&lp->lock);
+		list_add_tail(&vc->preempt_list, &lp->list);
+		spin_unlock(&lp->lock);
+	}
+
+	/* Start accumulating stolen time */
+	kvmppc_core_start_stolen(vc);
+}
+
+static void kvmppc_vcore_end_preempt(struct kvmppc_vcore *vc)
+{
+	struct preempted_vcore_list *lp;
+
+	kvmppc_core_end_stolen(vc);
+	if (!list_empty(&vc->preempt_list)) {
+		lp = &per_cpu(preempted_vcores, vc->pcpu);
+		spin_lock(&lp->lock);
+		list_del_init(&vc->preempt_list);
+		spin_unlock(&lp->lock);
+	}
+	vc->vcore_state = VCORE_INACTIVE;
+}
+
+/*
+ * This stores information about the virtual cores currently
+ * assigned to a physical core.
+ */
+struct core_info {
+	int		n_subcores;
+	int		max_subcore_threads;
+	int		total_threads;
+	int		subcore_threads[MAX_SUBCORES];
+	struct kvm	*subcore_vm[MAX_SUBCORES];
+	struct list_head vcs[MAX_SUBCORES];
+};
+
+/*
+ * This mapping means subcores 0 and 1 can use threads 0-3 and 4-7
+ * respectively in 2-way micro-threading (split-core) mode.
+ */
+static int subcore_thread_map[MAX_SUBCORES] = { 0, 4, 2, 6 };
+
+static void init_core_info(struct core_info *cip, struct kvmppc_vcore *vc)
+{
+	int sub;
+
+	memset(cip, 0, sizeof(*cip));
+	cip->n_subcores = 1;
+	cip->max_subcore_threads = vc->num_threads;
+	cip->total_threads = vc->num_threads;
+	cip->subcore_threads[0] = vc->num_threads;
+	cip->subcore_vm[0] = vc->kvm;
+	for (sub = 0; sub < MAX_SUBCORES; ++sub)
+		INIT_LIST_HEAD(&cip->vcs[sub]);
+	list_add_tail(&vc->preempt_list, &cip->vcs[0]);
+}
+
+static bool subcore_config_ok(int n_subcores, int n_threads)
+{
+	/* Can only dynamically split if unsplit to begin with */
+	if (n_subcores > 1 && threads_per_subcore < MAX_SMT_THREADS)
+		return false;
+	if (n_subcores > MAX_SUBCORES)
+		return false;
+	if (n_subcores > 1) {
+		if (!(dynamic_mt_modes & 2))
+			n_subcores = 4;
+		if (n_subcores > 2 && !(dynamic_mt_modes & 4))
+			return false;
+	}
+
+	return n_subcores * roundup_pow_of_two(n_threads) <= MAX_SMT_THREADS;
+}
+
+static void init_master_vcore(struct kvmppc_vcore *vc)
+{
+	vc->master_vcore = vc;
+	vc->entry_exit_map = 0;
+	vc->in_guest = 0;
+	vc->napping_threads = 0;
+	vc->conferring_threads = 0;
+}
+
+/*
+ * See if the existing subcores can be split into 3 (or fewer) subcores
+ * of at most two threads each, so we can fit in another vcore.  This
+ * assumes there are at most two subcores and at most 6 threads in total.
+ */
+static bool can_split_piggybacked_subcores(struct core_info *cip)
+{
+	int sub, new_sub;
+	int large_sub = -1;
+	int thr;
+	int n_subcores = cip->n_subcores;
+	struct kvmppc_vcore *vc, *vcnext;
+	struct kvmppc_vcore *master_vc = NULL;
+
+	for (sub = 0; sub < cip->n_subcores; ++sub) {
+		if (cip->subcore_threads[sub] <= 2)
+			continue;
+		if (large_sub >= 0)
+			return false;
+		large_sub = sub;
+		vc = list_first_entry(&cip->vcs[sub], struct kvmppc_vcore,
+				      preempt_list);
+		if (vc->num_threads > 2)
+			return false;
+		n_subcores += (cip->subcore_threads[sub] - 1) >> 1;
+	}
+	if (n_subcores > 3 || large_sub < 0)
+		return false;
+
+	/*
+	 * Seems feasible, so go through and move vcores to new subcores.
+	 * Note that when we have two or more vcores in one subcore,
+	 * all those vcores must have only one thread each.
+	 */
+	new_sub = cip->n_subcores;
+	thr = 0;
+	sub = large_sub;
+	list_for_each_entry_safe(vc, vcnext, &cip->vcs[sub], preempt_list) {
+		if (thr >= 2) {
+			list_del(&vc->preempt_list);
+			list_add_tail(&vc->preempt_list, &cip->vcs[new_sub]);
+			/* vc->num_threads must be 1 */
+			if (++cip->subcore_threads[new_sub] == 1) {
+				cip->subcore_vm[new_sub] = vc->kvm;
+				init_master_vcore(vc);
+				master_vc = vc;
+				++cip->n_subcores;
+			} else {
+				vc->master_vcore = master_vc;
+				++new_sub;
+			}
+		}
+		thr += vc->num_threads;
+	}
+	cip->subcore_threads[large_sub] = 2;
+	cip->max_subcore_threads = 2;
+
+	return true;
+}
+
+static bool can_dynamic_split(struct kvmppc_vcore *vc, struct core_info *cip)
+{
+	int n_threads = vc->num_threads;
+	int sub;
+
+	if (!cpu_has_feature(CPU_FTR_ARCH_207S))
+		return false;
+
+	if (n_threads < cip->max_subcore_threads)
+		n_threads = cip->max_subcore_threads;
+	if (subcore_config_ok(cip->n_subcores + 1, n_threads)) {
+		cip->max_subcore_threads = n_threads;
+	} else if (cip->n_subcores <= 2 && cip->total_threads <= 6 &&
+		   vc->num_threads <= 2) {
+		/*
+		 * We may be able to fit another subcore in by
+		 * splitting an existing subcore with 3 or 4
+		 * threads into two 2-thread subcores, or one
+		 * with 5 or 6 threads into three subcores.
+		 * We can only do this if those subcores have
+		 * piggybacked virtual cores.
+		 */
+		if (!can_split_piggybacked_subcores(cip))
+			return false;
+	} else {
+		return false;
+	}
+
+	sub = cip->n_subcores;
+	++cip->n_subcores;
+	cip->total_threads += vc->num_threads;
+	cip->subcore_threads[sub] = vc->num_threads;
+	cip->subcore_vm[sub] = vc->kvm;
+	init_master_vcore(vc);
+	list_del(&vc->preempt_list);
+	list_add_tail(&vc->preempt_list, &cip->vcs[sub]);
+
+	return true;
+}
+
+static bool can_piggyback_subcore(struct kvmppc_vcore *pvc,
+				  struct core_info *cip, int sub)
+{
+	struct kvmppc_vcore *vc;
+	int n_thr;
+
+	vc = list_first_entry(&cip->vcs[sub], struct kvmppc_vcore,
+			      preempt_list);
+
+	/* require same VM and same per-core reg values */
+	if (pvc->kvm != vc->kvm ||
+	    pvc->tb_offset != vc->tb_offset ||
+	    pvc->pcr != vc->pcr ||
+	    pvc->lpcr != vc->lpcr)
+		return false;
+
+	/* P8 guest with > 1 thread per core would see wrong TIR value */
+	if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
+	    (vc->num_threads > 1 || pvc->num_threads > 1))
+		return false;
+
+	n_thr = cip->subcore_threads[sub] + pvc->num_threads;
+	if (n_thr > cip->max_subcore_threads) {
+		if (!subcore_config_ok(cip->n_subcores, n_thr))
+			return false;
+		cip->max_subcore_threads = n_thr;
+	}
+
+	cip->total_threads += pvc->num_threads;
+	cip->subcore_threads[sub] = n_thr;
+	pvc->master_vcore = vc;
+	list_del(&pvc->preempt_list);
+	list_add_tail(&pvc->preempt_list, &cip->vcs[sub]);
+
+	return true;
+}
+
+/*
+ * Work out whether it is possible to piggyback the execution of
+ * vcore *pvc onto the execution of the other vcores described in *cip.
+ */
+static bool can_piggyback(struct kvmppc_vcore *pvc, struct core_info *cip,
+			  int target_threads)
+{
+	int sub;
+
+	if (cip->total_threads + pvc->num_threads > target_threads)
+		return false;
+	for (sub = 0; sub < cip->n_subcores; ++sub)
+		if (cip->subcore_threads[sub] &&
+		    can_piggyback_subcore(pvc, cip, sub))
+			return true;
+
+	if (can_dynamic_split(pvc, cip))
+		return true;
+
+	return false;
+}
+
 static void prepare_threads(struct kvmppc_vcore *vc)
 {
 	struct kvm_vcpu *vcpu, *vnext;
@@ -1909,12 +2212,45 @@ static void prepare_threads(struct kvmppc_vcore *vc)
 	}
 }
 
-static void post_guest_process(struct kvmppc_vcore *vc)
+static void collect_piggybacks(struct core_info *cip, int target_threads)
+{
+	struct preempted_vcore_list *lp = this_cpu_ptr(&preempted_vcores);
+	struct kvmppc_vcore *pvc, *vcnext;
+
+	spin_lock(&lp->lock);
+	list_for_each_entry_safe(pvc, vcnext, &lp->list, preempt_list) {
+		if (!spin_trylock(&pvc->lock))
+			continue;
+		prepare_threads(pvc);
+		if (!pvc->n_runnable) {
+			list_del_init(&pvc->preempt_list);
+			if (pvc->runner == NULL) {
+				pvc->vcore_state = VCORE_INACTIVE;
+				kvmppc_core_end_stolen(pvc);
+			}
+			spin_unlock(&pvc->lock);
+			continue;
+		}
+		if (!can_piggyback(pvc, cip, target_threads)) {
+			spin_unlock(&pvc->lock);
+			continue;
+		}
+		kvmppc_core_end_stolen(pvc);
+		pvc->vcore_state = VCORE_PIGGYBACK;
+		if (cip->total_threads >= target_threads)
+			break;
+	}
+	spin_unlock(&lp->lock);
+}
+
+static void post_guest_process(struct kvmppc_vcore *vc, bool is_master)
 {
+	int still_running = 0;
 	u64 now;
 	long ret;
 	struct kvm_vcpu *vcpu, *vnext;
 
+	spin_lock(&vc->lock);
 	now = get_tb();
 	list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
 				 arch.run_list) {
@@ -1933,17 +2269,36 @@ static void post_guest_process(struct kvmppc_vcore *vc)
 		vcpu->arch.ret = ret;
 		vcpu->arch.trap = 0;
 
-		if (vcpu->arch.ceded) {
-			if (!is_kvmppc_resume_guest(ret))
-				kvmppc_end_cede(vcpu);
-			else
+		if (is_kvmppc_resume_guest(vcpu->arch.ret)) {
+			if (vcpu->arch.pending_exceptions)
+				kvmppc_core_prepare_to_enter(vcpu);
+			if (vcpu->arch.ceded)
 				kvmppc_set_timer(vcpu);
-		}
-		if (!is_kvmppc_resume_guest(vcpu->arch.ret)) {
+			else
+				++still_running;
+		} else {
 			kvmppc_remove_runnable(vc, vcpu);
 			wake_up(&vcpu->arch.cpu_run);
 		}
 	}
+	list_del_init(&vc->preempt_list);
+	if (!is_master) {
+		if (still_running > 0) {
+			kvmppc_vcore_preempt(vc);
+		} else if (vc->runner) {
+			vc->vcore_state = VCORE_PREEMPT;
+			kvmppc_core_start_stolen(vc);
+		} else {
+			vc->vcore_state = VCORE_INACTIVE;
+		}
+		if (vc->n_runnable > 0 && vc->runner == NULL) {
+			/* make sure there's a candidate runner awake */
+			vcpu = list_first_entry(&vc->runnable_threads,
+						struct kvm_vcpu, arch.run_list);
+			wake_up(&vcpu->arch.cpu_run);
+		}
+	}
+	spin_unlock(&vc->lock);
 }
 
 /*
@@ -1955,6 +2310,15 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	struct kvm_vcpu *vcpu, *vnext;
 	int i;
 	int srcu_idx;
+	struct core_info core_info;
+	struct kvmppc_vcore *pvc, *vcnext;
+	struct kvm_split_mode split_info, *sip;
+	int split, subcore_size, active;
+	int sub;
+	bool thr0_done;
+	unsigned long cmd_bit, stat_bit;
+	int pcpu, thr;
+	int target_threads;
 
 	/*
 	 * Remove from the list any threads that have a signal pending
@@ -1969,11 +2333,8 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	/*
 	 * Initialize *vc.
 	 */
-	vc->entry_exit_map = 0;
+	init_master_vcore(vc);
 	vc->preempt_tb = TB_NIL;
-	vc->in_guest = 0;
-	vc->napping_threads = 0;
-	vc->conferring_threads = 0;
 
 	/*
 	 * Make sure we are running on primary threads, and that secondary
@@ -1991,24 +2352,120 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 		goto out;
 	}
 
+	/*
+	 * See if we could run any other vcores on the physical core
+	 * along with this one.
+	 */
+	init_core_info(&core_info, vc);
+	pcpu = smp_processor_id();
+	target_threads = threads_per_subcore;
+	if (target_smt_mode && target_smt_mode < target_threads)
+		target_threads = target_smt_mode;
+	if (vc->num_threads < target_threads)
+		collect_piggybacks(&core_info, target_threads);
+
+	/* Decide on micro-threading (split-core) mode */
+	subcore_size = threads_per_subcore;
+	cmd_bit = stat_bit = 0;
+	split = core_info.n_subcores;
+	sip = NULL;
+	if (split > 1) {
+		/* threads_per_subcore must be MAX_SMT_THREADS (8) here */
+		if (split == 2 && (dynamic_mt_modes & 2)) {
+			cmd_bit = HID0_POWER8_1TO2LPAR;
+			stat_bit = HID0_POWER8_2LPARMODE;
+		} else {
+			split = 4;
+			cmd_bit = HID0_POWER8_1TO4LPAR;
+			stat_bit = HID0_POWER8_4LPARMODE;
+		}
+		subcore_size = MAX_SMT_THREADS / split;
+		sip = &split_info;
+		memset(&split_info, 0, sizeof(split_info));
+		split_info.rpr = mfspr(SPRN_RPR);
+		split_info.pmmar = mfspr(SPRN_PMMAR);
+		split_info.ldbar = mfspr(SPRN_LDBAR);
+		split_info.subcore_size = subcore_size;
+		for (sub = 0; sub < core_info.n_subcores; ++sub)
+			split_info.master_vcs[sub] =
+				list_first_entry(&core_info.vcs[sub],
+					struct kvmppc_vcore, preempt_list);
+		/* order writes to split_info before kvm_split_mode pointer */
+		smp_wmb();
+	}
+	pcpu = smp_processor_id();
+	for (thr = 0; thr < threads_per_subcore; ++thr)
+		paca[pcpu + thr].kvm_hstate.kvm_split_mode = sip;
+
+	/* Initiate micro-threading (split-core) if required */
+	if (cmd_bit) {
+		unsigned long hid0 = mfspr(SPRN_HID0);
+
+		hid0 |= cmd_bit | HID0_POWER8_DYNLPARDIS;
+		mb();
+		mtspr(SPRN_HID0, hid0);
+		isync();
+		for (;;) {
+			hid0 = mfspr(SPRN_HID0);
+			if (hid0 & stat_bit)
+				break;
+			cpu_relax();
+		}
+	}
 
-	vc->pcpu = smp_processor_id();
-	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
-		kvmppc_start_thread(vcpu);
-		kvmppc_create_dtl_entry(vcpu, vc);
-		trace_kvm_guest_enter(vcpu);
+	/* Start all the threads */
+	active = 0;
+	for (sub = 0; sub < core_info.n_subcores; ++sub) {
+		thr = subcore_thread_map[sub];
+		thr0_done = false;
+		active |= 1 << thr;
+		list_for_each_entry(pvc, &core_info.vcs[sub], preempt_list) {
+			pvc->pcpu = pcpu + thr;
+			list_for_each_entry(vcpu, &pvc->runnable_threads,
+					    arch.run_list) {
+				kvmppc_start_thread(vcpu, pvc);
+				kvmppc_create_dtl_entry(vcpu, pvc);
+				trace_kvm_guest_enter(vcpu);
+				if (!vcpu->arch.ptid)
+					thr0_done = true;
+				active |= 1 << (thr + vcpu->arch.ptid);
+			}
+			/*
+			 * We need to start the first thread of each subcore
+			 * even if it doesn't have a vcpu.
+			 */
+			if (pvc->master_vcore == pvc && !thr0_done)
+				kvmppc_start_thread(NULL, pvc);
+			thr += pvc->num_threads;
+		}
 	}
 
-	/* Set this explicitly in case thread 0 doesn't have a vcpu */
-	get_paca()->kvm_hstate.kvm_vcore = vc;
-	get_paca()->kvm_hstate.ptid = 0;
+	/*
+	 * Ensure that split_info.do_nap is set after setting
+	 * the vcore pointer in the PACA of the secondaries.
+	 */
+	smp_mb();
+	if (cmd_bit)
+		split_info.do_nap = 1;	/* ask secondaries to nap when done */
+
+	/*
+	 * When doing micro-threading, poke the inactive threads as well.
+	 * This gets them to the nap instruction after kvm_do_nap,
+	 * which reduces the time taken to unsplit later.
+	 */
+	if (split > 1)
+		for (thr = 1; thr < threads_per_subcore; ++thr)
+			if (!(active & (1 << thr)))
+				kvmppc_ipi_thread(pcpu + thr);
 
 	vc->vcore_state = VCORE_RUNNING;
 	preempt_disable();
 
 	trace_kvmppc_run_core(vc, 0);
 
-	spin_unlock(&vc->lock);
+	for (sub = 0; sub < core_info.n_subcores; ++sub)
+		list_for_each_entry(pvc, &core_info.vcs[sub], preempt_list)
+			spin_unlock(&pvc->lock);
 
 	kvm_guest_enter();
 
@@ -2019,32 +2476,58 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 
 	__kvmppc_vcore_entry();
 
-	spin_lock(&vc->lock);
-
 	if (vc->mpp_buffer)
 		kvmppc_start_saving_l2_cache(vc);
 
-	/* disable sending of IPIs on virtual external irqs */
-	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
-		vcpu->cpu = -1;
-	/* wait for secondary threads to finish writing their state to memory */
-	kvmppc_wait_for_nap();
-	for (i = 0; i < threads_per_subcore; ++i)
-		kvmppc_release_hwthread(vc->pcpu + i);
+	srcu_read_unlock(&vc->kvm->srcu, srcu_idx);
+
+	spin_lock(&vc->lock);
 	/* prevent other vcpu threads from doing kvmppc_start_thread() now */
 	vc->vcore_state = VCORE_EXITING;
-	spin_unlock(&vc->lock);
 
-	srcu_read_unlock(&vc->kvm->srcu, srcu_idx);
+	/* wait for secondary threads to finish writing their state to memory */
+	kvmppc_wait_for_nap();
+
+	/* Return to whole-core mode if we split the core earlier */
+	if (split > 1) {
+		unsigned long hid0 = mfspr(SPRN_HID0);
+		unsigned lo