KVM: PPC: Book3S HV: Implement dynamic micro-threading on POWER8

This builds on the ability to run more than one vcore on a physical
core by using the micro-threading (split-core) modes of the POWER8
chip.  Previously, only vcores from the same VM could be run together,
and (on POWER8) only if they had just one thread per core.  With the
ability to split the core on guest entry and unsplit it on guest exit,
we can run up to 8 vcpu threads from up to 4 different VMs, and we can
run multiple vcores with 2 or 4 vcpus per vcore.

Dynamic micro-threading is only available if the static configuration
of the cores is whole-core mode (unsplit), and only on POWER8.

To manage this, we introduce a new kvm_split_mode struct which is
shared across all of the subcores in the core, with a pointer in the
paca on each thread.  In addition we extend the core_info struct to
have information on each subcore.  When deciding whether to add a
vcore to the set already on the core, we now have two possibilities:
(a) piggyback the vcore onto an existing subcore, or (b) start a new
subcore.

Currently, when any vcpu needs to exit the guest and switch to host
virtual mode, we interrupt all the threads in all subcores and switch
the core back to whole-core mode.  It may be possible in future to
allow some of the subcores to keep executing in the guest while
subcore 0 switches to the host, but that is not implemented in this
patch.

This adds a module parameter called dynamic_mt_modes which controls
which micro-threading (split-core) modes the code will consider, as a
bitmap.  In other words, if it is 0, no micro-threading mode is
considered; if it is 2, only 2-way micro-threading is considered; if
it is 4, only 4-way, and if it is 6, both 2-way and 4-way
micro-threading mode will be considered.  The default is 6.

With this, we now have secondary threads which are the primary thread
for their subcore and therefore need to do the MMU switch.  These
threads will need to be started even if they have no vcpu to run, so
we use the vcore pointer in the PACA rather than the vcpu pointer to
trigger them.

It is now possible for thread 0 to find that an exit has been
requested before it gets to switch the subcore state to the guest.  In
that case we haven't added the guest's timebase offset to the
timebase, so we need to be careful not to subtract the offset in the
guest exit path.  In fact we just skip the whole path that switches
back to host context, since we haven't switched to the guest context.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

6 files changed, 473 insertions, 62 deletions

diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index 5bdfb5dd3400..57d5dfef48bd 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -25,6 +25,12 @@
 #define XICS_MFRR		0xc
 #define XICS_IPI		2	/* interrupt source # for IPIs */
 
+/* Maximum number of threads per physical core */
+#define MAX_SMT_THREADS		8
+
+/* Maximum number of subcores per physical core */
+#define MAX_SUBCORES		4
+
 #ifdef __ASSEMBLY__
 
 #ifdef CONFIG_KVM_BOOK3S_HANDLER
@@ -65,6 +71,19 @@ kvmppc_resume_\intno:
 
 #else  /*__ASSEMBLY__ */
 
+struct kvmppc_vcore;
+
+/* Struct used for coordinating micro-threading (split-core) mode changes */
+struct kvm_split_mode {
+	unsigned long	rpr;
+	unsigned long	pmmar;
+	unsigned long	ldbar;
+	u8		subcore_size;
+	u8		do_nap;
+	u8		napped[MAX_SMT_THREADS];
+	struct kvmppc_vcore *master_vcs[MAX_SUBCORES];
+};
+
 /*
  * This struct goes in the PACA on 64-bit processors.  It is used
  * to store host state that needs to be saved when we enter a guest
@@ -100,6 +119,7 @@ struct kvmppc_host_state {
 	u64 host_spurr;
 	u64 host_dscr;
 	u64 dec_expires;
+	struct kvm_split_mode *kvm_split_mode;
 #endif
 #ifdef CONFIG_PPC_BOOK3S_64
 	u64 cfar;
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 2b7449017ae8..80eb29ab262a 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -302,6 +302,9 @@ struct kvmppc_vcore {
 #define VCORE_EXIT_MAP(vc)	((vc)->entry_exit_map >> 8)
 #define VCORE_IS_EXITING(vc)	(VCORE_EXIT_MAP(vc) != 0)
 
+/* This bit is used when a vcore exit is triggered from outside the vcore */
+#define VCORE_EXIT_REQ		0x10000
+
 /*
  * Values for vcore_state.
  * Note that these are arranged such that lower values
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index a78cdbf9b622..de62392f093c 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -676,7 +676,14 @@ int main(void)
 	HSTATE_FIELD(HSTATE_DSCR, host_dscr);
 	HSTATE_FIELD(HSTATE_DABR, dabr);
 	HSTATE_FIELD(HSTATE_DECEXP, dec_expires);
+	HSTATE_FIELD(HSTATE_SPLIT_MODE, kvm_split_mode);
 	DEFINE(IPI_PRIORITY, IPI_PRIORITY);
+	DEFINE(KVM_SPLIT_RPR, offsetof(struct kvm_split_mode, rpr));
+	DEFINE(KVM_SPLIT_PMMAR, offsetof(struct kvm_split_mode, pmmar));
+	DEFINE(KVM_SPLIT_LDBAR, offsetof(struct kvm_split_mode, ldbar));
+	DEFINE(KVM_SPLIT_SIZE, offsetof(struct kvm_split_mode, subcore_size));
+	DEFINE(KVM_SPLIT_DO_NAP, offsetof(struct kvm_split_mode, do_nap));
+	DEFINE(KVM_SPLIT_NAPPED, offsetof(struct kvm_split_mode, napped));
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 
 #ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 0173ce221111..6e3ef308b4c5 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -81,6 +81,9 @@ 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)");
@@ -1770,6 +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;
@@ -1801,28 +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 = mvc;
+	tpaca->kvm_hstate.kvm_vcpu = vcpu;
 	tpaca->kvm_hstate.ptid = cpu - mvc->pcpu;
-	vcpu->cpu = mvc->pcpu;
-	vcpu->arch.thread_cpu = cpu;
 	/* Order stores to hstate.kvm_vcpu etc. before store to kvm_vcore */
 	smp_wmb();
-	tpaca->kvm_hstate.kvm_vcpu = vcpu;
+	tpaca->kvm_hstate.kvm_vcore = mvc;
 	if (cpu != smp_processor_id())
 		kvmppc_ipi_thread(cpu);
 }
@@ -1835,12 +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();
@@ -1850,7 +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);
 }
 
@@ -1965,17 +1973,55 @@ static void kvmppc_vcore_end_preempt(struct kvmppc_vcore *vc)
 	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;
-	struct list_head vcs;
+	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;
-	INIT_LIST_HEAD(&cip->vcs);
-	list_add_tail(&vc->preempt_list, &cip->vcs);
+	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)
@@ -1988,15 +2034,113 @@ static void init_master_vcore(struct kvmppc_vcore *vc)
 }
 
 /*
- * Work out whether it is possible to piggyback the execute of
- * vcore *pvc onto the execution of the other vcores described in *cip.
+ * 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_piggyback(struct kvmppc_vcore *pvc, struct core_info *cip,
-			  int target_threads)
+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, struct kvmppc_vcore, preempt_list);
+	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 ||
@@ -2010,17 +2154,44 @@ static bool can_piggyback(struct kvmppc_vcore *pvc, struct core_info *cip,
 	    (vc->num_threads > 1 || pvc->num_threads > 1))
 		return false;
 
-	if (cip->total_threads + pvc->num_threads > target_threads)
-		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);
+	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;
@@ -2135,6 +2306,11 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	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;
 
@@ -2182,29 +2358,100 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	if (vc->num_threads < target_threads)
 		collect_piggybacks(&core_info, target_threads);
 
-	thr = 0;
-	list_for_each_entry(pvc, &core_info.vcs, preempt_list) {
-		pvc->pcpu = pcpu + thr;
-		list_for_each_entry(vcpu, &pvc->runnable_threads,
-				    arch.run_list) {
-			kvmppc_start_thread(vcpu);
-			kvmppc_create_dtl_entry(vcpu, pvc);
-			trace_kvm_guest_enter(vcpu);
+	/* 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;
 		}
-		thr += pvc->num_threads;
+		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();
 	}
-
-	/* 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;
+	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();
+		}
+		split_info.do_nap = 1;	/* ask secondaries to nap when done */
+	}
+
+	/* 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;
+		}
+	}
+	/*
+	 * 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);
 
-	list_for_each_entry(pvc, &core_info.vcs, preempt_list)
-		spin_unlock(&pvc->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();
 
@@ -2226,16 +2473,44 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 
 	/* 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);
+
+	/* Return to whole-core mode if we split the core earlier */
+	if (split > 1) {
+		unsigned long hid0 = mfspr(SPRN_HID0);
+		unsigned long loops = 0;
+
+		hid0 &= ~HID0_POWER8_DYNLPARDIS;
+		stat_bit = HID0_POWER8_2LPARMODE | HID0_POWER8_4LPARMODE;
+		mb();
+		mtspr(SPRN_HID0, hid0);
+		isync();
+		for (;;) {
+			hid0 = mfspr(SPRN_HID0);
+			if (!(hid0 & stat_bit))
+				break;
+			cpu_relax();
+			++loops;
+		}
+		split_info.do_nap = 0;
+	}
+
+	/* Let secondaries go back to the offline loop */
+	for (i = 0; i < threads_per_subcore; ++i) {
+		kvmppc_release_hwthread(pcpu + i);
+		if (sip && sip->napped[i])
+			kvmppc_ipi_thread(pcpu + i);
+	}
+
 	spin_unlock(&vc->lock);
 
 	/* make sure updates to secondary vcpu structs are visible now */
 	smp_mb();
 	kvm_guest_exit();
 
-	list_for_each_entry_safe(pvc, vcnext, &core_info.vcs, preempt_list)
-		post_guest_process(pvc, pvc == vc);
+	for (sub = 0; sub < core_info.n_subcores; ++sub)
+		list_for_each_entry_safe(pvc, vcnext, &core_info.vcs[sub],
+					 preempt_list)
+			post_guest_process(pvc, pvc == vc);
 
 	spin_lock(&vc->lock);
 	preempt_enable();
@@ -2341,7 +2616,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 				if (mvc->vcore_state == VCORE_RUNNING &&
 				    !VCORE_IS_EXITING(mvc)) {
 					kvmppc_create_dtl_entry(vcpu, vc);
-					kvmppc_start_thread(vcpu);
+					kvmppc_start_thread(vcpu, vc);
 					trace_kvm_guest_enter(vcpu);
 				}
 				spin_unlock(&mvc->lock);
@@ -2349,7 +2624,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 		} else if (vc->vcore_state == VCORE_RUNNING &&
 			   !VCORE_IS_EXITING(vc)) {
 			kvmppc_create_dtl_entry(vcpu, vc);
-			kvmppc_start_thread(vcpu);
+			kvmppc_start_thread(vcpu, vc);
 			trace_kvm_guest_enter(vcpu);
 		} else if (vc->vcore_state == VCORE_SLEEPING) {
 			wake_up(&vc->wq);
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 1fd0e3057396..fd7006bf6b1a 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -239,7 +239,8 @@ void kvmhv_commence_exit(int trap)
 {
 	struct kvmppc_vcore *vc = local_paca->kvm_hstate.kvm_vcore;
 	int ptid = local_paca->kvm_hstate.ptid;
-	int me, ee;
+	struct kvm_split_mode *sip = local_paca->kvm_hstate.kvm_split_mode;
+	int me, ee, i;
 
 	/* Set our bit in the threads-exiting-guest map in the 0xff00
 	   bits of vcore->entry_exit_map */
@@ -259,4 +260,26 @@ void kvmhv_commence_exit(int trap)
 	 */
 	if (trap != BOOK3S_INTERRUPT_HV_DECREMENTER)
 		kvmhv_interrupt_vcore(vc, ee & ~(1 << ptid));
+
+	/*
+	 * If we are doing dynamic micro-threading, interrupt the other
+	 * subcores to pull them out of their guests too.
+	 */
+	if (!sip)
+		return;
+
+	for (i = 0; i < MAX_SUBCORES; ++i) {
+		vc = sip->master_vcs[i];
+		if (!vc)
+			break;
+		do {
+			ee = vc->entry_exit_map;
+			/* Already asked to exit? */
+			if ((ee >> 8) != 0)
+				break;
+		} while (cmpxchg(&vc->entry_exit_map, ee,
+				 ee | VCORE_EXIT_REQ) != ee);
+		if ((ee >> 8) == 0)
+			kvmhv_interrupt_vcore(vc, ee);
+	}
 }
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index ac113b527bf9..db2427db4471 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -128,6 +128,10 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	subf	r4, r4, r3
 	mtspr	SPRN_DEC, r4
 
+	/* hwthread_req may have got set by cede or no vcpu, so clear it */
+	li	r0, 0
+	stb	r0, HSTATE_HWTHREAD_REQ(r13)
+
 	/*
 	 * For external and machine check interrupts, we need
 	 * to call the Linux handler to process the interrupt.
@@ -215,7 +219,6 @@ kvm_novcpu_wakeup:
 	ld	r5, HSTATE_KVM_VCORE(r13)
 	li	r0, 0
 	stb	r0, HSTATE_NAPPING(r13)
-	stb	r0, HSTATE_HWTHREAD_REQ(r13)
 
 	/* check the wake reason */
 	bl	kvmppc_check_wake_reason
@@ -315,10 +318,10 @@ kvm_start_guest:
 	cmpdi	r3, 0
 	bge	kvm_no_guest
 
-	/* get vcpu pointer, NULL if we have no vcpu to run */
-	ld	r4,HSTATE_KVM_VCPU(r13)
-	cmpdi	r4,0
-	/* if we have no vcpu to run, go back to sleep */
+	/* get vcore pointer, NULL if we have nothing to run */
+	ld	r5,HSTATE_KVM_VCORE(r13)
+	cmpdi	r5,0
+	/* if we have no vcore to run, go back to sleep */
 	beq	kvm_no_guest
 
 kvm_secondary_got_guest:
@@ -327,21 +330,42 @@ kvm_secondary_got_guest:
 	ld	r6, PACA_DSCR_DEFAULT(r13)
 	std	r6, HSTATE_DSCR(r13)
 
-	/* Order load of vcore, ptid etc. after load of vcpu */
+	/* On thread 0 of a subcore, set HDEC to max */
+	lbz	r4, HSTATE_PTID(r13)
+	cmpwi	r4, 0
+	bne	63f
+	lis	r6, 0x7fff
+	ori	r6, r6, 0xffff
+	mtspr	SPRN_HDEC, r6
+	/* and set per-LPAR registers, if doing dynamic micro-threading */
+	ld	r6, HSTATE_SPLIT_MODE(r13)
+	cmpdi	r6, 0
+	beq	63f
+	ld	r0, KVM_SPLIT_RPR(r6)
+	mtspr	SPRN_RPR, r0
+	ld	r0, KVM_SPLIT_PMMAR(r6)
+	mtspr	SPRN_PMMAR, r0
+	ld	r0, KVM_SPLIT_LDBAR(r6)
+	mtspr	SPRN_LDBAR, r0
+	isync
+63:
+	/* Order load of vcpu after load of vcore */
 	lwsync
+	ld	r4, HSTATE_KVM_VCPU(r13)
 	bl	kvmppc_hv_entry
 
 	/* Back from the guest, go back to nap */
-	/* Clear our vcpu pointer so we don't come back in early */
+	/* Clear our vcpu and vcore pointers so we don't come back in early */
 	li	r0, 0
+	std	r0, HSTATE_KVM_VCPU(r13)
 	/*
-	 * Once we clear HSTATE_KVM_VCPU(r13), the code in
+	 * Once we clear HSTATE_KVM_VCORE(r13), the code in
 	 * kvmppc_run_core() is going to assume that all our vcpu
 	 * state is visible in memory.  This lwsync makes sure
 	 * that that is true.
 	 */
 	lwsync
-	std	r0, HSTATE_KVM_VCPU(r13)
+	std	r0, HSTATE_KVM_VCORE(r13)
 
 /*
  * At this point we have finished executing in the guest.
@@ -374,16 +398,63 @@ kvm_no_guest:
 	b	power7_wakeup_loss
 
 53:	HMT_LOW
-	ld	r4, HSTATE_KVM_VCPU(r13)
-	cmpdi	r4, 0
+	ld	r5, HSTATE_KVM_VCORE(r13)
+	cmpdi	r5, 0
+	bne	60f
+	ld	r3, HSTATE_SPLIT_MODE(r13)
+	cmpdi	r3, 0
+	beq	kvm_no_guest
+	lbz	r0, KVM_SPLIT_DO_NAP(r3)
+	cmpwi	r0, 0
 	beq	kvm_no_guest
 	HMT_MEDIUM
+	b	kvm_unsplit_nap
+60:	HMT_MEDIUM
 	b	kvm_secondary_got_guest
 
 54:	li	r0, KVM_HWTHREAD_IN_KVM
 	stb	r0, HSTATE_HWTHREAD_STATE(r13)
 	b	kvm_no_guest
 
+/*
+ * Here the primary thread is trying to return the core to
+ * whole-core mode, so we need to nap.
+ */
+kvm_unsplit_nap:
+	/* clear any pending message */
+BEGIN_FTR_SECTION
+	lis	r6, (PPC_DBELL_SERVER << (63-36))@h
+	PPC_MSGCLR(6)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+	/* Set kvm_split_mode.napped[tid] = 1 */
+	ld	r3, HSTATE_SPLIT_MODE(r13)
+	li	r0, 1
+	lhz	r4, PACAPACAINDEX(r13)
+	clrldi	r4, r4, 61	/* micro-threading => P8 => 8 threads/core */
+	addi	r4, r4, KVM_SPLIT_NAPPED
+	stbx	r0, r3, r4
+	/* Check the do_nap flag again after setting napped[] */
+	sync
+	lbz	r0, KVM_SPLIT_DO_NAP(r3)
+	cmpwi	r0, 0
+	beq	57f
+	li	r3, (LPCR_PECEDH | LPCR_PECE0) >> 4
+	mfspr	r4, SPRN_LPCR
+	rlwimi	r4, r3, 4, (LPCR_PECEDP | LPCR_PECEDH | LPCR_PECE0 | LPCR_PECE1)
+	mtspr	SPRN_LPCR, r4
+	isync
+	std	r0, HSTATE_SCRATCH0(r13)
+	ptesync
+	ld	r0, HSTATE_SCRATCH0(r13)
+1:	cmpd	r0, r0
+	bne	1b
+	nap
+	b	.
+
+57:	li	r0, 0
+	stbx	r0, r3, r4
+	b	kvm_no_guest
+
 /******************************************************************************
  *                                                                            *
  *                               Entry code                                   *
@@ -854,7 +925,10 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	cmpwi	r0, 0
 	bne	21f
 	HMT_LOW
-20:	lbz	r0, VCORE_IN_GUEST(r5)
+20:	lwz	r3, VCORE_ENTRY_EXIT(r5)
+	cmpwi	r3, 0x100
+	bge	no_switch_exit
+	lbz	r0, VCORE_IN_GUEST(r5)
 	cmpwi	r0, 0
 	beq	20b
 	HMT_MEDIUM
@@ -985,9 +1059,13 @@ secondary_too_late:
 #endif
 11:	b	kvmhv_switch_to_host
 
+no_switch_exit:
+	HMT_MEDIUM
+	li	r12, 0
+	b	12f
 hdec_soon:
 	li	r12, BOOK3S_INTERRUPT_HV_DECREMENTER
-	stw	r12, VCPU_TRAP(r4)
+12:	stw	r12, VCPU_TRAP(r4)
 	mr	r9, r4
 #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
 	addi	r3, r4, VCPU_TB_RMEXIT
@@ -1545,12 +1623,17 @@ kvmhv_switch_to_host:
 
 	/* Primary thread waits for all the secondaries to exit guest */
 15:	lwz	r3,VCORE_ENTRY_EXIT(r5)
-	srwi	r0,r3,8
+	rlwinm	r0,r3,32-8,0xff
 	clrldi	r3,r3,56
 	cmpw	r3,r0
 	bne	15b
 	isync
 
+	/* Did we actually switch to the guest at all? */
+	lbz	r6, VCORE_IN_GUEST(r5)
+	cmpwi	r6, 0
+	beq	19f
+
 	/* Primary thread switches back to host partition */
 	ld	r6,KVM_HOST_SDR1(r4)
 	lwz	r7,KVM_HOST_LPID(r4)
@@ -1594,7 +1677,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 18:
 	/* Signal secondary CPUs to continue */
 	stb	r0,VCORE_IN_GUEST(r5)
-	lis	r8,0x7fff		/* MAX_INT@h */
+19:	lis	r8,0x7fff		/* MAX_INT@h */
 	mtspr	SPRN_HDEC,r8
 
 16:	ld	r8,KVM_HOST_LPCR(r4)