15 files changed, 429 insertions, 253 deletions

diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index de338d93d11b..6ad21f04a922 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -183,15 +183,15 @@ struct kvm_vcpu_arch {
 };
 
 struct kvm_vm_stat {
-	u32 remote_tlb_flush;
+	ulong remote_tlb_flush;
 };
 
 struct kvm_vcpu_stat {
-	u32 halt_successful_poll;
-	u32 halt_attempted_poll;
-	u32 halt_poll_invalid;
-	u32 halt_wakeup;
-	u32 hvc_exit_stat;
+	u64 halt_successful_poll;
+	u64 halt_attempted_poll;
+	u64 halt_poll_invalid;
+	u64 halt_wakeup;
+	u64 hvc_exit_stat;
 	u64 wfe_exit_stat;
 	u64 wfi_exit_stat;
 	u64 mmio_exit_user;
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 3eda975837d0..bd94e6766759 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -290,15 +290,15 @@ struct kvm_vcpu_arch {
 #endif
 
 struct kvm_vm_stat {
-	u32 remote_tlb_flush;
+	ulong remote_tlb_flush;
 };
 
 struct kvm_vcpu_stat {
-	u32 halt_successful_poll;
-	u32 halt_attempted_poll;
-	u32 halt_poll_invalid;
-	u32 halt_wakeup;
-	u32 hvc_exit_stat;
+	u64 halt_successful_poll;
+	u64 halt_attempted_poll;
+	u64 halt_poll_invalid;
+	u64 halt_wakeup;
+	u64 hvc_exit_stat;
 	u64 wfe_exit_stat;
 	u64 wfi_exit_stat;
 	u64 mmio_exit_user;
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index b54bcadd8aec..5f488dc8a7d5 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -110,32 +110,32 @@
 extern atomic_t kvm_mips_instance;
 
 struct kvm_vm_stat {
-	u32 remote_tlb_flush;
+	ulong remote_tlb_flush;
 };
 
 struct kvm_vcpu_stat {
-	u32 wait_exits;
-	u32 cache_exits;
-	u32 signal_exits;
-	u32 int_exits;
-	u32 cop_unusable_exits;
-	u32 tlbmod_exits;
-	u32 tlbmiss_ld_exits;
-	u32 tlbmiss_st_exits;
-	u32 addrerr_st_exits;
-	u32 addrerr_ld_exits;
-	u32 syscall_exits;
-	u32 resvd_inst_exits;
-	u32 break_inst_exits;
-	u32 trap_inst_exits;
-	u32 msa_fpe_exits;
-	u32 fpe_exits;
-	u32 msa_disabled_exits;
-	u32 flush_dcache_exits;
-	u32 halt_successful_poll;
-	u32 halt_attempted_poll;
-	u32 halt_poll_invalid;
-	u32 halt_wakeup;
+	u64 wait_exits;
+	u64 cache_exits;
+	u64 signal_exits;
+	u64 int_exits;
+	u64 cop_unusable_exits;
+	u64 tlbmod_exits;
+	u64 tlbmiss_ld_exits;
+	u64 tlbmiss_st_exits;
+	u64 addrerr_st_exits;
+	u64 addrerr_ld_exits;
+	u64 syscall_exits;
+	u64 resvd_inst_exits;
+	u64 break_inst_exits;
+	u64 trap_inst_exits;
+	u64 msa_fpe_exits;
+	u64 fpe_exits;
+	u64 msa_disabled_exits;
+	u64 flush_dcache_exits;
+	u64 halt_successful_poll;
+	u64 halt_attempted_poll;
+	u64 halt_poll_invalid;
+	u64 halt_wakeup;
 };
 
 struct kvm_arch_memory_slot {
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 8f39796c9da8..c261f52f6a55 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -69,6 +69,42 @@ struct hpte_cache {
 	int pagesize;
 };
 
+/*
+ * Struct for a virtual core.
+ * Note: entry_exit_map combines a bitmap of threads that have entered
+ * in the bottom 8 bits and a bitmap of threads that have exited in the
+ * next 8 bits.  This is so that we can atomically set the entry bit
+ * iff the exit map is 0 without taking a lock.
+ */
+struct kvmppc_vcore {
+	int n_runnable;
+	int num_threads;
+	int entry_exit_map;
+	int napping_threads;
+	int first_vcpuid;
+	u16 pcpu;
+	u16 last_cpu;
+	u8 vcore_state;
+	u8 in_guest;
+	struct kvmppc_vcore *master_vcore;
+	struct kvm_vcpu *runnable_threads[MAX_SMT_THREADS];
+	struct list_head preempt_list;
+	spinlock_t lock;
+	struct swait_queue_head wq;
+	spinlock_t stoltb_lock;	/* protects stolen_tb and preempt_tb */
+	u64 stolen_tb;
+	u64 preempt_tb;
+	struct kvm_vcpu *runner;
+	struct kvm *kvm;
+	u64 tb_offset;		/* guest timebase - host timebase */
+	ulong lpcr;
+	u32 arch_compat;
+	ulong pcr;
+	ulong dpdes;		/* doorbell state (POWER8) */
+	ulong conferring_threads;
+	unsigned int halt_poll_ns;
+};
+
 struct kvmppc_vcpu_book3s {
 	struct kvmppc_sid_map sid_map[SID_MAP_NUM];
 	struct {
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index ec35af34a3fb..373003f4551d 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -43,6 +43,8 @@
 #include <asm/cputhreads.h>
 #define KVM_MAX_VCPU_ID                (threads_per_subcore * KVM_MAX_VCORES)
 
+#define __KVM_HAVE_ARCH_INTC_INITIALIZED
+
 #ifdef CONFIG_KVM_MMIO
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #endif
@@ -95,41 +97,45 @@ struct kvmppc_vcpu_book3s;
 struct kvmppc_book3s_shadow_vcpu;
 
 struct kvm_vm_stat {
-	u32 remote_tlb_flush;
+	ulong remote_tlb_flush;
 };
 
 struct kvm_vcpu_stat {
-	u32 sum_exits;
-	u32 mmio_exits;
-	u32 signal_exits;
-	u32 light_exits;
+	u64 sum_exits;
+	u64 mmio_exits;
+	u64 signal_exits;
+	u64 light_exits;
 	/* Account for special types of light exits: */
-	u32 itlb_real_miss_exits;
-	u32 itlb_virt_miss_exits;
-	u32 dtlb_real_miss_exits;
-	u32 dtlb_virt_miss_exits;
-	u32 syscall_exits;
-	u32 isi_exits;
-	u32 dsi_exits;
-	u32 emulated_inst_exits;
-	u32 dec_exits;
-	u32 ext_intr_exits;
-	u32 halt_successful_poll;
-	u32 halt_attempted_poll;
-	u32 halt_poll_invalid;
-	u32 halt_wakeup;
-	u32 dbell_exits;
-	u32 gdbell_exits;
-	u32 ld;
-	u32 st;
+	u64 itlb_real_miss_exits;
+	u64 itlb_virt_miss_exits;
+	u64 dtlb_real_miss_exits;
+	u64 dtlb_virt_miss_exits;
+	u64 syscall_exits;
+	u64 isi_exits;
+	u64 dsi_exits;
+	u64 emulated_inst_exits;
+	u64 dec_exits;
+	u64 ext_intr_exits;
+	u64 halt_poll_success_ns;
+	u64 halt_poll_fail_ns;
+	u64 halt_wait_ns;
+	u64 halt_successful_poll;
+	u64 halt_attempted_poll;
+	u64 halt_successful_wait;
+	u64 halt_poll_invalid;
+	u64 halt_wakeup;
+	u64 dbell_exits;
+	u64 gdbell_exits;
+	u64 ld;
+	u64 st;
 #ifdef CONFIG_PPC_BOOK3S
-	u32 pf_storage;
-	u32 pf_instruc;
-	u32 sp_storage;
-	u32 sp_instruc;
-	u32 queue_intr;
-	u32 ld_slow;
-	u32 st_slow;
+	u64 pf_storage;
+	u64 pf_instruc;
+	u64 sp_storage;
+	u64 sp_instruc;
+	u64 queue_intr;
+	u64 ld_slow;
+	u64 st_slow;
 #endif
 };
 
@@ -275,41 +281,6 @@ struct kvm_arch {
 #endif
 };
 
-/*
- * Struct for a virtual core.
- * Note: entry_exit_map combines a bitmap of threads that have entered
- * in the bottom 8 bits and a bitmap of threads that have exited in the
- * next 8 bits.  This is so that we can atomically set the entry bit
- * iff the exit map is 0 without taking a lock.
- */
-struct kvmppc_vcore {
-	int n_runnable;
-	int num_threads;
-	int entry_exit_map;
-	int napping_threads;
-	int first_vcpuid;
-	u16 pcpu;
-	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;
-	struct swait_queue_head wq;
-	spinlock_t stoltb_lock;	/* protects stolen_tb and preempt_tb */
-	u64 stolen_tb;
-	u64 preempt_tb;
-	struct kvm_vcpu *runner;
-	struct kvm *kvm;
-	u64 tb_offset;		/* guest timebase - host timebase */
-	ulong lpcr;
-	u32 arch_compat;
-	ulong pcr;
-	ulong dpdes;		/* doorbell state (POWER8) */
-	ulong conferring_threads;
-};
-
 #define VCORE_ENTRY_MAP(vc)	((vc)->entry_exit_map & 0xff)
 #define VCORE_EXIT_MAP(vc)	((vc)->entry_exit_map >> 8)
 #define VCORE_IS_EXITING(vc)	(VCORE_EXIT_MAP(vc) != 0)
@@ -329,6 +300,7 @@ struct kvmppc_vcore {
 #define VCORE_SLEEPING	3
 #define VCORE_RUNNING	4
 #define VCORE_EXITING	5
+#define VCORE_POLLING	6
 
 /*
  * Struct used to manage memory for a virtual processor area
@@ -668,7 +640,6 @@ struct kvm_vcpu_arch {
 	long pgfault_index;
 	unsigned long pgfault_hpte[2];
 
-	struct list_head run_list;
 	struct task_struct *run_task;
 	struct kvm_run *kvm_run;
 
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index c2024ac9d4e8..c0a2478a8a2c 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -22,6 +22,7 @@ config KVM
 	select ANON_INODES
 	select HAVE_KVM_EVENTFD
 	select SRCU
+	select KVM_VFIO
 
 config KVM_BOOK3S_HANDLER
 	bool
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 855d4b95d752..7dd89b79d038 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -7,16 +7,16 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
 ccflags-y := -Ivirt/kvm -Iarch/powerpc/kvm
 KVM := ../../../virt/kvm
 
-common-objs-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
-		$(KVM)/eventfd.o
+common-objs-y = $(KVM)/kvm_main.o $(KVM)/eventfd.o
 common-objs-$(CONFIG_KVM_VFIO) += $(KVM)/vfio.o
+common-objs-$(CONFIG_KVM_MMIO) += $(KVM)/coalesced_mmio.o
 
 CFLAGS_e500_mmu.o := -I.
 CFLAGS_e500_mmu_host.o := -I.
 CFLAGS_emulate.o  := -I.
 CFLAGS_emulate_loadstore.o  := -I.
 
-common-objs-y += powerpc.o emulate.o emulate_loadstore.o
+common-objs-y += powerpc.o emulate_loadstore.o
 obj-$(CONFIG_KVM_EXIT_TIMING) += timing.o
 obj-$(CONFIG_KVM_BOOK3S_HANDLER) += book3s_exports.o
 
@@ -24,6 +24,7 @@ AFLAGS_booke_interrupts.o := -I$(objtree)/$(obj)
 
 kvm-e500-objs := \
 	$(common-objs-y) \
+	emulate.o \
 	booke.o \
 	booke_emulate.o \
 	booke_interrupts.o \
@@ -35,6 +36,7 @@ kvm-objs-$(CONFIG_KVM_E500V2) := $(kvm-e500-objs)
 
 kvm-e500mc-objs := \
 	$(common-objs-y) \
+	emulate.o \
 	booke.o \
 	booke_emulate.o \
 	bookehv_interrupts.o \
@@ -61,9 +63,6 @@ kvm-pr-y := \
 	book3s_32_mmu.o
 
 ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
-kvm-book3s_64-module-objs := \
-	$(KVM)/coalesced_mmio.o
-
 kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
 	book3s_rmhandlers.o
 endif
@@ -89,11 +88,8 @@ endif
 kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \
 	book3s_xics.o
 
-kvm-book3s_64-module-objs += \
-	$(KVM)/kvm_main.o \
-	$(KVM)/eventfd.o \
-	powerpc.o \
-	emulate_loadstore.o \
+kvm-book3s_64-module-objs := \
+	$(common-objs-y) \
 	book3s.o \
 	book3s_64_vio.o \
 	book3s_rtas.o \
@@ -103,6 +99,7 @@ kvm-objs-$(CONFIG_KVM_BOOK3S_64) := $(kvm-book3s_64-module-objs)
 
 kvm-book3s_32-objs := \
 	$(common-objs-y) \
+	emulate.o \
 	fpu.o \
 	book3s_paired_singles.o \
 	book3s.o \
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 47018fcbf7d6..71eb8f3d3b54 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -52,8 +52,12 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "dec",         VCPU_STAT(dec_exits) },
 	{ "ext_intr",    VCPU_STAT(ext_intr_exits) },
 	{ "queue_intr",  VCPU_STAT(queue_intr) },
+	{ "halt_poll_success_ns",	VCPU_STAT(halt_poll_success_ns) },
+	{ "halt_poll_fail_ns",		VCPU_STAT(halt_poll_fail_ns) },
+	{ "halt_wait_ns",		VCPU_STAT(halt_wait_ns) },
 	{ "halt_successful_poll", VCPU_STAT(halt_successful_poll), },
 	{ "halt_attempted_poll", VCPU_STAT(halt_attempted_poll), },
+	{ "halt_successful_wait",	VCPU_STAT(halt_successful_wait) },
 	{ "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) },
 	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
 	{ "pf_storage",  VCPU_STAT(pf_storage) },
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 2fd5580c8f6e..30ff8ab5aba1 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -58,6 +58,7 @@
 #include <linux/highmem.h>
 #include <linux/hugetlb.h>
 #include <linux/module.h>
+#include <linux/compiler.h>
 
 #include "book3s.h"
 
@@ -94,9 +95,46 @@ module_param_cb(h_ipi_redirect, &module_param_ops, &h_ipi_redirect,
 MODULE_PARM_DESC(h_ipi_redirect, "Redirect H_IPI wakeup to a free host core");
 #endif
 
+/* Maximum halt poll interval defaults to KVM_HALT_POLL_NS_DEFAULT */
+static unsigned int halt_poll_max_ns = KVM_HALT_POLL_NS_DEFAULT;
+module_param(halt_poll_max_ns, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(halt_poll_max_ns, "Maximum halt poll time in ns");
+
+/* Factor by which the vcore halt poll interval is grown, default is to double
+ */
+static unsigned int halt_poll_ns_grow = 2;
+module_param(halt_poll_ns_grow, int, S_IRUGO);
+MODULE_PARM_DESC(halt_poll_ns_grow, "Factor halt poll time is grown by");
+
+/* Factor by which the vcore halt poll interval is shrunk, default is to reset
+ */
+static unsigned int halt_poll_ns_shrink;
+module_param(halt_poll_ns_shrink, int, S_IRUGO);
+MODULE_PARM_DESC(halt_poll_ns_shrink, "Factor halt poll time is shrunk by");
+
 static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
 
+static inline struct kvm_vcpu *next_runnable_thread(struct kvmppc_vcore *vc,
+		int *ip)
+{
+	int i = *ip;
+	struct kvm_vcpu *vcpu;
+
+	while (++i < MAX_SMT_THREADS) {
+		vcpu = READ_ONCE(vc->runnable_threads[i]);
+		if (vcpu) {
+			*ip = i;
+			return vcpu;
+		}
+	}
+	return NULL;
+}
+
+/* Used to traverse the list of runnable threads for a given vcore */
+#define for_each_runnable_thread(i, vcpu, vc) \
+	for (i = -1; (vcpu = next_runnable_thread(vc, &i)); )
+
 static bool kvmppc_ipi_thread(int cpu)
 {
 	/* On POWER8 for IPIs to threads in the same core, use msgsnd */
@@ -1493,7 +1531,6 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
 	if (vcore == NULL)
 		return NULL;
 
-	INIT_LIST_HEAD(&vcore->runnable_threads);
 	spin_lock_init(&vcore->lock);
 	spin_lock_init(&vcore->stoltb_lock);
 	init_swait_queue_head(&vcore->wq);
@@ -1802,7 +1839,7 @@ static void kvmppc_remove_runnable(struct kvmppc_vcore *vc,
 	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
 	spin_unlock_irq(&vcpu->arch.tbacct_lock);
 	--vc->n_runnable;
-	list_del(&vcpu->arch.run_list);
+	WRITE_ONCE(vc->runnable_threads[vcpu->arch.ptid], NULL);
 }
 
 static int kvmppc_grab_hwthread(int cpu)
@@ -2209,10 +2246,10 @@ static bool can_piggyback(struct kvmppc_vcore *pvc, struct core_info *cip,
 
 static void prepare_threads(struct kvmppc_vcore *vc)
 {
-	struct kvm_vcpu *vcpu, *vnext;
+	int i;
+	struct kvm_vcpu *vcpu;
 
-	list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
-				 arch.run_list) {
+	for_each_runnable_thread(i, vcpu, vc) {
 		if (signal_pending(vcpu->arch.run_task))
 			vcpu->arch.ret = -EINTR;
 		else if (vcpu->arch.vpa.update_pending ||
@@ -2259,15 +2296,14 @@ static void collect_piggybacks(struct core_info *cip, int target_threads)
 
 static void post_guest_process(struct kvmppc_vcore *vc, bool is_master)
 {
-	int still_running = 0;
+	int still_running = 0, i;
 	u64 now;
 	long ret;
-	struct kvm_vcpu *vcpu, *vnext;
+	struct kvm_vcpu *vcpu;
 
 	spin_lock(&vc->lock);
 	now = get_tb();
-	list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
-				 arch.run_list) {
+	for_each_runnable_thread(i, vcpu, vc) {
 		/* cancel pending dec exception if dec is positive */
 		if (now < vcpu->arch.dec_expires &&
 		    kvmppc_core_pending_dec(vcpu))
@@ -2307,8 +2343,8 @@ static void post_guest_process(struct kvmppc_vcore *vc, bool is_master)
 		}
 		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);
+			i = -1;
+			vcpu = next_runnable_thread(vc, &i);
 			wake_up(&vcpu->arch.cpu_run);
 		}
 	}
@@ -2361,7 +2397,7 @@ static inline void kvmppc_set_host_core(int cpu)
  */
 static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 {
-	struct kvm_vcpu *vcpu, *vnext;
+	struct kvm_vcpu *vcpu;
 	int i;
 	int srcu_idx;
 	struct core_info core_info;
@@ -2397,8 +2433,7 @@ static noinline 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_safe(vcpu, vnext, &vc->runnable_threads,
-					 arch.run_list) {
+		for_each_runnable_thread(i, vcpu, vc) {
 			vcpu->arch.ret = -EBUSY;
 			kvmppc_remove_runnable(vc, vcpu);
 			wake_up(&vcpu->arch.cpu_run);
@@ -2477,8 +2512,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 		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) {
+			for_each_runnable_thread(i, vcpu, pvc) {
 				kvmppc_start_thread(vcpu, pvc);
 				kvmppc_create_dtl_entry(vcpu, pvc);
 				trace_kvm_guest_enter(vcpu);
@@ -2604,34 +2638,92 @@ static void kvmppc_wait_for_exec(struct kvmppc_vcore *vc,
 	finish_wait(&vcpu->arch.cpu_run, &wait);
 }
 
+static void grow_halt_poll_ns(struct kvmppc_vcore *vc)
+{
+	/* 10us base */
+	if (vc->halt_poll_ns == 0 && halt_poll_ns_grow)
+		vc->halt_poll_ns = 10000;
+	else
+		vc->halt_poll_ns *= halt_poll_ns_grow;
+
+	if (vc->halt_poll_ns > halt_poll_max_ns)
+		vc->halt_poll_ns = halt_poll_max_ns;
+}
+
+static void shrink_halt_poll_ns(struct kvmppc_vcore *vc)
+{
+	if (halt_poll_ns_shrink == 0)
+		vc->halt_poll_ns = 0;
+	else
+		vc->halt_poll_ns /= halt_poll_ns_shrink;
+}
+
+/* Check to see if any of the runnable vcpus on the vcore have pending
+ * exceptions or are no longer ceded
+ */
+static int kvmppc_vcore_check_block(struct kvmppc_vcore *vc)
+{
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	for_each_runnable_thread(i, vcpu, vc) {
+		if (vcpu->arch.pending_exceptions || !vcpu->arch.ceded)
+			return 1;
+	}
+
+	return 0;
+}
+
 /*
  * All the vcpus in this vcore are idle, so wait for a decrementer
  * or external interrupt to one of the vcpus.  vc->lock is held.
  */
 static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 {
-	struct kvm_vcpu *vcpu;
+	ktime_t cur, start_poll, start_wait;
 	int do_sleep = 1;
+	u64 block_ns;
 	DECLARE_SWAITQUEUE(wait);
 
-	prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
+	/* Poll for pending exceptions and ceded state */
+	cur = start_poll = ktime_get();
+	if (vc->halt_poll_ns) {
+		ktime_t stop = ktime_add_ns(start_poll, vc->halt_poll_ns);
+		++vc->runner->stat.halt_attempted_poll;
 
-	/*
-	 * Check one last time for pending exceptions and ceded state after
-	 * we put ourselves on the wait queue
-	 */
-	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
-		if (vcpu->arch.pending_exceptions || !vcpu->arch.ceded) {
-			do_sleep = 0;
-			break;
+		vc->vcore_state = VCORE_POLLING;
+		spin_unlock(&vc->lock);
+
+		do {
+			if (kvmppc_vcore_check_block(vc)) {
+				do_sleep = 0;
+				break;
+			}
+			cur = ktime_get();
+		} while (single_task_running() && ktime_before(cur, stop));
+
+		spin_lock(&vc->lock);
+		vc->vcore_state = VCORE_INACTIVE;
+
+		if (!do_sleep) {
+			++vc->runner->stat.halt_successful_poll;
+			goto out;
 		}
 	}
 
-	if (!do_sleep) {
+	prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
+
+	if (kvmppc_vcore_check_block(vc)) {
 		finish_swait(&vc->wq, &wait);
-		return;
+		do_sleep = 0;
+		/* If we polled, count this as a successful poll */
+		if (vc->halt_poll_ns)
+			++vc->runner->stat.halt_successful_poll;
+		goto out;
 	}
 
+	start_wait = ktime_get();
+
 	vc->vcore_state = VCORE_SLEEPING;
 	trace_kvmppc_vcore_blocked(vc, 0);
 	spin_unlock(&vc->lock);
@@ -2640,13 +2732,52 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 	spin_lock(&vc->lock);
 	vc->vcore_state = VCORE_INACTIVE;
 	trace_kvmppc_vcore_blocked(vc, 1);
+	++vc->runner->stat.halt_successful_wait;
+
+	cur = ktime_get();
+
+out:
+	block_ns = ktime_to_ns(cur) - ktime_to_ns(start_poll);
+
+	/* Attribute wait time */
+	if (do_sleep) {
+		vc->runner->stat.halt_wait_ns +=
+			ktime_to_ns(cur) - ktime_to_ns(start_wait);
+		/* Attribute failed poll time */
+		if (vc->halt_poll_ns)
+			vc->runner->stat.halt_poll_fail_ns +=
+				ktime_to_ns(start_wait) -
+				ktime_to_ns(start_poll);
+	} else {
+		/* Attribute successful poll time */
+		if (vc->halt_poll_ns)
+			vc->runner->stat.halt_poll_success_ns +=
+				ktime_to_ns(cur) -
+				ktime_to_ns(start_poll);
+	}
+
+	/* Adjust poll time */
+	if (halt_poll_max_ns) {
+		if (block_ns <= vc->halt_poll_ns)
+			;
+		/* We slept and blocked for longer than the max halt time */
+		else if (vc->halt_poll_ns && block_ns > halt_poll_max_ns)
+			shrink_halt_poll_ns(vc);
+		/* We slept and our poll time is too small */
+		else if (vc->halt_poll_ns < halt_poll_max_ns &&
+				block_ns < halt_poll_max_ns)
+			grow_halt_poll_ns(vc);
+	} else
+		vc->halt_poll_ns = 0;
+
+	trace_kvmppc_vcore_wakeup(do_sleep, block_ns);
 }
 
 static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
-	int n_ceded;
+	int n_ceded, i;
 	struct kvmppc_vcore *vc;
-	struct kvm_vcpu *v, *vn;
+	struct kvm_vcpu *v;
 
 	trace_kvmppc_run_vcpu_enter(vcpu);
 
@@ -2666,7 +2797,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	vcpu->arch.stolen_logged = vcore_stolen_time(vc, mftb());
 	vcpu->arch.state = KVMPPC_VCPU_RUNNABLE;
 	vcpu->arch.busy_preempt = TB_NIL;
-	list_add_tail(&vcpu->arch.run_list, &vc->runnable_threads);
+	WRITE_ONCE(vc->runnable_threads[vcpu->arch.ptid], vcpu);
 	++vc->n_runnable;
 
 	/*
@@ -2706,8 +2837,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 			kvmppc_wait_for_exec(vc, vcpu, TASK_INTERRUPTIBLE);
 			continue;
 		}
-		list_for_each_entry_safe(v, vn, &vc->runnable_threads,
-					 arch.run_list) {
+		for_each_runnable_thread(i, v, vc) {
 			kvmppc_core_prepare_to_enter(v);
 			if (signal_pending(v->arch.run_task)) {
 				kvmppc_remove_runnable(vc, v);
@@ -2720,7 +2850,7 @@ 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;
 		n_ceded = 0;
-		list_for_each_entry(v, &vc->runnable_threads, arch.run_list) {
+		for_each_runnable_thread(i, v, vc) {
 			if (!v->arch.pending_exceptions)
 				n_ceded += v->arch.ceded;
 			else
@@ -2759,8 +2889,8 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 
 	if (vc->n_runnable && vc->vcore_state == VCORE_INACTIVE) {
 		/* Wake up some vcpu to run the core */
-		v = list_first_entry(&vc->runnable_threads,
-				     struct kvm_vcpu, arch.run_list);
+		i = -1;
+		v = next_runnable_thread(vc, &i);
 		wake_up(&v->arch.cpu_run);
 	}
 
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index 05aa11399a78..686147efbac5 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -1252,6 +1252,8 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
 {
 	struct kvmppc_xics *xics = kvm->arch.xics;
 
+	if (!xics)
+		return -ENODEV;
 	return ics_deliver_irq(xics, irq, level);
 }
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 6ce40dd6fe51..ab2b3d544937 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -1167,6 +1167,19 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 	return r;
 }
 
+bool kvm_arch_intc_initialized(struct kvm *kvm)
+{
+#ifdef CONFIG_KVM_MPIC
+	if (kvm->arch.mpic)
+		return true;
+#endif
+#ifdef CONFIG_KVM_XICS
+	if (kvm->arch.xics)
+		return true;
+#endif
+	return false;
+}
+
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
                                     struct kvm_mp_state *mp_state)
 {
diff --git a/arch/powerpc/kvm/trace_hv.h b/arch/powerpc/kvm/trace_hv.h
index 33d9daff5783..fb21990c0fb4 100644
--- a/arch/powerpc/kvm/trace_hv.h
+++ b/arch/powerpc/kvm/trace_hv.h
@@ -432,6 +432,28 @@ TRACE_EVENT(kvmppc_vcore_blocked,
 		   __entry->runner_vcpu, __entry->n_runnable, __entry->tgid)
 );
 
+TRACE_EVENT(kvmppc_vcore_wakeup,
+	TP_PROTO(int do_sleep, __u64 ns),
+
+	TP_ARGS(do_sleep, ns),
+
+	TP_STRUCT__entry(
+		__field(__u64,  ns)
+		__field(int,    waited)
+		__field(pid_t,  tgid)
+	),
+
+	TP_fast_assign(
+		__entry->ns     = ns;
+		__entry->waited = do_sleep;
+		__entry->tgid   = current->tgid;
+	),
+
+	TP_printk("%s time %lld ns, tgid=%d",
+		__entry->waited ? "wait" : "poll",
+		__entry->ns, __entry->tgid)
+);
+
 TRACE_EVENT(kvmppc_run_vcpu_enter,
 	TP_PROTO(struct kvm_vcpu *vcpu),
 
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 8e5daf7a76ce..2bbe675c96b9 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -245,72 +245,72 @@ struct sie_page {
 } __packed;
 
 struct kvm_vcpu_stat {
-	u32 exit_userspace;
-	u32 exit_null;
-	u32 exit_external_request;
-	u32 exit_external_interrupt;
-	u32 exit_stop_request;
-	u32 exit_validity;
-	u32 exit_instruction;
-	u32 exit_pei;
-	u32 halt_successful_poll;
-	u32 halt_attempted_poll;
-	u32 halt_poll_invalid;
-	u32 halt_wakeup;
-	u32 instruction_lctl;
-	u32 instruction_lctlg;
-	u32 instruction_stctl;
-	u32 instruction_stctg;
-	u32 exit_program_interruption;
-	u32 exit_instr_and_program;
-	u32 exit_operation_exception;
-	u32 deliver_external_call;
-	u32 deliver_emergency_signal;
-	u32 deliver_service_signal;
-	u32 deliver_virtio_interrupt;
-	u32 deliver_stop_signal;
-	u32 deliver_prefix_signal;
-	u32 deliver_restart_signal;
-	u32 deliver_program_int;
-	u32 deliver_io_int;
-	u32 exit_wait_state;
-	u32 instruction_pfmf;
-	u32 instruction_stidp;
-	u32 instruction_spx;
-	u32 instruction_stpx;
-	u32 instruction_stap;
-	u32 instruction_storage_key;
-	u32 instruction_ipte_interlock;
-	u32 instruction_stsch;
-	u32 instruction_chsc;
-	u32 instruction_stsi;
-	u32 instruction_stfl;
-	u32 instruction_tprot;
-	u32 instruction_sie;
-	u32 instruction_essa;
-	u32 instruction_sthyi;
-	u32 instruction_sigp_sense;
-	u32 instruction_sigp_sense_running;
-	u32 instruction_sigp_external_call;
-	u32 instruction_sigp_emergency;
-	u32 instruction_sigp_cond_emergency;
-	u32 instruction_sigp_start;
-	u32 instruction_sigp_stop;
-	u32 instruction_sigp_stop_store_status;
-	u32 instruction_sigp_store_status;
-	u32 instruction_sigp_store_adtl_status;
-	u32 instruction_sigp_arch;
-	u32 instruction_sigp_prefix;
-	u32 instruction_sigp_restart;
-	u32 instruction_sigp_init_cpu_reset;
-	u32 instruction_sigp_cpu_reset;
-	u32 instruction_sigp_unknown;
-	u32 diagnose_10;
-	u32 diagnose_44;
-	u32 diagnose_9c;
-	u32 diagnose_258;
-	u32 diagnose_308;
-	u32 diagnose_500;
+	u64 exit_userspace;
+	u64 exit_null;
+	u64 exit_external_request;
+	u64 exit_external_interrupt;
+	u64 exit_stop_request;
+	u64 exit_validity;
+	u64 exit_instruction;
+	u64 exit_pei;
+	u64 halt_successful_poll;
+	u64 halt_attempted_poll;
+	u64 halt_poll_invalid;
+	u64 halt_wakeup;
+	u64 instruction_lctl;
+	u64 instruction_lctlg;
+	u64 instruction_stctl;
+	u64 instruction_stctg;
+	u64 exit_program_interruption;
+	u64 exit_instr_and_program;
+	u64 exit_operation_exception;
+	u64 deliver_external_call;
+	u64 deliver_emergency_signal;
+	u64 deliver_service_signal;
+	u64 deliver_virtio_interrupt;
+	u64 deliver_stop_signal;
+	u64 deliver_prefix_signal;
+	u64 deliver_restart_signal;
+	u64 deliver_program_int;
+	u64 deliver_io_int;
+	u64 exit_wait_state;
+	u64 instruction_pfmf;
+	u64 instruction_stidp;
+	u64 instruction_spx;
+	u64 instruction_stpx;
+	u64 instruction_stap;
+	u64 instruction_storage_key;
+	u64 instruction_ipte_interlock;
+	u64 instruction_stsch;
+	u64 instruction_chsc;
+	u64 instruction_stsi;
+	u64 instruction_stfl;
+	u64 instruction_tprot;
+	u64 instruction_sie;
+	u64 instruction_essa;
+	u64 instruction_sthyi;
+	u64 instruction_sigp_sense;
+	u64 instruction_sigp_sense_running;
+	u64 instruction_sigp_external_call;
+	u64 instruction_sigp_emergency;
+	u64 instruction_sigp_cond_emergency;
+	u64 instruction_sigp_start;
+	u64 instruction_sigp_stop;
+	u64 instruction_sigp_stop_store_status;
+	u64 instruction_sigp_store_status;
+	u64 instruction_sigp_store_adtl_status;
+	u64 instruction_sigp_arch;
+	u64 instruction_sigp_prefix;
+	u64 instruction_sigp_restart;
+	u64 instruction_sigp_init_cpu_reset;
+	u64 instruction_sigp_cpu_reset;
+	u64 instruction_sigp_unknown;
+	u64 diagnose_10;
+	u64 diagnose_44;
+	u64 diagnose_9c;
+	u64 diagnose_258;
+	u64 diagnose_308;
+	u64 diagnose_500;
 };
 
 #define PGM_OPERATION			0x01
@@ -577,7 +577,7 @@ struct kvm_vcpu_arch {
 };
 
 struct kvm_vm_stat {
-	u32 remote_tlb_flush;
+	ulong remote_tlb_flush;
 };
 
 struct kvm_arch_memory_slot {
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 33ae3a4d0159..67c8f5268af5 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -790,45 +790,45 @@ struct kvm_arch {
 };
 
 struct kvm_vm_stat {
-	u32 mmu_shadow_zapped;
-	u32 mmu_pte_write;
-	u32 mmu_pte_updated;
-	u32 mmu_pde_zapped;
-	u32 mmu_flooded;
-	u32 mmu_recycled;
-	u32 mmu_cache_miss;
-	u32 mmu_unsync;
-	u32 remote_tlb_flush;
-	u32 lpages;
+	ulong mmu_shadow_zapped;
+	ulong mmu_pte_write;
+	ulong mmu_pte_updated;
+	ulong mmu_pde_zapped;
+	ulong mmu_flooded;
+	ulong mmu_recycled;
+	ulong mmu_cache_miss;
+	ulong mmu_unsync;
+	ulong remote_tlb_flush;
+	ulong lpages;
 };
 
 struct kvm_vcpu_stat {
-	u32 pf_fixed;
-	u32 pf_guest;
-	u32 tlb_flush;
-	u32 invlpg;
-
-	u32 exits;
-	u32 io_exits;
-	u32 mmio_exits;
-	u32 signal_exits;
-	u32 irq_window_exits;
-	u32 nmi_window_exits;
-	u32 halt_exits;
-	u32 halt_successful_poll;
-	u32 halt_attempted_poll;
-	u32 halt_poll_invalid;
-	u32 halt_wakeup;
-	u32 request_irq_exits;
-	u32 irq_exits;
-	u32 host_state_reload;
-	u32 efer_reload;
-	u32 fpu_reload;
-	u32 insn_emulation;
-	u32 insn_emulation_fail;
-	u32 hypercalls;
-	u32 irq_injections;
-	u32 nmi_injections;
+	u64 pf_fixed;
+	u64 pf_guest;
+	u64 tlb_flush;
+	u64 invlpg;
+
+	u64 exits;
+	u64 io_exits;
+	u64 mmio_exits;
+	u64 signal_exits;
+	u64 irq_window_exits;
+	u64 nmi_window_exits;
+	u64 halt_exits;
+	u64 halt_successful_poll;
+	u64 halt_attempted_poll;
+	u64 halt_poll_invalid;
+	u64 halt_wakeup;
+	u64 request_irq_exits;
+	u64 irq_exits;
+	u64 host_state_reload;
+	u64 efer_reload;
+	u64 fpu_reload;
+	u64 insn_emulation;
+	u64 insn_emulation_fail;
+	u64 hypercalls;
+	u64 irq_injections;
+	u64 nmi_injections;
 };
 
 struct x86_instruction_info;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 195078225aa5..4171ef326543 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -3619,7 +3619,7 @@ static int vm_stat_get_per_vm(void *data, u64 *val)
 {
 	struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data;
 
-	*val = *(u32 *)((void *)stat_data->kvm + stat_data->offset);
+	*val = *(ulong *)((void *)stat_data->kvm + stat_data->offset);
 
 	return 0;
 }
@@ -3649,7 +3649,7 @@ static int vcpu_stat_get_per_vm(void *data, u64 *val)
 	*val = 0;
 
 	kvm_for_each_vcpu(i, vcpu, stat_data->kvm)
-		*val += *(u32 *)((void *)vcpu + stat_data->offset);
+		*val += *(u64 *)((void *)vcpu + stat_data->offset);
 
 	return 0;
 }