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

Pull second batch of KVM changes from Paolo Bonzini: "This mostly includes the PPC changes for 4.1, which this time cover Book3S HV only (debugging aids, minor performance improvements and some cleanups). But there are also bug fixes and small cleanups for ARM, x86 and s390. The task_migration_notifier revert and real fix is still pending review, but I'll send it as soon as possible after -rc1" * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (29 commits) KVM: arm/arm64: check IRQ number on userland injection KVM: arm: irqfd: fix value returned by kvm_irq_map_gsi KVM: VMX: Preserve host CR4.MCE value while in guest mode. KVM: PPC: Book3S HV: Use msgsnd for signalling threads on POWER8 KVM: PPC: Book3S HV: Translate kvmhv_commence_exit to C KVM: PPC: Book3S HV: Streamline guest entry and exit KVM: PPC: Book3S HV: Use bitmap of active threads rather than count KVM: PPC: Book3S HV: Use decrementer to wake napping threads KVM: PPC: Book3S HV: Don't wake thread with no vcpu on guest IPI KVM: PPC: Book3S HV: Get rid of vcore nap_count and n_woken KVM: PPC: Book3S HV: Move vcore preemption point up into kvmppc_run_vcpu KVM: PPC: Book3S HV: Minor cleanups KVM: PPC: Book3S HV: Simplify handling of VCPUs that need a VPA update KVM: PPC: Book3S HV: Accumulate timing information for real-mode code KVM: PPC: Book3S HV: Create debugfs file for each guest's HPT KVM: PPC: Book3S HV: Add ICP real mode counters KVM: PPC: Book3S HV: Move virtual mode ICP functions to real-mode KVM: PPC: Book3S HV: Convert ICS mutex lock to spin lock KVM: PPC: Book3S HV: Add guest->host real mode completion counters KVM: PPC: Book3S HV: Add helpers for lock/unlock hpte ...
author: Linus Torvalds 2015-04-26 13:06:22 -0700
committer: Linus Torvalds 2015-04-26 13:06:22 -0700
commit: eadf16a912b6bdf8bd476bde2f19fb41d06e0c3b (patch)
tree: db20ba1e739b1118147d667d79e074558ed238ac /arch
parent: 4a6554665c62ee39be40f4a18c3d37e49d03ccc1 (diff)
parent: 2fa462f826210bbec65f8ed06d5ef4e0cd4f5450 (diff)
29 files changed, 1607 insertions, 391 deletions
diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h
index 2499867dd0d8..df3f60cb1168 100644
--- a/arch/arm/include/uapi/asm/kvm.h
+++ b/arch/arm/include/uapi/asm/kvm.h
@@ -195,8 +195,14 @@ struct kvm_arch_memory_slot {
 #define KVM_ARM_IRQ_CPU_IRQ		0
 #define KVM_ARM_IRQ_CPU_FIQ		1
 
-/* Highest supported SPI, from VGIC_NR_IRQS */
+/*
+ * This used to hold the highest supported SPI, but it is now obsolete
+ * and only here to provide source code level compatibility with older
+ * userland. The highest SPI number can be set via KVM_DEV_ARM_VGIC_GRP_NR_IRQS.
+ */
+#ifndef __KERNEL__
 #define KVM_ARM_IRQ_GIC_MAX		127
+#endif
 
 /* One single KVM irqchip, ie. the VGIC */
 #define KVM_NR_IRQCHIPS          1
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 6f536451ab78..d9631ecddd56 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -671,8 +671,7 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
 		if (!irqchip_in_kernel(kvm))
 			return -ENXIO;
 
-		if (irq_num < VGIC_NR_PRIVATE_IRQS ||
-		    irq_num > KVM_ARM_IRQ_GIC_MAX)
+		if (irq_num < VGIC_NR_PRIVATE_IRQS)
 			return -EINVAL;
 
 		return kvm_vgic_inject_irq(kvm, 0, irq_num, level);
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index c154c0b7eb60..d26832022127 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -188,8 +188,14 @@ struct kvm_arch_memory_slot {
 #define KVM_ARM_IRQ_CPU_IRQ		0
 #define KVM_ARM_IRQ_CPU_FIQ		1
 
-/* Highest supported SPI, from VGIC_NR_IRQS */
+/*
+ * This used to hold the highest supported SPI, but it is now obsolete
+ * and only here to provide source code level compatibility with older
+ * userland. The highest SPI number can be set via KVM_DEV_ARM_VGIC_GRP_NR_IRQS.
+ */
+#ifndef __KERNEL__
 #define KVM_ARM_IRQ_GIC_MAX		127
+#endif
 
 /* One single KVM irqchip, ie. the VGIC */
 #define KVM_NR_IRQCHIPS          1
diff --git a/arch/powerpc/include/asm/archrandom.h b/arch/powerpc/include/asm/archrandom.h
index bde531103638..0cc6eedc4780 100644
--- a/arch/powerpc/include/asm/archrandom.h
+++ b/arch/powerpc/include/asm/archrandom.h
@@ -30,8 +30,6 @@ static inline int arch_has_random(void)
 	return !!ppc_md.get_random_long;
 }
 
-int powernv_get_random_long(unsigned long *v);
-
 static inline int arch_get_random_seed_long(unsigned long *v)
 {
 	return 0;
@@ -47,4 +45,13 @@ static inline int arch_has_random_seed(void)
 
 #endif /* CONFIG_ARCH_RANDOM */
 
+#ifdef CONFIG_PPC_POWERNV
+int powernv_hwrng_present(void);
+int powernv_get_random_long(unsigned long *v);
+int powernv_get_random_real_mode(unsigned long *v);
+#else
+static inline int powernv_hwrng_present(void) { return 0; }
+static inline int powernv_get_random_real_mode(unsigned long *v) { return 0; }
+#endif
+
 #endif /* _ASM_POWERPC_ARCHRANDOM_H */
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 993090422690..b91e74a817d8 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -288,6 +288,9 @@ static inline bool kvmppc_supports_magic_page(struct kvm_vcpu *vcpu)
 	return !is_kvmppc_hv_enabled(vcpu->kvm);
 }
 
+extern int kvmppc_h_logical_ci_load(struct kvm_vcpu *vcpu);
+extern int kvmppc_h_logical_ci_store(struct kvm_vcpu *vcpu);
+
 /* Magic register values loaded into r3 and r4 before the 'sc' assembly
  * instruction for the OSI hypercalls */
 #define OSI_SC_MAGIC_R3			0x113724FA
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 14619a59ec09..7ae407941be2 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -85,6 +85,20 @@ static inline long try_lock_hpte(__be64 *hpte, unsigned long bits)
 	return old == 0;
 }
 
+static inline void unlock_hpte(__be64 *hpte, unsigned long hpte_v)
+{
+	hpte_v &= ~HPTE_V_HVLOCK;
+	asm volatile(PPC_RELEASE_BARRIER "" : : : "memory");
+	hpte[0] = cpu_to_be64(hpte_v);
+}
+
+/* Without barrier */
+static inline void __unlock_hpte(__be64 *hpte, unsigned long hpte_v)
+{
+	hpte_v &= ~HPTE_V_HVLOCK;
+	hpte[0] = cpu_to_be64(hpte_v);
+}
+
 static inline int __hpte_actual_psize(unsigned int lp, int psize)
 {
 	int i, shift;
@@ -424,6 +438,10 @@ static inline struct kvm_memslots *kvm_memslots_raw(struct kvm *kvm)
 	return rcu_dereference_raw_notrace(kvm->memslots);
 }
 
+extern void kvmppc_mmu_debugfs_init(struct kvm *kvm);
+
+extern void kvmhv_rm_send_ipi(int cpu);
+
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 
 #endif /* __ASM_KVM_BOOK3S_64_H__ */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index c610961720c7..a193a13cf08b 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -227,10 +227,8 @@ struct kvm_arch {
 	unsigned long host_sdr1;
 	int tlbie_lock;
 	unsigned long lpcr;
-	unsigned long rmor;
-	struct kvm_rma_info *rma;
 	unsigned long vrma_slb_v;
-	int rma_setup_done;
+	int hpte_setup_done;
 	u32 hpt_order;
 	atomic_t vcpus_running;
 	u32 online_vcores;
@@ -239,6 +237,8 @@ struct kvm_arch {
 	atomic_t hpte_mod_interest;
 	cpumask_t need_tlb_flush;
 	int hpt_cma_alloc;
+	struct dentry *debugfs_dir;
+	struct dentry *htab_dentry;
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 	struct mutex hpt_mutex;
@@ -263,18 +263,15 @@ struct kvm_arch {
 
 /*
  * Struct for a virtual core.
- * Note: entry_exit_count combines an entry count in the bottom 8 bits
- * and an exit count in the next 8 bits.  This is so that we can
- * atomically increment the entry count iff the exit count is 0
- * without taking the lock.
+ * 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 n_busy;
 	int num_threads;
-	int entry_exit_count;
-	int n_woken;
-	int nap_count;
+	int entry_exit_map;
 	int napping_threads;
 	int first_vcpuid;
 	u16 pcpu;
@@ -299,13 +296,14 @@ struct kvmppc_vcore {
 	ulong conferring_threads;
 };
 
-#define VCORE_ENTRY_COUNT(vc)	((vc)->entry_exit_count & 0xff)
-#define VCORE_EXIT_COUNT(vc)	((vc)->entry_exit_count >> 8)
+#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)
 
 /* Values for vcore_state */
 #define VCORE_INACTIVE	0
 #define VCORE_SLEEPING	1
-#define VCORE_STARTING	2
+#define VCORE_PREEMPT	2
 #define VCORE_RUNNING	3
 #define VCORE_EXITING	4
 
@@ -368,6 +366,14 @@ struct kvmppc_slb {
 	u8 base_page_size;	/* MMU_PAGE_xxx */
 };
 
+/* Struct used to accumulate timing information in HV real mode code */
+struct kvmhv_tb_accumulator {
+	u64	seqcount;	/* used to synchronize access, also count * 2 */
+	u64	tb_total;	/* total time in timebase ticks */
+	u64	tb_min;		/* min time */
+	u64	tb_max;		/* max time */
+};
+
 # ifdef CONFIG_PPC_FSL_BOOK3E
 #define KVMPPC_BOOKE_IAC_NUM	2
 #define KVMPPC_BOOKE_DAC_NUM	2
@@ -656,6 +662,19 @@ struct kvm_vcpu_arch {
 
 	u32 emul_inst;
 #endif
+
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+	struct kvmhv_tb_accumulator *cur_activity;	/* What we're timing */
+	u64	cur_tb_start;			/* when it started */
+	struct kvmhv_tb_accumulator rm_entry;	/* real-mode entry code */
+	struct kvmhv_tb_accumulator rm_intr;	/* real-mode intr handling */
+	struct kvmhv_tb_accumulator rm_exit;	/* real-mode exit code */
+	struct kvmhv_tb_accumulator guest_time;	/* guest execution */
+	struct kvmhv_tb_accumulator cede_time;	/* time napping inside guest */
+
+	struct dentry *debugfs_dir;
+	struct dentry *debugfs_timings;
+#endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
 };
 
 #define VCPU_FPR(vcpu, i)	(vcpu)->arch.fp.fpr[i][TS_FPROFFSET]
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 46bf652c9169..b8475daad884 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -302,6 +302,8 @@ static inline bool is_kvmppc_hv_enabled(struct kvm *kvm)
 	return kvm->arch.kvm_ops == kvmppc_hv_ops;
 }
 
+extern int kvmppc_hwrng_present(void);
+
 /*
  * Cuts out inst bits with ordering according to spec.
  * That means the leftmost bit is zero. All given bits are included.
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 03cbada59d3a..10fc784a2ad4 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -211,5 +211,8 @@ extern void secondary_cpu_time_init(void);
 
 DECLARE_PER_CPU(u64, decrementers_next_tb);
 
+/* Convert timebase ticks to nanoseconds */
+unsigned long long tb_to_ns(unsigned long long tb_ticks);
+
 #endif /* __KERNEL__ */
 #endif /* __POWERPC_TIME_H */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 4717859fdd04..0034b6b3556a 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -37,6 +37,7 @@
 #include <asm/thread_info.h>
 #include <asm/rtas.h>
 #include <asm/vdso_datapage.h>
+#include <asm/dbell.h>
 #ifdef CONFIG_PPC64
 #include <asm/paca.h>
 #include <asm/lppaca.h>
@@ -459,6 +460,19 @@ int main(void)
 	DEFINE(VCPU_SPRG2, offsetof(struct kvm_vcpu, arch.shregs.sprg2));
 	DEFINE(VCPU_SPRG3, offsetof(struct kvm_vcpu, arch.shregs.sprg3));
 #endif
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+	DEFINE(VCPU_TB_RMENTRY, offsetof(struct kvm_vcpu, arch.rm_entry));
+	DEFINE(VCPU_TB_RMINTR, offsetof(struct kvm_vcpu, arch.rm_intr));
+	DEFINE(VCPU_TB_RMEXIT, offsetof(struct kvm_vcpu, arch.rm_exit));
+	DEFINE(VCPU_TB_GUEST, offsetof(struct kvm_vcpu, arch.guest_time));
+	DEFINE(VCPU_TB_CEDE, offsetof(struct kvm_vcpu, arch.cede_time));
+	DEFINE(VCPU_CUR_ACTIVITY, offsetof(struct kvm_vcpu, arch.cur_activity));
+	DEFINE(VCPU_ACTIVITY_START, offsetof(struct kvm_vcpu, arch.cur_tb_start));
+	DEFINE(TAS_SEQCOUNT, offsetof(struct kvmhv_tb_accumulator, seqcount));
+	DEFINE(TAS_TOTAL, offsetof(struct kvmhv_tb_accumulator, tb_total));
+	DEFINE(TAS_MIN, offsetof(struct kvmhv_tb_accumulator, tb_min));
+	DEFINE(TAS_MAX, offsetof(struct kvmhv_tb_accumulator, tb_max));
+#endif
 	DEFINE(VCPU_SHARED_SPRG3, offsetof(struct kvm_vcpu_arch_shared, sprg3));
 	DEFINE(VCPU_SHARED_SPRG4, offsetof(struct kvm_vcpu_arch_shared, sprg4));
 	DEFINE(VCPU_SHARED_SPRG5, offsetof(struct kvm_vcpu_arch_shared, sprg5));
@@ -492,7 +506,6 @@ int main(void)
 	DEFINE(KVM_NEED_FLUSH, offsetof(struct kvm, arch.need_tlb_flush.bits));
 	DEFINE(KVM_ENABLED_HCALLS, offsetof(struct kvm, arch.enabled_hcalls));
 	DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr));
-	DEFINE(KVM_RMOR, offsetof(struct kvm, arch.rmor));
 	DEFINE(KVM_VRMA_SLB_V, offsetof(struct kvm, arch.vrma_slb_v));
 	DEFINE(VCPU_DSISR, offsetof(struct kvm_vcpu, arch.shregs.dsisr));
 	DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar));
@@ -550,8 +563,7 @@ int main(void)
 	DEFINE(VCPU_ACOP, offsetof(struct kvm_vcpu, arch.acop));
 	DEFINE(VCPU_WORT, offsetof(struct kvm_vcpu, arch.wort));
 	DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1));
-	DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count));
-	DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count));
+	DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_map));
 	DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
 	DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads));
 	DEFINE(VCORE_KVM, offsetof(struct kvmppc_vcore, kvm));
@@ -748,5 +760,7 @@ int main(void)
 			offsetof(struct paca_struct, subcore_sibling_mask));
 #endif
 
+	DEFINE(PPC_DBELL_SERVER, PPC_DBELL_SERVER);
+
 	return 0;
 }
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 2d7b33fab953..56f44848b044 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -608,6 +608,12 @@ void arch_suspend_enable_irqs(void)
 }
 #endif
 
+unsigned long long tb_to_ns(unsigned long long ticks)
+{
+	return mulhdu(ticks, tb_to_ns_scale) << tb_to_ns_shift;
+}
+EXPORT_SYMBOL_GPL(tb_to_ns);
+
 /*
  * Scheduler clock - returns current time in nanosec units.
  *
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 11850f310fb4..2963e4dd0b80 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -110,6 +110,20 @@ config KVM_BOOK3S_64_PR
 	  processor, including emulating 32-bit processors on a 64-bit
 	  host.
 
+config KVM_BOOK3S_HV_EXIT_TIMING
+	bool "Detailed timing for hypervisor real-mode code"
+	depends on KVM_BOOK3S_HV_POSSIBLE && DEBUG_FS
+	---help---
+	  Calculate time taken for each vcpu in the real-mode guest entry,
+	  exit, and interrupt handling code, plus time spent in the guest
+	  and in nap mode due to idle (cede) while other threads are still
+	  in the guest.  The total, minimum and maximum times in nanoseconds
+	  together with the number of executions are reported in debugfs in
+	  kvm/vm#/vcpu#/timings.  The overhead is of the order of 30 - 40
+	  ns per exit on POWER8.
+
+	  If unsure, say N.
+
 config KVM_BOOKE_HV
 	bool
 
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index cfbcdc654201..453a8a47a467 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -821,6 +821,82 @@ void kvmppc_core_destroy_vm(struct kvm *kvm)
 #endif
 }
 
+int kvmppc_h_logical_ci_load(struct kvm_vcpu *vcpu)
+{
+	unsigned long size = kvmppc_get_gpr(vcpu, 4);
+	unsigned long addr = kvmppc_get_gpr(vcpu, 5);
+	u64 buf;
+	int ret;
+
+	if (!is_power_of_2(size) || (size > sizeof(buf)))
+		return H_TOO_HARD;
+
+	ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, size, &buf);
+	if (ret != 0)
+		return H_TOO_HARD;
+
+	switch (size) {
+	case 1:
+		kvmppc_set_gpr(vcpu, 4, *(u8 *)&buf);
+		break;
+
+	case 2:
+		kvmppc_set_gpr(vcpu, 4, be16_to_cpu(*(__be16 *)&buf));
+		break;
+
+	case 4:
+		kvmppc_set_gpr(vcpu, 4, be32_to_cpu(*(__be32 *)&buf));
+		break;
+
+	case 8:
+		kvmppc_set_gpr(vcpu, 4, be64_to_cpu(*(__be64 *)&buf));
+		break;
+
+	default:
+		BUG();
+	}
+
+	return H_SUCCESS;
+}
+EXPORT_SYMBOL_GPL(kvmppc_h_logical_ci_load);
+
+int kvmppc_h_logical_ci_store(struct kvm_vcpu *vcpu)
+{
+	unsigned long size = kvmppc_get_gpr(vcpu, 4);
+	unsigned long addr = kvmppc_get_gpr(vcpu, 5);
+	unsigned long val = kvmppc_get_gpr(vcpu, 6);
+	u64 buf;
+	int ret;
+
+	switch (size) {
+	case 1:
+		*(u8 *)&buf = val;
+		break;
+
+	case 2:
+		*(__be16 *)&buf = cpu_to_be16(val);
+		break;
+
+	case 4:
+		*(__be32 *)&buf = cpu_to_be32(val);
+		break;
+
+	case 8:
+		*(__be64 *)&buf = cpu_to_be64(val);
+		break;
+
+	default:
+		return H_TOO_HARD;
+	}
+
+	ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, addr, size, &buf);
+	if (ret != 0)
+		return H_TOO_HARD;
+
+	return H_SUCCESS;
+}
+EXPORT_SYMBOL_GPL(kvmppc_h_logical_ci_store);
+
 int kvmppc_core_check_processor_compat(void)
 {
 	/*
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 534acb3c6c3d..d6fe30835c58 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -27,6 +27,7 @@
 #include <linux/srcu.h>
 #include <linux/anon_inodes.h>
 #include <linux/file.h>
+#include <linux/debugfs.h>
 
 #include <asm/tlbflush.h>
 #include <asm/kvm_ppc.h>
@@ -116,12 +117,12 @@ long kvmppc_alloc_reset_hpt(struct kvm *kvm, u32 *htab_orderp)
 	long order;
 
 	mutex_lock(&kvm->lock);
-	if (kvm->arch.rma_setup_done) {
-		kvm->arch.rma_setup_done = 0;
-		/* order rma_setup_done vs. vcpus_running */
+	if (kvm->arch.hpte_setup_done) {
+		kvm->arch.hpte_setup_done = 0;
+		/* order hpte_setup_done vs. vcpus_running */
 		smp_mb();
 		if (atomic_read(&kvm->arch.vcpus_running)) {
-			kvm->arch.rma_setup_done = 1;
+			kvm->arch.hpte_setup_done = 1;
 			goto out;
 		}
 	}
@@ -338,9 +339,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	v = be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK;
 	gr = kvm->arch.revmap[index].guest_rpte;
 
-	/* Unlock the HPTE */
-	asm volatile("lwsync" : : : "memory");
-	hptep[0] = cpu_to_be64(v);
+	unlock_hpte(hptep, v);
 	preempt_enable();
 
 	gpte->eaddr = eaddr;
@@ -469,8 +468,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	hpte[0] = be64_to_cpu(hptep[0]) & ~HPTE_V_HVLOCK;
 	hpte[1] = be64_to_cpu(hptep[1]);
 	hpte[2] = r = rev->guest_rpte;
-	asm volatile("lwsync" : : : "memory");
-	hptep[0] = cpu_to_be64(hpte[0]);
+	unlock_hpte(hptep, hpte[0]);
 	preempt_enable();
 
 	if (hpte[0] != vcpu->arch.pgfault_hpte[0] ||
@@ -621,7 +619,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	hptep[1] = cpu_to_be64(r);
 	eieio();
-	hptep[0] = cpu_to_be64(hpte[0]);
+	__unlock_hpte(hptep, hpte[0]);
 	asm volatile("ptesync" : : : "memory");
 	preempt_enable();
 	if (page && hpte_is_writable(r))
@@ -642,7 +640,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	return ret;
 
  out_unlock:
-	hptep[0] &= ~cpu_to_be64(HPTE_V_HVLOCK);
+	__unlock_hpte(hptep, be64_to_cpu(hptep[0]));
 	preempt_enable();
 	goto out_put;
 }
@@ -771,7 +769,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
 			}
 		}
 		unlock_rmap(rmapp);
-		hptep[0] &= ~cpu_to_be64(HPTE_V_HVLOCK);
+		__unlock_hpte(hptep, be64_to_cpu(hptep[0]));
 	}
 	return 0;
 }
@@ -857,7 +855,7 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 			}
 			ret = 1;
 		}
-		hptep[0] &= ~cpu_to_be64(HPTE_V_HVLOCK);
+		__unlock_hpte(hptep, be64_to_cpu(hptep[0]));
 	} while ((i = j) != head);
 
 	unlock_rmap(rmapp);
@@ -974,8 +972,7 @@ static int kvm_test_clear_dirty_npages(struct kvm *kvm, unsigned long *rmapp)
 
 		/* Now check and modify the HPTE */
 		if (!(hptep[0] & cpu_to_be64(HPTE_V_VALID))) {
-			/* unlock and continue */
-			hptep[0] &= ~cpu_to_be64(HPTE_V_HVLOCK);
+			__unlock_hpte(hptep, be64_to_cpu(hptep[0]));
 			continue;
 		}
 
@@ -996,9 +993,9 @@ static int kvm_test_clear_dirty_npages(struct kvm *kvm, unsigned long *rmapp)
 				npages_dirty = n;
 			eieio();
 		}
-		v &= ~(HPTE_V_ABSENT | HPTE_V_HVLOCK);
+		v &= ~HPTE_V_ABSENT;
 		v |= HPTE_V_VALID;
-		hptep[0] = cpu_to_be64(v);
+		__unlock_hpte(hptep, v);
 	} while ((i = j) != head);
 
 	unlock_rmap(rmapp);
@@ -1218,8 +1215,7 @@ static long record_hpte(unsigned long flags, __be64 *hptp,
 			r &= ~HPTE_GR_MODIFIED;
 			revp->guest_rpte = r;
 		}
-		asm volatile(PPC_RELEASE_BARRIER "" : : : "memory");
-		hptp[0] &= ~cpu_to_be64(HPTE_V_HVLOCK);
+		unlock_hpte(hptp, be64_to_cpu(hptp[0]));
 		preempt_enable();
 		if (!(valid == want_valid && (first_pass || dirty)))
 			ok = 0;
@@ -1339,20 +1335,20 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
 	unsigned long tmp[2];
 	ssize_t nb;
 	long int err, ret;
-	int rma_setup;
+	int hpte_setup;
 
 	if (!access_ok(VERIFY_READ, buf, count))
 		return -EFAULT;
 
 	/* lock out vcpus from running while we're doing this */
 	mutex_lock(&kvm->lock);
-	rma_setup = kvm->arch.rma_setup_done;
-	if (rma_setup) {
-		kvm->arch.rma_setup_done = 0;	/* temporarily */
-		/* order rma_setup_done vs. vcpus_running */
+	hpte_setup = kvm->arch.hpte_setup_done;
+	if (hpte_setup) {
+		kvm->arch.hpte_setup_done = 0;	/* temporarily */
+		/* order hpte_setup_done vs. vcpus_running */
 		smp_mb();
 		if (atomic_read(&kvm->arch.vcpus_running)) {
-			kvm->arch.rma_setup_done = 1;
+			kvm->arch.hpte_setup_done = 1;
 			mutex_unlock(&kvm->lock);
 			return -EBUSY;
 		}
@@ -1405,7 +1401,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
 				       "r=%lx\n", ret, i, v, r);
 				goto out;
 			}
-			if (!rma_setup && is_vrma_hpte(v)) {
+			if (!hpte_setup && is_vrma_hpte(v)) {
 				unsigned long psize = hpte_base_page_size(v, r);
 				unsigned long senc = slb_pgsize_encoding(psize);
 				unsigned long lpcr;
@@ -1414,7 +1410,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
 					(VRMA_VSID << SLB_VSID_SHIFT_1T);
 				lpcr = senc << (LPCR_VRMASD_SH - 4);
 				kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD);
-				rma_setup = 1;
+				hpte_setup = 1;
 			}
 			++i;
 			hptp += 2;
@@ -1430,9 +1426,9 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
 	}
 
  out:
-	/* Order HPTE updates vs. rma_setup_done */
+	/* Order HPTE updates vs. hpte_setup_done */
 	smp_wmb();
-	kvm->arch.rma_setup_done = rma_setup;
+	kvm->arch.hpte_setup_done = hpte_setup;
 	mutex_unlock(&kvm->lock);
 
 	if (err)
@@ -1495,6 +1491,141 @@ int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *ghf)
 	return ret;
 }
 
+struct debugfs_htab_state {
+	struct kvm	*kvm;
+	struct mutex	mutex;
+	unsigned long	hpt_index;
+	int		chars_left;
+	int		buf_index;
+	char		buf[64];
+};
+
+static int debugfs_htab_open(struct inode *inode, struct file *file)
+{
+	struct kvm *kvm = inode->i_private;
+	struct debugfs_htab_state *p;
+
+	p = kzalloc(sizeof(*p), GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	kvm_get_kvm(kvm);
+	p->kvm = kvm;
+	mutex_init(&p->mutex);
+	file->private_data = p;
+
+	return nonseekable_open(inode, file);
+}
+
+static int debugfs_htab_release(struct inode *inode, struct file *file)
+{
+	struct debugfs_htab_state *p = file->private_data;
+
+	kvm_put_kvm(p->kvm);
+	kfree(p);
+	return 0;
+}
+
+static ssize_t debugfs_htab_read(struct file *file, char __user *buf,
+				 size_t len, loff_t *ppos)
+{
+	struct debugfs_htab_state *p = file->private_data;
+	ssize_t ret, r;
+	unsigned long i, n;
+	unsigned long v, hr, gr;
+	struct kvm *kvm;
+	__be64 *hptp;
+
+	ret = mutex_lock_interruptible(&p->mutex);
+	if (ret)
+		return ret;
+
+	if (p->chars_left) {
+		n = p->chars_left;
+		if (n > len)
+			n = len;
+		r = copy_to_user(buf, p->buf + p->buf_index, n);
+		n -= r;
+		p->chars_left -= n;
+		p->buf_index += n;
+		buf += n;
+		len -= n;
+		ret = n;
+		if (r) {
+			if (!n)
+				ret = -EFAULT;
+			goto out;
+		}
+	}
+
+	kvm = p->kvm;
+	i = p->hpt_index;
+	hptp = (__be64 *)(kvm->arch.hpt_virt + (i * HPTE_SIZE));
+	for (; len != 0 && i < kvm->arch.hpt_npte; ++i, hptp += 2) {
+		if (!(be64_to_cpu(hptp[0]) & (HPTE_V_VALID | HPTE_V_ABSENT)))
+			continue;
+
+		/* lock the HPTE so it's stable and read it */
+		preempt_disable();
+		while (!try_lock_hpte(hptp, HPTE_V_HVLOCK))
+			cpu_relax();
+		v = be64_to_cpu(hptp[0]) & ~HPTE_V_HVLOCK;
+		hr = be64_to_cpu(hptp[1]);
+		gr = kvm->arch.revmap[i].guest_rpte;
+		unlock_hpte(hptp, v);
+		preempt_enable();
+
+		if (!(v & (HPTE_V_VALID | HPTE_V_ABSENT)))
+			continue;
+
+		n = scnprintf(p->buf, sizeof(p->buf),
+			      "%6lx %.16lx %.16lx %.16lx\n",
+			      i, v, hr, gr);
+		p->chars_left = n;
+		if (n > len)
+			n = len;
+		r = copy_to_user(buf, p->buf, n);
+		n -= r;
+		p->chars_left -= n;
+		p->buf_index = n;
+		buf += n;
+		len -= n;
+		ret += n;
+		if (r) {
+			if (!ret)
+				ret = -EFAULT;
+			goto out;
+		}
+	}
+	p->hpt_index = i;
+
+ out:
+	mutex_unlock(&p->mutex);
+	return ret;
+}
+
+ssize_t debugfs_htab_write(struct file *file, const char __user *buf,
+			   size_t len, loff_t *ppos)
+{
+	return -EACCES;
+}
+
+static const struct file_operations debugfs_htab_fops = {
+	.owner	 = THIS_MODULE,
+	.open	 = debugfs_htab_open,
+	.release = debugfs_htab_release,
+	.read	 = debugfs_htab_read,
+	.write	 = debugfs_htab_write,
+	.llseek	 = generic_file_llseek,
+};
+
+void kvmppc_mmu_debugfs_init(struct kvm *kvm)
+{
+	kvm->arch.htab_dentry = debugfs_create_file("htab", 0400,
+						    kvm->arch.debugfs_dir, kvm,
+						    &debugfs_htab_fops);
+}
+
 void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_mmu *mmu = &vcpu->arch.mmu;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index de747563d29d..48d3c5d2ecc9 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -32,6 +32,7 @@
 #include <linux/page-flags.h>
 #include <linux/srcu.h>
 #include <linux/miscdevice.h>
+#include <linux/debugfs.h>
 
 #include <asm/reg.h>
 #include <asm/cputable.h>
@@ -50,6 +51,7 @@
 #include <asm/hvcall.h>
 #include <asm/switch_to.h>
 #include <asm/smp.h>
+#include <asm/dbell.h>
 #include <linux/gfp.h>
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
@@ -83,9 +85,35 @@ static DECLARE_BITMAP(default_enabled_hcalls, MAX_HCALL_OPCODE/4 + 1);
 static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
 static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
 
+static bool kvmppc_ipi_thread(int cpu)
+{
+	/* On POWER8 for IPIs to threads in the same core, use msgsnd */
+	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+		preempt_disable();
+		if (cpu_first_thread_sibling(cpu) ==
+		    cpu_first_thread_sibling(smp_processor_id())) {
+			unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
+			msg |= cpu_thread_in_core(cpu);
+			smp_mb();
+			__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
+			preempt_enable();
+			return true;
+		}
+		preempt_enable();
+	}
+
+#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
+	if (cpu >= 0 && cpu < nr_cpu_ids && paca[cpu].kvm_hstate.xics_phys) {
+		xics_wake_cpu(cpu);
+		return true;
+	}
+#endif
+
+	return false;
+}
+
 static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 {
-	int me;
 	int cpu = vcpu->cpu;
 	wait_queue_head_t *wqp;
 
@@ -95,20 +123,12 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 		++vcpu->stat.halt_wakeup;
 	}
 
-	me = get_cpu();
+	if (kvmppc_ipi_thread(cpu + vcpu->arch.ptid))
+		return;
 
 	/* CPU points to the first thread of the core */
-	if (cpu != me && cpu >= 0 && cpu < nr_cpu_ids) {
-#ifdef CONFIG_PPC_ICP_NATIVE
-		int real_cpu = cpu + vcpu->arch.ptid;
-		if (paca[real_cpu].kvm_hstate.xics_phys)
-			xics_wake_cpu(real_cpu);
-		else
-#endif
-		if (cpu_online(cpu))
-			smp_send_reschedule(cpu);
-	}
-	put_cpu();
+	if (cpu >= 0 && cpu < nr_cpu_ids && cpu_online(cpu))
+		smp_send_reschedule(cpu);
 }
 
 /*
@@ -706,6 +726,16 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 
 		/* Send the error out to userspace via KVM_RUN */
 		return rc;
+	case H_LOGICAL_CI_LOAD:
+		ret = kvmppc_h_logical_ci_load(vcpu);
+		if (ret == H_TOO_HARD)
+			return RESUME_HOST;
+		break;
+	case H_LOGICAL_CI_STORE:
+		ret = kvmppc_h_logical_ci_store(vcpu);
+		if (ret == H_TOO_HARD)
+			return RESUME_HOST;
+		break;
 	case H_SET_MODE:
 		ret = kvmppc_h_set_mode(vcpu, kvmppc_get_gpr(vcpu, 4),
 					kvmppc_get_gpr(vcpu, 5),
@@ -740,6 +770,8 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd)
 	case H_CONFER:
 	case H_REGISTER_VPA:
 	case H_SET_MODE:
+	case H_LOGICAL_CI_LOAD:
+	case H_LOGICAL_CI_STORE:
 #ifdef CONFIG_KVM_XICS
 	case H_XIRR:
 	case H_CPPR:
@@ -1410,6 +1442,154 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
 	return vcore;
 }
 
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+static struct debugfs_timings_element {
+	const char *name;
+	size_t offset;
+} timings[] = {
+	{"rm_entry",	offsetof(struct kvm_vcpu, arch.rm_entry)},
+	{"rm_intr",	offsetof(struct kvm_vcpu, arch.rm_intr)},
+	{"rm_exit",	offsetof(struct kvm_vcpu, arch.rm_exit)},
+	{"guest",	offsetof(struct kvm_vcpu, arch.guest_time)},
+	{"cede",	offsetof(struct kvm_vcpu, arch.cede_time)},
+};
+
+#define N_TIMINGS	(sizeof(timings) / sizeof(timings[0]))
+
+struct debugfs_timings_state {
+	struct kvm_vcpu	*vcpu;
+	unsigned int	buflen;
+	char		buf[N_TIMINGS * 100];
+};
+
+static int debugfs_timings_open(struct inode *inode, struct file *file)
+{
+	struct kvm_vcpu *vcpu = inode->i_private;
+	struct debugfs_timings_state *p;
+
+	p = kzalloc(sizeof(*p), GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	kvm_get_kvm(vcpu->kvm);
+	p->vcpu = vcpu;
+	file->private_data = p;
+
+	return nonseekable_open(inode, file);
+}
+
+static int debugfs_timings_release(struct inode *inode, struct file *file)
+{
+	struct debugfs_timings_state *p = file->private_data;
+
+	kvm_put_kvm(p->vcpu->kvm);
+	kfree(p);
+	return 0;
+}
+
+static ssize_t debugfs_timings_read(struct file *file, char __user *buf,
+				    size_t len, loff_t *ppos)
+{
+	struct debugfs_timings_state *p = file->private_data;
+	struct kvm_vcpu *vcpu = p->vcpu;
+	char *s, *buf_end;
+	struct kvmhv_tb_accumulator tb;
+	u64 count;
+	loff_t pos;
+	ssize_t n;
+	int i, loops;
+	bool ok;
+
+	if (!p->buflen) {
+		s = p->buf;
+		buf_end = s + sizeof(p->buf);
+		for (i = 0; i < N_TIMINGS; ++i) {
+			struct kvmhv_tb_accumulator *acc;
+
+			acc = (struct kvmhv_tb_accumulator *)
+				((unsigned long)vcpu + timings[i].offset);
+			ok = false;
+			for (loops = 0; loops < 1000; ++loops) {
+				count = acc->seqcount;
+				if (!(count & 1)) {
+					smp_rmb();
+					tb = *acc;
+					smp_rmb();
+					if (count == acc->seqcount) {
+						ok = true;
+						break;
+					}
+				}
+				udelay(1);
+			}
+			if (!ok)
+				snprintf(s, buf_end - s, "%s: stuck\n",
+					timings[i].name);
+			else
+				snprintf(s, buf_end - s,
+					"%s: %llu %llu %llu %llu\n",
+					timings[i].name, count / 2,
+					tb_to_ns(tb.tb_total),
+					tb_to_ns(tb.tb_min),
+					tb_to_ns(tb.tb_max));
+			s += strlen(s);
+		}
+		p->buflen = s - p->buf;
+	}
+
+	pos = *ppos;
+	if (pos >= p->buflen)
+		return 0;
+	if (len > p->buflen - pos)
+		len = p->buflen - pos;
+	n = copy_to_user(buf, p->buf + pos, len);
+	if (n) {
+		if (n == len)
+			return -EFAULT;
+		len -= n;
+	}
+	*ppos = pos + len;
+	return len;
+}
+
+static ssize_t debugfs_timings_write(struct file *file, const char __user *buf,
+				     size_t len, loff_t *ppos)
+{
+	return -EACCES;
+}
+
+static const struct file_operations debugfs_timings_ops = {
+	.owner	 = THIS_MODULE,
+	.open	 = debugfs_timings_open,
+	.release = debugfs_timings_release,
+	.read	 = debugfs_timings_read,
+	.write	 = debugfs_timings_write,
+	.llseek	 = generic_file_llseek,
+};
+
+/* Create a debugfs directory for the vcpu */
+static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id)
+{
+	char buf[16];
+	struct kvm *kvm = vcpu->kvm;
+
+	snprintf(buf, sizeof(buf), "vcpu%u", id);
+	if (IS_ERR_OR_NULL(kvm->arch.debugfs_dir))
+		return;
+	vcpu->arch.debugfs_dir = debugfs_create_dir(buf, kvm->arch.debugfs_dir);
+	if (IS_ERR_OR_NULL(vcpu->arch.debugfs_dir))
+		return;
+	vcpu->arch.debugfs_timings =
+		debugfs_create_file("timings", 0444, vcpu->arch.debugfs_dir,
+				    vcpu, &debugfs_timings_ops);
+}
+
+#else /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
+static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id)
+{
+}
+#endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
+
 static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
 						   unsigned int id)
 {
@@ -1479,6 +1659,8 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
 	vcpu->arch.cpu_type = KVM_CPU_3S_64;
 	kvmppc_sanity_check(vcpu);
 
+	debugfs_vcpu_init(vcpu, id);
+
 	return vcpu;
 
 free_vcpu:
@@ -1566,8 +1748,10 @@ static int kvmppc_grab_hwthread(int cpu)
 	tpaca = &paca[cpu];
 
 	/* Ensure the thread won't go into the kernel if it wakes */
-	tpaca->kvm_hstate.hwthread_req = 1;
 	tpaca->kvm_hstate.kvm_vcpu = NULL;
+	tpaca->kvm_hstate.napping = 0;
+	smp_wmb();
+	tpaca->kvm_hstate.hwthread_req = 1;
 
 	/*
 	 * If the thread is already executing in the kernel (e.g. handling
@@ -1610,35 +1794,41 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu)
 	}
 	cpu = vc->pcpu + vcpu->arch.ptid;
 	tpaca = &paca[cpu];
-	tpaca->kvm_hstate.kvm_vcpu = vcpu;
 	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();
-#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
-	if (cpu != smp_processor_id()) {
-		xics_wake_cpu(cpu);
-		if (vcpu->arch.ptid)
-			++vc->n_woken;
-	}
-#endif
+	tpaca->kvm_hstate.kvm_vcpu = vcpu;
+	if (cpu != smp_processor_id())
+		kvmppc_ipi_thread(cpu);
 }
 
-static void kvmppc_wait_for_nap(struct kvmppc_vcore *vc)
+static void kvmppc_wait_for_nap(void)
 {
-	int i;
+	int cpu = smp_processor_id();
+	int i, loops;
 
-	HMT_low();
-	i = 0;
-	while (vc->nap_count < vc->n_woken) {
-		if (++i >= 1000000) {
-			pr_err("kvmppc_wait_for_nap timeout %d %d\n",
-			       vc->nap_count, vc->n_woken);
-			break;
+	for (loops = 0; loops < 1000000; ++loops) {
+		/*
+		 * Check if all threads are finished.
+		 * We set the vcpu 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 (i = 1; i < threads_per_subcore; ++i)
+			if (paca[cpu + i].kvm_hstate.kvm_vcpu)
+				break;
+		if (i == threads_per_subcore) {
+			HMT_medium();
+			return;
 		}
-		cpu_relax();
+		HMT_low();
 	}
 	HMT_medium();
+	for (i = 1; i < threads_per_subcore; ++i)
+		if (paca[cpu + i].kvm_hstate.kvm_vcpu)
+			pr_err("KVM: CPU %d seems to be stuck\n", cpu + i);
 }
 
 /*
@@ -1700,63 +1890,103 @@ static void kvmppc_start_restoring_l2_cache(const struct kvmppc_vcore *vc)
 	mtspr(SPRN_MPPR, mpp_addr | PPC_MPPR_FETCH_WHOLE_TABLE);
 }
 
+static void prepare_threads(struct kvmppc_vcore *vc)
+{
+	struct kvm_vcpu *vcpu, *vnext;
+
+	list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
+				 arch.run_list) {
+		if (signal_pending(vcpu->arch.run_task))
+			vcpu->arch.ret = -EINTR;
+		else if (vcpu->arch.vpa.update_pending ||
+			 vcpu->arch.slb_shadow.update_pending ||
+			 vcpu->arch.dtl.update_pending)
+			vcpu->arch.ret = RESUME_GUEST;
+		else
+			continue;
+		kvmppc_remove_runnable(vc, vcpu);
+		wake_up(&vcpu->arch.cpu_run);
+	}
+}
+
+static void post_guest_process(struct kvmppc_vcore *vc)
+{
+	u64 now;
+	long ret;
+	struct kvm_vcpu *vcpu, *vnext;
+
+	now = get_tb();
+	list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
+				 arch.run_list) {
+		/* cancel pending dec exception if dec is positive */
+		if (now < vcpu->arch.dec_expires &&
+		    kvmppc_core_pending_dec(vcpu))
+			kvmppc_core_dequeue_dec(vcpu);
+
+		trace_kvm_guest_exit(vcpu);
+
+		ret = RESUME_GUEST;
+		if (vcpu->arch.trap)
+			ret = kvmppc_handle_exit_hv(vcpu->arch.kvm_run, vcpu,
+						    vcpu->arch.run_task);
+
+		vcpu->arch.ret = ret;
+		vcpu->arch.trap = 0;
+
+		if (vcpu->arch.ceded) {
+			if (!is_kvmppc_resume_guest(ret))
+				kvmppc_end_cede(vcpu);
+			else
+				kvmppc_set_timer(vcpu);
+		}
+		if (!is_kvmppc_resume_guest(vcpu->arch.ret)) {
+			kvmppc_remove_runnable(vc, vcpu);
+			wake_up(&vcpu->arch.cpu_run);
+		}
+	}
+}
+
 /*
  * Run a set of guest threads on a physical core.
  * Called with vc->lock held.
  */
-static void kvmppc_run_core(struct kvmppc_vcore *vc)
+static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 {
-	struct kvm_vcpu *vcpu, *vnext;
-	long ret;
-	u64 now;
-	int i, need_vpa_update;
+	struct kvm_vcpu *vcpu;
+	int i;
 	int srcu_idx;
-	struct kvm_vcpu *vcpus_to_update[threads_per_core];
 
-	/* don't start if any threads have a signal pending */
-	need_vpa_update = 0;
-	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
-		if (signal_pending(vcpu->arch.run_task))
-			return;
-		if (vcpu->arch.vpa.update_pending ||
-		    vcpu->arch.slb_shadow.update_pending ||
-		    vcpu->arch.dtl.update_pending)
-			vcpus_to_update[need_vpa_update++] = vcpu;
-	}
+	/*
+	 * Remove from the list any threads that have a signal pending
+	 * or need a VPA update done
+	 */
+	prepare_threads(vc);
+
+	/* if the runner is no longer runnable, let the caller pick a new one */
+	if (vc->runner->arch.state != KVMPPC_VCPU_RUNNABLE)
+		return;
 
 	/*
-	 * Initialize *vc, in particular vc->vcore_state, so we can
-	 * drop the vcore lock if necessary.
+	 * Initialize *vc.
 	 */
-	vc->n_woken = 0;
-	vc->nap_count = 0;
-	vc->entry_exit_count = 0;
+	vc->entry_exit_map = 0;
 	vc->preempt_tb = TB_NIL;
-	vc->vcore_state = VCORE_STARTING;
 	vc->in_guest = 0;
 	vc->napping_threads = 0;
 	vc->conferring_threads = 0;
 
 	/*
-	 * Updating any of the vpas requires calling kvmppc_pin_guest_page,
-	 * which can't be called with any spinlocks held.
-	 */
-	if (need_vpa_update) {
-		spin_unlock(&vc->lock);
-		for (i = 0; i < need_vpa_update; ++i)
-			kvmppc_update_vpas(vcpus_to_update[i]);
-		spin_lock(&vc->lock);
-	}
-
-	/*
 	 * Make sure we are running on primary threads, and that secondary
 	 * threads are offline.  Also check if the number of threads in this
 	 * guest are greater than the current system threads per guest.
 	 */
 	if ((threads_per_core > 1) &&
 	    ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
-		list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
+		list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
 			vcpu->arch.ret = -EBUSY;
+			kvmppc_remove_runnable(vc, vcpu);
+			wake_up(&vcpu->arch.cpu_run);
+		}
 		goto out;
 	}
 
@@ -1797,8 +2027,7 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 	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 */
-	if (vc->nap_count < vc->n_woken)
-		kvmppc_wait_for_nap(vc);
+	kvmppc_wait_for_nap();
 	for (i = 0; i < threads_per_subcore; ++i)
 		kvmppc_release_hwthread(vc->pcpu + i);
 	/* prevent other vcpu threads from doing kvmppc_start_thread() now */
@@ -1812,44 +2041,12 @@ static void kvmppc_run_core(struct kvmppc_vcore *vc)
 	kvm_guest_exit();
 
 	preempt_enable();
-	cond_resched();
 
 	spin_lock(&vc->lock);
-	now = get_tb();
-	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
-		/* cancel pending dec exception if dec is positive */
-		if (now < vcpu->arch.dec_expires &&
-		    kvmppc_core_pending_dec(vcpu))
-			kvmppc_core_dequeue_dec(vcpu);
-
-		trace_kvm_guest_exit(vcpu);
-
-		ret = RESUME_GUEST;
-		if (vcpu->arch.trap)
-			ret = kvmppc_handle_exit_hv(vcpu->arch.kvm_run, vcpu,
-						    vcpu->arch.run_task);
-
-		vcpu->arch.ret = ret;
-		vcpu->arch.trap = 0;
-
-		if (vcpu->arch.ceded) {
-			if (!is_kvmppc_resume_guest(ret))
-				kvmppc_end_cede(vcpu);
-			else
-				kvmppc_set_timer(vcpu);
-		}
-	}
+	post_guest_process(vc);
 
  out:
 	vc->vcore_state = VCORE_INACTIVE;
-	list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
-				 arch.run_list) {
-		if (!is_kvmppc_resume_guest(vcpu->arch.ret)) {
-			kvmppc_remove_runnable(vc, vcpu);
-			wake_up(&vcpu->arch.cpu_run);
-		}
-	}
-
 	trace_kvmppc_run_core(vc, 1);
 }
 
@@ -1939,8 +2136,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	 * this thread straight away and have it join in.
 	 */
 	if (!signal_pending(current)) {
-		if (vc->vcore_state == VCORE_RUNNING &&
-		    VCORE_EXIT_COUNT(vc) == 0) {
+		if (vc->vcore_state == VCORE_RUNNING && !VCORE_IS_EXITING(vc)) {
 			kvmppc_create_dtl_entry(vcpu, vc);
 			kvmppc_start_thread(vcpu);
 			trace_kvm_guest_enter(vcpu);
@@ -1971,7 +2167,6 @@ 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;
-		vc->runner = vcpu;
 		n_ceded = 0;
 		list_for_each_entry(v, &vc->runnable_threads, arch.run_list) {
 			if (!v->arch.pending_exceptions)
@@ -1979,10 +2174,17 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 			else
 				v->arch.ceded = 0;
 		}
-		if (n_ceded == vc->n_runnable)
+		vc->runner = vcpu;
+		if (n_ceded == vc->n_runnable) {
 			kvmppc_vcore_blocked(vc);
-		else
+		} else if (should_resched()) {
+			vc->vcore_state = VCORE_PREEMPT;
+			/* Let something else run */
+			cond_resched_lock(&vc->lock);
+			vc->vcore_state = VCORE_INACTIVE;
+		} else {
 			kvmppc_run_core(vc);
+		}
 		vc->runner = NULL;
 	}
 
@@ -2032,11 +2234,11 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	}
 
 	atomic_inc(&vcpu->kvm->arch.vcpus_running);
-	/* Order vcpus_running vs. rma_setup_done, see kvmppc_alloc_reset_hpt */
+	/* Order vcpus_running vs. hpte_setup_done, see kvmppc_alloc_reset_hpt */
 	smp_mb();
 
 	/* On the first time here, set up HTAB and VRMA */
-	if (!vcpu->kvm->arch.rma_setup_done) {
+	if (!vcpu->kvm->arch.hpte_setup_done) {
 		r = kvmppc_hv_setup_htab_rma(vcpu);
 		if (r)
 			goto out;
@@ -2238,7 +2440,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 	int srcu_idx;
 
 	mutex_lock(&kvm->lock);
-	if (kvm->arch.rma_setup_done)
+	if (kvm->arch.hpte_setup_done)
 		goto out;	/* another vcpu beat us to it */
 
 	/* Allocate hashed page table (if not done already) and reset it */
@@ -2289,9 +2491,9 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 
 	kvmppc_update_lpcr(kvm, lpcr, LPCR_VRMASD);
 
-	/* Order updates to kvm->arch.lpcr etc. vs. rma_setup_done */
+	/* Order updates to kvm->arch.lpcr etc. vs. hpte_setup_done */
 	smp_wmb();
-	kvm->arch.rma_setup_done = 1;
+	kvm->arch.hpte_setup_done = 1;
 	err = 0;
  out_srcu:
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
@@ -2307,6 +2509,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 static int kvmppc_core_init_vm_hv(struct kvm *kvm)
 {
 	unsigned long lpcr, lpid;
+	char buf[32];
 
 	/* Allocate the guest's logical partition ID */
 
@@ -2347,6 +2550,14 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
 	 */
 	kvm_hv_vm_activated();
 
+	/*
+	 * Create a debugfs directory for the VM
+	 */
+	snprintf(buf, sizeof(buf), "vm%d", current->pid);
+	kvm->arch.debugfs_dir = debugfs_create_dir(buf, kvm_debugfs_dir);
+	if (!IS_ERR_OR_NULL(kvm->arch.debugfs_dir))
+		kvmppc_mmu_debugfs_init(kvm);
+
 	return 0;
 }
 
@@ -2367,6 +2578,8 @@ static void kvmppc_free_vcores(struct kvm *kvm)
 
 static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
 {
+	debugfs_remove_recursive(kvm->arch.debugfs_dir);
+
 	kvm_hv_vm_deactivated();
 
 	kvmppc_free_vcores(kvm);
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 1f083ff8a61a..ed2589d4593f 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -21,6 +21,10 @@
 #include <asm/cputable.h>
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
+#include <asm/archrandom.h>
+#include <asm/xics.h>
+#include <asm/dbell.h>
+#include <asm/cputhreads.h>
 
 #define KVM_CMA_CHUNK_ORDER	18
 
@@ -114,11 +118,11 @@ long int kvmppc_rm_h_confer(struct kvm_vcpu *vcpu, int target,
 	int rv = H_SUCCESS; /* => don't yield */
 
 	set_bit(vcpu->arch.ptid, &vc->conferring_threads);
-	while ((get_tb() < stop) && (VCORE_EXIT_COUNT(vc) == 0)) {
-		threads_running = VCORE_ENTRY_COUNT(vc);
-		threads_ceded = hweight32(vc->napping_threads);
-		threads_conferring = hweight32(vc->conferring_threads);
-		if (threads_ceded + threads_conferring >= threads_running) {
+	while ((get_tb() < stop) && !VCORE_IS_EXITING(vc)) {
+		threads_running = VCORE_ENTRY_MAP(vc);
+		threads_ceded = vc->napping_threads;
+		threads_conferring = vc->conferring_threads;
+		if ((threads_ceded | threads_conferring) == threads_running) {
 			rv = H_TOO_HARD; /* => do yield */
 			break;
 		}
@@ -169,3 +173,89 @@ int kvmppc_hcall_impl_hv_realmode(unsigned long cmd)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(kvmppc_hcall_impl_hv_realmode);
+
+int kvmppc_hwrng_present(void)
+{
+	return powernv_hwrng_present();
+}
+EXPORT_SYMBOL_GPL(kvmppc_hwrng_present);
+
+long kvmppc_h_random(struct kvm_vcpu *vcpu)
+{
+	if (powernv_get_random_real_mode(&vcpu->arch.gpr[4]))
+		return H_SUCCESS;
+
+	return H_HARDWARE;
+}
+
+static inline void rm_writeb(unsigned long paddr, u8 val)
+{
+	__asm__ __volatile__("stbcix %0,0,%1"
+		: : "r" (val), "r" (paddr) : "memory");
+}
+
+/*
+ * Send an interrupt or message to another CPU.
+ * This can only be called in real mode.
+ * The caller needs to include any barrier needed to order writes
+ * to memory vs. the IPI/message.
+ */
+void kvmhv_rm_send_ipi(int cpu)
+{
+	unsigned long xics_phys;
+
+	/* On POWER8 for IPIs to threads in the same core, use msgsnd */
+	if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
+	    cpu_first_thread_sibling(cpu) ==
+	    cpu_first_thread_sibling(raw_smp_processor_id())) {
+		unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
+		msg |= cpu_thread_in_core(cpu);
+		__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
+		return;
+	}
+
+	/* Else poke the target with an IPI */
+	xics_phys = paca[cpu].kvm_hstate.xics_phys;
+	rm_writeb(xics_phys + XICS_MFRR, IPI_PRIORITY);
+}
+
+/*
+ * The following functions are called from the assembly code
+ * in book3s_hv_rmhandlers.S.
+ */
+static void kvmhv_interrupt_vcore(struct kvmppc_vcore *vc, int active)
+{
+	int cpu = vc->pcpu;
+
+	/* Order setting of exit map vs. msgsnd/IPI */
+	smp_mb();
+	for (; active; active >>= 1, ++cpu)
+		if (active & 1)
+			kvmhv_rm_send_ipi(cpu);
+}
+
+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;
+
+	/* Set our bit in the threads-exiting-guest map in the 0xff00
+	   bits of vcore->entry_exit_map */
+	me = 0x100 << ptid;
+	do {
+		ee = vc->entry_exit_map;
+	} while (cmpxchg(&vc->entry_exit_map, ee, ee | me) != ee);
+
+	/* Are we the first here? */
+	if ((ee >> 8) != 0)
+		return;
+
+	/*
+	 * Trigger the other threads in this vcore to exit the guest.
+	 * If this is a hypervisor decrementer interrupt then they
+	 * will be already on their way out of the guest.
+	 */
+	if (trap != BOOK3S_INTERRUPT_HV_DECREMENTER)
+		kvmhv_interrupt_vcore(vc, ee & ~(1 << ptid));
+}
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 625407e4d3b0..f6bf0b1de6d7 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -150,12 +150,6 @@ static pte_t lookup_linux_pte_and_update(pgd_t *pgdir, unsigned long hva,
 	return kvmppc_read_update_linux_pte(ptep, writing, hugepage_shift);
 }
 
-static inline void unlock_hpte(__be64 *hpte, unsigned long hpte_v)
-{
-	asm volatile(PPC_RELEASE_BARRIER "" : : : "memory");
-	hpte[0] = cpu_to_be64(hpte_v);
-}
-
 long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 		       long pte_index, unsigned long pteh, unsigned long ptel,
 		       pgd_t *pgdir, bool realmode, unsigned long *pte_idx_ret)
@@ -271,10 +265,10 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 				u64 pte;
 				while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
 					cpu_relax();
-				pte = be64_to_cpu(*hpte);
+				pte = be64_to_cpu(hpte[0]);
 				if (!(pte & (HPTE_V_VALID | HPTE_V_ABSENT)))
 					break;
-				*hpte &= ~cpu_to_be64(HPTE_V_HVLOCK);
+				__unlock_hpte(hpte, pte);
 				hpte += 2;
 			}
 			if (i == 8)
@@ -290,9 +284,9 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 
 			while (!try_lock_hpte(hpte, HPTE_V_HVLOCK))
 				cpu_relax();
-			pte = be64_to_cpu(*hpte);
+			pte = be64_to_cpu(hpte[0]);
 			if (pte & (HPTE_V_VALID | HPTE_V_ABSENT)) {
-				*hpte &= ~cpu_to_be64(HPTE_V_HVLOCK);
+				__unlock_hpte(hpte, pte);
 				return H_PTEG_FULL;
 			}
 		}
@@ -331,7 +325,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 
 	/* Write the first HPTE dword, unlocking the HPTE and making it valid */
 	eieio();
-	hpte[0] = cpu_to_be64(pteh);
+	__unlock_hpte(hpte, pteh);
 	asm volatile("ptesync" : : : "memory");
 
 	*pte_idx_ret = pte_index;
@@ -412,7 +406,7 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
 	if ((pte & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 ||
 	    ((flags & H_AVPN) && (pte & ~0x7fUL) != avpn) ||
 	    ((flags & H_ANDCOND) && (pte & avpn) != 0)) {
-		hpte[0] &= ~cpu_to_be64(HPTE_V_HVLOCK);
+		__unlock_hpte(hpte, pte);
 		return H_NOT_FOUND;
 	}
 
@@ -548,7 +542,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 				be64_to_cpu(hp[0]), be64_to_cpu(hp[1]));
 			rcbits = rev->guest_rpte & (HPTE_R_R|HPTE_R_C);
 			args[j] |= rcbits << (56 - 5);
-			hp[0] = 0;
+			__unlock_hpte(hp, 0);
 		}
 	}
 
@@ -574,7 +568,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 	pte = be64_to_cpu(hpte[0]);
 	if ((pte & (HPTE_V_ABSENT | HPTE_V_VALID)) == 0 ||
 	    ((flags & H_AVPN) && (pte & ~0x7fUL) != avpn)) {
-		hpte[0] &= ~cpu_to_be64(HPTE_V_HVLOCK);
+		__unlock_hpte(hpte, pte);
 		return H_NOT_FOUND;
 	}
 
@@ -755,8 +749,7 @@ long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr, unsigned long slb_v,
 				/* Return with the HPTE still locked */
 				return (hash << 3) + (i >> 1);
 
-			/* Unlock and move on */
-			hpte[i] = cpu_to_be64(v);
+			__unlock_hpte(&hpte[i], v);
 		}
 
 		if (val & HPTE_V_SECONDARY)
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c
index 7c22997de906..00e45b6d4f24 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xics.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c
@@ -23,17 +23,37 @@
 
 #define DEBUG_PASSUP
 
-static inline void rm_writeb(unsigned long paddr, u8 val)
+static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
+			    u32 new_irq);
+
+/* -- ICS routines -- */
+static void ics_rm_check_resend(struct kvmppc_xics *xics,
+				struct kvmppc_ics *ics, struct kvmppc_icp *icp)
 {
-	__asm__ __volatile__("sync; stbcix %0,0,%1"
-		: : "r" (val), "r" (paddr) : "memory");
+	int i;
+
+	arch_spin_lock(&ics->lock);
+
+	for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
+		struct ics_irq_state *state = &ics->irq_state[i];
+
+		if (!state->resend)
+			continue;
+
+		arch_spin_unlock(&ics->lock);
+		icp_rm_deliver_irq(xics, icp, state->number);
+		arch_spin_lock(&ics->lock);
+	}
+
+	arch_spin_unlock(&ics->lock);
 }
 
+/* -- ICP routines -- */
+
 static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu,
 				struct kvm_vcpu *this_vcpu)
 {
 	struct kvmppc_icp *this_icp = this_vcpu->arch.icp;
-	unsigned long xics_phys;
 	int cpu;
 
 	/* Mark the target VCPU as having an interrupt pending */
@@ -56,9 +76,8 @@ static void icp_rm_set_vcpu_irq(struct kvm_vcpu *vcpu,
 	/* In SMT cpu will always point to thread 0, we adjust it */
 	cpu += vcpu->arch.ptid;
 
-	/* Not too hard, then poke the target */
-	xics_phys = paca[cpu].kvm_hstate.xics_phys;
-	rm_writeb(xics_phys + XICS_MFRR, IPI_PRIORITY);
+	smp_mb();
+	kvmhv_rm_send_ipi(cpu);
 }
 
 static void icp_rm_clr_vcpu_irq(struct kvm_vcpu *vcpu)
@@ -116,6 +135,180 @@ static inline int check_too_hard(struct kvmppc_xics *xics,
 	return (xics->real_mode_dbg || icp->rm_action) ? H_TOO_HARD : H_SUCCESS;
 }
 
+static void icp_rm_check_resend(struct kvmppc_xics *xics,
+			     struct kvmppc_icp *icp)
+{
+	u32 icsid;
+
+	/* Order this load with the test for need_resend in the caller */
+	smp_rmb();
+	for_each_set_bit(icsid, icp->resend_map, xics->max_icsid + 1) {
+		struct kvmppc_ics *ics = xics->ics[icsid];
+
+		if (!test_and_clear_bit(icsid, icp->resend_map))
+			continue;
+		if (!ics)
+			continue;
+		ics_rm_check_resend(xics, ics, icp);
+	}
+}
+
+static bool icp_rm_try_to_deliver(struct kvmppc_icp *icp, u32 irq, u8 priority,
+			       u32 *reject)
+{
+	union kvmppc_icp_state old_state, new_state;
+	bool success;
+
+	do {
+		old_state = new_state = READ_ONCE(icp->state);
+
+		*reject = 0;
+
+		/* See if we can deliver */
+		success = new_state.cppr > priority &&
+			new_state.mfrr > priority &&
+			new_state.pending_pri > priority;
+
+		/*
+		 * If we can, check for a rejection and perform the
+		 * delivery
+		 */
+		if (success) {
+			*reject = new_state.xisr;
+			new_state.xisr = irq;
+			new_state.pending_pri = priority;
+		} else {
+			/*
+			 * If we failed to deliver we set need_resend
+			 * so a subsequent CPPR state change causes us
+			 * to try a new delivery.
+			 */
+			new_state.need_resend = true;
+		}
+
+	} while (!icp_rm_try_update(icp, old_state, new_state));
+
+	return success;
+}
+
+static void icp_rm_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
+			    u32 new_irq)
+{
+	struct ics_irq_state *state;
+	struct kvmppc_ics *ics;
+	u32 reject;
+	u16 src;
+
+	/*
+	 * This is used both for initial delivery of an interrupt and
+	 * for subsequent rejection.
+	 *
+	 * Rejection can be racy vs. resends. We have evaluated the
+	 * rejection in an atomic ICP transaction which is now complete,
+	 * so potentially the ICP can already accept the interrupt again.
+	 *
+	 * So we need to retry the delivery. Essentially the reject path
+	 * boils down to a failed delivery. Always.
+	 *
+	 * Now the interrupt could also have moved to a different target,
+	 * thus we may need to re-do the ICP lookup as well
+	 */
+
+ again:
+	/* Get the ICS state and lock it */
+	ics = kvmppc_xics_find_ics(xics, new_irq, &src);
+	if (!ics) {
+		/* Unsafe increment, but this does not need to be accurate */
+		xics->err_noics++;
+		return;
+	}
+	state = &ics->irq_state[src];
+
+	/* Get a lock on the ICS */
+	arch_spin_lock(&ics->lock);
+
+	/* Get our server */
+	if (!icp || state->server != icp->server_num) {
+		icp = kvmppc_xics_find_server(xics->kvm, state->server);
+		if (!icp) {
+			/* Unsafe increment again*/
+			xics->err_noicp++;
+			goto out;
+		}
+	}
+
+	/* Clear the resend bit of that interrupt */
+	state->resend = 0;
+
+	/*
+	 * If masked, bail out
+	 *
+	 * Note: PAPR doesn't mention anything about masked pending
+	 * when doing a resend, only when doing a delivery.
+	 *
+	 * However that would have the effect of losing a masked
+	 * interrupt that was rejected and isn't consistent with
+	 * the whole masked_pending business which is about not
+	 * losing interrupts that occur while masked.
+	 *
+	 * I don't differentiate normal deliveries and resends, this
+	 * implementation will differ from PAPR and not lose such
+	 * interrupts.
+	 */
+	if (state->priority == MASKED) {
+		state->masked_pending = 1;
+		goto out;
+	}
+
+	/*
+	 * Try the delivery, this will set the need_resend flag
+	 * in the ICP as part of the atomic transaction if the
+	 * delivery is not possible.
+	 *
+	 * Note that if successful, the new delivery might have itself
+	 * rejected an interrupt that was "delivered" before we took the
+	 * ics spin lock.
+	 *
+	 * In this case we do the whole sequence all over again for the
+	 * new guy. We cannot assume that the rejected interrupt is less
+	 * favored than the new one, and thus doesn't need to be delivered,
+	 * because by the time we exit icp_rm_try_to_deliver() the target
+	 * processor may well have already consumed & completed it, and thus
+	 * the rejected interrupt might actually be already acceptable.
+	 */
+	if (icp_rm_try_to_deliver(icp, new_irq, state->priority, &reject)) {
+		/*
+		 * Delivery was successful, did we reject somebody else ?
+		 */
+		if (reject && reject != XICS_IPI) {
+			arch_spin_unlock(&ics->lock);
+			new_irq = reject;
+			goto again;
+		}
+	} else {
+		/*
+		 * We failed to deliver the interrupt we need to set the
+		 * resend map bit and mark the ICS state as needing a resend
+		 */
+		set_bit(ics->icsid, icp->resend_map);
+		state->resend = 1;
+
+		/*
+		 * If the need_resend flag got cleared in the ICP some time
+		 * between icp_rm_try_to_deliver() atomic update and now, then
+		 * we know it might have missed the resend_map bit. So we
+		 * retry
+		 */
+		smp_mb();
+		if (!icp->state.need_resend) {
+			arch_spin_unlock(&ics->lock);
+			goto again;
+		}
+	}
+ out:
+	arch_spin_unlock(&ics->lock);
+}
+
 static void icp_rm_down_cppr(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
 			     u8 new_cppr)
 {
@@ -184,8 +377,8 @@ static void icp_rm_down_cppr(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
 	 * separately here as well.
 	 */
 	if (resend) {
-		icp->rm_action |= XICS_RM_CHECK_RESEND;
-		icp->rm_resend_icp = icp;
+		icp->n_check_resend++;
+		icp_rm_check_resend(xics, icp);
 	}
 }
 
@@ -300,16 +493,16 @@ int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
 		}
 	} while (!icp_rm_try_update(icp, old_state, new_state));
 
-	/* Pass rejects to virtual mode */
+	/* Handle reject in real mode */
 	if (reject && reject != XICS_IPI) {
-		this_icp->rm_action |= XICS_RM_REJECT;
-		this_icp->rm_reject = reject;
+		this_icp->n_reject++;
+		icp_rm_deliver_irq(xics, icp, reject);
 	}
 
-	/* Pass resends to virtual mode */
+	/* Handle resends in real mode */
 	if (resend) {
-		this_icp->rm_action |= XICS_RM_CHECK_RESEND;
-		this_icp->rm_resend_icp = icp;
+		this_icp->n_check_resend++;
+		icp_rm_check_resend(xics, icp);
 	}
 
 	return check_too_hard(xics, this_icp);
@@ -365,10 +558,13 @@ int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr)
 
 	} while (!icp_rm_try_update(icp, old_state, new_state));
 
-	/* Pass rejects to virtual mode */
+	/*
+	 * Check for rejects. They are handled by doing a new delivery
+	 * attempt (see comments in icp_rm_deliver_irq).
+	 */
 	if (reject && reject != XICS_IPI) {
-		icp->rm_action |= XICS_RM_REJECT;
-		icp->rm_reject = reject;
+		icp->n_reject++;
+		icp_rm_deliver_irq(xics, icp, reject);
 	}
  bail:
 	return check_too_hard(xics, icp);
@@ -416,10 +612,10 @@ int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
 		goto bail;
 	state = &ics->irq_state[src];
 
-	/* Still asserted, resend it, we make it look like a reject */
+	/* Still asserted, resend it */
 	if (state->asserted) {
-		icp->rm_action |= XICS_RM_REJECT;
-		icp->rm_reject = irq;
+		icp->n_reject++;
+		icp_rm_deliver_irq(xics, icp, irq);
 	}
 
 	if (!hlist_empty(&vcpu->kvm->irq_ack_notifier_list)) {
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 6cbf1630cb70..4d70df26c402 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -172,6 +172,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
 kvmppc_primary_no_guest:
 	/* We handle this much like a ceded vcpu */
+	/* put the HDEC into the DEC, since HDEC interrupts don't wake us */
+	mfspr	r3, SPRN_HDEC
+	mtspr	SPRN_DEC, r3
+	/*
+	 * Make sure the primary has finished the MMU switch.
+	 * We should never get here on a secondary thread, but
+	 * check it for robustness' sake.
+	 */
+	ld	r5, HSTATE_KVM_VCORE(r13)
+65:	lbz	r0, VCORE_IN_GUEST(r5)
+	cmpwi	r0, 0
+	beq	65b
+	/* Set LPCR. */
+	ld	r8,VCORE_LPCR(r5)
+	mtspr	SPRN_LPCR,r8
+	isync
 	/* set our bit in napping_threads */
 	ld	r5, HSTATE_KVM_VCORE(r13)
 	lbz	r7, HSTATE_PTID(r13)
@@ -182,7 +198,7 @@ kvmppc_primary_no_guest:
 	or	r3, r3, r0
 	stwcx.	r3, 0, r6
 	bne	1b
-	/* order napping_threads update vs testing entry_exit_count */
+	/* order napping_threads update vs testing entry_exit_map */
 	isync
 	li	r12, 0
 	lwz	r7, VCORE_ENTRY_EXIT(r5)
@@ -191,6 +207,7 @@ kvmppc_primary_no_guest:
 	li	r3, NAPPING_NOVCPU
 	stb	r3, HSTATE_NAPPING(r13)
 
+	li	r3, 0		/* Don't wake on privileged (OS) doorbell */
 	b	kvm_do_nap
 
 kvm_novcpu_wakeup:
@@ -202,7 +219,7 @@ kvm_novcpu_wakeup:
 
 	/* check the wake reason */
 	bl	kvmppc_check_wake_reason
-	
+
 	/* see if any other thread is already exiting */
 	lwz	r0, VCORE_ENTRY_EXIT(r5)
 	cmpwi	r0, 0x100
@@ -222,13 +239,37 @@ kvm_novcpu_wakeup:
 	cmpdi	r3, 0
 	bge	kvm_novcpu_exit
 
+	/* See if our timeslice has expired (HDEC is negative) */
+	mfspr	r0, SPRN_HDEC
+	li	r12, BOOK3S_INTERRUPT_HV_DECREMENTER
+	cmpwi	r0, 0
+	blt	kvm_novcpu_exit
+
 	/* Got an IPI but other vcpus aren't yet exiting, must be a latecomer */
 	ld	r4, HSTATE_KVM_VCPU(r13)
 	cmpdi	r4, 0
-	bne	kvmppc_got_guest
+	beq	kvmppc_primary_no_guest
+
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+	addi	r3, r4, VCPU_TB_RMENTRY
+	bl	kvmhv_start_timing
+#endif
+	b	kvmppc_got_guest
 
 kvm_novcpu_exit:
-	b	hdec_soon
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+	ld	r4, HSTATE_KVM_VCPU(r13)
+	cmpdi	r4, 0
+	beq	13f
+	addi	r3, r4, VCPU_TB_RMEXIT
+	bl	kvmhv_accumulate_time
+#endif
+13:	mr	r3, r12
+	stw	r12, 112-4(r1)
+	bl	kvmhv_commence_exit
+	nop
+	lwz	r12, 112-4(r1)
+	b	kvmhv_switch_to_host
 
 /*
  * We come in here when wakened from nap mode.
@@ -239,9 +280,9 @@ kvm_novcpu_exit:
 kvm_start_guest:
 
 	/* Set runlatch bit the minute you wake up from nap */
-	mfspr	r1, SPRN_CTRLF
-	ori 	r1, r1, 1
-	mtspr	SPRN_CTRLT, r1
+	mfspr	r0, SPRN_CTRLF
+	ori 	r0, r0, 1
+	mtspr	SPRN_CTRLT, r0
 
 	ld	r2,PACATOC(r13)
 
@@ -286,26 +327,21 @@ kvm_secondary_got_guest:
 	ld	r6, PACA_DSCR(r13)
 	std	r6, HSTATE_DSCR(r13)
 
+	/* Order load of vcore, ptid etc. after load of vcpu */
+	lwsync
 	bl	kvmppc_hv_entry
 
 	/* Back from the guest, go back to nap */
 	/* Clear our vcpu pointer so we don't come back in early */
 	li	r0, 0
-	std	r0, HSTATE_KVM_VCPU(r13)
 	/*
-	 * Make sure we clear HSTATE_KVM_VCPU(r13) before incrementing
-	 * the nap_count, because once the increment to nap_count is
-	 * visible we could be given another vcpu.
+	 * Once we clear HSTATE_KVM_VCPU(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
-
-	/* increment the nap count and then go to nap mode */
-	ld	r4, HSTATE_KVM_VCORE(r13)
-	addi	r4, r4, VCORE_NAP_COUNT
-51:	lwarx	r3, 0, r4
-	addi	r3, r3, 1
-	stwcx.	r3, 0, r4
-	bne	51b
+	std	r0, HSTATE_KVM_VCPU(r13)
 
 /*
  * At this point we have finished executing in the guest.
@@ -376,6 +412,14 @@ kvmppc_hv_entry:
 	li	r6, KVM_GUEST_MODE_HOST_HV
 	stb	r6, HSTATE_IN_GUEST(r13)
 
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+	/* Store initial timestamp */
+	cmpdi	r4, 0
+	beq	1f
+	addi	r3, r4, VCPU_TB_RMENTRY
+	bl	kvmhv_start_timing
+1:
+#endif
 	/* Clear out SLB */
 	li	r6,0
 	slbmte	r6,r6
@@ -387,21 +431,23 @@ kvmppc_hv_entry:
 	 * We don't have to lock against concurrent tlbies,
 	 * but we do have to coordinate across hardware threads.
 	 */
-	/* Increment entry count iff exit count is zero. */
-	ld	r5,HSTATE_KVM_VCORE(r13)
-	addi	r9,r5,VCORE_ENTRY_EXIT
-21:	lwarx	r3,0,r9
-	cmpwi	r3,0x100		/* any threads starting to exit? */
+	/* Set bit in entry map iff exit map is zero. */
+	ld	r5, HSTATE_KVM_VCORE(r13)
+	li	r7, 1
+	lbz	r6, HSTATE_PTID(r13)
+	sld	r7, r7, r6
+	addi	r9, r5, VCORE_ENTRY_EXIT
+21:	lwarx	r3, 0, r9
+	cmpwi	r3, 0x100		/* any threads starting to exit? */
 	bge	secondary_too_late	/* if so we're too late to the party */
-	addi	r3,r3,1
-	stwcx.	r3,0,r9
+	or	r3, r3, r7
+	stwcx.	r3, 0, r9
 	bne	21b
 
 	/* Primary thread switches to guest partition. */
 	ld	r9,VCORE_KVM(r5)	/* pointer to struct kvm */
-	lbz	r6,HSTATE_PTID(r13)
 	cmpwi	r6,0
-	bne	20f
+	bne	10f
 	ld	r6,KVM_SDR1(r9)
 	lwz	r7,KVM_LPID(r9)
 	li	r0,LPID_RSVD		/* switch to reserved LPID */
@@ -472,28 +518,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
 	li	r0,1
 	stb	r0,VCORE_IN_GUEST(r5)	/* signal secondaries to continue */
-	b	10f
-
-	/* Secondary threads wait for primary to have done partition switch */
-20:	lbz	r0,VCORE_IN_GUEST(r5)
-	cmpwi	r0,0
-	beq	20b
-
-	/* Set LPCR and RMOR. */
-10:	ld	r8,VCORE_LPCR(r5)
-	mtspr	SPRN_LPCR,r8
-	ld	r8,KVM_RMOR(r9)
-	mtspr	SPRN_RMOR,r8
-	isync
-
-	/* Check if HDEC expires soon */
-	mfspr	r3,SPRN_HDEC
-	cmpwi	r3,512		/* 1 microsecond */
-	li	r12,BOOK3S_INTERRUPT_HV_DECREMENTER
-	blt	hdec_soon
 
 	/* Do we have a guest vcpu to run? */
-	cmpdi	r4, 0
+10:	cmpdi	r4, 0
 	beq	kvmppc_primary_no_guest
 kvmppc_got_guest:
 
@@ -818,6 +845,30 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	clrrdi	r6,r6,1
 	mtspr	SPRN_CTRLT,r6
 4:
+	/* Secondary threads wait for primary to have done partition switch */
+	ld	r5, HSTATE_KVM_VCORE(r13)
+	lbz	r6, HSTATE_PTID(r13)
+	cmpwi	r6, 0
+	beq	21f
+	lbz	r0, VCORE_IN_GUEST(r5)
+	cmpwi	r0, 0
+	bne	21f
+	HMT_LOW
+20:	lbz	r0, VCORE_IN_GUEST(r5)
+	cmpwi	r0, 0
+	beq	20b
+	HMT_MEDIUM
+21:
+	/* Set LPCR. */
+	ld	r8,VCORE_LPCR(r5)
+	mtspr	SPRN_LPCR,r8
+	isync
+
+	/* Check if HDEC expires soon */
+	mfspr	r3, SPRN_HDEC
+	cmpwi	r3, 512		/* 1 microsecond */
+	blt	hdec_soon
+
 	ld	r6, VCPU_CTR(r4)
 	lwz	r7, VCPU_XER(r4)
 
@@ -880,6 +931,12 @@ fast_guest_return:
 	li	r9, KVM_GUEST_MODE_GUEST_HV
 	stb	r9, HSTATE_IN_GUEST(r13)
 
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+	/* Accumulate timing */
+	addi	r3, r4, VCPU_TB_GUEST
+	bl	kvmhv_accumulate_time
+#endif
+
 	/* Enter guest */
 
 BEGIN_FTR_SECTION
@@ -917,6 +974,27 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	hrfid
 	b	.
 
+secondary_too_late:
+	li	r12, 0
+	cmpdi	r4, 0
+	beq	11f
+	stw	r12, VCPU_TRAP(r4)
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+	addi	r3, r4, VCPU_TB_RMEXIT
+	bl	kvmhv_accumulate_time
+#endif
+11:	b	kvmhv_switch_to_host
+
+hdec_soon:
+	li	r12, BOOK3S_INTERRUPT_HV_DECREMENTER
+	stw	r12, VCPU_TRAP(r4)
+	mr	r9, r4
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+	addi	r3, r4, VCPU_TB_RMEXIT
+	bl	kvmhv_accumulate_time
+#endif
+	b	guest_exit_cont
+
 /******************************************************************************
  *                                                                            *
  *                               Exit code                                    *
@@ -1002,6 +1080,16 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 
 	stw	r12,VCPU_TRAP(r9)
 
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+	addi	r3, r9, VCPU_TB_RMINTR
+	mr	r4, r9
+	bl	kvmhv_accumulate_time
+	ld	r5, VCPU_GPR(R5)(r9)
+	ld	r6, VCPU_GPR(R6)(r9)
+	ld	r7, VCPU_GPR(R7)(r9)
+	ld	r8, VCPU_GPR(R8)(r9)
+#endif
+
 	/* Save HEIR (HV emulation assist reg) in emul_inst
 	   if this is an HEI (HV emulation interrupt, e40) */
 	li	r3,KVM_INST_FETCH_FAILED
@@ -1028,34 +1116,37 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	bne	2f
 	mfspr	r3,SPRN_HDEC
 	cmpwi	r3,0
-	bge	ignore_hdec
+	mr	r4,r9
+	bge	fast_guest_return
 2:
 	/* See if this is an hcall we can handle in real mode */
 	cmpwi	r12,BOOK3S_INTERRUPT_SYSCALL
 	beq	hcall_try_real_mode
 
+	/* Hypervisor doorbell - exit only if host IPI flag set */
+	cmpwi	r12, BOOK3S_INTERRUPT_H_DOORBELL
+	bne	3f
+	lbz	r0, HSTATE_HOST_IPI(r13)
+	beq	4f
+	b	guest_exit_cont
+3:
 	/* External interrupt ? */
 	cmpwi	r12, BOOK3S_INTERRUPT_EXTERNAL
-	bne+	ext_interrupt_to_host
+	bne+	guest_exit_cont
 
 	/* External interrupt, first check for host_ipi. If this is
 	 * set, we know the host wants us out so let's do it now
 	 */
 	bl	kvmppc_read_intr
 	cmpdi	r3, 0
-	bgt	ext_interrupt_to_host
+	bgt	guest_exit_cont
 
 	/* Check if any CPU is heading out to the host, if so head out too */
-	ld	r5, HSTATE_KVM_VCORE(r13)
+4:	ld	r5, HSTATE_KVM_VCORE(r13)
 	lwz	r0, VCORE_ENTRY_EXIT(r5)
 	cmpwi	r0, 0x100
-	bge	ext_interrupt_to_host
-
-	/* Return to guest after delivering any pending interrupt */
 	mr	r4, r9
-	b	deliver_guest_interrupt
-
-ext_interrupt_to_host:
+	blt	deliver_guest_interrupt
 
 guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
 	/* Save more register state  */
@@ -1065,7 +1156,7 @@ guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
 	stw	r7, VCPU_DSISR(r9)
 	/* don't overwrite fault_dar/fault_dsisr if HDSI */
 	cmpwi	r12,BOOK3S_INTERRUPT_H_DATA_STORAGE
-	beq	6f
+	beq	mc_cont
 	std	r6, VCPU_FAULT_DAR(r9)
 	stw	r7, VCPU_FAULT_DSISR(r9)
 
@@ -1073,9 +1164,20 @@ guest_exit_cont:		/* r9 = vcpu, r12 = trap, r13 = paca */
 	cmpwi	r12, BOOK3S_INTERRUPT_MACHINE_CHECK
 	beq	machine_check_realmode
 mc_cont:
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+	addi	r3, r9, VCPU_TB_RMEXIT
+	mr	r4, r9
+	bl	kvmhv_accumulate_time
+#endif
+
+	/* Increment exit count, poke other threads to exit */
+	bl	kvmhv_commence_exit
+	nop
+	ld	r9, HSTATE_KVM_VCPU(r13)
+	lwz	r12, VCPU_TRAP(r9)
 
 	/* Save guest CTRL register, set runlatch to 1 */
-6:	mfspr	r6,SPRN_CTRLF
+	mfspr	r6,SPRN_CTRLF
 	stw	r6,VCPU_CTRL(r9)
 	andi.	r0,r6,1
 	bne	4f
@@ -1417,68 +1519,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	slbia
 	ptesync
 
-hdec_soon:			/* r12 = trap, r13 = paca */
 	/*
 	 * POWER7/POWER8 guest -> host partition switch code.
 	 * We don't have to lock against tlbies but we do
 	 * have to coordinate the hardware threads.
 	 */
-	/* Increment the threads-exiting-guest count in the 0xff00
-	   bits of vcore->entry_exit_count */
-	ld	r5,HSTATE_KVM_VCORE(r13)
-	addi	r6,r5,VCORE_ENTRY_EXIT
-41:	lwarx	r3,0,r6
-	addi	r0,r3,0x100
-	stwcx.	r0,0,r6
-	bne	41b
-	isync		/* order stwcx. vs. reading napping_threads */
-
-	/*
-	 * At this point we have an interrupt that we have to pass
-	 * up to the kernel or qemu; we can't handle it in real mode.
-	 * Thus we have to do a partition switch, so we have to
-	 * collect the other threads, if we are the first thread
-	 * to take an interrupt.  To do this, we set the HDEC to 0,
-	 * which causes an HDEC interrupt in all threads within 2ns
-	 * because the HDEC register is shared between all 4 threads.
-	 * However, we don't need to bother if this is an HDEC
-	 * interrupt, since the other threads will already be on their
-	 * way here in that case.
-	 */
-	cmpwi	r3,0x100	/* Are we the first here? */
-	bge	43f
-	cmpwi	r12,BOOK3S_INTERRUPT_HV_DECREMENTER
-	beq	40f
-	li	r0,0
-	mtspr	SPRN_HDEC,r0
-40:
-	/*
-	 * Send an IPI to any napping threads, since an HDEC interrupt
-	 * doesn't wake CPUs up from nap.
-	 */
-	lwz	r3,VCORE_NAPPING_THREADS(r5)
-	lbz	r4,HSTATE_PTID(r13)
-	li	r0,1
-	sld	r0,r0,r4
-	andc.	r3,r3,r0		/* no sense IPI'ing ourselves */
-	beq	43f
-	/* Order entry/exit update vs. IPIs */
-	sync
-	mulli	r4,r4,PACA_SIZE		/* get paca for thread 0 */
-	subf	r6,r4,r13
-42:	andi.	r0,r3,1
-	beq	44f
-	ld	r8,HSTATE_XICS_PHYS(r6)	/* get thread's XICS reg addr */
-	li	r0,IPI_PRIORITY
-	li	r7,XICS_MFRR
-	stbcix	r0,r7,r8		/* trigger the IPI */
-44:	srdi.	r3,r3,1
-	addi	r6,r6,PACA_SIZE
-	bne	42b
-
-secondary_too_late:
+kvmhv_switch_to_host:
 	/* Secondary threads wait for primary to do partition switch */
-43:	ld	r5,HSTATE_KVM_VCORE(r13)
+	ld	r5,HSTATE_KVM_VCORE(r13)
 	ld	r4,VCORE_KVM(r5)	/* pointer to struct kvm */
 	lbz	r3,HSTATE_PTID(r13)
 	cmpwi	r3,0
@@ -1562,6 +1610,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 1:	addi	r8,r8,16
 	.endr
 
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+	/* Finish timing, if we have a vcpu */
+	ld	r4, HSTATE_KVM_VCPU(r13)
+	cmpdi	r4, 0
+	li	r3, 0
+	beq	2f
+	bl	kvmhv_accumulate_time
+2:
+#endif
 	/* Unset guest mode */
 	li	r0, KVM_GUEST_MODE_NONE
 	stb	r0, HSTATE_IN_GUEST(r13)
@@ -1696,8 +1753,10 @@ kvmppc_hisi:
  * Returns to the guest if we handle it, or continues on up to
  * the kernel if we can't (i.e. if we don't have a handler for
  * it, or if the handler returns H_TOO_HARD).
+ *
+ * r5 - r8 contain hcall args,
+ * r9 = vcpu, r10 = pc, r11 = msr, r12 = trap, r13 = paca
  */
-	.globl	hcall_try_real_mode
 hcall_try_real_mode:
 	ld	r3,VCPU_GPR(R3)(r9)
 	andi.	r0,r11,MSR_PR
@@ -1839,13 +1898,124 @@ hcall_real_table:
 	.long	0		/* 0x12c */
 	.long	0		/* 0x130 */
 	.long	DOTSYM(kvmppc_h_set_xdabr) - hcall_real_table
+	.long	0		/* 0x138 */
+	.long	0		/* 0x13c */
+	.long	0		/* 0x140 */
+	.long	0		/* 0x144 */
+	.long	0		/* 0x148 */
+	.long	0		/* 0x14c */
+	.long	0		/* 0x150 */
+	.long	0		/* 0x154 */
+	.long	0		/* 0x158 */
+	.long	0		/* 0x15c */
+	.long	0		/* 0x160 */
+	.long	0		/* 0x164 */
+	.long	0		/* 0x168 */
+	.long	0		/* 0x16c */
+	.long	0		/* 0x170 */
+	.long	0		/* 0x174 */
+	.long	0		/* 0x178 */
+	.long	0		/* 0x17c */
+	.long	0		/* 0x180 */
+	.long	0		/* 0x184 */
+	.long	0		/* 0x188 */
+	.long	0		/* 0x18c */
+	.long	0		/* 0x190 */
+	.long	0		/* 0x194 */
+	.long	0		/* 0x198 */
+	.long	0		/* 0x19c */
+	.long	0		/* 0x1a0 */
+	.long	0		/* 0x1a4 */
+	.long	0		/* 0x1a8 */
+	.long	0		/* 0x1ac */
+	.long	0		/* 0x1b0 */
+	.long	0		/* 0x1b4 */
+	.long	0		/* 0x1b8 */
+	.long	0		/* 0x1bc */
+	.long	0		/* 0x1c0 */
+	.long	0		/* 0x1c4 */
+	.long	0		/* 0x1c8 */
+	.long	0		/* 0x1cc */
+	.long	0		/* 0x1d0 */
+	.long	0		/* 0x1d4 */
+	.long	0		/* 0x1d8 */
+	.long	0		/* 0x1dc */
+	.long	0		/* 0x1e0 */
+	.long	0		/* 0x1e4 */
+	.long	0		/* 0x1e8 */
+	.long	0		/* 0x1ec */
+	.long	0		/* 0x1f0 */
+	.long	0		/* 0x1f4 */
+	.long	0		/* 0x1f8 */
+	.long	0		/* 0x1fc */
+	.long	0		/* 0x200 */
+	.long	0		/* 0x204 */
+	.long	0		/* 0x208 */
+	.long	0		/* 0x20c */
+	.long	0		/* 0x210 */
+	.long	0		/* 0x214 */
+	.long	0		/* 0x218 */
+	.long	0		/* 0x21c */
+	.long	0		/* 0x220 */
+	.long	0		/* 0x224 */
+	.long	0		/* 0x228 */
+	.long	0		/* 0x22c */
+	.long	0		/* 0x230 */
+	.long	0		/* 0x234 */
+	.long	0		/* 0x238 */
+	.long	0		/* 0x23c */
+	.long	0		/* 0x240 */
+	.long	0		/* 0x244 */
+	.long	0		/* 0x248 */
+	.long	0		/* 0x24c */
+	.long	0		/* 0x250 */
+	.long	0		/* 0x254 */
+	.long	0		/* 0x258 */
+	.long	0		/* 0x25c */
+	.long	0		/* 0x260 */
+	.long	0		/* 0x264 */
+	.long	0		/* 0x268 */
+	.long	0		/* 0x26c */
+	.long	0		/* 0x270 */
+	.long	0		/* 0x274 */
+	.long	0		/* 0x278 */
+	.long	0		/* 0x27c */
+	.long	0		/* 0x280 */
+	.long	0		/* 0x284 */
+	.long	0		/* 0x288 */
+	.long	0		/* 0x28c */
+	.long	0		/* 0x290 */
+	.long	0		/* 0x294 */
+	.long	0		/* 0x298 */
+	.long	0		/* 0x29c */
+	.long	0		/* 0x2a0 */
+	.long	0		/* 0x2a4 */
+	.long	0		/* 0x2a8 */
+	.long	0		/* 0x2ac */
+	.long	0		/* 0x2b0 */
+	.long	0		/* 0x2b4 */
+	.long	0		/* 0x2b8 */
+	.long	0		/* 0x2bc */
+	.long	0		/* 0x2c0 */
+	.long	0		/* 0x2c4 */
+	.long	0		/* 0x2c8 */
+	.long	0		/* 0x2cc */
+	.long	0		/* 0x2d0 */
+	.long	0		/* 0x2d4 */
+	.long	0		/* 0x2d8 */
+	.long	0		/* 0x2dc */
+	.long	0		/* 0x2e0 */
+	.long	0		/* 0x2e4 */
+	.long	0		/* 0x2e8 */
+	.long	0		/* 0x2ec */
+	.long	0		/* 0x2f0 */
+	.long	0		/* 0x2f4 */
+	.long	0		/* 0x2f8 */
+	.long	0		/* 0x2fc */
+	.long	DOTSYM(kvmppc_h_random) - hcall_real_table
 	.globl	hcall_real_table_end
 hcall_real_table_end:
 
-ignore_hdec:
-	mr	r4,r9
-	b	fast_guest_return
-
 _GLOBAL(kvmppc_h_set_xdabr)
 	andi.	r0, r5, DABRX_USER | DABRX_KERNEL
 	beq	6f
@@ -1884,7 +2054,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	li	r3, 0
 	blr
 
-_GLOBAL(kvmppc_h_cede)
+_GLOBAL(kvmppc_h_cede)		/* r3 = vcpu pointer, r11 = msr, r13 = paca */
 	ori	r11,r11,MSR_EE
 	std	r11,VCPU_MSR(r3)
 	li	r0,1
@@ -1893,8 +2063,8 @@ _GLOBAL(kvmppc_h_cede)
 	lbz	r5,VCPU_PRODDED(r3)
 	cmpwi	r5,0
 	bne	kvm_cede_prodded
-	li	r0,0		/* set trap to 0 to say hcall is handled */
-	stw	r0,VCPU_TRAP(r3)
+	li	r12,0		/* set trap to 0 to say hcall is handled */
+	stw	r12,VCPU_TRAP(r3)
 	li	r0,H_SUCCESS
 	std	r0,VCPU_GPR(R3)(r3)
 
@@ -1912,12 +2082,11 @@ _GLOBAL(kvmppc_h_cede)
 	addi	r6,r5,VCORE_NAPPING_THREADS
 31:	lwarx	r4,0,r6
 	or	r4,r4,r0
-	PPC_POPCNTW(R7,R4)
-	cmpw	r7,r8
-	bge	kvm_cede_exit
+	cmpw	r4,r8
+	beq	kvm_cede_exit
 	stwcx.	r4,0,r6
 	bne	31b
-	/* order napping_threads update vs testing entry_exit_count */
+	/* order napping_threads update vs testing entry_exit_map */
 	isync
 	li	r0,NAPPING_CEDE
 	stb	r0,HSTATE_NAPPING(r13)
@@ -1955,21 +2124,52 @@ _GLOBAL(kvmppc_h_cede)
 	bl	kvmppc_save_fp
 
 	/*
+	 * Set DEC to the smaller of DEC and HDEC, so that we wake
+	 * no later than the end of our timeslice (HDEC interrupts
+	 * don't wake us from nap).
+	 */
+	mfspr	r3, SPRN_DEC
+	mfspr	r4, SPRN_HDEC
+	mftb	r5
+	cmpw	r3, r4
+	ble	67f
+	mtspr	SPRN_DEC, r4
+67:
+	/* save expiry time of guest decrementer */
+	extsw	r3, r3
+	add	r3, r3, r5
+	ld	r4, HSTATE_KVM_VCPU(r13)
+	ld	r5, HSTATE_KVM_VCORE(r13)
+	ld	r6, VCORE_TB_OFFSET(r5)
+	subf	r3, r6, r3	/* convert to host TB value */
+	std	r3, VCPU_DEC_EXPIRES(r4)
+
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+	ld	r4, HSTATE_KVM_VCPU(r13)
+	addi	r3, r4, VCPU_TB_CEDE
+	bl	kvmhv_accumulate_time
+#endif
+
+	lis	r3, LPCR_PECEDP@h	/* Do wake on privileged doorbell */
+
+	/*
 	 * Take a nap until a decrementer or external or doobell interrupt
-	 * occurs, with PECE1, PECE0 and PECEDP set in LPCR. Also clear the
-	 * runlatch bit before napping.
+	 * occurs, with PECE1 and PECE0 set in LPCR.
+	 * On POWER8, set PECEDH, and if we are ceding, also set PECEDP.
+	 * Also clear the runlatch bit before napping.
 	 */
 kvm_do_nap:
-	mfspr	r2, SPRN_CTRLF
-	clrrdi	r2, r2, 1
-	mtspr	SPRN_CTRLT, r2
+	mfspr	r0, SPRN_CTRLF
+	clrrdi	r0, r0, 1
+	mtspr	SPRN_CTRLT, r0
 
 	li	r0,1
 	stb	r0,HSTATE_HWTHREAD_REQ(r13)
 	mfspr	r5,SPRN_LPCR
 	ori	r5,r5,LPCR_PECE0 | LPCR_PECE1
 BEGIN_FTR_SECTION
-	oris	r5,r5,LPCR_PECEDP@h
+	ori	r5, r5, LPCR_PECEDH
+	rlwimi	r5, r3, 0, LPCR_PECEDP
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	mtspr	SPRN_LPCR,r5
 	isync
@@ -1994,9 +2194,23 @@ kvm_end_cede:
 	/* Woken by external or decrementer interrupt */
 	ld	r1, HSTATE_HOST_R1(r13)
 
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+	addi	r3, r4, VCPU_TB_RMINTR
+	bl	kvmhv_accumulate_time
+#endif
+
 	/* load up FP state */
 	bl	kvmppc_load_fp
 
+	/* Restore guest decrementer */
+	ld	r3, VCPU_DEC_EXPIRES(r4)
+	ld	r5, HSTATE_KVM_VCORE(r13)
+	ld	r6, VCORE_TB_OFFSET(r5)
+	add	r3, r3, r6	/* convert host TB to guest TB value */
+	mftb	r7
+	subf	r3, r7, r3
+	mtspr	SPRN_DEC, r3
+
 	/* Load NV GPRS */
 	ld	r14, VCPU_GPR(R14)(r4)
 	ld	r15, VCPU_GPR(R15)(r4)
@@ -2057,7 +2271,8 @@ kvm_cede_prodded:
 
 	/* we've ceded but we want to give control to the host */
 kvm_cede_exit:
-	b	hcall_real_fallback
+	ld	r9, HSTATE_KVM_VCPU(r13)
+	b	guest_exit_cont
 
 	/* Try to handle a machine check in real mode */
 machine_check_realmode:
@@ -2089,13 +2304,14 @@ machine_check_realmode:
 
 /*
  * Check the reason we woke from nap, and take appropriate action.
- * Returns:
+ * Returns (in r3):
  *	0 if nothing needs to be done
  *	1 if something happened that needs to be handled by the host
- *	-1 if there was a guest wakeup (IPI)
+ *	-1 if there was a guest wakeup (IPI or msgsnd)
  *
  * Also sets r12 to the interrupt vector for any interrupt that needs
  * to be handled now by the host (0x500 for external interrupt), or zero.
+ * Modifies r0, r6, r7, r8.
  */
 kvmppc_check_wake_reason:
 	mfspr	r6, SPRN_SRR1
@@ -2122,7 +2338,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
 	/* hypervisor doorbell */
 3:	li	r12, BOOK3S_INTERRUPT_H_DOORBELL
+	/* see if it's a host IPI */
 	li	r3, 1
+	lbz	r0, HSTATE_HOST_IPI(r13)
+	cmpwi	r0, 0
+	bnelr
+	/* if not, clear it and return -1 */
+	lis	r6, (PPC_DBELL_SERVER << (63-36))@h
+	PPC_MSGCLR(6)
+	li	r3, -1
 	blr
 
 /*
@@ -2131,6 +2355,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
  *	0 if no interrupt is pending
  *	1 if an interrupt is pending that needs to be handled by the host
  *	-1 if there was a guest wakeup IPI (which has now been cleared)
+ * Modifies r0, r6, r7, r8, returns value in r3.
  */
 kvmppc_read_intr:
 	/* see if a host IPI is pending */
@@ -2185,6 +2410,7 @@ kvmppc_read_intr:
 	bne-	43f
 
 	/* OK, it's an IPI for us */
+	li	r12, 0
 	li	r3, -1
 1:	blr
 
@@ -2314,3 +2540,62 @@ kvmppc_fix_pmao:
 	mtspr	SPRN_PMC6, r3
 	isync
 	blr
+
+#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
+/*
+ * Start timing an activity
+ * r3 = pointer to time accumulation struct, r4 = vcpu
+ */
+kvmhv_start_timing:
+	ld	r5, HSTATE_KVM_VCORE(r13)
+	lbz	r6, VCORE_IN_GUEST(r5)
+	cmpwi	r6, 0
+	beq	5f				/* if in guest, need to */
+	ld	r6, VCORE_TB_OFFSET(r5)		/* subtract timebase offset */
+5:	mftb	r5
+	subf	r5, r6, r5
+	std	r3, VCPU_CUR_ACTIVITY(r4)
+	std	r5, VCPU_ACTIVITY_START(r4)
+	blr
+
+/*
+ * Accumulate time to one activity and start another.
+ * r3 = pointer to new time accumulation struct, r4 = vcpu
+ */
+kvmhv_accumulate_time:
+	ld	r5, HSTATE_KVM_VCORE(r13)
+	lbz	r8, VCORE_IN_GUEST(r5)
+	cmpwi	r8, 0
+	beq	4f				/* if in guest, need to */
+	ld	r8, VCORE_TB_OFFSET(r5)		/* subtract timebase offset */
+4:	ld	r5, VCPU_CUR_ACTIVITY(r4)
+	ld	r6, VCPU_ACTIVITY_START(r4)
+	std	r3, VCPU_CUR_ACTIVITY(r4)
+	mftb	r7
+	subf	r7, r8, r7
+	std	r7, VCPU_ACTIVITY_START(r4)
+	cmpdi	r5, 0
+	beqlr
+	subf	r3, r6, r7
+	ld	r8, TAS_SEQCOUNT(r5)
+	cmpdi	r8, 0
+	addi	r8, r8, 1
+	std	r8, TAS_SEQCOUNT(r5)
+	lwsync
+	ld	r7, TAS_TOTAL(r5)
+	add	r7, r7, r3
+	std	r7, TAS_TOTAL(r5)
+	ld	r6, TAS_MIN(r5)
+	ld	r7, TAS_MAX(r5)
+	beq	3f
+	cmpd	r3, r6
+	bge	1f
+3:	std	r3, TAS_MIN(r5)
+1:	cmpd	r3, r7
+	ble	2f
+	std	r3, TAS_MAX(r5)
+2:	lwsync
+	addi	r8, r8, 1
+	std	r8, TAS_SEQCOUNT(r5)
+	blr
+#endif
diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c
index ce3c893d509b..f2c75a1e0536 100644
--- a/arch/powerpc/kvm/book3s_pr_papr.c
+++ b/arch/powerpc/kvm/book3s_pr_papr.c
@@ -258,6 +258,28 @@ static int kvmppc_h_pr_put_tce(struct kvm_vcpu *vcpu)
 	return EMULATE_DONE;
 }
 
+static int kvmppc_h_pr_logical_ci_load(struct kvm_vcpu *vcpu)
+{
+	long rc;
+
+	rc = kvmppc_h_logical_ci_load(vcpu);
+	if (rc == H_TOO_HARD)
+		return EMULATE_FAIL;
+	kvmppc_set_gpr(vcpu, 3, rc);
+	return EMULATE_DONE;
+}
+
+static int kvmppc_h_pr_logical_ci_store(struct kvm_vcpu *vcpu)
+{
+	long rc;
+
+	rc = kvmppc_h_logical_ci_store(vcpu);
+	if (rc == H_TOO_HARD)
+		return EMULATE_FAIL;
+	kvmppc_set_gpr(vcpu, 3, rc);
+	return EMULATE_DONE;
+}
+
 static int kvmppc_h_pr_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd)
 {
 	long rc = kvmppc_xics_hcall(vcpu, cmd);
@@ -290,6 +312,10 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
 		clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
 		vcpu->stat.halt_wakeup++;
 		return EMULATE_DONE;
+	case H_LOGICAL_CI_LOAD:
+		return kvmppc_h_pr_logical_ci_load(vcpu);
+	case H_LOGICAL_CI_STORE:
+		return kvmppc_h_pr_logical_ci_store(vcpu);
 	case H_XIRR:
 	case H_CPPR:
 	case H_EOI:
@@ -323,6 +349,8 @@ int kvmppc_hcall_impl_pr(unsigned long cmd)
 	case H_BULK_REMOVE:
 	case H_PUT_TCE:
 	case H_CEDE:
+	case H_LOGICAL_CI_LOAD:
+	case H_LOGICAL_CI_STORE:
 #ifdef CONFIG_KVM_XICS
 	case H_XIRR:
 	case H_CPPR:
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index a4a8d9f0dcb7..8f3e6cc54d95 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -20,6 +20,7 @@
 #include <asm/xics.h>
 #include <asm/debug.h>
 #include <asm/time.h>
+#include <asm/spinlock.h>
 
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
@@ -39,7 +40,7 @@
  * LOCKING
  * =======
  *
- * Each ICS has a mutex protecting the information about the IRQ
+ * Each ICS has a spin lock protecting the information about the IRQ
  * sources and avoiding simultaneous deliveries if the same interrupt.
  *
  * ICP operations are done via a single compare & swap transaction
@@ -109,7 +110,10 @@ static void ics_check_resend(struct kvmppc_xics *xics, struct kvmppc_ics *ics,
 {
 	int i;
 
-	mutex_lock(&ics->lock);
+	unsigned long flags;
+
+	local_irq_save(flags);
+	arch_spin_lock(&ics->lock);
 
 	for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
 		struct ics_irq_state *state = &ics->irq_state[i];
@@ -120,12 +124,15 @@ static void ics_check_resend(struct kvmppc_xics *xics, struct kvmppc_ics *ics,
 		XICS_DBG("resend %#x prio %#x\n", state->number,
 			      state->priority);
 
-		mutex_unlock(&ics->lock);
+		arch_spin_unlock(&ics->lock);
+		local_irq_restore(flags);
 		icp_deliver_irq(xics, icp, state->number);
-		mutex_lock(&ics->lock);
+		local_irq_save(flags);
+		arch_spin_lock(&ics->lock);
 	}
 
-	mutex_unlock(&ics->lock);
+	arch_spin_unlock(&ics->lock);
+	local_irq_restore(flags);
 }
 
 static bool write_xive(struct kvmppc_xics *xics, struct kvmppc_ics *ics,
@@ -133,8 +140,10 @@ static bool write_xive(struct kvmppc_xics *xics, struct kvmppc_ics *ics,
 		       u32 server, u32 priority, u32 saved_priority)
 {
 	bool deliver;
+	unsigned long flags;
 
-	mutex_lock(&ics->lock);
+	local_irq_save(flags);
+	arch_spin_lock(&ics->lock);
 
 	state->server = server;
 	state->priority = priority;
@@ -145,7 +154,8 @@ static bool write_xive(struct kvmppc_xics *xics, struct kvmppc_ics *ics,
 		deliver = true;
 	}
 
-	mutex_unlock(&ics->lock);
+	arch_spin_unlock(&ics->lock);
+	local_irq_restore(flags);
 
 	return deliver;
 }
@@ -186,6 +196,7 @@ int kvmppc_xics_get_xive(struct kvm *kvm, u32 irq, u32 *server, u32 *priority)
 	struct kvmppc_ics *ics;
 	struct ics_irq_state *state;
 	u16 src;
+	unsigned long flags;
 
 	if (!xics)
 		return -ENODEV;
@@ -195,10 +206,12 @@ int kvmppc_xics_get_xive(struct kvm *kvm, u32 irq, u32 *server, u32 *priority)
 		return -EINVAL;
 	state = &ics->irq_state[src];
 
-	mutex_lock(&ics->lock);
+	local_irq_save(flags);
+	arch_spin_lock(&ics->lock);
 	*server = state->server;
 	*priority = state->priority;
-	mutex_unlock(&ics->lock);
+	arch_spin_unlock(&ics->lock);
+	local_irq_restore(flags);
 
 	return 0;
 }
@@ -365,6 +378,7 @@ static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
 	struct kvmppc_ics *ics;
 	u32 reject;
 	u16 src;
+	unsigned long flags;
 
 	/*
 	 * This is used both for initial delivery of an interrupt and
@@ -391,7 +405,8 @@ static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
 	state = &ics->irq_state[src];
 
 	/* Get a lock on the ICS */
-	mutex_lock(&ics->lock);
+	local_irq_save(flags);
+	arch_spin_lock(&ics->lock);
 
 	/* Get our server */
 	if (!icp || state->server != icp->server_num) {
@@ -434,7 +449,7 @@ static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
 	 *
 	 * Note that if successful, the new delivery might have itself
 	 * rejected an interrupt that was "delivered" before we took the
-	 * icp mutex.
+	 * ics spin lock.
 	 *
 	 * In this case we do the whole sequence all over again for the
 	 * new guy. We cannot assume that the rejected interrupt is less
@@ -448,7 +463,8 @@ static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
 		 * Delivery was successful, did we reject somebody else ?
 		 */
 		if (reject && reject != XICS_IPI) {
-			mutex_unlock(&ics->lock);
+			arch_spin_unlock(&ics->lock);
+			local_irq_restore(flags);
 			new_irq = reject;
 			goto again;
 		}
@@ -468,12 +484,14 @@ static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
 		 */
 		smp_mb();
 		if (!icp->state.need_resend) {
-			mutex_unlock(&ics->lock);
+			arch_spin_unlock(&ics->lock);
+			local_irq_restore(flags);
 			goto again;
 		}
 	}
  out:
-	mutex_unlock(&ics->lock);
+	arch_spin_unlock(&ics->lock);
+	local_irq_restore(flags);
 }
 
 static void icp_down_cppr(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
@@ -802,14 +820,22 @@ static noinline int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall)
 	XICS_DBG("XICS_RM: H_%x completing, act: %x state: %lx tgt: %p\n",
 		 hcall, icp->rm_action, icp->rm_dbgstate.raw, icp->rm_dbgtgt);
 
-	if (icp->rm_action & XICS_RM_KICK_VCPU)
+	if (icp->rm_action & XICS_RM_KICK_VCPU) {
+		icp->n_rm_kick_vcpu++;
 		kvmppc_fast_vcpu_kick(icp->rm_kick_target);
-	if (icp->rm_action & XICS_RM_CHECK_RESEND)
+	}
+	if (icp->rm_action & XICS_RM_CHECK_RESEND) {
+		icp->n_rm_check_resend++;
 		icp_check_resend(xics, icp->rm_resend_icp);
-	if (icp->rm_action & XICS_RM_REJECT)
+	}
+	if (icp->rm_action & XICS_RM_REJECT) {
+		icp->n_rm_reject++;
 		icp_deliver_irq(xics, icp, icp->rm_reject);
-	if (icp->rm_action & XICS_RM_NOTIFY_EOI)
+	}
+	if (icp->rm_action & XICS_RM_NOTIFY_EOI) {
+		icp->n_rm_notify_eoi++;
 		kvm_notify_acked_irq(vcpu->kvm, 0, icp->rm_eoied_irq);
+	}
 
 	icp->rm_action = 0;
 
@@ -872,10 +898,21 @@ static int xics_debug_show(struct seq_file *m, void *private)
 	struct kvm *kvm = xics->kvm;
 	struct kvm_vcpu *vcpu;
 	int icsid, i;
+	unsigned long flags;
+	unsigned long t_rm_kick_vcpu, t_rm_check_resend;
+	unsigned long t_rm_reject, t_rm_notify_eoi;
+	unsigned long t_reject, t_check_resend;
 
 	if (!kvm)
 		return 0;
 
+	t_rm_kick_vcpu = 0;
+	t_rm_notify_eoi = 0;
+	t_rm_check_resend = 0;
+	t_rm_reject = 0;
+	t_check_resend = 0;
+	t_reject = 0;
+
 	seq_printf(m, "=========\nICP state\n=========\n");
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
@@ -890,8 +927,19 @@ static int xics_debug_show(struct seq_file *m, void *private)
 			   icp->server_num, state.xisr,
 			   state.pending_pri, state.cppr, state.mfrr,
 			   state.out_ee, state.need_resend);
+		t_rm_kick_vcpu += icp->n_rm_kick_vcpu;
+		t_rm_notify_eoi += icp->n_rm_notify_eoi;
+		t_rm_check_resend += icp->n_rm_check_resend;
+		t_rm_reject += icp->n_rm_reject;
+		t_check_resend += icp->n_check_resend;
+		t_reject += icp->n_reject;
 	}
 
+	seq_printf(m, "ICP Guest->Host totals: kick_vcpu=%lu check_resend=%lu reject=%lu notify_eoi=%lu\n",
+			t_rm_kick_vcpu, t_rm_check_resend,
+			t_rm_reject, t_rm_notify_eoi);
+	seq_printf(m, "ICP Real Mode totals: check_resend=%lu resend=%lu\n",
+			t_check_resend, t_reject);
 	for (icsid = 0; icsid <= KVMPPC_XICS_MAX_ICS_ID; icsid++) {
 		struct kvmppc_ics *ics = xics->ics[icsid];
 
@@ -901,7 +949,8 @@ static int xics_debug_show(struct seq_file *m, void *private)
 		seq_printf(m, "=========\nICS state for ICS 0x%x\n=========\n",
 			   icsid);
 
-		mutex_lock(&ics->lock);
+		local_irq_save(flags);
+		arch_spin_lock(&ics->lock);
 
 		for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
 			struct ics_irq_state *irq = &ics->irq_state[i];
@@ -912,7 +961,8 @@ static int xics_debug_show(struct seq_file *m, void *private)
 				   irq->resend, irq->masked_pending);
 
 		}
-		mutex_unlock(&ics->lock);
+		arch_spin_unlock(&ics->lock);
+		local_irq_restore(flags);
 	}
 	return 0;
 }
@@ -965,7 +1015,6 @@ static struct kvmppc_ics *kvmppc_xics_create_ics(struct kvm *kvm,
 	if (!ics)
 		goto out;
 
-	mutex_init(&ics->lock);
 	ics->icsid = icsid;
 
 	for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
@@ -1107,13 +1156,15 @@ static int xics_get_source(struct kvmppc_xics *xics, long irq, u64 addr)
 	u64 __user *ubufp = (u64 __user *) addr;
 	u16 idx;
 	u64 val, prio;
+	unsigned long flags;
 
 	ics = kvmppc_xics_find_ics(xics, irq, &idx);
 	if (!ics)
 		return -ENOENT;
 
 	irqp = &ics->irq_state[idx];
-	mutex_lock(&ics->lock);
+	local_irq_save(flags);
+	arch_spin_lock(&ics->lock);
 	ret = -ENOENT;
 	if (irqp->exists) {
 		val = irqp->server;
@@ -1129,7 +1180,8 @@ static int xics_get_source(struct kvmppc_xics *xics, long irq, u64 addr)
 			val |= KVM_XICS_PENDING;
 		ret = 0;
 	}
-	mutex_unlock(&ics->lock);
+	arch_spin_unlock(&ics->lock);
+	local_irq_restore(flags);
 
 	if (!ret && put_user(val, ubufp))
 		ret = -EFAULT;
@@ -1146,6 +1198,7 @@ static int xics_set_source(struct kvmppc_xics *xics, long irq, u64 addr)
 	u64 val;
 	u8 prio;
 	u32 server;
+	unsigned long flags;
 
 	if (irq < KVMPPC_XICS_FIRST_IRQ || irq >= KVMPPC_XICS_NR_IRQS)
 		return -ENOENT;
@@ -1166,7 +1219,8 @@ static int xics_set_source(struct kvmppc_xics *xics, long irq, u64 addr)
 	    kvmppc_xics_find_server(xics->kvm, server) == NULL)
 		return -EINVAL;
 
-	mutex_lock(&ics->lock);
+	local_irq_save(flags);
+	arch_spin_lock(&ics->lock);
 	irqp->server = server;
 	irqp->saved_priority = prio;
 	if (val & KVM_XICS_MASKED)
@@ -1178,7 +1232,8 @@ static int xics_set_source(struct kvmppc_xics *xics, long irq, u64 addr)
 	if ((val & KVM_XICS_PENDING) && (val & KVM_XICS_LEVEL_SENSITIVE))
 		irqp->asserted = 1;
 	irqp->exists = 1;
-	mutex_unlock(&ics->lock);
+	arch_spin_unlock(&ics->lock);
+	local_irq_restore(flags);
 
 	if (val & KVM_XICS_PENDING)
 		icp_deliver_irq(xics, NULL, irqp->number);
diff --git a/arch/powerpc/kvm/book3s_xics.h b/arch/powerpc/kvm/book3s_xics.h
index 73f0f2723c07..56ea44f9867f 100644
--- a/arch/powerpc/kvm/book3s_xics.h
+++ b/arch/powerpc/kvm/book3s_xics.h
@@ -78,13 +78,22 @@ struct kvmppc_icp {
 	u32  rm_reject;
 	u32  rm_eoied_irq;
 
+	/* Counters for each reason we exited real mode */
+	unsigned long n_rm_kick_vcpu;
+	unsigned long n_rm_check_resend;
+	unsigned long n_rm_reject;
+	unsigned long n_rm_notify_eoi;
+	/* Counters for handling ICP processing in real mode */
+	unsigned long n_check_resend;
+	unsigned long n_reject;
+
 	/* Debug stuff for real mode */
 	union kvmppc_icp_state rm_dbgstate;
 	struct kvm_vcpu *rm_dbgtgt;
 };
 
 struct kvmppc_ics {
-	struct mutex lock;
+	arch_spinlock_t lock;
 	u16 icsid;
 	struct ics_irq_state irq_state[KVMPPC_XICS_IRQ_PER_ICS];
 };
@@ -96,6 +105,8 @@ struct kvmppc_xics {
 	u32 max_icsid;
 	bool real_mode;
 	bool real_mode_dbg;
+	u32 err_noics;
+	u32 err_noicp;
 	struct kvmppc_ics *ics[KVMPPC_XICS_MAX_ICS_ID + 1];
 };
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 91bbc845ac66..ac3ddf115f3d 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -529,6 +529,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_PPC_RMA:
 		r = 0;
 		break;
+	case KVM_CAP_PPC_HWRNG:
+		r = kvmppc_hwrng_present();
+		break;
 #endif
 	case KVM_CAP_SYNC_MMU:
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
diff --git a/arch/powerpc/platforms/powernv/rng.c b/arch/powerpc/platforms/powernv/rng.c
index 80db43944afe..6eb808ff637e 100644
--- a/arch/powerpc/platforms/powernv/rng.c
+++ b/arch/powerpc/platforms/powernv/rng.c
@@ -24,12 +24,22 @@
 
 struct powernv_rng {
 	void __iomem *regs;
+	void __iomem *regs_real;
 	unsigned long mask;
 };
 
 static DEFINE_PER_CPU(struct powernv_rng *, powernv_rng);
 
 
+int powernv_hwrng_present(void)
+{
+	struct powernv_rng *rng;
+
+	rng = get_cpu_var(powernv_rng);
+	put_cpu_var(rng);
+	return rng != NULL;
+}
+
 static unsigned long rng_whiten(struct powernv_rng *rng, unsigned long val)
 {
 	unsigned long parity;
@@ -46,6 +56,17 @@ static unsigned long rng_whiten(struct powernv_rng *rng, unsigned long val)
 	return val;
 }
 
+int powernv_get_random_real_mode(unsigned long *v)
+{
+	struct powernv_rng *rng;
+
+	rng = raw_cpu_read(powernv_rng);
+
+	*v = rng_whiten(rng, in_rm64(rng->regs_real));
+
+	return 1;
+}
+
 int powernv_get_random_long(unsigned long *v)
 {
 	struct powernv_rng *rng;
@@ -80,12 +101,20 @@ static __init void rng_init_per_cpu(struct powernv_rng *rng,
 static __init int rng_create(struct device_node *dn)
 {
 	struct powernv_rng *rng;
+	struct resource res;
 	unsigned long val;
 
 	rng = kzalloc(sizeof(*rng), GFP_KERNEL);
 	if (!rng)
 		return -ENOMEM;
 
+	if (of_address_to_resource(dn, 0, &res)) {
+		kfree(rng);
+		return -ENXIO;
+	}
+
+	rng->regs_real = (void __iomem *)res.start;
+
 	rng->regs = of_iomap(dn, 0);
 	if (!rng->regs) {
 		kfree(rng);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index afa2bd750ffc..8cd8e7b288c5 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -110,7 +110,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 /* upper facilities limit for kvm */
 unsigned long kvm_s390_fac_list_mask[] = {
 	0xffe6fffbfcfdfc40UL,
-	0x205c800000000000UL,
+	0x005c800000000000UL,
 };
 
 unsigned long kvm_s390_fac_list_mask_size(void)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index d67206a7b99a..629af0f1c5c4 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -683,8 +683,7 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
 	unsigned long bitmap = 1;
 	struct kvm_lapic **dst;
 	int i;
-	bool ret = false;
-	bool x2apic_ipi = src && apic_x2apic_mode(src);
+	bool ret, x2apic_ipi;
 
 	*r = -1;
 
@@ -696,16 +695,18 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
 	if (irq->shorthand)
 		return false;
 
+	x2apic_ipi = src && apic_x2apic_mode(src);
 	if (irq->dest_id == (x2apic_ipi ? X2APIC_BROADCAST : APIC_BROADCAST))
 		return false;
 
+	ret = true;
 	rcu_read_lock();
 	map = rcu_dereference(kvm->arch.apic_map);
 
-	if (!map)
+	if (!map) {
+		ret = false;
 		goto out;
-
-	ret = true;
+	}
 
 	if (irq->dest_mode == APIC_DEST_PHYSICAL) {
 		if (irq->dest_id >= ARRAY_SIZE(map->phys_map))
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 146f295ee322..d43867c33bc4 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4481,9 +4481,11 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
 		pfn = spte_to_pfn(*sptep);
 
 		/*
-		 * Only EPT supported for now; otherwise, one would need to
-		 * find out efficiently whether the guest page tables are
-		 * also using huge pages.
+		 * We cannot do huge page mapping for indirect shadow pages,
+		 * which are found on the last rmap (level = 1) when not using
+		 * tdp; such shadow pages are synced with the page table in
+		 * the guest, and the guest page table is using 4K page size
+		 * mapping if the indirect sp has level = 1.
 		 */
 		if (sp->role.direct &&
 			!kvm_is_reserved_pfn(pfn) &&
@@ -4504,19 +4506,12 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
 	bool flush = false;
 	unsigned long *rmapp;
 	unsigned long last_index, index;
-	gfn_t gfn_start, gfn_end;
 
 	spin_lock(&kvm->mmu_lock);
 
-	gfn_start = memslot->base_gfn;
-	gfn_end = memslot->base_gfn + memslot->npages - 1;
-
-	if (gfn_start >= gfn_end)
-		goto out;
-
 	rmapp = memslot->arch.rmap[0];
-	last_index = gfn_to_index(gfn_end, memslot->base_gfn,
-					PT_PAGE_TABLE_LEVEL);
+	last_index = gfn_to_index(memslot->base_gfn + memslot->npages - 1,
+				memslot->base_gfn, PT_PAGE_TABLE_LEVEL);
 
 	for (index = 0; index <= last_index; ++index, ++rmapp) {
 		if (*rmapp)
@@ -4534,7 +4529,6 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
 	if (flush)
 		kvm_flush_remote_tlbs(kvm);
 
-out:
 	spin_unlock(&kvm->mmu_lock);
 }
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f5e8dce8046c..f7b61687bd79 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3622,8 +3622,16 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 
 static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
-	unsigned long hw_cr4 = cr4 | (to_vmx(vcpu)->rmode.vm86_active ?
-		    KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON);
+	/*
+	 * Pass through host's Machine Check Enable value to hw_cr4, which
+	 * is in force while we are in guest mode.  Do not let guests control
+	 * this bit, even if host CR4.MCE == 0.
+	 */
+	unsigned long hw_cr4 =
+		(cr4_read_shadow() & X86_CR4_MCE) |
+		(cr4 & ~X86_CR4_MCE) |
+		(to_vmx(vcpu)->rmode.vm86_active ?
+		 KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON);
 
 	if (cr4 & X86_CR4_VMXE) {
 		/*
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e1a81267f3f6..ed31c31b2485 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5799,7 +5799,6 @@ int kvm_arch_init(void *opaque)
 	kvm_set_mmio_spte_mask();
 
 	kvm_x86_ops = ops;
-	kvm_init_msr_list();
 
 	kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
 			PT_DIRTY_MASK, PT64_NX_MASK, 0);
@@ -7253,7 +7252,14 @@ void kvm_arch_hardware_disable(void)
 
 int kvm_arch_hardware_setup(void)
 {
-	return kvm_x86_ops->hardware_setup();
+	int r;
+
+	r = kvm_x86_ops->hardware_setup();
+	if (r != 0)
+		return r;
+
+	kvm_init_msr_list();
+	return 0;
 }
 
 void kvm_arch_hardware_unsetup(void)
author	Linus Torvalds	2015-04-26 13:06:22 -0700
committer	Linus Torvalds	2015-04-26 13:06:22 -0700
commit	eadf16a912b6bdf8bd476bde2f19fb41d06e0c3b (patch)
tree	db20ba1e739b1118147d667d79e074558ed238ac /arch
parent	4a6554665c62ee39be40f4a18c3d37e49d03ccc1 (diff)
parent	2fa462f826210bbec65f8ed06d5ef4e0cd4f5450 (diff)