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
  ...

Documentation/virtual/kvm/api.txt

@@ -3573,3 +3573,20 @@ struct {
 @ar   - access register number
 
 KVM handlers should exit to userspace with rc = -EREMOTE.
+
+
+8. Other capabilities.
+----------------------
+
+This section lists capabilities that give information about other
+features of the KVM implementation.
+
+8.1 KVM_CAP_PPC_HWRNG
+
+Architectures: ppc
+
+This capability, if KVM_CHECK_EXTENSION indicates that it is
+available, means that that the kernel has an implementation of the
+H_RANDOM hypercall backed by a hardware random-number generator.
+If present, the kernel H_RANDOM handler can be enabled for guest use
+with the KVM_CAP_PPC_ENABLE_HCALL capability.

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

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);

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

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 */

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

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__ */

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]

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.

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 */

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>
@@ -458,6 +459,19 @@ int main(void)
 	DEFINE(VCPU_SPRG1, offsetof(struct kvm_vcpu, arch.shregs.sprg1));
 	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));
@@ -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;
 }

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.
  *

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