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

Pull KVM update from Paolo Bonzini:
 "Fairly small update, but there are some interesting new features.

  Common:
     Optional support for adding a small amount of polling on each HLT
     instruction executed in the guest (or equivalent for other
     architectures).  This can improve latency up to 50% on some
     scenarios (e.g. O_DSYNC writes or TCP_RR netperf tests).  This
     also has to be enabled manually for now, but the plan is to
     auto-tune this in the future.

  ARM/ARM64:
     The highlights are support for GICv3 emulation and dirty page
     tracking

  s390:
     Several optimizations and bugfixes.  Also a first: a feature
     exposed by KVM (UUID and long guest name in /proc/sysinfo) before
     it is available in IBM's hypervisor! :)

  MIPS:
     Bugfixes.

  x86:
     Support for PML (page modification logging, a new feature in
     Broadwell Xeons that speeds up dirty page tracking), nested
     virtualization improvements (nested APICv---a nice optimization),
     usual round of emulation fixes.

     There is also a new option to reduce latency of the TSC deadline
     timer in the guest; this needs to be tuned manually.

     Some commits are common between this pull and Catalin's; I see you
     have already included his tree.

  Powerpc:
     Nothing yet.

     The KVM/PPC changes will come in through the PPC maintainers,
     because I haven't received them yet and I might end up being
     offline for some part of next week"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (130 commits)
  KVM: ia64: drop kvm.h from installed user headers
  KVM: x86: fix build with !CONFIG_SMP
  KVM: x86: emulate: correct page fault error code for NoWrite instructions
  KVM: Disable compat ioctl for s390
  KVM: s390: add cpu model support
  KVM: s390: use facilities and cpu_id per KVM
  KVM: s390/CPACF: Choose crypto control block format
  s390/kernel: Update /proc/sysinfo file with Extended Name and UUID
  KVM: s390: reenable LPP facility
  KVM: s390: floating irqs: fix user triggerable endless loop
  kvm: add halt_poll_ns module parameter
  kvm: remove KVM_MMIO_SIZE
  KVM: MIPS: Don't leak FPU/DSP to guest
  KVM: MIPS: Disable HTW while in guest
  KVM: nVMX: Enable nested posted interrupt processing
  KVM: nVMX: Enable nested virtual interrupt delivery
  KVM: nVMX: Enable nested apic register virtualization
  KVM: nVMX: Make nested control MSRs per-cpu
  KVM: nVMX: Enable nested virtualize x2apic mode
  KVM: nVMX: Prepare for using hardware MSR bitmap
  ...

5 files changed, 122 insertions, 10 deletions

diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index ac4888d..7c55dd5 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -33,10 +33,11 @@
 #define VGIC_V2_MAX_LRS		(1 << 6)
 #define VGIC_V3_MAX_LRS		16
 #define VGIC_MAX_IRQS		1024
+#define VGIC_V2_MAX_CPUS	8
 
 /* Sanity checks... */
-#if (KVM_MAX_VCPUS > 8)
-#error	Invalid number of CPU interfaces
+#if (KVM_MAX_VCPUS > 255)
+#error Too many KVM VCPUs, the VGIC only supports up to 255 VCPUs for now
 #endif
 
 #if (VGIC_NR_IRQS_LEGACY & 31)
@@ -132,6 +133,18 @@ struct vgic_params {
 	unsigned int	maint_irq;
 	/* Virtual control interface base address */
 	void __iomem	*vctrl_base;
+	int		max_gic_vcpus;
+	/* Only needed for the legacy KVM_CREATE_IRQCHIP */
+	bool		can_emulate_gicv2;
+};
+
+struct vgic_vm_ops {
+	bool	(*handle_mmio)(struct kvm_vcpu *, struct kvm_run *,
+			       struct kvm_exit_mmio *);
+	bool	(*queue_sgi)(struct kvm_vcpu *, int irq);
+	void	(*add_sgi_source)(struct kvm_vcpu *, int irq, int source);
+	int	(*init_model)(struct kvm *);
+	int	(*map_resources)(struct kvm *, const struct vgic_params *);
 };
 
 struct vgic_dist {
@@ -140,6 +153,9 @@ struct vgic_dist {
 	bool			in_kernel;
 	bool			ready;
 
+	/* vGIC model the kernel emulates for the guest (GICv2 or GICv3) */
+	u32			vgic_model;
+
 	int			nr_cpus;
 	int			nr_irqs;
 
@@ -148,7 +164,11 @@ struct vgic_dist {
 
 	/* Distributor and vcpu interface mapping in the guest */
 	phys_addr_t		vgic_dist_base;
-	phys_addr_t		vgic_cpu_base;
+	/* GICv2 and GICv3 use different mapped register blocks */
+	union {
+		phys_addr_t		vgic_cpu_base;
+		phys_addr_t		vgic_redist_base;
+	};
 
 	/* Distributor enabled */
 	u32			enabled;
@@ -210,8 +230,13 @@ struct vgic_dist {
 	 */
 	struct vgic_bitmap	*irq_spi_target;
 
+	/* Target MPIDR for each IRQ (needed for GICv3 IROUTERn) only */
+	u32			*irq_spi_mpidr;
+
 	/* Bitmap indicating which CPU has something pending */
 	unsigned long		*irq_pending_on_cpu;
+
+	struct vgic_vm_ops	vm_ops;
 #endif
 };
 
@@ -229,6 +254,7 @@ struct vgic_v3_cpu_if {
 #ifdef CONFIG_ARM_GIC_V3
 	u32		vgic_hcr;
 	u32		vgic_vmcr;
+	u32		vgic_sre;	/* Restored only, change ignored */
 	u32		vgic_misr;	/* Saved only */
 	u32		vgic_eisr;	/* Saved only */
 	u32		vgic_elrsr;	/* Saved only */
@@ -275,13 +301,15 @@ struct kvm_exit_mmio;
 int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write);
 int kvm_vgic_hyp_init(void);
 int kvm_vgic_map_resources(struct kvm *kvm);
-int kvm_vgic_create(struct kvm *kvm);
+int kvm_vgic_get_max_vcpus(void);
+int kvm_vgic_create(struct kvm *kvm, u32 type);
 void kvm_vgic_destroy(struct kvm *kvm);
 void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
 void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
 void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
 int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
 			bool level);
+void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg);
 int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
 bool vgic_handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		      struct kvm_exit_mmio *mmio);
@@ -327,7 +355,7 @@ static inline int kvm_vgic_map_resources(struct kvm *kvm)
 	return 0;
 }
 
-static inline int kvm_vgic_create(struct kvm *kvm)
+static inline int kvm_vgic_create(struct kvm *kvm, u32 type)
 {
 	return 0;
 }
@@ -379,6 +407,11 @@ static inline bool vgic_ready(struct kvm *kvm)
 {
 	return true;
 }
+
+static inline int kvm_vgic_get_max_vcpus(void)
+{
+	return KVM_MAX_VCPUS;
+}
 #endif
 
 #endif
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 1e8b0cf..800544b 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -33,6 +33,7 @@
 #define GICD_SETSPI_SR			0x0050
 #define GICD_CLRSPI_SR			0x0058
 #define GICD_SEIR			0x0068
+#define GICD_IGROUPR			0x0080
 #define GICD_ISENABLER			0x0100
 #define GICD_ICENABLER			0x0180
 #define GICD_ISPENDR			0x0200
@@ -41,14 +42,37 @@
 #define GICD_ICACTIVER			0x0380
 #define GICD_IPRIORITYR			0x0400
 #define GICD_ICFGR			0x0C00
+#define GICD_IGRPMODR			0x0D00
+#define GICD_NSACR			0x0E00
 #define GICD_IROUTER			0x6000
+#define GICD_IDREGS			0xFFD0
 #define GICD_PIDR2			0xFFE8
 
+/*
+ * Those registers are actually from GICv2, but the spec demands that they
+ * are implemented as RES0 if ARE is 1 (which we do in KVM's emulated GICv3).
+ */
+#define GICD_ITARGETSR			0x0800
+#define GICD_SGIR			0x0F00
+#define GICD_CPENDSGIR			0x0F10
+#define GICD_SPENDSGIR			0x0F20
+
 #define GICD_CTLR_RWP			(1U << 31)
+#define GICD_CTLR_DS			(1U << 6)
 #define GICD_CTLR_ARE_NS		(1U << 4)
 #define GICD_CTLR_ENABLE_G1A		(1U << 1)
 #define GICD_CTLR_ENABLE_G1		(1U << 0)
 
+/*
+ * In systems with a single security state (what we emulate in KVM)
+ * the meaning of the interrupt group enable bits is slightly different
+ */
+#define GICD_CTLR_ENABLE_SS_G1		(1U << 1)
+#define GICD_CTLR_ENABLE_SS_G0		(1U << 0)
+
+#define GICD_TYPER_LPIS			(1U << 17)
+#define GICD_TYPER_MBIS			(1U << 16)
+
 #define GICD_TYPER_ID_BITS(typer)	((((typer) >> 19) & 0x1f) + 1)
 #define GICD_TYPER_IRQS(typer)		((((typer) & 0x1f) + 1) * 32)
 #define GICD_TYPER_LPIS			(1U << 17)
@@ -60,6 +84,8 @@
 #define GIC_PIDR2_ARCH_GICv3		0x30
 #define GIC_PIDR2_ARCH_GICv4		0x40
 
+#define GIC_V3_DIST_SIZE		0x10000
+
 /*
  * Re-Distributor registers, offsets from RD_base
  */
@@ -78,6 +104,7 @@
 #define GICR_SYNCR			0x00C0
 #define GICR_MOVLPIR			0x0100
 #define GICR_MOVALLR			0x0110
+#define GICR_IDREGS			GICD_IDREGS
 #define GICR_PIDR2			GICD_PIDR2
 
 #define GICR_CTLR_ENABLE_LPIS		(1UL << 0)
@@ -104,6 +131,7 @@
 /*
  * Re-Distributor registers, offsets from SGI_base
  */
+#define GICR_IGROUPR0			GICD_IGROUPR
 #define GICR_ISENABLER0			GICD_ISENABLER
 #define GICR_ICENABLER0			GICD_ICENABLER
 #define GICR_ISPENDR0			GICD_ISPENDR
@@ -112,11 +140,15 @@
 #define GICR_ICACTIVER0			GICD_ICACTIVER
 #define GICR_IPRIORITYR0		GICD_IPRIORITYR
 #define GICR_ICFGR0			GICD_ICFGR
+#define GICR_IGRPMODR0			GICD_IGRPMODR
+#define GICR_NSACR			GICD_NSACR
 
 #define GICR_TYPER_PLPIS		(1U << 0)
 #define GICR_TYPER_VLPIS		(1U << 1)
 #define GICR_TYPER_LAST			(1U << 4)
 
+#define GIC_V3_REDIST_SIZE		0x20000
+
 #define LPI_PROP_GROUP1			(1 << 1)
 #define LPI_PROP_ENABLED		(1 << 0)
 
@@ -248,6 +280,18 @@
 #define ICC_SRE_EL2_SRE			(1 << 0)
 #define ICC_SRE_EL2_ENABLE		(1 << 3)
 
+#define ICC_SGI1R_TARGET_LIST_SHIFT	0
+#define ICC_SGI1R_TARGET_LIST_MASK	(0xffff << ICC_SGI1R_TARGET_LIST_SHIFT)
+#define ICC_SGI1R_AFFINITY_1_SHIFT	16
+#define ICC_SGI1R_AFFINITY_1_MASK	(0xff << ICC_SGI1R_AFFINITY_1_SHIFT)
+#define ICC_SGI1R_SGI_ID_SHIFT		24
+#define ICC_SGI1R_SGI_ID_MASK		(0xff << ICC_SGI1R_SGI_ID_SHIFT)
+#define ICC_SGI1R_AFFINITY_2_SHIFT	32
+#define ICC_SGI1R_AFFINITY_2_MASK	(0xffULL << ICC_SGI1R_AFFINITY_1_SHIFT)
+#define ICC_SGI1R_IRQ_ROUTING_MODE_BIT	40
+#define ICC_SGI1R_AFFINITY_3_SHIFT	48
+#define ICC_SGI1R_AFFINITY_3_MASK	(0xffULL << ICC_SGI1R_AFFINITY_1_SHIFT)
+
 /*
  * System register definitions
  */
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index d189ee0..d12b210 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -33,10 +33,6 @@
 
 #include <asm/kvm_host.h>
 
-#ifndef KVM_MMIO_SIZE
-#define KVM_MMIO_SIZE 8
-#endif
-
 /*
  * The bit 16 ~ bit 31 of kvm_memory_region::flags are internally used
  * in kvm, other bits are visible for userspace which are defined in
@@ -600,6 +596,15 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext);
 
 int kvm_get_dirty_log(struct kvm *kvm,
 			struct kvm_dirty_log *log, int *is_dirty);
+
+int kvm_get_dirty_log_protect(struct kvm *kvm,
+			struct kvm_dirty_log *log, bool *is_dirty);
+
+void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
+					struct kvm_memory_slot *slot,
+					gfn_t gfn_offset,
+					unsigned long mask);
+
 int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 				struct kvm_dirty_log *log);
 
@@ -641,7 +646,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu);
 struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id);
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu);
-int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu);
+void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu);
 
 int kvm_arch_hardware_enable(void);
@@ -1031,6 +1036,8 @@ void kvm_unregister_device_ops(u32 type);
 
 extern struct kvm_device_ops kvm_mpic_ops;
 extern struct kvm_device_ops kvm_xics_ops;
+extern struct kvm_device_ops kvm_arm_vgic_v2_ops;
+extern struct kvm_device_ops kvm_arm_vgic_v3_ops;
 
 #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
 
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 86b399c..a44062d 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -37,6 +37,25 @@ TRACE_EVENT(kvm_userspace_exit,
 		  __entry->errno < 0 ? -__entry->errno : __entry->reason)
 );
 
+TRACE_EVENT(kvm_vcpu_wakeup,
+	    TP_PROTO(__u64 ns, bool waited),
+	    TP_ARGS(ns, waited),
+
+	TP_STRUCT__entry(
+		__field(	__u64,		ns		)
+		__field(	bool,		waited		)
+	),
+
+	TP_fast_assign(
+		__entry->ns		= ns;
+		__entry->waited		= waited;
+	),
+
+	TP_printk("%s time %lld ns",
+		  __entry->waited ? "wait" : "poll",
+		  __entry->ns)
+);
+
 #if defined(CONFIG_HAVE_KVM_IRQFD)
 TRACE_EVENT(kvm_set_irq,
 	TP_PROTO(unsigned int gsi, int level, int irq_source_id),
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index a37fd12..8055706 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -491,6 +491,11 @@ struct kvm_s390_emerg_info {
 	__u16 code;
 };
 
+#define KVM_S390_STOP_FLAG_STORE_STATUS	0x01
+struct kvm_s390_stop_info {
+	__u32 flags;
+};
+
 struct kvm_s390_mchk_info {
 	__u64 cr14;
 	__u64 mcic;
@@ -509,6 +514,7 @@ struct kvm_s390_irq {
 		struct kvm_s390_emerg_info emerg;
 		struct kvm_s390_extcall_info extcall;
 		struct kvm_s390_prefix_info prefix;
+		struct kvm_s390_stop_info stop;
 		struct kvm_s390_mchk_info mchk;
 		char reserved[64];
 	} u;
@@ -753,6 +759,7 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_PPC_FIXUP_HCALL 103
 #define KVM_CAP_PPC_ENABLE_HCALL 104
 #define KVM_CAP_CHECK_EXTENSION_VM 105
+#define KVM_CAP_S390_USER_SIGP 106
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -952,6 +959,8 @@ enum kvm_device_type {
 #define KVM_DEV_TYPE_ARM_VGIC_V2	KVM_DEV_TYPE_ARM_VGIC_V2
 	KVM_DEV_TYPE_FLIC,
 #define KVM_DEV_TYPE_FLIC		KVM_DEV_TYPE_FLIC
+	KVM_DEV_TYPE_ARM_VGIC_V3,
+#define KVM_DEV_TYPE_ARM_VGIC_V3	KVM_DEV_TYPE_ARM_VGIC_V3
 	KVM_DEV_TYPE_MAX,
 };