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

Pull second batch of KVM updates from Radim Krčmář:
 "General:

   - move kvm_stat tool from QEMU repo into tools/kvm/kvm_stat (kvm_stat
     had nothing to do with QEMU in the first place -- the tool only
     interprets debugfs)

   - expose per-vm statistics in debugfs and support them in kvm_stat
     (KVM always collected per-vm statistics, but they were summarised
     into global statistics)

  x86:

   - fix dynamic APICv (VMX was improperly configured and a guest could
     access host's APIC MSRs, CVE-2016-4440)

   - minor fixes

  ARM changes from Christoffer Dall:

   - new vgic reimplementation of our horribly broken legacy vgic
     implementation.  The two implementations will live side-by-side
     (with the new being the configured default) for one kernel release
     and then we'll remove the legacy one.

   - fix for a non-critical issue with virtual abort injection to guests"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (70 commits)
  tools: kvm_stat: Add comments
  tools: kvm_stat: Introduce pid monitoring
  KVM: Create debugfs dir and stat files for each VM
  MAINTAINERS: Add kvm tools
  tools: kvm_stat: Powerpc related fixes
  tools: Add kvm_stat man page
  tools: Add kvm_stat vm monitor script
  kvm:vmx: more complete state update on APICv on/off
  KVM: SVM: Add more SVM_EXIT_REASONS
  KVM: Unify traced vector format
  svm: bitwise vs logical op typo
  KVM: arm/arm64: vgic-new: Synchronize changes to active state
  KVM: arm/arm64: vgic-new: enable build
  KVM: arm/arm64: vgic-new: implement mapped IRQ handling
  KVM: arm/arm64: vgic-new: Wire up irqfd injection
  KVM: arm/arm64: vgic-new: Add vgic_v2/v3_enable
  KVM: arm/arm64: vgic-new: vgic_init: implement map_resources
  KVM: arm/arm64: vgic-new: vgic_init: implement vgic_init
  KVM: arm/arm64: vgic-new: vgic_init: implement vgic_create
  KVM: arm/arm64: vgic-new: vgic_init: implement kvm_vgic_hyp_init
  ...

7 files changed, 279 insertions, 19 deletions

diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index b651aed..dda39d8 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -24,9 +24,6 @@
 #include <linux/workqueue.h>
 
 struct arch_timer_kvm {
-	/* Is the timer enabled */
-	bool			enabled;
-
 	/* Virtual offset */
 	cycle_t			cntvoff;
 };
@@ -53,15 +50,15 @@ struct arch_timer_cpu {
 	/* Timer IRQ */
 	struct kvm_irq_level		irq;
 
-	/* VGIC mapping */
-	struct irq_phys_map		*map;
-
 	/* Active IRQ state caching */
 	bool				active_cleared_last;
+
+	/* Is the timer enabled */
+	bool			enabled;
 };
 
 int kvm_timer_hyp_init(void);
-void kvm_timer_enable(struct kvm *kvm);
+int kvm_timer_enable(struct kvm_vcpu *vcpu);
 void kvm_timer_init(struct kvm *kvm);
 int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
 			 const struct kvm_irq_level *irq);
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index be6037a..da0a5248 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -19,6 +19,10 @@
 #ifndef __ASM_ARM_KVM_VGIC_H
 #define __ASM_ARM_KVM_VGIC_H
 
+#ifdef CONFIG_KVM_NEW_VGIC
+#include <kvm/vgic/vgic.h>
+#else
+
 #include <linux/kernel.h>
 #include <linux/kvm.h>
 #include <linux/irqreturn.h>
@@ -158,7 +162,6 @@ struct vgic_io_device {
 struct irq_phys_map {
 	u32			virt_irq;
 	u32			phys_irq;
-	u32			irq;
 };
 
 struct irq_phys_map_entry {
@@ -305,9 +308,6 @@ struct vgic_cpu {
 	unsigned long   *active_shared;
 	unsigned long   *pend_act_shared;
 
-	/* Number of list registers on this CPU */
-	int		nr_lr;
-
 	/* CPU vif control registers for world switch */
 	union {
 		struct vgic_v2_cpu_if	vgic_v2;
@@ -342,17 +342,18 @@ 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);
 int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid,
-			       struct irq_phys_map *map, bool level);
+			       unsigned int virt_irq, bool level);
 void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg);
 int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
-struct irq_phys_map *kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu,
-					   int virt_irq, int irq);
-int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map);
-bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, struct irq_phys_map *map);
+int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, int virt_irq, int phys_irq);
+int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int virt_irq);
+bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int virt_irq);
 
 #define irqchip_in_kernel(k)	(!!((k)->arch.vgic.in_kernel))
 #define vgic_initialized(k)	(!!((k)->arch.vgic.nr_cpus))
 #define vgic_ready(k)		((k)->arch.vgic.ready)
+#define vgic_valid_spi(k, i)	(((i) >= VGIC_NR_PRIVATE_IRQS) && \
+				 ((i) < (k)->arch.vgic.nr_irqs))
 
 int vgic_v2_probe(const struct gic_kvm_info *gic_kvm_info,
 		  const struct vgic_ops **ops,
@@ -370,4 +371,5 @@ static inline int vgic_v3_probe(const struct gic_kvm_info *gic_kvm_info,
 }
 #endif
 
+#endif	/* old VGIC include */
 #endif
diff --git a/include/kvm/vgic/vgic.h b/include/kvm/vgic/vgic.h
new file mode 100644
index 0000000..3fbd175
--- /dev/null
+++ b/include/kvm/vgic/vgic.h
@@ -0,0 +1,246 @@
+/*
+ * Copyright (C) 2015, 2016 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_ARM_KVM_VGIC_VGIC_H
+#define __ASM_ARM_KVM_VGIC_VGIC_H
+
+#include <linux/kernel.h>
+#include <linux/kvm.h>
+#include <linux/irqreturn.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <kvm/iodev.h>
+
+#define VGIC_V3_MAX_CPUS	255
+#define VGIC_V2_MAX_CPUS	8
+#define VGIC_NR_IRQS_LEGACY     256
+#define VGIC_NR_SGIS		16
+#define VGIC_NR_PPIS		16
+#define VGIC_NR_PRIVATE_IRQS	(VGIC_NR_SGIS + VGIC_NR_PPIS)
+#define VGIC_MAX_PRIVATE	(VGIC_NR_PRIVATE_IRQS - 1)
+#define VGIC_MAX_SPI		1019
+#define VGIC_MAX_RESERVED	1023
+#define VGIC_MIN_LPI		8192
+
+enum vgic_type {
+	VGIC_V2,		/* Good ol' GICv2 */
+	VGIC_V3,		/* New fancy GICv3 */
+};
+
+/* same for all guests, as depending only on the _host's_ GIC model */
+struct vgic_global {
+	/* type of the host GIC */
+	enum vgic_type		type;
+
+	/* Physical address of vgic virtual cpu interface */
+	phys_addr_t		vcpu_base;
+
+	/* virtual control interface mapping */
+	void __iomem		*vctrl_base;
+
+	/* Number of implemented list registers */
+	int			nr_lr;
+
+	/* Maintenance IRQ number */
+	unsigned int		maint_irq;
+
+	/* maximum number of VCPUs allowed (GICv2 limits us to 8) */
+	int			max_gic_vcpus;
+
+	/* Only needed for the legacy KVM_CREATE_IRQCHIP */
+	bool			can_emulate_gicv2;
+};
+
+extern struct vgic_global kvm_vgic_global_state;
+
+#define VGIC_V2_MAX_LRS		(1 << 6)
+#define VGIC_V3_MAX_LRS		16
+#define VGIC_V3_LR_INDEX(lr)	(VGIC_V3_MAX_LRS - 1 - lr)
+
+enum vgic_irq_config {
+	VGIC_CONFIG_EDGE = 0,
+	VGIC_CONFIG_LEVEL
+};
+
+struct vgic_irq {
+	spinlock_t irq_lock;		/* Protects the content of the struct */
+	struct list_head ap_list;
+
+	struct kvm_vcpu *vcpu;		/* SGIs and PPIs: The VCPU
+					 * SPIs and LPIs: The VCPU whose ap_list
+					 * this is queued on.
+					 */
+
+	struct kvm_vcpu *target_vcpu;	/* The VCPU that this interrupt should
+					 * be sent to, as a result of the
+					 * targets reg (v2) or the
+					 * affinity reg (v3).
+					 */
+
+	u32 intid;			/* Guest visible INTID */
+	bool pending;
+	bool line_level;		/* Level only */
+	bool soft_pending;		/* Level only */
+	bool active;			/* not used for LPIs */
+	bool enabled;
+	bool hw;			/* Tied to HW IRQ */
+	u32 hwintid;			/* HW INTID number */
+	union {
+		u8 targets;			/* GICv2 target VCPUs mask */
+		u32 mpidr;			/* GICv3 target VCPU */
+	};
+	u8 source;			/* GICv2 SGIs only */
+	u8 priority;
+	enum vgic_irq_config config;	/* Level or edge */
+};
+
+struct vgic_register_region;
+
+struct vgic_io_device {
+	gpa_t base_addr;
+	struct kvm_vcpu *redist_vcpu;
+	const struct vgic_register_region *regions;
+	int nr_regions;
+	struct kvm_io_device dev;
+};
+
+struct vgic_dist {
+	bool			in_kernel;
+	bool			ready;
+	bool			initialized;
+
+	/* vGIC model the kernel emulates for the guest (GICv2 or GICv3) */
+	u32			vgic_model;
+
+	int			nr_spis;
+
+	/* TODO: Consider moving to global state */
+	/* Virtual control interface mapping */
+	void __iomem		*vctrl_base;
+
+	/* base addresses in guest physical address space: */
+	gpa_t			vgic_dist_base;		/* distributor */
+	union {
+		/* either a GICv2 CPU interface */
+		gpa_t			vgic_cpu_base;
+		/* or a number of GICv3 redistributor regions */
+		gpa_t			vgic_redist_base;
+	};
+
+	/* distributor enabled */
+	bool			enabled;
+
+	struct vgic_irq		*spis;
+
+	struct vgic_io_device	dist_iodev;
+	struct vgic_io_device	*redist_iodevs;
+};
+
+struct vgic_v2_cpu_if {
+	u32		vgic_hcr;
+	u32		vgic_vmcr;
+	u32		vgic_misr;	/* Saved only */
+	u64		vgic_eisr;	/* Saved only */
+	u64		vgic_elrsr;	/* Saved only */
+	u32		vgic_apr;
+	u32		vgic_lr[VGIC_V2_MAX_LRS];
+};
+
+struct vgic_v3_cpu_if {
+#ifdef CONFIG_KVM_ARM_VGIC_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 */
+	u32		vgic_ap0r[4];
+	u32		vgic_ap1r[4];
+	u64		vgic_lr[VGIC_V3_MAX_LRS];
+#endif
+};
+
+struct vgic_cpu {
+	/* CPU vif control registers for world switch */
+	union {
+		struct vgic_v2_cpu_if	vgic_v2;
+		struct vgic_v3_cpu_if	vgic_v3;
+	};
+
+	unsigned int used_lrs;
+	struct vgic_irq private_irqs[VGIC_NR_PRIVATE_IRQS];
+
+	spinlock_t ap_list_lock;	/* Protects the ap_list */
+
+	/*
+	 * List of IRQs that this VCPU should consider because they are either
+	 * Active or Pending (hence the name; AP list), or because they recently
+	 * were one of the two and need to be migrated off this list to another
+	 * VCPU.
+	 */
+	struct list_head ap_list_head;
+
+	u64 live_lrs;
+};
+
+int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write);
+void kvm_vgic_early_init(struct kvm *kvm);
+int kvm_vgic_create(struct kvm *kvm, u32 type);
+void kvm_vgic_destroy(struct kvm *kvm);
+void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu);
+void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu);
+int kvm_vgic_map_resources(struct kvm *kvm);
+int kvm_vgic_hyp_init(void);
+
+int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
+			bool level);
+int kvm_vgic_inject_mapped_irq(struct kvm *kvm, int cpuid, unsigned int intid,
+			       bool level);
+int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, u32 virt_irq, u32 phys_irq);
+int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int virt_irq);
+bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int virt_irq);
+
+int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu);
+
+#define irqchip_in_kernel(k)	(!!((k)->arch.vgic.in_kernel))
+#define vgic_initialized(k)	((k)->arch.vgic.initialized)
+#define vgic_ready(k)		((k)->arch.vgic.ready)
+#define vgic_valid_spi(k, i)	(((i) >= VGIC_NR_PRIVATE_IRQS) && \
+			((i) < (k)->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS))
+
+bool kvm_vcpu_has_pending_irqs(struct kvm_vcpu *vcpu);
+void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
+void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
+
+#ifdef CONFIG_KVM_ARM_VGIC_V3
+void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg);
+#else
+static inline void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg)
+{
+}
+#endif
+
+/**
+ * kvm_vgic_get_max_vcpus - Get the maximum number of VCPUs allowed by HW
+ *
+ * The host's GIC naturally limits the maximum amount of VCPUs a guest
+ * can use.
+ */
+static inline int kvm_vgic_get_max_vcpus(void)
+{
+	return kvm_vgic_global_state.max_gic_vcpus;
+}
+
+#endif /* __ASM_ARM_KVM_VGIC_VGIC_H */
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 9e6fdd3..bfbd707 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -273,6 +273,12 @@
 #define ICH_LR_ACTIVE_BIT		(1ULL << 63)
 #define ICH_LR_PHYS_ID_SHIFT		32
 #define ICH_LR_PHYS_ID_MASK		(0x3ffULL << ICH_LR_PHYS_ID_SHIFT)
+#define ICH_LR_PRIORITY_SHIFT		48
+
+/* These are for GICv2 emulation only */
+#define GICH_LR_VIRTUALID		(0x3ffUL << 0)
+#define GICH_LR_PHYSID_CPUID_SHIFT	(10)
+#define GICH_LR_PHYSID_CPUID		(7UL << GICH_LR_PHYSID_CPUID_SHIFT)
 
 #define ICH_MISR_EOI			(1 << 0)
 #define ICH_MISR_U			(1 << 1)
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index 9c94026..fd05185 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -33,6 +33,7 @@
 
 #define GIC_DIST_CTRL			0x000
 #define GIC_DIST_CTR			0x004
+#define GIC_DIST_IIDR			0x008
 #define GIC_DIST_IGROUP			0x080
 #define GIC_DIST_ENABLE_SET		0x100
 #define GIC_DIST_ENABLE_CLEAR		0x180
@@ -76,6 +77,7 @@
 #define GICH_LR_VIRTUALID		(0x3ff << 0)
 #define GICH_LR_PHYSID_CPUID_SHIFT	(10)
 #define GICH_LR_PHYSID_CPUID		(0x3ff << GICH_LR_PHYSID_CPUID_SHIFT)
+#define GICH_LR_PRIORITY_SHIFT		23
 #define GICH_LR_STATE			(3 << 28)
 #define GICH_LR_PENDING_BIT		(1 << 28)
 #define GICH_LR_ACTIVE_BIT		(1 << 29)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index b1fa8f1..1c9c973 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -412,6 +412,8 @@ struct kvm {
 #endif
 	long tlbs_dirty;
 	struct list_head devices;
+	struct dentry *debugfs_dentry;
+	struct kvm_stat_data **debugfs_stat_data;
 };
 
 #define kvm_err(fmt, ...) \
@@ -991,6 +993,11 @@ enum kvm_stat_kind {
 	KVM_STAT_VCPU,
 };
 
+struct kvm_stat_data {
+	int offset;
+	struct kvm *kvm;
+};
+
 struct kvm_stats_debugfs_item {
 	const char *name;
 	int offset;
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 526fb3d..f28292d 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -108,7 +108,7 @@ TRACE_EVENT(kvm_ioapic_set_irq,
 		__entry->coalesced	= coalesced;
 	),
 
-	TP_printk("pin %u dst %x vec=%u (%s|%s|%s%s)%s",
+	TP_printk("pin %u dst %x vec %u (%s|%s|%s%s)%s",
 		  __entry->pin, (u8)(__entry->e >> 56), (u8)__entry->e,
 		  __print_symbolic((__entry->e >> 8 & 0x7), kvm_deliver_mode),
 		  (__entry->e & (1<<11)) ? "logical" : "physical",
@@ -129,7 +129,7 @@ TRACE_EVENT(kvm_ioapic_delayed_eoi_inj,
 		__entry->e		= e;
 	),
 
-	TP_printk("dst %x vec=%u (%s|%s|%s%s)",
+	TP_printk("dst %x vec %u (%s|%s|%s%s)",
 		  (u8)(__entry->e >> 56), (u8)__entry->e,
 		  __print_symbolic((__entry->e >> 8 & 0x7), kvm_deliver_mode),
 		  (__entry->e & (1<<11)) ? "logical" : "physical",
@@ -151,7 +151,7 @@ TRACE_EVENT(kvm_msi_set_irq,
 		__entry->data		= data;
 	),
 
-	TP_printk("dst %u vec %x (%s|%s|%s%s)",
+	TP_printk("dst %u vec %u (%s|%s|%s%s)",
 		  (u8)(__entry->address >> 12), (u8)__entry->data,
 		  __print_symbolic((__entry->data >> 8 & 0x7), kvm_deliver_mode),
 		  (__entry->address & (1<<2)) ? "logical" : "physical",