Merge tag 'kvm-4.9-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Radim Krčmář:
 "All architectures:
   - move `make kvmconfig` stubs from x86
   - use 64 bits for debugfs stats

  ARM:
   - Important fixes for not using an in-kernel irqchip
   - handle SError exceptions and present them to guests if appropriate
   - proxying of GICV access at EL2 if guest mappings are unsafe
   - GICv3 on AArch32 on ARMv8
   - preparations for GICv3 save/restore, including ABI docs
   - cleanups and a bit of optimizations

  MIPS:
   - A couple of fixes in preparation for supporting MIPS EVA host
     kernels
   - MIPS SMP host & TLB invalidation fixes

  PPC:
   - Fix the bug which caused guests to falsely report lockups
   - other minor fixes
   - a small optimization

  s390:
   - Lazy enablement of runtime instrumentation
   - up to 255 CPUs for nested guests
   - rework of machine check deliver
   - cleanups and fixes

  x86:
   - IOMMU part of AMD's AVIC for vmexit-less interrupt delivery
   - Hyper-V TSC page
   - per-vcpu tsc_offset in debugfs
   - accelerated INS/OUTS in nVMX
   - cleanups and fixes"

* tag 'kvm-4.9-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (140 commits)
  KVM: MIPS: Drop dubious EntryHi optimisation
  KVM: MIPS: Invalidate TLB by regenerating ASIDs
  KVM: MIPS: Split kernel/user ASID regeneration
  KVM: MIPS: Drop other CPU ASIDs on guest MMU changes
  KVM: arm/arm64: vgic: Don't flush/sync without a working vgic
  KVM: arm64: Require in-kernel irqchip for PMU support
  KVM: PPC: Book3s PR: Allow access to unprivileged MMCR2 register
  KVM: PPC: Book3S PR: Support 64kB page size on POWER8E and POWER8NVL
  KVM: PPC: Book3S: Remove duplicate setting of the B field in tlbie
  KVM: PPC: BookE: Fix a sanity check
  KVM: PPC: Book3S HV: Take out virtual core piggybacking code
  KVM: PPC: Book3S: Treat VTB as a per-subcore register, not per-thread
  ARM: gic-v3: Work around definition of gic_write_bpr1
  KVM: nVMX: Fix the NMI IDT-vectoring handling
  KVM: VMX: Enable MSR-BASED TPR shadow even if APICv is inactive
  KVM: nVMX: Fix reload apic access page warning
  kvmconfig: add virtio-gpu to config fragment
  config: move x86 kvm_guest.config to a common location
  arm64: KVM: Remove duplicating init code for setting VMID
  ARM: KVM: Support vgic-v3
  ...

9 files changed, 151 insertions, 70 deletions

diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h
index dfe4002812da..a8088290b778 100644
--- a/arch/arm/include/asm/arch_gicv3.h
+++ b/arch/arm/include/asm/arch_gicv3.h
@@ -22,9 +22,7 @@
 
 #include <linux/io.h>
 #include <asm/barrier.h>
-
-#define __ACCESS_CP15(CRn, Op1, CRm, Op2)	p15, Op1, %0, CRn, CRm, Op2
-#define __ACCESS_CP15_64(Op1, CRm)		p15, Op1, %Q0, %R0, CRm
+#include <asm/cp15.h>
 
 #define ICC_EOIR1			__ACCESS_CP15(c12, 0, c12, 1)
 #define ICC_DIR				__ACCESS_CP15(c12, 0, c11, 1)
@@ -99,68 +97,129 @@
 #define ICH_AP1R2			__AP1Rx(2)
 #define ICH_AP1R3			__AP1Rx(3)
 
+/* A32-to-A64 mappings used by VGIC save/restore */
+
+#define CPUIF_MAP(a32, a64)			\
+static inline void write_ ## a64(u32 val)	\
+{						\
+	write_sysreg(val, a32);			\
+}						\
+static inline u32 read_ ## a64(void)		\
+{						\
+	return read_sysreg(a32); 		\
+}						\
+
+#define CPUIF_MAP_LO_HI(a32lo, a32hi, a64)	\
+static inline void write_ ## a64(u64 val)	\
+{						\
+	write_sysreg(lower_32_bits(val), a32lo);\
+	write_sysreg(upper_32_bits(val), a32hi);\
+}						\
+static inline u64 read_ ## a64(void)		\
+{						\
+	u64 val = read_sysreg(a32lo);		\
+						\
+	val |=	(u64)read_sysreg(a32hi) << 32;	\
+						\
+	return val; 				\
+}
+
+CPUIF_MAP(ICH_HCR, ICH_HCR_EL2)
+CPUIF_MAP(ICH_VTR, ICH_VTR_EL2)
+CPUIF_MAP(ICH_MISR, ICH_MISR_EL2)
+CPUIF_MAP(ICH_EISR, ICH_EISR_EL2)
+CPUIF_MAP(ICH_ELSR, ICH_ELSR_EL2)
+CPUIF_MAP(ICH_VMCR, ICH_VMCR_EL2)
+CPUIF_MAP(ICH_AP0R3, ICH_AP0R3_EL2)
+CPUIF_MAP(ICH_AP0R2, ICH_AP0R2_EL2)
+CPUIF_MAP(ICH_AP0R1, ICH_AP0R1_EL2)
+CPUIF_MAP(ICH_AP0R0, ICH_AP0R0_EL2)
+CPUIF_MAP(ICH_AP1R3, ICH_AP1R3_EL2)
+CPUIF_MAP(ICH_AP1R2, ICH_AP1R2_EL2)
+CPUIF_MAP(ICH_AP1R1, ICH_AP1R1_EL2)
+CPUIF_MAP(ICH_AP1R0, ICH_AP1R0_EL2)
+CPUIF_MAP(ICC_HSRE, ICC_SRE_EL2)
+CPUIF_MAP(ICC_SRE, ICC_SRE_EL1)
+
+CPUIF_MAP_LO_HI(ICH_LR15, ICH_LRC15, ICH_LR15_EL2)
+CPUIF_MAP_LO_HI(ICH_LR14, ICH_LRC14, ICH_LR14_EL2)
+CPUIF_MAP_LO_HI(ICH_LR13, ICH_LRC13, ICH_LR13_EL2)
+CPUIF_MAP_LO_HI(ICH_LR12, ICH_LRC12, ICH_LR12_EL2)
+CPUIF_MAP_LO_HI(ICH_LR11, ICH_LRC11, ICH_LR11_EL2)
+CPUIF_MAP_LO_HI(ICH_LR10, ICH_LRC10, ICH_LR10_EL2)
+CPUIF_MAP_LO_HI(ICH_LR9, ICH_LRC9, ICH_LR9_EL2)
+CPUIF_MAP_LO_HI(ICH_LR8, ICH_LRC8, ICH_LR8_EL2)
+CPUIF_MAP_LO_HI(ICH_LR7, ICH_LRC7, ICH_LR7_EL2)
+CPUIF_MAP_LO_HI(ICH_LR6, ICH_LRC6, ICH_LR6_EL2)
+CPUIF_MAP_LO_HI(ICH_LR5, ICH_LRC5, ICH_LR5_EL2)
+CPUIF_MAP_LO_HI(ICH_LR4, ICH_LRC4, ICH_LR4_EL2)
+CPUIF_MAP_LO_HI(ICH_LR3, ICH_LRC3, ICH_LR3_EL2)
+CPUIF_MAP_LO_HI(ICH_LR2, ICH_LRC2, ICH_LR2_EL2)
+CPUIF_MAP_LO_HI(ICH_LR1, ICH_LRC1, ICH_LR1_EL2)
+CPUIF_MAP_LO_HI(ICH_LR0, ICH_LRC0, ICH_LR0_EL2)
+
+#define read_gicreg(r)                 read_##r()
+#define write_gicreg(v, r)             write_##r(v)
+
 /* Low-level accessors */
 
 static inline void gic_write_eoir(u32 irq)
 {
-	asm volatile("mcr " __stringify(ICC_EOIR1) : : "r" (irq));
+	write_sysreg(irq, ICC_EOIR1);
 	isb();
 }
 
 static inline void gic_write_dir(u32 val)
 {
-	asm volatile("mcr " __stringify(ICC_DIR) : : "r" (val));
+	write_sysreg(val, ICC_DIR);
 	isb();
 }
 
 static inline u32 gic_read_iar(void)
 {
-	u32 irqstat;
+	u32 irqstat = read_sysreg(ICC_IAR1);
 
-	asm volatile("mrc " __stringify(ICC_IAR1) : "=r" (irqstat));
 	dsb(sy);
+
 	return irqstat;
 }
 
 static inline void gic_write_pmr(u32 val)
 {
-	asm volatile("mcr " __stringify(ICC_PMR) : : "r" (val));
+	write_sysreg(val, ICC_PMR);
 }
 
 static inline void gic_write_ctlr(u32 val)
 {
-	asm volatile("mcr " __stringify(ICC_CTLR) : : "r" (val));
+	write_sysreg(val, ICC_CTLR);
 	isb();
 }
 
 static inline void gic_write_grpen1(u32 val)
 {
-	asm volatile("mcr " __stringify(ICC_IGRPEN1) : : "r" (val));
+	write_sysreg(val, ICC_IGRPEN1);
 	isb();
 }
 
 static inline void gic_write_sgi1r(u64 val)
 {
-	asm volatile("mcrr " __stringify(ICC_SGI1R) : : "r" (val));
+	write_sysreg(val, ICC_SGI1R);
 }
 
 static inline u32 gic_read_sre(void)
 {
-	u32 val;
-
-	asm volatile("mrc " __stringify(ICC_SRE) : "=r" (val));
-	return val;
+	return read_sysreg(ICC_SRE);
 }
 
 static inline void gic_write_sre(u32 val)
 {
-	asm volatile("mcr " __stringify(ICC_SRE) : : "r" (val));
+	write_sysreg(val, ICC_SRE);
 	isb();
 }
 
 static inline void gic_write_bpr1(u32 val)
 {
-	asm volatile("mcr " __stringify(ICC_BPR1) : : "r" (val));
+	write_sysreg(val, ICC_BPR1);
 }
 
 /*
diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h
index c3f11524f10c..dbdbce1b3a72 100644
--- a/arch/arm/include/asm/cp15.h
+++ b/arch/arm/include/asm/cp15.h
@@ -49,6 +49,21 @@
 
 #ifdef CONFIG_CPU_CP15
 
+#define __ACCESS_CP15(CRn, Op1, CRm, Op2)	\
+	"mrc", "mcr", __stringify(p15, Op1, %0, CRn, CRm, Op2), u32
+#define __ACCESS_CP15_64(Op1, CRm)		\
+	"mrrc", "mcrr", __stringify(p15, Op1, %Q0, %R0, CRm), u64
+
+#define __read_sysreg(r, w, c, t) ({				\
+	t __val;						\
+	asm volatile(r " " c : "=r" (__val));			\
+	__val;							\
+})
+#define read_sysreg(...)		__read_sysreg(__VA_ARGS__)
+
+#define __write_sysreg(v, r, w, c, t)	asm volatile(w " " c : : "r" ((t)(v)))
+#define write_sysreg(v, ...)		__write_sysreg(v, __VA_ARGS__)
+
 extern unsigned long cr_alignment;	/* defined in entry-armv.S */
 
 static inline unsigned long get_cr(void)
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index 754f86f667d4..522b5feb4eaa 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -55,6 +55,7 @@
 
 #define MPIDR_LEVEL_BITS 8
 #define MPIDR_LEVEL_MASK ((1 << MPIDR_LEVEL_BITS) - 1)
+#define MPIDR_LEVEL_SHIFT(level) (MPIDR_LEVEL_BITS * level)
 
 #define MPIDR_AFFINITY_LEVEL(mpidr, level) \
 	((mpidr >> (MPIDR_LEVEL_BITS * level)) & MPIDR_LEVEL_MASK)
diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h
index 58faff5f1eb2..d7ea6bcb29bf 100644
--- a/arch/arm/include/asm/kvm_asm.h
+++ b/arch/arm/include/asm/kvm_asm.h
@@ -21,6 +21,10 @@
 
 #include <asm/virt.h>
 
+#define ARM_EXIT_WITH_ABORT_BIT  31
+#define ARM_EXCEPTION_CODE(x)	  ((x) & ~(1U << ARM_EXIT_WITH_ABORT_BIT))
+#define ARM_ABORT_PENDING(x)	  !!((x) & (1U << ARM_EXIT_WITH_ABORT_BIT))
+
 #define ARM_EXCEPTION_RESET	  0
 #define ARM_EXCEPTION_UNDEFINED   1
 #define ARM_EXCEPTION_SOFTWARE    2
@@ -68,6 +72,9 @@ extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 extern void __init_stage2_translation(void);
 
 extern void __kvm_hyp_reset(unsigned long);
+
+extern u64 __vgic_v3_get_ich_vtr_el2(void);
+extern void __vgic_v3_init_lrs(void);
 #endif
 
 #endif /* __ARM_KVM_ASM_H__ */
diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index ee5328fc4b06..9a8a45aaf19a 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -40,18 +40,29 @@ static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num,
 	*vcpu_reg(vcpu, reg_num) = val;
 }
 
-bool kvm_condition_valid(struct kvm_vcpu *vcpu);
-void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr);
+bool kvm_condition_valid32(const struct kvm_vcpu *vcpu);
+void kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr);
 void kvm_inject_undefined(struct kvm_vcpu *vcpu);
+void kvm_inject_vabt(struct kvm_vcpu *vcpu);
 void kvm_inject_dabt(struct kvm_vcpu *vcpu, unsigned long addr);
 void kvm_inject_pabt(struct kvm_vcpu *vcpu, unsigned long addr);
 
+static inline bool kvm_condition_valid(const struct kvm_vcpu *vcpu)
+{
+	return kvm_condition_valid32(vcpu);
+}
+
+static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr)
+{
+	kvm_skip_instr32(vcpu, is_wide_instr);
+}
+
 static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.hcr = HCR_GUEST_MASK;
 }
 
-static inline unsigned long vcpu_get_hcr(struct kvm_vcpu *vcpu)
+static inline unsigned long vcpu_get_hcr(const struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.hcr;
 }
@@ -61,7 +72,7 @@ static inline void vcpu_set_hcr(struct kvm_vcpu *vcpu, unsigned long hcr)
 	vcpu->arch.hcr = hcr;
 }
 
-static inline bool vcpu_mode_is_32bit(struct kvm_vcpu *vcpu)
+static inline bool vcpu_mode_is_32bit(const struct kvm_vcpu *vcpu)
 {
 	return 1;
 }
@@ -71,9 +82,9 @@ static inline unsigned long *vcpu_pc(struct kvm_vcpu *vcpu)
 	return &vcpu->arch.ctxt.gp_regs.usr_regs.ARM_pc;
 }
 
-static inline unsigned long *vcpu_cpsr(struct kvm_vcpu *vcpu)
+static inline unsigned long *vcpu_cpsr(const struct kvm_vcpu *vcpu)
 {
-	return &vcpu->arch.ctxt.gp_regs.usr_regs.ARM_cpsr;
+	return (unsigned long *)&vcpu->arch.ctxt.gp_regs.usr_regs.ARM_cpsr;
 }
 
 static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu)
@@ -93,11 +104,21 @@ static inline bool vcpu_mode_priv(struct kvm_vcpu *vcpu)
 	return cpsr_mode > USR_MODE;;
 }
 
-static inline u32 kvm_vcpu_get_hsr(struct kvm_vcpu *vcpu)
+static inline u32 kvm_vcpu_get_hsr(const struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.fault.hsr;
 }
 
+static inline int kvm_vcpu_get_condition(const struct kvm_vcpu *vcpu)
+{
+	u32 hsr = kvm_vcpu_get_hsr(vcpu);
+
+	if (hsr & HSR_CV)
+		return (hsr & HSR_COND) >> HSR_COND_SHIFT;
+
+	return -1;
+}
+
 static inline unsigned long kvm_vcpu_get_hfar(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.fault.hxfar;
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index de338d93d11b..2d19e02d03fd 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -39,7 +39,12 @@
 
 #include <kvm/arm_vgic.h>
 
+
+#ifdef CONFIG_ARM_GIC_V3
+#define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS
+#else
 #define KVM_MAX_VCPUS VGIC_V2_MAX_CPUS
+#endif
 
 #define KVM_REQ_VCPU_EXIT	8
 
@@ -183,15 +188,15 @@ struct kvm_vcpu_arch {
 };
 
 struct kvm_vm_stat {
-	u32 remote_tlb_flush;
+	ulong remote_tlb_flush;
 };
 
 struct kvm_vcpu_stat {
-	u32 halt_successful_poll;
-	u32 halt_attempted_poll;
-	u32 halt_poll_invalid;
-	u32 halt_wakeup;
-	u32 hvc_exit_stat;
+	u64 halt_successful_poll;
+	u64 halt_attempted_poll;
+	u64 halt_poll_invalid;
+	u64 halt_wakeup;
+	u64 hvc_exit_stat;
 	u64 wfe_exit_stat;
 	u64 wfi_exit_stat;
 	u64 mmio_exit_user;
diff --git a/arch/arm/include/asm/kvm_hyp.h b/arch/arm/include/asm/kvm_hyp.h
index 6eaff28f2ff3..343135ede5fa 100644
--- a/arch/arm/include/asm/kvm_hyp.h
+++ b/arch/arm/include/asm/kvm_hyp.h
@@ -20,28 +20,15 @@
 
 #include <linux/compiler.h>
 #include <linux/kvm_host.h>
+#include <asm/cp15.h>
 #include <asm/kvm_mmu.h>
 #include <asm/vfp.h>
 
 #define __hyp_text __section(.hyp.text) notrace
 
-#define __ACCESS_CP15(CRn, Op1, CRm, Op2)	\
-	"mrc", "mcr", __stringify(p15, Op1, %0, CRn, CRm, Op2), u32
-#define __ACCESS_CP15_64(Op1, CRm)		\
-	"mrrc", "mcrr", __stringify(p15, Op1, %Q0, %R0, CRm), u64
 #define __ACCESS_VFP(CRn)			\
 	"mrc", "mcr", __stringify(p10, 7, %0, CRn, cr0, 0), u32
 
-#define __write_sysreg(v, r, w, c, t)	asm volatile(w " " c : : "r" ((t)(v)))
-#define write_sysreg(v, ...)		__write_sysreg(v, __VA_ARGS__)
-
-#define __read_sysreg(r, w, c, t) ({				\
-	t __val;						\
-	asm volatile(r " " c : "=r" (__val));			\
-	__val;							\
-})
-#define read_sysreg(...)		__read_sysreg(__VA_ARGS__)
-
 #define write_special(v, r)					\
 	asm volatile("msr " __stringify(r) ", %0" : : "r" (v))
 #define read_special(r) ({					\
@@ -119,6 +106,9 @@ void __vgic_v2_restore_state(struct kvm_vcpu *vcpu);
 void __sysreg_save_state(struct kvm_cpu_context *ctxt);
 void __sysreg_restore_state(struct kvm_cpu_context *ctxt);
 
+void __vgic_v3_save_state(struct kvm_vcpu *vcpu);
+void __vgic_v3_restore_state(struct kvm_vcpu *vcpu);
+
 void asmlinkage __vfp_save_state(struct vfp_hard_struct *vfp);
 void asmlinkage __vfp_restore_state(struct vfp_hard_struct *vfp);
 static inline bool __vfp_enabled(void)
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 3bb803d6814b..74a44727f8e1 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -63,37 +63,13 @@ void kvm_clear_hyp_idmap(void);
 static inline void kvm_set_pmd(pmd_t *pmd, pmd_t new_pmd)
 {
 	*pmd = new_pmd;
-	flush_pmd_entry(pmd);
+	dsb(ishst);
 }
 
 static inline void kvm_set_pte(pte_t *pte, pte_t new_pte)
 {
 	*pte = new_pte;
-	/*
-	 * flush_pmd_entry just takes a void pointer and cleans the necessary
-	 * cache entries, so we can reuse the function for ptes.
-	 */
-	flush_pmd_entry(pte);
-}
-
-static inline void kvm_clean_pgd(pgd_t *pgd)
-{
-	clean_dcache_area(pgd, PTRS_PER_S2_PGD * sizeof(pgd_t));
-}
-
-static inline void kvm_clean_pmd(pmd_t *pmd)
-{
-	clean_dcache_area(pmd, PTRS_PER_PMD * sizeof(pmd_t));
-}
-
-static inline void kvm_clean_pmd_entry(pmd_t *pmd)
-{
-	clean_pmd_entry(pmd);
-}
-
-static inline void kvm_clean_pte(pte_t *pte)
-{
-	clean_pte_table(pte);
+	dsb(ishst);
 }
 
 static inline pte_t kvm_s2pte_mkwrite(pte_t pte)
diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h
index a2b3eb313a25..b38c10c73579 100644
--- a/arch/arm/include/uapi/asm/kvm.h
+++ b/arch/arm/include/uapi/asm/kvm.h
@@ -84,6 +84,13 @@ struct kvm_regs {
 #define KVM_VGIC_V2_DIST_SIZE		0x1000
 #define KVM_VGIC_V2_CPU_SIZE		0x2000
 
+/* Supported VGICv3 address types  */
+#define KVM_VGIC_V3_ADDR_TYPE_DIST	2
+#define KVM_VGIC_V3_ADDR_TYPE_REDIST	3
+
+#define KVM_VGIC_V3_DIST_SIZE		SZ_64K
+#define KVM_VGIC_V3_REDIST_SIZE		(2 * SZ_64K)
+
 #define KVM_ARM_VCPU_POWER_OFF		0 /* CPU is started in OFF state */
 #define KVM_ARM_VCPU_PSCI_0_2		1 /* CPU uses PSCI v0.2 */