diff options
88 files changed, 6026 insertions, 1626 deletions
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 0007fef4ed81..b112efc816f1 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -612,11 +612,14 @@ Type: vm ioctl Parameters: none Returns: 0 on success, -1 on error -Creates an interrupt controller model in the kernel. On x86, creates a virtual -ioapic, a virtual PIC (two PICs, nested), and sets up future vcpus to have a -local APIC. IRQ routing for GSIs 0-15 is set to both PIC and IOAPIC; GSI 16-23 -only go to the IOAPIC. On ARM/arm64, a GIC is -created. On s390, a dummy irq routing table is created. +Creates an interrupt controller model in the kernel. +On x86, creates a virtual ioapic, a virtual PIC (two PICs, nested), and sets up +future vcpus to have a local APIC. IRQ routing for GSIs 0-15 is set to both +PIC and IOAPIC; GSI 16-23 only go to the IOAPIC. +On ARM/arm64, a GICv2 is created. Any other GIC versions require the usage of +KVM_CREATE_DEVICE, which also supports creating a GICv2. Using +KVM_CREATE_DEVICE is preferred over KVM_CREATE_IRQCHIP for GICv2. +On s390, a dummy irq routing table is created. Note that on s390 the KVM_CAP_S390_IRQCHIP vm capability needs to be enabled before KVM_CREATE_IRQCHIP can be used. @@ -2312,7 +2315,7 @@ struct kvm_s390_interrupt { type can be one of the following: -KVM_S390_SIGP_STOP (vcpu) - sigp restart +KVM_S390_SIGP_STOP (vcpu) - sigp stop; optional flags in parm KVM_S390_PROGRAM_INT (vcpu) - program check; code in parm KVM_S390_SIGP_SET_PREFIX (vcpu) - sigp set prefix; prefix address in parm KVM_S390_RESTART (vcpu) - restart @@ -3225,3 +3228,23 @@ userspace from doing that. If the hcall number specified is not one that has an in-kernel implementation, the KVM_ENABLE_CAP ioctl will fail with an EINVAL error. + +7.2 KVM_CAP_S390_USER_SIGP + +Architectures: s390 +Parameters: none + +This capability controls which SIGP orders will be handled completely in user +space. With this capability enabled, all fast orders will be handled completely +in the kernel: +- SENSE +- SENSE RUNNING +- EXTERNAL CALL +- EMERGENCY SIGNAL +- CONDITIONAL EMERGENCY SIGNAL + +All other orders will be handled completely in user space. + +Only privileged operation exceptions will be checked for in the kernel (or even +in the hardware prior to interception). If this capability is not enabled, the +old way of handling SIGP orders is used (partially in kernel and user space). diff --git a/Documentation/virtual/kvm/devices/arm-vgic.txt b/Documentation/virtual/kvm/devices/arm-vgic.txt index df8b0c7540b6..3fb905429e8a 100644 --- a/Documentation/virtual/kvm/devices/arm-vgic.txt +++ b/Documentation/virtual/kvm/devices/arm-vgic.txt @@ -3,22 +3,42 @@ ARM Virtual Generic Interrupt Controller (VGIC) Device types supported: KVM_DEV_TYPE_ARM_VGIC_V2 ARM Generic Interrupt Controller v2.0 + KVM_DEV_TYPE_ARM_VGIC_V3 ARM Generic Interrupt Controller v3.0 Only one VGIC instance may be instantiated through either this API or the legacy KVM_CREATE_IRQCHIP api. The created VGIC will act as the VM interrupt controller, requiring emulated user-space devices to inject interrupts to the VGIC instead of directly to CPUs. +Creating a guest GICv3 device requires a host GICv3 as well. +GICv3 implementations with hardware compatibility support allow a guest GICv2 +as well. + Groups: KVM_DEV_ARM_VGIC_GRP_ADDR Attributes: KVM_VGIC_V2_ADDR_TYPE_DIST (rw, 64-bit) Base address in the guest physical address space of the GIC distributor - register mappings. + register mappings. Only valid for KVM_DEV_TYPE_ARM_VGIC_V2. + This address needs to be 4K aligned and the region covers 4 KByte. KVM_VGIC_V2_ADDR_TYPE_CPU (rw, 64-bit) Base address in the guest physical address space of the GIC virtual cpu - interface register mappings. + interface register mappings. Only valid for KVM_DEV_TYPE_ARM_VGIC_V2. + This address needs to be 4K aligned and the region covers 4 KByte. + + KVM_VGIC_V3_ADDR_TYPE_DIST (rw, 64-bit) + Base address in the guest physical address space of the GICv3 distributor + register mappings. Only valid for KVM_DEV_TYPE_ARM_VGIC_V3. + This address needs to be 64K aligned and the region covers 64 KByte. + + KVM_VGIC_V3_ADDR_TYPE_REDIST (rw, 64-bit) + Base address in the guest physical address space of the GICv3 + redistributor register mappings. There are two 64K pages for each + VCPU and all of the redistributor pages are contiguous. + Only valid for KVM_DEV_TYPE_ARM_VGIC_V3. + This address needs to be 64K aligned. + KVM_DEV_ARM_VGIC_GRP_DIST_REGS Attributes: @@ -36,6 +56,7 @@ Groups: the register. Limitations: - Priorities are not implemented, and registers are RAZ/WI + - Currently only implemented for KVM_DEV_TYPE_ARM_VGIC_V2. Errors: -ENODEV: Getting or setting this register is not yet supported -EBUSY: One or more VCPUs are running @@ -68,6 +89,7 @@ Groups: Limitations: - Priorities are not implemented, and registers are RAZ/WI + - Currently only implemented for KVM_DEV_TYPE_ARM_VGIC_V2. Errors: -ENODEV: Getting or setting this register is not yet supported -EBUSY: One or more VCPUs are running @@ -81,3 +103,14 @@ Groups: -EINVAL: Value set is out of the expected range -EBUSY: Value has already be set, or GIC has already been initialized with default values. + + KVM_DEV_ARM_VGIC_GRP_CTRL + Attributes: + KVM_DEV_ARM_VGIC_CTRL_INIT + request the initialization of the VGIC, no additional parameter in + kvm_device_attr.addr. + Errors: + -ENXIO: VGIC not properly configured as required prior to calling + this attribute + -ENODEV: no online VCPU + -ENOMEM: memory shortage when allocating vgic internal data diff --git a/Documentation/virtual/kvm/devices/vm.txt b/Documentation/virtual/kvm/devices/vm.txt index d426fc87fe93..5542c4641a3c 100644 --- a/Documentation/virtual/kvm/devices/vm.txt +++ b/Documentation/virtual/kvm/devices/vm.txt @@ -24,3 +24,62 @@ Returns: 0 Clear the CMMA status for all guest pages, so any pages the guest marked as unused are again used any may not be reclaimed by the host. + +1.3. ATTRIBUTE KVM_S390_VM_MEM_LIMIT_SIZE +Parameters: in attr->addr the address for the new limit of guest memory +Returns: -EFAULT if the given address is not accessible + -EINVAL if the virtual machine is of type UCONTROL + -E2BIG if the given guest memory is to big for that machine + -EBUSY if a vcpu is already defined + -ENOMEM if not enough memory is available for a new shadow guest mapping + 0 otherwise + +Allows userspace to query the actual limit and set a new limit for +the maximum guest memory size. The limit will be rounded up to +2048 MB, 4096 GB, 8192 TB respectively, as this limit is governed by +the number of page table levels. + +2. GROUP: KVM_S390_VM_CPU_MODEL +Architectures: s390 + +2.1. ATTRIBUTE: KVM_S390_VM_CPU_MACHINE (r/o) + +Allows user space to retrieve machine and kvm specific cpu related information: + +struct kvm_s390_vm_cpu_machine { + __u64 cpuid; # CPUID of host + __u32 ibc; # IBC level range offered by host + __u8 pad[4]; + __u64 fac_mask[256]; # set of cpu facilities enabled by KVM + __u64 fac_list[256]; # set of cpu facilities offered by host +} + +Parameters: address of buffer to store the machine related cpu data + of type struct kvm_s390_vm_cpu_machine* +Returns: -EFAULT if the given address is not accessible from kernel space + -ENOMEM if not enough memory is available to process the ioctl + 0 in case of success + +2.2. ATTRIBUTE: KVM_S390_VM_CPU_PROCESSOR (r/w) + +Allows user space to retrieve or request to change cpu related information for a vcpu: + +struct kvm_s390_vm_cpu_processor { + __u64 cpuid; # CPUID currently (to be) used by this vcpu + __u16 ibc; # IBC level currently (to be) used by this vcpu + __u8 pad[6]; + __u64 fac_list[256]; # set of cpu facilities currently (to be) used + # by this vcpu +} + +KVM does not enforce or limit the cpu model data in any form. Take the information +retrieved by means of KVM_S390_VM_CPU_MACHINE as hint for reasonable configuration +setups. Instruction interceptions triggered by additionally set facilitiy bits that +are not handled by KVM need to by imlemented in the VM driver code. + +Parameters: address of buffer to store/set the processor related cpu + data of type struct kvm_s390_vm_cpu_processor*. +Returns: -EBUSY in case 1 or more vcpus are already activated (only in write case) + -EFAULT if the given address is not accessible from kernel space + -ENOMEM if not enough memory is available to process the ioctl + 0 in case of success diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h index 3a67bec72d0c..25410b2d8bc1 100644 --- a/arch/arm/include/asm/kvm_asm.h +++ b/arch/arm/include/asm/kvm_asm.h @@ -96,6 +96,7 @@ extern char __kvm_hyp_code_end[]; extern void __kvm_flush_vm_context(void); extern void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa); +extern void __kvm_tlb_flush_vmid(struct kvm *kvm); extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu); #endif diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index 7b0152321b20..a9c80a2ea1a7 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -23,6 +23,7 @@ #include <asm/kvm_asm.h> #include <asm/kvm_mmio.h> #include <asm/kvm_arm.h> +#include <asm/cputype.h> unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num); unsigned long *vcpu_spsr(struct kvm_vcpu *vcpu); @@ -177,9 +178,9 @@ static inline u32 kvm_vcpu_hvc_get_imm(struct kvm_vcpu *vcpu) return kvm_vcpu_get_hsr(vcpu) & HSR_HVC_IMM_MASK; } -static inline unsigned long kvm_vcpu_get_mpidr(struct kvm_vcpu *vcpu) +static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu) { - return vcpu->arch.cp15[c0_MPIDR]; + return vcpu->arch.cp15[c0_MPIDR] & MPIDR_HWID_BITMASK; } static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu) diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 04b4ea0b550a..41008cd7c53f 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -68,6 +68,7 @@ struct kvm_arch { /* Interrupt controller */ struct vgic_dist vgic; + int max_vcpus; }; #define KVM_NR_MEM_OBJS 40 @@ -144,6 +145,7 @@ struct kvm_vm_stat { }; struct kvm_vcpu_stat { + u32 halt_successful_poll; u32 halt_wakeup; }; @@ -231,6 +233,10 @@ static inline void vgic_arch_setup(const struct vgic_params *vgic) int kvm_perf_init(void); int kvm_perf_teardown(void); +void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot); + +struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); + static inline void kvm_arch_hardware_disable(void) {} static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} diff --git a/arch/arm/include/asm/kvm_mmio.h b/arch/arm/include/asm/kvm_mmio.h index adcc0d7d3175..3f83db2f6cf0 100644 --- a/arch/arm/include/asm/kvm_mmio.h +++ b/arch/arm/include/asm/kvm_mmio.h @@ -37,6 +37,7 @@ struct kvm_exit_mmio { u8 data[8]; u32 len; bool is_write; + void *private; }; static inline void kvm_prepare_mmio(struct kvm_run *run, diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 1bca8f8af442..37ca2a4c6f09 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -115,6 +115,27 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd) pmd_val(*pmd) |= L_PMD_S2_RDWR; } +static inline void kvm_set_s2pte_readonly(pte_t *pte) +{ + pte_val(*pte) = (pte_val(*pte) & ~L_PTE_S2_RDWR) | L_PTE_S2_RDONLY; +} + +static inline bool kvm_s2pte_readonly(pte_t *pte) +{ + return (pte_val(*pte) & L_PTE_S2_RDWR) == L_PTE_S2_RDONLY; +} + +static inline void kvm_set_s2pmd_readonly(pmd_t *pmd) +{ + pmd_val(*pmd) = (pmd_val(*pmd) & ~L_PMD_S2_RDWR) | L_PMD_S2_RDONLY; +} + +static inline bool kvm_s2pmd_readonly(pmd_t *pmd) +{ + return (pmd_val(*pmd) & L_PMD_S2_RDWR) == L_PMD_S2_RDONLY; +} + + /* Open coded p*d_addr_end that can deal with 64bit addresses */ #define kvm_pgd_addr_end(addr, end) \ ({ u64 __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK; \ diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h index 423a5ac09d3a..a745a2a53853 100644 --- a/arch/arm/include/asm/pgtable-3level.h +++ b/arch/arm/include/asm/pgtable-3level.h @@ -129,6 +129,7 @@ #define L_PTE_S2_RDONLY (_AT(pteval_t, 1) << 6) /* HAP[1] */ #define L_PTE_S2_RDWR (_AT(pteval_t, 3) << 6) /* HAP[2:1] */ +#define L_PMD_S2_RDONLY (_AT(pmdval_t, 1) << 6) /* HAP[1] */ #define L_PMD_S2_RDWR (_AT(pmdval_t, 3) << 6) /* HAP[2:1] */ /* diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h index 09ee408c1a67..0db25bc32864 100644 --- a/arch/arm/include/uapi/asm/kvm.h +++ b/arch/arm/include/uapi/asm/kvm.h @@ -175,6 +175,8 @@ struct kvm_arch_memory_slot { #define KVM_DEV_ARM_VGIC_OFFSET_SHIFT 0 #define KVM_DEV_ARM_VGIC_OFFSET_MASK (0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT) #define KVM_DEV_ARM_VGIC_GRP_NR_IRQS 3 +#define KVM_DEV_ARM_VGIC_GRP_CTRL 4 +#define KVM_DEV_ARM_VGIC_CTRL_INIT 0 /* KVM_IRQ_LINE irq field index values */ #define KVM_ARM_IRQ_TYPE_SHIFT 24 diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig index 3afee5f40f4f..338ace78ed18 100644 --- a/arch/arm/kvm/Kconfig +++ b/arch/arm/kvm/Kconfig @@ -21,8 +21,10 @@ config KVM select PREEMPT_NOTIFIERS select ANON_INODES select HAVE_KVM_CPU_RELAX_INTERCEPT + select HAVE_KVM_ARCH_TLB_FLUSH_ALL select KVM_MMIO select KVM_ARM_HOST + select KVM_GENERIC_DIRTYLOG_READ_PROTECT select SRCU depends on ARM_VIRT_EXT && ARM_LPAE ---help--- diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile index f7057ed045b6..443b8bea43e9 100644 --- a/arch/arm/kvm/Makefile +++ b/arch/arm/kvm/Makefile @@ -22,4 +22,5 @@ obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2.o +obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2-emul.o obj-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 0b0d58a905c4..07e7eb1d7ab6 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -132,6 +132,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) /* Mark the initial VMID gene |