diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig index f1f79d104309..bfb915d05665 100644 --- a/arch/arm/kvm/Kconfig +++ b/arch/arm/kvm/Kconfig @@ -28,6 +28,7 @@ config KVM select KVM_GENERIC_DIRTYLOG_READ_PROTECT select SRCU select MMU_NOTIFIER + select KVM_VFIO select HAVE_KVM_EVENTFD select HAVE_KVM_IRQFD depends on ARM_VIRT_EXT && ARM_LPAE && ARM_ARCH_TIMER diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile index 139e46c08b6e..c5eef02c52ba 100644 --- a/arch/arm/kvm/Makefile +++ b/arch/arm/kvm/Makefile @@ -15,7 +15,7 @@ AFLAGS_init.o := -Wa,-march=armv7-a$(plus_virt) AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt) KVM := ../../../virt/kvm -kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o +kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o obj-y += kvm-arm.o init.o interrupts.o obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index e41cb11f71b2..bc738d2b8392 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -171,7 +171,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) int r; switch (ext) { case KVM_CAP_IRQCHIP: - case KVM_CAP_IRQFD: case KVM_CAP_IOEVENTFD: case KVM_CAP_DEVICE_CTRL: case KVM_CAP_USER_MEMORY: @@ -532,6 +531,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) kvm_vgic_flush_hwstate(vcpu); kvm_timer_flush_hwstate(vcpu); + preempt_disable(); local_irq_disable(); /* @@ -544,6 +544,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) if (ret <= 0 || need_new_vmid_gen(vcpu->kvm)) { local_irq_enable(); + preempt_enable(); kvm_timer_sync_hwstate(vcpu); kvm_vgic_sync_hwstate(vcpu); continue; @@ -559,8 +560,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) ret = kvm_call_hyp(__kvm_vcpu_run, vcpu); vcpu->mode = OUTSIDE_GUEST_MODE; - __kvm_guest_exit(); - trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu)); + /* + * Back from guest + *************************************************************/ + /* * We may have taken a host interrupt in HYP mode (ie * while executing the guest). This interrupt is still @@ -574,8 +577,17 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) local_irq_enable(); /* - * Back from guest - *************************************************************/ + * We do local_irq_enable() before calling kvm_guest_exit() so + * that if a timer interrupt hits while running the guest we + * account that tick as being spent in the guest. We enable + * preemption after calling kvm_guest_exit() so that if we get + * preempted we make sure ticks after that is not counted as + * guest time. + */ + kvm_guest_exit(); + trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu)); + preempt_enable(); + kvm_timer_sync_hwstate(vcpu); kvm_vgic_sync_hwstate(vcpu); diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S index 79caf79b304a..f7db3a5d80e3 100644 --- a/arch/arm/kvm/interrupts.S +++ b/arch/arm/kvm/interrupts.S @@ -170,13 +170,9 @@ __kvm_vcpu_return: @ Don't trap coprocessor accesses for host kernel set_hstr vmexit set_hdcr vmexit - set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)) + set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)), after_vfp_restore #ifdef CONFIG_VFPv3 - @ Save floating point registers we if let guest use them. - tst r2, #(HCPTR_TCP(10) | HCPTR_TCP(11)) - bne after_vfp_restore - @ Switch VFP/NEON hardware state to the host's add r7, vcpu, #VCPU_VFP_GUEST store_vfp_state r7 @@ -188,6 +184,8 @@ after_vfp_restore: @ Restore FPEXC_EN which we clobbered on entry pop {r2} VFPFMXR FPEXC, r2 +#else +after_vfp_restore: #endif @ Reset Hyp-role @@ -483,7 +481,7 @@ switch_to_guest_vfp: push {r3-r7} @ NEON/VFP used. Turn on VFP access. - set_hcptr vmexit, (HCPTR_TCP(10) | HCPTR_TCP(11)) + set_hcptr vmtrap, (HCPTR_TCP(10) | HCPTR_TCP(11)) @ Switch VFP/NEON hardware state to the guest's add r7, r0, #VCPU_VFP_HOST diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S index 35e4a3a0c476..702740d37465 100644 --- a/arch/arm/kvm/interrupts_head.S +++ b/arch/arm/kvm/interrupts_head.S @@ -412,7 +412,6 @@ vcpu .req r0 @ vcpu pointer always in r0 add r11, vcpu, #VCPU_VGIC_CPU /* Save all interesting registers */ - ldr r3, [r2, #GICH_HCR] ldr r4, [r2, #GICH_VMCR] ldr r5, [r2, #GICH_MISR] ldr r6, [r2, #GICH_EISR0] @@ -420,7 +419,6 @@ vcpu .req r0 @ vcpu pointer always in r0 ldr r8, [r2, #GICH_ELRSR0] ldr r9, [r2, #GICH_ELRSR1] ldr r10, [r2, #GICH_APR] -ARM_BE8(rev r3, r3 ) ARM_BE8(rev r4, r4 ) ARM_BE8(rev r5, r5 ) ARM_BE8(rev r6, r6 ) @@ -429,7 +427,6 @@ ARM_BE8(rev r8, r8 ) ARM_BE8(rev r9, r9 ) ARM_BE8(rev r10, r10 ) - str r3, [r11, #VGIC_V2_CPU_HCR] str r4, [r11, #VGIC_V2_CPU_VMCR] str r5, [r11, #VGIC_V2_CPU_MISR] #ifdef CONFIG_CPU_ENDIAN_BE8 @@ -591,8 +588,13 @@ ARM_BE8(rev r6, r6 ) .endm /* Configures the HCPTR (Hyp Coprocessor Trap Register) on entry/return - * (hardware reset value is 0). Keep previous value in r2. */ -.macro set_hcptr operation, mask + * (hardware reset value is 0). Keep previous value in r2. + * An ISB is emited on vmexit/vmtrap, but executed on vmexit only if + * VFP wasn't already enabled (always executed on vmtrap). + * If a label is specified with vmexit, it is branched to if VFP wasn't + * enabled. + */ +.macro set_hcptr operation, mask, label = none mrc p15, 4, r2, c1, c1, 2 ldr r3, =\mask .if \operation == vmentry @@ -601,6 +603,17 @@ ARM_BE8(rev r6, r6 ) bic r3, r2, r3 @ Don't trap defined coproc-accesses .endif mcr p15, 4, r3, c1, c1, 2 + .if \operation != vmentry + .if \operation == vmexit + tst r2, #(HCPTR_TCP(10) | HCPTR_TCP(11)) + beq 1f + .endif + isb + .if \label != none + b \label + .endif +1: + .endif .endm /* Configures the HDCR (Hyp Debug Configuration Register) on entry/return diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 7f473e6d3bf5..7b4201294187 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -691,8 +691,8 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm) * work. This is not used by the hardware and we have no * alignment requirement for this allocation. */ - pgd = (pgd_t *)kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t), - GFP_KERNEL | __GFP_ZERO); + pgd = kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t), + GFP_KERNEL | __GFP_ZERO); if (!pgd) { kvm_free_hwpgd(hwpgd); diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c index 02fa8eff6ae1..531e922486b2 100644 --- a/arch/arm/kvm/psci.c +++ b/arch/arm/kvm/psci.c @@ -230,10 +230,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) case PSCI_0_2_FN64_AFFINITY_INFO: val = kvm_psci_vcpu_affinity_info(vcpu); break; - case PSCI_0_2_FN_MIGRATE: - case PSCI_0_2_FN64_MIGRATE: - val = PSCI_RET_NOT_SUPPORTED; - break; case PSCI_0_2_FN_MIGRATE_INFO_TYPE: /* * Trusted OS is MP hence does not require migration @@ -242,10 +238,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) */ val = PSCI_0_2_TOS_MP; break; - case PSCI_0_2_FN_MIGRATE_INFO_UP_CPU: - case PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU: - val = PSCI_RET_NOT_SUPPORTED; - break; case PSCI_0_2_FN_SYSTEM_OFF: kvm_psci_system_off(vcpu); /* @@ -271,7 +263,8 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) ret = 0; break; default: - return -EINVAL; + val = PSCI_RET_NOT_SUPPORTED; + break; } *vcpu_reg(vcpu, 0) = val; @@ -291,12 +284,9 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) case KVM_PSCI_FN_CPU_ON: val = kvm_psci_vcpu_on(vcpu); break; - case KVM_PSCI_FN_CPU_SUSPEND: - case KVM_PSCI_FN_MIGRATE: + default: val = PSCI_RET_NOT_SUPPORTED; break; - default: - return -EINVAL; } *vcpu_reg(vcpu, 0) = val; diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 5105e297ed5f..bfffe8f4bd53 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -28,6 +28,7 @@ config KVM select KVM_ARM_HOST select KVM_GENERIC_DIRTYLOG_READ_PROTECT select SRCU + select KVM_VFIO select HAVE_KVM_EVENTFD select HAVE_KVM_IRQFD ---help--- diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index d5904f876cdb..f90f4aa7f88d 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -11,7 +11,7 @@ ARM=../../../arch/arm/kvm obj-$(CONFIG_KVM_ARM_HOST) += kvm.o -kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o +kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/arm.o $(ARM)/mmu.o $(ARM)/mmio.o kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/psci.o $(ARM)/perf.o diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S index 5befd010e232..519805f71876 100644 --- a/arch/arm64/kvm/hyp.S +++ b/arch/arm64/kvm/hyp.S @@ -50,8 +50,8 @@ stp x29, lr, [x3, #80] mrs x19, sp_el0 - mrs x20, elr_el2 // EL1 PC - mrs x21, spsr_el2 // EL1 pstate + mrs x20, elr_el2 // pc before entering el2 + mrs x21, spsr_el2 // pstate before entering el2 stp x19, x20, [x3, #96] str x21, [x3, #112] @@ -82,8 +82,8 @@ ldr x21, [x3, #16] msr sp_el0, x19 - msr elr_el2, x20 // EL1 PC - msr spsr_el2, x21 // EL1 pstate + msr elr_el2, x20 // pc on return from el2 + msr spsr_el2, x21 // pstate on return from el2 add x3, x2, #CPU_XREG_OFFSET(19) ldp x19, x20, [x3] diff --git a/arch/arm64/kvm/vgic-v2-switch.S b/arch/arm64/kvm/vgic-v2-switch.S index f002fe1c3700..3f000712a85d 100644 --- a/arch/arm64/kvm/vgic-v2-switch.S +++ b/arch/arm64/kvm/vgic-v2-switch.S @@ -47,7 +47,6 @@ __save_vgic_v2_state: add x3, x0, #VCPU_VGIC_CPU /* Save all interesting registers */ - ldr w4, [x2, #GICH_HCR] ldr w5, [x2, #GICH_VMCR] ldr w6, [x2, #GICH_MISR] ldr w7, [x2, #GICH_EISR0] @@ -55,7 +54,6 @@ __save_vgic_v2_state: ldr w9, [x2, #GICH_ELRSR0] ldr w10, [x2, #GICH_ELRSR1] ldr w11, [x2, #GICH_APR] -CPU_BE( rev w4, w4 ) CPU_BE( rev w5, w5 ) CPU_BE( rev w6, w6 ) CPU_BE( rev w7, w7 ) @@ -64,7 +62,6 @@ CPU_BE( rev w9, w9 ) CPU_BE( rev w10, w10 ) CPU_BE( rev w11, w11 ) - str w4, [x3, #VGIC_V2_CPU_HCR] str w5, [x3, #VGIC_V2_CPU_VMCR] str w6, [x3, #VGIC_V2_CPU_MISR] CPU_LE( str w7, [x3, #VGIC_V2_CPU_EISR] ) diff --git a/arch/arm64/kvm/vgic-v3-switch.S b/arch/arm64/kvm/vgic-v3-switch.S index 617a012a0107..3c20730ddff5 100644 --- a/arch/arm64/kvm/vgic-v3-switch.S +++ b/arch/arm64/kvm/vgic-v3-switch.S @@ -48,13 +48,11 @@ dsb st // Save all interesting registers - mrs_s x4, ICH_HCR_EL2 mrs_s x5, ICH_VMCR_EL2 mrs_s x6, ICH_MISR_EL2 mrs_s x7, ICH_EISR_EL2 mrs_s x8, ICH_ELSR_EL2 - str w4, [x3, #VGIC_V3_CPU_HCR] str w5, [x3, #VGIC_V3_CPU_VMCR] str w6, [x3, #VGIC_V3_CPU_MISR] str w7, [x3, #VGIC_V3_CPU_EISR] diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 5ff1038437e3..716ad4ae4d4b 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -897,7 +897,7 @@ struct kvm_xen_hvm_config { * * KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies * the irqfd to operate in resampling mode for level triggered interrupt - * emlation. See Documentation/virtual/kvm/api.txt. + * emulation. See Documentation/virtual/kvm/api.txt. */ #define KVM_IRQFD_FLAG_RESAMPLE (1 << 1) diff --git a/virt/kvm/arm/vgic-v3-emul.c b/virt/kvm/arm/vgic-v3-emul.c index e9c3a7a83833..e661e7fb9d91 100644 --- a/virt/kvm/arm/vgic-v3-emul.c +++ b/virt/kvm/arm/vgic-v3-emul.c @@ -76,8 +76,6 @@ static bool handle_mmio_ctlr(struct kvm_vcpu *vcpu, vgic_reg_access(mmio, ®, offset, ACCESS_READ_VALUE | ACCESS_WRITE_VALUE); if (mmio->is_write) { - if (reg & GICD_CTLR_ENABLE_SS_G0) - kvm_info("guest tried to enable unsupported Group0 interrupts\n"); vcpu->kvm->arch.vgic.enabled = !!(reg & GICD_CTLR_ENABLE_SS_G1); vgic_update_state(vcpu->kvm); return true; @@ -173,6 +171,32 @@ static bool handle_mmio_clear_pending_reg_dist(struct kvm_vcpu *vcpu, return false; } +static bool handle_mmio_set_active_reg_dist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + if (likely(offset >= VGIC_NR_PRIVATE_IRQS / 8)) + return vgic_handle_set_active_reg(vcpu->kvm, mmio, offset, + vcpu->vcpu_id); + + vgic_reg_access(mmio, NULL, offset, + ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED); + return false; +} + +static bool handle_mmio_clear_active_reg_dist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + if (likely(offset >= VGIC_NR_PRIVATE_IRQS / 8)) + return vgic_handle_clear_active_reg(vcpu->kvm, mmio, offset, + vcpu->vcpu_id); + + vgic_reg_access(mmio, NULL, offset, + ACCESS_READ_RAZ | ACCESS_WRITE_IGNORED); + return false; +} + static bool handle_mmio_priority_reg_dist(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio, phys_addr_t offset) @@ -428,13 +452,13 @@ static const struct vgic_io_range vgic_v3_dist_ranges[] = { .base = GICD_ISACTIVER, .len = 0x80, .bits_per_irq = 1, - .handle_mmio = handle_mmio_raz_wi, + .handle_mmio = handle_mmio_set_active_reg_dist, }, { .base = GICD_ICACTIVER, .len = 0x80, .bits_per_irq = 1, - .handle_mmio = handle_mmio_raz_wi, + .handle_mmio = handle_mmio_clear_active_reg_dist, }, { .base = GICD_IPRIORITYR, @@ -561,6 +585,26 @@ static bool handle_mmio_clear_enable_reg_redist(struct kvm_vcpu *vcpu, ACCESS_WRITE_CLEARBIT); } +static bool handle_mmio_set_active_reg_redist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + struct kvm_vcpu *redist_vcpu = mmio->private; + + return vgic_handle_set_active_reg(vcpu->kvm, mmio, offset, + redist_vcpu->vcpu_id); +} + +static bool handle_mmio_clear_active_reg_redist(struct kvm_vcpu *vcpu, + struct kvm_exit_mmio *mmio, + phys_addr_t offset) +{ + struct kvm_vcpu *redist_vcpu = mmio->private; + + return vgic_handle_clear_active_reg(vcpu->kvm, mmio, offset, + redist_vcpu->vcpu_id); +} + static bool handle_mmio_set_pending_reg_redist(struct kvm_vcpu *vcpu, struct kvm_exit_mmio *mmio, phys_addr_t offset) @@ -674,13 +718,13 @@ static const struct vgic_io_range vgic_redist_ranges[] = { .base = SGI_base(GICR_ISACTIVER0), .len = 0x04, .bits_per_irq = 1, - .handle_mmio = handle_mmio_raz_wi, + .handle_mmio = handle_mmio_set_active_reg_redist, }, { .base = SGI_base(GICR_ICACTIVER0), .len = 0x04, .bits_per_irq = 1, - .handle_mmio = handle_mmio_raz_wi, + .handle_mmio = handle_mmio_clear_active_reg_redist, }, { .base = SGI_base(GICR_IPRIORITYR0), diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index 78fb8201014f..f94d887d20e6 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -26,8 +26,6 @@ #include #include -#include - #include #include #include @@ -1561,7 +1559,7 @@ int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num, goto out; } - if (irq_num >= kvm->arch.vgic.nr_irqs) + if (irq_num >= min(kvm->arch.vgic.nr_irqs, 1020)) return -EINVAL; vcpu_id = vgic_update_irq_pending(kvm, cpuid, irq_num, level); @@ -2161,10 +2159,7 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, BUG_ON(!vgic_initialized(kvm)); - if (spi > kvm->arch.vgic.nr_irqs) - return -EINVAL; return kvm_vgic_inject_irq(kvm, 0, spi, level); - } /* MSI not implemented yet */