From: Joao Martins <joao.m.mart...@oracle.com> Handle the hypercall to set a per vcpu info, and also wire up the default vcpu_info in the shared_info page for the first 32 vCPUs.
To avoid deadlock within KVM a vCPU thread must set its *own* vcpu_info rather than it being set from the context in which the hypercall is invoked. Add the vcpu_info (and default) GPA to the vmstate_x86_cpu for migration, and restore it in kvm_arch_put_registers() appropriately. Signed-off-by: Joao Martins <joao.m.mart...@oracle.com> Signed-off-by: David Woodhouse <d...@amazon.co.uk> --- target/i386/cpu.h | 2 + target/i386/kvm/kvm.c | 19 +++++++++ target/i386/kvm/trace-events | 1 + target/i386/kvm/xen-emu.c | 78 ++++++++++++++++++++++++++++++++++-- target/i386/kvm/xen-emu.h | 1 + target/i386/machine.c | 21 ++++++++++ 6 files changed, 119 insertions(+), 3 deletions(-) diff --git a/target/i386/cpu.h b/target/i386/cpu.h index c6c57baed5..109b2e5669 100644 --- a/target/i386/cpu.h +++ b/target/i386/cpu.h @@ -1788,6 +1788,8 @@ typedef struct CPUArchState { #endif #if defined(CONFIG_KVM) struct kvm_nested_state *nested_state; + uint64_t xen_vcpu_info_gpa; + uint64_t xen_vcpu_info_default_gpa; #endif #if defined(CONFIG_HVF) HVFX86LazyFlags hvf_lflags; diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c index c37e44d88f..8affe1eeae 100644 --- a/target/i386/kvm/kvm.c +++ b/target/i386/kvm/kvm.c @@ -1802,6 +1802,9 @@ int kvm_arch_init_vcpu(CPUState *cs) has_msr_hv_hypercall = true; } + env->xen_vcpu_info_gpa = UINT64_MAX; + env->xen_vcpu_info_default_gpa = UINT64_MAX; + if (cs->kvm_state->xen_version) { #ifdef CONFIG_XEN_EMU struct kvm_cpuid_entry2 *xen_max_leaf; @@ -4723,6 +4726,22 @@ int kvm_arch_put_registers(CPUState *cpu, int level) kvm_arch_set_tsc_khz(cpu); } +#ifdef CONFIG_XEN_EMU + if (level == KVM_PUT_FULL_STATE) { + uint64_t gpa = x86_cpu->env.xen_vcpu_info_gpa; + if (gpa == UINT64_MAX) { + gpa = x86_cpu->env.xen_vcpu_info_default_gpa; + } + + if (gpa != UINT64_MAX) { + ret = kvm_xen_set_vcpu_attr(cpu, KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO, gpa); + if (ret < 0) { + return ret; + } + } + } +#endif + ret = kvm_getput_regs(x86_cpu, 1); if (ret < 0) { return ret; diff --git a/target/i386/kvm/trace-events b/target/i386/kvm/trace-events index 0a47c26e80..14e54dfca5 100644 --- a/target/i386/kvm/trace-events +++ b/target/i386/kvm/trace-events @@ -9,3 +9,4 @@ kvm_x86_update_msi_routes(int num) "Updated %d MSI routes" # xen-emu.c kvm_xen_hypercall(int cpu, uint8_t cpl, uint64_t input, uint64_t a0, uint64_t a1, uint64_t a2, uint64_t ret) "xen_hypercall: cpu %d cpl %d input %" PRIu64 " a0 0x%" PRIx64 " a1 0x%" PRIx64 " a2 0x%" PRIx64" ret 0x%" PRIx64 kvm_xen_set_shared_info(uint64_t gfn) "shared info at gfn 0x%" PRIx64 +kvm_xen_set_vcpu_attr(int cpu, int type, uint64_t gpa) "vcpu attr cpu %d type %d gpa 0x%" PRIx64 diff --git a/target/i386/kvm/xen-emu.c b/target/i386/kvm/xen-emu.c index 83d98cbfd9..25c48248ce 100644 --- a/target/i386/kvm/xen-emu.c +++ b/target/i386/kvm/xen-emu.c @@ -147,10 +147,47 @@ static bool kvm_xen_hcall_xen_version(struct kvm_xen_exit *exit, X86CPU *cpu, return true; } +int kvm_xen_set_vcpu_attr(CPUState *cs, uint16_t type, uint64_t gpa) +{ + struct kvm_xen_vcpu_attr xhsi; + + xhsi.type = type; + xhsi.u.gpa = gpa; + + trace_kvm_xen_set_vcpu_attr(cs->cpu_index, type, gpa); + + return kvm_vcpu_ioctl(cs, KVM_XEN_VCPU_SET_ATTR, &xhsi); +} + +static void do_set_vcpu_info_default_gpa(CPUState *cs, run_on_cpu_data data) +{ + X86CPU *cpu = X86_CPU(cs); + CPUX86State *env = &cpu->env; + + env->xen_vcpu_info_default_gpa = data.host_ulong; + + /* Changing the default does nothing if a vcpu_info was explicitly set. */ + if (env->xen_vcpu_info_gpa == UINT64_MAX) { + kvm_xen_set_vcpu_attr(cs, KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO, + env->xen_vcpu_info_default_gpa); + } +} + +static void do_set_vcpu_info_gpa(CPUState *cs, run_on_cpu_data data) +{ + X86CPU *cpu = X86_CPU(cs); + CPUX86State *env = &cpu->env; + + env->xen_vcpu_info_gpa = data.host_ulong; + + kvm_xen_set_vcpu_attr(cs, KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO, + env->xen_vcpu_info_gpa); +} + static int xen_set_shared_info(uint64_t gfn) { uint64_t gpa = gfn << TARGET_PAGE_BITS; - int err; + int i, err; /* The xen_overlay device tells KVM about it too, since it had to * do that on migration load anyway (unless we're going to jump @@ -162,6 +199,14 @@ static int xen_set_shared_info(uint64_t gfn) trace_kvm_xen_set_shared_info(gfn); + for (i = 0; i < XEN_LEGACY_MAX_VCPUS; i++) { + CPUState *cpu = qemu_get_cpu(i); + if (cpu) { + async_run_on_cpu(cpu, do_set_vcpu_info_default_gpa, RUN_ON_CPU_HOST_ULONG(gpa)); + } + gpa += sizeof(vcpu_info_t); + } + return err; } @@ -318,15 +363,42 @@ static bool kvm_xen_hcall_hvm_op(struct kvm_xen_exit *exit, X86CPU *cpu, } } +static int vcpuop_register_vcpu_info(CPUState *cs, CPUState *target, + uint64_t arg) +{ + struct vcpu_register_vcpu_info rvi; + uint64_t gpa; + + /* No need for 32/64 compat handling */ + qemu_build_assert(sizeof(rvi) == 16); + qemu_build_assert(sizeof(struct vcpu_info) == 64); + + if (!target) + return -ENOENT; + + if (kvm_copy_from_gva(cs, arg, &rvi, sizeof(rvi))) { + return -EFAULT; + } + + if (rvi.offset > TARGET_PAGE_SIZE - sizeof(struct vcpu_info)) { + return -EINVAL; + } + + gpa = ((rvi.mfn << TARGET_PAGE_BITS) + rvi.offset); + async_run_on_cpu(target, do_set_vcpu_info_gpa, RUN_ON_CPU_HOST_ULONG(gpa)); + return 0; +} + static bool kvm_xen_hcall_vcpu_op(struct kvm_xen_exit *exit, X86CPU *cpu, int cmd, int vcpu_id, uint64_t arg) { + CPUState *dest = qemu_get_cpu(vcpu_id); + CPUState *cs = CPU(cpu); int err; switch (cmd) { case VCPUOP_register_vcpu_info: - /* no vcpu info placement for now */ - err = -ENOSYS; + err = vcpuop_register_vcpu_info(cs, dest, arg); break; default: diff --git a/target/i386/kvm/xen-emu.h b/target/i386/kvm/xen-emu.h index 76a3de6c4d..20da62d39f 100644 --- a/target/i386/kvm/xen-emu.h +++ b/target/i386/kvm/xen-emu.h @@ -25,5 +25,6 @@ int kvm_xen_init(KVMState *s, uint32_t hypercall_msr); int kvm_xen_handle_exit(X86CPU *cpu, struct kvm_xen_exit *exit); +int kvm_xen_set_vcpu_attr(CPUState *cs, uint16_t type, uint64_t gpa); #endif /* QEMU_I386_KVM_XEN_EMU_H */ diff --git a/target/i386/machine.c b/target/i386/machine.c index 310b125235..104cd6047c 100644 --- a/target/i386/machine.c +++ b/target/i386/machine.c @@ -1257,6 +1257,26 @@ static const VMStateDescription vmstate_nested_state = { } }; +static bool xen_vcpu_needed(void *opaque) +{ + X86CPU *cpu = opaque; + CPUX86State *env = &cpu->env; + + return (env->xen_vcpu_info_gpa != UINT64_MAX || + env->xen_vcpu_info_default_gpa != UINT64_MAX); +} + +static const VMStateDescription vmstate_xen_vcpu = { + .name = "cpu/xen_vcpu", + .version_id = 1, + .minimum_version_id = 1, + .needed = xen_vcpu_needed, + .fields = (VMStateField[]) { + VMSTATE_UINT64(env.xen_vcpu_info_gpa, X86CPU), + VMSTATE_UINT64(env.xen_vcpu_info_default_gpa, X86CPU), + VMSTATE_END_OF_LIST() + } +}; #endif static bool mcg_ext_ctl_needed(void *opaque) @@ -1716,6 +1736,7 @@ const VMStateDescription vmstate_x86_cpu = { #endif #ifdef CONFIG_KVM &vmstate_nested_state, + &vmstate_xen_vcpu, #endif &vmstate_msr_tsx_ctrl, &vmstate_msr_intel_sgx, -- 2.35.3