From: Joao Martins <joao.m.mart...@oracle.com> In order to support Linux vdso in Xen.
Signed-off-by: Joao Martins <joao.m.mart...@oracle.com> Signed-off-by: David Woodhouse <d...@amazon.co.uk> --- target/i386/cpu.h | 1 + target/i386/kvm/kvm.c | 9 ++++ target/i386/kvm/xen-emu.c | 86 +++++++++++++++++++++++++++++++++------ target/i386/machine.c | 4 +- 4 files changed, 87 insertions(+), 13 deletions(-) diff --git a/target/i386/cpu.h b/target/i386/cpu.h index 109b2e5669..96c2d0d5cb 100644 --- a/target/i386/cpu.h +++ b/target/i386/cpu.h @@ -1790,6 +1790,7 @@ typedef struct CPUArchState { struct kvm_nested_state *nested_state; uint64_t xen_vcpu_info_gpa; uint64_t xen_vcpu_info_default_gpa; + uint64_t xen_vcpu_time_info_gpa; #endif #if defined(CONFIG_HVF) HVFX86LazyFlags hvf_lflags; diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c index 8affe1eeae..766e0add13 100644 --- a/target/i386/kvm/kvm.c +++ b/target/i386/kvm/kvm.c @@ -1804,6 +1804,7 @@ int kvm_arch_init_vcpu(CPUState *cs) env->xen_vcpu_info_gpa = UINT64_MAX; env->xen_vcpu_info_default_gpa = UINT64_MAX; + env->xen_vcpu_time_info_gpa = UINT64_MAX; if (cs->kvm_state->xen_version) { #ifdef CONFIG_XEN_EMU @@ -4739,6 +4740,14 @@ int kvm_arch_put_registers(CPUState *cpu, int level) return ret; } } + + gpa = x86_cpu->env.xen_vcpu_time_info_gpa; + if (gpa != UINT64_MAX) { + ret = kvm_xen_set_vcpu_attr(cpu, KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO, gpa); + if (ret < 0) { + return ret; + } + } } #endif diff --git a/target/i386/kvm/xen-emu.c b/target/i386/kvm/xen-emu.c index 25c48248ce..b45d5af7d7 100644 --- a/target/i386/kvm/xen-emu.c +++ b/target/i386/kvm/xen-emu.c @@ -33,27 +33,40 @@ #define hypercall_compat32(longmode) (false) #endif -static int kvm_gva_rw(CPUState *cs, uint64_t gva, void *_buf, size_t sz, - bool is_write) +static bool kvm_gva_to_gpa(CPUState *cs, uint64_t gva, uint64_t *gpa, + size_t *len, bool is_write) { - uint8_t *buf = (uint8_t *)_buf; - int ret; - - while (sz) { struct kvm_translation tr = { .linear_address = gva, }; - size_t len = TARGET_PAGE_SIZE - (tr.linear_address & ~TARGET_PAGE_MASK); - if (len > sz) - len = sz; + if (len) { + *len = TARGET_PAGE_SIZE - (gva & ~TARGET_PAGE_MASK); + } + + if (kvm_vcpu_ioctl(cs, KVM_TRANSLATE, &tr) || !tr.valid || + (is_write && !tr.writeable)) { + return false; + } + *gpa = tr.physical_address; + return true; +} + +static int kvm_gva_rw(CPUState *cs, uint64_t gva, void *_buf, size_t sz, + bool is_write) +{ + uint8_t *buf = (uint8_t *)_buf; + uint64_t gpa; + size_t len; - ret = kvm_vcpu_ioctl(cs, KVM_TRANSLATE, &tr); - if (ret || !tr.valid || (is_write && !tr.writeable)) { + while (sz) { + if (!kvm_gva_to_gpa(cs, gva, &gpa, &len, is_write)) { return -EFAULT; } + if (len > sz) + len = sz; - cpu_physical_memory_rw(tr.physical_address, buf, len, is_write); + cpu_physical_memory_rw(gpa, buf, len, is_write); buf += len; sz -= len; @@ -184,6 +197,17 @@ static void do_set_vcpu_info_gpa(CPUState *cs, run_on_cpu_data data) env->xen_vcpu_info_gpa); } +static void do_set_vcpu_time_info_gpa(CPUState *cs, run_on_cpu_data data) +{ + X86CPU *cpu = X86_CPU(cs); + CPUX86State *env = &cpu->env; + + env->xen_vcpu_time_info_gpa = data.host_ulong; + + kvm_xen_set_vcpu_attr(cs, KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO, + env->xen_vcpu_time_info_gpa); +} + static int xen_set_shared_info(uint64_t gfn) { uint64_t gpa = gfn << TARGET_PAGE_BITS; @@ -389,6 +413,41 @@ static int vcpuop_register_vcpu_info(CPUState *cs, CPUState *target, return 0; } +static int vcpuop_register_vcpu_time_info(CPUState *cs, CPUState *target, + uint64_t arg) +{ + struct vcpu_register_time_memory_area tma; + uint64_t gpa; + size_t len; + + /* No need for 32/64 compat handling */ + qemu_build_assert(sizeof(tma) == 8); + qemu_build_assert(sizeof(struct vcpu_time_info) == 32); + + if (!target) + return -ENOENT; + + if (kvm_copy_from_gva(cs, arg, &tma, sizeof(tma))) { + return -EFAULT; + } + + /* + * Xen actually uses the GVA and does the translation through the guest + * page tables each time. But Linux/KVM uses the GPA, on the assumption + * that guests only ever use *global* addresses (kernel virtual addresses) + * for it. If Linux is changed to redo the GVA→GPA translation each time, + * it will offer a new vCPU attribute for that, and we'll use it instead. + */ + if (!kvm_gva_to_gpa(cs, tma.addr.p, &gpa, &len, false) || + len < sizeof(struct vcpu_time_info)) { + return -EFAULT; + } + + async_run_on_cpu(target, do_set_vcpu_time_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) { @@ -397,6 +456,9 @@ static bool kvm_xen_hcall_vcpu_op(struct kvm_xen_exit *exit, X86CPU *cpu, int err; switch (cmd) { + case VCPUOP_register_vcpu_time_memory_area: + err = vcpuop_register_vcpu_time_info(cs, dest, arg); + break; case VCPUOP_register_vcpu_info: err = vcpuop_register_vcpu_info(cs, dest, arg); break; diff --git a/target/i386/machine.c b/target/i386/machine.c index 104cd6047c..9acef102a3 100644 --- a/target/i386/machine.c +++ b/target/i386/machine.c @@ -1263,7 +1263,8 @@ static bool xen_vcpu_needed(void *opaque) CPUX86State *env = &cpu->env; return (env->xen_vcpu_info_gpa != UINT64_MAX || - env->xen_vcpu_info_default_gpa != UINT64_MAX); + env->xen_vcpu_info_default_gpa != UINT64_MAX || + env->xen_vcpu_time_info_gpa != UINT64_MAX); } static const VMStateDescription vmstate_xen_vcpu = { @@ -1274,6 +1275,7 @@ static const VMStateDescription vmstate_xen_vcpu = { .fields = (VMStateField[]) { VMSTATE_UINT64(env.xen_vcpu_info_gpa, X86CPU), VMSTATE_UINT64(env.xen_vcpu_info_default_gpa, X86CPU), + VMSTATE_UINT64(env.xen_vcpu_time_info_gpa, X86CPU), VMSTATE_END_OF_LIST() } }; -- 2.35.3