i386/xen: handle VCPUOP_register_vcpu_time_info

In order to support Linux vdso in Xen.

Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Reviewed-by: Paul Durrant <paul@xen.org>

target/i386/cpu.h

@@ -1801,6 +1801,7 @@ 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;

target/i386/kvm/xen-emu.c

@@ -37,28 +37,41 @@
 #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) {
+            *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;
+
+    while (sz) {
+        if (!kvm_gva_to_gpa(cs, gva, &gpa, &len, is_write)) {
+            return -EFAULT;
+        }
         if (len > sz) {
             len = sz;
         }
 
-        ret = kvm_vcpu_ioctl(cs, KVM_TRANSLATE, &tr);
-        if (ret || !tr.valid || (is_write && !tr.writeable)) {
-            return -EFAULT;
-        }
-
-        cpu_physical_memory_rw(tr.physical_address, buf, len, is_write);
+        cpu_physical_memory_rw(gpa, buf, len, is_write);
 
         buf += len;
         sz -= len;
@@ -146,6 +159,7 @@ int kvm_xen_init_vcpu(CPUState *cs)
 
     env->xen_vcpu_info_gpa = INVALID_GPA;
     env->xen_vcpu_info_default_gpa = INVALID_GPA;
+    env->xen_vcpu_time_info_gpa = INVALID_GPA;
 
     return 0;
 }
@@ -229,6 +243,17 @@ 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 void do_vcpu_soft_reset(CPUState *cs, run_on_cpu_data data)
 {
     X86CPU *cpu = X86_CPU(cs);
@@ -236,8 +261,11 @@ static void do_vcpu_soft_reset(CPUState *cs, run_on_cpu_data data)
 
     env->xen_vcpu_info_gpa = INVALID_GPA;
     env->xen_vcpu_info_default_gpa = INVALID_GPA;
+    env->xen_vcpu_time_info_gpa = INVALID_GPA;
 
     kvm_xen_set_vcpu_attr(cs, KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO, INVALID_GPA);
+    kvm_xen_set_vcpu_attr(cs, KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO,
+                          INVALID_GPA);
 }
 
 static int xen_set_shared_info(uint64_t gfn)
@@ -453,6 +481,42 @@ 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)
 {
@@ -461,6 +525,9 @@ 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;
@@ -654,6 +721,15 @@ int kvm_put_xen_state(CPUState *cs)
         }
     }
 
+    gpa = env->xen_vcpu_time_info_gpa;
+    if (gpa != INVALID_GPA) {
+        ret = kvm_xen_set_vcpu_attr(cs, KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO,
+                                    gpa);
+        if (ret < 0) {
+            return ret;
+        }
+    }
+
     return 0;
 }
 

target/i386/machine.c

@@ -1272,6 +1272,7 @@ 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()
     }
 };