x86: add support for KVM_CAP_XSAVE2 and AMX state migration

When dynamic xfeatures (e.g. AMX) are used by the guest, the xsave
area would be larger than 4KB. KVM_GET_XSAVE2 and KVM_SET_XSAVE
under KVM_CAP_XSAVE2 works with a xsave buffer larger than 4KB.
Always use the new ioctls under KVM_CAP_XSAVE2 when KVM supports it.

Signed-off-by: Jing Liu <jing2.liu@intel.com>
Signed-off-by: Zeng Guang <guang.zeng@intel.com>
Signed-off-by: Wei Wang <wei.w.wang@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20220217060434.52460-7-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 27 insertions, 15 deletions

diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index 2edd1a2..4e871a6 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -124,6 +124,7 @@ static uint32_t num_architectural_pmu_gp_counters;
 static uint32_t num_architectural_pmu_fixed_counters;
 
 static int has_xsave;
+static int has_xsave2;
 static int has_xcrs;
 static int has_pit_state2;
 static int has_sregs2;
@@ -1587,6 +1588,26 @@ static Error *invtsc_mig_blocker;
 
 #define KVM_MAX_CPUID_ENTRIES  100
 
+static void kvm_init_xsave(CPUX86State *env)
+{
+    if (has_xsave2) {
+        env->xsave_buf_len = QEMU_ALIGN_UP(has_xsave2, 4096);
+    } else if (has_xsave) {
+        env->xsave_buf_len = sizeof(struct kvm_xsave);
+    } else {
+        return;
+    }
+
+    env->xsave_buf = qemu_memalign(4096, env->xsave_buf_len);
+    memset(env->xsave_buf, 0, env->xsave_buf_len);
+    /*
+     * The allocated storage must be large enough for all of the
+     * possible XSAVE state components.
+     */
+    assert(kvm_arch_get_supported_cpuid(kvm_state, 0xd, 0, R_ECX) <=
+           env->xsave_buf_len);
+}
+
 int kvm_arch_init_vcpu(CPUState *cs)
 {
     struct {
@@ -1616,6 +1637,8 @@ int kvm_arch_init_vcpu(CPUState *cs)
 
     cpuid_i = 0;
 
+    has_xsave2 = kvm_check_extension(cs->kvm_state, KVM_CAP_XSAVE2);
+
     r = kvm_arch_set_tsc_khz(cs);
     if (r < 0) {
         return r;
@@ -2005,19 +2028,7 @@ int kvm_arch_init_vcpu(CPUState *cs)
     if (r) {
         goto fail;
     }
-
-    if (has_xsave) {
-        env->xsave_buf_len = sizeof(struct kvm_xsave);
-        env->xsave_buf = qemu_memalign(4096, env->xsave_buf_len);
-        memset(env->xsave_buf, 0, env->xsave_buf_len);
-
-        /*
-         * The allocated storage must be large enough for all of the
-         * possible XSAVE state components.
-         */
-        assert(kvm_arch_get_supported_cpuid(kvm_state, 0xd, 0, R_ECX)
-               <= env->xsave_buf_len);
-    }
+    kvm_init_xsave(env);
 
     max_nested_state_len = kvm_max_nested_state_length();
     if (max_nested_state_len > 0) {
@@ -3321,13 +3332,14 @@ static int kvm_get_xsave(X86CPU *cpu)
 {
     CPUX86State *env = &cpu->env;
     void *xsave = env->xsave_buf;
-    int ret;
+    int type, ret;
 
     if (!has_xsave) {
         return kvm_get_fpu(cpu);
     }
 
-    ret = kvm_vcpu_ioctl(CPU(cpu), KVM_GET_XSAVE, xsave);
+    type = has_xsave2 ? KVM_GET_XSAVE2 : KVM_GET_XSAVE;
+    ret = kvm_vcpu_ioctl(CPU(cpu), type, xsave);
     if (ret < 0) {
         return ret;
     }