x86: Grant AMX permission for guest

Kernel allocates 4K xstate buffer by default. For XSAVE features
which require large state component (e.g. AMX), Linux kernel
dynamically expands the xstate buffer only after the process has
acquired the necessary permissions. Those are called dynamically-
enabled XSAVE features (or dynamic xfeatures).

There are separate permissions for native tasks and guests.

Qemu should request the guest permissions for dynamic xfeatures
which will be exposed to the guest. This only needs to be done
once before the first vcpu is created.

KVM implemented one new ARCH_GET_XCOMP_SUPP system attribute API to
get host side supported_xcr0 and Qemu can decide if it can request
dynamically enabled XSAVE features permission.
https://lore.kernel.org/all/20220126152210.3044876-1-pbonzini@redhat.com/

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Signed-off-by: Jing Liu <jing2.liu@intel.com>
Message-Id: <20220217060434.52460-4-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

3 files changed, 64 insertions, 6 deletions

diff --git a/target/i386/kvm/kvm-cpu.c b/target/i386/kvm/kvm-cpu.c
index ce27d3b..a35a1bf 100644
--- a/target/i386/kvm/kvm-cpu.c
+++ b/target/i386/kvm/kvm-cpu.c
@@ -84,7 +84,7 @@ static void kvm_cpu_max_instance_init(X86CPU *cpu)
 static void kvm_cpu_xsave_init(void)
 {
     static bool first = true;
-    KVMState *s = kvm_state;
+    uint32_t eax, ebx, ecx, edx;
     int i;
 
     if (!first) {
@@ -100,11 +100,11 @@ static void kvm_cpu_xsave_init(void)
         ExtSaveArea *esa = &x86_ext_save_areas[i];
 
         if (esa->size) {
-            int sz = kvm_arch_get_supported_cpuid(s, 0xd, i, R_EAX);
-            if (sz != 0) {
-                assert(esa->size == sz);
-                esa->offset = kvm_arch_get_supported_cpuid(s, 0xd, i, R_EBX);
-                esa->ecx = kvm_arch_get_supported_cpuid(s, 0xd, i, R_ECX);
+            host_cpuid(0xd, i, &eax, &ebx, &ecx, &edx);
+            if (eax != 0) {
+                assert(esa->size == eax);
+                esa->offset = ebx;
+                esa->ecx = ecx;
             }
         }
     }
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index 31d467b..f0d1de7 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -17,6 +17,7 @@
 #include "qapi/error.h"
 #include <sys/ioctl.h>
 #include <sys/utsname.h>
+#include <sys/syscall.h>
 
 #include <linux/kvm.h>
 #include "standard-headers/asm-x86/kvm_para.h"
@@ -349,6 +350,7 @@ uint32_t kvm_arch_get_supported_cpuid(KVMState *s, uint32_t function,
     struct kvm_cpuid2 *cpuid;
     uint32_t ret = 0;
     uint32_t cpuid_1_edx;
+    uint64_t bitmask;
 
     cpuid = get_supported_cpuid(s);
 
@@ -406,6 +408,25 @@ uint32_t kvm_arch_get_supported_cpuid(KVMState *s, uint32_t function,
         if (!has_msr_arch_capabs) {
             ret &= ~CPUID_7_0_EDX_ARCH_CAPABILITIES;
         }
+    } else if (function == 0xd && index == 0 &&
+               (reg == R_EAX || reg == R_EDX)) {
+        struct kvm_device_attr attr = {
+            .group = 0,
+            .attr = KVM_X86_XCOMP_GUEST_SUPP,
+            .addr = (unsigned long) &bitmask
+        };
+
+        bool sys_attr = kvm_check_extension(s, KVM_CAP_SYS_ATTRIBUTES);
+        if (!sys_attr) {
+            warn_report("cannot get sys attribute capabilities %d", sys_attr);
+        }
+
+        int rc = kvm_ioctl(s, KVM_GET_DEVICE_ATTR, &attr);
+        if (rc == -1 && (errno == ENXIO || errno == EINVAL)) {
+            warn_report("KVM_GET_DEVICE_ATTR(0, KVM_X86_XCOMP_GUEST_SUPP) "
+                        "error: %d", rc);
+        }
+        ret = (reg == R_EAX) ? bitmask : bitmask >> 32;
     } else if (function == 0x80000001 && reg == R_ECX) {
         /*
          * It's safe to enable TOPOEXT even if it's not returned by
@@ -5151,3 +5172,39 @@ bool kvm_arch_cpu_check_are_resettable(void)
 {
     return !sev_es_enabled();
 }
+
+#define ARCH_REQ_XCOMP_GUEST_PERM       0x1025
+
+void kvm_request_xsave_components(X86CPU *cpu, uint64_t mask)
+{
+    KVMState *s = kvm_state;
+    uint64_t supported;
+
+    mask &= XSTATE_DYNAMIC_MASK;
+    if (!mask) {
+        return;
+    }
+    /*
+     * Just ignore bits that are not in CPUID[EAX=0xD,ECX=0].
+     * ARCH_REQ_XCOMP_GUEST_PERM would fail, and QEMU has warned
+     * about them already because they are not supported features.
+     */
+    supported = kvm_arch_get_supported_cpuid(s, 0xd, 0, R_EAX);
+    supported |= (uint64_t)kvm_arch_get_supported_cpuid(s, 0xd, 0, R_EDX) << 32;
+    mask &= supported;
+
+    while (mask) {
+        int bit = ctz64(mask);
+        int rc = syscall(SYS_arch_prctl, ARCH_REQ_XCOMP_GUEST_PERM, bit);
+        if (rc) {
+            /*
+             * Older kernel version (<5.17) do not support
+             * ARCH_REQ_XCOMP_GUEST_PERM, but also do not return
+             * any dynamic feature from kvm_arch_get_supported_cpuid.
+             */
+            warn_report("prctl(ARCH_REQ_XCOMP_GUEST_PERM) failure "
+                        "for feature bit %d", bit);
+        }
+        mask &= ~BIT_ULL(bit);
+    }
+}
diff --git a/target/i386/kvm/kvm_i386.h b/target/i386/kvm/kvm_i386.h
index a978509..4124912 100644
--- a/target/i386/kvm/kvm_i386.h
+++ b/target/i386/kvm/kvm_i386.h
@@ -52,5 +52,6 @@ bool kvm_hyperv_expand_features(X86CPU *cpu, Error **errp);
 uint64_t kvm_swizzle_msi_ext_dest_id(uint64_t address);
 
 bool kvm_enable_sgx_provisioning(KVMState *s);
+void kvm_request_xsave_components(X86CPU *cpu, uint64_t mask);
 
 #endif