From: Gerd Hoffmann <kraxel@redhat.com>

Query kvm for supported guest physical address bits, in cpuid
function 80000008, eax[23:16].  Usually this is identical to host
physical address bits.  With NPT or EPT being used this might be
restricted to 48 (max 4-level paging address space size) even if
the host cpu supports more physical address bits.

When set pass this to the guest, using cpuid too.  Guest firmware
can use this to figure how big the usable guest physical address
space is, so PCI bar mapping are actually reachable.

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Reviewed-by: Zhao Liu <zhao1.liu@intel.com>
Message-ID: <20240318155336.156197-2-kraxel@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 target/i386/kvm/kvm-cpu.c | 50 ++++++++++++++++++++++++++++++++-------
 1 file changed, 42 insertions(+), 8 deletions(-)

diff --git a/target/i386/kvm/kvm-cpu.c b/target/i386/kvm/kvm-cpu.c
index 9c791b7b052..f76972e47e6 100644
--- a/target/i386/kvm/kvm-cpu.c
+++ b/target/i386/kvm/kvm-cpu.c
@@ -18,10 +18,32 @@
 #include "kvm_i386.h"
 #include "hw/core/accel-cpu.h"
 
+static void kvm_set_guest_phys_bits(CPUState *cs)
+{
+    X86CPU *cpu = X86_CPU(cs);
+    uint32_t eax, guest_phys_bits;
+
+    eax = kvm_arch_get_supported_cpuid(cs->kvm_state, 0x80000008, 0, R_EAX);
+    guest_phys_bits = (eax >> 16) & 0xff;
+    if (!guest_phys_bits) {
+        return;
+    }
+    cpu->guest_phys_bits = guest_phys_bits;
+    if (cpu->guest_phys_bits > cpu->phys_bits) {
+        cpu->guest_phys_bits = cpu->phys_bits;
+    }
+
+    if (cpu->host_phys_bits && cpu->host_phys_bits_limit &&
+        cpu->guest_phys_bits > cpu->host_phys_bits_limit) {
+        cpu->guest_phys_bits = cpu->host_phys_bits_limit;
+    }
+}
+
 static bool kvm_cpu_realizefn(CPUState *cs, Error **errp)
 {
     X86CPU *cpu = X86_CPU(cs);
     CPUX86State *env = &cpu->env;
+    bool ret;
 
     /*
      * The realize order is important, since x86_cpu_realize() checks if
@@ -32,13 +54,15 @@ static bool kvm_cpu_realizefn(CPUState *cs, Error **errp)
      *
      * realize order:
      *
-     * x86_cpu_realize():
-     *  -> x86_cpu_expand_features()
-     *  -> cpu_exec_realizefn():
-     *            -> accel_cpu_common_realize()
-     *               kvm_cpu_realizefn() -> host_cpu_realizefn()
-     *  -> cpu_common_realizefn()
-     *  -> check/update ucode_rev, phys_bits, mwait
+     * x86_cpu_realizefn():
+     *   x86_cpu_expand_features()
+     *   cpu_exec_realizefn():
+     *      accel_cpu_common_realize()
+     *        kvm_cpu_realizefn()
+     *          host_cpu_realizefn()
+     *          kvm_set_guest_phys_bits()
+     *   check/update ucode_rev, phys_bits, guest_phys_bits, mwait
+     *   cpu_common_realizefn() (via xcc->parent_realize)
      */
     if (cpu->max_features) {
         if (enable_cpu_pm && kvm_has_waitpkg()) {
@@ -50,7 +74,17 @@ static bool kvm_cpu_realizefn(CPUState *cs, Error **errp)
                                                    MSR_IA32_UCODE_REV);
         }
     }
-    return host_cpu_realizefn(cs, errp);
+    ret = host_cpu_realizefn(cs, errp);
+    if (!ret) {
+        return ret;
+    }
+
+    if ((env->features[FEAT_8000_0001_EDX] & CPUID_EXT2_LM) &&
+        cpu->guest_phys_bits == -1) {
+        kvm_set_guest_phys_bits(cs);
+    }
+
+    return true;
 }
 
 static bool lmce_supported(void)
-- 
2.44.0