[RFC PATCH 7/7] target/i386: Manipulate only AMD XSAVE state on AMD

[David Edmondson]

On AMD CPUs, ensure to save/load only the relevant XSAVE state.

Signed-off-by: David Edmondson <david.edmondson@oracle.com>
---
 target/i386/tcg/fpu_helper.c | 12 +++++--
 target/i386/xsave_helper.c   | 70 ++++++++++++++++++++++--------------
 2 files changed, 54 insertions(+), 28 deletions(-)

diff --git a/target/i386/tcg/fpu_helper.c b/target/i386/tcg/fpu_helper.c
index fba2de5b04..f1d4704b34 100644
--- a/target/i386/tcg/fpu_helper.c
+++ b/target/i386/tcg/fpu_helper.c
@@ -2643,7 +2643,11 @@ static void do_xsave(CPUX86State *env, target_ulong ptr, 
uint64_t rfbm,
         do_xsave_bndcsr(env, ptr + XO(intel.bndcsr_state), ra);
     }
     if (opt & XSTATE_PKRU_MASK) {
-        do_xsave_pkru(env, ptr + XO(intel.pkru_state), ra);
+        if (IS_AMD_CPU(env)) {
+            do_xsave_pkru(env, ptr + XO(amd.pkru_state), ra);
+        } else {
+            do_xsave_pkru(env, ptr + XO(intel.pkru_state), ra);
+        }
     }
 
     /* Update the XSTATE_BV field.  */
@@ -2854,7 +2858,11 @@ void helper_xrstor(CPUX86State *env, target_ulong ptr, 
uint64_t rfbm)
     if (rfbm & XSTATE_PKRU_MASK) {
         uint64_t old_pkru = env->pkru;
         if (xstate_bv & XSTATE_PKRU_MASK) {
-            do_xrstor_pkru(env, ptr + XO(intel.pkru_state), ra);
+            if (IS_AMD_CPU(env)) {
+                do_xrstor_pkru(env, ptr + XO(amd.pkru_state), ra);
+            } else {
+                do_xrstor_pkru(env, ptr + XO(intel.pkru_state), ra);
+            }
         } else {
             env->pkru = 0;
         }
diff --git a/target/i386/xsave_helper.c b/target/i386/xsave_helper.c
index 97dbab85d1..6b4501cf29 100644
--- a/target/i386/xsave_helper.c
+++ b/target/i386/xsave_helper.c
@@ -10,6 +10,7 @@ void x86_cpu_xsave_all_areas(X86CPU *cpu, X86XSaveArea *buf)
 {
     CPUX86State *env = &cpu->env;
     X86XSaveArea *xsave = buf;
+    const bool is_amd = IS_AMD_CPU(env);
 
     uint16_t cwd, swd, twd;
     int i;
@@ -31,30 +32,38 @@ void x86_cpu_xsave_all_areas(X86CPU *cpu, X86XSaveArea *buf)
             sizeof env->fpregs);
     xsave->legacy.mxcsr = env->mxcsr;
     xsave->header.xstate_bv = env->xstate_bv;
-    memcpy(&xsave->intel.bndreg_state.bnd_regs, env->bnd_regs,
-            sizeof env->bnd_regs);
-    xsave->intel.bndcsr_state.bndcsr = env->bndcs_regs;
-    memcpy(&xsave->intel.opmask_state.opmask_regs, env->opmask_regs,
-            sizeof env->opmask_regs);
+    if (!is_amd) {
+        memcpy(&xsave->intel.bndreg_state.bnd_regs, env->bnd_regs,
+               sizeof env->bnd_regs);
+        xsave->intel.bndcsr_state.bndcsr = env->bndcs_regs;
+        memcpy(&xsave->intel.opmask_state.opmask_regs, env->opmask_regs,
+               sizeof env->opmask_regs);
+    }
 
     for (i = 0; i < CPU_NB_REGS; i++) {
         uint8_t *xmm = xsave->legacy.xmm_regs[i];
         uint8_t *ymmh = xsave->avx_state.ymmh[i];
-        uint8_t *zmmh = xsave->intel.zmm_hi256_state.zmm_hi256[i];
         stq_p(xmm,     env->xmm_regs[i].ZMM_Q(0));
         stq_p(xmm+8,   env->xmm_regs[i].ZMM_Q(1));
         stq_p(ymmh,    env->xmm_regs[i].ZMM_Q(2));
         stq_p(ymmh+8,  env->xmm_regs[i].ZMM_Q(3));
-        stq_p(zmmh,    env->xmm_regs[i].ZMM_Q(4));
-        stq_p(zmmh+8,  env->xmm_regs[i].ZMM_Q(5));
-        stq_p(zmmh+16, env->xmm_regs[i].ZMM_Q(6));
-        stq_p(zmmh+24, env->xmm_regs[i].ZMM_Q(7));
+        if (!is_amd) {
+            uint8_t *zmmh = xsave->intel.zmm_hi256_state.zmm_hi256[i];
+            stq_p(zmmh,    env->xmm_regs[i].ZMM_Q(4));
+            stq_p(zmmh+8,  env->xmm_regs[i].ZMM_Q(5));
+            stq_p(zmmh+16, env->xmm_regs[i].ZMM_Q(6));
+            stq_p(zmmh+24, env->xmm_regs[i].ZMM_Q(7));
+        }
     }
 
 #ifdef TARGET_X86_64
-    memcpy(&xsave->intel.hi16_zmm_state.hi16_zmm, &env->xmm_regs[16],
-            16 * sizeof env->xmm_regs[16]);
-    memcpy(&xsave->intel.pkru_state, &env->pkru, sizeof env->pkru);
+    if (is_amd) {
+        memcpy(&xsave->amd.pkru_state, &env->pkru, sizeof env->pkru);
+    } else {
+        memcpy(&xsave->intel.hi16_zmm_state.hi16_zmm, &env->xmm_regs[16],
+               16 * sizeof env->xmm_regs[16]);
+        memcpy(&xsave->intel.pkru_state, &env->pkru, sizeof env->pkru);
+    }
 #endif
 
 }
@@ -64,6 +73,7 @@ void x86_cpu_xrstor_all_areas(X86CPU *cpu, const X86XSaveArea 
*buf)
 
     CPUX86State *env = &cpu->env;
     const X86XSaveArea *xsave = buf;
+    const bool is_amd = IS_AMD_CPU(env);
 
     int i;
     uint16_t cwd, swd, twd;
@@ -83,30 +93,38 @@ void x86_cpu_xrstor_all_areas(X86CPU *cpu, const 
X86XSaveArea *buf)
     memcpy(env->fpregs, &xsave->legacy.fpregs,
             sizeof env->fpregs);
     env->xstate_bv = xsave->header.xstate_bv;
-    memcpy(env->bnd_regs, &xsave->intel.bndreg_state.bnd_regs,
-            sizeof env->bnd_regs);
-    env->bndcs_regs = xsave->intel.bndcsr_state.bndcsr;
-    memcpy(env->opmask_regs, &xsave->intel.opmask_state.opmask_regs,
-            sizeof env->opmask_regs);
+    if (!is_amd) {
+        memcpy(env->bnd_regs, &xsave->intel.bndreg_state.bnd_regs,
+               sizeof env->bnd_regs);
+        env->bndcs_regs = xsave->intel.bndcsr_state.bndcsr;
+        memcpy(env->opmask_regs, &xsave->intel.opmask_state.opmask_regs,
+               sizeof env->opmask_regs);
+    }
 
     for (i = 0; i < CPU_NB_REGS; i++) {
         const uint8_t *xmm = xsave->legacy.xmm_regs[i];
         const uint8_t *ymmh = xsave->avx_state.ymmh[i];
-        const uint8_t *zmmh = xsave->intel.zmm_hi256_state.zmm_hi256[i];
         env->xmm_regs[i].ZMM_Q(0) = ldq_p(xmm);
         env->xmm_regs[i].ZMM_Q(1) = ldq_p(xmm+8);
         env->xmm_regs[i].ZMM_Q(2) = ldq_p(ymmh);
         env->xmm_regs[i].ZMM_Q(3) = ldq_p(ymmh+8);
-        env->xmm_regs[i].ZMM_Q(4) = ldq_p(zmmh);
-        env->xmm_regs[i].ZMM_Q(5) = ldq_p(zmmh+8);
-        env->xmm_regs[i].ZMM_Q(6) = ldq_p(zmmh+16);
-        env->xmm_regs[i].ZMM_Q(7) = ldq_p(zmmh+24);
+        if (!is_amd) {
+            const uint8_t *zmmh = xsave->intel.zmm_hi256_state.zmm_hi256[i];
+            env->xmm_regs[i].ZMM_Q(4) = ldq_p(zmmh);
+            env->xmm_regs[i].ZMM_Q(5) = ldq_p(zmmh+8);
+            env->xmm_regs[i].ZMM_Q(6) = ldq_p(zmmh+16);
+            env->xmm_regs[i].ZMM_Q(7) = ldq_p(zmmh+24);
+        }
     }
 
 #ifdef TARGET_X86_64
-    memcpy(&env->xmm_regs[16], &xsave->intel.hi16_zmm_state.hi16_zmm,
-           16 * sizeof env->xmm_regs[16]);
-    memcpy(&env->pkru, &xsave->intel.pkru_state, sizeof env->pkru);
+    if (is_amd) {
+        memcpy(&env->pkru, &xsave->amd.pkru_state, sizeof env->pkru);
+    } else {
+        memcpy(&env->xmm_regs[16], &xsave->intel.hi16_zmm_state.hi16_zmm,
+               16 * sizeof env->xmm_regs[16]);
+        memcpy(&env->pkru, &xsave->intel.pkru_state, sizeof env->pkru);
+    }
 #endif
 
 }
-- 
2.30.2