[PULL 48/53] target/i386: implement XSAVE and XRSTOR of AVX registers

[Paolo Bonzini]

Reviewed-by: Richard Henderson <richard.hender...@linaro.org>
Signed-off-by: Paolo Bonzini <pbonz...@redhat.com>
---
 target/i386/tcg/fpu_helper.c | 78 ++++++++++++++++++++++++++++++++++--
 1 file changed, 75 insertions(+), 3 deletions(-)

diff --git a/target/i386/tcg/fpu_helper.c b/target/i386/tcg/fpu_helper.c
index 5f3f7a1085..7670739abe 100644
--- a/target/i386/tcg/fpu_helper.c
+++ b/target/i386/tcg/fpu_helper.c
@@ -2559,6 +2559,22 @@ static void do_xsave_sse(CPUX86State *env, target_ulong 
ptr, uintptr_t ra)
     }
 }
 
+static void do_xsave_ymmh(CPUX86State *env, target_ulong ptr, uintptr_t ra)
+{
+    int i, nb_xmm_regs;
+
+    if (env->hflags & HF_CS64_MASK) {
+        nb_xmm_regs = 16;
+    } else {
+        nb_xmm_regs = 8;
+    }
+
+    for (i = 0; i < nb_xmm_regs; i++, ptr += 16) {
+        cpu_stq_data_ra(env, ptr, env->xmm_regs[i].ZMM_Q(2), ra);
+        cpu_stq_data_ra(env, ptr + 8, env->xmm_regs[i].ZMM_Q(3), ra);
+    }
+}
+
 static void do_xsave_bndregs(CPUX86State *env, target_ulong ptr, uintptr_t ra)
 {
     target_ulong addr = ptr + offsetof(XSaveBNDREG, bnd_regs);
@@ -2651,6 +2667,9 @@ static void do_xsave(CPUX86State *env, target_ulong ptr, 
uint64_t rfbm,
     if (opt & XSTATE_SSE_MASK) {
         do_xsave_sse(env, ptr, ra);
     }
+    if (opt & XSTATE_YMM_MASK) {
+        do_xsave_ymmh(env, ptr + XO(avx_state), ra);
+    }
     if (opt & XSTATE_BNDREGS_MASK) {
         do_xsave_bndregs(env, ptr + XO(bndreg_state), ra);
     }
@@ -2725,6 +2744,54 @@ static void do_xrstor_sse(CPUX86State *env, target_ulong 
ptr, uintptr_t ra)
     }
 }
 
+static void do_clear_sse(CPUX86State *env)
+{
+    int i, nb_xmm_regs;
+
+    if (env->hflags & HF_CS64_MASK) {
+        nb_xmm_regs = 16;
+    } else {
+        nb_xmm_regs = 8;
+    }
+
+    for (i = 0; i < nb_xmm_regs; i++) {
+        env->xmm_regs[i].ZMM_Q(0) = 0;
+        env->xmm_regs[i].ZMM_Q(1) = 0;
+    }
+}
+
+static void do_xrstor_ymmh(CPUX86State *env, target_ulong ptr, uintptr_t ra)
+{
+    int i, nb_xmm_regs;
+
+    if (env->hflags & HF_CS64_MASK) {
+        nb_xmm_regs = 16;
+    } else {
+        nb_xmm_regs = 8;
+    }
+
+    for (i = 0; i < nb_xmm_regs; i++, ptr += 16) {
+        env->xmm_regs[i].ZMM_Q(2) = cpu_ldq_data_ra(env, ptr, ra);
+        env->xmm_regs[i].ZMM_Q(3) = cpu_ldq_data_ra(env, ptr + 8, ra);
+    }
+}
+
+static void do_clear_ymmh(CPUX86State *env)
+{
+    int i, nb_xmm_regs;
+
+    if (env->hflags & HF_CS64_MASK) {
+        nb_xmm_regs = 16;
+    } else {
+        nb_xmm_regs = 8;
+    }
+
+    for (i = 0; i < nb_xmm_regs; i++) {
+        env->xmm_regs[i].ZMM_Q(2) = 0;
+        env->xmm_regs[i].ZMM_Q(3) = 0;
+    }
+}
+
 static void do_xrstor_bndregs(CPUX86State *env, target_ulong ptr, uintptr_t ra)
 {
     target_ulong addr = ptr + offsetof(XSaveBNDREG, bnd_regs);
@@ -2831,9 +2898,14 @@ static void do_xrstor(CPUX86State *env, target_ulong 
ptr, uint64_t rfbm, uintptr
         if (xstate_bv & XSTATE_SSE_MASK) {
             do_xrstor_sse(env, ptr, ra);
         } else {
-            /* ??? When AVX is implemented, we may have to be more
-               selective in the clearing.  */
-            memset(env->xmm_regs, 0, sizeof(env->xmm_regs));
+            do_clear_sse(env);
+        }
+    }
+    if (rfbm & XSTATE_YMM_MASK) {
+        if (xstate_bv & XSTATE_YMM_MASK) {
+            do_xrstor_ymmh(env, ptr + XO(avx_state), ra);
+        } else {
+            do_clear_ymmh(env);
         }
     }
     if (rfbm & XSTATE_BNDREGS_MASK) {
-- 
2.37.3