target-i386: make xmm_regs 512-bit wide

Right now, the AVX512 registers are split in many different fields:
xmm_regs for the low 128 bits of the first 16 registers, ymmh_regs
for the next 128 bits of the same first 16 registers, zmmh_regs
for the next 256 bits of the same first 16 registers, and finally
hi16_zmm_regs for the full 512 bits of the second 16 bit registers.

This makes it simple to move data in and out of the xsave region,
but would be a nightmare for a hypothetical TCG implementation and
leads to a proliferation of [XYZ]MM_[BWLSQD] macros.  Instead,
this patch marshals data manually from the xsave region to a single
32x512-bit array, simplifying the macro jungle and clarifying which
bits are in which vmstate subsection.

The migration format is unaffected.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

3 files changed, 59 insertions, 104 deletions

diff --git a/target-i386/cpu.h b/target-i386/cpu.h
index da33587..478450c 100644
--- a/target-i386/cpu.h
+++ b/target-i386/cpu.h
@@ -713,31 +713,13 @@ typedef struct SegmentCache {
 } SegmentCache;
 
 typedef union {
-    uint8_t _b[16];
-    uint16_t _w[8];
-    uint32_t _l[4];
-    uint64_t _q[2];
-    float32 _s[4];
-    float64 _d[2];
-} XMMReg;
-
-typedef union {
-    uint8_t _b[32];
-    uint16_t _w[16];
-    uint32_t _l[8];
-    uint64_t _q[4];
-    float32 _s[8];
-    float64 _d[4];
-} YMMReg;
-
-typedef union {
     uint8_t _b[64];
     uint16_t _w[32];
     uint32_t _l[16];
     uint64_t _q[8];
     float32 _s[16];
     float64 _d[8];
-} ZMMReg;
+} XMMReg; /* really zmm */
 
 typedef union {
     uint8_t _b[8];
@@ -758,46 +740,18 @@ typedef struct BNDCSReg {
 } BNDCSReg;
 
 #ifdef HOST_WORDS_BIGENDIAN
-#define ZMM_B(n) _b[63 - (n)]
-#define ZMM_W(n) _w[31 - (n)]
-#define ZMM_L(n) _l[15 - (n)]
-#define ZMM_S(n) _s[15 - (n)]
-#define ZMM_Q(n) _q[7 - (n)]
-#define ZMM_D(n) _d[7 - (n)]
-
-#define YMM_B(n) _b[31 - (n)]
-#define YMM_W(n) _w[15 - (n)]
-#define YMM_L(n) _l[7 - (n)]
-#define YMM_S(n) _s[7 - (n)]
-#define YMM_Q(n) _q[3 - (n)]
-#define YMM_D(n) _d[3 - (n)]
-
-#define XMM_B(n) _b[15 - (n)]
-#define XMM_W(n) _w[7 - (n)]
-#define XMM_L(n) _l[3 - (n)]
-#define XMM_S(n) _s[3 - (n)]
-#define XMM_Q(n) _q[1 - (n)]
-#define XMM_D(n) _d[1 - (n)]
+#define XMM_B(n) _b[63 - (n)]
+#define XMM_W(n) _w[31 - (n)]
+#define XMM_L(n) _l[15 - (n)]
+#define XMM_S(n) _s[15 - (n)]
+#define XMM_Q(n) _q[7 - (n)]
+#define XMM_D(n) _d[7 - (n)]
 
 #define MMX_B(n) _b[7 - (n)]
 #define MMX_W(n) _w[3 - (n)]
 #define MMX_L(n) _l[1 - (n)]
 #define MMX_S(n) _s[1 - (n)]
 #else
-#define ZMM_B(n) _b[n]
-#define ZMM_W(n) _w[n]
-#define ZMM_L(n) _l[n]
-#define ZMM_S(n) _s[n]
-#define ZMM_Q(n) _q[n]
-#define ZMM_D(n) _d[n]
-
-#define YMM_B(n) _b[n]
-#define YMM_W(n) _w[n]
-#define YMM_L(n) _l[n]
-#define YMM_S(n) _s[n]
-#define YMM_Q(n) _q[n]
-#define YMM_D(n) _d[n]
-
 #define XMM_B(n) _b[n]
 #define XMM_W(n) _w[n]
 #define XMM_L(n) _l[n]
@@ -896,17 +850,11 @@ typedef struct CPUX86State {
     float_status mmx_status; /* for 3DNow! float ops */
     float_status sse_status;
     uint32_t mxcsr;
-    XMMReg xmm_regs[CPU_NB_REGS];
+    XMMReg xmm_regs[CPU_NB_REGS == 8 ? 8 : 32];
     XMMReg xmm_t0;
     MMXReg mmx_t0;
 
-    XMMReg ymmh_regs[CPU_NB_REGS];
-
     uint64_t opmask_regs[NB_OPMASK_REGS];
-    YMMReg zmmh_regs[CPU_NB_REGS];
-#ifdef TARGET_X86_64
-    ZMMReg hi16_zmm_regs[CPU_NB_REGS];
-#endif
 
     /* sysenter registers */
     uint32_t sysenter_cs;
diff --git a/target-i386/kvm.c b/target-i386/kvm.c
index 36b1519..40d6a14 100644
--- a/target-i386/kvm.c
+++ b/target-i386/kvm.c
@@ -1048,7 +1048,7 @@ static int kvm_put_xsave(X86CPU *cpu)
     CPUX86State *env = &cpu->env;
     struct kvm_xsave* xsave = env->kvm_xsave_buf;
     uint16_t cwd, swd, twd;
-    uint8_t *xmm;
+    uint8_t *xmm, *ymmh, *zmmh;
     int i, r;
 
     if (!kvm_has_xsave()) {
@@ -1071,26 +1071,30 @@ static int kvm_put_xsave(X86CPU *cpu)
             sizeof env->fpregs);
     xsave->region[XSAVE_MXCSR] = env->mxcsr;
     *(uint64_t *)&xsave->region[XSAVE_XSTATE_BV] = env->xstate_bv;
-    memcpy(&xsave->region[XSAVE_YMMH_SPACE], env->ymmh_regs,
-            sizeof env->ymmh_regs);
     memcpy(&xsave->region[XSAVE_BNDREGS], env->bnd_regs,
             sizeof env->bnd_regs);
     memcpy(&xsave->region[XSAVE_BNDCSR], &env->bndcs_regs,
             sizeof(env->bndcs_regs));
     memcpy(&xsave->region[XSAVE_OPMASK], env->opmask_regs,
             sizeof env->opmask_regs);
-    memcpy(&xsave->region[XSAVE_ZMM_Hi256], env->zmmh_regs,
-            sizeof env->zmmh_regs);
 
     xmm = (uint8_t *)&xsave->region[XSAVE_XMM_SPACE];
-    for (i = 0; i < CPU_NB_REGS; i++, xmm += 16) {
+    ymmh = (uint8_t *)&xsave->region[XSAVE_YMMH_SPACE];
+    zmmh = (uint8_t *)&xsave->region[XSAVE_ZMM_Hi256];
+    for (i = 0; i < CPU_NB_REGS; i++, xmm += 16, ymmh += 16, zmmh += 32) {
         stq_p(xmm,     env->xmm_regs[i].XMM_Q(0));
         stq_p(xmm+8,   env->xmm_regs[i].XMM_Q(1));
+        stq_p(ymmh,    env->xmm_regs[i].XMM_Q(2));
+        stq_p(ymmh+8,  env->xmm_regs[i].XMM_Q(3));
+        stq_p(zmmh,    env->xmm_regs[i].XMM_Q(4));
+        stq_p(zmmh+8,  env->xmm_regs[i].XMM_Q(5));
+        stq_p(zmmh+16, env->xmm_regs[i].XMM_Q(6));
+        stq_p(zmmh+24, env->xmm_regs[i].XMM_Q(7));
     }
 
 #ifdef TARGET_X86_64
-    memcpy(&xsave->region[XSAVE_Hi16_ZMM], env->hi16_zmm_regs,
-            sizeof env->hi16_zmm_regs);
+    memcpy(&xsave->region[XSAVE_Hi16_ZMM], &env->xmm_regs[16],
+            16 * sizeof env->xmm_regs[16]);
 #endif
     r = kvm_vcpu_ioctl(CPU(cpu), KVM_SET_XSAVE, xsave);
     return r;
@@ -1407,7 +1411,7 @@ static int kvm_get_xsave(X86CPU *cpu)
     CPUX86State *env = &cpu->env;
     struct kvm_xsave* xsave = env->kvm_xsave_buf;
     int ret, i;
-    const uint8_t *xmm;
+    const uint8_t *xmm, *ymmh, *zmmh;
     uint16_t cwd, swd, twd;
 
     if (!kvm_has_xsave()) {
@@ -1435,26 +1439,30 @@ static int kvm_get_xsave(X86CPU *cpu)
     memcpy(env->fpregs, &xsave->region[XSAVE_ST_SPACE],
             sizeof env->fpregs);
     env->xstate_bv = *(uint64_t *)&xsave->region[XSAVE_XSTATE_BV];
-    memcpy(env->ymmh_regs, &xsave->region[XSAVE_YMMH_SPACE],
-            sizeof env->ymmh_regs);
     memcpy(env->bnd_regs, &xsave->region[XSAVE_BNDREGS],
             sizeof env->bnd_regs);
     memcpy(&env->bndcs_regs, &xsave->region[XSAVE_BNDCSR],
             sizeof(env->bndcs_regs));
     memcpy(env->opmask_regs, &xsave->region[XSAVE_OPMASK],
             sizeof env->opmask_regs);
-    memcpy(env->zmmh_regs, &xsave->region[XSAVE_ZMM_Hi256],
-            sizeof env->zmmh_regs);
 
     xmm = (const uint8_t *)&xsave->region[XSAVE_XMM_SPACE];
-    for (i = 0; i < CPU_NB_REGS; i++, xmm += 16) {
+    ymmh = (const uint8_t *)&xsave->region[XSAVE_YMMH_SPACE];
+    zmmh = (const uint8_t *)&xsave->region[XSAVE_ZMM_Hi256];
+    for (i = 0; i < CPU_NB_REGS; i++, xmm += 16, ymmh += 16, zmmh += 32) {
         env->xmm_regs[i].XMM_Q(0) = ldq_p(xmm);
         env->xmm_regs[i].XMM_Q(1) = ldq_p(xmm+8);
+        env->xmm_regs[i].XMM_Q(2) = ldq_p(ymmh);
+        env->xmm_regs[i].XMM_Q(3) = ldq_p(ymmh+8);
+        env->xmm_regs[i].XMM_Q(4) = ldq_p(zmmh);
+        env->xmm_regs[i].XMM_Q(5) = ldq_p(zmmh+8);
+        env->xmm_regs[i].XMM_Q(6) = ldq_p(zmmh+16);
+        env->xmm_regs[i].XMM_Q(7) = ldq_p(zmmh+24);
     }
 
 #ifdef TARGET_X86_64
-    memcpy(env->hi16_zmm_regs, &xsave->region[XSAVE_Hi16_ZMM],
-            sizeof env->hi16_zmm_regs);
+    memcpy(&env->xmm_regs[16], &xsave->region[XSAVE_Hi16_ZMM],
+           16 * sizeof env->xmm_regs[16]);
 #endif
     return 0;
 }
diff --git a/target-i386/machine.c b/target-i386/machine.c
index 604a49a..cd1ddd2 100644
--- a/target-i386/machine.c
+++ b/target-i386/machine.c
@@ -46,14 +46,14 @@ static const VMStateDescription vmstate_xmm_reg = {
     VMSTATE_STRUCT_SUB_ARRAY(_field, _state, _start, CPU_NB_REGS, 0,     \
                              vmstate_xmm_reg, XMMReg)
 
-/* YMMH format is the same as XMM */
+/* YMMH format is the same as XMM, but for bits 128-255 */
 static const VMStateDescription vmstate_ymmh_reg = {
     .name = "ymmh_reg",
     .version_id = 1,
     .minimum_version_id = 1,
     .fields = (VMStateField[]) {
-        VMSTATE_UINT64(XMM_Q(0), XMMReg),
-        VMSTATE_UINT64(XMM_Q(1), XMMReg),
+        VMSTATE_UINT64(XMM_Q(2), XMMReg),
+        VMSTATE_UINT64(XMM_Q(3), XMMReg),
         VMSTATE_END_OF_LIST()
     }
 };
@@ -67,17 +67,17 @@ static const VMStateDescription vmstate_zmmh_reg = {
     .version_id = 1,
     .minimum_version_id = 1,
     .fields = (VMStateField[]) {
-        VMSTATE_UINT64(YMM_Q(0), YMMReg),
-        VMSTATE_UINT64(YMM_Q(1), YMMReg),
-        VMSTATE_UINT64(YMM_Q(2), YMMReg),
-        VMSTATE_UINT64(YMM_Q(3), YMMReg),
+        VMSTATE_UINT64(XMM_Q(4), XMMReg),
+        VMSTATE_UINT64(XMM_Q(5), XMMReg),
+        VMSTATE_UINT64(XMM_Q(6), XMMReg),
+        VMSTATE_UINT64(XMM_Q(7), XMMReg),
         VMSTATE_END_OF_LIST()
     }
 };
 
 #define VMSTATE_ZMMH_REGS_VARS(_field, _state, _start)                   \
     VMSTATE_STRUCT_SUB_ARRAY(_field, _state, _start, CPU_NB_REGS, 0,     \
-                             vmstate_zmmh_reg, YMMReg)
+                             vmstate_zmmh_reg, XMMReg)
 
 #ifdef TARGET_X86_64
 static const VMStateDescription vmstate_hi16_zmm_reg = {
@@ -85,21 +85,21 @@ static const VMStateDescription vmstate_hi16_zmm_reg = {
     .version_id = 1,
     .minimum_version_id = 1,
     .fields = (VMStateField[]) {
-        VMSTATE_UINT64(ZMM_Q(0), ZMMReg),
-        VMSTATE_UINT64(ZMM_Q(1), ZMMReg),
-        VMSTATE_UINT64(ZMM_Q(2), ZMMReg),
-        VMSTATE_UINT64(ZMM_Q(3), ZMMReg),
-        VMSTATE_UINT64(ZMM_Q(4), ZMMReg),
-        VMSTATE_UINT64(ZMM_Q(5), ZMMReg),
-        VMSTATE_UINT64(ZMM_Q(6), ZMMReg),
-        VMSTATE_UINT64(ZMM_Q(7), ZMMReg),
+        VMSTATE_UINT64(XMM_Q(0), XMMReg),
+        VMSTATE_UINT64(XMM_Q(1), XMMReg),
+        VMSTATE_UINT64(XMM_Q(2), XMMReg),
+        VMSTATE_UINT64(XMM_Q(3), XMMReg),
+        VMSTATE_UINT64(XMM_Q(4), XMMReg),
+        VMSTATE_UINT64(XMM_Q(5), XMMReg),
+        VMSTATE_UINT64(XMM_Q(6), XMMReg),
+        VMSTATE_UINT64(XMM_Q(7), XMMReg),
         VMSTATE_END_OF_LIST()
     }
 };
 
 #define VMSTATE_Hi16_ZMM_REGS_VARS(_field, _state, _start)               \
     VMSTATE_STRUCT_SUB_ARRAY(_field, _state, _start, CPU_NB_REGS, 0,     \
-                             vmstate_hi16_zmm_reg, ZMMReg)
+                             vmstate_hi16_zmm_reg, XMMReg)
 #endif
 
 static const VMStateDescription vmstate_bnd_regs = {
@@ -658,17 +658,16 @@ static bool avx512_needed(void *opaque)
     }
 
     for (i = 0; i < CPU_NB_REGS; i++) {
-#define ENV_ZMMH(reg, field) (env->zmmh_regs[reg].YMM_Q(field))
-        if (ENV_ZMMH(i, 0) || ENV_ZMMH(i, 1) ||
-            ENV_ZMMH(i, 2) || ENV_ZMMH(i, 3)) {
+#define ENV_XMM(reg, field) (env->xmm_regs[reg].XMM_Q(field))
+        if (ENV_XMM(i, 4) || ENV_XMM(i, 6) ||
+            ENV_XMM(i, 5) || ENV_XMM(i, 7)) {
             return true;
         }
 #ifdef TARGET_X86_64
-#define ENV_Hi16_ZMM(reg, field) (env->hi16_zmm_regs[reg].ZMM_Q(field))
-        if (ENV_Hi16_ZMM(i, 0) || ENV_Hi16_ZMM(i, 1) ||
-            ENV_Hi16_ZMM(i, 2) || ENV_Hi16_ZMM(i, 3) ||
-            ENV_Hi16_ZMM(i, 4) || ENV_Hi16_ZMM(i, 5) ||
-            ENV_Hi16_ZMM(i, 6) || ENV_Hi16_ZMM(i, 7)) {
+        if (ENV_XMM(i+16, 0) || ENV_XMM(i+16, 1) ||
+            ENV_XMM(i+16, 2) || ENV_XMM(i+16, 3) ||
+            ENV_XMM(i+16, 4) || ENV_XMM(i+16, 5) ||
+            ENV_XMM(i+16, 6) || ENV_XMM(i+16, 7)) {
             return true;
         }
 #endif
@@ -683,9 +682,9 @@ static const VMStateDescription vmstate_avx512 = {
     .minimum_version_id = 1,
     .fields = (VMStateField[]) {
         VMSTATE_UINT64_ARRAY(env.opmask_regs, X86CPU, NB_OPMASK_REGS),
-        VMSTATE_ZMMH_REGS_VARS(env.zmmh_regs, X86CPU, 0),
+        VMSTATE_ZMMH_REGS_VARS(env.xmm_regs, X86CPU, 0),
 #ifdef TARGET_X86_64
-        VMSTATE_Hi16_ZMM_REGS_VARS(env.hi16_zmm_regs, X86CPU, 0),
+        VMSTATE_Hi16_ZMM_REGS_VARS(env.xmm_regs, X86CPU, 16),
 #endif
         VMSTATE_END_OF_LIST()
     }
@@ -807,7 +806,7 @@ VMStateDescription vmstate_x86_cpu = {
         /* XSAVE related fields */
         VMSTATE_UINT64_V(env.xcr0, X86CPU, 12),
         VMSTATE_UINT64_V(env.xstate_bv, X86CPU, 12),
-        VMSTATE_YMMH_REGS_VARS(env.ymmh_regs, X86CPU, 0, 12),
+        VMSTATE_YMMH_REGS_VARS(env.xmm_regs, X86CPU, 0, 12),
         VMSTATE_END_OF_LIST()
         /* The above list is not sorted /wrt version numbers, watch out! */
     },