target/arm/cpu: define same set of registers for aarch32 and aarch64

To eliminate TARGET_AARCH64, we need to make various definitions common
between 32 and 64 bit Arm targets.
Added registers are used only by aarch64 code, and the only impact is on
the size of CPUARMState, and added zarray
(ARMVectorReg zarray[ARM_MAX_VQ * 16]) member (+64KB)

It could be eventually possible to allocate this array only for aarch64
emulation, but I'm not sure it's worth the hassle to save a few KB per
vcpu. Running qemu-system takes already several hundreds of MB of
(resident) memory, and qemu-user takes dozens of MB of (resident) memory
anyway.

As part of this, we define ARM_MAX_VQ once for aarch32 and aarch64,
which will affect zregs field for aarch32.
This field is used for MVE and SVE implementations. MVE implementation
is clipping index value to 0 or 1 for zregs[*].d[],
so we should not touch the rest of data in this case anyway.

This change is safe regarding migration, because aarch64 registers still
have the same size, and for aarch32, only zregs is modified.
Migration code explicitly specify a size of 2 for env.vfp.zregs[0].d,
VMSTATE_UINT64_SUB_ARRAY(env.vfp.zregs[0].d, ARMCPU, 0, 2). So extending
the storage size has no impact.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Pierrick Bouvier <pierrick.bouvier@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-ID: <20250325045915.994760-22-pierrick.bouvier@linaro.org>

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index cc975175c618642a65d4ee2131b7aab4bdbb3d29..b1c3e46326772439aad8f4c45f49cb7dc0de5743 100644 (file)
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -169,17 +169,12 @@ typedef struct ARMGenericTimer {
  * Align the data for use with TCG host vector operations.
  */
 
-#ifdef TARGET_AARCH64
-# define ARM_MAX_VQ    16
-#else
-# define ARM_MAX_VQ    1
-#endif
+#define ARM_MAX_VQ    16
 
 typedef struct ARMVectorReg {
     uint64_t d[2 * ARM_MAX_VQ] QEMU_ALIGNED(16);
 } ARMVectorReg;
 
-#ifdef TARGET_AARCH64
 /* In AArch32 mode, predicate registers do not exist at all.  */
 typedef struct ARMPredicateReg {
     uint64_t p[DIV_ROUND_UP(2 * ARM_MAX_VQ, 8)] QEMU_ALIGNED(16);
@@ -189,7 +184,6 @@ typedef struct ARMPredicateReg {
 typedef struct ARMPACKey {
     uint64_t lo, hi;
 } ARMPACKey;
-#endif
 
 /* See the commentary above the TBFLAG field definitions.  */
 typedef struct CPUARMTBFlags {
@@ -660,13 +654,11 @@ typedef struct CPUArchState {
     struct {
         ARMVectorReg zregs[32];
 
-#ifdef TARGET_AARCH64
         /* Store FFR as pregs[16] to make it easier to treat as any other.  */
 #define FFR_PRED_NUM 16
         ARMPredicateReg pregs[17];
         /* Scratch space for aa64 sve predicate temporary.  */
         ARMPredicateReg preg_tmp;
-#endif
 
         /* We store these fpcsr fields separately for convenience.  */
         uint32_t qc[4] QEMU_ALIGNED(16);
@@ -711,7 +703,6 @@ typedef struct CPUArchState {
         uint32_t cregs[16];
     } iwmmxt;
 
-#ifdef TARGET_AARCH64
     struct {
         ARMPACKey apia;
         ARMPACKey apib;
@@ -743,7 +734,6 @@ typedef struct CPUArchState {
      * to keep the offsets into the rest of the structure smaller.
      */
     ARMVectorReg zarray[ARM_MAX_VQ * 16];
-#endif
 
     struct CPUBreakpoint *cpu_breakpoint[16];
     struct CPUWatchpoint *cpu_watchpoint[16];