target/arm: Add the SME ZA storage to CPUARMState

Place this late in the resettable section of the structure,
to keep the most common element offsets from being > 64k.

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20220620175235.60881-10-richard.henderson@linaro.org
[PMM: expanded comment on zarray[] format]
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

2 files changed, 56 insertions, 0 deletions

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 05d369e690..52ab6f9bb9 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -694,6 +694,28 @@ typedef struct CPUArchState {
     } keys;
 
     uint64_t scxtnum_el[4];
+
+    /*
+     * SME ZA storage -- 256 x 256 byte array, with bytes in host word order,
+     * as we do with vfp.zregs[].  This corresponds to the architectural ZA
+     * array, where ZA[N] is in the least-significant bytes of env->zarray[N].
+     * When SVL is less than the architectural maximum, the accessible
+     * storage is restricted, such that if the SVL is X bytes the guest can
+     * see only the bottom X elements of zarray[], and only the least
+     * significant X bytes of each element of the array. (In other words,
+     * the observable part is always square.)
+     *
+     * The ZA storage can also be considered as a set of square tiles of
+     * elements of different sizes. The mapping from tiles to the ZA array
+     * is architecturally defined, such that for tiles of elements of esz
+     * bytes, the Nth row (or "horizontal slice") of tile T is in
+     * ZA[T + N * esz]. Note that this means that each tile is not contiguous
+     * in the ZA storage, because its rows are striped through the ZA array.
+     *
+     * Because this is so large, keep this toward the end of the reset area,
+     * to keep the offsets into the rest of the structure smaller.
+     */
+    ARMVectorReg zarray[ARM_MAX_VQ * 16];
 #endif
 
 #if defined(CONFIG_USER_ONLY)
diff --git a/target/arm/machine.c b/target/arm/machine.c
index 285e387d2c..54c5c62433 100644
--- a/target/arm/machine.c
+++ b/target/arm/machine.c
@@ -167,6 +167,39 @@ static const VMStateDescription vmstate_sve = {
         VMSTATE_END_OF_LIST()
     }
 };
+
+static const VMStateDescription vmstate_vreg = {
+    .name = "vreg",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT64_ARRAY(d, ARMVectorReg, ARM_MAX_VQ * 2),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static bool za_needed(void *opaque)
+{
+    ARMCPU *cpu = opaque;
+
+    /*
+     * When ZA storage is disabled, its contents are discarded.
+     * It will be zeroed when ZA storage is re-enabled.
+     */
+    return FIELD_EX64(cpu->env.svcr, SVCR, ZA);
+}
+
+static const VMStateDescription vmstate_za = {
+    .name = "cpu/sme",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = za_needed,
+    .fields = (VMStateField[]) {
+        VMSTATE_STRUCT_ARRAY(env.zarray, ARMCPU, ARM_MAX_VQ * 16, 0,
+                             vmstate_vreg, ARMVectorReg),
+        VMSTATE_END_OF_LIST()
+    }
+};
 #endif /* AARCH64 */
 
 static bool serror_needed(void *opaque)
@@ -884,6 +917,7 @@ const VMStateDescription vmstate_arm_cpu = {
         &vmstate_m_security,
 #ifdef TARGET_AARCH64
         &vmstate_sve,
+        &vmstate_za,
 #endif
         &vmstate_serror,
         &vmstate_irq_line_state,