target/arm: Fix VCMLA Dd, Dn, Dm[idx]

The inner loop, bounded by eltspersegment, must not be
larger than the outer loop, bounded by elements.

Cc: [email protected]
Fixes: 18fc240 ("target/arm: Implement SVE fp complex multiply add (indexed)")
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2376
Reviewed-by: Peter Maydell <[email protected]>
Signed-off-by: Richard Henderson <[email protected]>
Message-id: [email protected]
Signed-off-by: Peter Maydell <[email protected]>

Author: rth7680

target/arm/tcg/vec_helper.c

@@ -907,7 +907,7 @@ void HELPER(gvec_fcmlah_idx)(void *vd, void *vn, void *vm, void *va,
     intptr_t index = extract32(desc, SIMD_DATA_SHIFT + 2, 2);
     uint32_t neg_real = flip ^ neg_imag;
     intptr_t elements = opr_sz / sizeof(float16);
-    intptr_t eltspersegment = 16 / sizeof(float16);
+    intptr_t eltspersegment = MIN(16 / sizeof(float16), elements);
     intptr_t i, j;
 
     /* Shift boolean to the sign bit so we can xor to negate.  */
@@ -969,7 +969,7 @@ void HELPER(gvec_fcmlas_idx)(void *vd, void *vn, void *vm, void *va,
     intptr_t index = extract32(desc, SIMD_DATA_SHIFT + 2, 2);
     uint32_t neg_real = flip ^ neg_imag;
     intptr_t elements = opr_sz / sizeof(float32);
-    intptr_t eltspersegment = 16 / sizeof(float32);
+    intptr_t eltspersegment = MIN(16 / sizeof(float32), elements);
     intptr_t i, j;
 
     /* Shift boolean to the sign bit so we can xor to negate.  */