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: qemu-stable@nongnu.org
Fixes: 18fc2405781 ("target/arm: Implement SVE fp complex multiply add (indexed)")
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2376
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240625183536.1672454-2-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 76bccf3cb9d9383da0128bbc6d1300cddbe3ae8f)
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>

diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index f59d3b26eacf08f80c1e601f221a54a3764fc9ce..859366e2641db26d90f2ed0dfb8095f691adcaaf 100644 (file)
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -842,7 +842,7 @@ 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.  */
@@ -904,7 +904,7 @@ 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.  */