vector: crypto: fix EMUL alignment check for .vs operations

riscv/insns/vsm4r_vs.h

@@ -6,6 +6,7 @@ const uint32_t EGS = 4;
 
 require_vsm4_constraints;
 require_align(insn.rd(), P.VU.vflmul);
+require_vs2_align_eglmul(128);
 // No overlap of vd and vs2.
 require_noover_eglmul(insn.rd(), insn.rs2());
 

riscv/zvk_ext_macros.h

@@ -86,6 +86,20 @@
 //    (LMUL * VLEN) <= EGW
 #define require_egw_fits(EGW)  require((EGW) <= (P.VU.VLEN * P.VU.vflmul))
 
+// Ensures that a register index is aligned to EMUL
+// evaluated as EGW / VLEN.
+// The check is only enabled if this value is greater
+// than one (no index alignment check required for fractional EMUL)
+#define require_vreg_align_eglmul(EGW, VREG_NUM) \
+  do { \
+    float vfeglmul = EGW / P.VU.VLEN; \
+    if (vfeglmul > 1) { \
+      require_align(VREG_NUM, vfeglmul); \
+    }\
+  } while (0)
+
+#define require_vs2_align_eglmul(EGW) require_vreg_align_eglmul(EGW, insn.rs2())
+
 // ensure that rs2 and rd do not overlap, assuming rd encodes an LMUL wide
 // vector register group and rs2 encodes an vs2_EMUL=ceil(EGW / VLEN) vector register
 // group.

riscv/zvkned_ext_macros.h

@@ -10,6 +10,8 @@
 // vaes*.vs instruction constraints:
 //  - Zvkned is enabled
 //  - EGW (128) <= LMUL * VLEN
+//  - vd is LMUL aligned
+//  - vs2 is ceil(EGW / VLEN) aligned
 //  - vd and vs2 cannot overlap
 //
 // The constraint that vstart and vl are both EGS (4) aligned
@@ -22,6 +24,7 @@
     require(P.VU.vsew == 32); \
     require_egw_fits(128); \
     require_align(insn.rd(), P.VU.vflmul); \
+    require_vs2_align_eglmul(128); \
     require_noover_eglmul(insn.rd(), insn.rs2()); \
   } while (false)