arch-arm: Fix decoding for SVE memory instructions

Some SVE memory instructions are missing the makeSP function for
register operands that can be the SP register. This leads to
segmentation faults on the application side as the wrong register is
decoded.

Change-Id: Ic71abc845e0786a60d665231b5f7b024d2955f4b
Signed-off-by: Giacomo Gabrielli <giacomo.gabrielli@arm.com>
Reviewed-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/19169
Tested-by: kokoro <noreply+kokoro@google.com>
Maintainer: Giacomo Travaglini <giacomo.travaglini@arm.com>
diff --git a/src/arch/arm/isa/formats/sve_2nd_level.isa b/src/arch/arm/isa/formats/sve_2nd_level.isa
index def1781..3bfae1d 100644
--- a/src/arch/arm/isa/formats/sve_2nd_level.isa
+++ b/src/arch/arm/isa/formats/sve_2nd_level.isa
@@ -2900,7 +2900,8 @@
             if (bits(machInst, 22)) {
                 // SVE load and broadcast element
                 IntRegIndex zt = (IntRegIndex) (uint8_t) bits(machInst, 4, 0);
-                IntRegIndex rn = (IntRegIndex) (uint8_t) bits(machInst, 9, 5);
+                IntRegIndex rn = makeSP(
+                        (IntRegIndex) (uint8_t) bits(machInst, 9, 5));
                 uint64_t imm = bits(machInst, 21, 16);
                 IntRegIndex pg = (IntRegIndex) (uint8_t)
                                  bits(machInst, 12, 10);
@@ -2940,7 +2941,8 @@
             if (b24_23 != 0x3 && bits(machInst, 21) == 0) {
                 // SVE 32-bit gather load (scalar plus 32-bit unscaled offsets)
                 IntRegIndex zt = (IntRegIndex) (uint8_t) bits(machInst, 4, 0);
-                IntRegIndex rn = (IntRegIndex) (uint8_t) bits(machInst, 9, 5);
+                IntRegIndex rn = makeSP(
+                        (IntRegIndex) (uint8_t) bits(machInst, 9, 5));
                 IntRegIndex zm = (IntRegIndex) (uint8_t)
                          bits(machInst, 20, 16);
                 IntRegIndex pg = (IntRegIndex) (uint8_t)
@@ -2966,8 +2968,8 @@
                     // scaled offsets)
                     IntRegIndex zt = (IntRegIndex) (uint8_t)
                              bits(machInst, 4, 0);
-                    IntRegIndex rn = (IntRegIndex) (uint8_t)
-                             bits(machInst, 9, 5);
+                    IntRegIndex rn = makeSP(
+                            (IntRegIndex) (uint8_t) bits(machInst, 9, 5));
                     IntRegIndex zm = (IntRegIndex) (uint8_t)
                              bits(machInst, 20, 16);
                     IntRegIndex pg = (IntRegIndex) (uint8_t)
@@ -2997,8 +2999,8 @@
                     // offsets)
                     IntRegIndex zt = (IntRegIndex) (uint8_t)
                              bits(machInst, 4, 0);
-                    IntRegIndex rn = (IntRegIndex) (uint8_t)
-                             bits(machInst, 9, 5);
+                    IntRegIndex rn = makeSP(
+                            (IntRegIndex) (uint8_t) bits(machInst, 9, 5));
                     IntRegIndex zm = (IntRegIndex) (uint8_t)
                              bits(machInst, 20, 16);
                     IntRegIndex pg = (IntRegIndex) (uint8_t)
@@ -3018,8 +3020,8 @@
                     // SVE load predicate register
                     IntRegIndex pt = (IntRegIndex) (uint8_t)
                         bits(machInst, 3, 0);
-                    IntRegIndex rn = (IntRegIndex) (uint8_t)
-                        bits(machInst, 9, 5);
+                    IntRegIndex rn = makeSP(
+                            (IntRegIndex) (uint8_t) bits(machInst, 9, 5));
                     uint64_t imm = sext<9>((bits(machInst, 21, 16) << 3) |
                                            bits(machInst, 12, 10));
                     return new SveLdrPred(machInst, pt, rn, imm);
@@ -3028,8 +3030,8 @@
                     // SVE load vector register
                     IntRegIndex zt = (IntRegIndex) (uint8_t)
                         bits(machInst, 4, 0);
-                    IntRegIndex rn = (IntRegIndex) (uint8_t)
-                        bits(machInst, 9, 5);
+                    IntRegIndex rn = makeSP(
+                            (IntRegIndex) (uint8_t) bits(machInst, 9, 5));
                     uint64_t imm = sext<9>((bits(machInst, 21, 16) << 3) |
                                            bits(machInst, 12, 10));
                     return new SveLdrVec(machInst, zt, rn, imm);
@@ -3061,8 +3063,7 @@
     {
         IntRegIndex zt = (IntRegIndex) (uint8_t) bits(machInst, 4, 0);
         IntRegIndex rn = makeSP((IntRegIndex) (uint8_t) bits(machInst, 9, 5));
-        IntRegIndex rm = makeSP(
-            (IntRegIndex) (uint8_t) bits(machInst, 20, 16));
+        IntRegIndex rm = (IntRegIndex) (uint8_t) bits(machInst, 20, 16);
         IntRegIndex pg = (IntRegIndex) (uint8_t) bits(machInst, 12, 10);
 
         if (rm == 0x1f) {
@@ -3078,8 +3079,7 @@
     {
         IntRegIndex zt = (IntRegIndex) (uint8_t) bits(machInst, 4, 0);
         IntRegIndex rn = makeSP((IntRegIndex) (uint8_t) bits(machInst, 9, 5));
-        IntRegIndex rm = makeSP(
-            (IntRegIndex) (uint8_t) bits(machInst, 20, 16));
+        IntRegIndex rm = (IntRegIndex) (uint8_t) bits(machInst, 20, 16);
         IntRegIndex pg = (IntRegIndex) (uint8_t) bits(machInst, 12, 10);
 
         if (rm == 0x1f) {
@@ -3124,7 +3124,8 @@
     decodeSveLoadStructsSS(ExtMachInst machInst)
     {
         IntRegIndex zt = (IntRegIndex) (uint8_t) bits(machInst, 4, 0);
-        IntRegIndex rn = (IntRegIndex) (uint8_t) bits(machInst, 9, 5);
+        IntRegIndex rn = makeSP(
+                (IntRegIndex) (uint8_t) bits(machInst, 9, 5));
         IntRegIndex rm = (IntRegIndex) (uint8_t) bits(machInst, 20, 16);
         IntRegIndex pg = (IntRegIndex) (uint8_t) bits(machInst, 12, 10);
         uint8_t msz = bits(machInst, 24, 23);
@@ -3148,7 +3149,8 @@
     decodeSveLoadStructsSI(ExtMachInst machInst)
     {
         IntRegIndex zt = (IntRegIndex) (uint8_t) bits(machInst, 4, 0);
-        IntRegIndex rn = (IntRegIndex) (uint8_t) bits(machInst, 9, 5);
+        IntRegIndex rn = makeSP(
+                (IntRegIndex) (uint8_t) bits(machInst, 9, 5));
         int64_t imm = sext<4>(bits(machInst, 19, 16));
         IntRegIndex pg = (IntRegIndex) (uint8_t) bits(machInst, 12, 10);
         uint8_t msz = bits(machInst, 24, 23);
@@ -3212,7 +3214,8 @@
                 // SVE 64-bit gather load (scalar plus unpacked 32-bit unscaled
                 // offsets)
                 IntRegIndex zt = (IntRegIndex) (uint8_t) bits(machInst, 4, 0);
-                IntRegIndex rn = (IntRegIndex) (uint8_t) bits(machInst, 9, 5);
+                IntRegIndex rn = makeSP(
+                        (IntRegIndex) (uint8_t) bits(machInst, 9, 5));
                 IntRegIndex zm = (IntRegIndex) (uint8_t)
                          bits(machInst, 20, 16);
                 IntRegIndex pg = (IntRegIndex) (uint8_t)
@@ -3229,7 +3232,8 @@
             if (bits(machInst, 22)) {
                 // SVE 64-bit gather load (scalar plus 64-bit unscaled offsets)
                 IntRegIndex zt = (IntRegIndex) (uint8_t) bits(machInst, 4, 0);
-                IntRegIndex rn = (IntRegIndex) (uint8_t) bits(machInst, 9, 5);
+                IntRegIndex rn = makeSP(
+                        (IntRegIndex) (uint8_t) bits(machInst, 9, 5));
                 IntRegIndex zm = (IntRegIndex) (uint8_t)
                          bits(machInst, 20, 16);
                 IntRegIndex pg = (IntRegIndex) (uint8_t)
@@ -3252,7 +3256,8 @@
                 //  SVE 64-bit gather load (scalar plus unpacked 32-bit scaled
                 //  offsets)
                 IntRegIndex zt = (IntRegIndex) (uint8_t) bits(machInst, 4, 0);
-                IntRegIndex rn = (IntRegIndex) (uint8_t) bits(machInst, 9, 5);
+                IntRegIndex rn = makeSP(
+                        (IntRegIndex) (uint8_t) bits(machInst, 9, 5));
                 IntRegIndex zm = (IntRegIndex) (uint8_t)
                          bits(machInst, 20, 16);
                 IntRegIndex pg = (IntRegIndex) (uint8_t)
@@ -3289,8 +3294,8 @@
                     // offsets)
                     IntRegIndex zt = (IntRegIndex) (uint8_t)
                              bits(machInst, 4, 0);
-                    IntRegIndex rn = (IntRegIndex) (uint8_t)
-                             bits(machInst, 9, 5);
+                    IntRegIndex rn = makeSP(
+                            (IntRegIndex) (uint8_t) bits(machInst, 9, 5));
                     IntRegIndex zm = (IntRegIndex) (uint8_t)
                              bits(machInst, 20, 16);
                     IntRegIndex pg = (IntRegIndex) (uint8_t)
@@ -3317,8 +3322,7 @@
     {
         IntRegIndex zt = (IntRegIndex) (uint8_t) bits(machInst, 4, 0);
         IntRegIndex rn = makeSP((IntRegIndex) (uint8_t) bits(machInst, 9, 5));
-        IntRegIndex rm = makeSP(
-            (IntRegIndex) (uint8_t) bits(machInst, 20, 16));
+        IntRegIndex rm = (IntRegIndex) (uint8_t) bits(machInst, 20, 16);
         IntRegIndex pg = (IntRegIndex) (uint8_t) bits(machInst, 12, 10);
 
         if (rm == 0x1f) {
@@ -3357,7 +3361,8 @@
     decodeSveStoreStructsSS(ExtMachInst machInst)
     {
         IntRegIndex zt = (IntRegIndex) (uint8_t) bits(machInst, 4, 0);
-        IntRegIndex rn = (IntRegIndex) (uint8_t) bits(machInst, 9, 5);
+        IntRegIndex rn = makeSP(
+                (IntRegIndex) (uint8_t) bits(machInst, 9, 5));
         IntRegIndex rm = (IntRegIndex) (uint8_t) bits(machInst, 20, 16);
         IntRegIndex pg = (IntRegIndex) (uint8_t) bits(machInst, 12, 10);
         uint8_t msz = bits(machInst, 24, 23);
@@ -3375,7 +3380,8 @@
     decodeSveStoreStructsSI(ExtMachInst machInst)
     {
         IntRegIndex zt = (IntRegIndex) (uint8_t) bits(machInst, 4, 0);
-        IntRegIndex rn = (IntRegIndex) (uint8_t) bits(machInst, 9, 5);
+        IntRegIndex rn = makeSP(
+                (IntRegIndex) (uint8_t) bits(machInst, 9, 5));
         int64_t imm = sext<4>(bits(machInst, 19, 16));
         IntRegIndex pg = (IntRegIndex) (uint8_t) bits(machInst, 12, 10);
         uint8_t msz = bits(machInst, 24, 23);
@@ -3426,7 +3432,8 @@
           case 0x6:
             {
                 IntRegIndex zt = (IntRegIndex) (uint8_t) bits(machInst, 4, 0);
-                IntRegIndex rn = (IntRegIndex) (uint8_t) bits(machInst, 9, 5);
+                IntRegIndex rn = makeSP(
+                        (IntRegIndex) (uint8_t) bits(machInst, 9, 5));
                 IntRegIndex zm = (IntRegIndex) (uint8_t)
                          bits(machInst, 20, 16);
                 IntRegIndex pg = (IntRegIndex) (uint8_t)
@@ -3476,8 +3483,8 @@
                     // offsets)
                     IntRegIndex zt = (IntRegIndex) (uint8_t)
                             bits(machInst, 4, 0);
-                    IntRegIndex rn = (IntRegIndex) (uint8_t)
-                            bits(machInst, 9, 5);
+                    IntRegIndex rn = makeSP(
+                            (IntRegIndex) (uint8_t) bits(machInst, 9, 5));
                     IntRegIndex zm = (IntRegIndex) (uint8_t)
                             bits(machInst, 20, 16);
                     IntRegIndex pg = (IntRegIndex) (uint8_t)
@@ -3494,8 +3501,8 @@
                     // offsets)
                     IntRegIndex zt = (IntRegIndex) (uint8_t)
                             bits(machInst, 4, 0);
-                    IntRegIndex rn = (IntRegIndex) (uint8_t)
-                            bits(machInst, 9, 5);
+                    IntRegIndex rn = makeSP(
+                            (IntRegIndex) (uint8_t) bits(machInst, 9, 5));
                     IntRegIndex zm = (IntRegIndex) (uint8_t)
                             bits(machInst, 20, 16);
                     IntRegIndex pg = (IntRegIndex) (uint8_t)