arch-arm: Move the memacc_code before op_wb in fp loads

This is trying to fix the bug that arises when a memory exception
is generated during a fp flavoured load (A memory load targeting
a SIMD & FP register).
With the previous template a fault was not stopping the register
value to be modified (wrong)

if (fault == NoFault) {
    fault = readMemAtomic(xc, traceData, EA, Mem, memAccessFlags);
    %(memacc_code)s;
}

if (fault == NoFault) {
    %(op_wb)s;
}

The patch introduces a Load64FpExecute template which is moving the
register write (memacc_code) just before the op_wb

Change-Id: I1c89c525dfa7a4ef489abe0872cd7baacdd6ce3c
Signed-off-by: Giacomo Travaglini <giacomo.travaglini@arm.com>
Reviewed-by: Nikos Nikoleris <nikos.nikoleris@arm.com>
Reviewed-on: https://gem5-review.googlesource.com/c/public/gem5/+/19228
Reviewed-by: Andreas Sandberg <andreas.sandberg@arm.com>
Maintainer: Andreas Sandberg <andreas.sandberg@arm.com>
Tested-by: kokoro <noreply+kokoro@google.com>

src/arch/arm/isa/insts/ldr64.isa

@@ -99,6 +99,13 @@ let {{
             if self.flavor in ("acex", "exclusive", "exp", "acexp"):
                 self.memFlags.append("Request::LLSC")
 
+            # Using a different execute template for fp flavoured loads.
+            # In this specific template the memacc_code is executed
+            # conditionally depending of wether the memory load has
+            # generated any fault
+            if flavor == "fp":
+                self.fullExecTemplate = eval(self.execBase + 'FpExecute')
+
         def buildEACode(self):
             # Address computation code
             eaCode = ""

src/arch/arm/isa/templates/mem64.isa

@@ -1,6 +1,6 @@
 // -*- mode:c++ -*-
 
-// Copyright (c) 2011-2014, 2017 ARM Limited
+// Copyright (c) 2011-2014, 2017, 2019 ARM Limited
 // All rights reserved
 //
 // The license below extends only to copyright in the software and shall
@@ -70,6 +70,30 @@ def template Load64Execute {{
     }
 }};
 
+def template Load64FpExecute {{
+    Fault %(class_name)s::execute(ExecContext *xc,
+                                  Trace::InstRecord *traceData) const
+    {
+        Addr EA;
+        Fault fault = NoFault;
+
+        %(op_decl)s;
+        %(op_rd)s;
+        %(ea_code)s;
+
+        if (fault == NoFault) {
+            fault = readMemAtomic(xc, traceData, EA, Mem, memAccessFlags);
+        }
+
+        if (fault == NoFault) {
+            %(memacc_code)s;
+            %(op_wb)s;
+        }
+
+        return fault;
+    }
+}};
+
 def template Store64Execute {{
     Fault %(class_name)s::execute(ExecContext *xc,
                                   Trace::InstRecord *traceData) const