Adds AArch64 Native Code Generator

In which we add a new code generator to the Glasgow Haskell
Compiler. This codegen supports ELF and Mach-O targets, thus covering
Linux, macOS, and BSDs in principle.  It was tested only on macOS and
Linux.  The NCG follows a similar structure as the other native code
generators we already have, and should therfore be realtively easy to
follow.

It supports most of the features required for a proper native code
generator, but does not claim to be perfect or fully optimised.  There
are still opportunities for optimisations.

Metric Decrease:
    ManyAlternatives
    ManyConstructors
    MultiLayerModules
    PmSeriesG
    PmSeriesS
    PmSeriesT
    PmSeriesV
    T10421
    T10421a
    T10858
    T11195
    T11276
    T11303b
    T11374
    T11822
    T12227
    T12545
    T12707
    T13035
    T13253
    T13253-spj
    T13379
    T13701
    T13719
    T14683
    T14697
    T15164
    T15630
    T16577
    T17096
    T17516
    T17836
    T17836b
    T17977
    T17977b
    T18140
    T18282
    T18304
    T18478
    T18698a
    T18698b
    T18923
    T1969
    T3064
    T5030
    T5321FD
    T5321Fun
    T5631
    T5642
    T5837
    T783
    T9198
    T9233
    T9630
    T9872d
    T9961
    WWRec
Metric Increase:
    T4801

3 files changed, 95 insertions, 3 deletions

diff --git a/includes/CodeGen.Platform.hs b/includes/CodeGen.Platform.hs
index 8c942662e6..0dfac62a3f 100644
--- a/includes/CodeGen.Platform.hs
+++ b/includes/CodeGen.Platform.hs
@@ -1,7 +1,8 @@
 
 import GHC.Cmm.Expr
 #if !(defined(MACHREGS_i386) || defined(MACHREGS_x86_64) \
-    || defined(MACHREGS_sparc) || defined(MACHREGS_powerpc))
+    || defined(MACHREGS_sparc) || defined(MACHREGS_powerpc) \
+    || defined(MACHREGS_aarch64))
 import GHC.Utils.Panic.Plain
 #endif
 import GHC.Platform.Reg
@@ -1016,6 +1017,98 @@ freeReg REG_HpLim = False
 # endif
 freeReg _ = True
 
+#elif defined(MACHREGS_aarch64)
+
+-- stack pointer / zero reg
+freeReg 31 = False
+-- link register
+freeReg 30 = False
+-- frame pointer
+freeReg 29 = False
+-- ip0 -- used for spill offset computations
+freeReg 16 = False
+
+# if defined(REG_Base)
+freeReg REG_Base  = False
+# endif
+# if defined(REG_Sp)
+freeReg REG_Sp    = False
+# endif
+# if defined(REG_SpLim)
+freeReg REG_SpLim = False
+# endif
+# if defined(REG_Hp)
+freeReg REG_Hp    = False
+# endif
+# if defined(REG_HpLim)
+freeReg REG_HpLim = False
+# endif
+
+# if defined(REG_R1)
+freeReg REG_R1    = False
+# endif
+# if defined(REG_R2)
+freeReg REG_R2    = False
+# endif
+# if defined(REG_R3)
+freeReg REG_R3    = False
+# endif
+# if defined(REG_R4)
+freeReg REG_R4    = False
+# endif
+# if defined(REG_R5)
+freeReg REG_R5    = False
+# endif
+# if defined(REG_R6)
+freeReg REG_R6    = False
+# endif
+# if defined(REG_R7)
+freeReg REG_R7    = False
+# endif
+# if defined(REG_R8)
+freeReg REG_R8    = False
+# endif
+
+# if defined(REG_F1)
+freeReg REG_F1    = False
+# endif
+# if defined(REG_F2)
+freeReg REG_F2    = False
+# endif
+# if defined(REG_F3)
+freeReg REG_F3    = False
+# endif
+# if defined(REG_F4)
+freeReg REG_F4    = False
+# endif
+# if defined(REG_F5)
+freeReg REG_F5    = False
+# endif
+# if defined(REG_F6)
+freeReg REG_F6    = False
+# endif
+
+# if defined(REG_D1)
+freeReg REG_D1    = False
+# endif
+# if defined(REG_D2)
+freeReg REG_D2    = False
+# endif
+# if defined(REG_D3)
+freeReg REG_D3    = False
+# endif
+# if defined(REG_D4)
+freeReg REG_D4    = False
+# endif
+# if defined(REG_D5)
+freeReg REG_D5    = False
+# endif
+# if defined(REG_D6)
+freeReg REG_D6    = False
+# endif
+
+freeReg _ = True
+
 #elif defined(MACHREGS_sparc)
 
 -- SPARC regs used by the OS / ABI
diff --git a/includes/rts/storage/GC.h b/includes/rts/storage/GC.h
index 12f0e32f0f..0258811728 100644
--- a/includes/rts/storage/GC.h
+++ b/includes/rts/storage/GC.h
@@ -208,7 +208,6 @@ void flushExec(W_ len, AdjustorExecutable exec_addr);
 #if defined(darwin_HOST_OS)
 AdjustorWritable execToWritable(AdjustorExecutable exec);
 #endif
-
 #if RTS_LINKER_USE_MMAP
 AdjustorWritable allocateWrite(W_ bytes);
 void markExec(W_ bytes, AdjustorWritable writ);
diff --git a/includes/stg/MachRegs.h b/includes/stg/MachRegs.h
index 4b0991891e..d50969b66a 100644
--- a/includes/stg/MachRegs.h
+++ b/includes/stg/MachRegs.h
@@ -548,7 +548,7 @@ the stack. See Note [Overlapping global registers] for implications.
      r30    |  LR     | The Link Register
      r29    |  FP     | The Frame Pointer
    r19-r28  |         | Callee-saved registers
-     r18    |         | The Platform Register, if needed; 
+     r18    |         | The Platform Register, if needed;
             |         | or temporary register
      r17    |  IP1    | The second intra-procedure-call temporary register
      r16    |  IP0    | The first intra-procedure-call scratch register