Add a RTS option -xp to load PIC object anywhere in address space

Add a RTS option -xp to load PIC object anywhere in address space. We do
this by relaxing the requirement of <0x80000000 result of
`mmapForLinker` and implying USE_CONTIGUOUS_MMAP.

We also need to change calls to `ocInit` and `ocGetNames` to avoid
dangling pointers when the address of `oc->image` is changed by
`ocAllocateSymbolExtra`.

Test Plan:
```
$ uname -a
Linux localhost 4.18.8-arch1-1-ARCH #1 SMP PREEMPT Sat Sep 15 20:34:48
UTC 2018 x86_64 GNU/Linux
$ cat mk/build.mk
DYNAMIC_GHC_PROGRAMS = NO
DYNAMIC_BY_DEFAULT = NO

GhcRTSWays += thr_debug
EXTRA_HC_OPTS += -debug
WAY_p_HC_OPTS += -fPIC -fexternal-dynamic-refs
$ inplace/bin/ghc-stage2 --interactive -prof +RTS -xp
GHCi, version 8.7.20180928: http://www.haskell.org/ghc/  :? for help
ghc-stage2: R_X86_64_32 relocation out of range:
ghczmprim_GHCziTypes_ZMZN_closure = 7f690bffab59
Recompile
/data/users/watashi/ghc/libraries/ghc-prim/dist-install/build/HSghc-prim
-0.5.3.o with -fPIC -fexternal-dynamic-refs.
ghc-stage2: unable to load package `ghc-prim-0.5.3'
$ strace -f -e open,mmap inplace/bin/ghc-stage2 --interactive -prof
-fexternal-interpreter  -opti+RTS -opti-xp
...
[pid 1355283]
open("/data/users/watashi/ghc/libraries/base/dist-install/build/libHSbas
e-4.12.0.0_p.a", O_RDONLY) = 14
[pid 1355283] mmap(NULL, 8192, PROT_READ|PROT_WRITE|PROT_EXEC,
MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7f6a84842000
[pid 1355283]
open("/data/users/watashi/ghc/libraries/base/dist-install/build/libHSbas
e-4.12.0.0_p.a", O_RDONLY) = 14
[pid 1355283] mmap(NULL, 8192, PROT_READ|PROT_WRITE|PROT_EXEC,
MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7f6a84676000
...
Prelude> System.Posix.Process.getProcessID
...
[pid 1355283]
open("/data/users/watashi/ghc/libraries/unix/dist-install/build/libHSuni
x-2.7.2.2_p.a", O_RDONLY) = 14
[pid 1355283] mmap(NULL, 45056, PROT_READ|PROT_WRITE|PROT_EXEC,
MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7f6a67d60000
[pid 1355283]
open("/data/users/watashi/ghc/libraries/unix/dist-install/build/libHSuni
x-2.7.2.2_p.a", O_RDONLY) = 14
[pid 1355283] mmap(NULL, 57344, PROT_READ|PROT_WRITE|PROT_EXEC,
MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7f6a67d52000
...
```

```
$ uname -a
Darwin watashis-iMac.local 18.0.0 Darwin Kernel Version 18.0.0: Wed Aug
22 20:13:40 PDT 2018; root:xnu-4903.201.2~1/RELEASE_X86_64 x86_64
$ mv
/Users/watashi/gao/ghc/libraries/integer-gmp/dist-install/build/HSintege
r-gmp-1.0.2.0.o{,._DISABLE_GHC_ISSUE_15105}
$ inplace/bin/ghc-stage2 --interactive  +RTS -xp
GHCi, version 8.7.20181003: http://www.haskell.org/ghc/  :? for help
Prelude> System.Posix.Process.getProcessID
42791
Prelude> Data.Set.fromList [1 .. 10]
fromList [1,2,3,4,5,6,7,8,9,10]
Prelude>
Leaving GHCi.
$ inplace/bin/ghc-stage2 --interactive -prof -fexternal-interpreter
GHCi, version 8.7.20181003: http://www.haskell.org/ghc/  :? for help
Prelude> System.Posix.Process.getProcessID
42806
Prelude> Data.Set.fromList [1 .. 10]
fromList [1,2,3,4,5,6,7,8,9,10]
Prelude>
Leaving GHCi.
```

Also test with something that used to hit the 2Gb limit and it loads
and runs without problem.

Reviewers: simonmar, bgamari, angerman, Phyx, hvr, erikd

Reviewed By: simonmar

Subscribers: rwbarton, carter

Differential Revision: https://phabricator.haskell.org/D5195

1 files changed, 39 insertions, 22 deletions

diff --git a/rts/linker/SymbolExtras.c b/rts/linker/SymbolExtras.c
index 88541f44d0..4c40b10877 100644
--- a/rts/linker/SymbolExtras.c
+++ b/rts/linker/SymbolExtras.c
@@ -19,6 +19,12 @@
 #include "linker/SymbolExtras.h"
 #include "linker/M32Alloc.h"
 
+#if defined(OBJFORMAT_ELF)
+#  include "linker/Elf.h"
+#elif defined(OBJFORMAT_MACHO)
+#  include "linker/MachO.h"
+#endif
+
 #include <string.h>
 #if RTS_LINKER_USE_MMAP
 #include <sys/mman.h>
@@ -46,8 +52,24 @@
 int ocAllocateSymbolExtras( ObjectCode* oc, int count, int first )
 {
   size_t n;
+  void* oldImage = oc->image;
+
+  if (count > 0) {
+    if (!RTS_LINKER_USE_MMAP) {
+
+      // round up to the nearest 4
+      int aligned = (oc->fileSize + 3) & ~3;
+      int misalignment = oc->misalignment;
 
-  if (RTS_LINKER_USE_MMAP && USE_CONTIGUOUS_MMAP) {
+      oc->image -= misalignment;
+      oc->image = stgReallocBytes( oc->image,
+                               misalignment +
+                               aligned + sizeof (SymbolExtra) * count,
+                               "ocAllocateSymbolExtras" );
+      oc->image += misalignment;
+
+      oc->symbol_extras = (SymbolExtra *) (oc->image + aligned);
+    } else if (USE_CONTIGUOUS_MMAP || RtsFlags.MiscFlags.linkerAlwaysPic) {
       n = roundUpToPage(oc->fileSize);
 
       /* Keep image and symbol_extras contiguous */
@@ -63,42 +85,37 @@ int ocAllocateSymbolExtras( ObjectCode* oc, int count, int first )
           oc->imageMapped = true;
           oc->fileSize = n + (sizeof(SymbolExtra) * count);
           oc->symbol_extras = (SymbolExtra *) (oc->image + n);
-          if(mprotect(new, allocated_size, PROT_READ | PROT_EXEC) != 0) {
-              sysErrorBelch("unable to protect memory");
+          if (mprotect(new, allocated_size,
+                       PROT_READ | PROT_WRITE | PROT_EXEC) != 0) {
+            sysErrorBelch("unable to protect memory");
           }
       }
       else {
           oc->symbol_extras = NULL;
           return 0;
       }
-  }
-  else if( count > 0 ) {
-    if (RTS_LINKER_USE_MMAP) {
-        n = roundUpToPage(oc->fileSize);
-
+    } else {
         oc->symbol_extras = m32_alloc(sizeof(SymbolExtra) * count, 8);
         if (oc->symbol_extras == NULL) return 0;
     }
-    else {
-        // round up to the nearest 4
-        int aligned = (oc->fileSize + 3) & ~3;
-        int misalignment = oc->misalignment;
-
-        oc->image -= misalignment;
-        oc->image = stgReallocBytes( oc->image,
-                                 misalignment +
-                                 aligned + sizeof (SymbolExtra) * count,
-                                 "ocAllocateSymbolExtras" );
-        oc->image += misalignment;
-
-        oc->symbol_extras = (SymbolExtra *) (oc->image + aligned);
-    }
   }
 
   if (oc->symbol_extras != NULL) {
       memset( oc->symbol_extras, 0, sizeof (SymbolExtra) * count );
   }
 
+  // ObjectCodeFormatInfo contains computed addresses based on offset to
+  // image, if the address of image changes, we need to invalidate
+  // the ObjectCodeFormatInfo and recompute it.
+  if (oc->image != oldImage) {
+#if defined(OBJFORMAT_MACHO)
+    ocInit_MachO( oc );
+#endif
+#if defined(OBJFORMAT_ELF)
+    ocInit_ELF( oc );
+#endif
+  }
+
   oc->first_symbol_extra = first;
   oc->n_symbol_extras = count;