[PATCH 2/4] Fix internal_clone for x32

[H.J. Lu]

We need to allcate 2 64-bit integers to restore fn and arg with pop,
which only pop 64-bit integer into 64-bit register.  Also pointers
are 32-bit for x32.  This patch properly loads r8/r10 fpr syscall.
Please install it.

Thanks.

H.J.
---
 libsanitizer/ChangeLog.x32                       |  6 ++++++
 libsanitizer/sanitizer_common/sanitizer_linux.cc | 16 ++++++++--------
 2 files changed, 14 insertions(+), 8 deletions(-)

diff --git a/libsanitizer/ChangeLog.x32 b/libsanitizer/ChangeLog.x32
index 7b54005..40b185d 100644
--- a/libsanitizer/ChangeLog.x32
+++ b/libsanitizer/ChangeLog.x32
@@ -1,5 +1,11 @@
 2013-11-05  H.J. Lu  <hongjiu...@intel.com>
 
+       * sanitizer_common/sanitizer_linux.cc (internal_clone): Allocate
+       2 64-bit integers to save and restore fn and arg.  Properly load
+       newtls/child_tidptr into r8/r10.
+
+2013-11-05  H.J. Lu  <hongjiu...@intel.com>
+
        * sanitizer_common/sanitizer_linux.cc (internal_mmap): Cast
        pointers to uptr for 64-bit syscalls.
        (internal_munmap): Likewise.
diff --git a/libsanitizer/sanitizer_common/sanitizer_linux.cc 
b/libsanitizer/sanitizer_common/sanitizer_linux.cc
index e48bee5..bb43437 100644
--- a/libsanitizer/sanitizer_common/sanitizer_linux.cc
+++ b/libsanitizer/sanitizer_common/sanitizer_linux.cc
@@ -772,9 +772,11 @@ uptr internal_clone(int (*fn)(void *), void *child_stack, 
int flags, void *arg,
   if (!fn || !child_stack)
     return -EINVAL;
   CHECK_EQ(0, (uptr)child_stack % 16);
-  child_stack = (char *)child_stack - 2 * sizeof(void *);
-  ((void **)child_stack)[0] = (void *)(uptr)fn;
-  ((void **)child_stack)[1] = arg;
+  child_stack = (char *)child_stack - 2 * sizeof(unsigned long long);
+  ((unsigned long long *)child_stack)[0] = (uptr)fn;
+  ((unsigned long long *)child_stack)[1] = (uptr)arg;
+  void *r8 __asm__ ("r8") = newtls;
+  int *r10 __asm__ ("r10") = child_tidptr;
   __asm__ __volatile__(
                        /* %rax = syscall(%rax = __NR_clone,
                         *                %rdi = flags,
@@ -783,8 +785,6 @@ uptr internal_clone(int (*fn)(void *), void *child_stack, 
int flags, void *arg,
                         *                %r8  = new_tls,
                         *                %r10 = child_tidptr)
                         */
-                       "movq   %6,%%r8\n"
-                       "movq   %7,%%r10\n"
                        ".cfi_endproc\n"
                        "syscall\n"
 
@@ -816,9 +816,9 @@ uptr internal_clone(int (*fn)(void *), void *child_stack, 
int flags, void *arg,
                          "S"(child_stack),
                          "D"(flags),
                          "d"(parent_tidptr),
-                         "r"(newtls),
-                         "r"(child_tidptr)
-                       : "rsp", "memory", "r8", "r10", "r11", "rcx");
+                         "r"(r8),
+                         "r"(r10)
+                       : "rsp", "memory", "r11", "rcx");
   return res;
 }
 #endif  // defined(__x86_64__)
-- 
1.8.3.1