--- old/src/os/linux/vm/os_linux.cpp	Wed Aug  3 14:50:05 2011
+++ new/src/os/linux/vm/os_linux.cpp	Wed Aug  3 14:50:05 2011
@@ -125,6 +125,10 @@
 # include <inttypes.h>
 # include <sys/ioctl.h>
 
+#ifdef AMD64
+#include <asm/vsyscall.h>
+#endif
+
 #define MAX_PATH    (2 * K)
 
 // for timer info max values which include all bits
@@ -2578,6 +2582,22 @@
   return end;
 }
 
+
+int os::Linux::sched_getcpu_syscall(void) {
+  unsigned int cpu;
+  int retval = -1;
+
+#if defined(IA32)
+  retval = syscall(SYS_getcpu, &cpu, NULL, NULL);
+#elif defined(AMD64)
+  typedef long (*vgetcpu_t)(unsigned int *cpu, unsigned int *node, unsigned long *tcache);
+  vgetcpu_t vgetcpu = (vgetcpu_t)VSYSCALL_ADDR(__NR_vgetcpu);
+  retval = vgetcpu(&cpu, NULL, NULL);
+#endif
+
+  return (retval == -1) ? retval : cpu;
+}
+
 // Something to do with the numa-aware allocator needs these symbols
 extern "C" JNIEXPORT void numa_warn(int number, char *where, ...) { }
 extern "C" JNIEXPORT void numa_error(char *where) { }
@@ -2601,6 +2621,10 @@
   set_sched_getcpu(CAST_TO_FN_PTR(sched_getcpu_func_t,
                                   dlsym(RTLD_DEFAULT, "sched_getcpu")));
 
+  // If it's not, try a direct syscall.
+  if (sched_getcpu() == -1)
+    set_sched_getcpu(CAST_TO_FN_PTR(sched_getcpu_func_t, (void*)&sched_getcpu_syscall));
+
   if (sched_getcpu() != -1) { // Does it work?
     void *handle = dlopen("libnuma.so.1", RTLD_LAZY);
     if (handle != NULL) {
--- old/src/os/linux/vm/os_linux.hpp	Wed Aug  3 14:50:07 2011
+++ new/src/os/linux/vm/os_linux.hpp	Wed Aug  3 14:50:07 2011
@@ -263,6 +263,7 @@
   static void set_numa_tonode_memory(numa_tonode_memory_func_t func) { _numa_tonode_memory = func; }
   static void set_numa_interleave_memory(numa_interleave_memory_func_t func) { _numa_interleave_memory = func; }
   static void set_numa_all_nodes(unsigned long* ptr) { _numa_all_nodes = ptr; }
+  static int sched_getcpu_syscall(void);
 public:
   static int sched_getcpu()  { return _sched_getcpu != NULL ? _sched_getcpu() : -1; }
   static int numa_node_to_cpus(int node, unsigned long *buffer, int bufferlen) {