diff --git a/arch/um/include/os.h b/arch/um/include/os.h
index 8f602667296d7b4eca716f2bdfd4337140d1f9b2..8629bd1914925aba5d78f4348221c796fc323920 100644
--- a/arch/um/include/os.h
+++ b/arch/um/include/os.h
@@ -340,4 +340,6 @@ extern void maybe_sigio_broken(int fd, int read);
 extern void sig_handler_common_skas(int sig, void *sc_ptr);
 extern void user_signal(int sig, union uml_pt_regs *regs, int pid);
 
+extern int os_arch_prctl(int pid, int code, unsigned long *addr);
+
 #endif
diff --git a/arch/um/os-Linux/sys-x86_64/Makefile b/arch/um/os-Linux/sys-x86_64/Makefile
index f67842a7735b80b09b6a7f1fbb13a1f98861a630..7955e061a678aaf3d7f29143b3a6ed65257ad391 100644
--- a/arch/um/os-Linux/sys-x86_64/Makefile
+++ b/arch/um/os-Linux/sys-x86_64/Makefile
@@ -3,7 +3,7 @@
 # Licensed under the GPL
 #
 
-obj-$(CONFIG_MODE_SKAS) = registers.o signal.o
+obj-$(CONFIG_MODE_SKAS) = registers.o prctl.o signal.o
 
 USER_OBJS := $(obj-y)
 
diff --git a/arch/um/os-Linux/sys-x86_64/prctl.c b/arch/um/os-Linux/sys-x86_64/prctl.c
new file mode 100644
index 0000000000000000000000000000000000000000..9d34eddb517fdca9f3495588d4d1d32e62ceecc1
--- /dev/null
+++ b/arch/um/os-Linux/sys-x86_64/prctl.c
@@ -0,0 +1,12 @@
+/*
+ * Copyright (C) 2007 Jeff Dike (jdike@{addtoit.com,linux.intel.com})
+ * Licensed under the GPL
+ */
+
+#include <sys/ptrace.h>
+#include <linux/ptrace.h>
+
+int os_arch_prctl(int pid, int code, unsigned long *addr)
+{
+        return ptrace(PTRACE_ARCH_PRCTL, pid, (unsigned long) addr, code);
+}
diff --git a/arch/um/sys-x86_64/syscalls.c b/arch/um/sys-x86_64/syscalls.c
index 73ce4463f70c6f96b2cd94f000b69df5a0da95ff..f309fa9bc23225ce43d4ce2bcb69dc3d48f75da9 100644
--- a/arch/um/sys-x86_64/syscalls.c
+++ b/arch/um/sys-x86_64/syscalls.c
@@ -16,6 +16,7 @@
 #include "asm/prctl.h" /* XXX This should get the constants from libc */
 #include "choose-mode.h"
 #include "kern.h"
+#include "os.h"
 
 asmlinkage long sys_uname64(struct new_utsname __user * name)
 {
@@ -58,40 +59,67 @@ static long arch_prctl_tt(int code, unsigned long addr)
 
 #ifdef CONFIG_MODE_SKAS
 
-/* XXX: Must also call arch_prctl in the host, beside saving the segment bases! */
-static long arch_prctl_skas(int code, unsigned long addr)
+static long arch_prctl_skas(int code, unsigned long __user *addr)
 {
-	long ret = 0;
+        unsigned long *ptr = addr, tmp;
+	long ret;
+        int pid = current->mm->context.skas.id.u.pid;
 
+	/*
+	 * With ARCH_SET_FS (and ARCH_SET_GS is treated similarly to
+	 * be safe), we need to call arch_prctl on the host because
+	 * setting %fs may result in something else happening (like a
+	 * GDT being set instead).  So, we let the host fiddle the
+	 * registers and restore them afterwards.
+	 *
+	 * So, the saved registers are stored to the process (this
+	 * needed because a stub may have been the last thing to run),
+	 * arch_prctl is run on the host, then the registers are read
+	 * back.
+	 */
 	switch(code){
 	case ARCH_SET_FS:
-		current->thread.regs.regs.skas.regs[FS_BASE / sizeof(unsigned long)] = addr;
-		break;
 	case ARCH_SET_GS:
-		current->thread.regs.regs.skas.regs[GS_BASE / sizeof(unsigned long)] = addr;
+                restore_registers(pid, &current->thread.regs.regs);
+                break;
+        case ARCH_GET_FS:
+        case ARCH_GET_GS:
+                /*
+                 * With these two, we read to a local pointer and
+                 * put_user it to the userspace pointer that we were
+                 * given.  If addr isn't valid (because it hasn't been
+                 * faulted in or is just bogus), we want put_user to
+                 * fault it in (or return -EFAULT) instead of having
+                 * the host return -EFAULT.
+                 */
+                ptr = &tmp;
+        }
+
+        ret = os_arch_prctl(pid, code, ptr);
+        if(ret)
+                return ret;
+
+        switch(code){
+	case ARCH_SET_FS:
+	case ARCH_SET_GS:
+                save_registers(pid, &current->thread.regs.regs);
 		break;
 	case ARCH_GET_FS:
-		ret = put_user(current->thread.regs.regs.skas.
-				regs[FS_BASE / sizeof(unsigned long)],
-				(unsigned long __user *)addr);
+		ret = put_user(tmp, addr);
 	        break;
 	case ARCH_GET_GS:
-		ret = put_user(current->thread.regs.regs.skas.
-				regs[GS_BASE / sizeof(unsigned long)],
-				(unsigned long __user *)addr);
+		ret = put_user(tmp, addr);
 	        break;
-	default:
-		ret = -EINVAL;
-		break;
 	}
 
-	return(ret);
+	return ret;
 }
 #endif
 
 long sys_arch_prctl(int code, unsigned long addr)
 {
-	return(CHOOSE_MODE_PROC(arch_prctl_tt, arch_prctl_skas, code, addr));
+	return CHOOSE_MODE_PROC(arch_prctl_tt, arch_prctl_skas, code,
+                                (unsigned long __user *) addr);
 }
 
 long sys_clone(unsigned long clone_flags, unsigned long newsp,
@@ -105,5 +133,14 @@ long sys_clone(unsigned long clone_flags, unsigned long newsp,
 	ret = do_fork(clone_flags, newsp, &current->thread.regs, 0, parent_tid,
 		      child_tid);
 	current->thread.forking = 0;
-	return(ret);
+	return ret;
+}
+
+void arch_switch_to_skas(struct task_struct *from, struct task_struct *to)
+{
+        if(to->thread.arch.fs == 0)
+                return;
+
+        arch_prctl_skas(ARCH_SET_FS, (void __user *) to->thread.arch.fs);
 }
+
diff --git a/arch/um/sys-x86_64/tls.c b/arch/um/sys-x86_64/tls.c
index ce1bf1b81c431dcb859db4f25410a2758c226f19..febbc94be25fd423c890ac8f11d1859ca919217a 100644
--- a/arch/um/sys-x86_64/tls.c
+++ b/arch/um/sys-x86_64/tls.c
@@ -1,14 +1,17 @@
 #include "linux/sched.h"
 
-void debug_arch_force_load_TLS(void)
-{
-}
-
 void clear_flushed_tls(struct task_struct *task)
 {
 }
 
 int arch_copy_tls(struct task_struct *t)
 {
+	/*
+	 * If CLONE_SETTLS is set, we need to save the thread id
+	 * (which is argument 5, child_tid, of clone) so it can be set
+	 * during context switches.
+	 */
+	t->thread.arch.fs = t->thread.regs.regs.skas.regs[R8 / sizeof(long)];
+
         return 0;
 }
diff --git a/include/asm-um/processor-x86_64.h b/include/asm-um/processor-x86_64.h
index 10609af376c0339af5f22bafe48c918a2103a34f..31c2d4d685bd7692677db195bb4738642dea8459 100644
--- a/include/asm-um/processor-x86_64.h
+++ b/include/asm-um/processor-x86_64.h
@@ -13,6 +13,7 @@
 struct arch_thread {
         unsigned long debugregs[8];
         int debugregs_seq;
+        unsigned long fs;
         struct faultinfo faultinfo;
 };
 
@@ -25,8 +26,9 @@ extern inline void rep_nop(void)
 #define cpu_relax()   rep_nop()
 
 #define INIT_ARCH_THREAD { .debugregs  		= { [ 0 ... 7 ] = 0 }, \
-                           .debugregs_seq	= 0, \
-                           .faultinfo		= { 0, 0, 0 } }
+                           .debugregs_seq	= 0,			       \
+			   .fs			= 0, \
+			   .faultinfo		= { 0, 0, 0 } }
 
 static inline void arch_flush_thread(struct arch_thread *thread)
 {
diff --git a/include/asm-um/ptrace-x86_64.h b/include/asm-um/ptrace-x86_64.h
index 03b4af4ac09a3c82509e93dc835ee84bb7f7d111..a927450ce4011c460b115b57357801fbb9f6201f 100644
--- a/include/asm-um/ptrace-x86_64.h
+++ b/include/asm-um/ptrace-x86_64.h
@@ -81,9 +81,7 @@ static inline void arch_switch_to_tt(struct task_struct *from,
 {
 }
 
-static inline void arch_switch_to_skas(struct task_struct *from,
-                                       struct task_struct *to)
-{
-}
+extern void arch_switch_to_skas(struct task_struct *from,
+				struct task_struct *to);
 
 #endif