Merge tag 'uml-for-linus-6.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/uml/linux

Pull UML updates from Richard Weinberger:

 - Clang coverage support

 - Many cleanups from Benjamin Berg

 - Various minor fixes

* tag 'uml-for-linus-6.8-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/uml/linux:
  um: Mark 32bit syscall helpers as clobbering memory
  um: Remove unused register save/restore functions
  um: Rely on PTRACE_SETREGSET to set FS/GS base registers
  Documentation: kunit: Add clang UML coverage example
  arch: um: Add Clang coverage support
  um: time-travel: fix time corruption
  um: net: Fix return type of uml_net_start_xmit()
  um: Always inline stub functions
  um: Do not use printk in userspace trampoline
  um: Reap winch thread if it fails
  um: Do not use printk in SIGWINCH helper thread
  um: Don't use vfprintf() for os_info()
  um: Make errors to stop ptraced child fatal during startup
  um: Drop NULL check from start_userspace
  um: Drop support for hosts without SYSEMU_SINGLESTEP support
  um: document arch_futex_atomic_op_inuser
  um: mmu: remove stub_pages
  um: Fix naming clash between UML and scheduler
  um: virt-pci: fix platform map offset

33 files changed, 201 insertions, 459 deletions

diff --git a/arch/um/Makefile-skas b/arch/um/Makefile-skas
index ac35de5316a6..67323b028999 100644
--- a/arch/um/Makefile-skas
+++ b/arch/um/Makefile-skas
@@ -4,7 +4,12 @@
 #
 
 GPROF_OPT += -pg
+
+ifdef CONFIG_CC_IS_CLANG
+GCOV_OPT += -fprofile-instr-generate -fcoverage-mapping
+else
 GCOV_OPT += -fprofile-arcs -ftest-coverage
+endif
 
 CFLAGS-$(CONFIG_GCOV) += $(GCOV_OPT)
 CFLAGS-$(CONFIG_GPROF) += $(GPROF_OPT)
diff --git a/arch/um/drivers/chan_user.c b/arch/um/drivers/chan_user.c
index 25727ed648b7..ed7cc830b3e7 100644
--- a/arch/um/drivers/chan_user.c
+++ b/arch/um/drivers/chan_user.c
@@ -141,7 +141,7 @@ struct winch_data {
 	int pipe_fd;
 };
 
-static int winch_thread(void *arg)
+static __noreturn int winch_thread(void *arg)
 {
 	struct winch_data *data = arg;
 	sigset_t sigs;
@@ -153,8 +153,8 @@ static int winch_thread(void *arg)
 	pipe_fd = data->pipe_fd;
 	count = write(pipe_fd, &c, sizeof(c));
 	if (count != sizeof(c))
-		printk(UM_KERN_ERR "winch_thread : failed to write "
-		       "synchronization byte, err = %d\n", -count);
+		os_info("winch_thread : failed to write synchronization byte, err = %d\n",
+			-count);
 
 	/*
 	 * We are not using SIG_IGN on purpose, so don't fix it as I thought to
@@ -166,29 +166,29 @@ static int winch_thread(void *arg)
 	sigfillset(&sigs);
 	/* Block all signals possible. */
 	if (sigprocmask(SIG_SETMASK, &sigs, NULL) < 0) {
-		printk(UM_KERN_ERR "winch_thread : sigprocmask failed, "
-		       "errno = %d\n", errno);
-		exit(1);
+		os_info("winch_thread : sigprocmask failed, errno = %d\n",
+			errno);
+		goto wait_kill;
 	}
 	/* In sigsuspend(), block anything else than SIGWINCH. */
 	sigdelset(&sigs, SIGWINCH);
 
 	if (setsid() < 0) {
-		printk(UM_KERN_ERR "winch_thread : setsid failed, errno = %d\n",
+		os_info("winch_thread : setsid failed, errno = %d\n",
 		       errno);
-		exit(1);
+		goto wait_kill;
 	}
 
 	if (ioctl(pty_fd, TIOCSCTTY, 0) < 0) {
-		printk(UM_KERN_ERR "winch_thread : TIOCSCTTY failed on "
-		       "fd %d err = %d\n", pty_fd, errno);
-		exit(1);
+		os_info("winch_thread : TIOCSCTTY failed on "
+			"fd %d err = %d\n", pty_fd, errno);
+		goto wait_kill;
 	}
 
 	if (tcsetpgrp(pty_fd, os_getpid()) < 0) {
-		printk(UM_KERN_ERR "winch_thread : tcsetpgrp failed on "
-		       "fd %d err = %d\n", pty_fd, errno);
-		exit(1);
+		os_info("winch_thread : tcsetpgrp failed on fd %d err = %d\n",
+			pty_fd, errno);
+		goto wait_kill;
 	}
 
 	/*
@@ -199,8 +199,8 @@ static int winch_thread(void *arg)
 	 */
 	count = read(pipe_fd, &c, sizeof(c));
 	if (count != sizeof(c))
-		printk(UM_KERN_ERR "winch_thread : failed to read "
-		       "synchronization byte, err = %d\n", errno);
+		os_info("winch_thread : failed to read synchronization byte, err = %d\n",
+			errno);
 
 	while(1) {
 		/*
@@ -211,9 +211,15 @@ static int winch_thread(void *arg)
 
 		count = write(pipe_fd, &c, sizeof(c));
 		if (count != sizeof(c))
-			printk(UM_KERN_ERR "winch_thread : write failed, "
-			       "err = %d\n", errno);
+			os_info("winch_thread : write failed, err = %d\n",
+				errno);
 	}
+
+wait_kill:
+	c = 2;
+	count = write(pipe_fd, &c, sizeof(c));
+	while (1)
+		pause();
 }
 
 static int winch_tramp(int fd, struct tty_port *port, int *fd_out,
diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c
index b98545f3edb5..449d320c3f55 100644
--- a/arch/um/drivers/line.c
+++ b/arch/um/drivers/line.c
@@ -629,15 +629,18 @@ static irqreturn_t winch_interrupt(int irq, void *data)
 
 	if (fd != -1) {
 		err = generic_read(fd, &c, NULL);
-		if (err < 0) {
+		/* A read of 2 means the winch thread failed and has warned */
+		if (err < 0 || (err == 1 && c == 2)) {
 			if (err != -EAGAIN) {
 				winch->fd = -1;
 				list_del(&winch->list);
 				os_close_file(fd);
-				printk(KERN_ERR "winch_interrupt : "
-				       "read failed, errno = %d\n", -err);
-				printk(KERN_ERR "fd %d is losing SIGWINCH "
-				       "support\n", winch->tty_fd);
+				if (err < 0) {
+					printk(KERN_ERR "winch_interrupt : read failed, errno = %d\n",
+					       -err);
+					printk(KERN_ERR "fd %d is losing SIGWINCH support\n",
+					       winch->tty_fd);
+				}
 				INIT_WORK(&winch->work, __free_winch);
 				schedule_work(&winch->work);
 				return IRQ_HANDLED;
diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c
index 3d7836c46507..cabcc501b448 100644
--- a/arch/um/drivers/net_kern.c
+++ b/arch/um/drivers/net_kern.c
@@ -204,7 +204,7 @@ static int uml_net_close(struct net_device *dev)
 	return 0;
 }
 
-static int uml_net_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t uml_net_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct uml_net_private *lp = netdev_priv(dev);
 	unsigned long flags;
diff --git a/arch/um/drivers/virt-pci.c b/arch/um/drivers/virt-pci.c
index ffe2ee8a0246..97a37c062997 100644
--- a/arch/um/drivers/virt-pci.c
+++ b/arch/um/drivers/virt-pci.c
@@ -971,7 +971,7 @@ static long um_pci_map_platform(unsigned long offset, size_t size,
 	*ops = &um_pci_device_bar_ops;
 	*priv = &um_pci_platform_device->resptr[0];
 
-	return 0;
+	return offset;
 }
 
 static const struct logic_iomem_region_ops um_pci_platform_ops = {
diff --git a/arch/um/include/asm/mmu.h b/arch/um/include/asm/mmu.h
index 5b072aba5b65..a7555e43ed14 100644
--- a/arch/um/include/asm/mmu.h
+++ b/arch/um/include/asm/mmu.h
@@ -12,7 +12,6 @@
 typedef struct mm_context {
 	struct mm_id id;
 	struct uml_arch_mm_context arch;
-	struct page *stub_pages[2];
 } mm_context_t;
 
 extern void __switch_mm(struct mm_id * mm_idp);
diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h
index 7414154b8e9a..6c3779541845 100644
--- a/arch/um/include/asm/processor-generic.h
+++ b/arch/um/include/asm/processor-generic.h
@@ -22,7 +22,6 @@ struct mm_struct;
 struct thread_struct {
 	struct pt_regs regs;
 	struct pt_regs *segv_regs;
-	int singlestep_syscall;
 	void *fault_addr;
 	jmp_buf *fault_catcher;
 	struct task_struct *prev_sched;
diff --git a/arch/um/include/shared/kern_util.h b/arch/um/include/shared/kern_util.h
index d8b8b4f07e42..789b83013f35 100644
--- a/arch/um/include/shared/kern_util.h
+++ b/arch/um/include/shared/kern_util.h
@@ -34,7 +34,6 @@ extern int handle_page_fault(unsigned long address, unsigned long ip,
 
 extern unsigned int do_IRQ(int irq, struct uml_pt_regs *regs);
 extern void initial_thread_cb(void (*proc)(void *), void *arg);
-extern int is_syscall(unsigned long addr);
 
 extern void timer_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs);
 
@@ -50,7 +49,7 @@ extern void do_uml_exitcalls(void);
  * Are we disallowed to sleep? Used to choose between GFP_KERNEL and
  * GFP_ATOMIC.
  */
-extern int __cant_sleep(void);
+extern int __uml_cant_sleep(void);
 extern int get_current_pid(void);
 extern int copy_from_user_proc(void *to, void *from, int size);
 extern char *uml_strdup(const char *string);
@@ -58,7 +57,7 @@ extern char *uml_strdup(const char *string);
 extern unsigned long to_irq_stack(unsigned long *mask_out);
 extern unsigned long from_irq_stack(int nested);
 
-extern int singlestepping(void *t);
+extern int singlestepping(void);
 
 extern void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs);
 extern void bus_handler(int sig, struct siginfo *si, struct uml_pt_regs *regs);
diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h
index 0df646c6651e..aff8906304ea 100644
--- a/arch/um/include/shared/os.h
+++ b/arch/um/include/shared/os.h
@@ -323,9 +323,6 @@ extern void sigio_broken(int fd);
 extern int __add_sigio_fd(int fd);
 extern int __ignore_sigio_fd(int fd);
 
-/* prctl.c */
-extern int os_arch_prctl(int pid, int option, unsigned long *arg2);
-
 /* tty.c */
 extern int get_pty(void);
 
diff --git a/arch/um/include/shared/ptrace_user.h b/arch/um/include/shared/ptrace_user.h
index 95455e8996e7..8a705d8f96ce 100644
--- a/arch/um/include/shared/ptrace_user.h
+++ b/arch/um/include/shared/ptrace_user.h
@@ -12,45 +12,4 @@
 extern int ptrace_getregs(long pid, unsigned long *regs_out);
 extern int ptrace_setregs(long pid, unsigned long *regs_in);
 
-/* syscall emulation path in ptrace */
-
-#ifndef PTRACE_SYSEMU
-#define PTRACE_SYSEMU 31
-#endif
-#ifndef PTRACE_SYSEMU_SINGLESTEP
-#define PTRACE_SYSEMU_SINGLESTEP 32
-#endif
-
-/* On architectures, that started to support PTRACE_O_TRACESYSGOOD
- * in linux 2.4, there are two different definitions of
- * PTRACE_SETOPTIONS: linux 2.4 uses 21 while linux 2.6 uses 0x4200.
- * For binary compatibility, 2.6 also supports the old "21", named
- * PTRACE_OLDSETOPTION. On these architectures, UML always must use
- * "21", to ensure the kernel runs on 2.4 and 2.6 host without
- * recompilation. So, we use PTRACE_OLDSETOPTIONS in UML.
- * We also want to be able to build the kernel on 2.4, which doesn't
- * have PTRACE_OLDSETOPTIONS. So, if it is missing, we declare
- * PTRACE_OLDSETOPTIONS to be the same as PTRACE_SETOPTIONS.
- *
- * On architectures, that start to support PTRACE_O_TRACESYSGOOD on
- * linux 2.6, PTRACE_OLDSETOPTIONS never is defined, and also isn't
- * supported by the host kernel. In that case, our trick lets us use
- * the new 0x4200 with the name PTRACE_OLDSETOPTIONS.
- */
-#ifndef PTRACE_OLDSETOPTIONS
-#define PTRACE_OLDSETOPTIONS PTRACE_SETOPTIONS
-#endif
-
-void set_using_sysemu(int value);
-int get_using_sysemu(void);
-extern int sysemu_supported;
-
-#define SELECT_PTRACE_OPERATION(sysemu_mode, singlestep_mode) \
-	(((int[3][3] ) { \
-		{ PTRACE_SYSCALL, PTRACE_SYSCALL, PTRACE_SINGLESTEP }, \
-		{ PTRACE_SYSEMU, PTRACE_SYSEMU, PTRACE_SINGLESTEP }, \
-		{ PTRACE_SYSEMU, PTRACE_SYSEMU_SINGLESTEP, \
-		  PTRACE_SYSEMU_SINGLESTEP } }) \
-		[sysemu_mode][singlestep_mode])
-
 #endif
diff --git a/arch/um/include/shared/registers.h b/arch/um/include/shared/registers.h
index 2f9c3ce5b45e..a0450326521c 100644
--- a/arch/um/include/shared/registers.h
+++ b/arch/um/include/shared/registers.h
@@ -14,8 +14,6 @@ extern int save_fp_registers(int pid, unsigned long *fp_regs);
 extern int restore_fp_registers(int pid, unsigned long *fp_regs);
 extern int save_fpx_registers(int pid, unsigned long *fp_regs);
 extern int restore_fpx_registers(int pid, unsigned long *fp_regs);
-extern int save_registers(int pid, struct uml_pt_regs *regs);
-extern int restore_pid_registers(int pid, struct uml_pt_regs *regs);
 extern int init_pid_registers(int pid);
 extern void get_safe_registers(unsigned long *regs, unsigned long *fp_regs);
 extern int get_fp_registers(int pid, unsigned long *regs);
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 106b7da2f8d6..ab95648e93e1 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -220,7 +220,7 @@ void arch_cpu_idle(void)
 	um_idle_sleep();
 }
 
-int __cant_sleep(void) {
+int __uml_cant_sleep(void) {
 	return in_atomic() || irqs_disabled() || in_interrupt();
 	/* Is in_interrupt() really needed? */
 }
@@ -332,17 +332,9 @@ int __init make_proc_sysemu(void)
 
 late_initcall(make_proc_sysemu);
 
-int singlestepping(void * t)
+int singlestepping(void)
 {
-	struct task_struct *task = t ? t : current;
-
-	if (!test_thread_flag(TIF_SINGLESTEP))
-		return 0;
-
-	if (task->thread.singlestep_syscall)
-		return 1;
-
-	return 2;
+	return test_thread_flag(TIF_SINGLESTEP);
 }
 
 /*
diff --git a/arch/um/kernel/ptrace.c b/arch/um/kernel/ptrace.c
index 5154b27de580..6600a2782796 100644
--- a/arch/um/kernel/ptrace.c
+++ b/arch/um/kernel/ptrace.c
@@ -12,7 +12,6 @@
 void user_enable_single_step(struct task_struct *child)
 {
 	set_tsk_thread_flag(child, TIF_SINGLESTEP);
-	child->thread.singlestep_syscall = 0;
 
 #ifdef SUBARCH_SET_SINGLESTEPPING
 	SUBARCH_SET_SINGLESTEPPING(child, 1);
@@ -22,7 +21,6 @@ void user_enable_single_step(struct task_struct *child)
 void user_disable_single_step(struct task_struct *child)
 {
 	clear_tsk_thread_flag(child, TIF_SINGLESTEP);
-	child->thread.singlestep_syscall = 0;
 
 #ifdef SUBARCH_SET_SINGLESTEPPING
 	SUBARCH_SET_SINGLESTEPPING(child, 0);
diff --git a/arch/um/kernel/signal.c b/arch/um/kernel/signal.c
index ae4658f576ab..a56b44522766 100644
--- a/arch/um/kernel/signal.c
+++ b/arch/um/kernel/signal.c
@@ -121,18 +121,6 @@ void do_signal(struct pt_regs *regs)
 	}
 
 	/*
-	 * This closes a way to execute a system call on the host.  If
-	 * you set a breakpoint on a system call instruction and singlestep
-	 * from it, the tracing thread used to PTRACE_SINGLESTEP the process
-	 * rather than PTRACE_SYSCALL it, allowing the system call to execute
-	 * on the host.  The tracing thread will check this flag and
-	 * PTRACE_SYSCALL if necessary.
-	 */
-	if (test_thread_flag(TIF_SINGLESTEP))
-		current->thread.singlestep_syscall =
-			is_syscall(PT_REGS_IP(&current->thread.regs));
-
-	/*
 	 * if there's no signal to deliver, we just put the saved sigmask
 	 * back
 	 */
diff --git a/arch/um/kernel/skas/uaccess.c b/arch/um/kernel/skas/uaccess.c
index aaee96f07172..198269e384c4 100644
--- a/arch/um/kernel/skas/uaccess.c
+++ b/arch/um/kernel/skas/uaccess.c
@@ -236,7 +236,9 @@ EXPORT_SYMBOL(strnlen_user);
  *			  argument and comparison of the previous
  *			  futex value with another constant.
  *
- * @encoded_op:	encoded operation to execute
+ * @op:		operation to execute
+ * @oparg:	argument to operation
+ * @oval:	old value at uaddr
  * @uaddr:	pointer to user space address
  *
  * Return:
diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c
index fddd1dec27e6..3e270da6b6f6 100644
--- a/arch/um/kernel/time.c
+++ b/arch/um/kernel/time.c
@@ -432,9 +432,29 @@ static void time_travel_update_time(unsigned long long next, bool idle)
 	time_travel_del_event(&ne);
 }
 
+static void time_travel_update_time_rel(unsigned long long offs)
+{
+	unsigned long flags;
+
+	/*
+	 * Disable interrupts before calculating the new time so
+	 * that a real timer interrupt (signal) can't happen at
+	 * a bad time e.g. after we read time_travel_time but
+	 * before we've completed updating the time.
+	 */
+	local_irq_save(flags);
+	time_travel_update_time(time_travel_time + offs, false);
+	local_irq_restore(flags);
+}
+
 void time_travel_ndelay(unsigned long nsec)
 {
-	time_travel_update_time(time_travel_time + nsec, false);
+	/*
+	 * Not strictly needed to use _rel() version since this is
+	 * only used in INFCPU/EXT modes, but it doesn't hurt and
+	 * is more readable too.
+	 */
+	time_travel_update_time_rel(nsec);
 }
 EXPORT_SYMBOL(time_travel_ndelay);
 
@@ -568,7 +588,11 @@ static void time_travel_set_start(void)
 #define time_travel_time 0
 #define time_travel_ext_waiting 0
 
-static inline void time_travel_update_time(unsigned long long ns, bool retearly)
+static inline void time_travel_update_time(unsigned long long ns, bool idle)
+{
+}
+
+static inline void time_travel_update_time_rel(unsigned long long offs)
 {
 }
 
@@ -720,9 +744,7 @@ static u64 timer_read(struct clocksource *cs)
 		 */
 		if (!irqs_disabled() && !in_interrupt() && !in_softirq() &&
 		    !time_travel_ext_waiting)
-			time_travel_update_time(time_travel_time +
-						TIMER_MULTIPLIER,
-						false);
+			time_travel_update_time_rel(TIMER_MULTIPLIER);
 		return time_travel_time / TIMER_MULTIPLIER;
 	}
 
diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c
index b459745f52e2..3cb8ac63be6e 100644
--- a/arch/um/os-Linux/helper.c
+++ b/arch/um/os-Linux/helper.c
@@ -46,7 +46,7 @@ int run_helper(void (*pre_exec)(void *), void *pre_data, char **argv)
 	unsigned long stack, sp;
 	int pid, fds[2], ret, n;
 
-	stack = alloc_stack(0, __cant_sleep());
+	stack = alloc_stack(0, __uml_cant_sleep());
 	if (stack == 0)
 		return -ENOMEM;
 
@@ -70,7 +70,7 @@ int run_helper(void (*pre_exec)(void *), void *pre_data, char **argv)
 	data.pre_data = pre_data;
 	data.argv = argv;
 	data.fd = fds[1];
-	data.buf = __cant_sleep() ? uml_kmalloc(PATH_MAX, UM_GFP_ATOMIC) :
+	data.buf = __uml_cant_sleep() ? uml_kmalloc(PATH_MAX, UM_GFP_ATOMIC) :
 					uml_kmalloc(PATH_MAX, UM_GFP_KERNEL);
 	pid = clone(helper_child, (void *) sp, CLONE_VM, &data);
 	if (pid < 0) {
@@ -121,7 +121,7 @@ int run_helper_thread(int (*proc)(void *), void *arg, unsigned int flags,
 	unsigned long stack, sp;
 	int pid, status, err;
 
-	stack = alloc_stack(0, __cant_sleep());
+	stack = alloc_stack(0, __uml_cant_sleep());
 	if (stack == 0)
 		return -ENOMEM;
 
diff --git a/arch/um/os-Linux/registers.c b/arch/um/os-Linux/registers.c
index b123955be7ac..bd80b921add0 100644
--- a/arch/um/os-Linux/registers.c
+++ b/arch/um/os-Linux/registers.c
@@ -11,26 +11,6 @@
 #include <sysdep/ptrace_user.h>
 #include <registers.h>
 
-int save_registers(int pid, struct uml_pt_regs *regs)
-{
-	int err;
-
-	err = ptrace(PTRACE_GETREGS, pid, 0, regs->gp);
-	if (err < 0)
-		return -errno;
-	return 0;
-}
-
-int restore_pid_registers(int pid, struct uml_pt_regs *regs)
-{
-	int err;
-
-	err = ptrace(PTRACE_SETREGS, pid, 0, regs->gp);
-	if (err < 0)
-		return -errno;
-	return 0;
-}
-
 /* This is set once at boot time and not changed thereafter */
 
 static unsigned long exec_regs[MAX_REG_NR];
diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
index 9464833e741a..1f5c3f2523d1 100644
--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -177,48 +177,11 @@ static void handle_segv(int pid, struct uml_pt_regs *regs, unsigned long *aux_fp
 	segv(regs->faultinfo, 0, 1, NULL);
 }
 
-/*
- * To use the same value of using_sysemu as the caller, ask it that value
- * (in local_using_sysemu
- */
-static void handle_trap(int pid, struct uml_pt_regs *regs,
-			int local_using_sysemu)
+static void handle_trap(int pid, struct uml_pt_regs *regs)
 {
-	int err, status;
-
 	if ((UPT_IP(regs) >= STUB_START) && (UPT_IP(regs) < STUB_END))
 		fatal_sigsegv();
 
-	if (!local_using_sysemu)
-	{
-		err = ptrace(PTRACE_POKEUSER, pid, PT_SYSCALL_NR_OFFSET,
-			     __NR_getpid);
-		if (err < 0) {
-			printk(UM_KERN_ERR "%s - nullifying syscall failed, errno = %d\n",
-			       __func__, errno);
-			fatal_sigsegv();
-		}
-
-		err = ptrace(PTRACE_SYSCALL, pid, 0, 0);
-		if (err < 0) {
-			printk(UM_KERN_ERR "%s - continuing to end of syscall failed, errno = %d\n",
-			       __func__, errno);
-			fatal_sigsegv();
-		}
-
-		CATCH_EINTR(err = waitpid(pid, &status, WUNTRACED | __WALL));
-		if ((err < 0) || !WIFSTOPPED(status) ||
-		    (WSTOPSIG(status) != SIGTRAP + 0x80)) {
-			err = ptrace_dump_regs(pid);
-			if (err)
-				printk(UM_KERN_ERR "Failed to get registers from process, errno = %d\n",
-				       -err);
-			printk(UM_KERN_ERR "%s - failed to wait at end of syscall, errno = %d, status = %d\n",
-			       __func__, errno, status);
-			fatal_sigsegv();
-		}
-	}
-
 	handle_syscall(regs);
 }
 
@@ -226,7 +189,7 @@ extern char __syscall_stub_start[];
 
 /**
  * userspace_tramp() - userspace trampoline
- * @stack:	pointer to the new userspace stack page, can be NULL, if? FIXME:
+ * @stack:	pointer to the new userspace stack page
  *
  * The userspace trampoline is used to setup a new userspace process in start_userspace() after it was clone()'ed.
  * This function will run on a temporary stack page.
@@ -241,9 +204,13 @@ extern char __syscall_stub_start[];
  */
 static int userspace_tramp(void *stack)
 {
+	struct sigaction sa;
 	void *addr;
 	int fd;
 	unsigned long long offset;
+	unsigned long segv_handler = STUB_CODE +
+				     (unsigned long) stub_segv_handler -
+				     (unsigned long) __syscall_stub_start;
 
 	ptrace(PTRACE_TRACEME, 0, 0, 0);
 
@@ -254,39 +221,30 @@ static int userspace_tramp(void *stack)
 	addr = mmap64((void *) STUB_CODE, UM_KERN_PAGE_SIZE,
 		      PROT_EXEC, MAP_FIXED | MAP_PRIVATE, fd, offset);
 	if (addr == MAP_FAILED) {
-		printk(UM_KERN_ERR "mapping mmap stub at 0x%lx failed, errno = %d\n",
-		       STUB_CODE, errno);
+		os_info("mapping mmap stub at 0x%lx failed, errno = %d\n",
+			STUB_CODE, errno);
 		exit(1);
 	}
 
-	if (stack != NULL) {
-		fd = phys_mapping(uml_to_phys(stack), &offset);
-		addr = mmap((void *) STUB_DATA,
-			    STUB_DATA_PAGES * UM_KERN_PAGE_SIZE, PROT_READ | PROT_WRITE,
-			    MAP_FIXED | MAP_SHARED, fd, offset);
-		if (addr == MAP_FAILED) {
-			printk(UM_KERN_ERR "mapping segfault stack at 0x%lx failed, errno = %d\n",
-			       STUB_DATA, errno);
-			exit(1);
-		}
+	fd = phys_mapping(uml_to_phys(stack), &offset);
+	addr = mmap((void *) STUB_DATA,
+		    STUB_DATA_PAGES * UM_KERN_PAGE_SIZE, PROT_READ | PROT_WRITE,
+		    MAP_FIXED | MAP_SHARED, fd, offset);
+	if (addr == MAP_FAILED) {
+		os_info("mapping segfault stack at 0x%lx failed, errno = %d\n",
+			STUB_DATA, errno);
+		exit(1);
 	}
-	if (stack != NULL) {
-		struct sigaction sa;
-
-		unsigned long v = STUB_CODE +
-				  (unsigned long) stub_segv_handler -
-				  (unsigned long) __syscall_stub_start;
-
-		set_sigstack((void *) STUB_DATA, STUB_DATA_PAGES * UM_KERN_PAGE_SIZE);
-		sigemptyset(&sa.sa_mask);
-		sa.sa_flags = SA_ONSTACK | SA_NODEFER | SA_SIGINFO;
-		sa.sa_sigaction = (void *) v;
-		sa.sa_restorer = NULL;
-		if (sigaction(SIGSEGV, &sa, NULL) < 0) {
-			printk(UM_KERN_ERR "%s - setting SIGSEGV handler failed - errno = %d\n",
-			       __func__, errno);
-			exit(1);
-		}
+
+	set_sigstack((void *) STUB_DATA, STUB_DATA_PAGES * UM_KERN_PAGE_SIZE);
+	sigemptyset(&sa.sa_mask);
+	sa.sa_flags = SA_ONSTACK | SA_NODEFER | SA_SIGINFO;
+	sa.sa_sigaction = (void *) segv_handler;
+	sa.sa_restorer = NULL;
+	if (sigaction(SIGSEGV, &sa, NULL) < 0) {
+		os_info("%s - setting SIGSEGV handler failed - errno = %d\n",
+			__func__, errno);
+		exit(1);
 	}
 
 	kill(os_getpid(), SIGSTOP);
@@ -298,7 +256,7 @@ int kill_userspace_mm[NR_CPUS];
 
 /**
  * start_userspace() - prepare a new userspace process
- * @stub_stack:	pointer to the stub stack. Can be NULL, if? FIXME:
+ * @stub_stack:	pointer to the stub stack.
  *
  * Setups a new temporary stack page that is used while userspace_tramp() runs
  * Clones the kernel process into a new userspace process, with FDs only.
@@ -355,10 +313,10 @@ int start_userspace(unsigned long stub_stack)
 		goto out_kill;
 	}
 
-	if (ptrace(PTRACE_OLDSETOPTIONS, pid, NULL,
+	if (ptrace(PTRACE_SETOPTIONS, pid, NULL,
 		   (void *) PTRACE_O_TRACESYSGOOD) < 0) {
 		err = -errno;
-		printk(UM_KERN_ERR "%s : PTRACE_OLDSETOPTIONS failed, errno = %d\n",
+		printk(UM_KERN_ERR "%s : PTRACE_SETOPTIONS failed, errno = %d\n",
 		       __func__, errno);
 		goto out_kill;
 	}
@@ -380,8 +338,6 @@ int start_userspace(unsigned long stub_stack)
 void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs)
 {
 	int err, status, op, pid = userspace_pid[0];
-	/* To prevent races if using_sysemu changes under us.*/
-	int local_using_sysemu;
 	siginfo_t si;
 
 	/* Handle any immediate reschedules or signals */
@@ -411,11 +367,10 @@ void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs)
 			fatal_sigsegv();
 		}
 
-		/* Now we set local_using_sysemu to be used for one loop */
-		local_using_sysemu = get_using_sysemu();
-
-		op = SELECT_PTRACE_OPERATION(local_using_sysemu,
-					     singlestepping(NULL));
+		if (singlestepping())
+			op = PTRACE_SYSEMU_SINGLESTEP;
+		else
+			op = PTRACE_SYSEMU;
 
 		if (ptrace(op, pid, 0, 0)) {
 			printk(UM_KERN_ERR "%s - ptrace continue failed, op = %d, errno = %d\n",
@@ -474,7 +429,7 @@ void userspace(struct uml_pt_regs *regs, unsigned long *aux_fp_regs)
 				else handle_segv(pid, regs, aux_fp_regs);
 				break;
 			case SIGTRAP + 0x80:
-			        handle_trap(pid, regs, local_using_sysemu);
+				handle_trap(pid, regs);
 				break;
 			case SIGTRAP:
 				relay_signal(SIGTRAP, (struct siginfo *)&si, regs);
@@ -597,10 +552,10 @@ int copy_context_skas0(unsigned long new_stack, int pid)
 		goto out_kill;
 	}
 
-	if (ptrace(PTRACE_OLDSETOPTIONS, pid, NULL,
+	if (ptrace(PTRACE_SETOPTIONS, pid, NULL,
 		   (void *)PTRACE_O_TRACESYSGOOD) < 0) {
 		err = -errno;
-		printk(UM_KERN_ERR "%s : PTRACE_OLDSETOPTIONS failed, errno = %d\n",
+		printk(UM_KERN_ERR "%s : PTRACE_SETOPTIONS failed, errno = %d\n",
 		       __func__, errno);
 		goto out_kill;
 	}
diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c
index e3ee4db58b40..8b0e98ab842c 100644
--- a/arch/um/os-Linux/start_up.c
+++ b/arch/um/os-Linux/start_up.c
@@ -112,102 +112,32 @@ static int start_ptraced_child(void)
 	return pid;
 }
 
-/* When testing for SYSEMU support, if it is one of the broken versions, we
- * must just avoid using sysemu, not panic, but only if SYSEMU features are
- * broken.
- * So only for SYSEMU features we test mustpanic, while normal host features
- * must work anyway!
- */
-static int stop_ptraced_child(int pid, int exitcode, int mustexit)
+static void stop_ptraced_child(int pid, int exitcode)
 {
-	int status, n, ret = 0;
+	int status, n;
+
+	if (ptrace(PTRACE_CONT, pid, 0, 0) < 0)
+		fatal_perror("stop_ptraced_child : ptrace failed");
 
-	if (ptrace(PTRACE_CONT, pid, 0, 0) < 0) {
-		perror("stop_ptraced_child : ptrace failed");
-		return -1;
-	}
 	CATCH_EINTR(n = waitpid(pid, &status, 0));
 	if (!WIFEXITED(status) || (WEXITSTATUS(status) != exitcode)) {
 		int exit_with = WEXITSTATUS(status);
-		if (exit_with == 2)
-			non_fatal("check_ptrace : child exited with status 2. "
-				  "\nDisabling SYSEMU support.\n");
-		non_fatal("check_ptrace : child exited with exitcode %d, while "
-			  "expecting %d; status 0x%x\n", exit_with,
-			  exitcode, status);
-		if (mustexit)
-			exit(1);
-		ret = -1;
+		fatal("stop_ptraced_child : child exited with exitcode %d, "
+		      "while expecting %d; status 0x%x\n", exit_with,
+		      exitcode, status);
 	}
-
-	return ret;
-}
-
-/* Changed only during early boot */
-static int force_sysemu_disabled = 0;
-
-static int __init nosysemu_cmd_param(char *str, int* add)
-{
-	force_sysemu_disabled = 1;
-	return 0;
 }
 
-__uml_setup("nosysemu", nosysemu_cmd_param,
-"nosysemu\n"
-"    Turns off syscall emulation patch for ptrace (SYSEMU).\n"
-"    SYSEMU is a performance-patch introduced by Laurent Vivier. It changes\n"
-"    behaviour of ptrace() and helps reduce host context switch rates.\n"
-"    To make it work, you need a kernel patch for your host, too.\n"
-"    See http://perso.wanadoo.fr/laurent.vivier/UML/ for further \n"
-"    information.\n\n");
-
 static void __init check_sysemu(void)
 {
-	unsigned long regs[MAX_REG_NR];
 	int pid, n, status, count=0;
 
-	os_info("Checking syscall emulation patch for ptrace...");
-	sysemu_supported = 0;
-	pid = start_ptraced_child();
-
-	if (ptrace(PTRACE_SYSEMU, pid, 0, 0) < 0)
-		goto fail;
-
-	CATCH_EINTR(n = waitpid(pid, &status, WUNTRACED));
-	if (n < 0)
-		fatal_perror("check_sysemu : wait failed");
-	if (!WIFSTOPPED(status) || (WSTOPSIG(status) != SIGTRAP))
-		fatal("check_sysemu : expected SIGTRAP, got status = %d\n",
-		      status);
-
-	if (ptrace(PTRACE_GETREGS, pid, 0, regs) < 0)
-		fatal_perror("check_sysemu : PTRACE_GETREGS failed");
-	if (PT_SYSCALL_NR(regs) != __NR_getpid) {
-		non_fatal("check_sysemu got system call number %d, "
-			  "expected %d...", PT_SYSCALL_NR(regs), __NR_getpid);
-		goto fail;
-	}
-
-	n = ptrace(PTRACE_POKEUSER, pid, PT_SYSCALL_RET_OFFSET, os_getpid());
-	if (n < 0) {
-		non_fatal("check_sysemu : failed to modify system call "
-			  "return");
-		goto fail;
-	}
-
-	if (stop_ptraced_child(pid, 0, 0) < 0)
-		goto fail_stopped;
-
-	sysemu_supported = 1;
-	os_info("OK\n");
-	set_using_sysemu(!force_sysemu_disabled);
-
-	os_info("Checking advanced syscall emulation patch for ptrace...");
+	os_info("Checking syscall emulation for ptrace...");
 	pid = start_ptraced_child();
 
-	if ((ptrace(PTRACE_OLDSETOPTIONS, pid, 0,
+	if ((ptrace(PTRACE_SETOPTIONS, pid, 0,
 		   (void *) PTRACE_O_TRACESYSGOOD) < 0))
-		fatal_perror("check_sysemu: PTRACE_OLDSETOPTIONS failed");
+		fatal_perror("check_sysemu: PTRACE_SETOPTIONS failed");
 
 	while (1) {
 		count++;
@@ -240,20 +170,15 @@ static void __init check_sysemu(void)
 			goto fail;
 		}
 	}
-	if (stop_ptraced_child(pid, 0, 0) < 0)
-		goto fail_stopped;
+	stop_ptraced_child(pid, 0);
 
-	sysemu_supported = 2;
 	os_info("OK\n");
 
-	if (!force_sysemu_disabled)
-		set_using_sysemu(sysemu_supported);
 	return;
 
 fail:
-	stop_ptraced_child(pid, 1, 0);
-fail_stopped:
-	non_fatal("missing\n");
+	stop_ptraced_child(pid, 1);
+	fatal("missing\n");
 }
 
 static void __init check_ptrace(void)
@@ -263,9 +188,9 @@ static void __init check_ptrace(void)
 	os_info("Checking that ptrace can change system call numbers...");
 	pid = start_ptraced_child();
 
-	if ((ptrace(PTRACE_OLDSETOPTIONS, pid, 0,
+	if ((ptrace(PTRACE_SETOPTIONS, pid, 0,
 		   (void *) PTRACE_O_TRACESYSGOOD) < 0))
-		fatal_perror("check_ptrace: PTRACE_OLDSETOPTIONS failed");
+		fatal_perror("check_ptrace: PTRACE_SETOPTIONS failed");
 
 	while (1) {
 		if (ptrace(PTRACE_SYSCALL, pid, 0, 0) < 0)
@@ -291,7 +216,7 @@ static void __init check_ptrace(void)
 			break;
 		}
 	}
-	stop_ptraced_child(pid, 0, 1);
+	stop_ptraced_child(pid, 0);
 	os_info("OK\n");
 	check_sysemu();
 }
@@ -370,7 +295,7 @@ void __init os_early_checks(void)
 	pid = start_ptraced_child();
 	if (init_pid_registers(pid))
 		fatal("Failed to initialize default registers");
-	stop_ptraced_child(pid, 1, 1);
+	stop_ptraced_child(pid, 1);
 }
 
 int __init parse_iomem(char *str, int *add)
diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c
index fc0f2a9dee5a..1dca4ffbd572 100644
--- a/arch/um/os-Linux/util.c
+++ b/arch/um/os-Linux/util.c
@@ -173,23 +173,38 @@ __uml_setup("quiet", quiet_cmd_param,
 "quiet\n"
 "    Turns off information messages during boot.\n\n");
 
+/*
+ * The os_info/os_warn functions will be called by helper threads. These
+ * have a very limited stack size and using the libc formatting functions
+ * may overflow the stack.
+ * So pull in the kernel vscnprintf and use that instead with a fixed
+ * on-stack buffer.
+ */
+int vscnprintf(char *buf, size_t size, const char *fmt, va_list args);
+
 void os_info(const char *fmt, ...)
 {
+	char buf[256];
 	va_list list;
+	int len;
 
 	if (quiet_info)
 		return;
 
 	va_start(list, fmt);
-	vfprintf(stderr, fmt, list);
+	len = vscnprintf(buf, sizeof(buf), fmt, list);
+	fwrite(buf, len, 1, stderr);
 	va_end(list);
 }
 
 void os_warn(const char *fmt, ...)
 {
+	char buf[256];
 	va_list list;
+	int len;
 
 	va_start(list, fmt);
-	vfprintf(stderr, fmt, list);
+	len = vscnprintf(buf, sizeof(buf), fmt, list);
+	fwrite(buf, len, 1, stderr);
 	va_end(list);
 }
diff --git a/arch/x86/um/asm/elf.h b/arch/x86/um/asm/elf.h
index 6523eb7c3bd1..6052200fe925 100644
--- a/arch/x86/um/asm/elf.h
+++ b/arch/x86/um/asm/elf.h
@@ -168,8 +168,8 @@ do {								\
 	(pr_reg)[18] = (_regs)->regs.gp[18];			\
 	(pr_reg)[19] = (_regs)->regs.gp[19];			\
 	(pr_reg)[20] = (_regs)->regs.gp[20];			\
-	(pr_reg)[21] = current->thread.arch.fs;			\
-	(pr_reg)[22] = 0;					\
+	(pr_reg)[21] = (_regs)->regs.gp[21];			\
+	(pr_reg)[22] = (_regs)->regs.gp[22];			\
 	(pr_reg)[23] = 0;					\
 	(pr_reg)[24] = 0;					\
 	(pr_reg)[25] = 0;					\
diff --git a/arch/x86/um/asm/processor_64.h b/arch/x86/um/asm/processor_64.h
index 1ef9c21877bc..f90159508936 100644
--- a/arch/x86/um/asm/processor_64.h
+++ b/arch/x86/um/asm/processor_64.h
@@ -10,13 +10,11 @@
 struct arch_thread {
         unsigned long debugregs[8];
         int debugregs_seq;
-        unsigned long fs;
         struct faultinfo faultinfo;
 };
 
 #define INIT_ARCH_THREAD { .debugregs  		= { [ 0 ... 7 ] = 0 }, \
 			   .debugregs_seq	= 0, \
-			   .fs			= 0, \
 			   .faultinfo		= { 0, 0, 0 } }
 
 #define STACKSLOTS_PER_LINE 4
@@ -28,7 +26,6 @@ static inline void arch_flush_thread(struct arch_thread *thread)
 static inline void arch_copy_thread(struct arch_thread *from,
                                     struct arch_thread *to)
 {
-	to->fs = from->fs;
 }
 
 #define current_sp() ({ void *sp; __asm__("movq %%rsp, %0" : "=r" (sp) : ); sp; })
diff --git a/arch/x86/um/os-Linux/Makefile b/arch/x86/um/os-Linux/Makefile
index ae169125d03f..5249bbc30dcd 100644
--- a/arch/x86/um/os-Linux/Makefile
+++ b/arch/x86/um/os-Linux/Makefile
@@ -6,7 +6,6 @@
 obj-y = registers.o task_size.o mcontext.o
 
 obj-$(CONFIG_X86_32) += tls.o
-obj-$(CONFIG_64BIT) += prctl.o
 
 USER_OBJS := $(obj-y)
 
diff --git a/arch/x86/um/os-Linux/prctl.c b/arch/x86/um/os-Linux/prctl.c
deleted file mode 100644
index 8431e87ac333..000000000000
--- a/arch/x86/um/os-Linux/prctl.c
+++ /dev/null
@@ -1,12 +0,0 @@
-/*
- * Copyright (C) 2007 Jeff Dike (jdike@{addtoit.com,linux.intel.com})
- * Licensed under the GPL
- */
-
-#include <sys/ptrace.h>
-#include <asm/ptrace.h>
-
-int os_arch_prctl(int pid, int option, unsigned long *arg2)
-{
-	return ptrace(PTRACE_ARCH_PRCTL, pid, (unsigned long) arg2, option);
-}
diff --git a/arch/x86/um/ptrace_32.c b/arch/x86/um/ptrace_32.c
index 0bc4b73a9cde..7f1abde2c84b 100644
--- a/arch/x86/um/ptrace_32.c
+++ b/arch/x86/um/ptrace_32.c
@@ -25,30 +25,6 @@ void arch_switch_to(struct task_struct *to)
 		printk(KERN_WARNING "arch_switch_tls failed, errno = EINVAL\n");
 }
 
-int is_syscall(unsigned long addr)
-{
-	unsigned short instr;
-	int n;
-
-	n = copy_from_user(&instr, (void __user *) addr, sizeof(instr));
-	if (n) {
-		/* access_process_vm() grants access to vsyscall and stub,
-		 * while copy_from_user doesn't. Maybe access_process_vm is
-		 * slow, but that doesn't matter, since it will be called only
-		 * in case of singlestepping, if copy_from_user failed.
-		 */
-		n = access_process_vm(current, addr, &instr, sizeof(instr),
-				FOLL_FORCE);
-		if (n != sizeof(instr)) {
-			printk(KERN_ERR "is_syscall : failed to read "
-			       "instruction from 0x%lx\n", addr);
-			return 1;
-		}
-	}
-	/* int 0x80 or sysenter */
-	return (instr == 0x80cd) || (instr == 0x340f);
-}
-
 /* determines which flags the user has access to. */
 /* 1 = access 0 = no access */
 #define FLAG_MASK 0x00044dd5
diff --git a/arch/x86/um/ptrace_64.c b/arch/x86/um/ptrace_64.c
index 289d0159b041..aa68d83d3f44 100644
--- a/arch/x86/um/ptrace_64.c
+++ b/arch/x86/um/ptrace_64.c
@@ -188,32 +188,6 @@ int peek_user(struct task_struct *child, long addr, long data)
 	return put_user(tmp, (unsigned long *) data);
 }
 
-/* XXX Mostly copied from sys-i386 */
-int is_syscall(unsigned long addr)
-{
-	unsigned short instr;
-	int n;
-
-	n = copy_from_user(&instr, (void __user *) addr, sizeof(instr));
-	if (n) {
-		/*
-		 * access_process_vm() grants access to vsyscall and stub,
-		 * while copy_from_user doesn't. Maybe access_process_vm is
-		 * slow, but that doesn't matter, since it will be called only
-		 * in case of singlestepping, if copy_from_user failed.
-		 */
-		n = access_process_vm(current, addr, &instr, sizeof(instr),
-				FOLL_FORCE);
-		if (n != sizeof(instr)) {
-			printk("is_syscall : failed to read instruction from "
-			       "0x%lx\n", addr);
-			return 1;
-		}
-	}
-	/* sysenter */
-	return instr == 0x050f;
-}
-
 static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child)
 {
 	int err, n, cpu = ((struct thread_info *) child->stack)->cpu;
diff --git a/arch/x86/um/shared/sysdep/ptrace_32.h b/arch/x86/um/shared/sysdep/ptrace_32.h
index db8478a83a09..0c4989842fbe 100644
--- a/arch/x86/um/shared/sysdep/ptrace_32.h
+++ b/arch/x86/um/shared/sysdep/ptrace_32.h
@@ -8,10 +8,6 @@
 
 #define MAX_FP_NR HOST_FPX_SIZE
 
-void set_using_sysemu(int value);
-int get_using_sysemu(void);
-extern int sysemu_supported;
-
 #define UPT_SYSCALL_ARG1(r) UPT_BX(r)
 #define UPT_SYSCALL_ARG2(r) UPT_CX(r)
 #define UPT_SYSCALL_ARG3(r) UPT_DX(r)
diff --git a/arch/x86/um/shared/sysdep/ptrace_user.h b/arch/x86/um/shared/sysdep/ptrace_user.h
index 44782bbad41e..1d1a824fa652 100644
--- a/arch/x86/um/shared/sysdep/ptrace_user.h
+++ b/arch/x86/um/shared/sysdep/ptrace_user.h
@@ -15,14 +15,12 @@
 #define FP_SIZE ((HOST_FPX_SIZE > HOST_FP_SIZE) ? HOST_FPX_SIZE : HOST_FP_SIZE)
 #else
 #define FP_SIZE HOST_FP_SIZE
+#endif
 
 /*
- * x86_64 FC3 doesn't define this in /usr/include/linux/ptrace.h even though
- * it's defined in the kernel's include/linux/ptrace.h. Additionally, use the
- * 2.4 name and value for 2.4 host compatibility.
+ * glibc before 2.27 does not include PTRACE_SYSEMU_SINGLESTEP in its enum,
+ * ensure we have a definition by (re-)defining it here.
  */
-#ifndef PTRACE_OLDSETOPTIONS
-#define PTRACE_OLDSETOPTIONS 21
-#endif
-
+#ifndef PTRACE_SYSEMU_SINGLESTEP
+#define PTRACE_SYSEMU_SINGLESTEP 32
 #endif
diff --git a/arch/x86/um/shared/sysdep/stub_32.h b/arch/x86/um/shared/sysdep/stub_32.h
index 38fa894b65d0..ea8b5a2d67af 100644
--- a/arch/x86/um/shared/sysdep/stub_32.h
+++ b/arch/x86/um/shared/sysdep/stub_32.h
@@ -12,72 +12,79 @@
 #define STUB_MMAP_NR __NR_mmap2
 #define MMAP_OFFSET(o) ((o) >> UM_KERN_PAGE_SHIFT)
 
-static inline long stub_syscall0(long syscall)
+static __always_inline long stub_syscall0(long syscall)
 {
 	long ret;
 
-	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall));
+	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall)
+			: "memory");
 
 	return ret;
 }
 
-static inline long stub_syscall1(long syscall, long arg1)
+static __always_inline long stub_syscall1(long syscall, long arg1)
 {
 	long ret;
 
-	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1));
+	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1)
+			: "memory");
 
 	return ret;
 }
 
-static inline long stub_syscall2(long syscall, long arg1, long arg2)
+static __always_inline long stub_syscall2(long syscall, long arg1, long arg2)
 {
 	long ret;
 
 	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1),
-			"c" (arg2));
+			"c" (arg2)
+			: "memory");
 
 	return ret;
 }
 
-static inline long stub_syscall3(long syscall, long arg1, long arg2, long arg3)
+static __always_inline long stub_syscall3(long syscall, long arg1, long arg2,
+					  long arg3)
 {
 	long ret;
 
 	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1),
-			"c" (arg2), "d" (arg3));
+			"c" (arg2), "d" (arg3)
+			: "memory");
 
 	return ret;
 }
 
-static inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3,
-				 long arg4)
+static __always_inline long stub_syscall4(long syscall, long arg1, long arg2,
+					  long arg3, long arg4)
 {
 	long ret;
 
 	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1),
-			"c" (arg2), "d" (arg3), "S" (arg4));
+			"c" (arg2), "d" (arg3), "S" (arg4)
+			: "memory");
 
 	return ret;
 }
 
-static inline long stub_syscall5(long syscall, long arg1, long arg2, long arg3,
-				 long arg4, long arg5)
+static __always_inline long stub_syscall5(long syscall, long arg1, long arg2,
+					  long arg3, long arg4, long arg5)
 {
 	long ret;
 
 	__asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1),
-			"c" (arg2), "d" (arg3), "S" (arg4), "D" (arg5));
+			"c" (arg2), "d" (arg3), "S" (arg4), "D" (arg5)
+			: "memory");
 
 	return ret;
 }
 
-static inline void trap_myself(void)
+static __always_inline void trap_myself(void)
 {
 	__asm("int3");
 }
 
-static inline void remap_stack_and_trap(void)
+static __always_inline void remap_stack_and_trap(void)
 {
 	__asm__ volatile (
 		"movl %%esp,%%ebx ;"
diff --git a/arch/x86/um/shared/sysdep/stub_64.h b/arch/x86/um/shared/sysdep/stub_64.h
index 2de1c8f88173..b24168ef0ac4 100644
--- a/arch/x86/um/shared/sysdep/stub_64.h
+++ b/arch/x86/um/shared/sysdep/stub_64.h
@@ -16,7 +16,7 @@
 #define __syscall_clobber "r11","rcx","memory"
 #define __syscall "syscall"
 
-static inline long stub_syscall0(long syscall)
+static __always_inline long stub_syscall0(long syscall)
 {
 	long ret;
 
@@ -27,7 +27,7 @@ static inline long stub_syscall0(long syscall)
 	return ret;
 }
 
-static inline long stub_syscall2(long syscall, long arg1, long arg2)
+static __always_inline long stub_syscall2(long syscall, long arg1, long arg2)
 {
 	long ret;
 
@@ -38,7 +38,8 @@ static inline long stub_syscall2(long syscall, long arg1, long arg2)
 	return ret;
 }
 
-static inline long stub_syscall3(long syscall, long arg1, long arg2, long arg3)
+static __always_inline long stub_syscall3(long syscall, long arg1, long arg2,
+					  long arg3)
 {
 	long ret;
 
@@ -50,7 +51,7 @@ static inline long stub_syscall3(long syscall, long arg1, long arg2, long arg3)
 	return ret;
 }
 
-static inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3,
+static __always_inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3,
 				 long arg4)
 {
 	long ret;
@@ -64,8 +65,8 @@ static inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3,
 	return ret;
 }
 
-static inline long stub_syscall5(long syscall, long arg1, long arg2, long arg3,
-				 long arg4, long arg5)
+static __always_inline long stub_syscall5(long syscall, long arg1, long arg2,
+					  long arg3, long arg4, long arg5)
 {
 	long ret;
 
@@ -78,12 +79,12 @@ static inline long stub_syscall5(long syscall, long arg1, long arg2, long arg3,
 	return ret;
 }
 
-static inline void trap_myself(void)
+static __always_inline void trap_myself(void)
 {
 	__asm("int3");
 }
 
-static inline void remap_stack_and_trap(void)
+static __always_inline void remap_stack_and_trap(void)
 {
 	__asm__ volatile (
 		"movq %0,%%rax ;"
diff --git a/arch/x86/um/syscalls_64.c b/arch/x86/um/syscalls_64.c
index 27b29ae6c471..6a00a28c9cca 100644
--- a/arch/x86/um/syscalls_64.c
+++ b/arch/x86/um/syscalls_64.c
@@ -16,60 +16,24 @@
 long arch_prctl(struct task_struct *task, int option,
 		unsigned long __user *arg2)
 {
-	unsigned long *ptr = arg2, tmp;
-	long ret;
-	int pid = task->mm->context.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 or thread.fs being set instead).  So, we let the host
-	 * fiddle the registers and thread struct and restore the
-	 * registers 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 (option) {
-	case ARCH_SET_FS:
-	case ARCH_SET_GS:
-		ret = restore_pid_registers(pid, &current->thread.regs.regs);
-		if (ret)
-			return ret;
-		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, option, ptr);
-	if (ret)
-		return ret;
+	long ret = -EINVAL;
 
 	switch (option) {
 	case ARCH_SET_FS:
-		current->thread.arch.fs = (unsigned long) ptr;
-		ret = save_registers(pid, &current->thread.regs.regs);
+		current->thread.regs.regs.gp[FS_BASE / sizeof(unsigned long)] =
+			(unsigned long) arg2;
+		ret = 0;
 		break;
 	case ARCH_SET_GS:
-		ret = save_registers(pid, &current->thread.regs.regs);
+		current->thread.regs.regs.gp[GS_BASE / sizeof(unsigned long)] =
+			(unsigned long) arg2;
+		ret = 0;
 		break;
 	case ARCH_GET_FS:
-		ret = put_user(tmp, arg2);
+		ret = put_user(current->thread.regs.regs.gp[FS_BASE / sizeof(unsigned long)], arg2);
 		break;
 	case ARCH_GET_GS:
-		ret = put_user(tmp, arg2);
+		ret = put_user(current->thread.regs.regs.gp[GS_BASE / sizeof(unsigned long)], arg2);
 		break;
 	}
 
@@ -83,10 +47,10 @@ SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2)
 
 void arch_switch_to(struct task_struct *to)
 {
-	if ((to->thread.arch.fs == 0) || (to->mm == NULL))
-		return;
-
-	arch_prctl(to, ARCH_SET_FS, (void __user *) to->thread.arch.fs);
+	/*
+	 * Nothing needs to be done on x86_64.
+	 * The FS_BASE/GS_BASE registers are saved in the ptrace register set.
+	 */
 }
 
 SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
diff --git a/arch/x86/um/tls_64.c b/arch/x86/um/tls_64.c
index ebd3855d9b13..c51a613f6f5c 100644
--- a/arch/x86/um/tls_64.c
+++ b/arch/x86/um/tls_64.c
@@ -12,7 +12,7 @@ int arch_set_tls(struct task_struct *t, unsigned long tls)
 	 * If CLONE_SETTLS is set, we need to save the thread id
 	 * so it can be set during context switches.
 	 */
-	t->thread.arch.fs = tls;
+	t->thread.regs.regs.gp[FS_BASE / sizeof(unsigned long)] = tls;
 
 	return 0;
 }