24 files changed, 98 insertions, 425 deletions

diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig
index 1bcd42c53039..186f13268401 100644
--- a/arch/x86/um/Kconfig
+++ b/arch/x86/um/Kconfig
@@ -32,12 +32,12 @@ config 3_LEVEL_PGTABLES
 	bool "Three-level pagetables" if !64BIT
 	default 64BIT
 	help
-	Three-level pagetables will let UML have more than 4G of physical
-	memory.  All the memory that can't be mapped directly will be treated
-	as high memory.
+	  Three-level pagetables will let UML have more than 4G of physical
+	  memory.  All the memory that can't be mapped directly will be treated
+	  as high memory.
 
-	However, this it experimental on 32-bit architectures, so if unsure say
-	N (on x86-64 it's automatically enabled, instead, as it's safe there).
+	  However, this it experimental on 32-bit architectures, so if unsure say
+	  N (on x86-64 it's automatically enabled, instead, as it's safe there).
 
 config ARCH_HAS_SC_SIGNALS
 	def_bool !64BIT
diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile
index ba5789c35809..8bc72a51b257 100644
--- a/arch/x86/um/Makefile
+++ b/arch/x86/um/Makefile
@@ -13,22 +13,25 @@ obj-y = bugs_$(BITS).o delay.o fault.o ldt.o \
 	ptrace_$(BITS).o ptrace_user.o setjmp_$(BITS).o signal.o \
 	stub_$(BITS).o stub_segv.o \
 	sys_call_table_$(BITS).o sysrq_$(BITS).o tls_$(BITS).o \
-	mem_$(BITS).o subarch.o os-$(OS)/
+	mem_$(BITS).o subarch.o os-Linux/
 
 ifeq ($(CONFIG_X86_32),y)
 
-obj-y += checksum_32.o syscalls_32.o
+obj-y += syscalls_32.o
 obj-$(CONFIG_ELF_CORE) += elfcore.o
 
 subarch-y = ../lib/string_32.o ../lib/atomic64_32.o ../lib/atomic64_cx8_32.o
 subarch-y += ../lib/cmpxchg8b_emu.o ../lib/atomic64_386_32.o
+subarch-y += ../lib/checksum_32.o
 subarch-y += ../kernel/sys_ia32.o
 
 else
 
 obj-y += syscalls_64.o vdso/
 
-subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../entry/thunk_64.o
+subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o \
+	../lib/memmove_64.o ../lib/memset_64.o
+subarch-$(CONFIG_PREEMPTION) += ../entry/thunk_64.o
 
 endif
 
@@ -46,4 +49,4 @@ include/generated/user_constants.h: $(obj)/user-offsets.s FORCE
 UNPROFILE_OBJS := stub_segv.o
 CFLAGS_stub_segv.o := $(CFLAGS_NO_HARDENING)
 
-include arch/um/scripts/Makefile.rules
+include $(srctree)/arch/um/scripts/Makefile.rules
diff --git a/arch/x86/um/asm/elf.h b/arch/x86/um/asm/elf.h
index dcaf3b38a9e0..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;					\
@@ -201,10 +201,6 @@ typedef struct user_i387_struct elf_fpregset_t;
 
 struct task_struct;
 
-extern int elf_core_copy_fpregs(struct task_struct *t, elf_fpregset_t *fpu);
-
-#define ELF_CORE_COPY_FPREGS(t, fpu) elf_core_copy_fpregs(t, fpu)
-
 #define ELF_EXEC_PAGESIZE 4096
 
 #define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2)
diff --git a/arch/x86/um/asm/mm_context.h b/arch/x86/um/asm/mm_context.h
index 4a73d63e4760..dc32dc023c2f 100644
--- a/arch/x86/um/asm/mm_context.h
+++ b/arch/x86/um/asm/mm_context.h
@@ -11,8 +11,6 @@
 #include <linux/mutex.h>
 #include <asm/ldt.h>
 
-extern void ldt_host_info(void);
-
 #define LDT_PAGES_MAX \
 	((LDT_ENTRIES * LDT_ENTRY_SIZE)/PAGE_SIZE)
 #define LDT_ENTRIES_PER_PAGE \
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/checksum_32.S b/arch/x86/um/checksum_32.S
deleted file mode 100644
index aed782ab7721..000000000000
--- a/arch/x86/um/checksum_32.S
+++ /dev/null
@@ -1,214 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * INET		An implementation of the TCP/IP protocol suite for the LINUX
- *		operating system.  INET is implemented using the  BSD Socket
- *		interface as the means of communication with the user level.
- *
- *		IP/TCP/UDP checksumming routines
- *
- * Authors:	Jorge Cwik, <jorge@laser.satlink.net>
- *		Arnt Gulbrandsen, <agulbra@nvg.unit.no>
- *		Tom May, <ftom@netcom.com>
- *              Pentium Pro/II routines:
- *              Alexander Kjeldaas <astor@guardian.no>
- *              Finn Arne Gangstad <finnag@guardian.no>
- *		Lots of code moved from tcp.c and ip.c; see those files
- *		for more names.
- *
- * Changes:     Ingo Molnar, converted csum_partial_copy() to 2.1 exception
- *			     handling.
- *		Andi Kleen,  add zeroing on error
- *                   converted to pure assembler
- */
-
-#include <asm/errno.h>
-#include <asm/asm.h>
-#include <asm/export.h>
-				
-/*
- * computes a partial checksum, e.g. for TCP/UDP fragments
- */
-
-/*	
-unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum)
- */
-		
-.text
-.align 4
-.globl csum_partial
-		
-#ifndef CONFIG_X86_USE_PPRO_CHECKSUM
-
-	  /*		
-	   * Experiments with Ethernet and SLIP connections show that buff
-	   * is aligned on either a 2-byte or 4-byte boundary.  We get at
-	   * least a twofold speedup on 486 and Pentium if it is 4-byte aligned.
-	   * Fortunately, it is easy to convert 2-byte alignment to 4-byte
-	   * alignment for the unrolled loop.
-	   */		
-csum_partial:
-	pushl %esi
-	pushl %ebx
-	movl 20(%esp),%eax	# Function arg: unsigned int sum
-	movl 16(%esp),%ecx	# Function arg: int len
-	movl 12(%esp),%esi	# Function arg: unsigned char *buff
-	testl $2, %esi		# Check alignment.
-	jz 2f			# Jump if alignment is ok.
-	subl $2, %ecx		# Alignment uses up two bytes.
-	jae 1f			# Jump if we had at least two bytes.
-	addl $2, %ecx		# ecx was < 2.  Deal with it.
-	jmp 4f
-1:	movw (%esi), %bx
-	addl $2, %esi
-	addw %bx, %ax
-	adcl $0, %eax
-2:
-	movl %ecx, %edx
-	shrl $5, %ecx
-	jz 2f
-	testl %esi, %esi
-1:	movl (%esi), %ebx
-	adcl %ebx, %eax
-	movl 4(%esi), %ebx
-	adcl %ebx, %eax
-	movl 8(%esi), %ebx
-	adcl %ebx, %eax
-	movl 12(%esi), %ebx
-	adcl %ebx, %eax
-	movl 16(%esi), %ebx
-	adcl %ebx, %eax
-	movl 20(%esi), %ebx
-	adcl %ebx, %eax
-	movl 24(%esi), %ebx
-	adcl %ebx, %eax
-	movl 28(%esi), %ebx
-	adcl %ebx, %eax
-	lea 32(%esi), %esi
-	dec %ecx
-	jne 1b
-	adcl $0, %eax
-2:	movl %edx, %ecx
-	andl $0x1c, %edx
-	je 4f
-	shrl $2, %edx		# This clears CF
-3:	adcl (%esi), %eax
-	lea 4(%esi), %esi
-	dec %edx
-	jne 3b
-	adcl $0, %eax
-4:	andl $3, %ecx
-	jz 7f
-	cmpl $2, %ecx
-	jb 5f
-	movw (%esi),%cx
-	leal 2(%esi),%esi
-	je 6f
-	shll $16,%ecx
-5:	movb (%esi),%cl
-6:	addl %ecx,%eax
-	adcl $0, %eax 
-7:	
-	popl %ebx
-	popl %esi
-	RET
-
-#else
-
-/* Version for PentiumII/PPro */
-
-csum_partial:
-	pushl %esi
-	pushl %ebx
-	movl 20(%esp),%eax	# Function arg: unsigned int sum
-	movl 16(%esp),%ecx	# Function arg: int len
-	movl 12(%esp),%esi	# Function arg:	const unsigned char *buf
-
-	testl $2, %esi         
-	jnz 30f                 
-10:
-	movl %ecx, %edx
-	movl %ecx, %ebx
-	andl $0x7c, %ebx
-	shrl $7, %ecx
-	addl %ebx,%esi
-	shrl $2, %ebx  
-	negl %ebx
-	lea 45f(%ebx,%ebx,2), %ebx
-	testl %esi, %esi
-	jmp *%ebx
-
-	# Handle 2-byte-aligned regions
-20:	addw (%esi), %ax
-	lea 2(%esi), %esi
-	adcl $0, %eax
-	jmp 10b
-
-30:	subl $2, %ecx          
-	ja 20b                 
-	je 32f
-	movzbl (%esi),%ebx	# csumming 1 byte, 2-aligned
-	addl %ebx, %eax
-	adcl $0, %eax
-	jmp 80f
-32:
-	addw (%esi), %ax	# csumming 2 bytes, 2-aligned
-	adcl $0, %eax
-	jmp 80f
-
-40: 
-	addl -128(%esi), %eax
-	adcl -124(%esi), %eax
-	adcl -120(%esi), %eax
-	adcl -116(%esi), %eax   
-	adcl -112(%esi), %eax   
-	adcl -108(%esi), %eax
-	adcl -104(%esi), %eax
-	adcl -100(%esi), %eax
-	adcl -96(%esi), %eax
-	adcl -92(%esi), %eax
-	adcl -88(%esi), %eax
-	adcl -84(%esi), %eax
-	adcl -80(%esi), %eax
-	adcl -76(%esi), %eax
-	adcl -72(%esi), %eax
-	adcl -68(%esi), %eax
-	adcl -64(%esi), %eax     
-	adcl -60(%esi), %eax     
-	adcl -56(%esi), %eax     
-	adcl -52(%esi), %eax   
-	adcl -48(%esi), %eax   
-	adcl -44(%esi), %eax
-	adcl -40(%esi), %eax
-	adcl -36(%esi), %eax
-	adcl -32(%esi), %eax
-	adcl -28(%esi), %eax
-	adcl -24(%esi), %eax
-	adcl -20(%esi), %eax
-	adcl -16(%esi), %eax
-	adcl -12(%esi), %eax
-	adcl -8(%esi), %eax
-	adcl -4(%esi), %eax
-45:
-	lea 128(%esi), %esi
-	adcl $0, %eax
-	dec %ecx
-	jge 40b
-	movl %edx, %ecx
-50:	andl $3, %ecx
-	jz 80f
-
-	# Handle the last 1-3 bytes without jumping
-	notl %ecx		# 1->2, 2->1, 3->0, higher bits are masked
-	movl $0xffffff,%ebx	# by the shll and shrl instructions
-	shll $3,%ecx
-	shrl %cl,%ebx
-	andl -128(%esi),%ebx	# esi is 4-aligned so should be ok
-	addl %ebx,%eax
-	adcl $0,%eax
-80: 
-	popl %ebx
-	popl %esi
-	RET
-				
-#endif
-	EXPORT_SYMBOL(csum_partial)
diff --git a/arch/x86/um/elfcore.c b/arch/x86/um/elfcore.c
index 48a3eb09d951..650cdbbdaf45 100644
--- a/arch/x86/um/elfcore.c
+++ b/arch/x86/um/elfcore.c
@@ -7,7 +7,7 @@
 #include <asm/elf.h>
 
 
-Elf32_Half elf_core_extra_phdrs(void)
+Elf32_Half elf_core_extra_phdrs(struct coredump_params *cprm)
 {
 	return vsyscall_ehdr ? (((struct elfhdr *)vsyscall_ehdr)->e_phnum) : 0;
 }
@@ -60,7 +60,7 @@ int elf_core_write_extra_data(struct coredump_params *cprm)
 	return 1;
 }
 
-size_t elf_core_extra_data_size(void)
+size_t elf_core_extra_data_size(struct coredump_params *cprm)
 {
 	if ( vsyscall_ehdr ) {
 		const struct elfhdr *const ehdrp =
diff --git a/arch/x86/um/mem_32.c b/arch/x86/um/mem_32.c
index 19c5dbd46770..29b2203bc82c 100644
--- a/arch/x86/um/mem_32.c
+++ b/arch/x86/um/mem_32.c
@@ -16,8 +16,8 @@ static int __init gate_vma_init(void)
 	vma_init(&gate_vma, NULL);
 	gate_vma.vm_start = FIXADDR_USER_START;
 	gate_vma.vm_end = FIXADDR_USER_END;
-	gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC;
-	gate_vma.vm_page_prot = __P101;
+	vm_flags_init(&gate_vma, VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC);
+	gate_vma.vm_page_prot = PAGE_READONLY;
 
 	return 0;
 }
diff --git a/arch/x86/um/os-Linux/Makefile b/arch/x86/um/os-Linux/Makefile
index 253bfb8cb702..5249bbc30dcd 100644
--- a/arch/x86/um/os-Linux/Makefile
+++ b/arch/x86/um/os-Linux/Makefile
@@ -6,8 +6,7 @@
 obj-y = registers.o task_size.o mcontext.o
 
 obj-$(CONFIG_X86_32) += tls.o
-obj-$(CONFIG_64BIT) += prctl.o
 
 USER_OBJS := $(obj-y)
 
-include arch/um/scripts/Makefile.rules
+include $(srctree)/arch/um/scripts/Makefile.rules
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 4c6c2be0c899..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 ;"
@@ -89,19 +96,19 @@ static inline void remap_stack_and_trap(void)
 		"addl %4,%%ebx ; movl %%eax, (%%ebx) ;"
 		"int $3"
 		: :
-		"g" (~(UM_KERN_PAGE_SIZE - 1)),
+		"g" (~(STUB_DATA_PAGES * UM_KERN_PAGE_SIZE - 1)),
 		"g" (STUB_MMAP_NR),
 		"g" (UML_STUB_FIELD_FD),
 		"g" (UML_STUB_FIELD_OFFSET),
 		"g" (UML_STUB_FIELD_CHILD_ERR),
-		"c" (UM_KERN_PAGE_SIZE),
+		"c" (STUB_DATA_PAGES * UM_KERN_PAGE_SIZE),
 		"d" (PROT_READ | PROT_WRITE),
 		"S" (MAP_FIXED | MAP_SHARED)
 		:
 		"memory");
 }
 
-static __always_inline void *get_stub_page(void)
+static __always_inline void *get_stub_data(void)
 {
 	unsigned long ret;
 
@@ -109,7 +116,7 @@ static __always_inline void *get_stub_page(void)
 		"movl %%esp,%0 ;"
 		"andl %1,%0"
 		: "=a" (ret)
-		: "g" (~(UM_KERN_PAGE_SIZE - 1)));
+		: "g" (~(STUB_DATA_PAGES * UM_KERN_PAGE_SIZE - 1)));
 
 	return (void *)ret;
 }
diff --git a/arch/x86/um/shared/sysdep/stub_64.h b/arch/x86/um/shared/sysdep/stub_64.h
index e9c4b2b38803..b24168ef0ac4 100644
--- a/arch/x86/um/shared/sysdep/stub_64.h
+++ b/arch/x86/um/shared/sysdep/stub_64.h
@@ -8,6 +8,7 @@
 
 #include <sysdep/ptrace_user.h>
 #include <generated/asm-offsets.h>
+#include <linux/stddef.h>
 
 #define STUB_MMAP_NR __NR_mmap
 #define MMAP_OFFSET(o) (o)
@@ -15,7 +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;
 
@@ -26,7 +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;
 
@@ -37,7 +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;
 
@@ -49,7 +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;
@@ -63,8 +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;
 
@@ -77,12 +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 ;"
@@ -97,18 +99,18 @@ static inline void remap_stack_and_trap(void)
 		"int3"
 		: :
 		"g" (STUB_MMAP_NR),
-		"g" (~(UM_KERN_PAGE_SIZE - 1)),
+		"g" (~(STUB_DATA_PAGES * UM_KERN_PAGE_SIZE - 1)),
 		"g" (MAP_FIXED | MAP_SHARED),
 		"g" (UML_STUB_FIELD_FD),
 		"g" (UML_STUB_FIELD_OFFSET),
 		"g" (UML_STUB_FIELD_CHILD_ERR),
-		"S" (UM_KERN_PAGE_SIZE),
+		"S" (STUB_DATA_PAGES * UM_KERN_PAGE_SIZE),
 		"d" (PROT_READ | PROT_WRITE)
 		:
 		__syscall_clobber, "r10", "r8", "r9");
 }
 
-static __always_inline void *get_stub_page(void)
+static __always_inline void *get_stub_data(void)
 {
 	unsigned long ret;
 
@@ -116,7 +118,7 @@ static __always_inline void *get_stub_page(void)
 		"movq %%rsp,%0 ;"
 		"andq %1,%0"
 		: "=a" (ret)
-		: "g" (~(UM_KERN_PAGE_SIZE - 1)));
+		: "g" (~(STUB_DATA_PAGES * UM_KERN_PAGE_SIZE - 1)));
 
 	return (void *)ret;
 }
diff --git a/arch/x86/um/shared/sysdep/syscalls_32.h b/arch/x86/um/shared/sysdep/syscalls_32.h
index 68fd2cf526fd..f6e9f84397e7 100644
--- a/arch/x86/um/shared/sysdep/syscalls_32.h
+++ b/arch/x86/um/shared/sysdep/syscalls_32.h
@@ -6,10 +6,9 @@
 #include <asm/unistd.h>
 #include <sysdep/ptrace.h>
 
-typedef long syscall_handler_t(struct pt_regs);
+typedef long syscall_handler_t(struct syscall_args);
 
 extern syscall_handler_t *sys_call_table[];
 
 #define EXECUTE_SYSCALL(syscall, regs) \
-	((long (*)(struct syscall_args)) \
-	 (*sys_call_table[syscall]))(SYSCALL_ARGS(&regs->regs))
+	((*sys_call_table[syscall]))(SYSCALL_ARGS(&regs->regs))
diff --git a/arch/x86/um/stub_segv.c b/arch/x86/um/stub_segv.c
index f7eefba034f9..040668b989b5 100644
--- a/arch/x86/um/stub_segv.c
+++ b/arch/x86/um/stub_segv.c
@@ -11,7 +11,7 @@
 void __attribute__ ((__section__ (".__syscall_stub")))
 stub_segv_handler(int sig, siginfo_t *info, void *p)
 {
-	struct faultinfo *f = get_stub_page();
+	struct faultinfo *f = get_stub_data();
 	ucontext_t *uc = p;
 
 	GET_FAULTINFO_FROM_MC(*f, &uc->uc_mcontext);
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/sysrq_64.c b/arch/x86/um/sysrq_64.c
index 903ad91b624f..0bf6de40abff 100644
--- a/arch/x86/um/sysrq_64.c
+++ b/arch/x86/um/sysrq_64.c
@@ -6,6 +6,7 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/pid.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
 #include <linux/utsname.h>
@@ -19,8 +20,8 @@ void show_regs(struct pt_regs *regs)
 	print_modules();
 	printk(KERN_INFO "Pid: %d, comm: %.20s %s %s\n", task_pid_nr(current),
 		current->comm, print_tainted(), init_utsname()->release);
-	printk(KERN_INFO "RIP: %04lx:[<%016lx>]\n", PT_REGS_CS(regs) & 0xffff,
-	       PT_REGS_IP(regs));
+	printk(KERN_INFO "RIP: %04lx:%pS\n", PT_REGS_CS(regs) & 0xffff,
+	       (void *)PT_REGS_IP(regs));
 	printk(KERN_INFO "RSP: %016lx  EFLAGS: %08lx\n", PT_REGS_SP(regs),
 	       PT_REGS_EFLAGS(regs));
 	printk(KERN_INFO "RAX: %016lx RBX: %016lx RCX: %016lx\n",
diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c
index ac8eee093f9c..66162eafd8e8 100644
--- a/arch/x86/um/tls_32.c
+++ b/arch/x86/um/tls_32.c
@@ -65,9 +65,6 @@ static int get_free_idx(struct task_struct* task)
 	struct thread_struct *t = &task->thread;
 	int idx;
 
-	if (!t->arch.tls_array)
-		return GDT_ENTRY_TLS_MIN;
-
 	for (idx = 0; idx < GDT_ENTRY_TLS_ENTRIES; idx++)
 		if (!t->arch.tls_array[idx].present)
 			return idx + GDT_ENTRY_TLS_MIN;
@@ -240,9 +237,6 @@ static int get_tls_entry(struct task_struct *task, struct user_desc *info,
 {
 	struct thread_struct *t = &task->thread;
 
-	if (!t->arch.tls_array)
-		goto clear;
-
 	if (idx < GDT_ENTRY_TLS_MIN || idx > GDT_ENTRY_TLS_MAX)
 		return -EINVAL;
 
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;
 }
diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile
index 5943387e3f35..b86d634730b2 100644
--- a/arch/x86/um/vdso/Makefile
+++ b/arch/x86/um/vdso/Makefile
@@ -3,6 +3,9 @@
 # Building vDSO images for x86.
 #
 
+# do not instrument on vdso because KASAN is not compatible with user mode
+KASAN_SANITIZE			:= n
+
 # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
 KCOV_INSTRUMENT                := n
 
@@ -58,21 +61,9 @@ CFLAGS_REMOVE_um_vdso.o = -pg -fprofile-arcs -ftest-coverage
 #
 quiet_cmd_vdso = VDSO    $@
       cmd_vdso = $(CC) -nostdlib -o $@ \
-		       $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \
+		       $(CC_FLAGS_LTO) $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \
 		       -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \
 		 sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
 
-VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv
+VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv -z noexecstack
 GCOV_PROFILE := n
-
-#
-# Install the unstripped copy of vdso*.so listed in $(vdso-install-y).
-#
-quiet_cmd_vdso_install = INSTALL $@
-      cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@
-$(vdso-install-y): %.so: $(obj)/%.so.dbg FORCE
-	@mkdir -p $(MODLIB)/vdso
-	$(call cmd,vdso_install)
-
-PHONY += vdso_install $(vdso-install-y)
-vdso_install: $(vdso-install-y)
diff --git a/arch/x86/um/vdso/um_vdso.c b/arch/x86/um/vdso/um_vdso.c
index 2112b8d14668..ff0f3b4b6c45 100644
--- a/arch/x86/um/vdso/um_vdso.c
+++ b/arch/x86/um/vdso/um_vdso.c
@@ -17,8 +17,10 @@ int __vdso_clock_gettime(clockid_t clock, struct __kernel_old_timespec *ts)
 {
 	long ret;
 
-	asm("syscall" : "=a" (ret) :
-		"0" (__NR_clock_gettime), "D" (clock), "S" (ts) : "memory");
+	asm("syscall"
+		: "=a" (ret)
+		: "0" (__NR_clock_gettime), "D" (clock), "S" (ts)
+		: "rcx", "r11", "memory");
 
 	return ret;
 }
@@ -29,8 +31,10 @@ int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 {
 	long ret;
 
-	asm("syscall" : "=a" (ret) :
-		"0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory");
+	asm("syscall"
+		: "=a" (ret)
+		: "0" (__NR_gettimeofday), "D" (tv), "S" (tz)
+		: "rcx", "r11", "memory");
 
 	return ret;
 }