Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 asm changes from Ingo Molnar:
 "The main change in this cycle is another step in the big x86 system
  call interface rework by Andy Lutomirski, which moves most of the low
  level x86 entry code from assembly to C, for all syscall entries
  except native 64-bit system calls:

    arch/x86/entry/entry_32.S        | 182 ++++------
    arch/x86/entry/entry_64_compat.S | 547 ++++++++-----------------------
    194 insertions(+), 535 deletions(-)

  ... our hope is that the final remaining step (converting native
  64-bit system calls) will be less painful as all the previous steps,
  given that most of the legacies and quirks are concentrated around
  native 32-bit and compat environments"

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (47 commits)
  x86/entry/32: Fix FS and GS restore in opportunistic SYSEXIT
  x86/entry/32: Fix entry_INT80_32() to expect interrupts to be on
  um/x86: Fix build after x86 syscall changes
  x86/asm: Remove the xyz_cfi macros from dwarf2.h
  selftests/x86: Style fixes for the 'unwind_vdso' test
  x86/entry/64/compat: Document sysenter_fix_flags's reason for existence
  x86/entry: Split and inline syscall_return_slowpath()
  x86/entry: Split and inline prepare_exit_to_usermode()
  x86/entry: Use pt_regs_to_thread_info() in syscall entry tracing
  x86/entry: Hide two syscall entry assertions behind CONFIG_DEBUG_ENTRY
  x86/entry: Micro-optimize compat fast syscall arg fetch
  x86/entry: Force inlining of 32-bit syscall code
  x86/entry: Make irqs_disabled checks in exit code depend on lockdep
  x86/entry: Remove unnecessary IRQ twiddling in fast 32-bit syscalls
  x86/asm: Remove thread_info.sysenter_return
  x86/entry/32: Re-implement SYSENTER using the new C path
  x86/entry/32: Switch INT80 to the new C syscall path
  x86/entry/32: Open-code return tracking from fork and kthreads
  x86/entry/compat: Implement opportunistic SYSRETL for compat syscalls
  x86/vdso/compat: Wire up SYSENTER and SYSCSALL for compat userspace
  ...

arch/x86/Kconfig

@@ -2027,6 +2027,55 @@ config COMPAT_VDSO
 	  If unsure, say N: if you are compiling your own kernel, you
 	  are unlikely to be using a buggy version of glibc.
 
+choice
+	prompt "vsyscall table for legacy applications"
+	depends on X86_64
+	default LEGACY_VSYSCALL_EMULATE
+	help
+	  Legacy user code that does not know how to find the vDSO expects
+	  to be able to issue three syscalls by calling fixed addresses in
+	  kernel space. Since this location is not randomized with ASLR,
+	  it can be used to assist security vulnerability exploitation.
+
+	  This setting can be changed at boot time via the kernel command
+	  line parameter vsyscall=[native|emulate|none].
+
+	  On a system with recent enough glibc (2.14 or newer) and no
+	  static binaries, you can say None without a performance penalty
+	  to improve security.
+
+	  If unsure, select "Emulate".
+
+	config LEGACY_VSYSCALL_NATIVE
+		bool "Native"
+		help
+		  Actual executable code is located in the fixed vsyscall
+		  address mapping, implementing time() efficiently. Since
+		  this makes the mapping executable, it can be used during
+		  security vulnerability exploitation (traditionally as
+		  ROP gadgets). This configuration is not recommended.
+
+	config LEGACY_VSYSCALL_EMULATE
+		bool "Emulate"
+		help
+		  The kernel traps and emulates calls into the fixed
+		  vsyscall address mapping. This makes the mapping
+		  non-executable, but it still contains known contents,
+		  which could be used in certain rare security vulnerability
+		  exploits. This configuration is recommended when userspace
+		  still uses the vsyscall area.
+
+	config LEGACY_VSYSCALL_NONE
+		bool "None"
+		help
+		  There will be no vsyscall mapping at all. This will
+		  eliminate any risk of ASLR bypass due to the vsyscall
+		  fixed address mapping. Attempts to use the vsyscalls
+		  will be reported to dmesg, so that either old or
+		  malicious userspace programs can be identified.
+
+endchoice
+
 config CMDLINE_BOOL
 	bool "Built-in kernel command line"
 	---help---

arch/x86/Makefile

@@ -159,6 +159,12 @@ endif
 sp-$(CONFIG_X86_32) := esp
 sp-$(CONFIG_X86_64) := rsp
 
+# do binutils support CFI?
+cfi := $(call as-instr,.cfi_startproc\n.cfi_rel_offset $(sp-y)$(comma)0\n.cfi_endproc,-DCONFIG_AS_CFI=1)
+# is .cfi_signal_frame supported too?
+cfi-sigframe := $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1)
+cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTIONS=1)
+
 # does binutils support specific instructions?
 asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1)
 asinstr += $(call as-instr,pshufb %xmm0$(comma)%xmm0,-DCONFIG_AS_SSSE3=1)
@@ -166,8 +172,8 @@ asinstr += $(call as-instr,crc32l %eax$(comma)%eax,-DCONFIG_AS_CRC32=1)
 avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1)
 avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1)
 
-KBUILD_AFLAGS += $(asinstr) $(avx_instr) $(avx2_instr)
-KBUILD_CFLAGS += $(asinstr) $(avx_instr) $(avx2_instr)
+KBUILD_AFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr)
+KBUILD_CFLAGS += $(cfi) $(cfi-sigframe) $(cfi-sections) $(asinstr) $(avx_instr) $(avx2_instr)
 
 LDFLAGS := -m elf_$(UTS_MACHINE)
 

arch/x86/entry/common.c

@@ -24,10 +24,19 @@
 
 #include <asm/desc.h>
 #include <asm/traps.h>
+#include <asm/vdso.h>
+#include <asm/uaccess.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
 
+static struct thread_info *pt_regs_to_thread_info(struct pt_regs *regs)
+{
+	unsigned long top_of_stack =
+		(unsigned long)(regs + 1) + TOP_OF_KERNEL_STACK_PADDING;
+	return (struct thread_info *)(top_of_stack - THREAD_SIZE);
+}
+
 #ifdef CONFIG_CONTEXT_TRACKING
 /* Called on entry from user mode with IRQs off. */
 __visible void enter_from_user_mode(void)
@@ -66,13 +75,14 @@ static void do_audit_syscall_entry(struct pt_regs *regs, u32 arch)
  */
 unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch)
 {
+	struct thread_info *ti = pt_regs_to_thread_info(regs);
 	unsigned long ret = 0;
 	u32 work;
 
-	BUG_ON(regs != task_pt_regs(current));
+	if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
+		BUG_ON(regs != task_pt_regs(current));
 
-	work = ACCESS_ONCE(current_thread_info()->flags) &
-		_TIF_WORK_SYSCALL_ENTRY;
+	work = ACCESS_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY;
 
 #ifdef CONFIG_CONTEXT_TRACKING
 	/*
@@ -154,11 +164,12 @@ unsigned long syscall_trace_enter_phase1(struct pt_regs *regs, u32 arch)
 long syscall_trace_enter_phase2(struct pt_regs *regs, u32 arch,
 				unsigned long phase1_result)
 {
+	struct thread_info *ti = pt_regs_to_thread_info(regs);
 	long ret = 0;
-	u32 work = ACCESS_ONCE(current_thread_info()->flags) &
-		_TIF_WORK_SYSCALL_ENTRY;
+	u32 work = ACCESS_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY;
 
-	BUG_ON(regs != task_pt_regs(current));
+	if (IS_ENABLED(CONFIG_DEBUG_ENTRY))
+		BUG_ON(regs != task_pt_regs(current));
 
 	/*
 	 * If we stepped into a sysenter/syscall insn, it trapped in
@@ -207,19 +218,12 @@ long syscall_trace_enter(struct pt_regs *regs)
 		return syscall_trace_enter_phase2(regs, arch, phase1_result);
 }
 
-static struct thread_info *pt_regs_to_thread_info(struct pt_regs *regs)
-{
-	unsigned long top_of_stack =
-		(unsigned long)(regs + 1) + TOP_OF_KERNEL_STACK_PADDING;
-	return (struct thread_info *)(top_of_stack - THREAD_SIZE);
-}
+#define EXIT_TO_USERMODE_LOOP_FLAGS				\
+	(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE |	\
+	 _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY)
 
-/* Called with IRQs disabled. */
-__visible void prepare_exit_to_usermode(struct pt_regs *regs)
+static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
 {
-	if (WARN_ON(!irqs_disabled()))
-		local_irq_disable();
-
 	/*
 	 * In order to return to user mode, we need to have IRQs off with
 	 * none of _TIF_SIGPENDING, _TIF_NOTIFY_RESUME, _TIF_USER_RETURN_NOTIFY,
@@ -229,14 +233,6 @@ __visible void prepare_exit_to_usermode(struct pt_regs *regs)
 	 * work to clear some of the flags can sleep.
 	 */
 	while (true) {
-		u32 cached_flags =
-			READ_ONCE(pt_regs_to_thread_info(regs)->flags);
-
-		if (!(cached_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME |
-				      _TIF_UPROBE | _TIF_NEED_RESCHED |
-				      _TIF_USER_RETURN_NOTIFY)))
-			break;
-
 		/* We have work to do. */
 		local_irq_enable();
 
@@ -260,50 +256,81 @@ __visible void prepare_exit_to_usermode(struct pt_regs *regs)
 
 		/* Disable IRQs and retry */
 		local_irq_disable();
+
+		cached_flags = READ_ONCE(pt_regs_to_thread_info(regs)->flags);
+
+		if (!(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
+			break;
+
 	}
+}
+
+/* Called with IRQs disabled. */
+__visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
+{
+	u32 cached_flags;
+
+	if (IS_ENABLED(CONFIG_PROVE_LOCKING) && WARN_ON(!irqs_disabled()))
+		local_irq_disable();
+
+	lockdep_sys_exit();
+
+	cached_flags =
+		READ_ONCE(pt_regs_to_thread_info(regs)->flags);
+
+	if (unlikely(cached_flags & EXIT_TO_USERMODE_LOOP_FLAGS))
+		exit_to_usermode_loop(regs, cached_flags);
 
 	user_enter();
 }
 
+#define SYSCALL_EXIT_WORK_FLAGS				\
+	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT |	\
+	 _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT)
+
+static void syscall_slow_exit_work(struct pt_regs *regs, u32 cached_flags)
+{
+	bool step;
+
+	audit_syscall_exit(regs);
+
+	if (cached_flags & _TIF_SYSCALL_TRACEPOINT)
+		trace_sys_exit(regs, regs->ax);
+
+	/*
+	 * If TIF_SYSCALL_EMU is set, we only get here because of
+	 * TIF_SINGLESTEP (i.e. this is PTRACE_SYSEMU_SINGLESTEP).
+	 * We already reported this syscall instruction in
+	 * syscall_trace_enter().
+	 */
+	step = unlikely(
+		(cached_flags & (_TIF_SINGLESTEP | _TIF_SYSCALL_EMU))
+		== _TIF_SINGLESTEP);
+	if (step || cached_flags & _TIF_SYSCALL_TRACE)
+		tracehook_report_syscall_exit(regs, step);
+}
+
 /*
  * Called with IRQs on and fully valid regs.  Returns with IRQs off in a
  * state such that we can immediately switch to user mode.
  */
-__visible void syscall_return_slowpath(struct pt_regs *regs)
+__visible inline void syscall_return_slowpath(struct pt_regs *regs)
 {
 	struct thread_info *ti = pt_regs_to_thread_info(regs);
 	u32 cached_flags = READ_ONCE(ti->flags);
-	bool step;
 
 	CT_WARN_ON(ct_state() != CONTEXT_KERNEL);
 
-	if (WARN(irqs_disabled(), "syscall %ld left IRQs disabled",
-		 regs->orig_ax))
+	if (IS_ENABLED(CONFIG_PROVE_LOCKING) &&
+	    WARN(irqs_disabled(), "syscall %ld left IRQs disabled", regs->orig_ax))
 		local_irq_enable();
 
 	/*
 	 * First do one-time work.  If these work items are enabled, we
 	 * want to run them exactly once per syscall exit with IRQs on.
 	 */
-	if (cached_flags & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT |
-			    _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT)) {
-		audit_syscall_exit(regs);
-
-		if (cached_flags & _TIF_SYSCALL_TRACEPOINT)
-			trace_sys_exit(regs, regs->ax);
-
-		/*
-		 * If TIF_SYSCALL_EMU is set, we only get here because of
-		 * TIF_SINGLESTEP (i.e. this is PTRACE_SYSEMU_SINGLESTEP).
-		 * We already reported this syscall instruction in
-		 * syscall_trace_enter().
-		 */
-		step = unlikely(
-			(cached_flags & (_TIF_SINGLESTEP | _TIF_SYSCALL_EMU))
-			== _TIF_SINGLESTEP);
-		if (step || cached_flags & _TIF_SYSCALL_TRACE)
-			tracehook_report_syscall_exit(regs, step);
-	}
+	if (unlikely(cached_flags & SYSCALL_EXIT_WORK_FLAGS))
+		syscall_slow_exit_work(regs, cached_flags);
 
 #ifdef CONFIG_COMPAT
 	/*
@@ -316,3 +343,144 @@ __visible void syscall_return_slowpath(struct pt_regs *regs)
 	local_irq_disable();
 	prepare_exit_to_usermode(regs);
 }
+
+#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
+/*
+ * Does a 32-bit syscall.  Called with IRQs on and does all entry and
+ * exit work and returns with IRQs off.  This function is extremely hot
+ * in workloads that use it, and it's usually called from
+ * do_fast_syscall_32, so forcibly inline it to improve performance.
+ */
+#ifdef CONFIG_X86_32
+/* 32-bit kernels use a trap gate for INT80, and the asm code calls here. */
+__visible
+#else
+/* 64-bit kernels use do_syscall_32_irqs_off() instead. */
+static
+#endif
+__always_inline void do_syscall_32_irqs_on(struct pt_regs *regs)
+{
+	struct thread_info *ti = pt_regs_to_thread_info(regs);
+	unsigned int nr = (unsigned int)regs->orig_ax;
+
+#ifdef CONFIG_IA32_EMULATION
+	ti->status |= TS_COMPAT;
+#endif
+
+	if (READ_ONCE(ti->flags) & _TIF_WORK_SYSCALL_ENTRY) {
+		/*
+		 * Subtlety here: if ptrace pokes something larger than
+		 * 2^32-1 into orig_ax, this truncates it.  This may or
+		 * may not be necessary, but it matches the old asm
+		 * behavior.
+		 */
+		nr = syscall_trace_enter(regs);
+	}
+
+	if (likely(nr < IA32_NR_syscalls)) {
+		/*
+		 * It's possible that a 32-bit syscall implementation
+		 * takes a 64-bit parameter but nonetheless assumes that
+		 * the high bits are zero.  Make sure we zero-extend all
+		 * of the args.
+		 */
+		regs->ax = ia32_sys_call_table[nr](
+			(unsigned int)regs->bx, (unsigned int)regs->cx,
+			(unsigned int)regs->dx, (unsigned int)regs->si,
+			(unsigned int)regs->di, (unsigned int)regs->bp);
+	}
+
+	syscall_return_slowpath(regs);
+}
+
+#ifdef CONFIG_X86_64
+/* Handles INT80 on 64-bit kernels */
+__visible void do_syscall_32_irqs_off(struct pt_regs *regs)
+{
+	local_irq_enable();
+	do_syscall_32_irqs_on(regs);
+}
+#endif
+
+/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */
+__visible long do_fast_syscall_32(struct pt_regs *regs)
+{
+	/*
+	 * Called using the internal vDSO SYSENTER/SYSCALL32 calling
+	 * convention.  Adjust regs so it looks like we entered using int80.
+	 */
+
+	unsigned long landing_pad = (unsigned long)current->mm->context.vdso +
+		vdso_image_32.sym_int80_landing_pad;
+
+	/*
+	 * SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward
+	 * so that 'regs->ip -= 2' lands back on an int $0x80 instruction.
+	 * Fix it up.
+	 */
+	regs->ip = landing_pad;
+
+	/*
+	 * Fetch ECX from where the vDSO stashed it.
+	 *
+	 * WARNING: We are in CONTEXT_USER and RCU isn't paying attention!
+	 */
+	local_irq_enable();
+	if (
+#ifdef CONFIG_X86_64
+		/*
+		 * Micro-optimization: the pointer we're following is explicitly
+		 * 32 bits, so it can't be out of range.
+		 */
+		__get_user(*(u32 *)&regs->cx,
+			    (u32 __user __force *)(unsigned long)(u32)regs->sp)
+#else
+		get_user(*(u32 *)&regs->cx,
+			 (u32 __user __force *)(unsigned long)(u32)regs->sp)
+#endif
+		) {
+
+		/* User code screwed up. */
+		local_irq_disable();
+		regs->ax = -EFAULT;
+#ifdef CONFIG_CONTEXT_TRACKING
+		enter_from_user_mode();
+#endif
+		prepare_exit_to_usermode(regs);
+		return 0;	/* Keep it simple: use IRET. */
+	}
+
+	/* Now this is just like a normal syscall. */
+	do_syscall_32_irqs_on(regs);
+
+#ifdef CONFIG_X86_64
+	/*
+	 * Opportunistic SYSRETL: if possible, try to return using SYSRETL.
+	 * SYSRETL is available on all 64-bit CPUs, so we don't need to
+	 * bother with SYSEXIT.
+	 *
+	 * Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP,
+	 * because the ECX fixup above will ensure that this is essentially
+	 * never the case.
+	 */
+	return regs->cs == __USER32_CS && regs->ss == __USER_DS &&
+		regs->ip == landing_pad &&
+		(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF)) == 0;
+#else
+	/*
+	 * Opportunistic SYSEXIT: if possible, try to return using SYSEXIT.
+	 *
+	 * Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP,
+	 * because the ECX fixup above will ensure that this is essentially
+	 * never the case.
+	 *
+	 * We don't allow syscalls at all from VM86 mode, but we still
+	 * need to check VM, because we might be returning from sys_vm86.
+	 */
+	return static_cpu_has(X86_FEATURE_SEP) &&
+		regs->cs == __USER_CS && regs->ss == __USER_DS &&
+		regs->ip == landing_pad &&
+		(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)) == 0;
+#endif
+}
+#endif

arch/x86/entry/entry_32.S

@@ -3,7 +3,7 @@
  *
  * entry_32.S contains the system-call and low-level fault and trap handling routines.
  *
- * Stack layout in 'syscall_exit':
+ * Stack layout while running C code:
  *	ptrace needs to have all registers on the stack.
  *	If the order here is changed, it needs to be
  *	updated in fork.c:copy_process(), signal.c:do_signal(),
@@ -153,13 +153,13 @@
 
 #endif /* CONFIG_X86_32_LAZY_GS */
 
-.macro SAVE_ALL
+.macro SAVE_ALL pt_regs_ax=%eax
 	cld
 	PUSH_GS
 	pushl	%fs
 	pushl	%es
 	pushl	%ds
-	pushl	%eax
+	pushl	\pt_regs_ax
 	pushl	%ebp
 	pushl	%edi
 	pushl	%esi
@@ -211,7 +211,11 @@ ENTRY(ret_from_fork)
 	popl	%eax
 	pushl	$0x0202				# Reset kernel eflags
 	popfl
-	jmp	syscall_exit
+
+	/* When we fork, we trace the syscall return in the child, too. */
+	movl    %esp, %eax
+	call    syscall_return_slowpath
+	jmp     restore_all
 END(ret_from_fork)
 
 ENTRY(ret_from_kernel_thread)
@@ -224,7 +228,15 @@ ENTRY(ret_from_kernel_thread)
 	movl	PT_EBP(%esp), %eax
 	call	*PT_EBX(%esp)
 	movl	$0, PT_EAX(%esp)
-	jmp	syscall_exit
+
+	/*
+	 * Kernel threads return to userspace as if returning from a syscall.
+	 * We should check whether anything actually uses this path and, if so,
+	 * consider switching it over to ret_from_fork.
+	 */
+	movl    %esp, %eax
+	call    syscall_return_slowpath
+	jmp     restore_all
 ENDPROC(ret_from_kernel_thread)
 
 /*
@@ -255,7 +267,6 @@ ret_from_intr:
 	jb	resume_kernel			# not returning to v8086 or userspace
 
 ENTRY(resume_userspace)
-	LOCKDEP_SYS_EXIT
 	DISABLE_INTERRUPTS(CLBR_ANY)
 	TRACE_IRQS_OFF
 	movl	%esp, %eax
@@ -276,76 +287,47 @@ need_resched:
 END(resume_kernel)
 #endif
 
-/*
- * SYSENTER_RETURN points to after the SYSENTER instruction
- * in the vsyscall page.  See vsyscall-sysentry.S, which defines
- * the symbol.
- */
-
 	# SYSENTER  call handler stub
 ENTRY(entry_SYSENTER_32)
 	movl	TSS_sysenter_sp0(%esp), %esp
 sysenter_past_esp:
+	pushl	$__USER_DS		/* pt_regs->ss */
+	pushl	%ecx			/* pt_regs->cx */
+	pushfl				/* pt_regs->flags (except IF = 0) */
+	orl	$X86_EFLAGS_IF, (%esp)	/* Fix IF */
+	pushl	$__USER_CS		/* pt_regs->cs */
+	pushl	$0			/* pt_regs->ip = 0 (placeholder) */
+	pushl	%eax			/* pt_regs->orig_ax */
+	SAVE_ALL pt_regs_ax=$-ENOSYS	/* save rest */
+
 	/*
-	 * Interrupts are disabled here, but we can't trace it until
-	 * enough kernel state to call TRACE_IRQS_OFF can be called - but
-	 * we immediately enable interrupts at that point anyway.
-	 */
-	pushl	$__USER_DS
-	pushl	%ebp
-	pushfl
-	orl	$X86_EFLAGS_IF, (%esp)
-	pushl	$__USER_CS
-	/*
-	 * Push current_thread_info()->sysenter_return to the stack.
-	 * A tiny bit of offset fixup is necessary: TI_sysenter_return
-	 * is relative to thread_info, which is at the bottom of the
-	 * kernel stack page.  4*4 means the 4 words pushed above;
-	 * TOP_OF_KERNEL_STACK_PADDING takes us to the top of the stack;
-	 * and THREAD_SIZE takes us to the bottom.
+	 * User mode is traced as though IRQs are on, and SYSENTER
+	 * turned them off.
 	 */
-	pushl	((TI_sysenter_return) - THREAD_SIZE + TOP_OF_KERNEL_STACK_PADDING + 4*4)(%esp)
-
-	pushl	%eax
-	SAVE_ALL
-	ENABLE_INTERRUPTS(CLBR_NONE)
-
-/*
- * Load the potential sixth argument from user stack.
- * Careful about security.
- */
-	cmpl	$__PAGE_OFFSET-3, %ebp
-	jae	syscall_fault
-	ASM_STAC
-1:	movl	(%ebp), %ebp
-	ASM_CLAC
-	movl	%ebp, PT_EBP(%esp)
-	_ASM_EXTABLE(1b, syscall_fault)
+	TRACE_IRQS_OFF
 
-	GET_THREAD_INFO(%ebp)
+	movl	%esp, %eax
+	call	do_fast_syscall_32
+	testl	%eax, %eax
+	jz	.Lsyscall_32_done
 
-	testl	$_TIF_WORK_SYSCALL_ENTRY, TI_flags(%ebp)
-	jnz	syscall_trace_entry
-sysenter_do_call:
-	cmpl	$(NR_syscalls), %eax
-	jae	sysenter_badsys
-	call	*sys_call_table(, %eax, 4)
-sysenter_after_call:
-	movl	%eax, PT_EAX(%esp)
-	LOCKDEP_SYS_EXIT
-	DISABLE_INTERRUPTS(CLBR_ANY)
-	TRACE_IRQS_OFF
-	movl	TI_flags(%ebp), %ecx
-	testl	$_TIF_ALLWORK_MASK, %ecx
-	jnz	syscall_exit_work_irqs_off
-sysenter_exit:
-/* if something modifies registers it must also disable sysexit */
-	movl	PT_EIP(%esp), %edx
-	movl	PT_OLDESP(%esp), %ecx
-	xorl	%ebp, %ebp
-	TRACE_IRQS_ON
+/* Opportunistic SYSEXIT */
+	TRACE_IRQS_ON			/* User mode traces as IRQs on. */
+	movl	PT_EIP(%esp), %edx	/* pt_regs->ip */
+	movl	PT_OLDESP(%esp), %ecx	/* pt_regs->sp */
 1:	mov	PT_FS(%esp), %fs
 	PTGS_TO_GS
+	popl	%ebx			/* pt_regs->bx */
+	addl	$2*4, %esp		/* skip pt_regs->cx and pt_regs->dx */
+	popl	%esi			/* pt_regs->si */
+	popl	%edi			/* pt_regs->di */
+	popl	%ebp			/* pt_regs->bp */
+	popl	%eax			/* pt_regs->ax */
+
+	/*
+	 * Return back to the vDSO, which will pop ecx and edx.
+	 * Don't bother with DS and ES (they already contain __USER_DS).
+	 */
 	ENABLE_INTERRUPTS_SYSEXIT
 
 .pushsection .fixup, "ax"
@@ -359,21 +341,18 @@ ENDPROC(entry_SYSENTER_32)
 	# system call handler stub
 ENTRY(entry_INT80_32)
 	ASM_CLAC
-	pushl	%eax				# save orig_eax
-	SAVE_ALL
-	GET_THREAD_INFO(%ebp)
-						# system call tracing in operation / emulation
-	testl	$_TIF_WORK_SYSCALL_ENTRY, TI_flags(%ebp)
-	jnz	syscall_trace_entry
-	cmpl	$(NR_syscalls), %eax
-	jae	syscall_badsys
-syscall_call:
-	call	*sys_call_table(, %eax, 4)
-syscall_after_call:
-	movl	%eax, PT_EAX(%esp)		# store the return value
-syscall_exit:
-	LOCKDEP_SYS_EXIT
-	jmp	syscall_exit_work
+	pushl	%eax			/* pt_regs->orig_ax */
+	SAVE_ALL pt_regs_ax=$-ENOSYS	/* save rest */
+
+	/*
+	 * User mode is traced as though IRQs are on.  Unlike the 64-bit
+	 * case, INT80 is a trap gate on 32-bit kernels, so interrupts
+	 * are already on (unless user code is messing around with iopl).
+	 */
+
+	movl	%esp, %eax
+	call	do_syscall_32_irqs_on
+.Lsyscall_32_done:
 
 restore_all:
 	TRACE_IRQS_IRET
@@ -450,47 +429,6 @@ ldt_ss:
 #endif
 ENDPROC(entry_INT80_32)
 
-	# perform syscall exit tracing
-	ALIGN
-syscall_trace_entry:
-	movl	$-ENOSYS, PT_EAX(%esp)
-	movl	%esp, %eax
-	call	syscall_trace_enter
-	/* What it returned is what we'll actually use.  */
-	cmpl	$(NR_syscalls), %eax
-	jnae	syscall_call
-	jmp	syscall_exit
-END(syscall_trace_entry)
-
-	# perform syscall exit tracing
-	ALIGN
-syscall_exit_work_irqs_off:
-	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_ANY)
-
-syscall_exit_work:
-	movl	%esp, %eax
-	call	syscall_return_slowpath
-	jmp	restore_all
-END(syscall_exit_work)
-
-syscall_fault:
-	ASM_CLAC
-	GET_THREAD_INFO(%ebp)
-	movl	$-EFAULT, PT_EAX(%esp)
-	jmp	resume_userspace
-END(syscall_fault)
-
-syscall_badsys:
-	movl	$-ENOSYS, %eax
-	jmp	syscall_after_call
-END(syscall_badsys)
-
-sysenter_badsys:
-	movl	$-ENOSYS, %eax
-	jmp	sysenter_after_call
-END(sysenter_badsys)
-
 .macro FIXUP_ESPFIX_STACK
 /*
  * Switch back for ESPFIX stack to the normal zerobased stack

arch/x86/entry/entry_64.S

@@ -391,20 +391,16 @@ GLOBAL(stub_execveat)
 	jmp	return_from_execve
 END(stub_execveat)
 
-#if defined(CONFIG_X86_X32_ABI) || defined(CONFIG_IA32_EMULATION)
+#if defined(CONFIG_X86_X32_ABI)
 	.align	8
 GLOBAL(stub_x32_execve)
-GLOBAL(stub32_execve)
 	call	compat_sys_execve
 	jmp	return_from_execve
-END(stub32_execve)
 END(stub_x32_execve)
 	.align	8
 GLOBAL(stub_x32_execveat)
-GLOBAL(stub32_execveat)
 	call	compat_sys_execveat
 	jmp	return_from_execve
-END(stub32_execveat)
 END(stub_x32_execveat)
 #endif
 
@@ -557,7 +553,6 @@ ret_from_intr:
 	jz	retint_kernel
 
 	/* Interrupt came from user space */
-	LOCKDEP_SYS_EXIT_IRQ
 GLOBAL(retint_user)
 	mov	%rsp,%rdi
 	call	prepare_exit_to_usermode
@@ -587,7 +582,7 @@ retint_kernel:
  * At this label, code paths which return to kernel and to user,
  * which come from interrupts/exception and from syscalls, merge.
  */
-restore_regs_and_iret:
+GLOBAL(restore_regs_and_iret)
 	RESTORE_EXTRA_REGS
 restore_c_regs_and_iret:
 	RESTORE_C_REGS

arch/x86/entry/entry_64_compat.S

@@ -16,16 +16,6 @@
 #include <linux/linkage.h>
 #include <linux/err.h>
 
-/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
-#include <linux/elf-em.h>
-#define AUDIT_ARCH_I386		(EM_386|__AUDIT_ARCH_LE)
-#define __AUDIT_ARCH_LE		0x40000000
-
-#ifndef CONFIG_AUDITSYSCALL
-# define sysexit_audit		ia32_ret_from_sys_call_irqs_off
-# define sysretl_audit		ia32_ret_from_sys_call_irqs_off
-#endif
-
 	.section .entry.text, "ax"
 
 #ifdef CONFIG_PARAVIRT
@@ -58,219 +48,87 @@ ENDPROC(native_usergs_sysret32)
  * with the int 0x80 path.
  */
 ENTRY(entry_SYSENTER_compat)
-	/*
-	 * Interrupts are off on entry.
-	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
-	 * it is too small to ever cause noticeable irq latency.
-	 */
+	/* Interrupts are off on entry. */
 	SWAPGS_UNSAFE_STACK
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
-	ENABLE_INTERRUPTS(CLBR_NONE)
 
-	/* Zero-extending 32-bit regs, do not remove */
-	movl	%ebp, %ebp
+	/*
+	 * User tracing code (ptrace or signal handlers) might assume that
+	 * the saved RAX contains a 32-bit number when we're invoking a 32-bit
+	 * syscall.  Just in case the high bits are nonzero, zero-extend
+	 * the syscall number.  (This could almost certainly be deleted
+	 * with no ill effects.)
+	 */
 	movl	%eax, %eax
 
-	movl	ASM_THREAD_INFO(TI_sysenter_return, %rsp, 0), %r10d
-
 	/* Construct struct pt_regs on stack */
 	pushq	$__USER32_DS		/* pt_regs->ss */
-	pushq	%rbp			/* pt_regs->sp */
-	pushfq				/* pt_regs->flags */
+	pushq	%rcx			/* pt_regs->sp */
+
+	/*
+	 * Push flags.  This is nasty.  First, interrupts are currently
+	 * off, but we need pt_regs->flags to have IF set.  Second, even
+	 * if TF was set when SYSENTER started, it's clear by now.  We fix
+	 * that later using TIF_SINGLESTEP.
+	 */
+	pushfq				/* pt_regs->flags (except IF = 0) */
+	orl	$X86_EFLAGS_IF, (%rsp)	/* Fix saved flags */
+	ASM_CLAC			/* Clear AC after saving FLAGS */
+
 	pushq	$__USER32_CS		/* pt_regs->cs */
-	pushq	%r10			/* pt_regs->ip = thread_info->sysenter_return */
+	xorq    %r8,%r8
+	pushq	%r8			/* pt_regs->ip = 0 (placeholder) */
 	pushq	%rax			/* pt_regs->orig_ax */
 	pushq	%rdi			/* pt_regs->di */
 	pushq	%rsi			/* pt_regs->si */
 	pushq	%rdx			/* pt_regs->dx */
-	pushq	%rcx			/* pt_regs->cx */
+	pushq	%rcx			/* pt_regs->cx (will be overwritten) */
 	pushq	$-ENOSYS		/* pt_regs->ax */
+	pushq   %r8                     /* pt_regs->r8  = 0 */
+	pushq   %r8                     /* pt_regs->r9  = 0 */
+	pushq   %r8                     /* pt_regs->r10 = 0 */
+	pushq   %r8                     /* pt_regs->r11 = 0 */
+	pushq   %rbx                    /* pt_regs->rbx */
+	pushq   %rbp                    /* pt_regs->rbp */
+	pushq   %r8                     /* pt_regs->r12 = 0 */
+	pushq   %r8                     /* pt_regs->r13 = 0 */
+	pushq   %r8                     /* pt_regs->r14 = 0 */
+	pushq   %r8                     /* pt_regs->r15 = 0 */
 	cld
-	sub	$(10*8), %rsp /* pt_regs->r8-11, bp, bx, r12-15 not saved */
-
-	/*
-	 * no need to do an access_ok check here because rbp has been
-	 * 32-bit zero extended
-	 */
-	ASM_STAC
-1:	movl	(%rbp), %ebp
-	_ASM_EXTABLE(1b, ia32_badarg)
-	ASM_CLAC
 
 	/*
 	 * Sysenter doesn't filter flags, so we need to clear NT
 	 * ourselves.  To save a few cycles, we can check whether
 	 * NT was set instead of doing an unconditional popfq.
+	 * This needs to happen before enabling interrupts so that
+	 * we don't get preempted with NT set.
+	 *
+	 * NB.: sysenter_fix_flags is a label with the code under it moved
+	 * out-of-line as an optimization: NT is unlikely to be set in the
+	 * majority of the cases and instead of polluting the I$ unnecessarily,
+	 * we're keeping that code behind a branch which will predict as
+	 * not-taken and therefore its instructions won't be fetched.
 	 */
 	testl	$X86_EFLAGS_NT, EFLAGS(%rsp)
 	jnz	sysenter_fix_flags
 sysenter_flags_fixed:
 
-	orl	$TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
-	testl	$_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz	sysenter_tracesys
-
-sysenter_do_call:
-	/* 32-bit syscall -> 64-bit C ABI argument conversion */
-	movl	%edi, %r8d		/* arg5 */
-	movl	%ebp, %r9d		/* arg6 */
-	xchg	%ecx, %esi		/* rsi:arg2, rcx:arg4 */
-	movl	%ebx, %edi		/* arg1 */
-	movl	%edx, %edx		/* arg3 (zero extension) */
-sysenter_dispatch:
-	cmpq	$(IA32_NR_syscalls-1), %rax
-	ja	1f
-	call	*ia32_sys_call_table(, %rax, 8)
-	movq	%rax, RAX(%rsp)
-1:
-	DISABLE_INTERRUPTS(CLBR_NONE)
-	TRACE_IRQS_OFF
-	testl	$_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz	sysexit_audit
-sysexit_from_sys_call:
 	/*
-	 * NB: SYSEXIT is not obviously safe for 64-bit kernels -- an
-	 * NMI between STI and SYSEXIT has poorly specified behavior,
-	 * and and NMI followed by an IRQ with usergs is fatal.  So
-	 * we just pretend we're using SYSEXIT but we really use
-	 * SYSRETL instead.
-	 *
-	 * This code path is still called 'sysexit' because it pairs
-	 * with 'sysenter' and it uses the SYSENTER calling convention.
+	 * User mode is traced as though IRQs are on, and SYSENTER
+	 * turned them off.
 	 */
-	andl	$~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
-	movl	RIP(%rsp), %ecx		/* User %eip */
-	movq    RAX(%rsp), %rax
-	movl	RSI(%rsp), %esi
-	movl	RDI(%rsp), %edi
-	xorl	%edx, %edx		/* Do not leak kernel information */
-	xorq	%r8, %r8
-	xorq	%r9, %r9
-	xorq	%r10, %r10
-	movl	EFLAGS(%rsp), %r11d	/* User eflags */
-	TRACE_IRQS_ON
-
-	/*
-	 * SYSRETL works even on Intel CPUs.  Use it in preference to SYSEXIT,
-	 * since it avoids a dicey window with interrupts enabled.
-	 */
-	movl	RSP(%rsp), %esp
-
-	/*
-	 * USERGS_SYSRET32 does:
-	 *  gsbase = user's gs base
-	 *  eip = ecx
-	 *  rflags = r11
-	 *  cs = __USER32_CS
-	 *  ss = __USER_DS
-	 *
-	 * The prologue set RIP(%rsp) to VDSO32_SYSENTER_RETURN, which does:
-	 *
-	 *  pop %ebp
-	 *  pop %edx
-	 *  pop %ecx
-	 *
-	 * Therefore, we invoke SYSRETL with EDX and R8-R10 zeroed to
-	 * avoid info leaks.  R11 ends up with VDSO32_SYSENTER_RETURN's
-	 * address (already known to user code), and R12-R15 are
-	 * callee-saved and therefore don't contain any interesting
-	 * kernel data.
-	 */
-	USERGS_SYSRET32
-
-#ifdef CONFIG_AUDITSYSCALL
-	.macro auditsys_entry_common
-	/*
-	 * At this point, registers hold syscall args in the 32-bit syscall ABI:
-	 * EAX is syscall number, the 6 args are in EBX,ECX,EDX,ESI,EDI,EBP.
-	 *
-	 * We want to pass them to __audit_syscall_entry(), which is a 64-bit
-	 * C function with 5 parameters, so shuffle them to match what
-	 * the function expects: RDI,RSI,RDX,RCX,R8.
-	 */
-	movl	%esi, %r8d		/* arg5 (R8 ) <= 4th syscall arg (ESI) */
-	xchg	%ecx, %edx		/* arg4 (RCX) <= 3rd syscall arg (EDX) */
-					/* arg3 (RDX) <= 2nd syscall arg (ECX) */
-	movl	%ebx, %esi		/* arg2 (RSI) <= 1st syscall arg (EBX) */
-	movl	%eax, %edi		/* arg1 (RDI) <= syscall number  (EAX) */
-	call	__audit_syscall_entry
-
-	/*
-	 * We are going to jump back to the syscall dispatch code.
-	 * Prepare syscall args as required by the 64-bit C ABI.
-	 * Registers clobbered by __audit_syscall_entry() are
-	 * loaded from pt_regs on stack:
-	 */
-	movl	ORIG_RAX(%rsp), %eax	/* syscall number */
-	movl	%ebx, %edi		/* arg1 */
-	movl	RCX(%rsp), %esi		/* arg2 */
-	movl	RDX(%rsp), %edx		/* arg3 */
-	movl	RSI(%rsp), %ecx		/* arg4 */
-	movl	RDI(%rsp), %r8d		/* arg5 */
-	.endm
-
-	.macro auditsys_exit exit
-	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_NONE)
-	testl	$(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz	ia32_ret_from_sys_call
-	movl	%eax, %esi		/* second arg, syscall return value */
-	cmpl	$-MAX_ERRNO, %eax	/* is it an error ? */
-	jbe	1f
-	movslq	%eax, %rsi		/* if error sign extend to 64 bits */
-1:	setbe	%al			/* 1 if error, 0 if not */
-	movzbl	%al, %edi		/* zero-extend that into %edi */
-	call	__audit_syscall_exit
-	movl	$(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %edi
-	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
-	testl	%edi, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jz	\exit
-	xorl	%eax, %eax		/* Do not leak kernel information */
-	movq	%rax, R11(%rsp)
-	movq	%rax, R10(%rsp)
-	movq	%rax, R9(%rsp)
-	movq	%rax, R8(%rsp)
-	jmp	int_ret_from_sys_call_irqs_off
-	.endm
 
-sysenter_auditsys:
-	auditsys_entry_common
-	movl	%ebp, %r9d		/* reload 6th syscall arg */
-	jmp	sysenter_dispatch
-
-sysexit_audit:
-	auditsys_exit sysexit_from_sys_call
-#endif
+	movq	%rsp, %rdi
+	call	do_fast_syscall_32
+	testl	%eax, %eax
+	jz	.Lsyscall_32_done
+	jmp	sysret32_from_system_call
 
 sysenter_fix_flags:
-	pushq	$(X86_EFLAGS_IF|X86_EFLAGS_FIXED)
+	pushq	$X86_EFLAGS_FIXED
 	popfq
 	jmp	sysenter_flags_fixed
-
-sysenter_tracesys:
-#ifdef CONFIG_AUDITSYSCALL
-	testl	$(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jz	sysenter_auditsys
-#endif
-	SAVE_EXTRA_REGS
-	xorl	%eax, %eax		/* Do not leak kernel information */
-	movq	%rax, R11(%rsp)
-	movq	%rax, R10(%rsp)
-	movq	%rax, R9(%rsp)
-	movq	%rax, R8(%rsp)
-	movq	%rsp, %rdi		/* &pt_regs -> arg1 */
-	call	syscall_trace_enter
-
-	/* Reload arg registers from stack. (see sysenter_tracesys) */
-	movl	RCX(%rsp), %ecx
-	movl	RDX(%rsp), %edx
-	movl	RSI(%rsp), %esi
-	movl	RDI(%rsp), %edi
-	movl	%eax, %eax		/* zero extension */
-
-	RESTORE_EXTRA_REGS
-	jmp	sysenter_do_call
 ENDPROC(entry_SYSENTER_compat)
 
 /*
@@ -298,21 +156,14 @@ ENDPROC(entry_SYSENTER_compat)
  * edi  arg5
  * esp  user stack
  * 0(%esp) arg6
- *
- * This is purely a fast path. For anything complicated we use the int 0x80
- * path below. We set up a complete hardware stack frame to share code
- * with the int 0x80 path.
  */
 ENTRY(entry_SYSCALL_compat)
-	/*
-	 * Interrupts are off on entry.
-	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
-	 * it is too small to ever cause noticeable irq latency.
-	 */
+	/* Interrupts are off on entry. */
 	SWAPGS_UNSAFE_STACK
+
+	/* Stash user ESP and switch to the kernel stack. */
 	movl	%esp, %r8d
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
-	ENABLE_INTERRUPTS(CLBR_NONE)
 
 	/* Zero-extending 32-bit regs, do not remove */
 	movl	%eax, %eax
@@ -327,162 +178,67 @@ ENTRY(entry_SYSCALL_compat)
 	pushq	%rdi			/* pt_regs->di */
 	pushq	%rsi			/* pt_regs->si */
 	pushq	%rdx			/* pt_regs->dx */
-	pushq	%rbp			/* pt_regs->cx */
-	movl	%ebp, %ecx
+	pushq	%rcx			/* pt_regs->cx (will be overwritten) */
 	pushq	$-ENOSYS		/* pt_regs->ax */
-	sub	$(10*8), %rsp		/* pt_regs->r8-11, bp, bx, r12-15 not saved */
+	xorq    %r8,%r8
+	pushq   %r8                     /* pt_regs->r8  = 0 */
+	pushq   %r8                     /* pt_regs->r9  = 0 */
+	pushq   %r8                     /* pt_regs->r10 = 0 */
+	pushq   %r8                     /* pt_regs->r11 = 0 */
+	pushq   %rbx                    /* pt_regs->rbx */
+	pushq   %rbp                    /* pt_regs->rbp */
+	pushq   %r8                     /* pt_regs->r12 = 0 */
+	pushq   %r8                     /* pt_regs->r13 = 0 */
+	pushq   %r8                     /* pt_regs->r14 = 0 */
+	pushq   %r8                     /* pt_regs->r15 = 0 */
 
 	/*
-	 * No need to do an access_ok check here because r8 has been
-	 * 32-bit zero extended:
+	 * User mode is traced as though IRQs are on, and SYSENTER
+	 * turned them off.
 	 */
-	ASM_STAC
-1:	movl	(%r8), %r9d
-	_ASM_EXTABLE(1b, ia32_badarg)
-	ASM_CLAC
-	orl	$TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
-	testl	$_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz	cstar_tracesys
-
-cstar_do_call:
-	/* 32-bit syscall -> 64-bit C ABI argument conversion */
-	movl	%edi, %r8d		/* arg5 */
-	/* r9 already loaded */		/* arg6 */
-	xchg	%ecx, %esi		/* rsi:arg2, rcx:arg4 */
-	movl	%ebx, %edi		/* arg1 */
-	movl	%edx, %edx		/* arg3 (zero extension) */
-
-cstar_dispatch:
-	cmpq	$(IA32_NR_syscalls-1), %rax
-	ja	1f
-
-	call	*ia32_sys_call_table(, %rax, 8)
-	movq	%rax, RAX(%rsp)
-1:
-	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
-	testl	$_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz	sysretl_audit
 
-sysretl_from_sys_call:
-	andl	$~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
-	movl	RDX(%rsp), %edx
-	movl	RSI(%rsp), %esi
-	movl	RDI(%rsp), %edi
-	movl	RIP(%rsp), %ecx
-	movl	EFLAGS(%rsp), %r11d
-	movq    RAX(%rsp), %rax
-	xorq	%r10, %r10
-	xorq	%r9, %r9
-	xorq	%r8, %r8
-	TRACE_IRQS_ON
-	movl	RSP(%rsp), %esp
-	/*
-	 * 64-bit->32-bit SYSRET restores eip from ecx,
-	 * eflags from r11 (but RF and VM bits are forced to 0),
-	 * cs and ss are loaded from MSRs.
-	 * (Note: 32-bit->32-bit SYSRET is different: since r11
-	 * does not exist, it merely sets eflags.IF=1).
+	movq	%rsp, %rdi
+	call	do_fast_syscall_32
+	testl	%eax, %eax
+	jz	.Lsyscall_32_done
+
+	/* Opportunistic SYSRET */
+sysret32_from_system_call:
+	TRACE_IRQS_ON			/* User mode traces as IRQs on. */
+	movq	RBX(%rsp), %rbx		/* pt_regs->rbx */
+	movq	RBP(%rsp), %rbp		/* pt_regs->rbp */
+	movq	EFLAGS(%rsp), %r11	/* pt_regs->flags (in r11) */
+	movq	RIP(%rsp), %rcx		/* pt_regs->ip (in rcx) */
+	addq	$RAX, %rsp		/* Skip r8-r15 */
+	popq	%rax			/* pt_regs->rax */
+	popq	%rdx			/* Skip pt_regs->cx */
+	popq	%rdx			/* pt_regs->dx */
+	popq	%rsi			/* pt_regs->si */
+	popq	%rdi			/* pt_regs->di */
+
+        /*
+         * USERGS_SYSRET32 does:
+         *  GSBASE = user's GS base
+         *  EIP = ECX
+         *  RFLAGS = R11
+         *  CS = __USER32_CS
+         *  SS = __USER_DS
+         *
+	 * ECX will not match pt_regs->cx, but we're returning to a vDSO
+	 * trampoline that will fix up RCX, so this is okay.
 	 *
-	 * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss
-	 * descriptor is not reinitialized.  This means that we must
-	 * avoid SYSRET with SS == NULL, which could happen if we schedule,
-	 * exit the kernel, and re-enter using an interrupt vector.  (All
-	 * interrupt entries on x86_64 set SS to NULL.)  We prevent that
-	 * from happening by reloading SS in __switch_to.
-	 */
-	USERGS_SYSRET32
-
-#ifdef CONFIG_AUDITSYSCALL
-cstar_auditsys:
-	movl	%r9d, R9(%rsp)		/* register to be clobbered by call */
-	auditsys_entry_common
-	movl	R9(%rsp), %r9d		/* reload 6th syscall arg */
-	jmp	cstar_dispatch
-
-sysretl_audit:
-	auditsys_exit sysretl_from_sys_call
-#endif
-
-cstar_tracesys:
-#ifdef CONFIG_AUDITSYSCALL
-	testl	$(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jz	cstar_auditsys
-#endif
-	xchgl	%r9d, %ebp
-	SAVE_EXTRA_REGS
-	xorl	%eax, %eax		/* Do not leak kernel information */
-	movq	%rax, R11(%rsp)
-	movq	%rax, R10(%rsp)
-	movq	%r9, R9(%rsp)
-	movq	%rax, R8(%rsp)
-	movq	%rsp, %rdi		/* &pt_regs -> arg1 */
-	call	syscall_trace_enter
-	movl	R9(%rsp), %r9d
-
-	/* Reload arg registers from stack. (see sysenter_tracesys) */
-	movl	RCX(%rsp), %ecx
-	movl	RDX(%rsp), %edx
-	movl	RSI(%rsp), %esi
-	movl	RDI(%rsp), %edi
-	movl	%eax, %eax		/* zero extension */
-
-	RESTORE_EXTRA_REGS
-	xchgl	%ebp, %r9d
-	jmp	cstar_do_call
+	 * R12-R15 are callee-saved, so they contain whatever was in them
+	 * when the system call started, which is already known to user
+	 * code.  We zero R8-R10 to avoid info leaks.
+         */
+	xorq	%r8, %r8
+	xorq	%r9, %r9
+	xorq	%r10, %r10
+	movq	RSP-ORIG_RAX(%rsp), %rsp
+        USERGS_SYSRET32
 END(entry_SYSCALL_compat)
 
-ia32_badarg:
-	/*
-	 * So far, we've entered kernel mode, set AC, turned on IRQs, and
-	 * saved C regs except r8-r11.  We haven't done any of the other
-	 * standard entry work, though.  We want to bail, but we shouldn't
-	 * treat this as a syscall entry since we don't even know what the
-	 * args are.  Instead, treat this as a non-syscall entry, finish
-	 * the entry work, and immediately exit after setting AX = -EFAULT.
-	 *
-	 * We're really just being polite here.  Killing the task outright
-	 * would be a reasonable action, too.  Given that the only valid
-	 * way to have gotten here is through the vDSO, and we already know
-	 * that the stack pointer is bad, the task isn't going to survive
-	 * for long no matter what we do.
-	 */
-
-	ASM_CLAC			/* undo STAC */
-	movq	$-EFAULT, RAX(%rsp)	/* return -EFAULT if possible */
-
-	/* Fill in the rest of pt_regs */
-	xorl	%eax, %eax
-	movq	%rax, R11(%rsp)
-	movq	%rax, R10(%rsp)
-	movq	%rax, R9(%rsp)
-	movq	%rax, R8(%rsp)
-	SAVE_EXTRA_REGS
-
-	/* Turn IRQs back off. */
-	DISABLE_INTERRUPTS(CLBR_NONE)
-	TRACE_IRQS_OFF
-
-	/* Now finish entering normal kernel mode. */
-#ifdef CONFIG_CONTEXT_TRACKING
-	call enter_from_user_mode
-#endif
-
-	/* And exit again. */
-	jmp retint_user
-
-ia32_ret_from_sys_call_irqs_off:
-	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS(CLBR_NONE)
-
-ia32_ret_from_sys_call:
-	xorl	%eax, %eax		/* Do not leak kernel information */
-	movq	%rax, R11(%rsp)
-	movq	%rax, R10(%rsp)
-	movq	%rax, R9(%rsp)
-	movq	%rax, R8(%rsp)
-	jmp	int_ret_from_sys_call
-
 /*
  * Emulated IA32 system calls via int 0x80.
  *
@@ -507,14 +263,17 @@ ia32_ret_from_sys_call:
 ENTRY(entry_INT80_compat)
 	/*
 	 * Interrupts are off on entry.
-	 * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
-	 * it is too small to ever cause noticeable irq latency.
 	 */
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
 	SWAPGS
-	ENABLE_INTERRUPTS(CLBR_NONE)
 
-	/* Zero-extending 32-bit regs, do not remove */
+	/*
+	 * User tracing code (ptrace or signal handlers) might assume that
+	 * the saved RAX contains a 32-bit number when we're invoking a 32-bit
+	 * syscall.  Just in case the high bits are nonzero, zero-extend
+	 * the syscall number.  (This could almost certainly be deleted
+	 * with no ill effects.)
+	 */
 	movl	%eax, %eax
 
 	/* Construct struct pt_regs on stack (iret frame is already on stack) */
@@ -524,67 +283,37 @@ ENTRY(entry_INT80_compat)
 	pushq	%rdx			/* pt_regs->dx */
 	pushq	%rcx			/* pt_regs->cx */
 	pushq	$-ENOSYS		/* pt_regs->ax */
-	pushq	$0			/* pt_regs->r8 */
-	pushq	$0			/* pt_regs->r9 */
-	pushq	$0			/* pt_regs->r10 */
-	pushq	$0			/* pt_regs->r11 */
+	xorq    %r8,%r8
+	pushq   %r8                     /* pt_regs->r8  = 0 */
+	pushq   %r8                     /* pt_regs->r9  = 0 */
+	pushq   %r8                     /* pt_regs->r10 = 0 */
+	pushq   %r8                     /* pt_regs->r11 = 0 */
+	pushq   %rbx                    /* pt_regs->rbx */
+	pushq   %rbp                    /* pt_regs->rbp */
+	pushq   %r12                    /* pt_regs->r12 */
+	pushq   %r13                    /* pt_regs->r13 */
+	pushq   %r14                    /* pt_regs->r14 */
+	pushq   %r15                    /* pt_regs->r15 */
 	cld
-	sub	$(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */
-
-	orl	$TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
-	testl	$_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
-	jnz	ia32_tracesys
-
-ia32_do_call:
-	/* 32-bit syscall -> 64-bit C ABI argument conversion */
-	movl	%edi, %r8d		/* arg5 */
-	movl	%ebp, %r9d		/* arg6 */
-	xchg	%ecx, %esi		/* rsi:arg2, rcx:arg4 */
-	movl	%ebx, %edi		/* arg1 */
-	movl	%edx, %edx		/* arg3 (zero extension) */
-	cmpq	$(IA32_NR_syscalls-1), %rax
-	ja	1f
 
-	call	*ia32_sys_call_table(, %rax, 8)
-	movq	%rax, RAX(%rsp)
-1:
-	jmp	int_ret_from_sys_call
-
-ia32_tracesys:
-	SAVE_EXTRA_REGS
-	movq	%rsp, %rdi			/* &pt_regs -> arg1 */
-	call	syscall_trace_enter
 	/*
-	 * Reload arg registers from stack in case ptrace changed them.
-	 * Don't reload %eax because syscall_trace_enter() returned
-	 * the %rax value we should see.  But do truncate it to 32 bits.
-	 * If it's -1 to make us punt the syscall, then (u32)-1 is still
-	 * an appropriately invalid value.
+	 * User mode is traced as though IRQs are on, and the interrupt
+	 * gate turned them off.
 	 */
-	movl	RCX(%rsp), %ecx
-	movl	RDX(%rsp), %edx
-	movl	RSI(%rsp), %esi
-	movl	RDI(%rsp), %edi
-	movl	%eax, %eax		/* zero extension */
-	RESTORE_EXTRA_REGS
-	jmp	ia32_do_call
-END(entry_INT80_compat)
+	TRACE_IRQS_OFF
 
-	.macro PTREGSCALL label, func
-	ALIGN
-GLOBAL(\label)
-	leaq	\func(%rip), %rax
-	jmp	ia32_ptregs_common
-	.endm
+	movq	%rsp, %rdi
+	call	do_syscall_32_irqs_off
+.Lsyscall_32_done:
 
-	PTREGSCALL stub32_rt_sigreturn,	sys32_rt_sigreturn
-	PTREGSCALL stub32_sigreturn,	sys32_sigreturn
-	PTREGSCALL stub32_fork,		sys_fork
-	PTREGSCALL stub32_vfork,	sys_vfork
+	/* Go back to user mode. */
+	TRACE_IRQS_ON
+	SWAPGS
+	jmp	restore_regs_and_iret
+END(entry_INT80_compat)
 
 	ALIGN
 GLOBAL(stub32_clone)
-	leaq	sys_clone(%rip), %rax
 	/*
 	 * The 32-bit clone ABI is: clone(..., int tls_val, int *child_tidptr).
 	 * The 64-bit clone ABI is: clone(..., int *child_tidptr, int tls_val).
@@ -593,12 +322,4 @@ GLOBAL(stub32_clone)
 	 * so we need to swap arguments here before calling it:
 	 */
 	xchg	%r8, %rcx
-	jmp	ia32_ptregs_common
-
-	ALIGN
-ia32_ptregs_common:
-	SAVE_EXTRA_REGS 8
-	call	*%rax
-	RESTORE_EXTRA_REGS 8
-	ret
-END(ia32_ptregs_common)
+	jmp	sys_clone

arch/x86/entry/syscall_32.c

@@ -4,24 +4,21 @@
 #include <linux/sys.h>
 #include <linux/cache.h>
 #include <asm/asm-offsets.h>
+#include <asm/syscall.h>
 
 #ifdef CONFIG_IA32_EMULATION
 #define SYM(sym, compat) compat
 #else
 #define SYM(sym, compat) sym
-#define ia32_sys_call_table sys_call_table
-#define __NR_syscall_compat_max __NR_syscall_max
 #endif
 
-#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void SYM(sym, compat)(void) ;
+#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage long SYM(sym, compat)(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
 #include <asm/syscalls_32.h>
 #undef __SYSCALL_I386
 
 #define __SYSCALL_I386(nr, sym, compat) [nr] = SYM(sym, compat),
 
-typedef asmlinkage void (*sys_call_ptr_t)(void);
-
-extern asmlinkage void sys_ni_syscall(void);
+extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
 
 __visible const sys_call_ptr_t ia32_sys_call_table[__NR_syscall_compat_max+1] = {
 	/*

arch/x86/entry/syscall_64.c

@@ -14,13 +14,13 @@
 # define __SYSCALL_X32(nr, sym, compat) /* nothing */
 #endif
 
-#define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ;
+#define __SYSCALL_64(nr, sym, compat) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
 #include <asm/syscalls_64.h>
 #undef __SYSCALL_64
 
 #define __SYSCALL_64(nr, sym, compat) [nr] = sym,
 
-extern void sys_ni_syscall(void);
+extern long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
 
 asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
 	/*

arch/x86/entry/syscalls/syscall_32.tbl

@@ -8,7 +8,7 @@
 #
 0	i386	restart_syscall		sys_restart_syscall
 1	i386	exit			sys_exit
-2	i386	fork			sys_fork			stub32_fork
+2	i386	fork			sys_fork			sys_fork
 3	i386	read			sys_read
 4	i386	write			sys_write
 5	i386	open			sys_open			compat_sys_open
@@ -17,7 +17,7 @@
 8	i386	creat			sys_creat
 9	i386	link			sys_link
 10	i386	unlink			sys_unlink
-11	i386	execve			sys_execve			stub32_execve
+11	i386	execve			sys_execve			compat_sys_execve
 12	i386	chdir			sys_chdir
 13	i386	time			sys_time			compat_sys_time
 14	i386	mknod			sys_mknod
@@ -125,7 +125,7 @@
 116	i386	sysinfo			sys_sysinfo			compat_sys_sysinfo
 117	i386	ipc			sys_ipc				compat_sys_ipc
 118	i386	fsync			sys_fsync
-119	i386	sigreturn		sys_sigreturn			stub32_sigreturn
+119	i386	sigreturn		sys_sigreturn			sys32_sigreturn
 120	i386	clone			sys_clone			stub32_clone
 121	i386	setdomainname		sys_setdomainname
 122	i386	uname			sys_newuname
@@ -179,7 +179,7 @@
 170	i386	setresgid		sys_setresgid16
 171	i386	getresgid		sys_getresgid16
 172	i386	prctl			sys_prctl
-173	i386	rt_sigreturn		sys_rt_sigreturn		stub32_rt_sigreturn
+173	i386	rt_sigreturn		sys_rt_sigreturn		sys32_rt_sigreturn
 174	i386	rt_sigaction		sys_rt_sigaction		compat_sys_rt_sigaction
 175	i386	rt_sigprocmask		sys_rt_sigprocmask
 176	i386	rt_sigpending		sys_rt_sigpending		compat_sys_rt_sigpending
@@ -196,7 +196,7 @@
 187	i386	sendfile		sys_sendfile			compat_sys_sendfile
 188	i386	getpmsg
 189	i386	putpmsg
-190	i386	vfork			sys_vfork			stub32_vfork
+190	i386	vfork			sys_vfork			sys_vfork
 191	i386	ugetrlimit		sys_getrlimit			compat_sys_getrlimit
 192	i386	mmap2			sys_mmap_pgoff
 193	i386	truncate64		sys_truncate64			sys32_truncate64
@@ -364,7 +364,7 @@
 355	i386	getrandom		sys_getrandom
 356	i386	memfd_create		sys_memfd_create
 357	i386	bpf			sys_bpf
-358	i386	execveat		sys_execveat			stub32_execveat
+358	i386	execveat		sys_execveat			compat_sys_execveat
 359	i386	socket			sys_socket
 360	i386	socketpair		sys_socketpair
 361	i386	bind			sys_bind

arch/x86/entry/vdso/Makefile

@@ -19,9 +19,7 @@ obj-y				+= vma.o
 # vDSO images to build
 vdso_img-$(VDSO64-y)		+= 64
 vdso_img-$(VDSOX32-y)		+= x32
-vdso_img-$(VDSO32-y)		+= 32-int80
-vdso_img-$(CONFIG_IA32_EMULATION)	+= 32-syscall
-vdso_img-$(VDSO32-y)		+= 32-sysenter
+vdso_img-$(VDSO32-y)		+= 32
 
 obj-$(VDSO32-y)			+= vdso32-setup.o
 
@@ -69,7 +67,7 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
 CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
        $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \
        -fno-omit-frame-pointer -foptimize-sibling-calls \
-       -DDISABLE_BRANCH_PROFILING
+       -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
 
 $(vobjs): KBUILD_CFLAGS += $(CFL)
 
@@ -122,15 +120,6 @@ $(obj)/%.so: $(obj)/%.so.dbg
 $(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE
 	$(call if_changed,vdso)
 
-#
-# Build multiple 32-bit vDSO images to choose from at boot time.
-#
-vdso32.so-$(VDSO32-y)		+= int80
-vdso32.so-$(CONFIG_IA32_EMULATION)	+= syscall
-vdso32.so-$(VDSO32-y)		+= sysenter
-
-vdso32-images			= $(vdso32.so-y:%=vdso32-%.so)
-
 CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
 VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1
 
@@ -139,14 +128,12 @@ VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1
 override obj-dirs = $(dir $(obj)) $(obj)/vdso32/
 
 targets += vdso32/vdso32.lds
-targets += vdso32/note.o vdso32/vclock_gettime.o $(vdso32.so-y:%=vdso32/%.o)
+targets += vdso32/note.o vdso32/vclock_gettime.o vdso32/system_call.o
 targets += vdso32/vclock_gettime.o
 
-$(obj)/vdso32.o: $(vdso32-images:%=$(obj)/%)
-
-KBUILD_AFLAGS_32 := $(filter-out -m64,$(KBUILD_AFLAGS))
-$(vdso32-images:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_32)
-$(vdso32-images:%=$(obj)/%.dbg): asflags-$(CONFIG_X86_64) += -m32
+KBUILD_AFLAGS_32 := $(filter-out -m64,$(KBUILD_AFLAGS)) -DBUILD_VDSO
+$(obj)/vdso32.so.dbg: KBUILD_AFLAGS = $(KBUILD_AFLAGS_32)
+$(obj)/vdso32.so.dbg: asflags-$(CONFIG_X86_64) += -m32
 
 KBUILD_CFLAGS_32 := $(filter-out -m64,$(KBUILD_CFLAGS))
 KBUILD_CFLAGS_32 := $(filter-out -mcmodel=kernel,$(KBUILD_CFLAGS_32))
@@ -157,13 +144,13 @@ KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector)
 KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
 KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
 KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
-$(vdso32-images:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
+$(obj)/vdso32.so.dbg: KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
 
-$(vdso32-images:%=$(obj)/%.dbg): $(obj)/vdso32-%.so.dbg: FORCE \
-				 $(obj)/vdso32/vdso32.lds \
-				 $(obj)/vdso32/vclock_gettime.o \
-				 $(obj)/vdso32/note.o \
-				 $(obj)/vdso32/%.o
+$(obj)/vdso32.so.dbg: FORCE \
+		      $(obj)/vdso32/vdso32.lds \
+		      $(obj)/vdso32/vclock_gettime.o \
+		      $(obj)/vdso32/note.o \
+		      $(obj)/vdso32/system_call.o
 	$(call if_changed,vdso)
 
 #
@@ -206,4 +193,4 @@ $(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso FORCE
 PHONY += vdso_install $(vdso_img_insttargets)
 vdso_install: $(vdso_img_insttargets) FORCE
 
-clean-files := vdso32-syscall* vdso32-sysenter* vdso32-int80* vdso64* vdso-image-*.c vdsox32.so*
+clean-files := vdso32.so vdso32.so.dbg vdso64* vdso-image-*.c vdsox32.so*

arch/x86/entry/vdso/vdso2c.c

@@ -98,10 +98,10 @@ struct vdso_sym required_syms[] = {
 		"VDSO_FAKE_SECTION_TABLE_END", false
 	},
 	{"VDSO32_NOTE_MASK", true},
-	{"VDSO32_SYSENTER_RETURN", true},
 	{"__kernel_vsyscall", true},
 	{"__kernel_sigreturn", true},
 	{"__kernel_rt_sigreturn", true},
+	{"int80_landing_pad", true},
 };
 
 __attribute__((format(printf, 1, 2))) __attribute__((noreturn))

arch/x86/entry/vdso/vdso32-setup.c

@@ -48,35 +48,9 @@ __setup("vdso32=", vdso32_setup);
 __setup_param("vdso=", vdso_setup, vdso32_setup, 0);
 #endif
 
-#ifdef CONFIG_X86_64
-
-#define	vdso32_sysenter()	(boot_cpu_has(X86_FEATURE_SYSENTER32))
-#define	vdso32_syscall()	(boot_cpu_has(X86_FEATURE_SYSCALL32))
-
-#else  /* CONFIG_X86_32 */
-
-#define vdso32_sysenter()	(boot_cpu_has(X86_FEATURE_SEP))
-#define vdso32_syscall()	(0)
-
-#endif	/* CONFIG_X86_64 */
-
-#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT)
-const struct vdso_image *selected_vdso32;
-#endif
-
 int __init sysenter_setup(void)
 {
-#ifdef CONFIG_COMPAT
-	if (vdso32_syscall())
-		selected_vdso32 = &vdso_image_32_syscall;
-	else
-#endif
-	if (vdso32_sysenter())
-		selected_vdso32 = &vdso_image_32_sysenter;
-	else
-		selected_vdso32 = &vdso_image_32_int80;
-
-	init_vdso_image(selected_vdso32);
+	init_vdso_image(&vdso_image_32);
 
 	return 0;
 }

arch/x86/entry/vdso/vdso32/int80.S

@@ -1,56 +0,0 @@
-/*
- * Code for the vDSO.  This version uses the old int $0x80 method.
- *
- * First get the common code for the sigreturn entry points.
- * This must come first.
- */
-#include "sigreturn.S"
-
-	.text
-	.globl __kernel_vsyscall
-	.type __kernel_vsyscall,@function
-	ALIGN
-__kernel_vsyscall:
-.LSTART_vsyscall:
-	int $0x80
-	ret
-.LEND_vsyscall:
-	.size __kernel_vsyscall,.-.LSTART_vsyscall
-	.previous
-
-	.section .eh_frame,"a",@progbits
-.LSTARTFRAMEDLSI:
-	.long .LENDCIEDLSI-.LSTARTCIEDLSI
-.LSTARTCIEDLSI:
-	.long 0			/* CIE ID */
-	.byte 1			/* Version number */
-	.string "zR"		/* NUL-terminated augmentation string */
-	.uleb128 1		/* Code alignment factor */
-	.sleb128 -4		/* Data alignment factor */
-	.byte 8			/* Return address register column */
-	.uleb128 1		/* Augmentation value length */
-	.byte 0x1b		/* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */
-	.byte 0x0c		/* DW_CFA_def_cfa */
-	.uleb128 4
-	.uleb128 4
-	.byte 0x88		/* DW_CFA_offset, column 0x8 */
-	.uleb128 1
-	.align 4
-.LENDCIEDLSI:
-	.long .LENDFDEDLSI-.LSTARTFDEDLSI /* Length FDE */
-.LSTARTFDEDLSI:
-	.long .LSTARTFDEDLSI-.LSTARTFRAMEDLSI /* CIE pointer */
-	.long .LSTART_vsyscall-.	/* PC-relative start address */
-	.long .LEND_vsyscall-.LSTART_vsyscall
-	.uleb128 0
-	.align 4
-.LENDFDEDLSI:
-	.previous
-
-	/*
-	 * Pad out the segment to match the size of the sysenter.S version.
-	 */
-VDSO32_vsyscall_eh_frame_size = 0x40
-	.section .data,"aw",@progbits
-	.space VDSO32_vsyscall_eh_frame_size-(.LENDFDEDLSI-.LSTARTFRAMEDLSI), 0
-	.previous

arch/x86/entry/vdso/vdso32/syscall.S

@@ -1,75 +0,0 @@
-/*
- * Code for the vDSO.  This version uses the syscall instruction.
- *
- * First get the common code for the sigreturn entry points.
- * This must come first.
- */
-#define SYSCALL_ENTER_KERNEL	syscall
-#include "sigreturn.S"
-
-#include <asm/segment.h>
-
-	.text
-	.globl __kernel_vsyscall
-	.type __kernel_vsyscall,@function
-	ALIGN
-__kernel_vsyscall:
-.LSTART_vsyscall:
-	push	%ebp
-.Lpush_ebp:
-	movl	%ecx, %ebp
-	syscall
-	movl	%ebp, %ecx
-	popl	%ebp
-.Lpop_ebp:
-	ret
-.LEND_vsyscall:
-	.size __kernel_vsyscall,.-.LSTART_vsyscall
-
-	.section .eh_frame,"a",@progbits
-.LSTARTFRAME:
-	.long .LENDCIE-.LSTARTCIE
-.LSTARTCIE:
-	.long 0			/* CIE ID */
-	.byte 1			/* Version number */
-	.string "zR"		/* NUL-terminated augmentation string */
-	.uleb128 1		/* Code alignment factor */
-	.sleb128 -4		/* Data alignment factor */
-	.byte 8			/* Return address register column */
-	.uleb128 1		/* Augmentation value length */
-	.byte 0x1b		/* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */
-	.byte 0x0c		/* DW_CFA_def_cfa */
-	.uleb128 4
-	.uleb128 4
-	.byte 0x88		/* DW_CFA_offset, column 0x8 */
-	.uleb128 1
-	.align 4
-.LENDCIE:
-
-	.long .LENDFDE1-.LSTARTFDE1	/* Length FDE */
-.LSTARTFDE1:
-	.long .LSTARTFDE1-.LSTARTFRAME	/* CIE pointer */
-	.long .LSTART_vsyscall-.	/* PC-relative start address */
-	.long .LEND_vsyscall-.LSTART_vsyscall
-	.uleb128 0			/* Augmentation length */
-	/* What follows are the instructions for the table generation.
-	   We have to record all changes of the stack pointer.  */
-	.byte 0x40 + .Lpush_ebp-.LSTART_vsyscall /* DW_CFA_advance_loc */
-	.byte 0x0e		/* DW_CFA_def_cfa_offset */
-	.uleb128 8
-	.byte 0x85, 0x02	/* DW_CFA_offset %ebp -8 */
-	.byte 0x40 + .Lpop_ebp-.Lpush_ebp /* DW_CFA_advance_loc */
-	.byte 0xc5		/* DW_CFA_restore %ebp */
-	.byte 0x0e		/* DW_CFA_def_cfa_offset */
-	.uleb128 4
-	.align 4
-.LENDFDE1:
-	.previous
-
-	/*
-	 * Pad out the segment to match the size of the sysenter.S version.
-	 */
-VDSO32_vsyscall_eh_frame_size = 0x40
-	.section .data,"aw",@progbits
-	.space VDSO32_vsyscall_eh_frame_size-(.LENDFDE1-.LSTARTFRAME), 0
-	.previous

arch/x86/entry/vdso/vdso32/sysenter.S

@@ -1,116 +0,0 @@
-/*
- * Code for the vDSO.  This version uses the sysenter instruction.
- *
- * First get the common code for the sigreturn entry points.
- * This must come first.
- */
-#include "sigreturn.S"
-
-/*
- * The caller puts arg2 in %ecx, which gets pushed. The kernel will use
- * %ecx itself for arg2. The pushing is because the sysexit instruction
- * (found in entry.S) requires that we clobber %ecx with the desired %esp.
- * User code might expect that %ecx is unclobbered though, as it would be
- * for returning via the iret instruction, so we must push and pop.
- *
- * The caller puts arg3 in %edx, which the sysexit instruction requires
- * for %eip. Thus, exactly as for arg2, we must push and pop.
- *
- * Arg6 is different. The caller puts arg6 in %ebp. Since the sysenter
- * instruction clobbers %esp, the user's %esp won't even survive entry
- * into the kernel. We store %esp in %ebp. Code in entry.S must fetch
- * arg6 from the stack.
- *
- * You can not use this vsyscall for the clone() syscall because the
- * three words on the parent stack do not get copied to the child.
- */
-	.text
-	.globl __kernel_vsyscall
-	.type __kernel_vsyscall,@function
-	ALIGN
-__kernel_vsyscall:
-.LSTART_vsyscall:
-	push %ecx
-.Lpush_ecx:
-	push %edx
-.Lpush_edx:
-	push %ebp
-.Lenter_kernel:
-	movl %esp,%ebp
-	sysenter
-
-	/* 7: align return point with nop's to make disassembly easier */
-	.space 7,0x90
-
-	/* 14: System call restart point is here! (SYSENTER_RETURN-2) */
-	int $0x80
-	/* 16: System call normal return point is here! */
-VDSO32_SYSENTER_RETURN:	/* Symbol used by sysenter.c via vdso32-syms.h */
-	pop %ebp
-.Lpop_ebp:
-	pop %edx
-.Lpop_edx:
-	pop %ecx
-.Lpop_ecx:
-	ret
-.LEND_vsyscall:
-	.size __kernel_vsyscall,.-.LSTART_vsyscall
-	.previous
-
-	.section .eh_frame,"a",@progbits
-.LSTARTFRAMEDLSI:
-	.long .LENDCIEDLSI-.LSTARTCIEDLSI
-.LSTARTCIEDLSI:
-	.long 0			/* CIE ID */
-	.byte 1			/* Version number */
-	.string "zR"		/* NUL-terminated augmentation string */
-	.uleb128 1		/* Code alignment factor */
-	.sleb128 -4		/* Data alignment factor */
-	.byte 8			/* Return address register column */
-	.uleb128 1		/* Augmentation value length */
-	.byte 0x1b		/* DW_EH_PE_pcrel|DW_EH_PE_sdata4. */
-	.byte 0x0c		/* DW_CFA_def_cfa */
-	.uleb128 4
-	.uleb128 4
-	.byte 0x88		/* DW_CFA_offset, column 0x8 */
-	.uleb128 1
-	.align 4
-.LENDCIEDLSI:
-	.long .LENDFDEDLSI-.LSTARTFDEDLSI /* Length FDE */
-.LSTARTFDEDLSI:
-	.long .LSTARTFDEDLSI-.LSTARTFRAMEDLSI /* CIE pointer */
-	.long .LSTART_vsyscall-.	/* PC-relative start address */
-	.long .LEND_vsyscall-.LSTART_vsyscall
-	.uleb128 0
-	/* What follows are the instructions for the table generation.
-	   We have to record all changes of the stack pointer.  */
-	.byte 0x40 + (.Lpush_ecx-.LSTART_vsyscall) /* DW_CFA_advance_loc */
-	.byte 0x0e		/* DW_CFA_def_cfa_offset */
-	.byte 0x08		/* RA at offset 8 now */
-	.byte 0x40 + (.Lpush_edx-.Lpush_ecx) /* DW_CFA_advance_loc */
-	.byte 0x0e		/* DW_CFA_def_cfa_offset */
-	.byte 0x0c		/* RA at offset 12 now */
-	.byte 0x40 + (.Lenter_kernel-.Lpush_edx) /* DW_CFA_advance_loc */
-	.byte 0x0e		/* DW_CFA_def_cfa_offset */
-	.byte 0x10		/* RA at offset 16 now */
-	.byte 0x85, 0x04	/* DW_CFA_offset %ebp -16 */
-	/* Finally the epilogue.  */
-	.byte 0x40 + (.Lpop_ebp-.Lenter_kernel)	/* DW_CFA_advance_loc */
-	.byte 0x0e		/* DW_CFA_def_cfa_offset */
-	.byte 0x0c		/* RA at offset 12 now */
-	.byte 0xc5		/* DW_CFA_restore %ebp */
-	.byte 0x40 + (.Lpop_edx-.Lpop_ebp) /* DW_CFA_advance_loc */
-	.byte 0x0e		/* DW_CFA_def_cfa_offset */
-	.byte 0x08		/* RA at offset 8 now */
-	.byte 0x40 + (.Lpop_ecx-.Lpop_edx) /* DW_CFA_advance_loc */
-	.byte 0x0e		/* DW_CFA_def_cfa_offset */
-	.byte 0x04		/* RA at offset 4 now */
-	.align 4
-.LENDFDEDLSI:
-	.previous
-
-	/*
-	 * Emit a symbol with the size of this .eh_frame data,
-	 * to verify it matches the other versions.
-	 */
-VDSO32_vsyscall_eh_frame_size = (.LENDFDEDLSI-.LSTARTFRAMEDLSI)

arch/x86/entry/vdso/vdso32/system_call.S

@@ -0,0 +1,57 @@
+/*
+ * Code for the vDSO.  This version uses the old int $0x80 method.
+*/
+
+#include <asm/dwarf2.h>
+#include <asm/cpufeature.h>
+#include <asm/alternative-asm.h>
+
+/*
+ * First get the common code for the sigreturn entry points.
+ * This must come first.
+ */
+#include "sigreturn.S"
+
+	.text
+	.globl __kernel_vsyscall
+	.type __kernel_vsyscall,@function
+	ALIGN
+__kernel_vsyscall:
+	CFI_STARTPROC
+	/*
+	 * Reshuffle regs so that all of any of the entry instructions
+	 * will preserve enough state.
+	 */
+	pushl	%edx
+	CFI_ADJUST_CFA_OFFSET	4
+	CFI_REL_OFFSET		edx, 0
+	pushl	%ecx
+	CFI_ADJUST_CFA_OFFSET	4
+	CFI_REL_OFFSET		ecx, 0
+	movl	%esp, %ecx
+
+#ifdef CONFIG_X86_64
+	/* If SYSENTER (Intel) or SYSCALL32 (AMD) is available, use it. */
+	ALTERNATIVE_2 "", "sysenter", X86_FEATURE_SYSENTER32, \
+	                  "syscall",  X86_FEATURE_SYSCALL32
+#else
+	ALTERNATIVE "", "sysenter", X86_FEATURE_SEP
+#endif
+
+	/* Enter using int $0x80 */
+	movl	(%esp), %ecx
+	int	$0x80
+GLOBAL(int80_landing_pad)
+
+	/* Restore ECX and EDX in case they were clobbered. */
+	popl	%ecx
+	CFI_RESTORE		ecx
+	CFI_ADJUST_CFA_OFFSET	-4
+	popl	%edx
+	CFI_RESTORE		edx
+	CFI_ADJUST_CFA_OFFSET	-4
+	ret
+	CFI_ENDPROC
+
+	.size __kernel_vsyscall,.-__kernel_vsyscall
+	.previous

arch/x86/entry/vdso/vma.c

@@ -180,21 +180,10 @@ up_fail:
 #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
 static int load_vdso32(void)
 {
-	int ret;
-
 	if (vdso32_enabled != 1)  /* Other values all mean "disabled" */
 		return 0;
 
-	ret = map_vdso(selected_vdso32, false);
-	if (ret)
-		return ret;
-
-	if (selected_vdso32->sym_VDSO32_SYSENTER_RETURN)
-		current_thread_info()->sysenter_return =
-			current->mm->context.vdso +
-			selected_vdso32->sym_VDSO32_SYSENTER_RETURN;
-
-	return 0;
+	return map_vdso(&vdso_image_32, false);
 }
 #endif
 

arch/x86/entry/vsyscall/vsyscall_64.c

@@ -38,7 +38,14 @@
 #define CREATE_TRACE_POINTS
 #include "vsyscall_trace.h"
 
-static enum { EMULATE, NATIVE, NONE } vsyscall_mode = EMULATE;
+static enum { EMULATE, NATIVE, NONE } vsyscall_mode =
+#if defined(CONFIG_LEGACY_VSYSCALL_NATIVE)
+	NATIVE;
+#elif defined(CONFIG_LEGACY_VSYSCALL_NONE)
+	NONE;
+#else
+	EMULATE;
+#endif
 
 static int __init vsyscall_setup(char *str)
 {

arch/x86/ia32/ia32_signal.c

@@ -289,7 +289,7 @@ int ia32_setup_frame(int sig, struct ksignal *ksig,
 		/* Return stub is in 32bit vsyscall page */
 		if (current->mm->context.vdso)
 			restorer = current->mm->context.vdso +
-				selected_vdso32->sym___kernel_sigreturn;
+				vdso_image_32.sym___kernel_sigreturn;
 		else
 			restorer = &frame->retcode;
 	}
@@ -368,7 +368,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
 			restorer = ksig->ka.sa.sa_restorer;
 		else
 			restorer = current->mm->context.vdso +
-				selected_vdso32->sym___kernel_rt_sigreturn;
+				vdso_image_32.sym___kernel_rt_sigreturn;
 		put_user_ex(ptr_to_compat(restorer), &frame->pretcode);
 
 		/*

arch/x86/include/asm/dwarf2.h

@@ -0,0 +1,84 @@
+#ifndef _ASM_X86_DWARF2_H
+#define _ASM_X86_DWARF2_H
+
+#ifndef __ASSEMBLY__
+#warning "asm/dwarf2.h should be only included in pure assembly files"
+#endif
+
+/*
+ * Macros for dwarf2 CFI unwind table entries.
+ * See "as.info" for details on these pseudo ops. Unfortunately
+ * they are only supported in very new binutils, so define them
+ * away for older version.
+ */
+
+#ifdef CONFIG_AS_CFI
+
+#define CFI_STARTPROC		.cfi_startproc
+#define CFI_ENDPROC		.cfi_endproc
+#define CFI_DEF_CFA		.cfi_def_cfa
+#define CFI_DEF_CFA_REGISTER	.cfi_def_cfa_register
+#define CFI_DEF_CFA_OFFSET	.cfi_def_cfa_offset
+#define CFI_ADJUST_CFA_OFFSET	.cfi_adjust_cfa_offset
+#define CFI_OFFSET		.cfi_offset
+#define CFI_REL_OFFSET		.cfi_rel_offset
+#define CFI_REGISTER		.cfi_register
+#define CFI_RESTORE		.cfi_restore
+#define CFI_REMEMBER_STATE	.cfi_remember_state
+#define CFI_RESTORE_STATE	.cfi_restore_state
+#define CFI_UNDEFINED		.cfi_undefined
+#define CFI_ESCAPE		.cfi_escape
+
+#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
+#define CFI_SIGNAL_FRAME	.cfi_signal_frame
+#else
+#define CFI_SIGNAL_FRAME
+#endif
+
+#if defined(CONFIG_AS_CFI_SECTIONS) && defined(__ASSEMBLY__)
+#ifndef BUILD_VDSO
+	/*
+	 * Emit CFI data in .debug_frame sections, not .eh_frame sections.
+	 * The latter we currently just discard since we don't do DWARF
+	 * unwinding at runtime.  So only the offline DWARF information is
+	 * useful to anyone.  Note we should not use this directive if
+	 * vmlinux.lds.S gets changed so it doesn't discard .eh_frame.
+	 */
+	.cfi_sections .debug_frame
+#else
+	 /*
+	  * For the vDSO, emit both runtime unwind information and debug
+	  * symbols for the .dbg file.
+	  */
+	.cfi_sections .eh_frame, .debug_frame
+#endif
+#endif
+
+#else
+
+/*
+ * Due to the structure of pre-exisiting code, don't use assembler line
+ * comment character # to ignore the arguments. Instead, use a dummy macro.
+ */
+.macro cfi_ignore a=0, b=0, c=0, d=0
+.endm
+
+#define CFI_STARTPROC		cfi_ignore
+#define CFI_ENDPROC		cfi_ignore
+#define CFI_DEF_CFA		cfi_ignore
+#define CFI_DEF_CFA_REGISTER	cfi_ignore
+#define CFI_DEF_CFA_OFFSET	cfi_ignore
+#define CFI_ADJUST_CFA_OFFSET	cfi_ignore
+#define CFI_OFFSET		cfi_ignore
+#define CFI_REL_OFFSET		cfi_ignore
+#define CFI_REGISTER		cfi_ignore
+#define CFI_RESTORE		cfi_ignore
+#define CFI_REMEMBER_STATE	cfi_ignore
+#define CFI_RESTORE_STATE	cfi_ignore
+#define CFI_UNDEFINED		cfi_ignore
+#define CFI_ESCAPE		cfi_ignore
+#define CFI_SIGNAL_FRAME	cfi_ignore
+
+#endif
+
+#endif /* _ASM_X86_DWARF2_H */

arch/x86/include/asm/elf.h

@@ -171,11 +171,11 @@ do {						\
 static inline void elf_common_init(struct thread_struct *t,
 				   struct pt_regs *regs, const u16 ds)
 {
-	/* Commented-out registers are cleared in stub_execve */
-	/*regs->ax = regs->bx =*/ regs->cx = regs->dx = 0;
-	regs->si = regs->di /*= regs->bp*/ = 0;
+	/* ax gets execve's return value. */
+	/*regs->ax = */ regs->bx = regs->cx = regs->dx = 0;
+	regs->si = regs->di = regs->bp = 0;
 	regs->r8 = regs->r9 = regs->r10 = regs->r11 = 0;
-	/*regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0;*/
+	regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0;
 	t->fs = t->gs = 0;
 	t->fsindex = t->gsindex = 0;
 	t->ds = t->es = ds;
@@ -328,7 +328,7 @@ else									\
 
 #define VDSO_ENTRY							\
 	((unsigned long)current->mm->context.vdso +			\
-	 selected_vdso32->sym___kernel_vsyscall)
+	 vdso_image_32.sym___kernel_vsyscall)
 
 struct linux_binprm;
 

arch/x86/include/asm/processor.h

@@ -556,12 +556,12 @@ static inline unsigned int cpuid_edx(unsigned int op)
 }
 
 /* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
-static inline void rep_nop(void)
+static __always_inline void rep_nop(void)
 {
 	asm volatile("rep; nop" ::: "memory");
 }
 
-static inline void cpu_relax(void)
+static __always_inline void cpu_relax(void)
 {
 	rep_nop();
 }

arch/x86/include/asm/switch_to.h

@@ -79,12 +79,12 @@ do {									\
 #else /* CONFIG_X86_32 */
 
 /* frame pointer must be last for get_wchan */
-#define SAVE_CONTEXT    "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
-#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t"
+#define SAVE_CONTEXT    "pushq %%rbp ; movq %%rsi,%%rbp\n\t"
+#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp\t"
 
 #define __EXTRA_CLOBBER  \
 	, "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
-	  "r12", "r13", "r14", "r15"
+	  "r12", "r13", "r14", "r15", "flags"
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 #define __switch_canary							  \
@@ -100,7 +100,11 @@ do {									\
 #define __switch_canary_iparam
 #endif	/* CC_STACKPROTECTOR */
 
-/* Save restore flags to clear handle leaking NT */
+/*
+ * There is no need to save or restore flags, because flags are always
+ * clean in kernel mode, with the possible exception of IOPL.  Kernel IOPL
+ * has no effect.
+ */
 #define switch_to(prev, next, last) \
 	asm volatile(SAVE_CONTEXT					  \
 	     "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */	  \

arch/x86/include/asm/syscall.h

@@ -20,9 +20,21 @@
 #include <asm/thread_info.h>	/* for TS_COMPAT */
 #include <asm/unistd.h>
 
-typedef void (*sys_call_ptr_t)(void);
+typedef asmlinkage long (*sys_call_ptr_t)(unsigned long, unsigned long,
+					  unsigned long, unsigned long,
+					  unsigned long, unsigned long);
 extern const sys_call_ptr_t sys_call_table[];
 
+#if defined(CONFIG_X86_32)
+#define ia32_sys_call_table sys_call_table
+#define __NR_syscall_compat_max __NR_syscall_max
+#define IA32_NR_syscalls NR_syscalls
+#endif
+
+#if defined(CONFIG_IA32_EMULATION)
+extern const sys_call_ptr_t ia32_sys_call_table[];
+#endif
+
 /*
  * Only the low 32 bits of orig_ax are meaningful, so we return int.
  * This importantly ignores the high bits on 64-bit, so comparisons

arch/x86/include/asm/thread_info.h

@@ -58,7 +58,6 @@ struct thread_info {
 	__u32			status;		/* thread synchronous flags */
 	__u32			cpu;		/* current CPU */
 	mm_segment_t		addr_limit;
-	void __user		*sysenter_return;
 	unsigned int		sig_on_uaccess_error:1;
 	unsigned int		uaccess_err:1;	/* uaccess failed */
 };

arch/x86/include/asm/uaccess.h

@@ -51,13 +51,13 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
 	 * limit, not add it to the address).
 	 */
 	if (__builtin_constant_p(size))
-		return addr > limit - size;
+		return unlikely(addr > limit - size);
 
 	/* Arbitrary sizes? Be careful about overflow */
 	addr += size;
-	if (addr < size)
+	if (unlikely(addr < size))
 		return true;
-	return addr > limit;
+	return unlikely(addr > limit);
 }
 
 #define __range_not_ok(addr, size, limit)				\
@@ -182,7 +182,7 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
 		     : "=a" (__ret_gu), "=r" (__val_gu)			\
 		     : "0" (ptr), "i" (sizeof(*(ptr))));		\
 	(x) = (__force __typeof__(*(ptr))) __val_gu;			\
-	__ret_gu;							\
+	__builtin_expect(__ret_gu, 0);					\
 })
 
 #define __put_user_x(size, x, ptr, __ret_pu)			\
@@ -278,7 +278,7 @@ extern void __put_user_8(void);
 		__put_user_x(X, __pu_val, ptr, __ret_pu);	\
 		break;						\
 	}							\
-	__ret_pu;						\
+	__builtin_expect(__ret_pu, 0);				\
 })
 
 #define __put_user_size(x, ptr, size, retval, errret)			\
@@ -401,7 +401,7 @@ do {									\
 ({								\
 	int __pu_err;						\
 	__put_user_size((x), (ptr), (size), __pu_err, -EFAULT);	\
-	__pu_err;						\
+	__builtin_expect(__pu_err, 0);				\
 })
 
 #define __get_user_nocheck(x, ptr, size)				\
@@ -410,7 +410,7 @@ do {									\
 	unsigned long __gu_val;						\
 	__get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT);	\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
-	__gu_err;							\
+	__builtin_expect(__gu_err, 0);					\
 })
 
 /* FIXME: this hack is definitely wrong -AK */

arch/x86/include/asm/vdso.h

@@ -26,7 +26,7 @@ struct vdso_image {
 	long sym___kernel_sigreturn;
 	long sym___kernel_rt_sigreturn;
 	long sym___kernel_vsyscall;
-	long sym_VDSO32_SYSENTER_RETURN;
+	long sym_int80_landing_pad;
 };
 
 #ifdef CONFIG_X86_64
@@ -38,13 +38,7 @@ extern const struct vdso_image vdso_image_x32;
 #endif
 
 #if defined CONFIG_X86_32 || defined CONFIG_COMPAT
-extern const struct vdso_image vdso_image_32_int80;
-#ifdef CONFIG_COMPAT
-extern const struct vdso_image vdso_image_32_syscall;
-#endif
-extern const struct vdso_image vdso_image_32_sysenter;
-
-extern const struct vdso_image *selected_vdso32;
+extern const struct vdso_image vdso_image_32;
 #endif
 
 extern void __init init_vdso_image(const struct vdso_image *image);

arch/x86/kernel/asm-offsets.c

@@ -53,9 +53,6 @@ void common(void) {
 	OFFSET(IA32_SIGCONTEXT_sp, sigcontext_ia32, sp);
 	OFFSET(IA32_SIGCONTEXT_ip, sigcontext_ia32, ip);
 
-	BLANK();
-	OFFSET(TI_sysenter_return, thread_info, sysenter_return);
-
 	BLANK();
 	OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
 #endif

arch/x86/kernel/signal.c

@@ -299,7 +299,7 @@ __setup_frame(int sig, struct ksignal *ksig, sigset_t *set,
 
 	if (current->mm->context.vdso)
 		restorer = current->mm->context.vdso +
-			selected_vdso32->sym___kernel_sigreturn;
+			vdso_image_32.sym___kernel_sigreturn;
 	else
 		restorer = &frame->retcode;
 	if (ksig->ka.sa.sa_flags & SA_RESTORER)
@@ -363,7 +363,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 
 		/* Set up to return from userspace.  */
 		restorer = current->mm->context.vdso +
-			selected_vdso32->sym___kernel_rt_sigreturn;
+			vdso_image_32.sym___kernel_rt_sigreturn;
 		if (ksig->ka.sa.sa_flags & SA_RESTORER)
 			restorer = ksig->ka.sa.sa_restorer;
 		put_user_ex(restorer, &frame->pretcode);

arch/x86/um/asm/syscall.h

@@ -3,6 +3,10 @@
 
 #include <uapi/linux/audit.h>
 
+typedef asmlinkage long (*sys_call_ptr_t)(unsigned long, unsigned long,
+					  unsigned long, unsigned long,
+					  unsigned long, unsigned long);
+
 static inline int syscall_get_arch(void)
 {
 #ifdef CONFIG_X86_32

arch/x86/um/sys_call_table_32.c

@@ -7,6 +7,7 @@
 #include <linux/sys.h>
 #include <linux/cache.h>
 #include <generated/user_constants.h>
+#include <asm/syscall.h>
 
 #define __NO_STUBS
 
@@ -24,15 +25,13 @@
 
 #define old_mmap sys_old_mmap
 
-#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage void sym(void) ;
+#define __SYSCALL_I386(nr, sym, compat) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
 #include <asm/syscalls_32.h>
 
 #undef __SYSCALL_I386
 #define __SYSCALL_I386(nr, sym, compat) [ nr ] = sym,
 
-typedef asmlinkage void (*sys_call_ptr_t)(void);
-
-extern asmlinkage void sys_ni_syscall(void);
+extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
 
 const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = {
 	/*

arch/x86/um/sys_call_table_64.c

@@ -7,6 +7,7 @@
 #include <linux/sys.h>
 #include <linux/cache.h>
 #include <generated/user_constants.h>
+#include <asm/syscall.h>
 
 #define __NO_STUBS
 
@@ -37,15 +38,13 @@
 #define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
 #define __SYSCALL_X32(nr, sym, compat) /* Not supported */
 
-#define __SYSCALL_64(nr, sym, compat) extern asmlinkage void sym(void) ;
+#define __SYSCALL_64(nr, sym, compat) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long) ;
 #include <asm/syscalls_64.h>
 
 #undef __SYSCALL_64
 #define __SYSCALL_64(nr, sym, compat) [ nr ] = sym,
 
-typedef void (*sys_call_ptr_t)(void);
-
-extern void sys_ni_syscall(void);
+extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
 
 const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = {
 	/*

arch/x86/xen/setup.c

@@ -965,17 +965,8 @@ char * __init xen_auto_xlated_memory_setup(void)
 static void __init fiddle_vdso(void)
 {
 #ifdef CONFIG_X86_32
-	/*
-	 * This could be called before selected_vdso32 is initialized, so
-	 * just fiddle with both possible images.  vdso_image_32_syscall
-	 * can't be selected, since it only exists on 64-bit systems.
-	 */
-	u32 *mask;
-	mask = vdso_image_32_int80.data +
-		vdso_image_32_int80.sym_VDSO32_NOTE_MASK;
-	*mask |= 1 << VDSO_NOTE_NONEGSEG_BIT;
-	mask = vdso_image_32_sysenter.data +
-		vdso_image_32_sysenter.sym_VDSO32_NOTE_MASK;
+	u32 *mask = vdso_image_32.data +
+		vdso_image_32.sym_VDSO32_NOTE_MASK;
 	*mask |= 1 << VDSO_NOTE_NONEGSEG_BIT;
 #endif
 }

tools/testing/selftests/x86/Makefile

@@ -4,8 +4,8 @@ include ../lib.mk
 
 .PHONY: all all_32 all_64 warn_32bit_failure clean
 
-TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs ldt_gdt syscall_nt
-TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault sigreturn
+TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs ldt_gdt syscall_nt ptrace_syscall
+TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault sigreturn test_syscall_vdso unwind_vdso
 
 TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY)
 BINARIES_32 := $(TARGETS_C_32BIT_ALL:%=%_32)
@@ -60,3 +60,5 @@ endif
 
 # Some tests have additional dependencies.
 sysret_ss_attrs_64: thunks.S
+ptrace_syscall_32: raw_syscall_helper_32.S
+test_syscall_vdso_32: thunks_32.S

tools/testing/selftests/x86/ptrace_syscall.c

@@ -0,0 +1,294 @@
+#define _GNU_SOURCE
+
+#include <sys/ptrace.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/syscall.h>
+#include <sys/user.h>
+#include <unistd.h>
+#include <errno.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <err.h>
+#include <string.h>
+#include <asm/ptrace-abi.h>
+#include <sys/auxv.h>
+
+/* Bitness-agnostic defines for user_regs_struct fields. */
+#ifdef __x86_64__
+# define user_syscall_nr	orig_rax
+# define user_arg0		rdi
+# define user_arg1		rsi
+# define user_arg2		rdx
+# define user_arg3		r10
+# define user_arg4		r8
+# define user_arg5		r9
+# define user_ip		rip
+# define user_ax		rax
+#else
+# define user_syscall_nr	orig_eax
+# define user_arg0		ebx
+# define user_arg1		ecx
+# define user_arg2		edx
+# define user_arg3		esi
+# define user_arg4		edi
+# define user_arg5		ebp
+# define user_ip		eip
+# define user_ax		eax
+#endif
+
+static int nerrs = 0;
+
+struct syscall_args32 {
+	uint32_t nr, arg0, arg1, arg2, arg3, arg4, arg5;
+};
+
+#ifdef __i386__
+extern void sys32_helper(struct syscall_args32 *, void *);
+extern void int80_and_ret(void);
+#endif
+
+/*
+ * Helper to invoke int80 with controlled regs and capture the final regs.
+ */
+static void do_full_int80(struct syscall_args32 *args)
+{
+#ifdef __x86_64__
+	register unsigned long bp asm("bp") = args->arg5;
+	asm volatile ("int $0x80"
+		      : "+a" (args->nr),
+			"+b" (args->arg0), "+c" (args->arg1), "+d" (args->arg2),
+			"+S" (args->arg3), "+D" (args->arg4), "+r" (bp));
+	args->arg5 = bp;
+#else
+	sys32_helper(args, int80_and_ret);
+#endif
+}
+
+#ifdef __i386__
+static void (*vsyscall32)(void);
+
+/*
+ * Nasty helper to invoke AT_SYSINFO (i.e. __kernel_vsyscall) with
+ * controlled regs and capture the final regs.  This is so nasty that it
+ * crashes my copy of gdb :)
+ */
+static void do_full_vsyscall32(struct syscall_args32 *args)
+{
+	sys32_helper(args, vsyscall32);
+}
+#endif
+
+static siginfo_t wait_trap(pid_t chld)
+{
+	siginfo_t si;
+	if (waitid(P_PID, chld, &si, WEXITED|WSTOPPED) != 0)
+		err(1, "waitid");
+	if (si.si_pid != chld)
+		errx(1, "got unexpected pid in event\n");
+	if (si.si_code != CLD_TRAPPED)
+		errx(1, "got unexpected event type %d\n", si.si_code);
+	return si;
+}
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+		       int flags)
+{
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handler;
+	sa.sa_flags = SA_SIGINFO | flags;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+}
+
+static void clearhandler(int sig)
+{
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_handler = SIG_DFL;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+}
+
+#ifdef __x86_64__
+# define REG_BP REG_RBP
+#else
+# define REG_BP REG_EBP
+#endif
+
+static void empty_handler(int sig, siginfo_t *si, void *ctx_void)
+{
+}
+
+static void test_sys32_regs(void (*do_syscall)(struct syscall_args32 *))
+{
+	struct syscall_args32 args = {
+		.nr = 224,	/* gettid */
+		.arg0 = 10, .arg1 = 11, .arg2 = 12,
+		.arg3 = 13, .arg4 = 14, .arg5 = 15,
+	};
+
+	do_syscall(&args);
+
+	if (args.nr != getpid() ||
+	    args.arg0 != 10 || args.arg1 != 11 || args.arg2 != 12 ||
+	    args.arg3 != 13 || args.arg4 != 14 || args.arg5 != 15) {
+		printf("[FAIL]\tgetpid() failed to preseve regs\n");
+		nerrs++;
+	} else {
+		printf("[OK]\tgetpid() preserves regs\n");
+	}
+
+	sethandler(SIGUSR1, empty_handler, 0);
+
+	args.nr = 37;	/* kill */
+	args.arg0 = getpid();
+	args.arg1 = SIGUSR1;
+	do_syscall(&args);
+	if (args.nr != 0 ||
+	    args.arg0 != getpid() || args.arg1 != SIGUSR1 || args.arg2 != 12 ||
+	    args.arg3 != 13 || args.arg4 != 14 || args.arg5 != 15) {
+		printf("[FAIL]\tkill(getpid(), SIGUSR1) failed to preseve regs\n");
+		nerrs++;
+	} else {
+		printf("[OK]\tkill(getpid(), SIGUSR1) preserves regs\n");
+	}
+	clearhandler(SIGUSR1);
+}
+
+static void test_ptrace_syscall_restart(void)
+{
+	printf("[RUN]\tptrace-induced syscall restart\n");
+	pid_t chld = fork();
+	if (chld < 0)
+		err(1, "fork");
+
+	if (chld == 0) {
+		if (ptrace(PTRACE_TRACEME, 0, 0, 0) != 0)
+			err(1, "PTRACE_TRACEME");
+
+		printf("\tChild will make one syscall\n");
+		raise(SIGSTOP);
+
+		syscall(SYS_gettid, 10, 11, 12, 13, 14, 15);
+		_exit(0);
+	}
+
+	int status;
+
+	/* Wait for SIGSTOP. */
+	if (waitpid(chld, &status, 0) != chld || !WIFSTOPPED(status))
+		err(1, "waitpid");
+
+	struct user_regs_struct regs;
+
+	printf("[RUN]\tSYSEMU\n");
+	if (ptrace(PTRACE_SYSEMU, chld, 0, 0) != 0)
+		err(1, "PTRACE_SYSCALL");
+	wait_trap(chld);
+
+	if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_GETREGS");
+
+	if (regs.user_syscall_nr != SYS_gettid ||
+	    regs.user_arg0 != 10 || regs.user_arg1 != 11 ||
+	    regs.user_arg2 != 12 || regs.user_arg3 != 13 ||
+	    regs.user_arg4 != 14 || regs.user_arg5 != 15) {
+		printf("[FAIL]\tInitial args are wrong (nr=%lu, args=%lu %lu %lu %lu %lu %lu)\n", (unsigned long)regs.user_syscall_nr, (unsigned long)regs.user_arg0, (unsigned long)regs.user_arg1, (unsigned long)regs.user_arg2, (unsigned long)regs.user_arg3, (unsigned long)regs.user_arg4, (unsigned long)regs.user_arg5);
+		nerrs++;
+	} else {
+		printf("[OK]\tInitial nr and args are correct\n");
+	}
+
+	printf("[RUN]\tRestart the syscall (ip = 0x%lx)\n",
+	       (unsigned long)regs.user_ip);
+
+	/*
+	 * This does exactly what it appears to do if syscall is int80 or
+	 * SYSCALL64.  For SYSCALL32 or SYSENTER, though, this is highly
+	 * magical.  It needs to work so that ptrace and syscall restart
+	 * work as expected.
+	 */
+	regs.user_ax = regs.user_syscall_nr;
+	regs.user_ip -= 2;
+	if (ptrace(PTRACE_SETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_SETREGS");
+
+	if (ptrace(PTRACE_SYSEMU, chld, 0, 0) != 0)
+		err(1, "PTRACE_SYSCALL");
+	wait_trap(chld);
+
+	if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_GETREGS");
+
+	if (regs.user_syscall_nr != SYS_gettid ||
+	    regs.user_arg0 != 10 || regs.user_arg1 != 11 ||
+	    regs.user_arg2 != 12 || regs.user_arg3 != 13 ||
+	    regs.user_arg4 != 14 || regs.user_arg5 != 15) {
+		printf("[FAIL]\tRestart nr or args are wrong (nr=%lu, args=%lu %lu %lu %lu %lu %lu)\n", (unsigned long)regs.user_syscall_nr, (unsigned long)regs.user_arg0, (unsigned long)regs.user_arg1, (unsigned long)regs.user_arg2, (unsigned long)regs.user_arg3, (unsigned long)regs.user_arg4, (unsigned long)regs.user_arg5);
+		nerrs++;
+	} else {
+		printf("[OK]\tRestarted nr and args are correct\n");
+	}
+
+	printf("[RUN]\tChange nr and args and restart the syscall (ip = 0x%lx)\n",
+	       (unsigned long)regs.user_ip);
+
+	regs.user_ax = SYS_getpid;
+	regs.user_arg0 = 20;
+	regs.user_arg1 = 21;
+	regs.user_arg2 = 22;
+	regs.user_arg3 = 23;
+	regs.user_arg4 = 24;
+	regs.user_arg5 = 25;
+	regs.user_ip -= 2;
+
+	if (ptrace(PTRACE_SETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_SETREGS");
+
+	if (ptrace(PTRACE_SYSEMU, chld, 0, 0) != 0)
+		err(1, "PTRACE_SYSCALL");
+	wait_trap(chld);
+
+	if (ptrace(PTRACE_GETREGS, chld, 0, &regs) != 0)
+		err(1, "PTRACE_GETREGS");
+
+	if (regs.user_syscall_nr != SYS_getpid ||
+	    regs.user_arg0 != 20 || regs.user_arg1 != 21 || regs.user_arg2 != 22 ||
+	    regs.user_arg3 != 23 || regs.user_arg4 != 24 || regs.user_arg5 != 25) {
+		printf("[FAIL]\tRestart nr or args are wrong (nr=%lu, args=%lu %lu %lu %lu %lu %lu)\n", (unsigned long)regs.user_syscall_nr, (unsigned long)regs.user_arg0, (unsigned long)regs.user_arg1, (unsigned long)regs.user_arg2, (unsigned long)regs.user_arg3, (unsigned long)regs.user_arg4, (unsigned long)regs.user_arg5);
+		nerrs++;
+	} else {
+		printf("[OK]\tReplacement nr and args are correct\n");
+	}
+
+	if (ptrace(PTRACE_CONT, chld, 0, 0) != 0)
+		err(1, "PTRACE_CONT");
+	if (waitpid(chld, &status, 0) != chld)
+		err(1, "waitpid");
+	if (!WIFEXITED(status) || WEXITSTATUS(status) != 0) {
+		printf("[FAIL]\tChild failed\n");
+		nerrs++;
+	} else {
+		printf("[OK]\tChild exited cleanly\n");
+	}
+}
+
+int main()
+{
+	printf("[RUN]\tCheck int80 return regs\n");
+	test_sys32_regs(do_full_int80);
+
+#if defined(__i386__) && (!defined(__GLIBC__) || __GLIBC__ > 2 || __GLIBC_MINOR__ >= 16)
+	vsyscall32 = (void *)getauxval(AT_SYSINFO);
+	printf("[RUN]\tCheck AT_SYSINFO return regs\n");
+	test_sys32_regs(do_full_vsyscall32);
+#endif
+
+	test_ptrace_syscall_restart();
+
+	return 0;
+}

tools/testing/selftests/x86/raw_syscall_helper_32.S

@@ -0,0 +1,46 @@
+.global sys32_helper
+sys32_helper:
+	/* Args: syscall_args_32*, function pointer */
+	pushl	%ebp
+	pushl	%ebx
+	pushl	%esi
+	pushl	%edi
+	movl	5*4(%esp), %eax	/* pointer to args struct */
+
+	movl	1*4(%eax), %ebx
+	movl	2*4(%eax), %ecx
+	movl	3*4(%eax), %edx
+	movl	4*4(%eax), %esi
+	movl	5*4(%eax), %edi
+	movl	6*4(%eax), %ebp
+	movl	0*4(%eax), %eax
+
+	call	*(6*4)(%esp)	/* Do the syscall */
+
+	/* Now we need to recover without losing any reg values */
+	pushl	%eax
+	movl	6*4(%esp), %eax
+	popl	0*4(%eax)
+	movl	%ebx, 1*4(%eax)
+	movl	%ecx, 2*4(%eax)
+	movl	%edx, 3*4(%eax)
+	movl	%esi, 4*4(%eax)
+	movl	%edi, 5*4(%eax)
+	movl	%ebp, 6*4(%eax)
+
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	popl	%ebp
+	ret
+
+	.type sys32_helper, @function
+	.size sys32_helper, .-sys32_helper
+
+.global int80_and_ret
+int80_and_ret:
+	int	$0x80
+	ret
+
+	.type int80_and_ret, @function
+	.size int80_and_ret, .-int80_and_ret

tools/testing/selftests/x86/test_syscall_vdso.c

@@ -0,0 +1,401 @@
+/*
+ * 32-bit syscall ABI conformance test.
+ *
+ * Copyright (c) 2015 Denys Vlasenko
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+/*
+ * Can be built statically:
+ * gcc -Os -Wall -static -m32 test_syscall_vdso.c thunks_32.S
+ */
+#undef _GNU_SOURCE
+#define _GNU_SOURCE 1
+#undef __USE_GNU
+#define __USE_GNU 1
+#include <unistd.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdio.h>
+#include <signal.h>
+#include <sys/types.h>
+#include <sys/select.h>
+#include <sys/time.h>
+#include <elf.h>
+#include <sys/ptrace.h>
+#include <sys/wait.h>
+
+#if !defined(__i386__)
+int main(int argc, char **argv, char **envp)
+{
+	printf("[SKIP]\tNot a 32-bit x86 userspace\n");
+	return 0;
+}
+#else
+
+long syscall_addr;
+long get_syscall(char **envp)
+{
+	Elf32_auxv_t *auxv;
+	while (*envp++ != NULL)
+		continue;
+	for (auxv = (void *)envp; auxv->a_type != AT_NULL; auxv++)
+		if (auxv->a_type == AT_SYSINFO)
+			return auxv->a_un.a_val;
+	printf("[WARN]\tAT_SYSINFO not supplied\n");
+	return 0;
+}
+
+asm (
+	"	.pushsection .text\n"
+	"	.global	int80\n"
+	"int80:\n"
+	"	int	$0x80\n"
+	"	ret\n"
+	"	.popsection\n"
+);
+extern char int80;
+
+struct regs64 {
+	uint64_t rax, rbx, rcx, rdx;
+	uint64_t rsi, rdi, rbp, rsp;
+	uint64_t r8,  r9,  r10, r11;
+	uint64_t r12, r13, r14, r15;
+};
+struct regs64 regs64;
+int kernel_is_64bit;
+
+asm (
+	"	.pushsection .text\n"
+	"	.code64\n"
+	"get_regs64:\n"
+	"	push	%rax\n"
+	"	mov	$regs64, %eax\n"
+	"	pop	0*8(%rax)\n"
+	"	movq	%rbx, 1*8(%rax)\n"
+	"	movq	%rcx, 2*8(%rax)\n"
+	"	movq	%rdx, 3*8(%rax)\n"
+	"	movq	%rsi, 4*8(%rax)\n"
+	"	movq	%rdi, 5*8(%rax)\n"
+	"	movq	%rbp, 6*8(%rax)\n"
+	"	movq	%rsp, 7*8(%rax)\n"
+	"	movq	%r8,  8*8(%rax)\n"
+	"	movq	%r9,  9*8(%rax)\n"
+	"	movq	%r10, 10*8(%rax)\n"
+	"	movq	%r11, 11*8(%rax)\n"
+	"	movq	%r12, 12*8(%rax)\n"
+	"	movq	%r13, 13*8(%rax)\n"
+	"	movq	%r14, 14*8(%rax)\n"
+	"	movq	%r15, 15*8(%rax)\n"
+	"	ret\n"
+	"poison_regs64:\n"
+	"	movq	$0x7f7f7f7f, %r8\n"
+	"	shl	$32, %r8\n"
+	"	orq	$0x7f7f7f7f, %r8\n"
+	"	movq	%r8, %r9\n"
+	"	movq	%r8, %r10\n"
+	"	movq	%r8, %r11\n"
+	"	movq	%r8, %r12\n"
+	"	movq	%r8, %r13\n"
+	"	movq	%r8, %r14\n"
+	"	movq	%r8, %r15\n"
+	"	ret\n"
+	"	.code32\n"
+	"	.popsection\n"
+);
+extern void get_regs64(void);
+extern void poison_regs64(void);
+extern unsigned long call64_from_32(void (*function)(void));
+void print_regs64(void)
+{
+	if (!kernel_is_64bit)
+		return;
+	printf("ax:%016llx bx:%016llx cx:%016llx dx:%016llx\n", regs64.rax,  regs64.rbx,  regs64.rcx,  regs64.rdx);
+	printf("si:%016llx di:%016llx bp:%016llx sp:%016llx\n", regs64.rsi,  regs64.rdi,  regs64.rbp,  regs64.rsp);
+	printf(" 8:%016llx  9:%016llx 10:%016llx 11:%016llx\n", regs64.r8 ,  regs64.r9 ,  regs64.r10,  regs64.r11);
+	printf("12:%016llx 13:%016llx 14:%016llx 15:%016llx\n", regs64.r12,  regs64.r13,  regs64.r14,  regs64.r15);
+}
+
+int check_regs64(void)
+{
+	int err = 0;
+	int num = 8;
+	uint64_t *r64 = &regs64.r8;
+
+	if (!kernel_is_64bit)
+		return 0;
+
+	do {
+		if (*r64 == 0x7f7f7f7f7f7f7f7fULL)
+			continue; /* register did not change */
+		if (syscall_addr != (long)&int80) {
+			/*
+			 * Non-INT80 syscall entrypoints are allowed to clobber R8+ regs:
+			 * either clear them to 0, or for R11, load EFLAGS.
+			 */
+			if (*r64 == 0)
+				continue;
+			if (num == 11) {
+				printf("[NOTE]\tR11 has changed:%016llx - assuming clobbered by SYSRET insn\n", *r64);
+				continue;
+			}
+		} else {
+			/* INT80 syscall entrypoint can be used by
+			 * 64-bit programs too, unlike SYSCALL/SYSENTER.
+			 * Therefore it must preserve R12+
+			 * (they are callee-saved registers in 64-bit C ABI).
+			 *
+			 * This was probably historically not intended,
+			 * but R8..11 are clobbered (cleared to 0).
+			 * IOW: they are the only registers which aren't
+			 * preserved across INT80 syscall.
+			 */
+			if (*r64 == 0 && num <= 11)
+				continue;
+		}
+		printf("[FAIL]\tR%d has changed:%016llx\n", num, *r64);
+		err++;
+	} while (r64++, ++num < 16);
+
+	if (!err)
+		printf("[OK]\tR8..R15 did not leak kernel data\n");
+	return err;
+}
+
+int nfds;
+fd_set rfds;
+fd_set wfds;
+fd_set efds;
+struct timespec timeout;
+sigset_t sigmask;
+struct {
+	sigset_t *sp;
+	int sz;
+} sigmask_desc;
+
+void prep_args()
+{
+	nfds = 42;
+	FD_ZERO(&rfds);
+	FD_ZERO(&wfds);
+	FD_ZERO(&efds);
+	FD_SET(0, &rfds);
+	FD_SET(1, &wfds);
+	FD_SET(2, &efds);
+	timeout.tv_sec = 0;
+	timeout.tv_nsec = 123;
+	sigemptyset(&sigmask);
+	sigaddset(&sigmask, SIGINT);
+	sigaddset(&sigmask, SIGUSR2);
+	sigaddset(&sigmask, SIGRTMAX);
+	sigmask_desc.sp = &sigmask;
+	sigmask_desc.sz = 8; /* bytes */
+}
+
+static void print_flags(const char *name, unsigned long r)
+{
+	static const char *bitarray[] = {
+	"\n" ,"c\n" ,/* Carry Flag */
+	"0 " ,"1 "  ,/* Bit 1 - always on */
+	""   ,"p "  ,/* Parity Flag */
+	"0 " ,"3? " ,
+	""   ,"a "  ,/* Auxiliary carry Flag */
+	"0 " ,"5? " ,
+	""   ,"z "  ,/* Zero Flag */
+	""   ,"s "  ,/* Sign Flag */
+	""   ,"t "  ,/* Trap Flag */
+	""   ,"i "  ,/* Interrupt Flag */
+	""   ,"d "  ,/* Direction Flag */
+	""   ,"o "  ,/* Overflow Flag */
+	"0 " ,"1 "  ,/* I/O Privilege Level (2 bits) */
+	"0"  ,"1"   ,/* I/O Privilege Level (2 bits) */
+	""   ,"n "  ,/* Nested Task */
+	"0 " ,"15? ",
+	""   ,"r "  ,/* Resume Flag */
+	""   ,"v "  ,/* Virtual Mode */
+	""   ,"ac " ,/* Alignment Check/Access Control */
+	""   ,"vif ",/* Virtual Interrupt Flag */
+	""   ,"vip ",/* Virtual Interrupt Pending */
+	""   ,"id " ,/* CPUID detection */
+	NULL
+	};
+	const char **bitstr;
+	int bit;
+
+	printf("%s=%016lx ", name, r);
+	bitstr = bitarray + 42;
+	bit = 21;
+	if ((r >> 22) != 0)
+		printf("(extra bits are set) ");
+	do {
+		if (bitstr[(r >> bit) & 1][0])
+			fputs(bitstr[(r >> bit) & 1], stdout);
+		bitstr -= 2;
+		bit--;
+	} while (bit >= 0);
+}
+
+int run_syscall(void)
+{
+	long flags, bad_arg;
+
+	prep_args();
+
+	if (kernel_is_64bit)
+		call64_from_32(poison_regs64);
+	/*print_regs64();*/
+
+	asm("\n"
+	/* Try 6-arg syscall: pselect. It should return quickly */
+	"	push	%%ebp\n"
+	"	mov	$308, %%eax\n"     /* PSELECT */
+	"	mov	nfds, %%ebx\n"     /* ebx  arg1 */
+	"	mov	$rfds, %%ecx\n"    /* ecx  arg2 */
+	"	mov	$wfds, %%edx\n"    /* edx  arg3 */
+	"	mov	$efds, %%esi\n"    /* esi  arg4 */
+	"	mov	$timeout, %%edi\n" /* edi  arg5 */
+	"	mov	$sigmask_desc, %%ebp\n" /* %ebp arg6 */
+	"	push	$0x200ed7\n"      /* set almost all flags */
+	"	popf\n"		/* except TF, IOPL, NT, RF, VM, AC, VIF, VIP */
+	"	call	*syscall_addr\n"
+	/* Check that registers are not clobbered */
+	"	pushf\n"
+	"	pop	%%eax\n"
+	"	cld\n"
+	"	cmp	nfds, %%ebx\n"     /* ebx  arg1 */
+	"	mov	$1, %%ebx\n"
+	"	jne	1f\n"
+	"	cmp	$rfds, %%ecx\n"    /* ecx  arg2 */
+	"	mov	$2, %%ebx\n"
+	"	jne	1f\n"
+	"	cmp	$wfds, %%edx\n"    /* edx  arg3 */
+	"	mov	$3, %%ebx\n"
+	"	jne	1f\n"
+	"	cmp	$efds, %%esi\n"    /* esi  arg4 */
+	"	mov	$4, %%ebx\n"
+	"	jne	1f\n"
+	"	cmp	$timeout, %%edi\n" /* edi  arg5 */
+	"	mov	$5, %%ebx\n"
+	"	jne	1f\n"
+	"	cmpl	$sigmask_desc, %%ebp\n" /* %ebp arg6 */
+	"	mov	$6, %%ebx\n"
+	"	jne	1f\n"
+	"	mov	$0, %%ebx\n"
+	"1:\n"
+	"	pop	%%ebp\n"
+	: "=a" (flags), "=b" (bad_arg)
+	:
+	: "cx", "dx", "si", "di"
+	);
+
+	if (kernel_is_64bit) {
+		memset(&regs64, 0x77, sizeof(regs64));
+		call64_from_32(get_regs64);
+		/*print_regs64();*/
+	}
+
+	/*
+	 * On paravirt kernels, flags are not preserved across syscalls.
+	 * Thus, we do not consider it a bug if some are changed.
+	 * We just show ones which do.
+	 */
+	if ((0x200ed7 ^ flags) != 0) {
+		print_flags("[WARN]\tFlags before", 0x200ed7);
+		print_flags("[WARN]\tFlags  after", flags);
+		print_flags("[WARN]\tFlags change", (0x200ed7 ^ flags));
+	}
+
+	if (bad_arg) {
+		printf("[FAIL]\targ#%ld clobbered\n", bad_arg);
+		return 1;
+	}
+	printf("[OK]\tArguments are preserved across syscall\n");
+
+	return check_regs64();
+}
+
+int run_syscall_twice()
+{
+	int exitcode = 0;
+	long sv;
+
+	if (syscall_addr) {
+		printf("[RUN]\tExecuting 6-argument 32-bit syscall via VDSO\n");
+		exitcode = run_syscall();
+	}
+	sv = syscall_addr;
+	syscall_addr = (long)&int80;
+	printf("[RUN]\tExecuting 6-argument 32-bit syscall via INT 80\n");
+	exitcode += run_syscall();
+	syscall_addr = sv;
+	return exitcode;
+}
+
+void ptrace_me()
+{
+	pid_t pid;
+
+	fflush(NULL);
+	pid = fork();
+	if (pid < 0)
+		exit(1);
+	if (pid == 0) {
+		/* child */
+		if (ptrace(PTRACE_TRACEME, 0L, 0L, 0L) != 0)
+			exit(0);
+		raise(SIGSTOP);
+		return;
+	}
+	/* parent */
+	printf("[RUN]\tRunning tests under ptrace\n");
+	while (1) {
+		int status;
+		pid = waitpid(-1, &status, __WALL);
+		if (WIFEXITED(status))
+			exit(WEXITSTATUS(status));
+		if (WIFSIGNALED(status))
+			exit(WTERMSIG(status));
+		if (pid <= 0 || !WIFSTOPPED(status)) /* paranoia */
+			exit(255);
+		/*
+		 * Note: we do not inject sig = WSTOPSIG(status).
+		 * We probably should, but careful: do not inject SIGTRAP
+		 * generated by syscall entry/exit stops.
+		 * That kills the child.
+		 */
+		ptrace(PTRACE_SYSCALL, pid, 0L, 0L /*sig*/);
+	}
+}
+
+int main(int argc, char **argv, char **envp)
+{
+	int exitcode = 0;
+	int cs;
+
+	asm("\n"
+	"	movl	%%cs, %%eax\n"
+	: "=a" (cs)
+	);
+	kernel_is_64bit = (cs == 0x23);
+	if (!kernel_is_64bit)
+		printf("[NOTE]\tNot a 64-bit kernel, won't test R8..R15 leaks\n");
+
+	/* This only works for non-static builds:
+	 * syscall_addr = dlsym(dlopen("linux-gate.so.1", RTLD_NOW), "__kernel_vsyscall");
+	 */
+	syscall_addr = get_syscall(envp);
+
+	exitcode += run_syscall_twice();
+	ptrace_me();
+	exitcode += run_syscall_twice();
+
+	return exitcode;
+}
+#endif

tools/testing/selftests/x86/thunks_32.S

@@ -0,0 +1,55 @@
+/*
+ * thunks_32.S - assembly helpers for mixed-bitness code
+ * Copyright (c) 2015 Denys Vlasenko
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * These are little helpers that make it easier to switch bitness on
+ * the fly.
+ */
+
+	.text
+	.code32
+
+	.global call64_from_32
+	.type call32_from_64, @function
+
+	// 4(%esp): function to call
+call64_from_32:
+	// Fetch function address
+	mov	4(%esp), %eax
+
+	// Save registers which are callee-clobbered by 64-bit ABI
+	push	%ecx
+	push	%edx
+	push	%esi
+	push	%edi
+
+	// Switch to long mode
+	jmp	$0x33,$1f
+1:	.code64
+
+	// Call the function
+	call	*%rax
+
+	// Switch to compatibility mode
+	push	$0x23  /* USER32_CS */
+	.code32; push $1f; .code64 /* hack: can't have X86_64_32S relocation in 32-bit ELF */
+	lretq
+1:	.code32
+
+	pop	%edi
+	pop	%esi
+	pop	%edx
+	pop	%ecx
+
+	ret
+
+.size call64_from_32, .-call64_from_32

tools/testing/selftests/x86/unwind_vdso.c

@@ -0,0 +1,211 @@
+/*
+ * unwind_vdso.c - tests unwind info for AT_SYSINFO in the vDSO
+ * Copyright (c) 2014-2015 Andrew Lutomirski
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * This tests __kernel_vsyscall's unwind info.
+ */
+
+#define _GNU_SOURCE
+
+#include <features.h>
+#include <stdio.h>
+
+#if defined(__GLIBC__) && __GLIBC__ == 2 && __GLIBC_MINOR__ < 16
+
+int main()
+{
+	/* We need getauxval(). */
+	printf("[SKIP]\tGLIBC before 2.16 cannot compile this test\n");
+	return 0;
+}
+
+#else
+
+#include <sys/time.h>
+#include <stdlib.h>
+#include <syscall.h>
+#include <unistd.h>
+#include <string.h>
+#include <inttypes.h>
+#include <sys/mman.h>
+#include <signal.h>
+#include <sys/ucontext.h>
+#include <err.h>
+#include <stddef.h>
+#include <stdbool.h>
+#include <sys/ptrace.h>
+#include <sys/user.h>
+#include <sys/ucontext.h>
+#include <link.h>
+#include <sys/auxv.h>
+#include <dlfcn.h>
+#include <unwind.h>
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+		       int flags)
+{
+	struct sigaction sa;
+	memset(&sa, 0, sizeof(sa));
+	sa.sa_sigaction = handler;
+	sa.sa_flags = SA_SIGINFO | flags;
+	sigemptyset(&sa.sa_mask);
+	if (sigaction(sig, &sa, 0))
+		err(1, "sigaction");
+}
+
+#ifdef __x86_64__
+# define WIDTH "q"
+#else
+# define WIDTH "l"
+#endif
+
+static unsigned long get_eflags(void)
+{
+	unsigned long eflags;
+	asm volatile ("pushf" WIDTH "\n\tpop" WIDTH " %0" : "=rm" (eflags));
+	return eflags;
+}
+
+static void set_eflags(unsigned long eflags)
+{
+	asm volatile ("push" WIDTH " %0\n\tpopf" WIDTH
+		      : : "rm" (eflags) : "flags");
+}
+
+#define X86_EFLAGS_TF (1UL << 8)
+
+static volatile sig_atomic_t nerrs;
+static unsigned long sysinfo;
+static bool got_sysinfo = false;
+static unsigned long return_address;
+
+struct unwind_state {
+	unsigned long ip;	/* trap source */
+	int depth;		/* -1 until we hit the trap source */
+};
+
+_Unwind_Reason_Code trace_fn(struct _Unwind_Context * ctx, void *opaque)
+{
+	struct unwind_state *state = opaque;
+	unsigned long ip = _Unwind_GetIP(ctx);
+
+	if (state->depth == -1) {
+		if (ip == state->ip)
+			state->depth = 0;
+		else
+			return _URC_NO_REASON;	/* Not there yet */
+	}
+	printf("\t  0x%lx\n", ip);
+
+	if (ip == return_address) {
+		/* Here we are. */
+		unsigned long eax = _Unwind_GetGR(ctx, 0);
+		unsigned long ecx = _Unwind_GetGR(ctx, 1);
+		unsigned long edx = _Unwind_GetGR(ctx, 2);
+		unsigned long ebx = _Unwind_GetGR(ctx, 3);
+		unsigned long ebp = _Unwind_GetGR(ctx, 5);
+		unsigned long esi = _Unwind_GetGR(ctx, 6);
+		unsigned long edi = _Unwind_GetGR(ctx, 7);
+		bool ok = (eax == SYS_getpid || eax == getpid()) &&
+			ebx == 1 && ecx == 2 && edx == 3 &&
+			esi == 4 && edi == 5 && ebp == 6;
+
+		if (!ok)
+			nerrs++;
+		printf("[%s]\t  NR = %ld, args = %ld, %ld, %ld, %ld, %ld, %ld\n",
+		       (ok ? "OK" : "FAIL"),
+		       eax, ebx, ecx, edx, esi, edi, ebp);
+
+		return _URC_NORMAL_STOP;
+	} else {
+		state->depth++;
+		return _URC_NO_REASON;
+	}
+}
+
+static void sigtrap(int sig, siginfo_t *info, void *ctx_void)
+{
+	ucontext_t *ctx = (ucontext_t *)ctx_void;
+	struct unwind_state state;
+	unsigned long ip = ctx->uc_mcontext.gregs[REG_EIP];
+
+	if (!got_sysinfo && ip == sysinfo) {
+		got_sysinfo = true;
+
+		/* Find the return address. */
+		return_address = *(unsigned long *)(unsigned long)ctx->uc_mcontext.gregs[REG_ESP];
+
+		printf("\tIn vsyscall at 0x%lx, returning to 0x%lx\n",
+		       ip, return_address);
+	}
+
+	if (!got_sysinfo)
+		return;		/* Not there yet */
+
+	if (ip == return_address) {
+		ctx->uc_mcontext.gregs[REG_EFL] &= ~X86_EFLAGS_TF;
+		printf("\tVsyscall is done\n");
+		return;
+	}
+
+	printf("\tSIGTRAP at 0x%lx\n", ip);
+
+	state.ip = ip;
+	state.depth = -1;
+	_Unwind_Backtrace(trace_fn, &state);
+}
+
+int main()
+{
+	sysinfo = getauxval(AT_SYSINFO);
+	printf("\tAT_SYSINFO is 0x%lx\n", sysinfo);
+
+	Dl_info info;
+	if (!dladdr((void *)sysinfo, &info)) {
+		printf("[WARN]\tdladdr failed on AT_SYSINFO\n");
+	} else {
+		printf("[OK]\tAT_SYSINFO maps to %s, loaded at 0x%p\n",
+		       info.dli_fname, info.dli_fbase);
+	}
+
+	sethandler(SIGTRAP, sigtrap, 0);
+
+	syscall(SYS_getpid);  /* Force symbol binding without TF set. */
+	printf("[RUN]\tSet TF and check a fast syscall\n");
+	set_eflags(get_eflags() | X86_EFLAGS_TF);
+	syscall(SYS_getpid, 1, 2, 3, 4, 5, 6);
+	if (!got_sysinfo) {
+		set_eflags(get_eflags() & ~X86_EFLAGS_TF);
+
+		/*
+		 * The most likely cause of this is that you're on Debian or
+		 * a Debian-based distro, you're missing libc6-i686, and you're
+		 * affected by libc/19006 (https://sourceware.org/PR19006).
+		 */
+		printf("[WARN]\tsyscall(2) didn't enter AT_SYSINFO\n");
+	}
+
+	if (get_eflags() & X86_EFLAGS_TF) {
+		printf("[FAIL]\tTF is still set\n");
+		nerrs++;
+	}
+
+	if (nerrs) {
+		printf("[FAIL]\tThere were errors\n");
+		return 1;
+	} else {
+		printf("[OK]\tAll is well\n");
+		return 0;
+	}
+}
+
+#endif	/* New enough libc */