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

…x/kernel/git/tip/tip

Pull x86 asm changes from Ingo Molnar:
 "The biggest changes in this cycle were:

   - Revamp, simplify (and in some cases fix) Time Stamp Counter (TSC)
     primitives.  (Andy Lutomirski)

   - Add new, comprehensible entry and exit handlers written in C.
     (Andy Lutomirski)

   - vm86 mode cleanups and fixes.  (Brian Gerst)

   - 32-bit compat code cleanups.  (Brian Gerst)

  The amount of simplification in low level assembly code is already
  palpable:

     arch/x86/entry/entry_32.S                          | 130 +----
     arch/x86/entry/entry_64.S                          | 197 ++-----

  but more simplifications are planned.

  There's also the usual laudry mix of low level changes - see the
  changelog for details"

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (83 commits)
  x86/asm: Drop repeated macro of X86_EFLAGS_AC definition
  x86/asm/msr: Make wrmsrl() a function
  x86/asm/delay: Introduce an MWAITX-based delay with a configurable timer
  x86/asm: Add MONITORX/MWAITX instruction support
  x86/traps: Weaken context tracking entry assertions
  x86/asm/tsc: Add rdtscll() merge helper
  selftests/x86: Add syscall_nt selftest
  selftests/x86: Disable sigreturn_64
  x86/vdso: Emit a GNU hash
  x86/entry: Remove do_notify_resume(), syscall_trace_leave(), and their TIF masks
  x86/entry/32: Migrate to C exit path
  x86/entry/32: Remove 32-bit syscall audit optimizations
  x86/vm86: Rename vm86->v86flags and v86mask
  x86/vm86: Rename vm86->vm86_info to user_vm86
  x86/vm86: Clean up vm86.h includes
  x86/vm86: Move the vm86 IRQ definitions to vm86.h
  x86/vm86: Use the normal pt_regs area for vm86
  x86/vm86: Eliminate 'struct kernel_vm86_struct'
  x86/vm86: Move fields from 'struct kernel_vm86_struct' to 'struct vm86'
  x86/vm86: Move vm86 fields out of 'thread_struct'
  ...

arch/um/include/shared/kern_util.h

@@ -22,7 +22,8 @@ extern int kmalloc_ok;
 extern unsigned long alloc_stack(int order, int atomic);
 extern void free_stack(unsigned long stack, int order);
 
-extern int do_signal(void);
+struct pt_regs;
+extern void do_signal(struct pt_regs *regs);
 extern void interrupt_end(void);
 extern void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs);
 

arch/um/kernel/process.c

@@ -90,12 +90,14 @@ void *__switch_to(struct task_struct *from, struct task_struct *to)
 
 void interrupt_end(void)
 {
+	struct pt_regs *regs = &current->thread.regs;
+
 	if (need_resched())
 		schedule();
 	if (test_thread_flag(TIF_SIGPENDING))
-		do_signal();
+		do_signal(regs);
 	if (test_and_clear_thread_flag(TIF_NOTIFY_RESUME))
-		tracehook_notify_resume(&current->thread.regs);
+		tracehook_notify_resume(regs);
 }
 
 void exit_thread(void)

arch/um/kernel/signal.c

@@ -64,7 +64,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	signal_setup_done(err, ksig, singlestep);
 }
 
-static int kern_do_signal(struct pt_regs *regs)
+void do_signal(struct pt_regs *regs)
 {
 	struct ksignal ksig;
 	int handled_sig = 0;
@@ -110,10 +110,4 @@ static int kern_do_signal(struct pt_regs *regs)
 	 */
 	if (!handled_sig)
 		restore_saved_sigmask();
-	return handled_sig;
-}
-
-int do_signal(void)
-{
-	return kern_do_signal(&current->thread.regs);
 }

arch/um/kernel/tlb.c

@@ -291,7 +291,7 @@ void fix_range_common(struct mm_struct *mm, unsigned long start_addr,
 		/* We are under mmap_sem, release it such that current can terminate */
 		up_write(&current->mm->mmap_sem);
 		force_sig(SIGKILL, current);
-		do_signal();
+		do_signal(&current->thread.regs);
 	}
 }
 

arch/um/kernel/trap.c

@@ -173,7 +173,7 @@ static void bad_segv(struct faultinfo fi, unsigned long ip)
 void fatal_sigsegv(void)
 {
 	force_sigsegv(SIGSEGV, current);
-	do_signal();
+	do_signal(&current->thread.regs);
 	/*
 	 * This is to tell gcc that we're not returning - do_signal
 	 * can, in general, return, but in this case, it's not, since

arch/x86/Kconfig

@@ -133,7 +133,7 @@ config X86
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_SYSCALL_TRACEPOINTS
-	select HAVE_UID16			if X86_32
+	select HAVE_UID16			if X86_32 || IA32_EMULATION
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select HAVE_USER_RETURN_NOTIFIER
 	select IRQ_FORCED_THREADING
@@ -1003,19 +1003,41 @@ config X86_THERMAL_VECTOR
 	def_bool y
 	depends on X86_MCE_INTEL
 
-config VM86
-	bool "Enable VM86 support" if EXPERT
-	default y
+config X86_LEGACY_VM86
+	bool "Legacy VM86 support (obsolete)"
+	default n
 	depends on X86_32
 	---help---
-	  This option is required by programs like DOSEMU to run
-	  16-bit real mode legacy code on x86 processors. It also may
-	  be needed by software like XFree86 to initialize some video
-	  cards via BIOS. Disabling this option saves about 6K.
+	  This option allows user programs to put the CPU into V8086
+	  mode, which is an 80286-era approximation of 16-bit real mode.
+
+	  Some very old versions of X and/or vbetool require this option
+	  for user mode setting.  Similarly, DOSEMU will use it if
+	  available to accelerate real mode DOS programs.  However, any
+	  recent version of DOSEMU, X, or vbetool should be fully
+	  functional even without kernel VM86 support, as they will all
+	  fall back to (pretty well performing) software emulation.
+
+	  Anything that works on a 64-bit kernel is unlikely to need
+	  this option, as 64-bit kernels don't, and can't, support V8086
+	  mode.  This option is also unrelated to 16-bit protected mode
+	  and is not needed to run most 16-bit programs under Wine.
+
+	  Enabling this option adds considerable attack surface to the
+	  kernel and slows down system calls and exception handling.
+
+	  Unless you use very old userspace or need the last drop of
+	  performance in your real mode DOS games and can't use KVM,
+	  say N here.
+
+config VM86
+       bool
+       default X86_LEGACY_VM86
 
 config X86_16BIT
 	bool "Enable support for 16-bit segments" if EXPERT
 	default y
+	depends on MODIFY_LDT_SYSCALL
 	---help---
 	  This option is required by programs like Wine to run 16-bit
 	  protected mode legacy code on x86 processors.  Disabling
@@ -1510,6 +1532,7 @@ config X86_RESERVE_LOW
 
 config MATH_EMULATION
 	bool
+	depends on MODIFY_LDT_SYSCALL
 	prompt "Math emulation" if X86_32
 	---help---
 	  Linux can emulate a math coprocessor (used for floating point
@@ -2054,6 +2077,22 @@ config CMDLINE_OVERRIDE
 	  This is used to work around broken boot loaders.  This should
 	  be set to 'N' under normal conditions.
 
+config MODIFY_LDT_SYSCALL
+	bool "Enable the LDT (local descriptor table)" if EXPERT
+	default y
+	---help---
+	  Linux can allow user programs to install a per-process x86
+	  Local Descriptor Table (LDT) using the modify_ldt(2) system
+	  call.  This is required to run 16-bit or segmented code such as
+	  DOSEMU or some Wine programs.  It is also used by some very old
+	  threading libraries.
+
+	  Enabling this feature adds a small amount of overhead to
+	  context switches and increases the low-level kernel attack
+	  surface.  Disabling it removes the modify_ldt(2) system call.
+
+	  Saying 'N' here may make sense for embedded or server kernels.
+
 source "kernel/livepatch/Kconfig"
 
 endmenu
@@ -2523,7 +2562,7 @@ config IA32_EMULATION
 	depends on X86_64
 	select BINFMT_ELF
 	select COMPAT_BINFMT_ELF
-	select HAVE_UID16
+	select ARCH_WANT_OLD_COMPAT_IPC
 	---help---
 	  Include code to run legacy 32-bit programs under a
 	  64-bit kernel. You should likely turn this on, unless you're
@@ -2537,7 +2576,7 @@ config IA32_AOUT
 
 config X86_X32
 	bool "x32 ABI for 64-bit mode"
-	depends on X86_64 && IA32_EMULATION
+	depends on X86_64
 	---help---
 	  Include code to run binaries for the x32 native 32-bit ABI
 	  for 64-bit processors.  An x32 process gets access to the
@@ -2551,7 +2590,6 @@ config X86_X32
 config COMPAT
 	def_bool y
 	depends on IA32_EMULATION || X86_X32
-	select ARCH_WANT_OLD_COMPAT_IPC
 
 if COMPAT
 config COMPAT_FOR_U64_ALIGNMENT

arch/x86/Makefile

@@ -39,6 +39,16 @@ ifdef CONFIG_X86_NEED_RELOCS
         LDFLAGS_vmlinux := --emit-relocs
 endif
 
+#
+# Prevent GCC from generating any FP code by mistake.
+#
+# This must happen before we try the -mpreferred-stack-boundary, see:
+#
+#    https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383
+#
+KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow
+KBUILD_CFLAGS += $(call cc-option,-mno-avx,)
+
 ifeq ($(CONFIG_X86_32),y)
         BITS := 32
         UTS_MACHINE := i386
@@ -167,9 +177,6 @@ KBUILD_CFLAGS += -pipe
 KBUILD_CFLAGS += -Wno-sign-compare
 #
 KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
-# prevent gcc from generating any FP code by mistake
-KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow
-KBUILD_CFLAGS += $(call cc-option,-mno-avx,)
 
 KBUILD_CFLAGS += $(mflags-y)
 KBUILD_AFLAGS += $(mflags-y)

arch/x86/boot/compressed/aslr.c

@@ -82,7 +82,7 @@ static unsigned long get_random_long(void)
 
 	if (has_cpuflag(X86_FEATURE_TSC)) {
 		debug_putstr(" RDTSC");
-		rdtscll(raw);
+		raw = rdtsc();
 
 		random ^= raw;
 		use_i8254 = false;

arch/x86/entry/Makefile

@@ -2,6 +2,7 @@
 # Makefile for the x86 low level entry code
 #
 obj-y				:= entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
+obj-y				+= common.o
 
 obj-y				+= vdso/
 obj-y				+= vsyscall/

arch/x86/entry/calling.h

@@ -135,9 +135,6 @@ For 32-bit we have the following conventions - kernel is built with
 	movq %rbp, 4*8+\offset(%rsp)
 	movq %rbx, 5*8+\offset(%rsp)
 	.endm
-	.macro SAVE_EXTRA_REGS_RBP offset=0
-	movq %rbp, 4*8+\offset(%rsp)
-	.endm
 
 	.macro RESTORE_EXTRA_REGS offset=0
 	movq 0*8+\offset(%rsp), %r15
@@ -193,12 +190,6 @@ For 32-bit we have the following conventions - kernel is built with
 	.macro RESTORE_C_REGS_EXCEPT_RCX_R11
 	RESTORE_C_REGS_HELPER 1,0,0,1,1
 	.endm
-	.macro RESTORE_RSI_RDI
-	RESTORE_C_REGS_HELPER 0,0,0,0,0
-	.endm
-	.macro RESTORE_RSI_RDI_RDX
-	RESTORE_C_REGS_HELPER 0,0,0,0,1
-	.endm
 
 	.macro REMOVE_PT_GPREGS_FROM_STACK addskip=0
 	subq $-(15*8+\addskip), %rsp