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
  ...

8 files changed, 121 insertions, 28 deletions

diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h
new file mode 100644
index 0000000..b7a1ab8
--- /dev/null
+++ b/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 */
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 141c561..1514753 100644
--- a/arch/x86/include/asm/elf.h
+++ b/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;
 
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 19577dd..b55f309 100644
--- a/arch/x86/include/asm/processor.h
+++ b/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();
 }
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index d7f3b3b..751bf4b 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/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 */	  \
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index d6a756a..999b7cd 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/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
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 809877e..c7b5510 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/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 */
 };
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index a8df874..09b1b0a 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/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 */
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index 8021bd2..756de91 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/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);