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:
 "There were lots of changes in this development cycle:

   - over 100 separate cleanups, restructuring changes, speedups and
     fixes in the x86 system call, irq, trap and other entry code, part
     of a heroic effort to deobfuscate a decade old spaghetti asm code
     and its C code dependencies (Denys Vlasenko, Andy Lutomirski)

   - alternatives code fixes and enhancements (Borislav Petkov)

   - simplifications and cleanups to the compat code (Brian Gerst)

   - signal handling fixes and new x86 testcases (Andy Lutomirski)

   - various other fixes and cleanups

  By their nature many of these changes are risky - we tried to test
  them well on many different x86 systems (there are no known
  regressions), and they are split up finely to help bisection - but
  there's still a fair bit of residual risk left so caveat emptor"

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (148 commits)
  perf/x86/64: Report regs_user->ax too in get_regs_user()
  perf/x86/64: Simplify regs_user->abi setting code in get_regs_user()
  perf/x86/64: Do report user_regs->cx while we are in syscall, in get_regs_user()
  perf/x86/64: Do not guess user_regs->cs, ss, sp in get_regs_user()
  x86/asm/entry/32: Tidy up JNZ instructions after TESTs
  x86/asm/entry/64: Reduce padding in execve stubs
  x86/asm/entry/64: Remove GET_THREAD_INFO() in ret_from_fork
  x86/asm/entry/64: Simplify jumps in ret_from_fork
  x86/asm/entry/64: Remove a redundant jump
  x86/asm/entry/64: Optimize [v]fork/clone stubs
  x86/asm/entry: Zero EXTRA_REGS for stub32_execve() too
  x86/asm/entry/64: Move stub_x32_execvecloser() to stub_execveat()
  x86/asm/entry/64: Use common code for rt_sigreturn() epilogue
  x86/asm/entry/64: Add forgotten CFI annotation
  x86/asm/entry/irq: Simplify interrupt dispatch table (IDT) layout
  x86/asm/entry/64: Move opportunistic sysret code to syscall code path
  x86, selftests: Add sigreturn selftest
  x86/alternatives: Guard NOPs optimization
  x86/asm/entry: Clear EXTRA_REGS for all executable formats
  x86/signal: Remove pax argument from restore_sigcontext
  ...

1 files changed, 52 insertions, 55 deletions

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index ec1c93588cef..d2203b5d9538 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -210,8 +210,23 @@ struct x86_hw_tss {
 	unsigned long		sp0;
 	unsigned short		ss0, __ss0h;
 	unsigned long		sp1;
-	/* ss1 caches MSR_IA32_SYSENTER_CS: */
-	unsigned short		ss1, __ss1h;
+
+	/*
+	 * We don't use ring 1, so ss1 is a convenient scratch space in
+	 * the same cacheline as sp0.  We use ss1 to cache the value in
+	 * MSR_IA32_SYSENTER_CS.  When we context switch
+	 * MSR_IA32_SYSENTER_CS, we first check if the new value being
+	 * written matches ss1, and, if it's not, then we wrmsr the new
+	 * value and update ss1.
+	 *
+	 * The only reason we context switch MSR_IA32_SYSENTER_CS is
+	 * that we set it to zero in vm86 tasks to avoid corrupting the
+	 * stack if we were to go through the sysenter path from vm86
+	 * mode.
+	 */
+	unsigned short		ss1;	/* MSR_IA32_SYSENTER_CS */
+
+	unsigned short		__ss1h;
 	unsigned long		sp2;
 	unsigned short		ss2, __ss2h;
 	unsigned long		__cr3;
@@ -276,13 +291,17 @@ struct tss_struct {
 	unsigned long		io_bitmap[IO_BITMAP_LONGS + 1];
 
 	/*
-	 * .. and then another 0x100 bytes for the emergency kernel stack:
+	 * Space for the temporary SYSENTER stack:
 	 */
-	unsigned long		stack[64];
+	unsigned long		SYSENTER_stack[64];
 
 } ____cacheline_aligned;
 
-DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss);
+DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss);
+
+#ifdef CONFIG_X86_32
+DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);
+#endif
 
 /*
  * Save the original ist values for checking stack pointers during debugging
@@ -474,7 +493,6 @@ struct thread_struct {
 #ifdef CONFIG_X86_32
 	unsigned long		sysenter_cs;
 #else
-	unsigned long		usersp;	/* Copy from PDA */
 	unsigned short		es;
 	unsigned short		ds;
 	unsigned short		fsindex;
@@ -564,6 +582,16 @@ static inline void native_swapgs(void)
 #endif
 }
 
+static inline unsigned long current_top_of_stack(void)
+{
+#ifdef CONFIG_X86_64
+	return this_cpu_read_stable(cpu_tss.x86_tss.sp0);
+#else
+	/* sp0 on x86_32 is special in and around vm86 mode. */
+	return this_cpu_read_stable(cpu_current_top_of_stack);
+#endif
+}
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else
@@ -761,10 +789,10 @@ extern char			ignore_fpu_irq;
 #define ARCH_HAS_SPINLOCK_PREFETCH
 
 #ifdef CONFIG_X86_32
-# define BASE_PREFETCH		ASM_NOP4
+# define BASE_PREFETCH		""
 # define ARCH_HAS_PREFETCH
 #else
-# define BASE_PREFETCH		"prefetcht0 (%1)"
+# define BASE_PREFETCH		"prefetcht0 %P1"
 #endif
 
 /*
@@ -775,10 +803,9 @@ extern char			ignore_fpu_irq;
  */
 static inline void prefetch(const void *x)
 {
-	alternative_input(BASE_PREFETCH,
-			  "prefetchnta (%1)",
+	alternative_input(BASE_PREFETCH, "prefetchnta %P1",
 			  X86_FEATURE_XMM,
-			  "r" (x));
+			  "m" (*(const char *)x));
 }
 
 /*
@@ -788,10 +815,9 @@ static inline void prefetch(const void *x)
  */
 static inline void prefetchw(const void *x)
 {
-	alternative_input(BASE_PREFETCH,
-			  "prefetchw (%1)",
-			  X86_FEATURE_3DNOW,
-			  "r" (x));
+	alternative_input(BASE_PREFETCH, "prefetchw %P1",
+			  X86_FEATURE_3DNOWPREFETCH,
+			  "m" (*(const char *)x));
 }
 
 static inline void spin_lock_prefetch(const void *x)
@@ -799,6 +825,9 @@ static inline void spin_lock_prefetch(const void *x)
 	prefetchw(x);
 }
 
+#define TOP_OF_INIT_STACK ((unsigned long)&init_stack + sizeof(init_stack) - \
+			   TOP_OF_KERNEL_STACK_PADDING)
+
 #ifdef CONFIG_X86_32
 /*
  * User space process size: 3GB (default).
@@ -809,39 +838,16 @@ static inline void spin_lock_prefetch(const void *x)
 #define STACK_TOP_MAX		STACK_TOP
 
 #define INIT_THREAD  {							  \
-	.sp0			= sizeof(init_stack) + (long)&init_stack, \
+	.sp0			= TOP_OF_INIT_STACK,			  \
 	.vm86_info		= NULL,					  \
 	.sysenter_cs		= __KERNEL_CS,				  \
 	.io_bitmap_ptr		= NULL,					  \
 }
 
-/*
- * Note that the .io_bitmap member must be extra-big. This is because
- * the CPU will access an additional byte beyond the end of the IO
- * permission bitmap. The extra byte must be all 1 bits, and must
- * be within the limit.
- */
-#define INIT_TSS  {							  \
-	.x86_tss = {							  \
-		.sp0		= sizeof(init_stack) + (long)&init_stack, \
-		.ss0		= __KERNEL_DS,				  \
-		.ss1		= __KERNEL_CS,				  \
-		.io_bitmap_base	= INVALID_IO_BITMAP_OFFSET,		  \
-	 },								  \
-	.io_bitmap		= { [0 ... IO_BITMAP_LONGS] = ~0 },	  \
-}
-
 extern unsigned long thread_saved_pc(struct task_struct *tsk);
 
-#define THREAD_SIZE_LONGS      (THREAD_SIZE/sizeof(unsigned long))
-#define KSTK_TOP(info)                                                 \
-({                                                                     \
-       unsigned long *__ptr = (unsigned long *)(info);                 \
-       (unsigned long)(&__ptr[THREAD_SIZE_LONGS]);                     \
-})
-
 /*
- * The below -8 is to reserve 8 bytes on top of the ring0 stack.
+ * TOP_OF_KERNEL_STACK_PADDING reserves 8 bytes on top of the ring0 stack.
  * This is necessary to guarantee that the entire "struct pt_regs"
  * is accessible even if the CPU haven't stored the SS/ESP registers
  * on the stack (interrupt gate does not save these registers
@@ -850,11 +856,11 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
  * "struct pt_regs" is possible, but they may contain the
  * completely wrong values.
  */
-#define task_pt_regs(task)                                             \
-({                                                                     \
-       struct pt_regs *__regs__;                                       \
-       __regs__ = (struct pt_regs *)(KSTK_TOP(task_stack_page(task))-8); \
-       __regs__ - 1;                                                   \
+#define task_pt_regs(task) \
+({									\
+	unsigned long __ptr = (unsigned long)task_stack_page(task);	\
+	__ptr += THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING;		\
+	((struct pt_regs *)__ptr) - 1;					\
 })
 
 #define KSTK_ESP(task)		(task_pt_regs(task)->sp)
@@ -886,11 +892,7 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
 #define STACK_TOP_MAX		TASK_SIZE_MAX
 
 #define INIT_THREAD  { \
-	.sp0 = (unsigned long)&init_stack + sizeof(init_stack) \
-}
-
-#define INIT_TSS  { \
-	.x86_tss.sp0 = (unsigned long)&init_stack + sizeof(init_stack) \
+	.sp0 = TOP_OF_INIT_STACK \
 }
 
 /*
@@ -902,11 +904,6 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
 #define task_pt_regs(tsk)	((struct pt_regs *)(tsk)->thread.sp0 - 1)
 extern unsigned long KSTK_ESP(struct task_struct *task);
 
-/*
- * User space RSP while inside the SYSCALL fast path
- */
-DECLARE_PER_CPU(unsigned long, old_rsp);
-
 #endif /* CONFIG_X86_64 */
 
 extern void start_thread(struct pt_regs *regs, unsigned long new_ip,