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

Pull low-level x86 updates from Ingo Molnar:
 "In this cycle this topic tree has become one of those 'super topics'
  that accumulated a lot of changes:

   - Add CONFIG_VMAP_STACK=y support to the core kernel and enable it on
     x86 - preceded by an array of changes. v4.8 saw preparatory changes
     in this area already - this is the rest of the work. Includes the
     thread stack caching performance optimization. (Andy Lutomirski)

   - switch_to() cleanups and all around enhancements. (Brian Gerst)

   - A large number of dumpstack infrastructure enhancements and an
     unwinder abstraction. The secret long term plan is safe(r) live
     patching plus maybe another attempt at debuginfo based unwinding -
     but all these current bits are standalone enhancements in a frame
     pointer based debug environment as well. (Josh Poimboeuf)

   - More __ro_after_init and const annotations. (Kees Cook)

   - Enable KASLR for the vmemmap memory region. (Thomas Garnier)"

[ The virtually mapped stack changes are pretty fundamental, and not
  x86-specific per se, even if they are only used on x86 right now. ]

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (70 commits)
  x86/asm: Get rid of __read_cr4_safe()
  thread_info: Use unsigned long for flags
  x86/alternatives: Add stack frame dependency to alternative_call_2()
  x86/dumpstack: Fix show_stack() task pointer regression
  x86/dumpstack: Remove dump_trace() and related callbacks
  x86/dumpstack: Convert show_trace_log_lvl() to use the new unwinder
  oprofile/x86: Convert x86_backtrace() to use the new unwinder
  x86/stacktrace: Convert save_stack_trace_*() to use the new unwinder
  perf/x86: Convert perf_callchain_kernel() to use the new unwinder
  x86/unwind: Add new unwind interface and implementations
  x86/dumpstack: Remove NULL task pointer convention
  fork: Optimize task creation by caching two thread stacks per CPU if CONFIG_VMAP_STACK=y
  sched/core: Free the stack early if CONFIG_THREAD_INFO_IN_TASK
  lib/syscall: Pin the task stack in collect_syscall()
  x86/process: Pin the target stack in get_wchan()
  x86/dumpstack: Pin the target stack when dumping it
  kthread: Pin the stack via try_get_task_stack()/put_task_stack() in to_live_kthread() function
  sched/core: Add try_get_task_stack() and put_task_stack()
  x86/entry/64: Fix a minor comment rebase error
  iommu/amd: Don't put completion-wait semaphore on stack
  ...

20 files changed, 237 insertions, 299 deletions

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index e77a6443104f..1b020381ab38 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -217,10 +217,14 @@ static inline int alternatives_text_reserved(void *start, void *end)
  */
 #define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2,   \
 			   output, input...)				      \
+{									      \
+	register void *__sp asm(_ASM_SP);				      \
 	asm volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\
 		"call %P[new2]", feature2)				      \
-		: output : [old] "i" (oldfunc), [new1] "i" (newfunc1),	      \
-		[new2] "i" (newfunc2), ## input)
+		: output, "+r" (__sp)					      \
+		: [old] "i" (oldfunc), [new1] "i" (newfunc1),		      \
+		  [new2] "i" (newfunc2), ## input);			      \
+}
 
 /*
  * use this macro(s) if you need more than one output parameter
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 4e10d73cf018..12080d87da3b 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -36,7 +36,7 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in
 
 extern struct desc_ptr idt_descr;
 extern gate_desc idt_table[];
-extern struct desc_ptr debug_idt_descr;
+extern const struct desc_ptr debug_idt_descr;
 extern gate_desc debug_idt_table[];
 
 struct gdt_page {
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index ae55a43e09c0..d4957ac72b48 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -45,7 +45,8 @@
 extern u64 xfeatures_mask;
 extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
 
-extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
+extern void __init update_regset_xstate_info(unsigned int size,
+					     u64 xstate_mask);
 
 void fpu__xstate_clear_all_cpu_caps(void);
 void *get_xsave_addr(struct xregs_state *xsave, int xstate);
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index a4820d4df617..eccd0ac6bc38 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -6,6 +6,7 @@
 # define MCOUNT_ADDR		((unsigned long)(__fentry__))
 #else
 # define MCOUNT_ADDR		((unsigned long)(mcount))
+# define HAVE_FUNCTION_GRAPH_FP_TEST
 #endif
 #define MCOUNT_INSN_SIZE	5 /* sizeof mcount call */
 
@@ -13,6 +14,8 @@
 #define ARCH_SUPPORTS_FTRACE_OPS 1
 #endif
 
+#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
+
 #ifndef __ASSEMBLY__
 extern void mcount(void);
 extern atomic_t modifying_ftrace_code;
diff --git a/arch/x86/include/asm/kaslr.h b/arch/x86/include/asm/kaslr.h
index 2674ee3de748..1052a797d71d 100644
--- a/arch/x86/include/asm/kaslr.h
+++ b/arch/x86/include/asm/kaslr.h
@@ -6,6 +6,7 @@ unsigned long kaslr_get_random_long(const char *purpose);
 #ifdef CONFIG_RANDOMIZE_MEMORY
 extern unsigned long page_offset_base;
 extern unsigned long vmalloc_base;
+extern unsigned long vmemmap_base;
 
 void kernel_randomize_memory(void);
 #else
diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h
index 1ef9d581b5d9..d31881188431 100644
--- a/arch/x86/include/asm/kdebug.h
+++ b/arch/x86/include/asm/kdebug.h
@@ -24,8 +24,6 @@ enum die_val {
 extern void printk_address(unsigned long address);
 extern void die(const char *, struct pt_regs *,long);
 extern int __must_check __die(const char *, struct pt_regs *, long);
-extern void show_trace(struct task_struct *t, struct pt_regs *regs,
-		       unsigned long *sp, unsigned long bp);
 extern void show_stack_regs(struct pt_regs *regs);
 extern void __show_regs(struct pt_regs *regs, int all);
 extern unsigned long oops_begin(void);
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 4cd8db05301f..ce932812f142 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -80,10 +80,6 @@ static inline unsigned long __read_cr4(void)
 {
 	return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4);
 }
-static inline unsigned long __read_cr4_safe(void)
-{
-	return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4_safe);
-}
 
 static inline void __write_cr4(unsigned long x)
 {
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 60aac60ba25f..0f400c0e4979 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -108,7 +108,6 @@ struct pv_cpu_ops {
 	unsigned long (*read_cr0)(void);
 	void (*write_cr0)(unsigned long);
 
-	unsigned long (*read_cr4_safe)(void);
 	unsigned long (*read_cr4)(void);
 	void (*write_cr4)(unsigned long);
 
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 6fdef9eef2d5..3a264200c62f 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -57,11 +57,13 @@ typedef struct { pteval_t pte; } pte_t;
 #define MAXMEM		_AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
 #define VMALLOC_SIZE_TB	_AC(32, UL)
 #define __VMALLOC_BASE	_AC(0xffffc90000000000, UL)
-#define VMEMMAP_START	_AC(0xffffea0000000000, UL)
+#define __VMEMMAP_BASE	_AC(0xffffea0000000000, UL)
 #ifdef CONFIG_RANDOMIZE_MEMORY
 #define VMALLOC_START	vmalloc_base
+#define VMEMMAP_START	vmemmap_base
 #else
 #define VMALLOC_START	__VMALLOC_BASE
+#define VMEMMAP_START	__VMEMMAP_BASE
 #endif /* CONFIG_RANDOMIZE_MEMORY */
 #define VMALLOC_END	(VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL))
 #define MODULES_VADDR    (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 63def9537a2d..984a7bf17f6a 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -389,9 +389,9 @@ struct thread_struct {
 	unsigned short		fsindex;
 	unsigned short		gsindex;
 #endif
-#ifdef CONFIG_X86_32
-	unsigned long		ip;
-#endif
+
+	u32			status;		/* thread synchronous flags */
+
 #ifdef CONFIG_X86_64
 	unsigned long		fsbase;
 	unsigned long		gsbase;
@@ -438,6 +438,15 @@ struct thread_struct {
 };
 
 /*
+ * Thread-synchronous status.
+ *
+ * This is different from the flags in that nobody else
+ * ever touches our thread-synchronous status, so we don't
+ * have to worry about atomic accesses.
+ */
+#define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
+
+/*
  * Set IOPL bits in EFLAGS from given mask
  */
 static inline void native_set_iopl_mask(unsigned mask)
@@ -724,8 +733,6 @@ static inline void spin_lock_prefetch(const void *x)
 	.addr_limit		= KERNEL_DS,				  \
 }
 
-extern unsigned long thread_saved_pc(struct task_struct *tsk);
-
 /*
  * 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"
@@ -776,17 +783,13 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
 	.addr_limit		= KERNEL_DS,			\
 }
 
-/*
- * Return saved PC of a blocked thread.
- * What is this good for? it will be always the scheduler or ret_from_fork.
- */
-#define thread_saved_pc(t)	READ_ONCE_NOCHECK(*(unsigned long *)((t)->thread.sp - 8))
-
 #define task_pt_regs(tsk)	((struct pt_regs *)(tsk)->thread.sp0 - 1)
 extern unsigned long KSTK_ESP(struct task_struct *task);
 
 #endif /* CONFIG_X86_64 */
 
+extern unsigned long thread_saved_pc(struct task_struct *tsk);
+
 extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
 					       unsigned long new_sp);
 
diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h
index b2988c0ed829..230e1903acf0 100644
--- a/arch/x86/include/asm/realmode.h
+++ b/arch/x86/include/asm/realmode.h
@@ -44,9 +44,9 @@ struct trampoline_header {
 extern struct real_mode_header *real_mode_header;
 extern unsigned char real_mode_blob_end[];
 
-extern unsigned long init_rsp;
 extern unsigned long initial_code;
 extern unsigned long initial_gs;
+extern unsigned long initial_stack;
 
 extern unsigned char real_mode_blob[];
 extern unsigned char real_mode_relocs[];
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index ebd0c164cd4e..19980b36f394 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -39,9 +39,6 @@ DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid);
 DECLARE_EARLY_PER_CPU_READ_MOSTLY(int, x86_cpu_to_logical_apicid);
 #endif
 
-/* Static state in head.S used to set up a CPU */
-extern unsigned long stack_start; /* Initial stack pointer address */
-
 struct task_struct;
 
 struct smp_ops {
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 587d7914ea4b..19a2224f9e16 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -59,22 +59,19 @@ static inline void native_write_cr3(unsigned long val)
 static inline unsigned long native_read_cr4(void)
 {
 	unsigned long val;
-	asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order));
-	return val;
-}
-
-static inline unsigned long native_read_cr4_safe(void)
-{
-	unsigned long val;
-	/* This could fault if %cr4 does not exist. In x86_64, a cr4 always
-	 * exists, so it will never fail. */
 #ifdef CONFIG_X86_32
+	/*
+	 * This could fault if CR4 does not exist.  Non-existent CR4
+	 * is functionally equivalent to CR4 == 0.  Keep it simple and pretend
+	 * that CR4 == 0 on CPUs that don't have CR4.
+	 */
 	asm volatile("1: mov %%cr4, %0\n"
 		     "2:\n"
 		     _ASM_EXTABLE(1b, 2b)
 		     : "=r" (val), "=m" (__force_order) : "0" (0));
 #else
-	val = native_read_cr4();
+	/* CR4 always exists on x86_64. */
+	asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order));
 #endif
 	return val;
 }
@@ -182,11 +179,6 @@ static inline unsigned long __read_cr4(void)
 	return native_read_cr4();
 }
 
-static inline unsigned long __read_cr4_safe(void)
-{
-	return native_read_cr4_safe();
-}
-
 static inline void __write_cr4(unsigned long x)
 {
 	native_write_cr4(x);
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 0944218af9e2..37f2e0b377ad 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -8,86 +8,86 @@
 
 #include <linux/uaccess.h>
 #include <linux/ptrace.h>
+#include <asm/switch_to.h>
+
+enum stack_type {
+	STACK_TYPE_UNKNOWN,
+	STACK_TYPE_TASK,
+	STACK_TYPE_IRQ,
+	STACK_TYPE_SOFTIRQ,
+	STACK_TYPE_EXCEPTION,
+	STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1,
+};
 
-extern int kstack_depth_to_print;
-
-struct thread_info;
-struct stacktrace_ops;
-
-typedef unsigned long (*walk_stack_t)(struct task_struct *task,
-				      unsigned long *stack,
-				      unsigned long bp,
-				      const struct stacktrace_ops *ops,
-				      void *data,
-				      unsigned long *end,
-				      int *graph);
-
-extern unsigned long
-print_context_stack(struct task_struct *task,
-		    unsigned long *stack, unsigned long bp,
-		    const struct stacktrace_ops *ops, void *data,
-		    unsigned long *end, int *graph);
-
-extern unsigned long
-print_context_stack_bp(struct task_struct *task,
-		       unsigned long *stack, unsigned long bp,
-		       const struct stacktrace_ops *ops, void *data,
-		       unsigned long *end, int *graph);
-
-/* Generic stack tracer with callbacks */
-
-struct stacktrace_ops {
-	int (*address)(void *data, unsigned long address, int reliable);
-	/* On negative return stop dumping */
-	int (*stack)(void *data, char *name);
-	walk_stack_t	walk_stack;
+struct stack_info {
+	enum stack_type type;
+	unsigned long *begin, *end, *next_sp;
 };
 
-void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp,
-		const struct stacktrace_ops *ops, void *data);
+bool in_task_stack(unsigned long *stack, struct task_struct *task,
+		   struct stack_info *info);
+
+int get_stack_info(unsigned long *stack, struct task_struct *task,
+		   struct stack_info *info, unsigned long *visit_mask);
+
+void stack_type_str(enum stack_type type, const char **begin,
+		    const char **end);
+
+static inline bool on_stack(struct stack_info *info, void *addr, size_t len)
+{
+	void *begin = info->begin;
+	void *end   = info->end;
+
+	return (info->type != STACK_TYPE_UNKNOWN &&
+		addr >= begin && addr < end &&
+		addr + len > begin && addr + len <= end);
+}
+
+extern int kstack_depth_to_print;
 
 #ifdef CONFIG_X86_32
 #define STACKSLOTS_PER_LINE 8
-#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :)
 #else
 #define STACKSLOTS_PER_LINE 4
-#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
 #endif
 
 #ifdef CONFIG_FRAME_POINTER
-static inline unsigned long
-stack_frame(struct task_struct *task, struct pt_regs *regs)
+static inline unsigned long *
+get_frame_pointer(struct task_struct *task, struct pt_regs *regs)
 {
-	unsigned long bp;
-
 	if (regs)
-		return regs->bp;
+		return (unsigned long *)regs->bp;
 
-	if (task == current) {
-		/* Grab bp right from our regs */
-		get_bp(bp);
-		return bp;
-	}
+	if (task == current)
+		return __builtin_frame_address(0);
 
-	/* bp is the last reg pushed by switch_to */
-	return *(unsigned long *)task->thread.sp;
+	return (unsigned long *)((struct inactive_task_frame *)task->thread.sp)->bp;
 }
 #else
-static inline unsigned long
-stack_frame(struct task_struct *task, struct pt_regs *regs)
+static inline unsigned long *
+get_frame_pointer(struct task_struct *task, struct pt_regs *regs)
 {
-	return 0;
+	return NULL;
+}
+#endif /* CONFIG_FRAME_POINTER */
+
+static inline unsigned long *
+get_stack_pointer(struct task_struct *task, struct pt_regs *regs)
+{
+	if (regs)
+		return (unsigned long *)kernel_stack_pointer(regs);
+
+	if (task == current)
+		return __builtin_frame_address(0);
+
+	return (unsigned long *)task->thread.sp;
 }
-#endif
 
-extern void
-show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
-		   unsigned long *stack, unsigned long bp, char *log_lvl);
+void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
+			unsigned long *stack, char *log_lvl);
 
-extern void
-show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
-		   unsigned long *sp, unsigned long bp, char *log_lvl);
+void show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
+			unsigned long *sp, char *log_lvl);
 
 extern unsigned int code_bytes;
 
@@ -106,7 +106,7 @@ static inline unsigned long caller_frame_pointer(void)
 {
 	struct stack_frame *frame;
 
-	get_bp(frame);
+	frame = __builtin_frame_address(0);
 
 #ifdef CONFIG_FRAME_POINTER
 	frame = frame->next_frame;
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 8f321a1b03a1..5cb436acd463 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -2,130 +2,66 @@
 #define _ASM_X86_SWITCH_TO_H
 
 struct task_struct; /* one of the stranger aspects of C forward declarations */
+
+struct task_struct *__switch_to_asm(struct task_struct *prev,
+				    struct task_struct *next);
+
 __visible struct task_struct *__switch_to(struct task_struct *prev,
-					   struct task_struct *next);
+					  struct task_struct *next);
 struct tss_struct;
 void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 		      struct tss_struct *tss);
 
-#ifdef CONFIG_X86_32
+/* This runs runs on the previous thread's stack. */
+static inline void prepare_switch_to(struct task_struct *prev,
+				     struct task_struct *next)
+{
+#ifdef CONFIG_VMAP_STACK
+	/*
+	 * If we switch to a stack that has a top-level paging entry
+	 * that is not present in the current mm, the resulting #PF will
+	 * will be promoted to a double-fault and we'll panic.  Probe
+	 * the new stack now so that vmalloc_fault can fix up the page
+	 * tables if needed.  This can only happen if we use a stack
+	 * in vmap space.
+	 *
+	 * We assume that the stack is aligned so that it never spans
+	 * more than one top-level paging entry.
+	 *
+	 * To minimize cache pollution, just follow the stack pointer.
+	 */
+	READ_ONCE(*(unsigned char *)next->thread.sp);
+#endif
+}
+
+asmlinkage void ret_from_fork(void);
+
+/* data that is pointed to by thread.sp */
+struct inactive_task_frame {
+#ifdef CONFIG_X86_64
+	unsigned long r15;
+	unsigned long r14;
+	unsigned long r13;
+	unsigned long r12;
+#else
+	unsigned long si;
+	unsigned long di;
+#endif
+	unsigned long bx;
+	unsigned long bp;
+	unsigned long ret_addr;
+};
 
-#ifdef CONFIG_CC_STACKPROTECTOR
-#define __switch_canary							\
-	"movl %P[task_canary](%[next]), %%ebx\n\t"			\
-	"movl %%ebx, "__percpu_arg([stack_canary])"\n\t"
-#define __switch_canary_oparam						\
-	, [stack_canary] "=m" (stack_canary.canary)
-#define __switch_canary_iparam						\
-	, [task_canary] "i" (offsetof(struct task_struct, stack_canary))
-#else	/* CC_STACKPROTECTOR */
-#define __switch_canary
-#define __switch_canary_oparam
-#define __switch_canary_iparam
-#endif	/* CC_STACKPROTECTOR */
+struct fork_frame {
+	struct inactive_task_frame frame;
+	struct pt_regs regs;
+};
 
-/*
- * Saving eflags is important. It switches not only IOPL between tasks,
- * it also protects other tasks from NT leaking through sysenter etc.
- */
 #define switch_to(prev, next, last)					\
 do {									\
-	/*								\
-	 * Context-switching clobbers all registers, so we clobber	\
-	 * them explicitly, via unused output variables.		\
-	 * (EAX and EBP is not listed because EBP is saved/restored	\
-	 * explicitly for wchan access and EAX is the return value of	\
-	 * __switch_to())						\
-	 */								\
-	unsigned long ebx, ecx, edx, esi, edi;				\
-									\
-	asm volatile("pushl %%ebp\n\t"		/* save    EBP   */	\
-		     "movl %%esp,%[prev_sp]\n\t"	/* save    ESP   */ \
-		     "movl %[next_sp],%%esp\n\t"	/* restore ESP   */ \
-		     "movl $1f,%[prev_ip]\n\t"	/* save    EIP   */	\
-		     "pushl %[next_ip]\n\t"	/* restore EIP   */	\
-		     __switch_canary					\
-		     "jmp __switch_to\n"	/* regparm call  */	\
-		     "1:\t"						\
-		     "popl %%ebp\n\t"		/* restore EBP   */	\
-									\
-		     /* output parameters */				\
-		     : [prev_sp] "=m" (prev->thread.sp),		\
-		       [prev_ip] "=m" (prev->thread.ip),		\
-		       "=a" (last),					\
-									\
-		       /* clobbered output registers: */		\
-		       "=b" (ebx), "=c" (ecx), "=d" (edx),		\
-		       "=S" (esi), "=D" (edi)				\
-		       							\
-		       __switch_canary_oparam				\
-									\
-		       /* input parameters: */				\
-		     : [next_sp]  "m" (next->thread.sp),		\
-		       [next_ip]  "m" (next->thread.ip),		\
-		       							\
-		       /* regparm parameters for __switch_to(): */	\
-		       [prev]     "a" (prev),				\
-		       [next]     "d" (next)				\
+	prepare_switch_to(prev, next);					\
 									\
-		       __switch_canary_iparam				\
-									\
-		     : /* reloaded segment registers */			\
-			"memory");					\
+	((last) = __switch_to_asm((prev), (next)));			\
 } while (0)
 
-#else /* CONFIG_X86_32 */
-
-/* frame pointer must be last for get_wchan */
-#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", "flags"
-
-#ifdef CONFIG_CC_STACKPROTECTOR
-#define __switch_canary							  \
-	"movq %P[task_canary](%%rsi),%%r8\n\t"				  \
-	"movq %%r8,"__percpu_arg([gs_canary])"\n\t"
-#define __switch_canary_oparam						  \
-	, [gs_canary] "=m" (irq_stack_union.stack_canary)
-#define __switch_canary_iparam						  \
-	, [task_canary] "i" (offsetof(struct task_struct, stack_canary))
-#else	/* CC_STACKPROTECTOR */
-#define __switch_canary
-#define __switch_canary_oparam
-#define __switch_canary_iparam
-#endif	/* CC_STACKPROTECTOR */
-
-/*
- * 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 */	  \
-	     "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */	  \
-	     "call __switch_to\n\t"					  \
-	     "movq "__percpu_arg([current_task])",%%rsi\n\t"		  \
-	     __switch_canary						  \
-	     "movq %P[thread_info](%%rsi),%%r8\n\t"			  \
-	     "movq %%rax,%%rdi\n\t" 					  \
-	     "testl  %[_tif_fork],%P[ti_flags](%%r8)\n\t"		  \
-	     "jnz   ret_from_fork\n\t"					  \
-	     RESTORE_CONTEXT						  \
-	     : "=a" (last)					  	  \
-	       __switch_canary_oparam					  \
-	     : [next] "S" (next), [prev] "D" (prev),			  \
-	       [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \
-	       [ti_flags] "i" (offsetof(struct thread_info, flags)),	  \
-	       [_tif_fork] "i" (_TIF_FORK),			  	  \
-	       [thread_info] "i" (offsetof(struct task_struct, stack)),   \
-	       [current_task] "m" (current_task)			  \
-	       __switch_canary_iparam					  \
-	     : "memory", "cc" __EXTRA_CLOBBER)
-
-#endif /* CONFIG_X86_32 */
-
 #endif /* _ASM_X86_SWITCH_TO_H */
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index 4e23dd15c661..e3c95e8e61c5 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -60,7 +60,7 @@ static inline long syscall_get_error(struct task_struct *task,
 	 * TS_COMPAT is set for 32-bit syscall entries and then
 	 * remains set until we return to user mode.
 	 */
-	if (task_thread_info(task)->status & (TS_COMPAT|TS_I386_REGS_POKED))
+	if (task->thread.status & (TS_COMPAT|TS_I386_REGS_POKED))
 		/*
 		 * Sign-extend the value so (int)-EFOO becomes (long)-EFOO
 		 * and will match correctly in comparisons.
@@ -116,7 +116,7 @@ static inline void syscall_get_arguments(struct task_struct *task,
 					 unsigned long *args)
 {
 # ifdef CONFIG_IA32_EMULATION
-	if (task_thread_info(task)->status & TS_COMPAT)
+	if (task->thread.status & TS_COMPAT)
 		switch (i) {
 		case 0:
 			if (!n--) break;
@@ -177,7 +177,7 @@ static inline void syscall_set_arguments(struct task_struct *task,
 					 const unsigned long *args)
 {
 # ifdef CONFIG_IA32_EMULATION
-	if (task_thread_info(task)->status & TS_COMPAT)
+	if (task->thread.status & TS_COMPAT)
 		switch (i) {
 		case 0:
 			if (!n--) break;
@@ -234,18 +234,8 @@ static inline void syscall_set_arguments(struct task_struct *task,
 
 static inline int syscall_get_arch(void)
 {
-#ifdef CONFIG_IA32_EMULATION
-	/*
-	 * TS_COMPAT is set for 32-bit syscall entry and then
-	 * remains set until we return to user mode.
-	 *
-	 * x32 tasks should be considered AUDIT_ARCH_X86_64.
-	 */
-	if (task_thread_info(current)->status & TS_COMPAT)
-		return AUDIT_ARCH_I386;
-#endif
-	/* Both x32 and x86_64 are considered "64-bit". */
-	return AUDIT_ARCH_X86_64;
+	/* x32 tasks should be considered AUDIT_ARCH_X86_64. */
+	return in_ia32_syscall() ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
 }
 #endif	/* CONFIG_X86_32 */
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 8b7c8d8e0852..2aaca53c0974 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -52,21 +52,6 @@ struct task_struct;
 #include <asm/cpufeature.h>
 #include <linux/atomic.h>
 
-struct thread_info {
-	struct task_struct	*task;		/* main task structure */
-	__u32			flags;		/* low level flags */
-	__u32			status;		/* thread synchronous flags */
-	__u32			cpu;		/* current CPU */
-};
-
-#define INIT_THREAD_INFO(tsk)			\
-{						\
-	.task		= &tsk,			\
-	.flags		= 0,			\
-	.cpu		= 0,			\
-}
-
-#define init_thread_info	(init_thread_union.thread_info)
 #define init_stack		(init_thread_union.stack)
 
 #else /* !__ASSEMBLY__ */
@@ -95,7 +80,6 @@ struct thread_info {
 #define TIF_UPROBE		12	/* breakpointed or singlestepping */
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
 #define TIF_IA32		17	/* IA32 compatibility process */
-#define TIF_FORK		18	/* ret_from_fork */
 #define TIF_NOHZ		19	/* in adaptive nohz mode */
 #define TIF_MEMDIE		20	/* is terminating due to OOM killer */
 #define TIF_POLLING_NRFLAG	21	/* idle is polling for TIF_NEED_RESCHED */
@@ -119,7 +103,6 @@ struct thread_info {
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
 #define _TIF_IA32		(1 << TIF_IA32)
-#define _TIF_FORK		(1 << TIF_FORK)
 #define _TIF_NOHZ		(1 << TIF_NOHZ)
 #define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
 #define _TIF_IO_BITMAP		(1 << TIF_IO_BITMAP)
@@ -160,11 +143,6 @@ struct thread_info {
  */
 #ifndef __ASSEMBLY__
 
-static inline struct thread_info *current_thread_info(void)
-{
-	return (struct thread_info *)(current_top_of_stack() - THREAD_SIZE);
-}
-
 static inline unsigned long current_stack_pointer(void)
 {
 	unsigned long sp;
@@ -226,60 +204,19 @@ static inline int arch_within_stack_frames(const void * const stack,
 # define cpu_current_top_of_stack (cpu_tss + TSS_sp0)
 #endif
 
-/*
- * ASM operand which evaluates to a 'thread_info' address of
- * the current task, if it is known that "reg" is exactly "off"
- * bytes below the top of the stack currently.
- *
- * ( The kernel stack's size is known at build time, it is usually
- *   2 or 4 pages, and the bottom  of the kernel stack contains
- *   the thread_info structure. So to access the thread_info very
- *   quickly from assembly code we can calculate down from the
- *   top of the kernel stack to the bottom, using constant,
- *   build-time calculations only. )
- *
- * For example, to fetch the current thread_info->flags value into %eax
- * on x86-64 defconfig kernels, in syscall entry code where RSP is
- * currently at exactly SIZEOF_PTREGS bytes away from the top of the
- * stack:
- *
- *      mov ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS), %eax
- *
- * will translate to:
- *
- *      8b 84 24 b8 c0 ff ff      mov    -0x3f48(%rsp), %eax
- *
- * which is below the current RSP by almost 16K.
- */
-#define ASM_THREAD_INFO(field, reg, off) ((field)+(off)-THREAD_SIZE)(reg)
-
 #endif
 
-/*
- * Thread-synchronous status.
- *
- * This is different from the flags in that nobody else
- * ever touches our thread-synchronous status, so we don't
- * have to worry about atomic accesses.
- */
-#define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
 #ifdef CONFIG_COMPAT
 #define TS_I386_REGS_POKED	0x0004	/* regs poked by 32-bit ptracer */
 #endif
-
 #ifndef __ASSEMBLY__
 
-static inline bool in_ia32_syscall(void)
-{
 #ifdef CONFIG_X86_32
-	return true;
-#endif
-#ifdef CONFIG_IA32_EMULATION
-	if (current_thread_info()->status & TS_COMPAT)
-		return true;
+#define in_ia32_syscall() true
+#else
+#define in_ia32_syscall() (IS_ENABLED(CONFIG_IA32_EMULATION) && \
+			   current->thread.status & TS_COMPAT)
 #endif
-	return false;
-}
 
 /*
  * Force syscall return via IRET by making it look as if there was
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index dee8a70382ba..6fa85944af83 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -81,7 +81,7 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
 /* Initialize cr4 shadow for this CPU. */
 static inline void cr4_init_shadow(void)
 {
-	this_cpu_write(cpu_tlbstate.cr4, __read_cr4_safe());
+	this_cpu_write(cpu_tlbstate.cr4, __read_cr4());
 }
 
 /* Set in this cpu's CR4. */
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index c3496619740a..01fd0a7f48cd 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -117,6 +117,12 @@ extern void ist_exit(struct pt_regs *regs);
 extern void ist_begin_non_atomic(struct pt_regs *regs);
 extern void ist_end_non_atomic(void);
 
+#ifdef CONFIG_VMAP_STACK
+void __noreturn handle_stack_overflow(const char *message,
+				      struct pt_regs *regs,
+				      unsigned long fault_address);
+#endif
+
 /* Interrupts/Exceptions */
 enum {
 	X86_TRAP_DE = 0,	/*  0, Divide-by-zero */
diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
new file mode 100644
index 000000000000..c4b6d1cafa46
--- /dev/null
+++ b/arch/x86/include/asm/unwind.h
@@ -0,0 +1,73 @@
+#ifndef _ASM_X86_UNWIND_H
+#define _ASM_X86_UNWIND_H
+
+#include <linux/sched.h>
+#include <linux/ftrace.h>
+#include <asm/ptrace.h>
+#include <asm/stacktrace.h>
+
+struct unwind_state {
+	struct stack_info stack_info;
+	unsigned long stack_mask;
+	struct task_struct *task;
+	int graph_idx;
+#ifdef CONFIG_FRAME_POINTER
+	unsigned long *bp;
+#else
+	unsigned long *sp;
+#endif
+};
+
+void __unwind_start(struct unwind_state *state, struct task_struct *task,
+		    struct pt_regs *regs, unsigned long *first_frame);
+
+bool unwind_next_frame(struct unwind_state *state);
+
+static inline bool unwind_done(struct unwind_state *state)
+{
+	return state->stack_info.type == STACK_TYPE_UNKNOWN;
+}
+
+static inline
+void unwind_start(struct unwind_state *state, struct task_struct *task,
+		  struct pt_regs *regs, unsigned long *first_frame)
+{
+	first_frame = first_frame ? : get_stack_pointer(task, regs);
+
+	__unwind_start(state, task, regs, first_frame);
+}
+
+#ifdef CONFIG_FRAME_POINTER
+
+static inline
+unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
+{
+	if (unwind_done(state))
+		return NULL;
+
+	return state->bp + 1;
+}
+
+unsigned long unwind_get_return_address(struct unwind_state *state);
+
+#else /* !CONFIG_FRAME_POINTER */
+
+static inline
+unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
+{
+	return NULL;
+}
+
+static inline
+unsigned long unwind_get_return_address(struct unwind_state *state)
+{
+	if (unwind_done(state))
+		return 0;
+
+	return ftrace_graph_ret_addr(state->task, &state->graph_idx,
+				     *state->sp, state->sp);
+}
+
+#endif /* CONFIG_FRAME_POINTER */
+
+#endif /* _ASM_X86_UNWIND_H */