x86: Move thread_info into task_struct

Now that most of the thread_info users have been cleaned up,
this is straightforward.

Most of this code was written by Linus.

Originally-from: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jann Horn <jann@thejh.net>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/a50eab40abeaec9cb9a9e3cbdeafd32190206654.1473801993.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/Kconfig

@@ -157,6 +157,7 @@ config X86
 	select SPARSE_IRQ
 	select SRCU
 	select SYSCTL_EXCEPTION_TRACE
+	select THREAD_INFO_IN_TASK
 	select USER_STACKTRACE_SUPPORT
 	select VIRT_TO_BUS
 	select X86_DEV_DMA_OPS			if X86_64

arch/x86/entry/entry_64.S

@@ -179,7 +179,8 @@ GLOBAL(entry_SYSCALL_64_after_swapgs)
 	 * If we need to do entry work or if we guess we'll need to do
 	 * exit work, go straight to the slow path.
 	 */
-	testl	$_TIF_WORK_SYSCALL_ENTRY|_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	movq	PER_CPU_VAR(current_task), %r11
+	testl	$_TIF_WORK_SYSCALL_ENTRY|_TIF_ALLWORK_MASK, TASK_TI_flags(%r11)
 	jnz	entry_SYSCALL64_slow_path
 
 entry_SYSCALL_64_fastpath:
@@ -217,7 +218,8 @@ entry_SYSCALL_64_fastpath:
 	 */
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
-	testl	$_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
+	movq	PER_CPU_VAR(current_task), %r11
+	testl	$_TIF_ALLWORK_MASK, TASK_TI_flags(%r11)
 	jnz	1f
 
 	LOCKDEP_SYS_EXIT
@@ -370,6 +372,7 @@ END(ptregs_\func)
 /*
  * %rdi: prev task
  * %rsi: next task
+ * rsi: task we're switching to
  */
 ENTRY(__switch_to_asm)
 	/*

arch/x86/include/asm/thread_info.h

@@ -52,20 +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			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__ */
@@ -157,11 +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;
@@ -223,33 +204,6 @@ 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
 
 #ifdef CONFIG_COMPAT

arch/x86/kernel/asm-offsets.c

@@ -35,9 +35,7 @@ void common(void) {
 #endif
 
 	BLANK();
-	OFFSET(TI_flags, thread_info, flags);
+	OFFSET(TASK_TI_flags, task_struct, thread_info.flags);
-
-	BLANK();
 	OFFSET(TASK_addr_limit, task_struct, thread.addr_limit);
 
 	BLANK();

arch/x86/kernel/irq_64.c

@@ -40,8 +40,7 @@ static inline void stack_overflow_check(struct pt_regs *regs)
 	if (user_mode(regs))
 		return;
 
-	if (regs->sp >= curbase + sizeof(struct thread_info) +
+	if (regs->sp >= curbase + sizeof(struct pt_regs) + STACK_TOP_MARGIN &&
-				  sizeof(struct pt_regs) + STACK_TOP_MARGIN &&
 	    regs->sp <= curbase + THREAD_SIZE)
 		return;
 

arch/x86/kernel/process.c

@@ -549,9 +549,7 @@ unsigned long get_wchan(struct task_struct *p)
 	 * PADDING
 	 * ----------- top = topmax - TOP_OF_KERNEL_STACK_PADDING
 	 * stack
-	 * ----------- bottom = start + sizeof(thread_info)
+	 * ----------- bottom = start
-	 * thread_info
-	 * ----------- start
 	 *
 	 * The tasks stack pointer points at the location where the
 	 * framepointer is stored. The data on the stack is:
@@ -562,7 +560,7 @@ unsigned long get_wchan(struct task_struct *p)
 	 */
 	top = start + THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING;
 	top -= 2 * sizeof(unsigned long);
-	bottom = start + sizeof(struct thread_info);
+	bottom = start;
 
 	sp = READ_ONCE(p->thread.sp);
 	if (sp < bottom || sp > top)