Merge tag 'pr-move-task-cpu-to-ti' of git://git.kernel.org/pub/scm/linux/kernel/git/ardb/linux.git

Cross-architecture update to move task_struct::cpu back into thread_info
on arm64, x86, s390, powerpc, and riscv. All Acked by arch maintainers.

Quoting Ard Biesheuvel:

 "Move task_struct::cpu back into thread_info

  Keeping CPU in task_struct is problematic for architectures that define
  raw_smp_processor_id() in terms of this field, as it requires
  linux/sched.h to be included, which causes a lot of pain in terms of
  circular dependencies (aka 'header soup')

  This series moves it back into thread_info (where it came from) for all
  architectures that enable THREAD_INFO_IN_TASK, addressing the header
  soup issue as well as some pointless differences in the implementations
  of task_cpu() and set_task_cpu()."

arch/arm64/include/asm/thread_info.h

@@ -42,6 +42,7 @@ struct thread_info {
 	void			*scs_base;
 	void			*scs_sp;
 #endif
+	u32			cpu;
 };
 
 #define thread_saved_pc(tsk)	\

arch/arm64/kernel/asm-offsets.c

@@ -27,8 +27,8 @@
 int main(void)
 {
   DEFINE(TSK_ACTIVE_MM,		offsetof(struct task_struct, active_mm));
-  DEFINE(TSK_CPU,		offsetof(struct task_struct, cpu));
   BLANK();
+  DEFINE(TSK_TI_CPU,		offsetof(struct task_struct, thread_info.cpu));
   DEFINE(TSK_TI_FLAGS,		offsetof(struct task_struct, thread_info.flags));
   DEFINE(TSK_TI_PREEMPT,	offsetof(struct task_struct, thread_info.preempt_count));
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN

arch/arm64/kernel/head.S

@@ -412,7 +412,7 @@ SYM_FUNC_END(__create_page_tables)
 	scs_load \tsk
 
 	adr_l	\tmp1, __per_cpu_offset
-	ldr	w\tmp2, [\tsk, #TSK_CPU]
+	ldr	w\tmp2, [\tsk, #TSK_TI_CPU]
 	ldr	\tmp1, [\tmp1, \tmp2, lsl #3]
 	set_this_cpu_offset \tmp1
 	.endm

arch/powerpc/Makefile

@@ -446,17 +446,6 @@ else
 endif
 endif
 
-ifdef CONFIG_SMP
-ifdef CONFIG_PPC32
-prepare: task_cpu_prepare
-
-PHONY += task_cpu_prepare
-task_cpu_prepare: prepare0
-	$(eval KBUILD_CFLAGS += -D_TASK_CPU=$(shell awk '{if ($$2 == "TASK_CPU") print $$3;}' include/generated/asm-offsets.h))
-
-endif # CONFIG_PPC32
-endif # CONFIG_SMP
-
 PHONY += checkbin
 # Check toolchain versions:
 # - gcc-4.6 is the minimum kernel-wide version so nothing required.

arch/powerpc/include/asm/smp.h

@@ -87,22 +87,7 @@ int is_cpu_dead(unsigned int cpu);
 /* 32-bit */
 extern int smp_hw_index[];
 
-/*
- * This is particularly ugly: it appears we can't actually get the definition
- * of task_struct here, but we need access to the CPU this task is running on.
- * Instead of using task_struct we're using _TASK_CPU which is extracted from
- * asm-offsets.h by kbuild to get the current processor ID.
- *
- * This also needs to be safeguarded when building asm-offsets.s because at
- * that time _TASK_CPU is not defined yet. It could have been guarded by
- * _TASK_CPU itself, but we want the build to fail if _TASK_CPU is missing
- * when building something else than asm-offsets.s
- */
-#ifdef GENERATING_ASM_OFFSETS
-#define raw_smp_processor_id()		(0)
-#else
-#define raw_smp_processor_id()		(*(unsigned int *)((void *)current + _TASK_CPU))
-#endif
+#define raw_smp_processor_id()		(current_thread_info()->cpu)
 #define hard_smp_processor_id() 	(smp_hw_index[smp_processor_id()])
 
 static inline int get_hard_smp_processor_id(int cpu)

arch/powerpc/include/asm/thread_info.h

@@ -47,6 +47,9 @@
 struct thread_info {
 	int		preempt_count;		/* 0 => preemptable,
 						   <0 => BUG */
+#ifdef CONFIG_SMP
+	unsigned int	cpu;
+#endif
 	unsigned long	local_flags;		/* private flags for thread */
 #ifdef CONFIG_LIVEPATCH
 	unsigned long *livepatch_sp;

arch/powerpc/kernel/asm-offsets.c

@@ -9,8 +9,6 @@
  * #defines from the assembly-language output.
  */
 
-#define GENERATING_ASM_OFFSETS	/* asm/smp.h */
-
 #include <linux/compat.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
@@ -93,7 +91,7 @@ int main(void)
 #endif /* CONFIG_PPC64 */
 	OFFSET(TASK_STACK, task_struct, stack);
 #ifdef CONFIG_SMP
-	OFFSET(TASK_CPU, task_struct, cpu);
+	OFFSET(TASK_CPU, task_struct, thread_info.cpu);
 #endif
 
 #ifdef CONFIG_LIVEPATCH

arch/powerpc/kernel/smp.c

@@ -1223,7 +1223,7 @@ static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
 	paca_ptrs[cpu]->kstack = (unsigned long)task_stack_page(idle) +
 				 THREAD_SIZE - STACK_FRAME_OVERHEAD;
 #endif
-	idle->cpu = cpu;
+	task_thread_info(idle)->cpu = cpu;
 	secondary_current = current_set[cpu] = idle;
 }
 

arch/riscv/kernel/asm-offsets.c

@@ -33,7 +33,6 @@ void asm_offsets(void)
 	OFFSET(TASK_TI_PREEMPT_COUNT, task_struct, thread_info.preempt_count);
 	OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp);
 	OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp);
-	OFFSET(TASK_TI_CPU, task_struct, thread_info.cpu);
 
 	OFFSET(TASK_THREAD_F0,  task_struct, thread.fstate.f[0]);
 	OFFSET(TASK_THREAD_F1,  task_struct, thread.fstate.f[1]);

arch/riscv/kernel/entry.S

@@ -544,11 +544,6 @@ ENTRY(__switch_to)
 	REG_L s9,  TASK_THREAD_S9_RA(a4)
 	REG_L s10, TASK_THREAD_S10_RA(a4)
 	REG_L s11, TASK_THREAD_S11_RA(a4)
-	/* Swap the CPU entry around. */
-	lw a3, TASK_TI_CPU(a0)
-	lw a4, TASK_TI_CPU(a1)
-	sw a3, TASK_TI_CPU(a1)
-	sw a4, TASK_TI_CPU(a0)
 	/* The offset of thread_info in task_struct is zero. */
 	move tp, a1
 	ret

arch/riscv/kernel/head.S

@@ -317,7 +317,6 @@ clear_bss_done:
 	call setup_trap_vector
 	/* Restore C environment */
 	la tp, init_task
-	sw zero, TASK_TI_CPU(tp)
 	la sp, init_thread_union + THREAD_SIZE
 
 #ifdef CONFIG_KASAN

arch/s390/include/asm/thread_info.h

@@ -37,6 +37,7 @@
 struct thread_info {
 	unsigned long		flags;		/* low level flags */
 	unsigned long		syscall_work;	/* SYSCALL_WORK_ flags */
+	unsigned int		cpu;		/* current CPU */
 };
 
 /*

arch/x86/include/asm/thread_info.h

@@ -57,6 +57,9 @@ struct thread_info {
 	unsigned long		flags;		/* low level flags */
 	unsigned long		syscall_work;	/* SYSCALL_WORK_ flags */
 	u32			status;		/* thread synchronous flags */
+#ifdef CONFIG_SMP
+	u32			cpu;		/* current CPU */
+#endif
 };
 
 #define INIT_THREAD_INFO(tsk)			\

include/linux/sched.h

@@ -750,10 +750,6 @@ struct task_struct {
 #ifdef CONFIG_SMP
 	int				on_cpu;
 	struct __call_single_node	wake_entry;
-#ifdef CONFIG_THREAD_INFO_IN_TASK
-	/* Current CPU: */
-	unsigned int			cpu;
-#endif
 	unsigned int			wakee_flips;
 	unsigned long			wakee_flip_decay_ts;
 	struct task_struct		*last_wakee;
@@ -1886,10 +1882,7 @@ extern struct thread_info init_thread_info;
 extern unsigned long init_stack[THREAD_SIZE / sizeof(unsigned long)];
 
 #ifdef CONFIG_THREAD_INFO_IN_TASK
-static inline struct thread_info *task_thread_info(struct task_struct *task)
-{
-	return &task->thread_info;
-}
+# define task_thread_info(task)	(&(task)->thread_info)
 #elif !defined(__HAVE_THREAD_FUNCTIONS)
 # define task_thread_info(task)	((struct thread_info *)(task)->stack)
 #endif
@@ -2114,11 +2107,7 @@ static __always_inline bool need_resched(void)
 
 static inline unsigned int task_cpu(const struct task_struct *p)
 {
-#ifdef CONFIG_THREAD_INFO_IN_TASK
-	return READ_ONCE(p->cpu);
-#else
 	return READ_ONCE(task_thread_info(p)->cpu);
-#endif
 }
 
 extern void set_task_cpu(struct task_struct *p, unsigned int cpu);

kernel/sched/sched.h

@@ -1926,11 +1926,7 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
 	 * per-task data have been completed by this moment.
 	 */
 	smp_wmb();
-#ifdef CONFIG_THREAD_INFO_IN_TASK
-	WRITE_ONCE(p->cpu, cpu);
-#else
 	WRITE_ONCE(task_thread_info(p)->cpu, cpu);
-#endif
 	p->wake_cpu = cpu;
 #endif
 }