ARM: implement THREAD_INFO_IN_TASK for uniprocessor systems

On UP systems, only a single task can be 'current' at the same time,
which means we can use a global variable to track it. This means we can
also enable THREAD_INFO_IN_TASK for those systems, as in that case,
thread_info is accessed via current rather than the other way around,
removing the need to store thread_info at the base of the task stack.
This, in turn, permits us to enable IRQ stacks and vmap'ed stacks on UP
systems as well.

To partially mitigate the performance overhead of this arrangement, use
a ADD/ADD/LDR sequence with the appropriate PC-relative group
relocations to load the value of current when needed. This means that
accessing current will still only require a single load as before,
avoiding the need for a literal to carry the address of the global
variable in each function. However, accessing thread_info will now
require this load as well.

Acked-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Nicolas Pitre <nico@fluxnic.net>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Tested-by: Marc Zyngier <maz@kernel.org>
Tested-by: Vladimir Murzin <vladimir.murzin@arm.com> # ARMv7M

4 files changed, 78 insertions, 72 deletions

diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index f9b3dd0e9ef5..59d7b9e81934 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -203,41 +203,12 @@ THUMB(	fpreg	.req	r7	)
 	.endm
 	.endr
 
-	.macro	get_current, rd
-#ifdef CONFIG_CURRENT_POINTER_IN_TPIDRURO
-	mrc	p15, 0, \rd, c13, c0, 3		@ get TPIDRURO register
-#else
-	get_thread_info \rd
-	ldr	\rd, [\rd, #TI_TASK]
-#endif
-	.endm
-
-	.macro	set_current, rn
-#ifdef CONFIG_CURRENT_POINTER_IN_TPIDRURO
-	mcr	p15, 0, \rn, c13, c0, 3		@ set TPIDRURO register
-#endif
-	.endm
-
-	.macro	reload_current, t1:req, t2:req
-#ifdef CONFIG_CURRENT_POINTER_IN_TPIDRURO
-	ldr_this_cpu \t1, __entry_task, \t1, \t2
-	mcr	p15, 0, \t1, c13, c0, 3		@ store in TPIDRURO
-#endif
-	.endm
-
 /*
  * Get current thread_info.
  */
 	.macro	get_thread_info, rd
-#ifdef CONFIG_THREAD_INFO_IN_TASK
 	/* thread_info is the first member of struct task_struct */
 	get_current \rd
-#else
- ARM(	mov	\rd, sp, lsr #THREAD_SIZE_ORDER + PAGE_SHIFT	)
- THUMB(	mov	\rd, sp			)
- THUMB(	lsr	\rd, \rd, #THREAD_SIZE_ORDER + PAGE_SHIFT	)
-	mov	\rd, \rd, lsl #THREAD_SIZE_ORDER + PAGE_SHIFT
-#endif
 	.endm
 
 /*
@@ -330,6 +301,60 @@ ALT_UP_B(.L1_\@)
 #endif
 	.endm
 
+	/*
+	 * set_current - store the task pointer of this CPU's current task
+	 */
+	.macro		set_current, rn:req, tmp:req
+#if defined(CONFIG_CURRENT_POINTER_IN_TPIDRURO) || defined(CONFIG_SMP)
+9998:	mcr		p15, 0, \rn, c13, c0, 3		@ set TPIDRURO register
+#ifdef CONFIG_CPU_V6
+ALT_UP_B(.L0_\@)
+	.subsection	1
+.L0_\@: str_va		\rn, __current, \tmp
+	b		.L1_\@
+	.previous
+.L1_\@:
+#endif
+#else
+	str_va		\rn, __current, \tmp
+#endif
+	.endm
+
+	/*
+	 * get_current - load the task pointer of this CPU's current task
+	 */
+	.macro		get_current, rd:req
+#if defined(CONFIG_CURRENT_POINTER_IN_TPIDRURO) || defined(CONFIG_SMP)
+9998:	mrc		p15, 0, \rd, c13, c0, 3		@ get TPIDRURO register
+#ifdef CONFIG_CPU_V6
+ALT_UP_B(.L0_\@)
+	.subsection	1
+.L0_\@: ldr_va		\rd, __current
+	b		.L1_\@
+	.previous
+.L1_\@:
+#endif
+#else
+	ldr_va		\rd, __current
+#endif
+	.endm
+
+	/*
+	 * reload_current - reload the task pointer of this CPU's current task
+	 *		    into the TLS register
+	 */
+	.macro		reload_current, t1:req, t2:req
+#if defined(CONFIG_CURRENT_POINTER_IN_TPIDRURO) || defined(CONFIG_SMP)
+#ifdef CONFIG_CPU_V6
+ALT_SMP(nop)
+ALT_UP_B(.L0_\@)
+#endif
+	ldr_this_cpu	\t1, __entry_task, \t1, \t2
+	mcr		p15, 0, \t1, c13, c0, 3		@ store in TPIDRURO
+.L0_\@:
+#endif
+	.endm
+
 /*
  * Instruction barrier
  */
diff --git a/arch/arm/include/asm/current.h b/arch/arm/include/asm/current.h
index 6bf0aad672c3..69ecf4c6c725 100644
--- a/arch/arm/include/asm/current.h
+++ b/arch/arm/include/asm/current.h
@@ -8,25 +8,18 @@
 #define _ASM_ARM_CURRENT_H
 
 #ifndef __ASSEMBLY__
+#include <asm/insn.h>
 
 struct task_struct;
 
-static inline void set_current(struct task_struct *cur)
-{
-	if (!IS_ENABLED(CONFIG_CURRENT_POINTER_IN_TPIDRURO))
-		return;
-
-	/* Set TPIDRURO */
-	asm("mcr p15, 0, %0, c13, c0, 3" :: "r"(cur) : "memory");
-}
+extern struct task_struct *__current;
 
-#ifdef CONFIG_CURRENT_POINTER_IN_TPIDRURO
-
-static inline struct task_struct *get_current(void)
+static inline __attribute_const__ struct task_struct *get_current(void)
 {
 	struct task_struct *cur;
 
 #if __has_builtin(__builtin_thread_pointer) && \
+    defined(CONFIG_CURRENT_POINTER_IN_TPIDRURO) && \
     !(defined(CONFIG_THUMB2_KERNEL) && \
       defined(CONFIG_CC_IS_CLANG) && CONFIG_CLANG_VERSION < 130001)
 	/*
@@ -39,16 +32,30 @@ static inline struct task_struct *get_current(void)
 	 * https://github.com/ClangBuiltLinux/linux/issues/1485
 	 */
 	cur = __builtin_thread_pointer();
+#elif defined(CONFIG_CURRENT_POINTER_IN_TPIDRURO) || defined(CONFIG_SMP)
+	asm("0:	mrc p15, 0, %0, c13, c0, 3			\n\t"
+#ifdef CONFIG_CPU_V6
+	    "1:							\n\t"
+	    "	.subsection 1					\n\t"
+	    "2: " LOAD_SYM_ARMV6(%0, __current) "		\n\t"
+	    "	b	1b					\n\t"
+	    "	.previous					\n\t"
+	    "	.pushsection \".alt.smp.init\", \"a\"		\n\t"
+	    "	.long	0b - .					\n\t"
+	    "	b	. + (2b - 0b)				\n\t"
+	    "	.popsection					\n\t"
+#endif
+	    : "=r"(cur));
+#elif __LINUX_ARM_ARCH__>=7 || \
+      (defined(MODULE) && defined(CONFIG_ARM_MODULE_PLTS))
+	cur = __current;
 #else
-	asm("mrc p15, 0, %0, c13, c0, 3" : "=r"(cur));
+	asm(LOAD_SYM_ARMV6(%0, __current) : "=r"(cur));
 #endif
 	return cur;
 }
 
 #define current get_current()
-#else
-#include <asm-generic/current.h>
-#endif /* CONFIG_CURRENT_POINTER_IN_TPIDRURO */
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/arm/include/asm/switch_to.h b/arch/arm/include/asm/switch_to.h
index b55c7b2755e4..a482c99934ff 100644
--- a/arch/arm/include/asm/switch_to.h
+++ b/arch/arm/include/asm/switch_to.h
@@ -40,7 +40,8 @@ static inline void set_ti_cpu(struct task_struct *p)
 do {									\
 	__complete_pending_tlbi();					\
 	set_ti_cpu(next);						\
-	if (IS_ENABLED(CONFIG_CURRENT_POINTER_IN_TPIDRURO))		\
+	if (IS_ENABLED(CONFIG_CURRENT_POINTER_IN_TPIDRURO) ||		\
+	    IS_ENABLED(CONFIG_SMP))					\
 		__this_cpu_write(__entry_task, next);			\
 	last = __switch_to(prev,task_thread_info(prev), task_thread_info(next));	\
 } while (0)
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 004b89d86224..aecc403b2880 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -62,9 +62,6 @@ struct cpu_context_save {
 struct thread_info {
 	unsigned long		flags;		/* low level flags */
 	int			preempt_count;	/* 0 => preemptable, <0 => bug */
-#ifndef CONFIG_THREAD_INFO_IN_TASK
-	struct task_struct	*task;		/* main task structure */
-#endif
 	__u32			cpu;		/* cpu */
 	__u32			cpu_domain;	/* cpu domain */
 	struct cpu_context_save	cpu_context;	/* cpu context */
@@ -80,39 +77,15 @@ struct thread_info {
 
 #define INIT_THREAD_INFO(tsk)						\
 {									\
-	INIT_THREAD_INFO_TASK(tsk)					\
 	.flags		= 0,						\
 	.preempt_count	= INIT_PREEMPT_COUNT,				\
 }
 
-#ifdef CONFIG_THREAD_INFO_IN_TASK
-#define INIT_THREAD_INFO_TASK(tsk)
-
 static inline struct task_struct *thread_task(struct thread_info* ti)
 {
 	return (struct task_struct *)ti;
 }
 
-#else
-#define INIT_THREAD_INFO_TASK(tsk)	.task = &(tsk),
-
-static inline struct task_struct *thread_task(struct thread_info* ti)
-{
-	return ti->task;
-}
-
-/*
- * how to get the thread information struct from C
- */
-static inline struct thread_info *current_thread_info(void) __attribute_const__;
-
-static inline struct thread_info *current_thread_info(void)
-{
-	return (struct thread_info *)
-		(current_stack_pointer & ~(THREAD_SIZE - 1));
-}
-#endif
-
 #define thread_saved_pc(tsk)	\
 	((unsigned long)(task_thread_info(tsk)->cpu_context.pc))
 #define thread_saved_sp(tsk)	\