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

arch/arm/Kconfig

@@ -127,8 +127,8 @@ config ARM
 	select PERF_USE_VMALLOC
 	select RTC_LIB
 	select SYS_SUPPORTS_APM_EMULATION
-	select THREAD_INFO_IN_TASK if CURRENT_POINTER_IN_TPIDRURO
-	select HAVE_ARCH_VMAP_STACK if MMU && THREAD_INFO_IN_TASK && (!LD_IS_LLD || LLD_VERSION >= 140000)
+	select THREAD_INFO_IN_TASK
+	select HAVE_ARCH_VMAP_STACK if MMU && (!LD_IS_LLD || LLD_VERSION >= 140000)
 	select TRACE_IRQFLAGS_SUPPORT if !CPU_V7M
 	# Above selects are sorted alphabetically; please add new ones
 	# according to that.  Thanks.
@@ -1158,7 +1158,7 @@ config CURRENT_POINTER_IN_TPIDRURO
 
 config IRQSTACKS
 	def_bool y
-	depends on THREAD_INFO_IN_TASK
+	depends on MMU
 	select HAVE_IRQ_EXIT_ON_IRQ_STACK
 	select HAVE_SOFTIRQ_ON_OWN_STACK
 
@@ -1608,7 +1608,7 @@ config CC_HAVE_STACKPROTECTOR_TLS
 
 config STACKPROTECTOR_PER_TASK
 	bool "Use a unique stack canary value for each task"
-	depends on STACKPROTECTOR && THREAD_INFO_IN_TASK && !XIP_DEFLATED_DATA
+	depends on STACKPROTECTOR && CURRENT_POINTER_IN_TPIDRURO && !XIP_DEFLATED_DATA
 	depends on GCC_PLUGINS || CC_HAVE_STACKPROTECTOR_TLS
 	select GCC_PLUGIN_ARM_SSP_PER_TASK if !CC_HAVE_STACKPROTECTOR_TLS
 	default y

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
  */

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__ */
 

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)

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)	\

arch/arm/kernel/asm-offsets.c

@@ -43,9 +43,6 @@ int main(void)
   BLANK();
   DEFINE(TI_FLAGS,		offsetof(struct thread_info, flags));
   DEFINE(TI_PREEMPT,		offsetof(struct thread_info, preempt_count));
-#ifndef CONFIG_THREAD_INFO_IN_TASK
-  DEFINE(TI_TASK,		offsetof(struct thread_info, task));
-#endif
   DEFINE(TI_CPU,		offsetof(struct thread_info, cpu));
   DEFINE(TI_CPU_DOMAIN,		offsetof(struct thread_info, cpu_domain));
   DEFINE(TI_CPU_SAVE,		offsetof(struct thread_info, cpu_context));

arch/arm/kernel/entry-armv.S

@@ -807,12 +807,13 @@ ENTRY(__switch_to)
 	switch_tls r1, r4, r5, r3, r7
 #if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_SMP) && \
     !defined(CONFIG_STACKPROTECTOR_PER_TASK)
-	ldr	r9, [r2, #TI_TASK]
 	ldr	r8, =__stack_chk_guard
 	.if (TSK_STACK_CANARY > IMM12_MASK)
-	add	r9, r9, #TSK_STACK_CANARY & ~IMM12_MASK
-	.endif
+	add	r9, r2, #TSK_STACK_CANARY & ~IMM12_MASK
 	ldr	r9, [r9, #TSK_STACK_CANARY & IMM12_MASK]
+	.else
+	ldr	r9, [r2, #TSK_STACK_CANARY & IMM12_MASK]
+	.endif
 #endif
 	mov	r7, r2				@ Preserve 'next'
 #ifdef CONFIG_CPU_USE_DOMAINS
@@ -829,7 +830,7 @@ ENTRY(__switch_to)
 #endif
 	mov	r0, r5
 #if !defined(CONFIG_THUMB2_KERNEL) && !defined(CONFIG_VMAP_STACK)
-	set_current r7
+	set_current r7, r8
 	ldmia	r4, {r4 - sl, fp, sp, pc}	@ Load all regs saved previously
 #else
 	mov	r1, r7
@@ -851,7 +852,7 @@ ENTRY(__switch_to)
 	@ switches us to another stack, with few other side effects. In order
 	@ to prevent this distinction from causing any inconsistencies, let's
 	@ keep the 'set_current' call as close as we can to the update of SP.
-	set_current r1
+	set_current r1, r2
 	mov	sp, ip
 	ret	lr
 #endif

arch/arm/kernel/entry-v7m.S

@@ -97,15 +97,17 @@ ENTRY(__switch_to)
 	str	sp, [ip], #4
 	str	lr, [ip], #4
 	mov	r5, r0
+	mov	r6, r2			@ Preserve 'next'
 	add	r4, r2, #TI_CPU_SAVE
 	ldr	r0, =thread_notify_head
 	mov	r1, #THREAD_NOTIFY_SWITCH
 	bl	atomic_notifier_call_chain
-	mov	ip, r4
 	mov	r0, r5
-	ldmia	ip!, {r4 - r11}		@ Load all regs saved previously
-	ldr	sp, [ip]
-	ldr	pc, [ip, #4]!
+	mov	r1, r6
+	ldmia	r4, {r4 - r12, lr}	@ Load all regs saved previously
+	set_current r1, r2
+	mov	sp, ip
+	bx	lr
 	.fnend
 ENDPROC(__switch_to)
 

arch/arm/kernel/head-common.S

@@ -105,10 +105,8 @@ __mmap_switched:
 	mov	r1, #0
 	bl	__memset			@ clear .bss
 
-#ifdef CONFIG_CURRENT_POINTER_IN_TPIDRURO
 	adr_l	r0, init_task			@ get swapper task_struct
-	set_current r0
-#endif
+	set_current r0, r1
 
 	ldmia	r4, {r0, r1, r2, r3}
 	str	r9, [r0]			@ Save processor ID

arch/arm/kernel/process.c

@@ -36,7 +36,7 @@
 
 #include "signal.h"
 
-#ifdef CONFIG_CURRENT_POINTER_IN_TPIDRURO
+#if defined(CONFIG_CURRENT_POINTER_IN_TPIDRURO) || defined(CONFIG_SMP)
 DEFINE_PER_CPU(struct task_struct *, __entry_task);
 #endif
 
@@ -46,6 +46,11 @@ unsigned long __stack_chk_guard __read_mostly;
 EXPORT_SYMBOL(__stack_chk_guard);
 #endif
 
+#ifndef CONFIG_CURRENT_POINTER_IN_TPIDRURO
+asmlinkage struct task_struct *__current;
+EXPORT_SYMBOL(__current);
+#endif
+
 static const char *processor_modes[] __maybe_unused = {
   "USER_26", "FIQ_26" , "IRQ_26" , "SVC_26" , "UK4_26" , "UK5_26" , "UK6_26" , "UK7_26" ,
   "UK8_26" , "UK9_26" , "UK10_26", "UK11_26", "UK12_26", "UK13_26", "UK14_26", "UK15_26",

arch/arm/kernel/smp.c

@@ -403,6 +403,17 @@ static void smp_store_cpu_info(unsigned int cpuid)
 	check_cpu_icache_size(cpuid);
 }
 
+static void set_current(struct task_struct *cur)
+{
+	if (!IS_ENABLED(CONFIG_CURRENT_POINTER_IN_TPIDRURO) && !is_smp()) {
+		__current = cur;
+		return;
+	}
+
+	/* Set TPIDRURO */
+	asm("mcr p15, 0, %0, c13, c0, 3" :: "r"(cur) : "memory");
+}
+
 /*
  * This is the secondary CPU boot entry.  We're using this CPUs
  * idle thread stack, but a set of temporary page tables.

arch/arm/kernel/traps.c

@@ -865,7 +865,9 @@ early_initcall(allocate_overflow_stacks);
 asmlinkage void handle_bad_stack(struct pt_regs *regs)
 {
 	unsigned long tsk_stk = (unsigned long)current->stack;
+#ifdef CONFIG_IRQSTACKS
 	unsigned long irq_stk = (unsigned long)this_cpu_read(irq_stack_ptr);
+#endif
 	unsigned long ovf_stk = (unsigned long)this_cpu_read(overflow_stack_ptr);
 
 	console_verbose();
@@ -873,8 +875,10 @@ asmlinkage void handle_bad_stack(struct pt_regs *regs)
 
 	pr_emerg("Task stack:     [0x%08lx..0x%08lx]\n",
 		 tsk_stk, tsk_stk + THREAD_SIZE);
+#ifdef CONFIG_IRQSTACKS
 	pr_emerg("IRQ stack:      [0x%08lx..0x%08lx]\n",
 		 irq_stk - THREAD_SIZE, irq_stk);
+#endif
 	pr_emerg("Overflow stack: [0x%08lx..0x%08lx]\n",
 		 ovf_stk - OVERFLOW_STACK_SIZE, ovf_stk);