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

7 files changed, 34 insertions, 16 deletions

diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 645845e4982a..2c8d76fd7c66 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/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));
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 43d917f0d9a9..b58bda51e4b8 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/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
diff --git a/arch/arm/kernel/entry-v7m.S b/arch/arm/kernel/entry-v7m.S
index 520dd43e7e08..4e0d318b67c6 100644
--- a/arch/arm/kernel/entry-v7m.S
+++ b/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)
 
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index da18e0a17dc2..42cae73fcc19 100644
--- a/arch/arm/kernel/head-common.S
+++ b/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
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index d47159f3791c..0617af11377f 100644
--- a/arch/arm/kernel/process.c
+++ b/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",
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 9c55ca915ba4..951559e5bea3 100644
--- a/arch/arm/kernel/smp.c
+++ b/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.
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index b28a705c49cb..3f38357efc46 100644
--- a/arch/arm/kernel/traps.c
+++ b/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);