[PATCH v2] arm64: Introduce IRQ stack

From: Jungseok Lee
Date: Sun Sep 13 2015 - 10:43:00 EST


Currently, kernel context and interrupts are handled using a single
kernel stack navigated by sp_el1. This forces many systems to use
16KB stack, not 8KB one. Low memory platforms naturally suffer from
memory pressure accompanied by performance degradation.

This patch addresses the issue as introducing a separate percpu IRQ
stack to handle both hard and soft interrupts with two ground rules:

- Utilize sp_el0 in EL1 context, which is not used currently
- Do not complicate current_thread_info calculation

It is a core concept to trace struct thread_info using sp_el0 instead
of sp_el1. This approach helps arm64 align with other architectures
regarding object_is_on_stack() without additional complexity.

Cc: James Morse <james.morse@xxxxxxx>
Signed-off-by: Jungseok Lee <jungseoklee85@xxxxxxxxx>
---
Changes since v1:
- Rebased on top of v4.3-rc1
- Removed Kconfig about IRQ stack, per James
- Used PERCPU for IRQ stack, per James
- Tried to allocate IRQ stack when CPU is about to start up, per James
- Moved sp_el0 update into kernel_entry macro, per James
- Dropped S_SP removal patch, per Mark and James

arch/arm64/include/asm/irq.h | 8 +++
arch/arm64/include/asm/thread_info.h | 7 +-
arch/arm64/kernel/asm-offsets.c | 5 ++
arch/arm64/kernel/entry.S | 54 ++++++++++++++--
arch/arm64/kernel/head.S | 3 +
arch/arm64/kernel/irq.c | 21 ++++++
arch/arm64/kernel/smp.c | 6 ++
7 files changed, 95 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index bbb251b..67975a2 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -5,11 +5,19 @@

#include <asm-generic/irq.h>

+struct irq_stack {
+ void *stack;
+ unsigned long thread_sp;
+ unsigned int count;
+};
+
struct pt_regs;

extern void migrate_irqs(void);
extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));

+extern int alloc_irq_stack(unsigned int cpu);
+
static inline void acpi_irq_init(void)
{
/*
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index dcd06d1..44839c0 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -73,8 +73,11 @@ 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));
+ unsigned long sp_el0;
+
+ asm volatile("mrs %0, sp_el0" : "=r" (sp_el0));
+
+ return (struct thread_info *)(sp_el0 & ~(THREAD_SIZE - 1));
}

#define thread_saved_pc(tsk) \
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 8d89cf8..3bb5ce0 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -22,6 +22,7 @@
#include <linux/mm.h>
#include <linux/dma-mapping.h>
#include <linux/kvm_host.h>
+#include <asm/irq.h>
#include <asm/thread_info.h>
#include <asm/memory.h>
#include <asm/smp_plat.h>
@@ -41,6 +42,10 @@ int main(void)
BLANK();
DEFINE(THREAD_CPU_CONTEXT, offsetof(struct task_struct, thread.cpu_context));
BLANK();
+ DEFINE(IRQ_STACK, offsetof(struct irq_stack, stack));
+ DEFINE(IRQ_THREAD_SP, offsetof(struct irq_stack, thread_sp));
+ DEFINE(IRQ_COUNT, offsetof(struct irq_stack, count));
+ BLANK();
DEFINE(S_X0, offsetof(struct pt_regs, regs[0]));
DEFINE(S_X1, offsetof(struct pt_regs, regs[1]));
DEFINE(S_X2, offsetof(struct pt_regs, regs[2]));
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 4306c93..c156540 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -88,7 +88,7 @@

.if \el == 0
mrs x21, sp_el0
- get_thread_info tsk // Ensure MDSCR_EL1.SS is clear,
+ get_thread_info \el, tsk // Ensure MDSCR_EL1.SS is clear,
ldr x19, [tsk, #TI_FLAGS] // since we can unmask debug
disable_step_tsk x19, x20 // exceptions when scheduling.
.else
@@ -105,6 +105,8 @@
.if \el == 0
mvn x21, xzr
str x21, [sp, #S_SYSCALLNO]
+ mov x25, sp
+ msr sp_el0, x25
.endif

/*
@@ -163,9 +165,45 @@ alternative_endif
eret // return to kernel
.endm

- .macro get_thread_info, rd
+ .macro get_thread_info, el, rd
+ .if \el == 0
mov \rd, sp
- and \rd, \rd, #~(THREAD_SIZE - 1) // top of stack
+ .else
+ mrs \rd, sp_el0
+ .endif
+ and \rd, \rd, #~(THREAD_SIZE - 1) // bottom of thread stack
+ .endm
+
+ .macro get_irq_stack
+ adr_l x21, irq_stacks
+ mrs x22, tpidr_el1
+ add x21, x21, x22
+ .endm
+
+ .macro irq_stack_entry
+ get_irq_stack
+ ldr w23, [x21, #IRQ_COUNT]
+ cbnz w23, 1f // check irq recursion
+ mov x23, sp
+ str x23, [x21, #IRQ_THREAD_SP]
+ ldr x23, [x21, #IRQ_STACK]
+ mov sp, x23
+ mov x23, xzr
+1: add w23, w23, #1
+ str w23, [x21, #IRQ_COUNT]
+ .endm
+
+ .macro irq_stack_exit
+ get_irq_stack
+ ldr w23, [x21, #IRQ_COUNT]
+ sub w23, w23, #1
+ cbnz w23, 1f // check irq recursion
+ mov x23, sp
+ str x23, [x21, #IRQ_STACK]
+ ldr x23, [x21, #IRQ_THREAD_SP]
+ mov sp, x23
+ mov x23, xzr
+1: str w23, [x21, #IRQ_COUNT]
.endm

/*
@@ -183,10 +221,11 @@ tsk .req x28 // current thread_info
* Interrupt handling.
*/
.macro irq_handler
- adrp x1, handle_arch_irq
- ldr x1, [x1, #:lo12:handle_arch_irq]
+ ldr_l x1, handle_arch_irq
mov x0, sp
+ irq_stack_entry
blr x1
+ irq_stack_exit
.endm

.text
@@ -361,7 +400,7 @@ el1_irq:
irq_handler

#ifdef CONFIG_PREEMPT
- get_thread_info tsk
+ get_thread_info 1, tsk
ldr w24, [tsk, #TI_PREEMPT] // get preempt count
cbnz w24, 1f // preempt count != 0
ldr x0, [tsk, #TI_FLAGS] // get flags
@@ -597,6 +636,7 @@ ENTRY(cpu_switch_to)
ldp x29, x9, [x8], #16
ldr lr, [x8]
mov sp, x9
+ msr sp_el0, x9
ret
ENDPROC(cpu_switch_to)

@@ -655,7 +695,7 @@ ENTRY(ret_from_fork)
cbz x19, 1f // not a kernel thread
mov x0, x20
blr x19
-1: get_thread_info tsk
+1: get_thread_info 1, tsk
b ret_to_user
ENDPROC(ret_from_fork)

diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index a055be6..cb13290 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -441,6 +441,8 @@ __mmap_switched:
b 1b
2:
adr_l sp, initial_sp, x4
+ mov x4, sp
+ msr sp_el0, x4
str_l x21, __fdt_pointer, x5 // Save FDT pointer
str_l x24, memstart_addr, x6 // Save PHYS_OFFSET
mov x29, #0
@@ -613,6 +615,7 @@ ENDPROC(secondary_startup)
ENTRY(__secondary_switched)
ldr x0, [x21] // get secondary_data.stack
mov sp, x0
+ msr sp_el0, x0
mov x29, #0
b secondary_start_kernel
ENDPROC(__secondary_switched)
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 11dc3fd..88acb63 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -31,6 +31,8 @@

unsigned long irq_err_count;

+DEFINE_PER_CPU(struct irq_stack, irq_stacks);
+
int arch_show_interrupts(struct seq_file *p, int prec)
{
show_ipi_list(p, prec);
@@ -50,6 +52,9 @@ void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))

void __init init_IRQ(void)
{
+ if (alloc_irq_stack(smp_processor_id()))
+ panic("Failed to allocate IRQ stack for boot cpu");
+
irqchip_init();
if (!handle_arch_irq)
panic("No interrupt controller found.");
@@ -115,3 +120,19 @@ void migrate_irqs(void)
local_irq_restore(flags);
}
#endif /* CONFIG_HOTPLUG_CPU */
+
+int alloc_irq_stack(unsigned int cpu)
+{
+ void *stack;
+
+ if (per_cpu(irq_stacks, cpu).stack)
+ return 0;
+
+ stack = (void *)__get_free_pages(THREADINFO_GFP, THREAD_SIZE_ORDER);
+ if (!stack)
+ return -ENOMEM;
+
+ per_cpu(irq_stacks, cpu).stack = stack + THREAD_START_SP;
+
+ return 0;
+}
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index dbdaacd..0bd7049 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -97,6 +97,12 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
secondary_data.stack = task_stack_page(idle) + THREAD_START_SP;
__flush_dcache_area(&secondary_data, sizeof(secondary_data));

+ ret = alloc_irq_stack(cpu);
+ if (ret) {
+ pr_crit("CPU%u: failed to allocate IRQ stack\n", cpu);
+ return ret;
+ }
+
/*
* Now bring the CPU into our world.
*/
--
2.5.0

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/