linux_dsm_epyc7002/arch/x86/kernel/irq_32.c
Andrey Ryabinin 196bd485ee x86/asm: Use register variable to get stack pointer value
Currently we use current_stack_pointer() function to get the value
of the stack pointer register. Since commit:

  f5caf621ee ("x86/asm: Fix inline asm call constraints for Clang")

... we have a stack register variable declared. It can be used instead of
current_stack_pointer() function which allows to optimize away some
excessive "mov %rsp, %<dst>" instructions:

 -mov    %rsp,%rdx
 -sub    %rdx,%rax
 -cmp    $0x3fff,%rax
 -ja     ffffffff810722fd <ist_begin_non_atomic+0x2d>

 +sub    %rsp,%rax
 +cmp    $0x3fff,%rax
 +ja     ffffffff810722fa <ist_begin_non_atomic+0x2a>

Remove current_stack_pointer(), rename __asm_call_sp to current_stack_pointer
and use it instead of the removed function.

Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20170929141537.29167-1-aryabinin@virtuozzo.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-09-29 19:39:44 +02:00

162 lines
4.0 KiB
C

/*
* Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar
*
* This file contains the lowest level x86-specific interrupt
* entry, irq-stacks and irq statistics code. All the remaining
* irq logic is done by the generic kernel/irq/ code and
* by the x86-specific irq controller code. (e.g. i8259.c and
* io_apic.c.)
*/
#include <linux/seq_file.h>
#include <linux/interrupt.h>
#include <linux/kernel_stat.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/delay.h>
#include <linux/uaccess.h>
#include <linux/percpu.h>
#include <linux/mm.h>
#include <asm/apic.h>
#ifdef CONFIG_DEBUG_STACKOVERFLOW
int sysctl_panic_on_stackoverflow __read_mostly;
/* Debugging check for stack overflow: is there less than 1KB free? */
static int check_stack_overflow(void)
{
long sp;
__asm__ __volatile__("andl %%esp,%0" :
"=r" (sp) : "0" (THREAD_SIZE - 1));
return sp < (sizeof(struct thread_info) + STACK_WARN);
}
static void print_stack_overflow(void)
{
printk(KERN_WARNING "low stack detected by irq handler\n");
dump_stack();
if (sysctl_panic_on_stackoverflow)
panic("low stack detected by irq handler - check messages\n");
}
#else
static inline int check_stack_overflow(void) { return 0; }
static inline void print_stack_overflow(void) { }
#endif
DEFINE_PER_CPU(struct irq_stack *, hardirq_stack);
DEFINE_PER_CPU(struct irq_stack *, softirq_stack);
static void call_on_stack(void *func, void *stack)
{
asm volatile("xchgl %%ebx,%%esp \n"
"call *%%edi \n"
"movl %%ebx,%%esp \n"
: "=b" (stack)
: "0" (stack),
"D"(func)
: "memory", "cc", "edx", "ecx", "eax");
}
static inline void *current_stack(void)
{
return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
}
static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
{
struct irq_stack *curstk, *irqstk;
u32 *isp, *prev_esp, arg1;
curstk = (struct irq_stack *) current_stack();
irqstk = __this_cpu_read(hardirq_stack);
/*
* this is where we switch to the IRQ stack. However, if we are
* already using the IRQ stack (because we interrupted a hardirq
* handler) we can't do that and just have to keep using the
* current stack (which is the irq stack already after all)
*/
if (unlikely(curstk == irqstk))
return 0;
isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));
/* Save the next esp at the bottom of the stack */
prev_esp = (u32 *)irqstk;
*prev_esp = current_stack_pointer;
if (unlikely(overflow))
call_on_stack(print_stack_overflow, isp);
asm volatile("xchgl %%ebx,%%esp \n"
"call *%%edi \n"
"movl %%ebx,%%esp \n"
: "=a" (arg1), "=b" (isp)
: "0" (desc), "1" (isp),
"D" (desc->handle_irq)
: "memory", "cc", "ecx");
return 1;
}
/*
* allocate per-cpu stacks for hardirq and for softirq processing
*/
void irq_ctx_init(int cpu)
{
struct irq_stack *irqstk;
if (per_cpu(hardirq_stack, cpu))
return;
irqstk = page_address(alloc_pages_node(cpu_to_node(cpu),
THREADINFO_GFP,
THREAD_SIZE_ORDER));
per_cpu(hardirq_stack, cpu) = irqstk;
irqstk = page_address(alloc_pages_node(cpu_to_node(cpu),
THREADINFO_GFP,
THREAD_SIZE_ORDER));
per_cpu(softirq_stack, cpu) = irqstk;
printk(KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n",
cpu, per_cpu(hardirq_stack, cpu), per_cpu(softirq_stack, cpu));
}
void do_softirq_own_stack(void)
{
struct irq_stack *irqstk;
u32 *isp, *prev_esp;
irqstk = __this_cpu_read(softirq_stack);
/* build the stack frame on the softirq stack */
isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));
/* Push the previous esp onto the stack */
prev_esp = (u32 *)irqstk;
*prev_esp = current_stack_pointer;
call_on_stack(__do_softirq, isp);
}
bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
{
int overflow = check_stack_overflow();
if (IS_ERR_OR_NULL(desc))
return false;
if (user_mode(regs) || !execute_on_irq_stack(overflow, desc)) {
if (unlikely(overflow))
print_stack_overflow();
generic_handle_irq_desc(desc);
}
return true;
}