linux_dsm_epyc7002/arch/x86/kernel/irq_32.c
Linus Torvalds 986cb48c5a x86-32/irq: Don't switch to irq stack for a user-mode irq
If the irq happens in user mode, our kernel stack is empty
(apart from the pt_regs themselves, of course), so there's no
need or advantage to switch.

And it really doesn't save any stack space, quite the reverse:
it means that a nested interrupt cannot switch irq stacks. So
instead of saving kernel stack space, it actually causes the
potential for *more* stack usage.

Also simplify the preemption count copy when we do switch
stacks: just copy the whole preemption count, rather than just
the softirq parts of it.  There is no advantage to the partial
copy: it is more effort to get a less correct result.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1202191139260.10000@i5.linux-foundation.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-02-20 09:30:18 +01:00

202 lines
5.1 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/module.h>
#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>
DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
EXPORT_PER_CPU_SYMBOL(irq_stat);
DEFINE_PER_CPU(struct pt_regs *, irq_regs);
EXPORT_PER_CPU_SYMBOL(irq_regs);
#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
/*
* per-CPU IRQ handling contexts (thread information and stack)
*/
union irq_ctx {
struct thread_info tinfo;
u32 stack[THREAD_SIZE/sizeof(u32)];
} __attribute__((aligned(THREAD_SIZE)));
static DEFINE_PER_CPU(union irq_ctx *, hardirq_ctx);
static DEFINE_PER_CPU(union irq_ctx *, softirq_ctx);
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 int
execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
{
union irq_ctx *curctx, *irqctx;
u32 *isp, arg1, arg2;
curctx = (union irq_ctx *) current_thread_info();
irqctx = __this_cpu_read(hardirq_ctx);
/*
* 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(curctx == irqctx))
return 0;
/* build the stack frame on the IRQ stack */
isp = (u32 *) ((char *)irqctx + sizeof(*irqctx));
irqctx->tinfo.task = curctx->tinfo.task;
irqctx->tinfo.previous_esp = current_stack_pointer;
/* Copy the preempt_count so that the [soft]irq checks work. */
irqctx->tinfo.preempt_count = curctx->tinfo.preempt_count;
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), "=d" (arg2), "=b" (isp)
: "0" (irq), "1" (desc), "2" (isp),
"D" (desc->handle_irq)
: "memory", "cc", "ecx");
return 1;
}
/*
* allocate per-cpu stacks for hardirq and for softirq processing
*/
void __cpuinit irq_ctx_init(int cpu)
{
union irq_ctx *irqctx;
if (per_cpu(hardirq_ctx, cpu))
return;
irqctx = page_address(alloc_pages_node(cpu_to_node(cpu),
THREAD_FLAGS,
THREAD_ORDER));
memset(&irqctx->tinfo, 0, sizeof(struct thread_info));
irqctx->tinfo.cpu = cpu;
irqctx->tinfo.preempt_count = HARDIRQ_OFFSET;
irqctx->tinfo.addr_limit = MAKE_MM_SEG(0);
per_cpu(hardirq_ctx, cpu) = irqctx;
irqctx = page_address(alloc_pages_node(cpu_to_node(cpu),
THREAD_FLAGS,
THREAD_ORDER));
memset(&irqctx->tinfo, 0, sizeof(struct thread_info));
irqctx->tinfo.cpu = cpu;
irqctx->tinfo.addr_limit = MAKE_MM_SEG(0);
per_cpu(softirq_ctx, cpu) = irqctx;
printk(KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n",
cpu, per_cpu(hardirq_ctx, cpu), per_cpu(softirq_ctx, cpu));
}
asmlinkage void do_softirq(void)
{
unsigned long flags;
struct thread_info *curctx;
union irq_ctx *irqctx;
u32 *isp;
if (in_interrupt())
return;
local_irq_save(flags);
if (local_softirq_pending()) {
curctx = current_thread_info();
irqctx = __this_cpu_read(softirq_ctx);
irqctx->tinfo.task = curctx->task;
irqctx->tinfo.previous_esp = current_stack_pointer;
/* build the stack frame on the softirq stack */
isp = (u32 *) ((char *)irqctx + sizeof(*irqctx));
call_on_stack(__do_softirq, isp);
/*
* Shouldn't happen, we returned above if in_interrupt():
*/
WARN_ON_ONCE(softirq_count());
}
local_irq_restore(flags);
}
bool handle_irq(unsigned irq, struct pt_regs *regs)
{
struct irq_desc *desc;
int overflow;
overflow = check_stack_overflow();
desc = irq_to_desc(irq);
if (unlikely(!desc))
return false;
if (user_mode_vm(regs) || !execute_on_irq_stack(overflow, desc, irq)) {
if (unlikely(overflow))
print_stack_overflow();
desc->handle_irq(irq, desc);
}
return true;
}