linux/arch/x86/kernel/irq_32.c
Steven Rostedt 0788aa6a23 x86: Prepare removal of previous_esp from i386 thread_info structure
The i386 thread_info contains a previous_esp field that is used
to daisy chain the different stacks for dump_stack()
(ie. irq, softirq, thread stacks).

The goal is to eventual make i386 handling of thread_info the same
as x86_64, which means that the thread_info will not be in the stack
but as a per_cpu variable. We will no longer depend on thread_info
being able to daisy chain different stacks as it will only exist
in one location (the thread stack).

By moving previous_esp to the end of thread_info and referencing
it as an offset instead of using a thread_info field, this becomes
a stepping stone to moving the thread_info.

The offset to get to the previous stack is rather ugly in this
patch, but this is only temporary and the prev_esp will be changed
in the next commit. This commit is more for sanity checks of the
change.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Robert Richter <rric@kernel.org>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/20110806012353.891757693@goodmis.org
Link: http://lkml.kernel.org/r/20140206144321.608754481@goodmis.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
2014-03-06 16:56:54 -08:00

191 lines
4.9 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, *prev_esp, 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;
/* Save the next esp after thread_info */
prev_esp = (u32 *) ((char *)irqctx + sizeof(struct thread_info) -
sizeof(long));
*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), "=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 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),
THREADINFO_GFP,
THREAD_SIZE_ORDER));
memset(&irqctx->tinfo, 0, sizeof(struct thread_info));
irqctx->tinfo.cpu = cpu;
irqctx->tinfo.addr_limit = MAKE_MM_SEG(0);
per_cpu(hardirq_ctx, cpu) = irqctx;
irqctx = page_address(alloc_pages_node(cpu_to_node(cpu),
THREADINFO_GFP,
THREAD_SIZE_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));
}
void do_softirq_own_stack(void)
{
struct thread_info *curctx;
union irq_ctx *irqctx;
u32 *isp, *prev_esp;
curctx = current_thread_info();
irqctx = __this_cpu_read(softirq_ctx);
irqctx->tinfo.task = curctx->task;
/* build the stack frame on the softirq stack */
isp = (u32 *) ((char *)irqctx + sizeof(*irqctx));
/* Push the previous esp onto the stack */
prev_esp = (u32 *) ((char *)irqctx + sizeof(struct thread_info) -
sizeof(long));
*prev_esp = current_stack_pointer;
call_on_stack(__do_softirq, isp);
}
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;
}