1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
|
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 1992, 1998 Linus Torvalds, Ingo Molnar
*
* This file contains the lowest level x86_64-specific interrupt
* entry and irq statistics code. All the remaining irq logic is
* done by the generic kernel/irq/ code and in the
* x86_64-specific irq controller code. (e.g. i8259.c and
* io_apic.c.)
*/
#include <linux/kernel_stat.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/seq_file.h>
#include <linux/delay.h>
#include <linux/ftrace.h>
#include <linux/uaccess.h>
#include <linux/smp.h>
#include <linux/sched/task_stack.h>
#include <asm/cpu_entry_area.h>
#include <asm/io_apic.h>
#include <asm/apic.h>
DEFINE_PER_CPU_PAGE_ALIGNED(struct irq_stack, irq_stack_backing_store) __visible;
DECLARE_INIT_PER_CPU(irq_stack_backing_store);
int sysctl_panic_on_stackoverflow;
/*
* Probabilistic stack overflow check:
*
* Regular device interrupts can enter on the following stacks:
*
* - User stack
*
* - Kernel task stack
*
* - Interrupt stack if a device driver reenables interrupts
* which should only happen in really old drivers.
*
* - Debug IST stack
*
* All other contexts are invalid.
*/
static inline void stack_overflow_check(struct pt_regs *regs)
{
#ifdef CONFIG_DEBUG_STACKOVERFLOW
#define STACK_MARGIN 128
u64 irq_stack_top, irq_stack_bottom, estack_top, estack_bottom;
u64 curbase = (u64)task_stack_page(current);
struct cea_exception_stacks *estacks;
if (user_mode(regs))
return;
if (regs->sp >= curbase + sizeof(struct pt_regs) + STACK_MARGIN &&
regs->sp <= curbase + THREAD_SIZE)
return;
irq_stack_top = (u64)__this_cpu_read(hardirq_stack_ptr);
irq_stack_bottom = irq_stack_top - IRQ_STACK_SIZE + STACK_MARGIN;
if (regs->sp >= irq_stack_bottom && regs->sp <= irq_stack_top)
return;
estacks = __this_cpu_read(cea_exception_stacks);
estack_top = CEA_ESTACK_TOP(estacks, DB);
estack_bottom = CEA_ESTACK_BOT(estacks, DB) + STACK_MARGIN;
if (regs->sp >= estack_bottom && regs->sp <= estack_top)
return;
WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx, irq stack:%Lx-%Lx, exception stack: %Lx-%Lx, ip:%pF)\n",
current->comm, curbase, regs->sp,
irq_stack_bottom, irq_stack_top,
estack_bottom, estack_top, (void *)regs->ip);
if (sysctl_panic_on_stackoverflow)
panic("low stack detected by irq handler - check messages\n");
#endif
}
bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
{
stack_overflow_check(regs);
if (IS_ERR_OR_NULL(desc))
return false;
generic_handle_irq_desc(desc);
return true;
}
#ifdef CONFIG_VMAP_STACK
/*
* VMAP the backing store with guard pages
*/
static int map_irq_stack(unsigned int cpu)
{
char *stack = (char *)per_cpu_ptr(&irq_stack_backing_store, cpu);
struct page *pages[IRQ_STACK_SIZE / PAGE_SIZE];
void *va;
int i;
for (i = 0; i < IRQ_STACK_SIZE / PAGE_SIZE; i++) {
phys_addr_t pa = per_cpu_ptr_to_phys(stack + (i << PAGE_SHIFT));
pages[i] = pfn_to_page(pa >> PAGE_SHIFT);
}
va = vmap(pages, IRQ_STACK_SIZE / PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL);
if (!va)
return -ENOMEM;
per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE;
return 0;
}
#else
/*
* If VMAP stacks are disabled due to KASAN, just use the per cpu
* backing store without guard pages.
*/
static int map_irq_stack(unsigned int cpu)
{
void *va = per_cpu_ptr(&irq_stack_backing_store, cpu);
per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE;
return 0;
}
#endif
int irq_init_percpu_irqstack(unsigned int cpu)
{
if (per_cpu(hardirq_stack_ptr, cpu))
return 0;
return map_irq_stack(cpu);
}
|