mirror of
https://github.com/edk2-porting/linux-next.git
synced 2025-01-04 11:43:54 +08:00
18b7a6bef6
The IRQ stack lives in percpu space, so an IRQ handler that overflows it will overwrite other data structures. Use vmap() to remap the IRQ stack so that it will have the usual guard pages that vmap()/vmalloc() allocations have. With this, the kernel will panic immediately on an IRQ stack overflow. [ tglx: Move the map code to a proper place and invoke it only when a CPU is about to be brought online. No point in installing the map at early boot for all possible CPUs. Fail the CPU bringup if the vmap() fails as done for all other preparatory stages in CPU hotplug. ] Signed-off-by: Andy Lutomirski <luto@kernel.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Borislav Petkov <bp@suse.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Nicolai Stange <nstange@suse.de> Cc: Sean Christopherson <sean.j.christopherson@intel.com> Cc: x86-ml <x86@kernel.org> Link: https://lkml.kernel.org/r/20190414160146.363733568@linutronix.de
138 lines
3.5 KiB
C
138 lines
3.5 KiB
C
// 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);
|
|
}
|