Revision 1a3f2fd7fc4e8f24510830e265de2ffb8e3300d2 authored by Lu Baolu on 27 September 2020, 06:24:28 UTC, committed by Joerg Roedel on 01 October 2020, 12:54:17 UTC
Lock(&iommu->lock) without disabling irq causes lockdep warnings.

[   12.703950] ========================================================
[   12.703962] WARNING: possible irq lock inversion dependency detected
[   12.703975] 5.9.0-rc6+ #659 Not tainted
[   12.703983] --------------------------------------------------------
[   12.703995] systemd-udevd/284 just changed the state of lock:
[   12.704007] ffffffffbd6ff4d8 (device_domain_lock){..-.}-{2:2}, at:
               iommu_flush_dev_iotlb.part.57+0x2e/0x90
[   12.704031] but this lock took another, SOFTIRQ-unsafe lock in the past:
[   12.704043]  (&iommu->lock){+.+.}-{2:2}
[   12.704045]

               and interrupts could create inverse lock ordering between
               them.

[   12.704073]
               other info that might help us debug this:
[   12.704085]  Possible interrupt unsafe locking scenario:

[   12.704097]        CPU0                    CPU1
[   12.704106]        ----                    ----
[   12.704115]   lock(&iommu->lock);
[   12.704123]                                local_irq_disable();
[   12.704134]                                lock(device_domain_lock);
[   12.704146]                                lock(&iommu->lock);
[   12.704158]   <Interrupt>
[   12.704164]     lock(device_domain_lock);
[   12.704174]
                *** DEADLOCK ***

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20200927062428.13713-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
1 parent 0bbe4ce
Raw File
vmacache.c
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2014 Davidlohr Bueso.
 */
#include <linux/sched/signal.h>
#include <linux/sched/task.h>
#include <linux/mm.h>
#include <linux/vmacache.h>

/*
 * Hash based on the pmd of addr if configured with MMU, which provides a good
 * hit rate for workloads with spatial locality.  Otherwise, use pages.
 */
#ifdef CONFIG_MMU
#define VMACACHE_SHIFT	PMD_SHIFT
#else
#define VMACACHE_SHIFT	PAGE_SHIFT
#endif
#define VMACACHE_HASH(addr) ((addr >> VMACACHE_SHIFT) & VMACACHE_MASK)

/*
 * This task may be accessing a foreign mm via (for example)
 * get_user_pages()->find_vma().  The vmacache is task-local and this
 * task's vmacache pertains to a different mm (ie, its own).  There is
 * nothing we can do here.
 *
 * Also handle the case where a kernel thread has adopted this mm via
 * kthread_use_mm(). That kernel thread's vmacache is not applicable to this mm.
 */
static inline bool vmacache_valid_mm(struct mm_struct *mm)
{
	return current->mm == mm && !(current->flags & PF_KTHREAD);
}

void vmacache_update(unsigned long addr, struct vm_area_struct *newvma)
{
	if (vmacache_valid_mm(newvma->vm_mm))
		current->vmacache.vmas[VMACACHE_HASH(addr)] = newvma;
}

static bool vmacache_valid(struct mm_struct *mm)
{
	struct task_struct *curr;

	if (!vmacache_valid_mm(mm))
		return false;

	curr = current;
	if (mm->vmacache_seqnum != curr->vmacache.seqnum) {
		/*
		 * First attempt will always be invalid, initialize
		 * the new cache for this task here.
		 */
		curr->vmacache.seqnum = mm->vmacache_seqnum;
		vmacache_flush(curr);
		return false;
	}
	return true;
}

struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr)
{
	int idx = VMACACHE_HASH(addr);
	int i;

	count_vm_vmacache_event(VMACACHE_FIND_CALLS);

	if (!vmacache_valid(mm))
		return NULL;

	for (i = 0; i < VMACACHE_SIZE; i++) {
		struct vm_area_struct *vma = current->vmacache.vmas[idx];

		if (vma) {
#ifdef CONFIG_DEBUG_VM_VMACACHE
			if (WARN_ON_ONCE(vma->vm_mm != mm))
				break;
#endif
			if (vma->vm_start <= addr && vma->vm_end > addr) {
				count_vm_vmacache_event(VMACACHE_FIND_HITS);
				return vma;
			}
		}
		if (++idx == VMACACHE_SIZE)
			idx = 0;
	}

	return NULL;
}

#ifndef CONFIG_MMU
struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm,
					   unsigned long start,
					   unsigned long end)
{
	int idx = VMACACHE_HASH(start);
	int i;

	count_vm_vmacache_event(VMACACHE_FIND_CALLS);

	if (!vmacache_valid(mm))
		return NULL;

	for (i = 0; i < VMACACHE_SIZE; i++) {
		struct vm_area_struct *vma = current->vmacache.vmas[idx];

		if (vma && vma->vm_start == start && vma->vm_end == end) {
			count_vm_vmacache_event(VMACACHE_FIND_HITS);
			return vma;
		}
		if (++idx == VMACACHE_SIZE)
			idx = 0;
	}

	return NULL;
}
#endif
back to top