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
msync.c
// SPDX-License-Identifier: GPL-2.0
/*
 *	linux/mm/msync.c
 *
 * Copyright (C) 1994-1999  Linus Torvalds
 */

/*
 * The msync() system call.
 */
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/file.h>
#include <linux/syscalls.h>
#include <linux/sched.h>

/*
 * MS_SYNC syncs the entire file - including mappings.
 *
 * MS_ASYNC does not start I/O (it used to, up to 2.5.67).
 * Nor does it marks the relevant pages dirty (it used to up to 2.6.17).
 * Now it doesn't do anything, since dirty pages are properly tracked.
 *
 * The application may now run fsync() to
 * write out the dirty pages and wait on the writeout and check the result.
 * Or the application may run fadvise(FADV_DONTNEED) against the fd to start
 * async writeout immediately.
 * So by _not_ starting I/O in MS_ASYNC we provide complete flexibility to
 * applications.
 */
SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags)
{
	unsigned long end;
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	int unmapped_error = 0;
	int error = -EINVAL;

	start = untagged_addr(start);

	if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC))
		goto out;
	if (offset_in_page(start))
		goto out;
	if ((flags & MS_ASYNC) && (flags & MS_SYNC))
		goto out;
	error = -ENOMEM;
	len = (len + ~PAGE_MASK) & PAGE_MASK;
	end = start + len;
	if (end < start)
		goto out;
	error = 0;
	if (end == start)
		goto out;
	/*
	 * If the interval [start,end) covers some unmapped address ranges,
	 * just ignore them, but return -ENOMEM at the end.
	 */
	mmap_read_lock(mm);
	vma = find_vma(mm, start);
	for (;;) {
		struct file *file;
		loff_t fstart, fend;

		/* Still start < end. */
		error = -ENOMEM;
		if (!vma)
			goto out_unlock;
		/* Here start < vma->vm_end. */
		if (start < vma->vm_start) {
			start = vma->vm_start;
			if (start >= end)
				goto out_unlock;
			unmapped_error = -ENOMEM;
		}
		/* Here vma->vm_start <= start < vma->vm_end. */
		if ((flags & MS_INVALIDATE) &&
				(vma->vm_flags & VM_LOCKED)) {
			error = -EBUSY;
			goto out_unlock;
		}
		file = vma->vm_file;
		fstart = (start - vma->vm_start) +
			 ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
		fend = fstart + (min(end, vma->vm_end) - start) - 1;
		start = vma->vm_end;
		if ((flags & MS_SYNC) && file &&
				(vma->vm_flags & VM_SHARED)) {
			get_file(file);
			mmap_read_unlock(mm);
			error = vfs_fsync_range(file, fstart, fend, 1);
			fput(file);
			if (error || start >= end)
				goto out;
			mmap_read_lock(mm);
			vma = find_vma(mm, start);
		} else {
			if (start >= end) {
				error = 0;
				goto out_unlock;
			}
			vma = vma->vm_next;
		}
	}
out_unlock:
	mmap_read_unlock(mm);
out:
	return error ? : unmapped_error;
}
back to top