Revision 35bf49e054214a0c7d3b0a0f8606f753f3f6ae96 authored by Lu Baolu on 23 August 2022, 06:15:57 UTC, committed by Joerg Roedel on 07 September 2022, 13:14:57 UTC
With CONFIG_INTEL_IOMMU_DEBUGFS enabled, below lockdep splat are seen
when an I/O fault occurs on a machine with an Intel IOMMU in it.

 DMAR: DRHD: handling fault status reg 3
 DMAR: [DMA Write NO_PASID] Request device [00:1a.0] fault addr 0x0
       [fault reason 0x05] PTE Write access is not set
 DMAR: Dump dmar0 table entries for IOVA 0x0
 DMAR: root entry: 0x0000000127f42001
 DMAR: context entry: hi 0x0000000000001502, low 0x000000012d8ab001
 ================================
 WARNING: inconsistent lock state
 5.20.0-0.rc0.20220812git7ebfc85e2cd7.10.fc38.x86_64 #1 Not tainted
 --------------------------------
 inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage.
 rngd/1006 [HC1[1]:SC0[0]:HE0:SE1] takes:
 ff177021416f2d78 (&k->k_lock){?.+.}-{2:2}, at: klist_next+0x1b/0x160
 {HARDIRQ-ON-W} state was registered at:
   lock_acquire+0xce/0x2d0
   _raw_spin_lock+0x33/0x80
   klist_add_tail+0x46/0x80
   bus_add_device+0xee/0x150
   device_add+0x39d/0x9a0
   add_memory_block+0x108/0x1d0
   memory_dev_init+0xe1/0x117
   driver_init+0x43/0x4d
   kernel_init_freeable+0x1c2/0x2cc
   kernel_init+0x16/0x140
   ret_from_fork+0x1f/0x30
 irq event stamp: 7812
 hardirqs last  enabled at (7811): [<ffffffff85000e86>] asm_sysvec_apic_timer_interrupt+0x16/0x20
 hardirqs last disabled at (7812): [<ffffffff84f16894>] irqentry_enter+0x54/0x60
 softirqs last  enabled at (7794): [<ffffffff840ff669>] __irq_exit_rcu+0xf9/0x170
 softirqs last disabled at (7787): [<ffffffff840ff669>] __irq_exit_rcu+0xf9/0x170

The klist iterator functions using spin_*lock_irq*() but the klist
insertion functions using spin_*lock(), combined with the Intel DMAR
IOMMU driver iterating over klists from atomic (hardirq) context, where
pci_get_domain_bus_and_slot() calls into bus_find_device() which iterates
over klists.

As currently there's no plan to fix the klist to make it safe to use in
atomic context, this fixes the lockdep splat by avoid calling
pci_get_domain_bus_and_slot() in the hardirq context.

Fixes: 8ac0b64b9735 ("iommu/vt-d: Use pci_get_domain_bus_and_slot() in pgtable_walk()")
Reported-by: Lennert Buytenhek <buytenh@wantstofly.org>
Link: https://lore.kernel.org/linux-iommu/Yvo2dfpEh%2FWC+Wrr@wantstofly.org/
Link: https://lore.kernel.org/linux-iommu/YvyBdPwrTuHHbn5X@wantstofly.org/
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20220819015949.4795-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
1 parent a349ffc
Raw File
file.c
// SPDX-License-Identifier: GPL-2.0+
/*
 * NILFS regular file handling primitives including fsync().
 *
 * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
 *
 * Written by Amagai Yoshiji and Ryusuke Konishi.
 */

#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/writeback.h>
#include "nilfs.h"
#include "segment.h"

int nilfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
	/*
	 * Called from fsync() system call
	 * This is the only entry point that can catch write and synch
	 * timing for both data blocks and intermediate blocks.
	 *
	 * This function should be implemented when the writeback function
	 * will be implemented.
	 */
	struct the_nilfs *nilfs;
	struct inode *inode = file->f_mapping->host;
	int err = 0;

	if (nilfs_inode_dirty(inode)) {
		if (datasync)
			err = nilfs_construct_dsync_segment(inode->i_sb, inode,
							    start, end);
		else
			err = nilfs_construct_segment(inode->i_sb);
	}

	nilfs = inode->i_sb->s_fs_info;
	if (!err)
		err = nilfs_flush_device(nilfs);

	return err;
}

static vm_fault_t nilfs_page_mkwrite(struct vm_fault *vmf)
{
	struct vm_area_struct *vma = vmf->vma;
	struct page *page = vmf->page;
	struct inode *inode = file_inode(vma->vm_file);
	struct nilfs_transaction_info ti;
	int ret = 0;

	if (unlikely(nilfs_near_disk_full(inode->i_sb->s_fs_info)))
		return VM_FAULT_SIGBUS; /* -ENOSPC */

	sb_start_pagefault(inode->i_sb);
	lock_page(page);
	if (page->mapping != inode->i_mapping ||
	    page_offset(page) >= i_size_read(inode) || !PageUptodate(page)) {
		unlock_page(page);
		ret = -EFAULT;	/* make the VM retry the fault */
		goto out;
	}

	/*
	 * check to see if the page is mapped already (no holes)
	 */
	if (PageMappedToDisk(page))
		goto mapped;

	if (page_has_buffers(page)) {
		struct buffer_head *bh, *head;
		int fully_mapped = 1;

		bh = head = page_buffers(page);
		do {
			if (!buffer_mapped(bh)) {
				fully_mapped = 0;
				break;
			}
		} while (bh = bh->b_this_page, bh != head);

		if (fully_mapped) {
			SetPageMappedToDisk(page);
			goto mapped;
		}
	}
	unlock_page(page);

	/*
	 * fill hole blocks
	 */
	ret = nilfs_transaction_begin(inode->i_sb, &ti, 1);
	/* never returns -ENOMEM, but may return -ENOSPC */
	if (unlikely(ret))
		goto out;

	file_update_time(vma->vm_file);
	ret = block_page_mkwrite(vma, vmf, nilfs_get_block);
	if (ret) {
		nilfs_transaction_abort(inode->i_sb);
		goto out;
	}
	nilfs_set_file_dirty(inode, 1 << (PAGE_SHIFT - inode->i_blkbits));
	nilfs_transaction_commit(inode->i_sb);

 mapped:
	wait_for_stable_page(page);
 out:
	sb_end_pagefault(inode->i_sb);
	return block_page_mkwrite_return(ret);
}

static const struct vm_operations_struct nilfs_file_vm_ops = {
	.fault		= filemap_fault,
	.map_pages	= filemap_map_pages,
	.page_mkwrite	= nilfs_page_mkwrite,
};

static int nilfs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	file_accessed(file);
	vma->vm_ops = &nilfs_file_vm_ops;
	return 0;
}

/*
 * We have mostly NULL's here: the current defaults are ok for
 * the nilfs filesystem.
 */
const struct file_operations nilfs_file_operations = {
	.llseek		= generic_file_llseek,
	.read_iter	= generic_file_read_iter,
	.write_iter	= generic_file_write_iter,
	.unlocked_ioctl	= nilfs_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= nilfs_compat_ioctl,
#endif	/* CONFIG_COMPAT */
	.mmap		= nilfs_file_mmap,
	.open		= generic_file_open,
	/* .release	= nilfs_release_file, */
	.fsync		= nilfs_sync_file,
	.splice_read	= generic_file_splice_read,
	.splice_write   = iter_file_splice_write,
};

const struct inode_operations nilfs_file_inode_operations = {
	.setattr	= nilfs_setattr,
	.permission     = nilfs_permission,
	.fiemap		= nilfs_fiemap,
	.fileattr_get	= nilfs_fileattr_get,
	.fileattr_set	= nilfs_fileattr_set,
};

/* end of file */
back to top