Commit 8c26c4e2 authored by Vyacheslav Dubeyko's avatar Vyacheslav Dubeyko Committed by Linus Torvalds
Browse files

nilfs2: fix issue with flush kernel thread after remount in RO mode because of... 


nilfs2: fix issue with flush kernel thread after remount in RO mode because of driver's internal error or metadata corruption

The NILFS2 driver remounts itself in RO mode in the case of discovering
metadata corruption (for example, discovering a broken bmap).  But
usually, this takes place when there have been file system operations
before remounting in RO mode.

Thereby, NILFS2 driver can be in RO mode with presence of dirty pages in
modified inodes' address spaces.  It results in flush kernel thread's
infinite trying to flush dirty pages in RO mode.  As a result, it is
possible to see such side effects as: (1) flush kernel thread occupies
50% - 99% of CPU time; (2) system can't be shutdowned without manual
power switch off.

SYMPTOMS:
(1) System log contains error message: "Remounting filesystem read-only".
(2) The flush kernel thread occupies 50% - 99% of CPU time.
(3) The system can't be shutdowned without manual power switch off.

REPRODUCTION PATH:
(1) Create volume group with name "unencrypted" by means of vgcreate utility.
(2) Run script (prepared by Anthony Doggett <Anthony2486@interfaces.org.uk>):

  ----------------[BEGIN SCRIPT]--------------------
  #!/bin/bash

  VG=unencrypted
  #apt-get install nilfs-tools darcs
  lvcreate --size 2G --name ntest $VG
  mkfs.nilfs2 -b 1024 -B 8192 /dev/mapper/$VG-ntest
  mkdir /var/tmp/n
  mkdir /var/tmp/n/ntest
  mount /dev/mapper/$VG-ntest /var/tmp/n/ntest
  mkdir /var/tmp/n/ntest/thedir
  cd /var/tmp/n/ntest/thedir
  sleep 2
  date
  darcs init
  sleep 2
  dmesg|tail -n 5
  date
  darcs whatsnew || true
  date
  sleep 2
  dmesg|tail -n 5
  ----------------[END SCRIPT]--------------------

(3) Try to shutdown the system.

REPRODUCIBILITY: 100%

FIX:

This patch implements checking mount state of NILFS2 driver in
nilfs_writepage(), nilfs_writepages() and nilfs_mdt_write_page()
methods.  If it is detected the RO mount state then all dirty pages are
simply discarded with warning messages is written in system log.

[akpm@linux-foundation.org: fix printk warning]
Signed-off-by: default avatarVyacheslav Dubeyko <slava@dubeyko.com>
Acked-by: default avatarRyusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Cc: Anthony Doggett <Anthony2486@interfaces.org.uk>
Cc: ARAI Shun-ichi <hermes@ceres.dti.ne.jp>
Cc: Piotr Szymaniak <szarpaj@grubelek.pl>
Cc: Zahid Chowdhury <zahid.chowdhury@starsolutions.com>
Cc: Elmer Zhang <freeboy6716@gmail.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 9151b398

fs/nilfs2/inode.c

+17 −0
Original line number Diff line number Diff line
@@ -175,6 +175,11 @@ static int nilfs_writepages(struct address_space *mapping, 
	struct inode *inode = mapping->host;

	int err = 0;



	if (inode->i_sb->s_flags & MS_RDONLY) {

		nilfs_clear_dirty_pages(mapping, false);

		return -EROFS;

	}



	if (wbc->sync_mode == WB_SYNC_ALL)

		err = nilfs_construct_dsync_segment(inode->i_sb, inode,

						    wbc->range_start,
@@ -187,6 +192,18 @@ static int nilfs_writepage(struct page *page, struct writeback_control *wbc) 
	struct inode *inode = page->mapping->host;

	int err;



	if (inode && (inode->i_sb->s_flags & MS_RDONLY)) {

		/*

		 * It means that filesystem was remounted in read-only

		 * mode because of error or metadata corruption. But we

		 * have dirty pages that try to be flushed in background.

		 * So, here we simply discard this dirty page.

		 */

		nilfs_clear_dirty_page(page, false);

		unlock_page(page);

		return -EROFS;

	}



	redirty_page_for_writepage(wbc, page);

	unlock_page(page);

fs/nilfs2/mdt.c

+15 −4
Original line number Diff line number Diff line
@@ -375,14 +375,25 @@ int nilfs_mdt_fetch_dirty(struct inode *inode) 
static int

nilfs_mdt_write_page(struct page *page, struct writeback_control *wbc)

{

	struct inode *inode;

	struct inode *inode = page->mapping->host;

	struct super_block *sb;

	int err = 0;



	if (inode && (inode->i_sb->s_flags & MS_RDONLY)) {

		/*

		 * It means that filesystem was remounted in read-only

		 * mode because of error or metadata corruption. But we

		 * have dirty pages that try to be flushed in background.

		 * So, here we simply discard this dirty page.

		 */

		nilfs_clear_dirty_page(page, false);

		unlock_page(page);

		return -EROFS;

	}



	redirty_page_for_writepage(wbc, page);

	unlock_page(page);



	inode = page->mapping->host;

	if (!inode)

		return 0;
@@ -561,10 +572,10 @@ void nilfs_mdt_restore_from_shadow_map(struct inode *inode) 
	if (mi->mi_palloc_cache)

		nilfs_palloc_clear_cache(inode);



	nilfs_clear_dirty_pages(inode->i_mapping);

	nilfs_clear_dirty_pages(inode->i_mapping, true);

	nilfs_copy_back_pages(inode->i_mapping, &shadow->frozen_data);



	nilfs_clear_dirty_pages(&ii->i_btnode_cache);

	nilfs_clear_dirty_pages(&ii->i_btnode_cache, true);

	nilfs_copy_back_pages(&ii->i_btnode_cache, &shadow->frozen_btnodes);



	nilfs_bmap_restore(ii->i_bmap, &shadow->bmap_store);

fs/nilfs2/page.c

+52 −18
Original line number Diff line number Diff line
@@ -370,7 +370,12 @@ repeat: 
	goto repeat;

}



void nilfs_clear_dirty_pages(struct address_space *mapping)

/**

 * nilfs_clear_dirty_pages - discard dirty pages in address space

 * @mapping: address space with dirty pages for discarding

 * @silent: suppress [true] or print [false] warning messages

 */

void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent)

{

	struct pagevec pvec;

	unsigned int i;
@@ -382,14 +387,48 @@ void nilfs_clear_dirty_pages(struct address_space *mapping) 
				  PAGEVEC_SIZE)) {

		for (i = 0; i < pagevec_count(&pvec); i++) {

			struct page *page = pvec.pages[i];

			struct buffer_head *bh, *head;



			lock_page(page);

			nilfs_clear_dirty_page(page, silent);

			unlock_page(page);

		}

		pagevec_release(&pvec);

		cond_resched();

	}

}



/**

 * nilfs_clear_dirty_page - discard dirty page

 * @page: dirty page that will be discarded

 * @silent: suppress [true] or print [false] warning messages

 */

void nilfs_clear_dirty_page(struct page *page, bool silent)

{

	struct inode *inode = page->mapping->host;

	struct super_block *sb = inode->i_sb;



	BUG_ON(!test_bit(PG_locked, &page->flags));



	if (!silent) {

		nilfs_warning(sb, __func__,

				"discard page: offset %lld, ino %lu",

				page_offset(page), inode->i_ino);

	}



	ClearPageUptodate(page);

	ClearPageMappedToDisk(page);



	if (page_has_buffers(page)) {

		struct buffer_head *bh, *head;



		bh = head = page_buffers(page);

		do {

			lock_buffer(bh);

			if (!silent) {

				nilfs_warning(sb, __func__,

					"discard block %llu, size %zu",

					(u64)bh->b_blocknr, bh->b_size);

			}

			clear_buffer_dirty(bh);

			clear_buffer_nilfs_volatile(bh);

			clear_buffer_nilfs_checked(bh);
@@ -397,15 +436,10 @@ void nilfs_clear_dirty_pages(struct address_space *mapping) 
			clear_buffer_uptodate(bh);

			clear_buffer_mapped(bh);

			unlock_buffer(bh);

				bh = bh->b_this_page;

			} while (bh != head);

		} while (bh = bh->b_this_page, bh != head);

	}



	__nilfs_clear_page_dirty(page);

			unlock_page(page);

		}

		pagevec_release(&pvec);

		cond_resched();

	}

}



unsigned nilfs_page_count_clean_buffers(struct page *page,

fs/nilfs2/page.h

+2 −1
Original line number Diff line number Diff line
@@ -55,7 +55,8 @@ void nilfs_page_bug(struct page *); 


int nilfs_copy_dirty_pages(struct address_space *, struct address_space *);

void nilfs_copy_back_pages(struct address_space *, struct address_space *);

void nilfs_clear_dirty_pages(struct address_space *);

void nilfs_clear_dirty_page(struct page *, bool);

void nilfs_clear_dirty_pages(struct address_space *, bool);

void nilfs_mapping_init(struct address_space *mapping, struct inode *inode,

			struct backing_dev_info *bdi);

unsigned nilfs_page_count_clean_buffers(struct page *, unsigned, unsigned);

CRA Git | Maintained and supported by SUSTech CRA and CCSE