From ae76dd9a6b5bbe5315fb7028e03f68f75b8538f3 Mon Sep 17 00:00:00 2001 From: Duane Griffin Date: Fri, 25 Jul 2008 01:46:23 -0700 Subject: ext3: handle corrupted orphan list at mount If the orphan node list includes valid, untruncatable nodes with nlink > 0 the ext3_orphan_cleanup loop which attempts to delete them will not do so, causing it to loop forever. Fix by checking for such nodes in the ext3_orphan_get function. This patch fixes the second case (image hdb.20000009.softlockup.gz) reported in http://bugzilla.kernel.org/show_bug.cgi?id=10882. [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: printk warning fix] Signed-off-by: Duane Griffin Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext3/inode.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) (limited to 'fs/ext3/inode.c') diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 6ae4ecf3ce40..74b432fa166b 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -2253,6 +2253,19 @@ static void ext3_free_branches(handle_t *handle, struct inode *inode, } } +int ext3_can_truncate(struct inode *inode) +{ + if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) + return 0; + if (S_ISREG(inode->i_mode)) + return 1; + if (S_ISDIR(inode->i_mode)) + return 1; + if (S_ISLNK(inode->i_mode)) + return !ext3_inode_is_fast_symlink(inode); + return 0; +} + /* * ext3_truncate() * @@ -2297,12 +2310,7 @@ void ext3_truncate(struct inode *inode) unsigned blocksize = inode->i_sb->s_blocksize; struct page *page; - if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || - S_ISLNK(inode->i_mode))) - return; - if (ext3_inode_is_fast_symlink(inode)) - return; - if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) + if (!ext3_can_truncate(inode)) return; /* -- cgit v1.2.3 From 95450f5a7e53d5752ce1a0d0b8282e10fe745ae0 Mon Sep 17 00:00:00 2001 From: Hidehiro Kawai Date: Fri, 25 Jul 2008 01:46:24 -0700 Subject: ext3: don't read inode block if the buffer has a write error A transient I/O error can corrupt inode data. Here is the scenario: (1) update inode_A at the block_B (2) pdflush writes out new inode_A to the filesystem, but it results in write I/O error, at this point, BH_Uptodate flag of the buffer for block_B is cleared and BH_Write_EIO is set (3) create new inode_C which located at block_B, and __ext3_get_inode_loc() tries to read on-disk block_B because the buffer is not uptodate (4) if it can read on-disk block_B successfully, inode_A is overwritten by old data This patch makes __ext3_get_inode_loc() not read the inode block if the buffer has BH_Write_EIO flag. In this case, the buffer should have the latest information, so setting the uptodate flag to the buffer (this avoids WARN_ON_ONCE() in mark_buffer_dirty().) According to this change, we would need to test BH_Write_EIO flag for the error checking. Currently nobody checks write I/O errors on metadata buffers, but it will be done in other patches I'm working on. Signed-off-by: Hidehiro Kawai Cc: sugita Cc: Satoshi OSHIMA Cc: Nick Piggin Cc: Jan Kara Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext3/inode.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'fs/ext3/inode.c') diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 74b432fa166b..36f74f17a11c 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -2521,6 +2521,16 @@ static int __ext3_get_inode_loc(struct inode *inode, } if (!buffer_uptodate(bh)) { lock_buffer(bh); + + /* + * If the buffer has the write error flag, we have failed + * to write out another inode in the same block. In this + * case, we don't have to read the block because we may + * read the old inode data successfully. + */ + if (buffer_write_io_error(bh) && !buffer_uptodate(bh)) + set_buffer_uptodate(bh); + if (buffer_uptodate(bh)) { /* someone brought it uptodate while we waited */ unlock_buffer(bh); -- cgit v1.2.3 From 3ccc3167b0e5d46ab3bf03e22fbdb7616ce038cd Mon Sep 17 00:00:00 2001 From: Duane Griffin Date: Fri, 25 Jul 2008 01:46:26 -0700 Subject: ext3: handle deleting corrupted indirect blocks While freeing indirect blocks we attach a journal head to the parent buffer head, free the blocks, then journal the parent. If the indirect block list is corrupted and points to the parent the journal head will be detached when the block is cleared, causing an OOPS. Check for that explicitly and handle it gracefully. This patch fixes the third case (image hdb.20000057.nullderef.gz) reported in http://bugzilla.kernel.org/show_bug.cgi?id=10882. Immediately above the change, in the ext3_free_data function, we call ext3_clear_blocks to clear the indirect blocks in this parent block. If one of those blocks happens to actually be the parent block it will clear b_private / BH_JBD. I did the check at the end rather than earlier as it seemed more elegant. I don't think there should be much practical difference, although it is possible the FS may not be quite so badly corrupted if we did it the other way (and didn't clear the block at all). To be honest, I'm not convinced there aren't other similar failure modes lurking in this code, although I couldn't find any with a quick review. [akpm@linux-foundation.org: fix printk warning] Signed-off-by: Duane Griffin Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext3/inode.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'fs/ext3/inode.c') diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 36f74f17a11c..3bf07d70b914 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -2127,7 +2127,21 @@ static void ext3_free_data(handle_t *handle, struct inode *inode, if (this_bh) { BUFFER_TRACE(this_bh, "call ext3_journal_dirty_metadata"); - ext3_journal_dirty_metadata(handle, this_bh); + + /* + * The buffer head should have an attached journal head at this + * point. However, if the data is corrupted and an indirect + * block pointed to itself, it would have been detached when + * the block was cleared. Check for this instead of OOPSing. + */ + if (bh2jh(this_bh)) + ext3_journal_dirty_metadata(handle, this_bh); + else + ext3_error(inode->i_sb, "ext3_free_data", + "circular indirect block detected, " + "inode=%lu, block=%llu", + inode->i_ino, + (unsigned long long)this_bh->b_blocknr); } } -- cgit v1.2.3 From 8ab22b9abb5c55413802e4adc9aa6223324547c3 Mon Sep 17 00:00:00 2001 From: Hisashi Hifumi Date: Mon, 28 Jul 2008 15:46:36 -0700 Subject: vfs: pagecache usage optimization for pagesize!=blocksize When we read some part of a file through pagecache, if there is a pagecache of corresponding index but this page is not uptodate, read IO is issued and this page will be uptodate. I think this is good for pagesize == blocksize environment but there is room for improvement on pagesize != blocksize environment. Because in this case a page can have multiple buffers and even if a page is not uptodate, some buffers can be uptodate. So I suggest that when all buffers which correspond to a part of a file that we want to read are uptodate, use this pagecache and copy data from this pagecache to user buffer even if a page is not uptodate. This can reduce read IO and improve system throughput. I wrote a benchmark program and got result number with this program. This benchmark do: 1: mount and open a test file. 2: create a 512MB file. 3: close a file and umount. 4: mount and again open a test file. 5: pwrite randomly 300000 times on a test file. offset is aligned by IO size(1024bytes). 6: measure time of preading randomly 100000 times on a test file. The result was: 2.6.26 330 sec 2.6.26-patched 226 sec Arch:i386 Filesystem:ext3 Blocksize:1024 bytes Memory: 1GB On ext3/4, a file is written through buffer/block. So random read/write mixed workloads or random read after random write workloads are optimized with this patch under pagesize != blocksize environment. This test result showed this. The benchmark program is as follows: #include #include #include #include #include #include #include #include #include #define LEN 1024 #define LOOP 1024*512 /* 512MB */ main(void) { unsigned long i, offset, filesize; int fd; char buf[LEN]; time_t t1, t2; if (mount("/dev/sda1", "/root/test1/", "ext3", 0, 0) < 0) { perror("cannot mount\n"); exit(1); } memset(buf, 0, LEN); fd = open("/root/test1/testfile", O_CREAT|O_RDWR|O_TRUNC); if (fd < 0) { perror("cannot open file\n"); exit(1); } for (i = 0; i < LOOP; i++) write(fd, buf, LEN); close(fd); if (umount("/root/test1/") < 0) { perror("cannot umount\n"); exit(1); } if (mount("/dev/sda1", "/root/test1/", "ext3", 0, 0) < 0) { perror("cannot mount\n"); exit(1); } fd = open("/root/test1/testfile", O_RDWR); if (fd < 0) { perror("cannot open file\n"); exit(1); } filesize = LEN * LOOP; for (i = 0; i < 300000; i++){ offset = (random() % filesize) & (~(LEN - 1)); pwrite(fd, buf, LEN, offset); } printf("start test\n"); time(&t1); for (i = 0; i < 100000; i++){ offset = (random() % filesize) & (~(LEN - 1)); pread(fd, buf, LEN, offset); } time(&t2); printf("%ld sec\n", t2-t1); close(fd); if (umount("/root/test1/") < 0) { perror("cannot umount\n"); exit(1); } } Signed-off-by: Hisashi Hifumi Cc: Nick Piggin Cc: Christoph Hellwig Cc: Jan Kara Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/buffer.c | 46 +++++++++++++++++++++++ fs/ext2/inode.c | 1 + fs/ext3/inode.c | 67 +++++++++++++++++---------------- fs/ext4/inode.c | 92 +++++++++++++++++++++++---------------------- include/linux/buffer_head.h | 2 + include/linux/fs.h | 44 +++++++++++----------- mm/filemap.c | 14 ++++++- 7 files changed, 167 insertions(+), 99 deletions(-) (limited to 'fs/ext3/inode.c') diff --git a/fs/buffer.c b/fs/buffer.c index f95805019639..ca12a6bb82b1 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2095,6 +2095,52 @@ int generic_write_end(struct file *file, struct address_space *mapping, } EXPORT_SYMBOL(generic_write_end); +/* + * block_is_partially_uptodate checks whether buffers within a page are + * uptodate or not. + * + * Returns true if all buffers which correspond to a file portion + * we want to read are uptodate. + */ +int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc, + unsigned long from) +{ + struct inode *inode = page->mapping->host; + unsigned block_start, block_end, blocksize; + unsigned to; + struct buffer_head *bh, *head; + int ret = 1; + + if (!page_has_buffers(page)) + return 0; + + blocksize = 1 << inode->i_blkbits; + to = min_t(unsigned, PAGE_CACHE_SIZE - from, desc->count); + to = from + to; + if (from < blocksize && to > PAGE_CACHE_SIZE - blocksize) + return 0; + + head = page_buffers(page); + bh = head; + block_start = 0; + do { + block_end = block_start + blocksize; + if (block_end > from && block_start < to) { + if (!buffer_uptodate(bh)) { + ret = 0; + break; + } + if (block_end >= to) + break; + } + block_start = block_end; + bh = bh->b_this_page; + } while (bh != head); + + return ret; +} +EXPORT_SYMBOL(block_is_partially_uptodate); + /* * Generic "read page" function for block devices that have the normal * get_block functionality. This is most of the block device filesystems. diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 384fc0d1dd74..991d6dfeb51f 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -791,6 +791,7 @@ const struct address_space_operations ext2_aops = { .direct_IO = ext2_direct_IO, .writepages = ext2_writepages, .migratepage = buffer_migrate_page, + .is_partially_uptodate = block_is_partially_uptodate, }; const struct address_space_operations ext2_aops_xip = { diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 3bf07d70b914..507d8689b111 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -1767,44 +1767,47 @@ static int ext3_journalled_set_page_dirty(struct page *page) } static const struct address_space_operations ext3_ordered_aops = { - .readpage = ext3_readpage, - .readpages = ext3_readpages, - .writepage = ext3_ordered_writepage, - .sync_page = block_sync_page, - .write_begin = ext3_write_begin, - .write_end = ext3_ordered_write_end, - .bmap = ext3_bmap, - .invalidatepage = ext3_invalidatepage, - .releasepage = ext3_releasepage, - .direct_IO = ext3_direct_IO, - .migratepage = buffer_migrate_page, + .readpage = ext3_readpage, + .readpages = ext3_readpages, + .writepage = ext3_ordered_writepage, + .sync_page = block_sync_page, + .write_begin = ext3_write_begin, + .write_end = ext3_ordered_write_end, + .bmap = ext3_bmap, + .invalidatepage = ext3_invalidatepage, + .releasepage = ext3_releasepage, + .direct_IO = ext3_direct_IO, + .migratepage = buffer_migrate_page, + .is_partially_uptodate = block_is_partially_uptodate, }; static const struct address_space_operations ext3_writeback_aops = { - .readpage = ext3_readpage, - .readpages = ext3_readpages, - .writepage = ext3_writeback_writepage, - .sync_page = block_sync_page, - .write_begin = ext3_write_begin, - .write_end = ext3_writeback_write_end, - .bmap = ext3_bmap, - .invalidatepage = ext3_invalidatepage, - .releasepage = ext3_releasepage, - .direct_IO = ext3_direct_IO, - .migratepage = buffer_migrate_page, + .readpage = ext3_readpage, + .readpages = ext3_readpages, + .writepage = ext3_writeback_writepage, + .sync_page = block_sync_page, + .write_begin = ext3_write_begin, + .write_end = ext3_writeback_write_end, + .bmap = ext3_bmap, + .invalidatepage = ext3_invalidatepage, + .releasepage = ext3_releasepage, + .direct_IO = ext3_direct_IO, + .migratepage = buffer_migrate_page, + .is_partially_uptodate = block_is_partially_uptodate, }; static const struct address_space_operations ext3_journalled_aops = { - .readpage = ext3_readpage, - .readpages = ext3_readpages, - .writepage = ext3_journalled_writepage, - .sync_page = block_sync_page, - .write_begin = ext3_write_begin, - .write_end = ext3_journalled_write_end, - .set_page_dirty = ext3_journalled_set_page_dirty, - .bmap = ext3_bmap, - .invalidatepage = ext3_invalidatepage, - .releasepage = ext3_releasepage, + .readpage = ext3_readpage, + .readpages = ext3_readpages, + .writepage = ext3_journalled_writepage, + .sync_page = block_sync_page, + .write_begin = ext3_write_begin, + .write_end = ext3_journalled_write_end, + .set_page_dirty = ext3_journalled_set_page_dirty, + .bmap = ext3_bmap, + .invalidatepage = ext3_invalidatepage, + .releasepage = ext3_releasepage, + .is_partially_uptodate = block_is_partially_uptodate, }; void ext3_set_aops(struct inode *inode) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 8ca2763df091..9843b046c235 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2806,59 +2806,63 @@ static int ext4_journalled_set_page_dirty(struct page *page) } static const struct address_space_operations ext4_ordered_aops = { - .readpage = ext4_readpage, - .readpages = ext4_readpages, - .writepage = ext4_normal_writepage, - .sync_page = block_sync_page, - .write_begin = ext4_write_begin, - .write_end = ext4_ordered_write_end, - .bmap = ext4_bmap, - .invalidatepage = ext4_invalidatepage, - .releasepage = ext4_releasepage, - .direct_IO = ext4_direct_IO, - .migratepage = buffer_migrate_page, + .readpage = ext4_readpage, + .readpages = ext4_readpages, + .writepage = ext4_normal_writepage, + .sync_page = block_sync_page, + .write_begin = ext4_write_begin, + .write_end = ext4_ordered_write_end, + .bmap = ext4_bmap, + .invalidatepage = ext4_invalidatepage, + .releasepage = ext4_releasepage, + .direct_IO = ext4_direct_IO, + .migratepage = buffer_migrate_page, + .is_partially_uptodate = block_is_partially_uptodate, }; static const struct address_space_operations ext4_writeback_aops = { - .readpage = ext4_readpage, - .readpages = ext4_readpages, - .writepage = ext4_normal_writepage, - .sync_page = block_sync_page, - .write_begin = ext4_write_begin, - .write_end = ext4_writeback_write_end, - .bmap = ext4_bmap, - .invalidatepage = ext4_invalidatepage, - .releasepage = ext4_releasepage, - .direct_IO = ext4_direct_IO, - .migratepage = buffer_migrate_page, + .readpage = ext4_readpage, + .readpages = ext4_readpages, + .writepage = ext4_normal_writepage, + .sync_page = block_sync_page, + .write_begin = ext4_write_begin, + .write_end = ext4_writeback_write_end, + .bmap = ext4_bmap, + .invalidatepage = ext4_invalidatepage, + .releasepage = ext4_releasepage, + .direct_IO = ext4_direct_IO, + .migratepage = buffer_migrate_page, + .is_partially_uptodate = block_is_partially_uptodate, }; static const struct address_space_operations ext4_journalled_aops = { - .readpage = ext4_readpage, - .readpages = ext4_readpages, - .writepage = ext4_journalled_writepage, - .sync_page = block_sync_page, - .write_begin = ext4_write_begin, - .write_end = ext4_journalled_write_end, - .set_page_dirty = ext4_journalled_set_page_dirty, - .bmap = ext4_bmap, - .invalidatepage = ext4_invalidatepage, - .releasepage = ext4_releasepage, + .readpage = ext4_readpage, + .readpages = ext4_readpages, + .writepage = ext4_journalled_writepage, + .sync_page = block_sync_page, + .write_begin = ext4_write_begin, + .write_end = ext4_journalled_write_end, + .set_page_dirty = ext4_journalled_set_page_dirty, + .bmap = ext4_bmap, + .invalidatepage = ext4_invalidatepage, + .releasepage = ext4_releasepage, + .is_partially_uptodate = block_is_partially_uptodate, }; static const struct address_space_operations ext4_da_aops = { - .readpage = ext4_readpage, - .readpages = ext4_readpages, - .writepage = ext4_da_writepage, - .writepages = ext4_da_writepages, - .sync_page = block_sync_page, - .write_begin = ext4_da_write_begin, - .write_end = ext4_da_write_end, - .bmap = ext4_bmap, - .invalidatepage = ext4_da_invalidatepage, - .releasepage = ext4_releasepage, - .direct_IO = ext4_direct_IO, - .migratepage = buffer_migrate_page, + .readpage = ext4_readpage, + .readpages = ext4_readpages, + .writepage = ext4_da_writepage, + .writepages = ext4_da_writepages, + .sync_page = block_sync_page, + .write_begin = ext4_da_write_begin, + .write_end = ext4_da_write_end, + .bmap = ext4_bmap, + .invalidatepage = ext4_da_invalidatepage, + .releasepage = ext4_releasepage, + .direct_IO = ext4_direct_IO, + .migratepage = buffer_migrate_page, + .is_partially_uptodate = block_is_partially_uptodate, }; void ext4_set_aops(struct inode *inode) diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 82aa36c53ea7..50cfe8ceb478 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -205,6 +205,8 @@ void block_invalidatepage(struct page *page, unsigned long offset); int block_write_full_page(struct page *page, get_block_t *get_block, struct writeback_control *wbc); int block_read_full_page(struct page*, get_block_t*); +int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc, + unsigned long from); int block_write_begin(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t*); diff --git a/include/linux/fs.h b/include/linux/fs.h index 8252b045e624..580b513668fe 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -443,6 +443,27 @@ static inline size_t iov_iter_count(struct iov_iter *i) return i->count; } +/* + * "descriptor" for what we're up to with a read. + * This allows us to use the same read code yet + * have multiple different users of the data that + * we read from a file. + * + * The simplest case just copies the data to user + * mode. + */ +typedef struct { + size_t written; + size_t count; + union { + char __user *buf; + void *data; + } arg; + int error; +} read_descriptor_t; + +typedef int (*read_actor_t)(read_descriptor_t *, struct page *, + unsigned long, unsigned long); struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); @@ -484,6 +505,8 @@ struct address_space_operations { int (*migratepage) (struct address_space *, struct page *, struct page *); int (*launder_page) (struct page *); + int (*is_partially_uptodate) (struct page *, read_descriptor_t *, + unsigned long); }; /* @@ -1198,27 +1221,6 @@ struct block_device_operations { struct module *owner; }; -/* - * "descriptor" for what we're up to with a read. - * This allows us to use the same read code yet - * have multiple different users of the data that - * we read from a file. - * - * The simplest case just copies the data to user - * mode. - */ -typedef struct { - size_t written; - size_t count; - union { - char __user * buf; - void *data; - } arg; - int error; -} read_descriptor_t; - -typedef int (*read_actor_t)(read_descriptor_t *, struct page *, unsigned long, unsigned long); - /* These macros are for out of kernel modules to test that * the kernel supports the unlocked_ioctl and compat_ioctl * fields in struct file_operations. */ diff --git a/mm/filemap.c b/mm/filemap.c index 5de7633e1dbe..42bbc6909ba4 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1023,8 +1023,17 @@ find_page: ra, filp, page, index, last_index - index); } - if (!PageUptodate(page)) - goto page_not_up_to_date; + if (!PageUptodate(page)) { + if (inode->i_blkbits == PAGE_CACHE_SHIFT || + !mapping->a_ops->is_partially_uptodate) + goto page_not_up_to_date; + if (TestSetPageLocked(page)) + goto page_not_up_to_date; + if (!mapping->a_ops->is_partially_uptodate(page, + desc, offset)) + goto page_not_up_to_date_locked; + unlock_page(page); + } page_ok: /* * i_size must be checked after we know the page is Uptodate. @@ -1094,6 +1103,7 @@ page_not_up_to_date: if (lock_page_killable(page)) goto readpage_eio; +page_not_up_to_date_locked: /* Did it get truncated before we got the lock? */ if (!page->mapping) { unlock_page(page); -- cgit v1.2.3