diff options
Diffstat (limited to 'fs/xfs/xfs_aops.c')
| -rw-r--r-- | fs/xfs/xfs_aops.c | 123 |
1 files changed, 98 insertions, 25 deletions
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 75df77d09f7..faaf716e208 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -975,14 +975,39 @@ xfs_vm_writepage( * Given that we do not allow direct reclaim to call us, we should * never be called while in a filesystem transaction. */ - if (WARN_ON(current->flags & PF_FSTRANS)) + if (WARN_ON_ONCE(current->flags & PF_FSTRANS)) goto redirty; /* Is this page beyond the end of the file? */ offset = i_size_read(inode); end_index = offset >> PAGE_CACHE_SHIFT; last_index = (offset - 1) >> PAGE_CACHE_SHIFT; - if (page->index >= end_index) { + + /* + * The page index is less than the end_index, adjust the end_offset + * to the highest offset that this page should represent. + * ----------------------------------------------------- + * | file mapping | <EOF> | + * ----------------------------------------------------- + * | Page ... | Page N-2 | Page N-1 | Page N | | + * ^--------------------------------^----------|-------- + * | desired writeback range | see else | + * ---------------------------------^------------------| + */ + if (page->index < end_index) + end_offset = (xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT; + else { + /* + * Check whether the page to write out is beyond or straddles + * i_size or not. + * ------------------------------------------------------- + * | file mapping | <EOF> | + * ------------------------------------------------------- + * | Page ... | Page N-2 | Page N-1 | Page N | Beyond | + * ^--------------------------------^-----------|--------- + * | | Straddles | + * ---------------------------------^-----------|--------| + */ unsigned offset_into_page = offset & (PAGE_CACHE_SIZE - 1); /* @@ -990,24 +1015,36 @@ xfs_vm_writepage( * truncate operation that is in progress. We must redirty the * page so that reclaim stops reclaiming it. Otherwise * xfs_vm_releasepage() is called on it and gets confused. + * + * Note that the end_index is unsigned long, it would overflow + * if the given offset is greater than 16TB on 32-bit system + * and if we do check the page is fully outside i_size or not + * via "if (page->index >= end_index + 1)" as "end_index + 1" + * will be evaluated to 0. Hence this page will be redirtied + * and be written out repeatedly which would result in an + * infinite loop, the user program that perform this operation + * will hang. Instead, we can verify this situation by checking + * if the page to write is totally beyond the i_size or if it's + * offset is just equal to the EOF. */ - if (page->index >= end_index + 1 || offset_into_page == 0) + if (page->index > end_index || + (page->index == end_index && offset_into_page == 0)) goto redirty; /* * The page straddles i_size. It must be zeroed out on each * and every writepage invocation because it may be mmapped. * "A file is mapped in multiples of the page size. For a file - * that is not a multiple of the page size, the remaining + * that is not a multiple of the page size, the remaining * memory is zeroed when mapped, and writes to that region are * not written out to the file." */ zero_user_segment(page, offset_into_page, PAGE_CACHE_SIZE); + + /* Adjust the end_offset to the end of file */ + end_offset = offset; } - end_offset = min_t(unsigned long long, - (xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT, - offset); len = 1 << inode->i_blkbits; bh = head = page_buffers(page); @@ -1188,9 +1225,9 @@ xfs_vm_releasepage( xfs_count_page_state(page, &delalloc, &unwritten); - if (WARN_ON(delalloc)) + if (WARN_ON_ONCE(delalloc)) return 0; - if (WARN_ON(unwritten)) + if (WARN_ON_ONCE(unwritten)) return 0; return try_to_free_buffers(page); @@ -1344,6 +1381,14 @@ __xfs_get_blocks( /* * If this is O_DIRECT or the mpage code calling tell them how large * the mapping is, so that we can avoid repeated get_blocks calls. + * + * If the mapping spans EOF, then we have to break the mapping up as the + * mapping for blocks beyond EOF must be marked new so that sub block + * regions can be correctly zeroed. We can't do this for mappings within + * EOF unless the mapping was just allocated or is unwritten, otherwise + * the callers would overwrite existing data with zeros. Hence we have + * to split the mapping into a range up to and including EOF, and a + * second mapping for beyond EOF. */ if (direct || size > (1 << inode->i_blkbits)) { xfs_off_t mapping_size; @@ -1354,6 +1399,12 @@ __xfs_get_blocks( ASSERT(mapping_size > 0); if (mapping_size > size) mapping_size = size; + if (offset < i_size_read(inode) && + offset + mapping_size >= i_size_read(inode)) { + /* limit mapping to block that spans EOF */ + mapping_size = roundup_64(i_size_read(inode) - offset, + 1 << inode->i_blkbits); + } if (mapping_size > LONG_MAX) mapping_size = LONG_MAX; @@ -1435,9 +1486,8 @@ STATIC ssize_t xfs_vm_direct_IO( int rw, struct kiocb *iocb, - const struct iovec *iov, - loff_t offset, - unsigned long nr_segs) + struct iov_iter *iter, + loff_t offset) { struct inode *inode = iocb->ki_filp->f_mapping->host; struct block_device *bdev = xfs_find_bdev_for_inode(inode); @@ -1445,7 +1495,7 @@ xfs_vm_direct_IO( ssize_t ret; if (rw & WRITE) { - size_t size = iov_length(iov, nr_segs); + size_t size = iov_iter_count(iter); /* * We cannot preallocate a size update transaction here as we @@ -1457,17 +1507,15 @@ xfs_vm_direct_IO( if (offset + size > XFS_I(inode)->i_d.di_size) ioend->io_isdirect = 1; - ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iov, - offset, nr_segs, - xfs_get_blocks_direct, + ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iter, + offset, xfs_get_blocks_direct, xfs_end_io_direct_write, NULL, DIO_ASYNC_EXTEND); if (ret != -EIOCBQUEUED && iocb->private) goto out_destroy_ioend; } else { - ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iov, - offset, nr_segs, - xfs_get_blocks_direct, + ret = __blockdev_direct_IO(rw, iocb, inode, bdev, iter, + offset, xfs_get_blocks_direct, NULL, NULL, 0); } @@ -1566,6 +1614,16 @@ xfs_vm_write_failed( xfs_vm_kill_delalloc_range(inode, block_offset, block_offset + bh->b_size); + + /* + * This buffer does not contain data anymore. make sure anyone + * who finds it knows that for certain. + */ + clear_buffer_delay(bh); + clear_buffer_uptodate(bh); + clear_buffer_mapped(bh); + clear_buffer_new(bh); + clear_buffer_dirty(bh); } } @@ -1599,12 +1657,21 @@ xfs_vm_write_begin( status = __block_write_begin(page, pos, len, xfs_get_blocks); if (unlikely(status)) { struct inode *inode = mapping->host; + size_t isize = i_size_read(inode); xfs_vm_write_failed(inode, page, pos, len); unlock_page(page); - if (pos + len > i_size_read(inode)) - truncate_pagecache(inode, i_size_read(inode)); + /* + * If the write is beyond EOF, we only want to kill blocks + * allocated in this write, not blocks that were previously + * written successfully. + */ + if (pos + len > isize) { + ssize_t start = max_t(ssize_t, pos, isize); + + truncate_pagecache_range(inode, start, pos + len); + } page_cache_release(page); page = NULL; @@ -1615,9 +1682,12 @@ xfs_vm_write_begin( } /* - * On failure, we only need to kill delalloc blocks beyond EOF because they - * will never be written. For blocks within EOF, generic_write_end() zeros them - * so they are safe to leave alone and be written with all the other valid data. + * On failure, we only need to kill delalloc blocks beyond EOF in the range of + * this specific write because they will never be written. Previous writes + * beyond EOF where block allocation succeeded do not need to be trashed, so + * only new blocks from this write should be trashed. For blocks within + * EOF, generic_write_end() zeros them so they are safe to leave alone and be + * written with all the other valid data. */ STATIC int xfs_vm_write_end( @@ -1640,8 +1710,11 @@ xfs_vm_write_end( loff_t to = pos + len; if (to > isize) { - truncate_pagecache(inode, isize); + /* only kill blocks in this write beyond EOF */ + if (pos > isize) + isize = pos; xfs_vm_kill_delalloc_range(inode, isize, to); + truncate_pagecache_range(inode, isize, to); } } return ret; |