diff options
Diffstat (limited to 'fs/ext4/inode.c')
-rw-r--r-- | fs/ext4/inode.c | 220 |
1 files changed, 205 insertions, 15 deletions
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 39a263ecca18..72d07c77bc7f 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -46,6 +46,7 @@ #include "truncate.h" #include <trace/events/ext4.h> +#include <trace/events/android_fs.h> #define MPAGE_DA_EXTENT_TAIL 0x01 @@ -141,7 +142,7 @@ static int ext4_meta_trans_blocks(struct inode *inode, int lblocks, /* * Test whether an inode is a fast symlink. */ -static int ext4_inode_is_fast_symlink(struct inode *inode) +int ext4_inode_is_fast_symlink(struct inode *inode) { int ea_blocks = EXT4_I(inode)->i_file_acl ? EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0; @@ -661,6 +662,20 @@ has_zeroout: ret = check_block_validity(inode, map); if (ret != 0) return ret; + + /* + * Inodes with freshly allocated blocks where contents will be + * visible after transaction commit must be on transaction's + * ordered data list. + */ + if (map->m_flags & EXT4_MAP_NEW && + !(map->m_flags & EXT4_MAP_UNWRITTEN) && + !IS_NOQUOTA(inode) && + ext4_should_order_data(inode)) { + ret = ext4_jbd2_file_inode(handle, inode); + if (ret) + return ret; + } } return retval; } @@ -879,6 +894,95 @@ int do_journal_get_write_access(handle_t *handle, static int ext4_get_block_write_nolock(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); + +#ifdef CONFIG_EXT4_FS_ENCRYPTION +static int ext4_block_write_begin(struct page *page, loff_t pos, unsigned len, + get_block_t *get_block) +{ + unsigned from = pos & (PAGE_CACHE_SIZE - 1); + unsigned to = from + len; + struct inode *inode = page->mapping->host; + unsigned block_start, block_end; + sector_t block; + int err = 0; + unsigned blocksize = inode->i_sb->s_blocksize; + unsigned bbits; + struct buffer_head *bh, *head, *wait[2], **wait_bh = wait; + bool decrypt = false; + + BUG_ON(!PageLocked(page)); + BUG_ON(from > PAGE_CACHE_SIZE); + BUG_ON(to > PAGE_CACHE_SIZE); + BUG_ON(from > to); + + if (!page_has_buffers(page)) + create_empty_buffers(page, blocksize, 0); + head = page_buffers(page); + bbits = ilog2(blocksize); + block = (sector_t)page->index << (PAGE_CACHE_SHIFT - bbits); + + for (bh = head, block_start = 0; bh != head || !block_start; + block++, block_start = block_end, bh = bh->b_this_page) { + block_end = block_start + blocksize; + if (block_end <= from || block_start >= to) { + if (PageUptodate(page)) { + if (!buffer_uptodate(bh)) + set_buffer_uptodate(bh); + } + continue; + } + if (buffer_new(bh)) + clear_buffer_new(bh); + if (!buffer_mapped(bh)) { + WARN_ON(bh->b_size != blocksize); + err = get_block(inode, block, bh, 1); + if (err) + break; + if (buffer_new(bh)) { + unmap_underlying_metadata(bh->b_bdev, + bh->b_blocknr); + if (PageUptodate(page)) { + clear_buffer_new(bh); + set_buffer_uptodate(bh); + mark_buffer_dirty(bh); + continue; + } + if (block_end > to || block_start < from) + zero_user_segments(page, to, block_end, + block_start, from); + continue; + } + } + if (PageUptodate(page)) { + if (!buffer_uptodate(bh)) + set_buffer_uptodate(bh); + continue; + } + if (!buffer_uptodate(bh) && !buffer_delay(bh) && + !buffer_unwritten(bh) && + (block_start < from || block_end > to)) { + ll_rw_block(READ, 1, &bh); + *wait_bh++ = bh; + decrypt = ext4_encrypted_inode(inode) && + S_ISREG(inode->i_mode); + } + } + /* + * If we issued read requests, let them complete. + */ + while (wait_bh > wait) { + wait_on_buffer(*--wait_bh); + if (!buffer_uptodate(*wait_bh)) + err = -EIO; + } + if (unlikely(err)) + page_zero_new_buffers(page, from, to); + else if (decrypt) + err = ext4_decrypt(page); + return err; +} +#endif + static int ext4_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) @@ -891,6 +995,16 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping, pgoff_t index; unsigned from, to; + if (trace_android_fs_datawrite_start_enabled()) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + inode); + trace_android_fs_datawrite_start(inode, pos, len, + current->pid, path, + current->comm); + } trace_ext4_write_begin(inode, pos, len, flags); /* * Reserve one block more for addition to orphan list in case @@ -941,11 +1055,19 @@ retry_journal: /* In case writeback began while the page was unlocked */ wait_for_stable_page(page); +#ifdef CONFIG_EXT4_FS_ENCRYPTION + if (ext4_should_dioread_nolock(inode)) + ret = ext4_block_write_begin(page, pos, len, + ext4_get_block_write); + else + ret = ext4_block_write_begin(page, pos, len, + ext4_get_block); +#else if (ext4_should_dioread_nolock(inode)) ret = __block_write_begin(page, pos, len, ext4_get_block_write); else ret = __block_write_begin(page, pos, len, ext4_get_block); - +#endif if (!ret && ext4_should_journal_data(inode)) { ret = ext4_walk_page_buffers(handle, page_buffers(page), from, to, NULL, @@ -1018,16 +1140,8 @@ static int ext4_write_end(struct file *file, int ret = 0, ret2; int i_size_changed = 0; + trace_android_fs_datawrite_end(inode, pos, len); trace_ext4_write_end(inode, pos, len, copied); - if (ext4_test_inode_state(inode, EXT4_STATE_ORDERED_MODE)) { - ret = ext4_jbd2_file_inode(handle, inode); - if (ret) { - unlock_page(page); - page_cache_release(page); - goto errout; - } - } - if (ext4_has_inline_data(inode)) { ret = ext4_write_inline_data_end(inode, pos, len, copied, page); @@ -1091,6 +1205,7 @@ static int ext4_journalled_write_end(struct file *file, unsigned from, to; int size_changed = 0; + trace_android_fs_datawrite_end(inode, pos, len); trace_ext4_journalled_write_end(inode, pos, len, copied); from = pos & (PAGE_CACHE_SIZE - 1); to = from + len; @@ -1738,11 +1853,22 @@ static int ext4_writepage(struct page *page, * the page. But we may reach here when we do a journal commit via * journal_submit_inode_data_buffers() and in that case we must write * allocated buffers to achieve data=ordered mode guarantees. + * + * Also, if there is only one buffer per page (the fs block + * size == the page size), if one buffer needs block + * allocation or needs to modify the extent tree to clear the + * unwritten flag, we know that the page can't be written at + * all, so we might as well refuse the write immediately. + * Unfortunately if the block size != page size, we can't as + * easily detect this case using ext4_walk_page_buffers(), but + * for the extremely common case, this is an optimization that + * skips a useless round trip through ext4_bio_write_page(). */ if (ext4_walk_page_buffers(NULL, page_bufs, 0, len, NULL, ext4_bh_delay_or_unwritten)) { redirty_page_for_writepage(wbc, page); - if (current->flags & PF_MEMALLOC) { + if ((current->flags & PF_MEMALLOC) || + (inode->i_sb->s_blocksize == PAGE_CACHE_SIZE)) { /* * For memory cleaning there's no point in writing only * some buffers. So just bail out. Warn if we came here @@ -2574,6 +2700,16 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, len, flags, pagep, fsdata); } *fsdata = (void *)0; + if (trace_android_fs_datawrite_start_enabled()) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + inode); + trace_android_fs_datawrite_start(inode, pos, len, + current->pid, + path, current->comm); + } trace_ext4_da_write_begin(inode, pos, len, flags); if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { @@ -2624,7 +2760,12 @@ retry_journal: /* In case writeback began while the page was unlocked */ wait_for_stable_page(page); +#ifdef CONFIG_EXT4_FS_ENCRYPTION + ret = ext4_block_write_begin(page, pos, len, + ext4_da_get_block_prep); +#else ret = __block_write_begin(page, pos, len, ext4_da_get_block_prep); +#endif if (ret < 0) { unlock_page(page); ext4_journal_stop(handle); @@ -2687,6 +2828,7 @@ static int ext4_da_write_end(struct file *file, return ext4_write_end(file, mapping, pos, len, copied, page, fsdata); + trace_android_fs_datawrite_end(inode, pos, len); trace_ext4_da_write_end(inode, pos, len, copied); start = pos & (PAGE_CACHE_SIZE - 1); end = start + copied - 1; @@ -2870,7 +3012,7 @@ static int ext4_readpage(struct file *file, struct page *page) ret = ext4_readpage_inline(inode, page); if (ret == -EAGAIN) - return mpage_readpage(page, ext4_get_block); + return ext4_mpage_readpages(page->mapping, NULL, page, 1); return ret; } @@ -2885,7 +3027,7 @@ ext4_readpages(struct file *file, struct address_space *mapping, if (ext4_has_inline_data(inode)) return 0; - return mpage_readpages(mapping, pages, nr_pages, ext4_get_block); + return ext4_mpage_readpages(mapping, pages, NULL, nr_pages); } static void ext4_invalidatepage(struct page *page, unsigned int offset, @@ -3082,6 +3224,9 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb, get_block_func = ext4_get_block_write; dio_flags = DIO_LOCKING; } +#ifdef CONFIG_EXT4_FS_ENCRYPTION + BUG_ON(ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode)); +#endif ret = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iter, offset, @@ -3145,6 +3290,11 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, size_t count = iov_iter_count(iter); ssize_t ret; +#ifdef CONFIG_EXT4_FS_ENCRYPTION + if (ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode)) + return 0; +#endif + /* * If we are doing data journalling we don't support O_DIRECT */ @@ -3155,12 +3305,39 @@ static ssize_t ext4_direct_IO(int rw, struct kiocb *iocb, if (ext4_has_inline_data(inode)) return 0; + if (trace_android_fs_dataread_start_enabled() && (rw == READ)) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + inode); + trace_android_fs_dataread_start(inode, offset, count, + current->pid, path, + current->comm); + } + if (trace_android_fs_datawrite_start_enabled() && (rw == WRITE)) { + char *path, pathbuf[MAX_TRACE_PATHBUF_LEN]; + + path = android_fstrace_get_pathname(pathbuf, + MAX_TRACE_PATHBUF_LEN, + inode); + trace_android_fs_datawrite_start(inode, offset, count, + current->pid, path, + current->comm); + } + trace_ext4_direct_IO_enter(inode, offset, count, rw); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) ret = ext4_ext_direct_IO(rw, iocb, iter, offset); else ret = ext4_ind_direct_IO(rw, iocb, iter, offset); trace_ext4_direct_IO_exit(inode, offset, count, rw, ret); + + if (trace_android_fs_dataread_start_enabled() && (rw == READ)) + trace_android_fs_dataread_end(inode, offset, count); + if (trace_android_fs_datawrite_start_enabled() && (rw == WRITE)) + trace_android_fs_datawrite_end(inode, offset, count); + return ret; } @@ -3324,6 +3501,13 @@ static int ext4_block_zero_page_range(handle_t *handle, /* Uhhuh. Read error. Complain and punt. */ if (!buffer_uptodate(bh)) goto unlock; + if (S_ISREG(inode->i_mode) && + ext4_encrypted_inode(inode)) { + /* We expect the key to be set. */ + BUG_ON(!ext4_has_encryption_key(inode)); + BUG_ON(blocksize != PAGE_CACHE_SIZE); + WARN_ON_ONCE(ext4_decrypt(page)); + } } if (ext4_should_journal_data(inode)) { BUFFER_TRACE(bh, "get write access"); @@ -3363,6 +3547,11 @@ static int ext4_block_truncate_page(handle_t *handle, unsigned blocksize; struct inode *inode = mapping->host; + /* If we are processing an encrypted inode during orphan list + * handling */ + if (ext4_encrypted_inode(inode) && !ext4_has_encryption_key(inode)) + return 0; + blocksize = inode->i_sb->s_blocksize; length = blocksize - (offset & (blocksize - 1)); @@ -4130,7 +4319,8 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) inode->i_op = &ext4_dir_inode_operations; inode->i_fop = &ext4_dir_operations; } else if (S_ISLNK(inode->i_mode)) { - if (ext4_inode_is_fast_symlink(inode)) { + if (ext4_inode_is_fast_symlink(inode) && + !ext4_encrypted_inode(inode)) { inode->i_op = &ext4_fast_symlink_inode_operations; nd_terminate_link(ei->i_data, inode->i_size, sizeof(ei->i_data) - 1); |