X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fext4%2Finode.c;h=634f0bc757008d6534944b8dd9115e34a40f0778;hb=ae4d537211ff250a8c23c4f1227c4276cd2508ab;hp=2bef4f879e4b006d072b9bc8e79007a7ffb6c56b;hpb=64769240bd07f446f83660bb143bb609d8ab4910;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 2bef4f8..634f0bc 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -39,6 +39,9 @@ #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" +#include "ext4_extents.h" + +#define MPAGE_DA_EXTENT_TAIL 0x01 static inline int ext4_begin_ordered_truncate(struct inode *inode, loff_t new_size) @@ -187,9 +190,10 @@ static int ext4_journal_test_restart(handle_t *handle, struct inode *inode) /* * Called at the last iput() if i_nlink is zero. */ -void ext4_delete_inode (struct inode * inode) +void ext4_delete_inode(struct inode *inode) { handle_t *handle; + int err; if (ext4_should_order_data(inode)) ext4_begin_ordered_truncate(inode, 0); @@ -198,8 +202,9 @@ void ext4_delete_inode (struct inode * inode) if (is_bad_inode(inode)) goto no_delete; - handle = start_transaction(inode); + handle = ext4_journal_start(inode, blocks_for_truncate(inode)+3); if (IS_ERR(handle)) { + ext4_std_error(inode->i_sb, PTR_ERR(handle)); /* * If we're going to skip the normal cleanup, we still need to * make sure that the in-core orphan linked list is properly @@ -212,8 +217,34 @@ void ext4_delete_inode (struct inode * inode) if (IS_SYNC(inode)) handle->h_sync = 1; inode->i_size = 0; + err = ext4_mark_inode_dirty(handle, inode); + if (err) { + ext4_warning(inode->i_sb, __func__, + "couldn't mark inode dirty (err %d)", err); + goto stop_handle; + } if (inode->i_blocks) ext4_truncate(inode); + + /* + * ext4_ext_truncate() doesn't reserve any slop when it + * restarts journal transactions; therefore there may not be + * enough credits left in the handle to remove the inode from + * the orphan list and set the dtime field. + */ + if (handle->h_buffer_credits < 3) { + err = ext4_journal_extend(handle, 3); + if (err > 0) + err = ext4_journal_restart(handle, 3); + if (err != 0) { + ext4_warning(inode->i_sb, __func__, + "couldn't extend journal (err %d)", err); + stop_handle: + ext4_journal_stop(handle); + goto no_delete; + } + } + /* * Kill off the orphan record which ext4_truncate created. * AKPM: I think this can be inside the above `if'. @@ -299,11 +330,11 @@ static int ext4_block_to_path(struct inode *inode, int final = 0; if (i_block < 0) { - ext4_warning (inode->i_sb, "ext4_block_to_path", "block < 0"); + ext4_warning(inode->i_sb, "ext4_block_to_path", "block < 0"); } else if (i_block < direct_blocks) { offsets[n++] = i_block; final = direct_blocks; - } else if ( (i_block -= direct_blocks) < indirect_blocks) { + } else if ((i_block -= direct_blocks) < indirect_blocks) { offsets[n++] = EXT4_IND_BLOCK; offsets[n++] = i_block; final = ptrs; @@ -369,14 +400,14 @@ static Indirect *ext4_get_branch(struct inode *inode, int depth, *err = 0; /* i_data is not going away, no lock needed */ - add_chain (chain, NULL, EXT4_I(inode)->i_data + *offsets); + add_chain(chain, NULL, EXT4_I(inode)->i_data + *offsets); if (!p->key) goto no_block; while (--depth) { bh = sb_bread(sb, le32_to_cpu(p->key)); if (!bh) goto failure; - add_chain(++p, bh, (__le32*)bh->b_data + *++offsets); + add_chain(++p, bh, (__le32 *)bh->b_data + *++offsets); /* Reader: end */ if (!p->key) goto no_block; @@ -412,7 +443,7 @@ no_block: static ext4_fsblk_t ext4_find_near(struct inode *inode, Indirect *ind) { struct ext4_inode_info *ei = EXT4_I(inode); - __le32 *start = ind->bh ? (__le32*) ind->bh->b_data : ei->i_data; + __le32 *start = ind->bh ? (__le32 *) ind->bh->b_data : ei->i_data; __le32 *p; ext4_fsblk_t bg_start; ext4_fsblk_t last_block; @@ -599,7 +630,7 @@ allocated: *err = 0; return ret; failed_out: - for (i = 0; i b_data + offsets[n]; branch[n].key = cpu_to_le32(new_blocks[n]); *branch[n].p = branch[n].key; - if ( n == indirect_blks) { + if (n == indirect_blks) { current_block = new_blocks[n]; /* * End of chain, update the last new metablock of @@ -699,7 +730,7 @@ failed: BUFFER_TRACE(branch[i].bh, "call jbd2_journal_forget"); ext4_journal_forget(handle, branch[i].bh); } - for (i = 0; i 1) { current_block = le32_to_cpu(where->key) + 1; for (i = 1; i < blks; i++) - *(where->p + i ) = cpu_to_le32(current_block++); + *(where->p + i) = cpu_to_le32(current_block++); } /* @@ -846,6 +877,7 @@ int ext4_get_blocks_handle(handle_t *handle, struct inode *inode, struct ext4_inode_info *ei = EXT4_I(inode); int count = 0; ext4_fsblk_t first_block = 0; + loff_t disksize; J_ASSERT(!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)); @@ -921,8 +953,13 @@ int ext4_get_blocks_handle(handle_t *handle, struct inode *inode, * protect it if you're about to implement concurrent * ext4_get_block() -bzzz */ - if (!err && extend_disksize && inode->i_size > ei->i_disksize) - ei->i_disksize = inode->i_size; + if (!err && extend_disksize) { + disksize = ((loff_t) iblock + count) << inode->i_blkbits; + if (disksize > i_size_read(inode)) + disksize = i_size_read(inode); + if (disksize > ei->i_disksize) + ei->i_disksize = disksize; + } if (err) goto cleanup; @@ -945,23 +982,75 @@ out: return err; } -/* Maximum number of blocks we map for direct IO at once. */ -#define DIO_MAX_BLOCKS 4096 /* - * Number of credits we need for writing DIO_MAX_BLOCKS: - * We need sb + group descriptor + bitmap + inode -> 4 - * For B blocks with A block pointers per block we need: - * 1 (triple ind.) + (B/A/A + 2) (doubly ind.) + (B/A + 2) (indirect). - * If we plug in 4096 for B and 256 for A (for 1KB block size), we get 25. + * Calculate the number of metadata blocks need to reserve + * to allocate @blocks for non extent file based file */ -#define DIO_CREDITS 25 +static int ext4_indirect_calc_metadata_amount(struct inode *inode, int blocks) +{ + int icap = EXT4_ADDR_PER_BLOCK(inode->i_sb); + int ind_blks, dind_blks, tind_blks; + + /* number of new indirect blocks needed */ + ind_blks = (blocks + icap - 1) / icap; + + dind_blks = (ind_blks + icap - 1) / icap; + tind_blks = 1; + + return ind_blks + dind_blks + tind_blks; +} /* + * Calculate the number of metadata blocks need to reserve + * to allocate given number of blocks + */ +static int ext4_calc_metadata_amount(struct inode *inode, int blocks) +{ + if (!blocks) + return 0; + + if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) + return ext4_ext_calc_metadata_amount(inode, blocks); + + return ext4_indirect_calc_metadata_amount(inode, blocks); +} + +static void ext4_da_update_reserve_space(struct inode *inode, int used) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + int total, mdb, mdb_free; + + spin_lock(&EXT4_I(inode)->i_block_reservation_lock); + /* recalculate the number of metablocks still need to be reserved */ + total = EXT4_I(inode)->i_reserved_data_blocks - used; + mdb = ext4_calc_metadata_amount(inode, total); + + /* figure out how many metablocks to release */ + BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks); + mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb; + + if (mdb_free) { + /* Account for allocated meta_blocks */ + mdb_free -= EXT4_I(inode)->i_allocated_meta_blocks; + + /* update fs dirty blocks counter */ + percpu_counter_sub(&sbi->s_dirtyblocks_counter, mdb_free); + EXT4_I(inode)->i_allocated_meta_blocks = 0; + EXT4_I(inode)->i_reserved_meta_blocks = mdb; + } + + /* update per-inode reservations */ + BUG_ON(used > EXT4_I(inode)->i_reserved_data_blocks); + EXT4_I(inode)->i_reserved_data_blocks -= used; + + spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); +} + +/* + * The ext4_get_blocks_wrap() function try to look up the requested blocks, + * and returns if the blocks are already mapped. * - * - * ext4_ext4 get_block() wrapper function - * It will do a look up first, and returns if the blocks already mapped. * Otherwise it takes the write lock of the i_data_sem and allocate blocks * and store the allocated blocks in the result buffer head and mark it * mapped. @@ -982,7 +1071,7 @@ out: */ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, unsigned long max_blocks, struct buffer_head *bh, - int create, int extend_disksize) + int create, int extend_disksize, int flag) { int retval; @@ -1023,6 +1112,15 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, * with create == 1 flag. */ down_write((&EXT4_I(inode)->i_data_sem)); + + /* + * if the caller is from delayed allocation writeout path + * we have already reserved fs blocks for allocation + * let the underlying get_block() function know to + * avoid double accounting + */ + if (flag) + EXT4_I(inode)->i_delalloc_reserved_flag = 1; /* * We need to check for EXT4 here because migrate * could have changed the inode type in between @@ -1044,23 +1142,39 @@ int ext4_get_blocks_wrap(handle_t *handle, struct inode *inode, sector_t block, ~EXT4_EXT_MIGRATE; } } + + if (flag) { + EXT4_I(inode)->i_delalloc_reserved_flag = 0; + /* + * Update reserved blocks/metadata blocks + * after successful block allocation + * which were deferred till now + */ + if ((retval > 0) && buffer_delay(bh)) + ext4_da_update_reserve_space(inode, retval); + } + up_write((&EXT4_I(inode)->i_data_sem)); return retval; } +/* Maximum number of blocks we map for direct IO at once. */ +#define DIO_MAX_BLOCKS 4096 + static int ext4_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { handle_t *handle = ext4_journal_current_handle(); int ret = 0, started = 0; unsigned max_blocks = bh_result->b_size >> inode->i_blkbits; + int dio_credits; if (create && !handle) { /* Direct IO write... */ if (max_blocks > DIO_MAX_BLOCKS) max_blocks = DIO_MAX_BLOCKS; - handle = ext4_journal_start(inode, DIO_CREDITS + - 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb)); + dio_credits = ext4_chunk_trans_blocks(inode, max_blocks); + handle = ext4_journal_start(inode, dio_credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto out; @@ -1069,7 +1183,7 @@ static int ext4_get_block(struct inode *inode, sector_t iblock, } ret = ext4_get_blocks_wrap(handle, inode, iblock, - max_blocks, bh_result, create, 0); + max_blocks, bh_result, create, 0, 0); if (ret > 0) { bh_result->b_size = (ret << inode->i_blkbits); ret = 0; @@ -1095,7 +1209,7 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, dummy.b_blocknr = -1000; buffer_trace_init(&dummy.b_history); err = ext4_get_blocks_wrap(handle, inode, block, 1, - &dummy, create, 1); + &dummy, create, 1, 0); /* * ext4_get_blocks_handle() returns number of blocks * mapped. 0 in case of a HOLE. @@ -1128,7 +1242,7 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, BUFFER_TRACE(bh, "call get_create_access"); fatal = ext4_journal_get_create_access(handle, bh); if (!fatal && !buffer_uptodate(bh)) { - memset(bh->b_data,0,inode->i_sb->s_blocksize); + memset(bh->b_data, 0, inode->i_sb->s_blocksize); set_buffer_uptodate(bh); } unlock_buffer(bh); @@ -1153,7 +1267,7 @@ err: struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode, ext4_lblk_t block, int create, int *err) { - struct buffer_head * bh; + struct buffer_head *bh; bh = ext4_getblk(handle, inode, block, create, err); if (!bh) @@ -1169,13 +1283,13 @@ struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode, return NULL; } -static int walk_page_buffers( handle_t *handle, - struct buffer_head *head, - unsigned from, - unsigned to, - int *partial, - int (*fn)( handle_t *handle, - struct buffer_head *bh)) +static int walk_page_buffers(handle_t *handle, + struct buffer_head *head, + unsigned from, + unsigned to, + int *partial, + int (*fn)(handle_t *handle, + struct buffer_head *bh)) { struct buffer_head *bh; unsigned block_start, block_end; @@ -1183,9 +1297,9 @@ static int walk_page_buffers( handle_t *handle, int err, ret = 0; struct buffer_head *next; - for ( bh = head, block_start = 0; - ret == 0 && (bh != head || !block_start); - block_start = block_end, bh = next) + for (bh = head, block_start = 0; + ret == 0 && (bh != head || !block_start); + block_start = block_end, bh = next) { next = bh->b_this_page; block_end = block_start + blocksize; @@ -1238,23 +1352,23 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { - struct inode *inode = mapping->host; + struct inode *inode = mapping->host; int ret, needed_blocks = ext4_writepage_trans_blocks(inode); handle_t *handle; int retries = 0; - struct page *page; + struct page *page; pgoff_t index; - unsigned from, to; + unsigned from, to; index = pos >> PAGE_CACHE_SHIFT; - from = pos & (PAGE_CACHE_SIZE - 1); - to = from + len; + from = pos & (PAGE_CACHE_SIZE - 1); + to = from + len; retry: - handle = ext4_journal_start(inode, needed_blocks); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - goto out; + handle = ext4_journal_start(inode, needed_blocks); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + goto out; } page = __grab_cache_page(mapping, index); @@ -1274,9 +1388,16 @@ retry: } if (ret) { - unlock_page(page); + unlock_page(page); ext4_journal_stop(handle); - page_cache_release(page); + page_cache_release(page); + /* + * block_write_begin may have instantiated a few blocks + * outside i_size. Trim these off again. Don't need + * i_size_read because we hold i_mutex. + */ + if (pos + len > inode->i_size) + vmtruncate(inode, inode->i_size); } if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) @@ -1308,12 +1429,8 @@ static int ext4_ordered_write_end(struct file *file, { handle_t *handle = ext4_journal_current_handle(); struct inode *inode = mapping->host; - unsigned from, to; int ret = 0, ret2; - from = pos & (PAGE_CACHE_SIZE - 1); - to = from + len; - ret = ext4_jbd2_file_inode(handle, inode); if (ret == 0) { @@ -1410,6 +1527,108 @@ static int ext4_journalled_write_end(struct file *file, return ret ? ret : copied; } +static int ext4_da_reserve_space(struct inode *inode, int nrblocks) +{ + int retries = 0; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + unsigned long md_needed, mdblocks, total = 0; + + /* + * recalculate the amount of metadata blocks to reserve + * in order to allocate nrblocks + * worse case is one extent per block + */ +repeat: + spin_lock(&EXT4_I(inode)->i_block_reservation_lock); + total = EXT4_I(inode)->i_reserved_data_blocks + nrblocks; + mdblocks = ext4_calc_metadata_amount(inode, total); + BUG_ON(mdblocks < EXT4_I(inode)->i_reserved_meta_blocks); + + md_needed = mdblocks - EXT4_I(inode)->i_reserved_meta_blocks; + total = md_needed + nrblocks; + + if (ext4_claim_free_blocks(sbi, total)) { + spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); + if (ext4_should_retry_alloc(inode->i_sb, &retries)) { + yield(); + goto repeat; + } + return -ENOSPC; + } + EXT4_I(inode)->i_reserved_data_blocks += nrblocks; + EXT4_I(inode)->i_reserved_meta_blocks = mdblocks; + + spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); + return 0; /* success */ +} + +static void ext4_da_release_space(struct inode *inode, int to_free) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + int total, mdb, mdb_free, release; + + if (!to_free) + return; /* Nothing to release, exit */ + + spin_lock(&EXT4_I(inode)->i_block_reservation_lock); + + if (!EXT4_I(inode)->i_reserved_data_blocks) { + /* + * if there is no reserved blocks, but we try to free some + * then the counter is messed up somewhere. + * but since this function is called from invalidate + * page, it's harmless to return without any action + */ + printk(KERN_INFO "ext4 delalloc try to release %d reserved " + "blocks for inode %lu, but there is no reserved " + "data blocks\n", to_free, inode->i_ino); + spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); + return; + } + + /* recalculate the number of metablocks still need to be reserved */ + total = EXT4_I(inode)->i_reserved_data_blocks - to_free; + mdb = ext4_calc_metadata_amount(inode, total); + + /* figure out how many metablocks to release */ + BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks); + mdb_free = EXT4_I(inode)->i_reserved_meta_blocks - mdb; + + release = to_free + mdb_free; + + /* update fs dirty blocks counter for truncate case */ + percpu_counter_sub(&sbi->s_dirtyblocks_counter, release); + + /* update per-inode reservations */ + BUG_ON(to_free > EXT4_I(inode)->i_reserved_data_blocks); + EXT4_I(inode)->i_reserved_data_blocks -= to_free; + + BUG_ON(mdb > EXT4_I(inode)->i_reserved_meta_blocks); + EXT4_I(inode)->i_reserved_meta_blocks = mdb; + spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); +} + +static void ext4_da_page_release_reservation(struct page *page, + unsigned long offset) +{ + int to_release = 0; + struct buffer_head *head, *bh; + unsigned int curr_off = 0; + + head = page_buffers(page); + bh = head; + do { + unsigned int next_off = curr_off + bh->b_size; + + if ((offset <= curr_off) && (buffer_delay(bh))) { + to_release++; + clear_buffer_delay(bh); + } + curr_off = next_off; + } while ((bh = bh->b_this_page) != head); + ext4_da_release_space(page->mapping->host, to_release); +} + /* * Delayed allocation stuff */ @@ -1420,11 +1639,14 @@ struct mpage_da_data { unsigned long first_page, next_page; /* extent of pages */ get_block_t *get_block; struct writeback_control *wbc; + int io_done; + long pages_written; + int retval; }; /* * mpage_da_submit_io - walks through extent of pages and try to write - * them with __mpage_writepage() + * them with writepage() call back * * @mpd->inode: inode * @mpd->first_page: first page of the extent @@ -1439,18 +1661,11 @@ struct mpage_da_data { static int mpage_da_submit_io(struct mpage_da_data *mpd) { struct address_space *mapping = mpd->inode->i_mapping; - struct mpage_data mpd_pp = { - .bio = NULL, - .last_block_in_bio = 0, - .get_block = mpd->get_block, - .use_writepage = 1, - }; int ret = 0, err, nr_pages, i; unsigned long index, end; struct pagevec pvec; BUG_ON(mpd->next_page <= mpd->first_page); - pagevec_init(&pvec, 0); index = mpd->first_page; end = mpd->next_page - 1; @@ -1468,8 +1683,9 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd) break; index++; - err = __mpage_writepage(page, mpd->wbc, &mpd_pp); - + err = mapping->a_ops->writepage(page, mpd->wbc); + if (!err) + mpd->pages_written++; /* * In error case, we have to continue because * remaining pages are still locked @@ -1480,9 +1696,6 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd) } pagevec_release(&pvec); } - if (mpd_pp.bio) - mpage_bio_submit(WRITE, mpd_pp.bio); - return ret; } @@ -1505,7 +1718,7 @@ static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical, int blocks = exbh->b_size >> inode->i_blkbits; sector_t pblock = exbh->b_blocknr, cur_logical; struct buffer_head *head, *bh; - unsigned long index, end; + pgoff_t index, end; struct pagevec pvec; int nr_pages, i; @@ -1545,13 +1758,18 @@ static void mpage_put_bnr_to_bhs(struct mpage_da_data *mpd, sector_t logical, do { if (cur_logical >= logical + blocks) break; - if (buffer_delay(bh)) { bh->b_blocknr = pblock; clear_buffer_delay(bh); - } else if (buffer_mapped(bh)) { + bh->b_bdev = inode->i_sb->s_bdev; + } else if (buffer_unwritten(bh)) { + bh->b_blocknr = pblock; + clear_buffer_unwritten(bh); + set_buffer_mapped(bh); + set_buffer_new(bh); + bh->b_bdev = inode->i_sb->s_bdev; + } else if (buffer_mapped(bh)) BUG_ON(bh->b_blocknr != pblock); - } cur_logical++; pblock++; @@ -1577,6 +1795,57 @@ static inline void __unmap_underlying_blocks(struct inode *inode, unmap_underlying_metadata(bdev, bh->b_blocknr + i); } +static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd, + sector_t logical, long blk_cnt) +{ + int nr_pages, i; + pgoff_t index, end; + struct pagevec pvec; + struct inode *inode = mpd->inode; + struct address_space *mapping = inode->i_mapping; + + index = logical >> (PAGE_CACHE_SHIFT - inode->i_blkbits); + end = (logical + blk_cnt - 1) >> + (PAGE_CACHE_SHIFT - inode->i_blkbits); + while (index <= end) { + nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE); + if (nr_pages == 0) + break; + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + index = page->index; + if (index > end) + break; + index++; + + BUG_ON(!PageLocked(page)); + BUG_ON(PageWriteback(page)); + block_invalidatepage(page, 0); + ClearPageUptodate(page); + unlock_page(page); + } + } + return; +} + +static void ext4_print_free_blocks(struct inode *inode) +{ + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + printk(KERN_EMERG "Total free blocks count %lld\n", + ext4_count_free_blocks(inode->i_sb)); + printk(KERN_EMERG "Free/Dirty block details\n"); + printk(KERN_EMERG "free_blocks=%lld\n", + percpu_counter_sum(&sbi->s_freeblocks_counter)); + printk(KERN_EMERG "dirty_blocks=%lld\n", + percpu_counter_sum(&sbi->s_dirtyblocks_counter)); + printk(KERN_EMERG "Block reservation details\n"); + printk(KERN_EMERG "i_reserved_data_blocks=%lu\n", + EXT4_I(inode)->i_reserved_data_blocks); + printk(KERN_EMERG "i_reserved_meta_blocks=%lu\n", + EXT4_I(inode)->i_reserved_meta_blocks); + return; +} + /* * mpage_da_map_blocks - go through given space * @@ -1585,54 +1854,87 @@ static inline void __unmap_underlying_blocks(struct inode *inode, * * The function skips space we know is already mapped to disk blocks. * - * The function ignores errors ->get_block() returns, thus real - * error handling is postponed to __mpage_writepage() */ -static void mpage_da_map_blocks(struct mpage_da_data *mpd) +static int mpage_da_map_blocks(struct mpage_da_data *mpd) { - struct buffer_head *lbh = &mpd->lbh; - int err = 0, remain = lbh->b_size; - sector_t next = lbh->b_blocknr; + int err = 0; struct buffer_head new; + struct buffer_head *lbh = &mpd->lbh; + sector_t next; /* * We consider only non-mapped and non-allocated blocks */ if (buffer_mapped(lbh) && !buffer_delay(lbh)) - return; + return 0; + new.b_state = lbh->b_state; + new.b_blocknr = 0; + new.b_size = lbh->b_size; + next = lbh->b_blocknr; + /* + * If we didn't accumulate anything + * to write simply return + */ + if (!new.b_size) + return 0; + err = mpd->get_block(mpd->inode, next, &new, 1); + if (err) { - while (remain) { - new.b_state = lbh->b_state; - new.b_blocknr = 0; - new.b_size = remain; - err = mpd->get_block(mpd->inode, next, &new, 1); - if (err) { - /* - * Rather than implement own error handling - * here, we just leave remaining blocks - * unallocated and try again with ->writepage() - */ - break; - } - BUG_ON(new.b_size == 0); + /* If get block returns with error + * we simply return. Later writepage + * will redirty the page and writepages + * will find the dirty page again + */ + if (err == -EAGAIN) + return 0; - if (buffer_new(&new)) - __unmap_underlying_blocks(mpd->inode, &new); + if (err == -ENOSPC && + ext4_count_free_blocks(mpd->inode->i_sb)) { + mpd->retval = err; + return 0; + } /* - * If blocks are delayed marked, we need to - * put actual blocknr and drop delayed bit + * get block failure will cause us + * to loop in writepages. Because + * a_ops->writepage won't be able to + * make progress. The page will be redirtied + * by writepage and writepages will again + * try to write the same. */ - if (buffer_delay(lbh)) - mpage_put_bnr_to_bhs(mpd, next, &new); - - /* go for the remaining blocks */ - next += new.b_size >> mpd->inode->i_blkbits; - remain -= new.b_size; + printk(KERN_EMERG "%s block allocation failed for inode %lu " + "at logical offset %llu with max blocks " + "%zd with error %d\n", + __func__, mpd->inode->i_ino, + (unsigned long long)next, + lbh->b_size >> mpd->inode->i_blkbits, err); + printk(KERN_EMERG "This should not happen.!! " + "Data will be lost\n"); + if (err == -ENOSPC) { + ext4_print_free_blocks(mpd->inode); } + /* invlaidate all the pages */ + ext4_da_block_invalidatepages(mpd, next, + lbh->b_size >> mpd->inode->i_blkbits); + return err; + } + BUG_ON(new.b_size == 0); + + if (buffer_new(&new)) + __unmap_underlying_blocks(mpd->inode, &new); + + /* + * If blocks are delayed marked, we need to + * put actual blocknr and drop delayed bit + */ + if (buffer_delay(lbh) || buffer_unwritten(lbh)) + mpage_put_bnr_to_bhs(mpd, next, &new); + + return 0; } -#define BH_FLAGS ((1 << BH_Uptodate) | (1 << BH_Mapped) | (1 << BH_Delay)) +#define BH_FLAGS ((1 << BH_Uptodate) | (1 << BH_Mapped) | \ + (1 << BH_Delay) | (1 << BH_Unwritten)) /* * mpage_add_bh_to_extent - try to add one more block to extent of blocks @@ -1646,41 +1948,61 @@ static void mpage_da_map_blocks(struct mpage_da_data *mpd) static void mpage_add_bh_to_extent(struct mpage_da_data *mpd, sector_t logical, struct buffer_head *bh) { - struct buffer_head *lbh = &mpd->lbh; sector_t next; + size_t b_size = bh->b_size; + struct buffer_head *lbh = &mpd->lbh; + int nrblocks = lbh->b_size >> mpd->inode->i_blkbits; - next = lbh->b_blocknr + (lbh->b_size >> mpd->inode->i_blkbits); - + /* check if thereserved journal credits might overflow */ + if (!(EXT4_I(mpd->inode)->i_flags & EXT4_EXTENTS_FL)) { + if (nrblocks >= EXT4_MAX_TRANS_DATA) { + /* + * With non-extent format we are limited by the journal + * credit available. Total credit needed to insert + * nrblocks contiguous blocks is dependent on the + * nrblocks. So limit nrblocks. + */ + goto flush_it; + } else if ((nrblocks + (b_size >> mpd->inode->i_blkbits)) > + EXT4_MAX_TRANS_DATA) { + /* + * Adding the new buffer_head would make it cross the + * allowed limit for which we have journal credit + * reserved. So limit the new bh->b_size + */ + b_size = (EXT4_MAX_TRANS_DATA - nrblocks) << + mpd->inode->i_blkbits; + /* we will do mpage_da_submit_io in the next loop */ + } + } /* * First block in the extent */ if (lbh->b_size == 0) { lbh->b_blocknr = logical; - lbh->b_size = bh->b_size; + lbh->b_size = b_size; lbh->b_state = bh->b_state & BH_FLAGS; return; } + next = lbh->b_blocknr + nrblocks; /* * Can we merge the block to our big extent? */ if (logical == next && (bh->b_state & BH_FLAGS) == lbh->b_state) { - lbh->b_size += bh->b_size; + lbh->b_size += b_size; return; } +flush_it: /* * We couldn't merge the block to our extent, so we * need to flush current extent and start new one */ - mpage_da_map_blocks(mpd); - - /* - * Now start a new extent - */ - lbh->b_size = bh->b_size; - lbh->b_state = bh->b_state & BH_FLAGS; - lbh->b_blocknr = logical; + if (mpage_da_map_blocks(mpd) == 0) + mpage_da_submit_io(mpd); + mpd->io_done = 1; + return; } /* @@ -1700,17 +2022,35 @@ static int __mpage_da_writepage(struct page *page, struct buffer_head *bh, *head, fake; sector_t logical; + if (mpd->io_done) { + /* + * Rest of the page in the page_vec + * redirty then and skip then. We will + * try to to write them again after + * starting a new transaction + */ + redirty_page_for_writepage(wbc, page); + unlock_page(page); + return MPAGE_DA_EXTENT_TAIL; + } /* * Can we merge this page to current extent? */ if (mpd->next_page != page->index) { /* * Nope, we can't. So, we map non-allocated blocks - * and start IO on them using __mpage_writepage() + * and start IO on them using writepage() */ if (mpd->next_page != mpd->first_page) { - mpage_da_map_blocks(mpd); - mpage_da_submit_io(mpd); + if (mpage_da_map_blocks(mpd) == 0) + mpage_da_submit_io(mpd); + /* + * skip rest of the page in the page_vec + */ + mpd->io_done = 1; + redirty_page_for_writepage(wbc, page); + unlock_page(page); + return MPAGE_DA_EXTENT_TAIL; } /* @@ -1741,6 +2081,8 @@ static int __mpage_da_writepage(struct page *page, set_buffer_dirty(bh); set_buffer_uptodate(bh); mpage_add_bh_to_extent(mpd, logical, bh); + if (mpd->io_done) + return MPAGE_DA_EXTENT_TAIL; } else { /* * Page with regular buffer heads, just add all dirty ones @@ -1749,8 +2091,12 @@ static int __mpage_da_writepage(struct page *page, bh = head; do { BUG_ON(buffer_locked(bh)); - if (buffer_dirty(bh)) + if (buffer_dirty(bh) && + (!buffer_mapped(bh) || buffer_delay(bh))) { mpage_add_bh_to_extent(mpd, logical, bh); + if (mpd->io_done) + return MPAGE_DA_EXTENT_TAIL; + } logical++; } while ((bh = bh->b_this_page) != head); } @@ -1769,46 +2115,39 @@ static int __mpage_da_writepage(struct page *page, * * This is a library function, which implements the writepages() * address_space_operation. - * - * In order to avoid duplication of logic that deals with partial pages, - * multiple bio per page, etc, we find non-allocated blocks, allocate - * them with minimal calls to ->get_block() and re-use __mpage_writepage() - * - * It's important that we call __mpage_writepage() only once for each - * involved page, otherwise we'd have to implement more complicated logic - * to deal with pages w/o PG_lock or w/ PG_writeback and so on. - * - * See comments to mpage_writepages() */ static int mpage_da_writepages(struct address_space *mapping, struct writeback_control *wbc, - get_block_t get_block) + struct mpage_da_data *mpd) { - struct mpage_da_data mpd; + long to_write; int ret; - if (!get_block) + if (!mpd->get_block) return generic_writepages(mapping, wbc); - mpd.wbc = wbc; - mpd.inode = mapping->host; - mpd.lbh.b_size = 0; - mpd.lbh.b_state = 0; - mpd.lbh.b_blocknr = 0; - mpd.first_page = 0; - mpd.next_page = 0; - mpd.get_block = get_block; + mpd->lbh.b_size = 0; + mpd->lbh.b_state = 0; + mpd->lbh.b_blocknr = 0; + mpd->first_page = 0; + mpd->next_page = 0; + mpd->io_done = 0; + mpd->pages_written = 0; + mpd->retval = 0; + + to_write = wbc->nr_to_write; - ret = write_cache_pages(mapping, wbc, __mpage_da_writepage, &mpd); + ret = write_cache_pages(mapping, wbc, __mpage_da_writepage, mpd); /* * Handle last extent of pages */ - if (mpd.next_page != mpd.first_page) { - mpage_da_map_blocks(&mpd); - mpage_da_submit_io(&mpd); + if (!mpd->io_done && mpd->next_page != mpd->first_page) { + if (mpage_da_map_blocks(mpd) == 0) + mpage_da_submit_io(mpd); } + wbc->nr_to_write = to_write - mpd->pages_written; return ret; } @@ -1829,14 +2168,18 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, * preallocated blocks are unmapped but should treated * the same as allocated blocks. */ - ret = ext4_get_blocks_wrap(NULL, inode, iblock, 1, bh_result, 0, 0); - if (ret == 0) { - /* the block isn't allocated yet, let's reserve space */ - /* XXX: call reservation here */ + ret = ext4_get_blocks_wrap(NULL, inode, iblock, 1, bh_result, 0, 0, 0); + if ((ret == 0) && !buffer_delay(bh_result)) { + /* the block isn't (pre)allocated yet, let's reserve space */ /* * XXX: __block_prepare_write() unmaps passed block, * is it OK? */ + ret = ext4_da_reserve_space(inode, 1); + if (ret) + /* not enough space to reserve */ + return ret; + map_bh(bh_result, inode->i_sb, 0); set_buffer_new(bh_result); set_buffer_delay(bh_result); @@ -1847,28 +2190,34 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, return ret; } - +#define EXT4_DELALLOC_RSVED 1 static int ext4_da_get_block_write(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { - int ret, needed_blocks = ext4_writepage_trans_blocks(inode); + int ret; unsigned max_blocks = bh_result->b_size >> inode->i_blkbits; loff_t disksize = EXT4_I(inode)->i_disksize; handle_t *handle = NULL; - if (create) { - handle = ext4_journal_start(inode, needed_blocks); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - goto out; - } - } - + handle = ext4_journal_current_handle(); + BUG_ON(!handle); ret = ext4_get_blocks_wrap(handle, inode, iblock, max_blocks, - bh_result, create, 0); + bh_result, create, 0, EXT4_DELALLOC_RSVED); if (ret > 0) { + bh_result->b_size = (ret << inode->i_blkbits); + if (ext4_should_order_data(inode)) { + int retval; + retval = ext4_jbd2_file_inode(handle, inode); + if (retval) + /* + * Failed to add inode for ordered + * mode. Don't update file size + */ + return retval; + } + /* * Update on-disk size along with block allocation * we don't use 'extend_disksize' as size may change @@ -1887,72 +2236,294 @@ static int ext4_da_get_block_write(struct inode *inode, sector_t iblock, up_write(&EXT4_I(inode)->i_data_sem); if (EXT4_I(inode)->i_disksize == disksize) { - if (handle == NULL) - handle = ext4_journal_start(inode, 1); - if (!IS_ERR(handle)) - ext4_mark_inode_dirty(handle, inode); + ret = ext4_mark_inode_dirty(handle, inode); + return ret; } } - ret = 0; } + return ret; +} -out: - if (handle && !IS_ERR(handle)) - ext4_journal_stop(handle); +static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh) +{ + /* + * unmapped buffer is possible for holes. + * delay buffer is possible with delayed allocation + */ + return ((!buffer_mapped(bh) || buffer_delay(bh)) && buffer_dirty(bh)); +} + +static int ext4_normal_get_block_write(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + int ret = 0; + unsigned max_blocks = bh_result->b_size >> inode->i_blkbits; + /* + * we don't want to do block allocation in writepage + * so call get_block_wrap with create = 0 + */ + ret = ext4_get_blocks_wrap(NULL, inode, iblock, max_blocks, + bh_result, 0, 0, 0); + if (ret > 0) { + bh_result->b_size = (ret << inode->i_blkbits); + ret = 0; + } return ret; } -/* FIXME!! only support data=writeback mode */ + +/* + * get called vi ext4_da_writepages after taking page lock (have journal handle) + * get called via journal_submit_inode_data_buffers (no journal handle) + * get called via shrink_page_list via pdflush (no journal handle) + * or grab_page_cache when doing write_begin (have journal handle) + */ static int ext4_da_writepage(struct page *page, struct writeback_control *wbc) { - struct inode *inode = page->mapping->host; - handle_t *handle = NULL; int ret = 0; - int err; + loff_t size; + unsigned long len; + struct buffer_head *page_bufs; + struct inode *inode = page->mapping->host; - if (ext4_journal_current_handle()) - goto out_fail; + size = i_size_read(inode); + if (page->index == size >> PAGE_CACHE_SHIFT) + len = size & ~PAGE_CACHE_MASK; + else + len = PAGE_CACHE_SIZE; - handle = ext4_journal_start(inode, ext4_writepage_trans_blocks(inode)); - if (IS_ERR(handle)) { - ret = PTR_ERR(handle); - goto out_fail; + if (page_has_buffers(page)) { + page_bufs = page_buffers(page); + if (walk_page_buffers(NULL, page_bufs, 0, len, NULL, + ext4_bh_unmapped_or_delay)) { + /* + * We don't want to do block allocation + * So redirty the page and return + * We may reach here when we do a journal commit + * via journal_submit_inode_data_buffers. + * If we don't have mapping block we just ignore + * them. We can also reach here via shrink_page_list + */ + redirty_page_for_writepage(wbc, page); + unlock_page(page); + return 0; + } + } else { + /* + * The test for page_has_buffers() is subtle: + * We know the page is dirty but it lost buffers. That means + * that at some moment in time after write_begin()/write_end() + * has been called all buffers have been clean and thus they + * must have been written at least once. So they are all + * mapped and we can happily proceed with mapping them + * and writing the page. + * + * Try to initialize the buffer_heads and check whether + * all are mapped and non delay. We don't want to + * do block allocation here. + */ + ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE, + ext4_normal_get_block_write); + if (!ret) { + page_bufs = page_buffers(page); + /* check whether all are mapped and non delay */ + if (walk_page_buffers(NULL, page_bufs, 0, len, NULL, + ext4_bh_unmapped_or_delay)) { + redirty_page_for_writepage(wbc, page); + unlock_page(page); + return 0; + } + } else { + /* + * We can't do block allocation here + * so just redity the page and unlock + * and return + */ + redirty_page_for_writepage(wbc, page); + unlock_page(page); + return 0; + } } if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode)) - ret = nobh_writepage(page, ext4_get_block, wbc); + ret = nobh_writepage(page, ext4_normal_get_block_write, wbc); else - ret = block_write_full_page(page, ext4_get_block, wbc); + ret = block_write_full_page(page, + ext4_normal_get_block_write, + wbc); - if (!ret && inode->i_size > EXT4_I(inode)->i_disksize) { - EXT4_I(inode)->i_disksize = inode->i_size; - ext4_mark_inode_dirty(handle, inode); + return ret; +} + +/* + * This is called via ext4_da_writepages() to + * calulate the total number of credits to reserve to fit + * a single extent allocation into a single transaction, + * ext4_da_writpeages() will loop calling this before + * the block allocation. + */ + +static int ext4_da_writepages_trans_blocks(struct inode *inode) +{ + int max_blocks = EXT4_I(inode)->i_reserved_data_blocks; + + /* + * With non-extent format the journal credit needed to + * insert nrblocks contiguous block is dependent on + * number of contiguous block. So we will limit + * number of contiguous block to a sane value + */ + if (!(inode->i_flags & EXT4_EXTENTS_FL) && + (max_blocks > EXT4_MAX_TRANS_DATA)) + max_blocks = EXT4_MAX_TRANS_DATA; + + return ext4_chunk_trans_blocks(inode, max_blocks); +} + +static int ext4_da_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + handle_t *handle = NULL; + loff_t range_start = 0; + struct mpage_da_data mpd; + struct inode *inode = mapping->host; + int needed_blocks, ret = 0, nr_to_writebump = 0; + long to_write, pages_skipped = 0; + struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb); + + /* + * No pages to write? This is mainly a kludge to avoid starting + * a transaction for special inodes like journal inode on last iput() + * because that could violate lock ordering on umount + */ + if (!mapping->nrpages || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) + return 0; + /* + * Make sure nr_to_write is >= sbi->s_mb_stream_request + * This make sure small files blocks are allocated in + * single attempt. This ensure that small files + * get less fragmented. + */ + if (wbc->nr_to_write < sbi->s_mb_stream_request) { + nr_to_writebump = sbi->s_mb_stream_request - wbc->nr_to_write; + wbc->nr_to_write = sbi->s_mb_stream_request; } - err = ext4_journal_stop(handle); - if (!ret) - ret = err; - return ret; + if (!wbc->range_cyclic) + /* + * If range_cyclic is not set force range_cont + * and save the old writeback_index + */ + wbc->range_cont = 1; -out_fail: - redirty_page_for_writepage(wbc, page); - unlock_page(page); + range_start = wbc->range_start; + pages_skipped = wbc->pages_skipped; + + mpd.wbc = wbc; + mpd.inode = mapping->host; + +restart_loop: + to_write = wbc->nr_to_write; + while (!ret && to_write > 0) { + + /* + * we insert one extent at a time. So we need + * credit needed for single extent allocation. + * journalled mode is currently not supported + * by delalloc + */ + BUG_ON(ext4_should_journal_data(inode)); + needed_blocks = ext4_da_writepages_trans_blocks(inode); + + /* start a new transaction*/ + handle = ext4_journal_start(inode, needed_blocks); + if (IS_ERR(handle)) { + ret = PTR_ERR(handle); + printk(KERN_EMERG "%s: jbd2_start: " + "%ld pages, ino %lu; err %d\n", __func__, + wbc->nr_to_write, inode->i_ino, ret); + dump_stack(); + goto out_writepages; + } + to_write -= wbc->nr_to_write; + + mpd.get_block = ext4_da_get_block_write; + ret = mpage_da_writepages(mapping, wbc, &mpd); + + ext4_journal_stop(handle); + + if (mpd.retval == -ENOSPC) + jbd2_journal_force_commit_nested(sbi->s_journal); + + /* reset the retry count */ + if (ret == MPAGE_DA_EXTENT_TAIL) { + /* + * got one extent now try with + * rest of the pages + */ + to_write += wbc->nr_to_write; + ret = 0; + } else if (wbc->nr_to_write) { + /* + * There is no more writeout needed + * or we requested for a noblocking writeout + * and we found the device congested + */ + to_write += wbc->nr_to_write; + break; + } + wbc->nr_to_write = to_write; + } + + if (wbc->range_cont && (pages_skipped != wbc->pages_skipped)) { + /* We skipped pages in this loop */ + wbc->range_start = range_start; + wbc->nr_to_write = to_write + + wbc->pages_skipped - pages_skipped; + wbc->pages_skipped = pages_skipped; + goto restart_loop; + } + +out_writepages: + wbc->nr_to_write = to_write - nr_to_writebump; + wbc->range_start = range_start; return ret; } -static int ext4_da_writepages(struct address_space *mapping, - struct writeback_control *wbc) +#define FALL_BACK_TO_NONDELALLOC 1 +static int ext4_nonda_switch(struct super_block *sb) { - return mpage_da_writepages(mapping, wbc, ext4_da_get_block_write); + s64 free_blocks, dirty_blocks; + struct ext4_sb_info *sbi = EXT4_SB(sb); + + /* + * switch to non delalloc mode if we are running low + * on free block. The free block accounting via percpu + * counters can get slightly wrong with FBC_BATCH getting + * accumulated on each CPU without updating global counters + * Delalloc need an accurate free block accounting. So switch + * to non delalloc when we are near to error range. + */ + free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter); + dirty_blocks = percpu_counter_read_positive(&sbi->s_dirtyblocks_counter); + if (2 * free_blocks < 3 * dirty_blocks || + free_blocks < (dirty_blocks + EXT4_FREEBLOCKS_WATERMARK)) { + /* + * free block count is less that 150% of dirty blocks + * or free blocks is less that watermark + */ + return 1; + } + return 0; } static int ext4_da_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { - int ret; + int ret, retries = 0; struct page *page; pgoff_t index; unsigned from, to; @@ -1963,6 +2534,13 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, from = pos & (PAGE_CACHE_SIZE - 1); to = from + len; + if (ext4_nonda_switch(inode->i_sb)) { + *fsdata = (void *)FALL_BACK_TO_NONDELALLOC; + return ext4_write_begin(file, mapping, pos, + len, flags, pagep, fsdata); + } + *fsdata = (void *)0; +retry: /* * With delayed allocation, we don't log the i_disksize update * if there is delayed block allocation. But we still need @@ -1976,8 +2554,11 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, } page = __grab_cache_page(mapping, index); - if (!page) - return -ENOMEM; + if (!page) { + ext4_journal_stop(handle); + ret = -ENOMEM; + goto out; + } *pagep = page; ret = block_write_begin(file, mapping, pos, len, flags, pagep, fsdata, @@ -1986,15 +2567,42 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping, unlock_page(page); ext4_journal_stop(handle); page_cache_release(page); + /* + * block_write_begin may have instantiated a few blocks + * outside i_size. Trim these off again. Don't need + * i_size_read because we hold i_mutex. + */ + if (pos + len > inode->i_size) + vmtruncate(inode, inode->i_size); } + if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) + goto retry; out: return ret; } -static int ext4_bh_unmapped_or_delay(handle_t *handle, struct buffer_head *bh) +/* + * Check if we should update i_disksize + * when write to the end of file but not require block allocation + */ +static int ext4_da_should_update_i_disksize(struct page *page, + unsigned long offset) { - return !buffer_mapped(bh) || buffer_delay(bh); + struct buffer_head *bh; + struct inode *inode = page->mapping->host; + unsigned int idx; + int i; + + bh = page_buffers(page); + idx = offset >> inode->i_blkbits; + + for (i = 0; i < idx; i++) + bh = bh->b_this_page; + + if (!buffer_mapped(bh) || (buffer_delay(bh))) + return 0; + return 1; } static int ext4_da_write_end(struct file *file, @@ -2006,6 +2614,23 @@ static int ext4_da_write_end(struct file *file, int ret = 0, ret2; handle_t *handle = ext4_journal_current_handle(); loff_t new_i_size; + unsigned long start, end; + int write_mode = (int)(unsigned long)fsdata; + + if (write_mode == FALL_BACK_TO_NONDELALLOC) { + if (ext4_should_order_data(inode)) { + return ext4_ordered_write_end(file, mapping, pos, + len, copied, page, fsdata); + } else if (ext4_should_writeback_data(inode)) { + return ext4_writeback_write_end(file, mapping, pos, + len, copied, page, fsdata); + } else { + BUG(); + } + } + + start = pos & (PAGE_CACHE_SIZE - 1); + end = start + copied - 1; /* * generic_write_end() will run mark_inode_dirty() if i_size @@ -2014,18 +2639,23 @@ static int ext4_da_write_end(struct file *file, */ new_i_size = pos + copied; - if (new_i_size > EXT4_I(inode)->i_disksize) - if (!walk_page_buffers(NULL, page_buffers(page), - 0, len, NULL, ext4_bh_unmapped_or_delay)){ - /* - * Updating i_disksize when extending file without - * needing block allocation - */ - if (ext4_should_order_data(inode)) - ret = ext4_jbd2_file_inode(handle, inode); + if (new_i_size > EXT4_I(inode)->i_disksize) { + if (ext4_da_should_update_i_disksize(page, end)) { + down_write(&EXT4_I(inode)->i_data_sem); + if (new_i_size > EXT4_I(inode)->i_disksize) { + /* + * Updating i_disksize when extending file + * without needing block allocation + */ + if (ext4_should_order_data(inode)) + ret = ext4_jbd2_file_inode(handle, + inode); - EXT4_I(inode)->i_disksize = new_i_size; + EXT4_I(inode)->i_disksize = new_i_size; + } + up_write(&EXT4_I(inode)->i_data_sem); } + } ret2 = generic_write_end(file, mapping, pos, len, copied, page, fsdata); copied = ret2; @@ -2040,9 +2670,6 @@ static int ext4_da_write_end(struct file *file, static void ext4_da_invalidatepage(struct page *page, unsigned long offset) { - struct buffer_head *head, *bh; - unsigned int curr_off = 0; - /* * Drop reserved blocks */ @@ -2050,21 +2677,7 @@ static void ext4_da_invalidatepage(struct page *page, unsigned long offset) if (!page_has_buffers(page)) goto out; - head = page_buffers(page); - bh = head; - do { - unsigned int next_off = curr_off + bh->b_size; - - /* - * is this block fully invalidated? - */ - if (offset <= curr_off && buffer_delay(bh)) { - clear_buffer_delay(bh); - /* XXX: add real stuff here */ - } - curr_off = next_off; - bh = bh->b_this_page; - } while (bh != head); + ext4_da_page_release_reservation(page, offset); out: ext4_invalidatepage(page, offset); @@ -2132,7 +2745,7 @@ static sector_t ext4_bmap(struct address_space *mapping, sector_t block) return 0; } - return generic_block_bmap(mapping,block,ext4_get_block); + return generic_block_bmap(mapping, block, ext4_get_block); } static int bget_one(handle_t *handle, struct buffer_head *bh) @@ -2206,12 +2819,14 @@ static int __ext4_normal_writepage(struct page *page, struct inode *inode = page->mapping->host; if (test_opt(inode->i_sb, NOBH)) - return nobh_writepage(page, ext4_get_block, wbc); + return nobh_writepage(page, + ext4_normal_get_block_write, wbc); else - return block_write_full_page(page, ext4_get_block, wbc); + return block_write_full_page(page, + ext4_normal_get_block_write, + wbc); } - static int ext4_normal_writepage(struct page *page, struct writeback_control *wbc) { @@ -2220,13 +2835,24 @@ static int ext4_normal_writepage(struct page *page, loff_t len; J_ASSERT(PageLocked(page)); - J_ASSERT(page_has_buffers(page)); if (page->index == size >> PAGE_CACHE_SHIFT) len = size & ~PAGE_CACHE_MASK; else len = PAGE_CACHE_SIZE; - BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL, - ext4_bh_unmapped_or_delay)); + + if (page_has_buffers(page)) { + /* if page has buffers it should all be mapped + * and allocated. If there are not buffers attached + * to the page we know the page is dirty but it lost + * buffers. That means that at some moment in time + * after write_begin() / write_end() has been called + * all buffers have been clean and thus they must have been + * written at least once. So they are all mapped and we can + * happily proceed with mapping them and writing the page. + */ + BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL, + ext4_bh_unmapped_or_delay)); + } if (!ext4_journal_current_handle()) return __ext4_normal_writepage(page, wbc); @@ -2246,7 +2872,8 @@ static int __ext4_journalled_writepage(struct page *page, int ret = 0; int err; - ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE, ext4_get_block); + ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE, + ext4_normal_get_block_write); if (ret != 0) goto out_unlock; @@ -2293,13 +2920,24 @@ static int ext4_journalled_writepage(struct page *page, loff_t len; J_ASSERT(PageLocked(page)); - J_ASSERT(page_has_buffers(page)); if (page->index == size >> PAGE_CACHE_SHIFT) len = size & ~PAGE_CACHE_MASK; else len = PAGE_CACHE_SIZE; - BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL, - ext4_bh_unmapped_or_delay)); + + if (page_has_buffers(page)) { + /* if page has buffers it should all be mapped + * and allocated. If there are not buffers attached + * to the page we know the page is dirty but it lost + * buffers. That means that at some moment in time + * after write_begin() / write_end() has been called + * all buffers have been clean and thus they must have been + * written at least once. So they are all mapped and we can + * happily proceed with mapping them and writing the page. + */ + BUG_ON(walk_page_buffers(NULL, page_buffers(page), 0, len, NULL, + ext4_bh_unmapped_or_delay)); + } if (ext4_journal_current_handle()) goto no_write; @@ -2317,7 +2955,9 @@ static int ext4_journalled_writepage(struct page *page, * really know unless we go poke around in the buffer_heads. * But block_write_full_page will do the right thing. */ - return block_write_full_page(page, ext4_get_block, wbc); + return block_write_full_page(page, + ext4_normal_get_block_write, + wbc); } no_write: redirty_page_for_writepage(wbc, page); @@ -2463,64 +3103,71 @@ 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) { - if (ext4_should_order_data(inode)) + if (ext4_should_order_data(inode) && + test_opt(inode->i_sb, DELALLOC)) + inode->i_mapping->a_ops = &ext4_da_aops; + else if (ext4_should_order_data(inode)) inode->i_mapping->a_ops = &ext4_ordered_aops; else if (ext4_should_writeback_data(inode) && test_opt(inode->i_sb, DELALLOC)) @@ -2704,7 +3351,7 @@ static Indirect *ext4_find_shared(struct inode *inode, int depth, if (!partial->key && *partial->p) /* Writer: end */ goto no_top; - for (p=partial; p>chain && all_zeroes((__le32*)p->bh->b_data,p->p); p--) + for (p = partial; (p > chain) && all_zeroes((__le32 *) p->bh->b_data, p->p); p--) ; /* * OK, we've found the last block that must survive. The rest of our @@ -2723,7 +3370,7 @@ static Indirect *ext4_find_shared(struct inode *inode, int depth, } /* Writer: end */ - while(partial > p) { + while (partial > p) { brelse(partial->bh); partial--; } @@ -2915,9 +3562,9 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode, /* This zaps the entire block. Bottom up. */ BUFFER_TRACE(bh, "free child branches"); ext4_free_branches(handle, inode, bh, - (__le32*)bh->b_data, - (__le32*)bh->b_data + addr_per_block, - depth); + (__le32 *) bh->b_data, + (__le32 *) bh->b_data + addr_per_block, + depth); /* * We've probably journalled the indirect block several @@ -3080,6 +3727,14 @@ void ext4_truncate(struct inode *inode) goto out_stop; /* + * From here we block out all ext4_get_block() callers who want to + * modify the block allocation tree. + */ + down_write(&ei->i_data_sem); + + ext4_discard_reservation(inode); + + /* * The orphan list entry will now protect us from any crash which * occurs before the truncate completes, so it is now safe to propagate * the new, shorter inode size (held for now in i_size) into the @@ -3088,12 +3743,6 @@ void ext4_truncate(struct inode *inode) */ ei->i_disksize = inode->i_size; - /* - * From here we block out all ext4_get_block() callers who want to - * modify the block allocation tree. - */ - down_write(&ei->i_data_sem); - if (n == 1) { /* direct blocks */ ext4_free_data(handle, inode, NULL, i_data+offsets[0], i_data + EXT4_NDIR_BLOCKS); @@ -3154,8 +3803,6 @@ do_indirects: ; } - ext4_discard_reservation(inode); - up_write(&ei->i_data_sem); inode->i_mtime = inode->i_ctime = ext4_current_time(inode); ext4_mark_inode_dirty(handle, inode); @@ -3241,6 +3888,16 @@ static int __ext4_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); @@ -3424,7 +4081,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) inode->i_mode = le16_to_cpu(raw_inode->i_mode); inode->i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); inode->i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); - if(!(test_opt (inode->i_sb, NO_UID32))) { + if (!(test_opt(inode->i_sb, NO_UID32))) { inode->i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; inode->i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; } @@ -3442,7 +4099,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) if (inode->i_mode == 0 || !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) { /* this inode is deleted */ - brelse (bh); + brelse(bh); ret = -ESTALE; goto bad_inode; } @@ -3475,7 +4132,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize); if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > EXT4_INODE_SIZE(inode->i_sb)) { - brelse (bh); + brelse(bh); ret = -EIO; goto bad_inode; } @@ -3528,7 +4185,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) init_special_inode(inode, inode->i_mode, new_decode_dev(le32_to_cpu(raw_inode->i_block[1]))); } - brelse (iloc.bh); + brelse(iloc.bh); ext4_set_inode_flags(inode); unlock_new_inode(inode); return inode; @@ -3610,14 +4267,14 @@ static int ext4_do_update_inode(handle_t *handle, ext4_get_inode_flags(ei); raw_inode->i_mode = cpu_to_le16(inode->i_mode); - if(!(test_opt(inode->i_sb, NO_UID32))) { + if (!(test_opt(inode->i_sb, NO_UID32))) { raw_inode->i_uid_low = cpu_to_le16(low_16_bits(inode->i_uid)); raw_inode->i_gid_low = cpu_to_le16(low_16_bits(inode->i_gid)); /* * Fix up interoperability with old kernels. Otherwise, old inodes get * re-used with the upper 16 bits of the uid/gid intact */ - if(!ei->i_dtime) { + if (!ei->i_dtime) { raw_inode->i_uid_high = cpu_to_le16(high_16_bits(inode->i_uid)); raw_inode->i_gid_high = @@ -3705,7 +4362,7 @@ static int ext4_do_update_inode(handle_t *handle, ei->i_state &= ~EXT4_STATE_NEW; out_brelse: - brelse (bh); + brelse(bh); ext4_std_error(inode->i_sb, err); return err; } @@ -3886,58 +4543,156 @@ err_out: return error; } +int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry, + struct kstat *stat) +{ + struct inode *inode; + unsigned long delalloc_blocks; + + inode = dentry->d_inode; + generic_fillattr(inode, stat); + + /* + * We can't update i_blocks if the block allocation is delayed + * otherwise in the case of system crash before the real block + * allocation is done, we will have i_blocks inconsistent with + * on-disk file blocks. + * We always keep i_blocks updated together with real + * allocation. But to not confuse with user, stat + * will return the blocks that include the delayed allocation + * blocks for this file. + */ + spin_lock(&EXT4_I(inode)->i_block_reservation_lock); + delalloc_blocks = EXT4_I(inode)->i_reserved_data_blocks; + spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); + + stat->blocks += (delalloc_blocks << inode->i_sb->s_blocksize_bits)>>9; + return 0; +} +static int ext4_indirect_trans_blocks(struct inode *inode, int nrblocks, + int chunk) +{ + int indirects; + + /* if nrblocks are contiguous */ + if (chunk) { + /* + * With N contiguous data blocks, it need at most + * N/EXT4_ADDR_PER_BLOCK(inode->i_sb) indirect blocks + * 2 dindirect blocks + * 1 tindirect block + */ + indirects = nrblocks / EXT4_ADDR_PER_BLOCK(inode->i_sb); + return indirects + 3; + } + /* + * if nrblocks are not contiguous, worse case, each block touch + * a indirect block, and each indirect block touch a double indirect + * block, plus a triple indirect block + */ + indirects = nrblocks * 2 + 1; + return indirects; +} + +static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk) +{ + if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL)) + return ext4_indirect_trans_blocks(inode, nrblocks, 0); + return ext4_ext_index_trans_blocks(inode, nrblocks, 0); +} /* - * How many blocks doth make a writepage()? - * - * With N blocks per page, it may be: - * N data blocks - * 2 indirect block - * 2 dindirect - * 1 tindirect - * N+5 bitmap blocks (from the above) - * N+5 group descriptor summary blocks - * 1 inode block - * 1 superblock. - * 2 * EXT4_SINGLEDATA_TRANS_BLOCKS for the quote files + * Account for index blocks, block groups bitmaps and block group + * descriptor blocks if modify datablocks and index blocks + * worse case, the indexs blocks spread over different block groups * - * 3 * (N + 5) + 2 + 2 * EXT4_SINGLEDATA_TRANS_BLOCKS + * If datablocks are discontiguous, they are possible to spread over + * different block groups too. If they are contiugous, with flexbg, + * they could still across block group boundary. * - * With ordered or writeback data it's the same, less the N data blocks. + * Also account for superblock, inode, quota and xattr blocks + */ +int ext4_meta_trans_blocks(struct inode *inode, int nrblocks, int chunk) +{ + int groups, gdpblocks; + int idxblocks; + int ret = 0; + + /* + * How many index blocks need to touch to modify nrblocks? + * The "Chunk" flag indicating whether the nrblocks is + * physically contiguous on disk + * + * For Direct IO and fallocate, they calls get_block to allocate + * one single extent at a time, so they could set the "Chunk" flag + */ + idxblocks = ext4_index_trans_blocks(inode, nrblocks, chunk); + + ret = idxblocks; + + /* + * Now let's see how many group bitmaps and group descriptors need + * to account + */ + groups = idxblocks; + if (chunk) + groups += 1; + else + groups += nrblocks; + + gdpblocks = groups; + if (groups > EXT4_SB(inode->i_sb)->s_groups_count) + groups = EXT4_SB(inode->i_sb)->s_groups_count; + if (groups > EXT4_SB(inode->i_sb)->s_gdb_count) + gdpblocks = EXT4_SB(inode->i_sb)->s_gdb_count; + + /* bitmaps and block group descriptor blocks */ + ret += groups + gdpblocks; + + /* Blocks for super block, inode, quota and xattr blocks */ + ret += EXT4_META_TRANS_BLOCKS(inode->i_sb); + + return ret; +} + +/* + * Calulate the total number of credits to reserve to fit + * the modification of a single pages into a single transaction, + * which may include multiple chunks of block allocations. * - * If the inode's direct blocks can hold an integral number of pages then a - * page cannot straddle two indirect blocks, and we can only touch one indirect - * and dindirect block, and the "5" above becomes "3". + * This could be called via ext4_write_begin() * - * This still overestimates under most circumstances. If we were to pass the - * start and end offsets in here as well we could do block_to_path() on each - * block and work out the exact number of indirects which are touched. Pah. + * We need to consider the worse case, when + * one new block per extent. */ - int ext4_writepage_trans_blocks(struct inode *inode) { int bpp = ext4_journal_blocks_per_page(inode); - int indirects = (EXT4_NDIR_BLOCKS % bpp) ? 5 : 3; int ret; - if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) - return ext4_ext_writepage_trans_blocks(inode, bpp); + ret = ext4_meta_trans_blocks(inode, bpp, 0); + /* Account for data blocks for journalled mode */ if (ext4_should_journal_data(inode)) - ret = 3 * (bpp + indirects) + 2; - else - ret = 2 * (bpp + indirects) + 2; - -#ifdef CONFIG_QUOTA - /* We know that structure was already allocated during DQUOT_INIT so - * we will be updating only the data blocks + inodes */ - ret += 2*EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb); -#endif - + ret += bpp; return ret; } /* + * Calculate the journal credits for a chunk of data modification. + * + * This is called from DIO, fallocate or whoever calling + * ext4_get_blocks_wrap() to map/allocate a chunk of contigous disk blocks. + * + * journal buffers for data blocks are not included here, as DIO + * and fallocate do no need to journal data buffers. + */ +int ext4_chunk_trans_blocks(struct inode *inode, int nrblocks) +{ + return ext4_meta_trans_blocks(inode, nrblocks, 1); +} + +/* * The caller must have previously called ext4_reserve_inode_write(). * Give this, we know that the caller already has write access to iloc->bh. */ @@ -4210,6 +4965,7 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct page *page) loff_t size; unsigned long len; int ret = -EINVAL; + void *fsdata; struct file *file = vma->vm_file; struct inode *inode = file->f_path.dentry->d_inode; struct address_space *mapping = inode->i_mapping; @@ -4248,11 +5004,11 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct page *page) * on the same page though */ ret = mapping->a_ops->write_begin(file, mapping, page_offset(page), - len, AOP_FLAG_UNINTERRUPTIBLE, &page, NULL); + len, AOP_FLAG_UNINTERRUPTIBLE, &page, &fsdata); if (ret < 0) goto out_unlock; ret = mapping->a_ops->write_end(file, mapping, page_offset(page), - len, len, page, NULL); + len, len, page, fsdata); if (ret < 0) goto out_unlock; ret = 0;