diff options
Diffstat (limited to 'fs/exfat/inode.c')
| -rw-r--r-- | fs/exfat/inode.c | 390 |
1 files changed, 223 insertions, 167 deletions
diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c index cf9ca6c4d046..f9501c3a3666 100644 --- a/fs/exfat/inode.c +++ b/fs/exfat/inode.c @@ -17,21 +17,22 @@ #include "exfat_raw.h" #include "exfat_fs.h" -static int __exfat_write_inode(struct inode *inode, int sync) +int __exfat_write_inode(struct inode *inode, int sync) { unsigned long long on_disk_size; struct exfat_dentry *ep, *ep2; - struct exfat_entry_set_cache *es = NULL; + struct exfat_entry_set_cache es; struct super_block *sb = inode->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_inode_info *ei = EXFAT_I(inode); - bool is_dir = (ei->type == TYPE_DIR) ? true : false; + bool is_dir = (ei->type == TYPE_DIR); + struct timespec64 ts; if (inode->i_ino == EXFAT_ROOT_INO) return 0; /* - * If the indode is already unlinked, there is no need for updating it. + * If the inode is already unlinked, there is no need for updating it. */ if (ei->dir.dir == DIR_DELETED) return 0; @@ -39,14 +40,13 @@ static int __exfat_write_inode(struct inode *inode, int sync) if (is_dir && ei->dir.dir == sbi->root_dir && ei->entry == -1) return 0; - exfat_set_vol_flags(sb, VOL_DIRTY); + exfat_set_volume_dirty(sb); /* get the directory entry of given file or directory */ - es = exfat_get_dentry_set(sb, &(ei->dir), ei->entry, ES_ALL_ENTRIES); - if (!es) + if (exfat_get_dentry_set_by_ei(&es, sb, ei)) return -EIO; - ep = exfat_get_dentry_cached(es, 0); - ep2 = exfat_get_dentry_cached(es, 1); + ep = exfat_get_dentry_cached(&es, ES_IDX_FILE); + ep2 = exfat_get_dentry_cached(&es, ES_IDX_STREAM); ep->dentry.file.attr = cpu_to_le16(exfat_make_attr(inode)); @@ -56,16 +56,18 @@ static int __exfat_write_inode(struct inode *inode, int sync) &ep->dentry.file.create_time, &ep->dentry.file.create_date, &ep->dentry.file.create_time_cs); - exfat_set_entry_time(sbi, &inode->i_mtime, - &ep->dentry.file.modify_tz, - &ep->dentry.file.modify_time, - &ep->dentry.file.modify_date, - &ep->dentry.file.modify_time_cs); - exfat_set_entry_time(sbi, &inode->i_atime, - &ep->dentry.file.access_tz, - &ep->dentry.file.access_time, - &ep->dentry.file.access_date, - NULL); + ts = inode_get_mtime(inode); + exfat_set_entry_time(sbi, &ts, + &ep->dentry.file.modify_tz, + &ep->dentry.file.modify_time, + &ep->dentry.file.modify_date, + &ep->dentry.file.modify_time_cs); + ts = inode_get_atime(inode); + exfat_set_entry_time(sbi, &ts, + &ep->dentry.file.access_tz, + &ep->dentry.file.access_time, + &ep->dentry.file.access_date, + NULL); /* File size should be zero if there is no cluster allocated */ on_disk_size = i_size_read(inode); @@ -73,18 +75,36 @@ static int __exfat_write_inode(struct inode *inode, int sync) if (ei->start_clu == EXFAT_EOF_CLUSTER) on_disk_size = 0; - ep2->dentry.stream.valid_size = cpu_to_le64(on_disk_size); - ep2->dentry.stream.size = ep2->dentry.stream.valid_size; + ep2->dentry.stream.size = cpu_to_le64(on_disk_size); + /* + * mmap write does not use exfat_write_end(), valid_size may be + * extended to the sector-aligned length in exfat_get_block(). + * So we need to fixup valid_size to the writren length. + */ + if (on_disk_size < ei->valid_size) + ep2->dentry.stream.valid_size = ep2->dentry.stream.size; + else + ep2->dentry.stream.valid_size = cpu_to_le64(ei->valid_size); + + if (on_disk_size) { + ep2->dentry.stream.flags = ei->flags; + ep2->dentry.stream.start_clu = cpu_to_le32(ei->start_clu); + } else { + ep2->dentry.stream.flags = ALLOC_FAT_CHAIN; + ep2->dentry.stream.start_clu = EXFAT_FREE_CLUSTER; + } - exfat_update_dir_chksum_with_entry_set(es); - exfat_free_dentry_set(es, sync); - return 0; + exfat_update_dir_chksum(&es); + return exfat_put_dentry_set(&es, sync); } int exfat_write_inode(struct inode *inode, struct writeback_control *wbc) { int ret; + if (unlikely(exfat_forced_shutdown(inode->i_sb))) + return -EIO; + mutex_lock(&EXFAT_SB(inode->i_sb)->s_lock); ret = __exfat_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL); mutex_unlock(&EXFAT_SB(inode->i_sb)->s_lock); @@ -106,21 +126,16 @@ void exfat_sync_inode(struct inode *inode) static int exfat_map_cluster(struct inode *inode, unsigned int clu_offset, unsigned int *clu, int create) { - int ret, modified = false; + int ret; unsigned int last_clu; struct exfat_chain new_clu; struct super_block *sb = inode->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_inode_info *ei = EXFAT_I(inode); unsigned int local_clu_offset = clu_offset; - unsigned int num_to_be_allocated = 0, num_clusters = 0; - - ei->rwoffset = EXFAT_CLU_TO_B(clu_offset, sbi); + unsigned int num_to_be_allocated = 0, num_clusters; - if (EXFAT_I(inode)->i_size_ondisk > 0) - num_clusters = - EXFAT_B_TO_CLU_ROUND_UP(EXFAT_I(inode)->i_size_ondisk, - sbi); + num_clusters = EXFAT_B_TO_CLU(exfat_ondisk_size(inode), sbi); if (clu_offset >= num_clusters) num_to_be_allocated = clu_offset - num_clusters + 1; @@ -168,7 +183,7 @@ static int exfat_map_cluster(struct inode *inode, unsigned int clu_offset, } if (*clu == EXFAT_EOF_CLUSTER) { - exfat_set_vol_flags(sb, VOL_DIRTY); + exfat_set_volume_dirty(sb); new_clu.dir = (last_clu == EXFAT_EOF_CLUSTER) ? EXFAT_EOF_CLUSTER : last_clu + 1; @@ -182,7 +197,8 @@ static int exfat_map_cluster(struct inode *inode, unsigned int clu_offset, return -EIO; } - ret = exfat_alloc_cluster(inode, num_to_be_allocated, &new_clu); + ret = exfat_alloc_cluster(inode, num_to_be_allocated, &new_clu, + inode_needs_sync(inode)); if (ret) return ret; @@ -199,7 +215,6 @@ static int exfat_map_cluster(struct inode *inode, unsigned int clu_offset, if (new_clu.flags == ALLOC_FAT_CHAIN) ei->flags = ALLOC_FAT_CHAIN; ei->start_clu = new_clu.dir; - modified = true; } else { if (new_clu.flags != ei->flags) { /* no-fat-chain bit is disabled, @@ -209,7 +224,6 @@ static int exfat_map_cluster(struct inode *inode, unsigned int clu_offset, exfat_chain_cont_cluster(sb, ei->start_clu, num_clusters); ei->flags = ALLOC_FAT_CHAIN; - modified = true; } if (new_clu.flags == ALLOC_FAT_CHAIN) if (exfat_ent_set(sb, last_clu, new_clu.dir)) @@ -219,33 +233,7 @@ static int exfat_map_cluster(struct inode *inode, unsigned int clu_offset, num_clusters += num_to_be_allocated; *clu = new_clu.dir; - if (ei->dir.dir != DIR_DELETED && modified) { - struct exfat_dentry *ep; - struct exfat_entry_set_cache *es; - - es = exfat_get_dentry_set(sb, &(ei->dir), ei->entry, - ES_ALL_ENTRIES); - if (!es) - return -EIO; - /* get stream entry */ - ep = exfat_get_dentry_cached(es, 1); - - /* update directory entry */ - ep->dentry.stream.flags = ei->flags; - ep->dentry.stream.start_clu = - cpu_to_le32(ei->start_clu); - ep->dentry.stream.valid_size = - cpu_to_le64(i_size_read(inode)); - ep->dentry.stream.size = - ep->dentry.stream.valid_size; - - exfat_update_dir_chksum_with_entry_set(es); - exfat_free_dentry_set(es, inode_needs_sync(inode)); - - } /* end of if != DIR_DELETED */ - - inode->i_blocks += - num_to_be_allocated << sbi->sect_per_clus_bits; + inode->i_blocks += EXFAT_CLU_TO_B(num_to_be_allocated, sbi) >> 9; /* * Move *clu pointer along FAT chains (hole care) because the @@ -273,21 +261,6 @@ static int exfat_map_cluster(struct inode *inode, unsigned int clu_offset, return 0; } -static int exfat_map_new_buffer(struct exfat_inode_info *ei, - struct buffer_head *bh, loff_t pos) -{ - if (buffer_delay(bh) && pos > ei->i_size_aligned) - return -EIO; - set_buffer_new(bh); - - /* - * Adjust i_size_aligned if i_size_ondisk is bigger than it. - */ - if (ei->i_size_ondisk > ei->i_size_aligned) - ei->i_size_aligned = ei->i_size_ondisk; - return 0; -} - static int exfat_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { @@ -300,10 +273,12 @@ static int exfat_get_block(struct inode *inode, sector_t iblock, unsigned int cluster, sec_offset; sector_t last_block; sector_t phys = 0; - loff_t pos; + sector_t valid_blks; + loff_t i_size; mutex_lock(&sbi->s_lock); - last_block = EXFAT_B_TO_BLK_ROUND_UP(i_size_read(inode), sb); + i_size = i_size_read(inode); + last_block = EXFAT_B_TO_BLK_ROUND_UP(i_size, sb); if (iblock >= last_block && !create) goto done; @@ -328,54 +303,135 @@ static int exfat_get_block(struct inode *inode, sector_t iblock, mapped_blocks = sbi->sect_per_clus - sec_offset; max_blocks = min(mapped_blocks, max_blocks); - /* Treat newly added block / cluster */ - if (iblock < last_block) - create = 0; + map_bh(bh_result, sb, phys); + if (buffer_delay(bh_result)) + clear_buffer_delay(bh_result); + + /* + * In most cases, we just need to set bh_result to mapped, unmapped + * or new status as follows: + * 1. i_size == valid_size + * 2. write case (create == 1) + * 3. direct_read (!bh_result->b_folio) + * -> the unwritten part will be zeroed in exfat_direct_IO() + * + * Otherwise, in the case of buffered read, it is necessary to take + * care the last nested block if valid_size is not equal to i_size. + */ + if (i_size == ei->valid_size || create || !bh_result->b_folio) + valid_blks = EXFAT_B_TO_BLK_ROUND_UP(ei->valid_size, sb); + else + valid_blks = EXFAT_B_TO_BLK(ei->valid_size, sb); - if (create || buffer_delay(bh_result)) { - pos = EXFAT_BLK_TO_B((iblock + 1), sb); - if (ei->i_size_ondisk < pos) - ei->i_size_ondisk = pos; + /* The range has been fully written, map it */ + if (iblock + max_blocks < valid_blks) + goto done; + + /* The range has been partially written, map the written part */ + if (iblock < valid_blks) { + max_blocks = valid_blks - iblock; + goto done; } + /* The area has not been written, map and mark as new for create case */ if (create) { - err = exfat_map_new_buffer(ei, bh_result, pos); - if (err) { - exfat_fs_error(sb, - "requested for bmap out of range(pos : (%llu) > i_size_aligned(%llu)\n", - pos, ei->i_size_aligned); - goto unlock_ret; + set_buffer_new(bh_result); + ei->valid_size = EXFAT_BLK_TO_B(iblock + max_blocks, sb); + mark_inode_dirty(inode); + goto done; + } + + /* + * The area has just one block partially written. + * In that case, we should read and fill the unwritten part of + * a block with zero. + */ + if (bh_result->b_folio && iblock == valid_blks && + (ei->valid_size & (sb->s_blocksize - 1))) { + loff_t size, pos; + void *addr; + + max_blocks = 1; + + /* + * No buffer_head is allocated. + * (1) bmap: It's enough to set blocknr without I/O. + * (2) read: The unwritten part should be filled with zero. + * If a folio does not have any buffers, + * let's returns -EAGAIN to fallback to + * block_read_full_folio() for per-bh IO. + */ + if (!folio_buffers(bh_result->b_folio)) { + err = -EAGAIN; + goto done; } + + pos = EXFAT_BLK_TO_B(iblock, sb); + size = ei->valid_size - pos; + addr = folio_address(bh_result->b_folio) + + offset_in_folio(bh_result->b_folio, pos); + + /* Check if bh->b_data points to proper addr in folio */ + if (bh_result->b_data != addr) { + exfat_fs_error_ratelimit(sb, + "b_data(%p) != folio_addr(%p)", + bh_result->b_data, addr); + err = -EINVAL; + goto done; + } + + /* Read a block */ + err = bh_read(bh_result, 0); + if (err < 0) + goto done; + + /* Zero unwritten part of a block */ + memset(bh_result->b_data + size, 0, bh_result->b_size - size); + err = 0; + goto done; } - if (buffer_delay(bh_result)) - clear_buffer_delay(bh_result); - map_bh(bh_result, sb, phys); + /* + * The area has not been written, clear mapped for read/bmap cases. + * If so, it will be filled with zero without reading from disk. + */ + clear_buffer_mapped(bh_result); done: bh_result->b_size = EXFAT_BLK_TO_B(max_blocks, sb); + if (err < 0) + clear_buffer_mapped(bh_result); unlock_ret: mutex_unlock(&sbi->s_lock); return err; } -static int exfat_readpage(struct file *file, struct page *page) +static int exfat_read_folio(struct file *file, struct folio *folio) { - return mpage_readpage(page, exfat_get_block); + return mpage_read_folio(folio, exfat_get_block); } static void exfat_readahead(struct readahead_control *rac) { - mpage_readahead(rac, exfat_get_block); -} + struct address_space *mapping = rac->mapping; + struct inode *inode = mapping->host; + struct exfat_inode_info *ei = EXFAT_I(inode); + loff_t pos = readahead_pos(rac); -static int exfat_writepage(struct page *page, struct writeback_control *wbc) -{ - return block_write_full_page(page, exfat_get_block, wbc); + /* Range cross valid_size, read it page by page. */ + if (ei->valid_size < i_size_read(inode) && + pos <= ei->valid_size && + ei->valid_size < pos + readahead_length(rac)) + return; + + mpage_readahead(rac, exfat_get_block); } static int exfat_writepages(struct address_space *mapping, struct writeback_control *wbc) { + if (unlikely(exfat_forced_shutdown(mapping->host->i_sb))) + return -EIO; + return mpage_writepages(mapping, wbc, exfat_get_block); } @@ -385,20 +441,22 @@ static void exfat_write_failed(struct address_space *mapping, loff_t to) if (to > i_size_read(inode)) { truncate_pagecache(inode, i_size_read(inode)); - exfat_truncate(inode, EXFAT_I(inode)->i_size_aligned); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); + exfat_truncate(inode); } } -static int exfat_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned int len, unsigned int flags, - struct page **pagep, void **fsdata) +static int exfat_write_begin(const struct kiocb *iocb, + struct address_space *mapping, + loff_t pos, unsigned int len, + struct folio **foliop, void **fsdata) { int ret; - *pagep = NULL; - ret = cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata, - exfat_get_block, - &EXFAT_I(mapping->host)->i_size_ondisk); + if (unlikely(exfat_forced_shutdown(mapping->host->i_sb))) + return -EIO; + + ret = block_write_begin(mapping, pos, len, foliop, exfat_get_block); if (ret < 0) exfat_write_failed(mapping, pos+len); @@ -406,29 +464,27 @@ static int exfat_write_begin(struct file *file, struct address_space *mapping, return ret; } -static int exfat_write_end(struct file *file, struct address_space *mapping, - loff_t pos, unsigned int len, unsigned int copied, - struct page *pagep, void *fsdata) +static int exfat_write_end(const struct kiocb *iocb, + struct address_space *mapping, + loff_t pos, unsigned int len, unsigned int copied, + struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; struct exfat_inode_info *ei = EXFAT_I(inode); int err; - err = generic_write_end(file, mapping, pos, len, copied, pagep, fsdata); - - if (EXFAT_I(inode)->i_size_aligned < i_size_read(inode)) { - exfat_fs_error(inode->i_sb, - "invalid size(size(%llu) > aligned(%llu)\n", - i_size_read(inode), EXFAT_I(inode)->i_size_aligned); - return -EIO; - } - + err = generic_write_end(iocb, mapping, pos, len, copied, folio, fsdata); if (err < len) exfat_write_failed(mapping, pos+len); - if (!(err < 0) && !(ei->attr & ATTR_ARCHIVE)) { - inode->i_mtime = inode->i_ctime = current_time(inode); - ei->attr |= ATTR_ARCHIVE; + if (!(err < 0) && pos + err > ei->valid_size) { + ei->valid_size = pos + err; + mark_inode_dirty(inode); + } + + if (!(err < 0) && !(ei->attr & EXFAT_ATTR_ARCHIVE)) { + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); + ei->attr |= EXFAT_ATTR_ARCHIVE; mark_inode_dirty(inode); } @@ -439,31 +495,41 @@ static ssize_t exfat_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = mapping->host; - loff_t size = iocb->ki_pos + iov_iter_count(iter); + struct exfat_inode_info *ei = EXFAT_I(inode); + loff_t pos = iocb->ki_pos; + loff_t size = pos + iov_iter_count(iter); int rw = iov_iter_rw(iter); ssize_t ret; - if (rw == WRITE) { - /* - * FIXME: blockdev_direct_IO() doesn't use ->write_begin(), - * so we need to update the ->i_size_aligned to block boundary. - * - * But we must fill the remaining area or hole by nul for - * updating ->i_size_aligned - * - * Return 0, and fallback to normal buffered write. - */ - if (EXFAT_I(inode)->i_size_aligned < size) - return 0; - } - /* * Need to use the DIO_LOCKING for avoiding the race * condition of exfat_get_block() and ->truncate(). */ ret = blockdev_direct_IO(iocb, inode, iter, exfat_get_block); - if (ret < 0 && (rw & WRITE)) - exfat_write_failed(mapping, size); + if (ret < 0) { + if (rw == WRITE && ret != -EIOCBQUEUED) + exfat_write_failed(mapping, size); + + return ret; + } else + size = pos + ret; + + if (rw == WRITE) { + /* + * If the block had been partially written before this write, + * ->valid_size will not be updated in exfat_get_block(), + * update it here. + */ + if (ei->valid_size < size) { + ei->valid_size = size; + mark_inode_dirty(inode); + } + } else if (pos < ei->valid_size && ei->valid_size < size) { + /* zero the unwritten part in the partially written block */ + iov_iter_revert(iter, size - ei->valid_size); + iov_iter_zero(size - ei->valid_size, iter); + } + return ret; } @@ -491,14 +557,16 @@ int exfat_block_truncate_page(struct inode *inode, loff_t from) } static const struct address_space_operations exfat_aops = { - .readpage = exfat_readpage, + .dirty_folio = block_dirty_folio, + .invalidate_folio = block_invalidate_folio, + .read_folio = exfat_read_folio, .readahead = exfat_readahead, - .writepage = exfat_writepage, .writepages = exfat_writepages, .write_begin = exfat_write_begin, .write_end = exfat_write_end, .direct_IO = exfat_direct_IO, - .bmap = exfat_aop_bmap + .bmap = exfat_aop_bmap, + .migrate_folio = buffer_migrate_folio, }; static inline unsigned long exfat_hash(loff_t i_pos) @@ -555,27 +623,27 @@ static int exfat_fill_inode(struct inode *inode, struct exfat_dir_entry *info) struct exfat_inode_info *ei = EXFAT_I(inode); loff_t size = info->size; - memcpy(&ei->dir, &info->dir, sizeof(struct exfat_chain)); + ei->dir = info->dir; ei->entry = info->entry; ei->attr = info->attr; ei->start_clu = info->start_clu; ei->flags = info->flags; ei->type = info->type; + ei->valid_size = info->valid_size; ei->version = 0; ei->hint_stat.eidx = 0; ei->hint_stat.clu = info->start_clu; ei->hint_femp.eidx = EXFAT_HINT_NONE; - ei->rwoffset = 0; ei->hint_bmap.off = EXFAT_EOF_CLUSTER; ei->i_pos = 0; inode->i_uid = sbi->options.fs_uid; inode->i_gid = sbi->options.fs_gid; inode_inc_iversion(inode); - inode->i_generation = prandom_u32(); + inode->i_generation = get_random_u32(); - if (info->attr & ATTR_SUBDIR) { /* directory */ + if (info->attr & EXFAT_ATTR_SUBDIR) { /* directory */ inode->i_generation &= ~1; inode->i_mode = exfat_make_mode(sbi, info->attr, 0777); inode->i_op = &exfat_dir_inode_operations; @@ -592,25 +660,13 @@ static int exfat_fill_inode(struct inode *inode, struct exfat_dir_entry *info) i_size_write(inode, size); - /* ondisk and aligned size should be aligned with block size */ - if (size & (inode->i_sb->s_blocksize - 1)) { - size |= (inode->i_sb->s_blocksize - 1); - size++; - } - - ei->i_size_aligned = size; - ei->i_size_ondisk = size; - exfat_save_attr(inode, info->attr); - inode->i_blocks = ((i_size_read(inode) + (sbi->cluster_size - 1)) & - ~(sbi->cluster_size - 1)) >> inode->i_blkbits; - inode->i_mtime = info->mtime; - inode->i_ctime = info->mtime; + inode->i_blocks = round_up(i_size_read(inode), sbi->cluster_size) >> 9; + inode_set_mtime_to_ts(inode, info->mtime); + inode_set_ctime_to_ts(inode, info->mtime); ei->i_crtime = info->crtime; - inode->i_atime = info->atime; - - exfat_cache_init_inode(inode); + inode_set_atime_to_ts(inode, info->atime); return 0; } @@ -650,7 +706,7 @@ void exfat_evict_inode(struct inode *inode) if (!inode->i_nlink) { i_size_write(inode, 0); mutex_lock(&EXFAT_SB(inode->i_sb)->s_lock); - __exfat_truncate(inode, 0); + __exfat_truncate(inode); mutex_unlock(&EXFAT_SB(inode->i_sb)->s_lock); } |
