static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { struct page *page = vmf->page; struct inode *inode = file_inode(vma->vm_file); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct dnode_of_data dn; int err; f2fs_balance_fs(sbi); vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE); f2fs_bug_on(sbi, f2fs_has_inline_data(inode)); /* block allocation */ f2fs_lock_op(sbi); set_new_dnode(&dn, inode, NULL, NULL, 0); err = f2fs_reserve_block(&dn, page->index); if (err) { f2fs_unlock_op(sbi); goto out; } f2fs_put_dnode(&dn); f2fs_unlock_op(sbi); file_update_time(vma->vm_file); lock_page(page); if (unlikely(page->mapping != inode->i_mapping || page_offset(page) > i_size_read(inode) || !PageUptodate(page))) { unlock_page(page); err = -EFAULT; goto out; } /* * check to see if the page is mapped already (no holes) */ if (PageMappedToDisk(page)) goto mapped; /* page is wholly or partially inside EOF */ if (((page->index + 1) << PAGE_CACHE_SHIFT) > i_size_read(inode)) { unsigned offset; offset = i_size_read(inode) & ~PAGE_CACHE_MASK; zero_user_segment(page, offset, PAGE_CACHE_SIZE); } set_page_dirty(page); SetPageUptodate(page); trace_f2fs_vm_page_mkwrite(page, DATA); mapped: /* fill the page */ f2fs_wait_on_page_writeback(page, DATA); /* if gced page is attached, don't write to cold segment */ clear_cold_data(page); out: return block_page_mkwrite_return(err); }
static int f2fs_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 f2fs_sb_info *sbi = F2FS_I_SB(inode); struct page *page = NULL; struct page *ipage; pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT; struct dnode_of_data dn; int err = 0; trace_f2fs_write_begin(inode, pos, len, flags); f2fs_balance_fs(sbi); /* * We should check this at this moment to avoid deadlock on inode page * and #0 page. The locking rule for inline_data conversion should be: * lock_page(page #0) -> lock_page(inode_page) */ if (index != 0) { err = f2fs_convert_inline_inode(inode); if (err) goto fail; } repeat: page = grab_cache_page_write_begin(mapping, index, flags); if (!page) { err = -ENOMEM; goto fail; } *pagep = page; f2fs_lock_op(sbi); /* check inline_data */ ipage = get_node_page(sbi, inode->i_ino); if (IS_ERR(ipage)) { err = PTR_ERR(ipage); goto unlock_fail; } set_new_dnode(&dn, inode, ipage, ipage, 0); if (f2fs_has_inline_data(inode)) { if (pos + len <= MAX_INLINE_DATA) { read_inline_data(page, ipage); set_inode_flag(F2FS_I(inode), FI_DATA_EXIST); sync_inode_page(&dn); goto put_next; } err = f2fs_convert_inline_page(&dn, page); if (err) goto put_fail; } err = f2fs_get_block(&dn, index); if (err) goto put_fail; put_next: f2fs_put_dnode(&dn); f2fs_unlock_op(sbi); f2fs_wait_on_page_writeback(page, DATA); if (len == PAGE_CACHE_SIZE) goto out_update; if (PageUptodate(page)) goto out_clear; if ((pos & PAGE_CACHE_MASK) >= i_size_read(inode)) { unsigned start = pos & (PAGE_CACHE_SIZE - 1); unsigned end = start + len; /* Reading beyond i_size is simple: memset to zero */ zero_user_segments(page, 0, start, end, PAGE_CACHE_SIZE); goto out_update; } if (dn.data_blkaddr == NEW_ADDR) { zero_user_segment(page, 0, PAGE_CACHE_SIZE); } else { struct f2fs_io_info fio = { .sbi = sbi, .type = DATA, .rw = READ_SYNC, .blk_addr = dn.data_blkaddr, .page = page, .encrypted_page = NULL, }; err = f2fs_submit_page_bio(&fio); if (err) goto fail; lock_page(page); if (unlikely(!PageUptodate(page))) { err = -EIO; goto fail; } if (unlikely(page->mapping != mapping)) { f2fs_put_page(page, 1); goto repeat; } /* avoid symlink page */ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) { err = f2fs_decrypt_one(inode, page); if (err) goto fail; } } out_update: SetPageUptodate(page); out_clear: clear_cold_data(page); return 0; put_fail: f2fs_put_dnode(&dn); unlock_fail: f2fs_unlock_op(sbi); fail: f2fs_put_page(page, 1); f2fs_write_failed(mapping, pos + len); return err; } static int f2fs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct inode *inode = page->mapping->host; trace_f2fs_write_end(inode, pos, len, copied); set_page_dirty(page); if (pos + copied > i_size_read(inode)) { i_size_write(inode, pos + copied); mark_inode_dirty(inode); update_inode_page(inode); } f2fs_put_page(page, 1); return copied; } static int check_direct_IO(struct inode *inode, struct iov_iter *iter, loff_t offset) { unsigned blocksize_mask = inode->i_sb->s_blocksize - 1; if (offset & blocksize_mask) return -EINVAL; if (iov_iter_alignment(iter) & blocksize_mask) return -EINVAL; return 0; }
static int f2fs_write_data_page(struct page *page, struct writeback_control *wbc) { struct inode *inode = page->mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); loff_t i_size = i_size_read(inode); const pgoff_t end_index = ((unsigned long long) i_size) >> PAGE_CACHE_SHIFT; unsigned offset = 0; bool need_balance_fs = false; int err = 0; struct f2fs_io_info fio = { .sbi = sbi, .type = DATA, .rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE, .page = page, .encrypted_page = NULL, }; trace_f2fs_writepage(page, DATA); if (page->index < end_index) goto write; /* * If the offset is out-of-range of file size, * this page does not have to be written to disk. */ offset = i_size & (PAGE_CACHE_SIZE - 1); if ((page->index >= end_index + 1) || !offset) goto out; zero_user_segment(page, offset, PAGE_CACHE_SIZE); write: if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) goto redirty_out; if (f2fs_is_drop_cache(inode)) goto out; if (f2fs_is_volatile_file(inode) && !wbc->for_reclaim && available_free_memory(sbi, BASE_CHECK)) goto redirty_out; /* Dentry blocks are controlled by checkpoint */ if (S_ISDIR(inode->i_mode)) { if (unlikely(f2fs_cp_error(sbi))) goto redirty_out; err = do_write_data_page(&fio); goto done; } /* we should bypass data pages to proceed the kworkder jobs */ if (unlikely(f2fs_cp_error(sbi))) { SetPageError(page); goto out; } if (!wbc->for_reclaim) need_balance_fs = true; else if (has_not_enough_free_secs(sbi, 0)) goto redirty_out; err = -EAGAIN; f2fs_lock_op(sbi); if (f2fs_has_inline_data(inode)) err = f2fs_write_inline_data(inode, page); if (err == -EAGAIN) err = do_write_data_page(&fio); f2fs_unlock_op(sbi); done: if (err && err != -ENOENT) goto redirty_out; clear_cold_data(page); out: inode_dec_dirty_pages(inode); if (err) ClearPageUptodate(page); unlock_page(page); if (need_balance_fs) f2fs_balance_fs(sbi); if (wbc->for_reclaim) f2fs_submit_merged_bio(sbi, DATA, WRITE); return 0; redirty_out: redirty_page_for_writepage(wbc, page); return AOP_WRITEPAGE_ACTIVATE; } static int __f2fs_writepage(struct page *page, struct writeback_control *wbc, void *data) { struct address_space *mapping = data; int ret = mapping->a_ops->writepage(page, wbc); mapping_set_error(mapping, ret); return ret; } /* * This function was copied from write_cche_pages from mm/page-writeback.c. * The major change is making write step of cold data page separately from * warm/hot data page. */ static int f2fs_write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data) { int ret = 0; int done = 0; struct pagevec pvec; int nr_pages; pgoff_t uninitialized_var(writeback_index); pgoff_t index; pgoff_t end; /* Inclusive */ pgoff_t done_index; int cycled; int range_whole = 0; int tag; int step = 0; pagevec_init(&pvec, 0); next: if (wbc->range_cyclic) { writeback_index = mapping->writeback_index; /* prev offset */ index = writeback_index; if (index == 0) cycled = 1; else cycled = 0; end = -1; } else { index = wbc->range_start >> PAGE_CACHE_SHIFT; end = wbc->range_end >> PAGE_CACHE_SHIFT; if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; cycled = 1; /* ignore range_cyclic tests */ } if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag = PAGECACHE_TAG_TOWRITE; else tag = PAGECACHE_TAG_DIRTY; retry: if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag_pages_for_writeback(mapping, index, end); done_index = index; while (!done && (index <= end)) { int i; nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag, min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1); if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; if (page->index > end) { done = 1; break; } done_index = page->index; lock_page(page); if (unlikely(page->mapping != mapping)) { continue_unlock: unlock_page(page); continue; } if (!PageDirty(page)) { /* someone wrote it for us */ goto continue_unlock; } if (step == is_cold_data(page)) goto continue_unlock; if (PageWriteback(page)) { if (wbc->sync_mode != WB_SYNC_NONE) f2fs_wait_on_page_writeback(page, DATA); else goto continue_unlock; } BUG_ON(PageWriteback(page)); if (!clear_page_dirty_for_io(page)) goto continue_unlock; ret = (*writepage)(page, wbc, data); if (unlikely(ret)) { if (ret == AOP_WRITEPAGE_ACTIVATE) { unlock_page(page); ret = 0; } else { done_index = page->index + 1; done = 1; break; } } if (--wbc->nr_to_write <= 0 && wbc->sync_mode == WB_SYNC_NONE) { done = 1; break; } } pagevec_release(&pvec); cond_resched(); } if (step < 1) { step++; goto next; } if (!cycled && !done) { cycled = 1; index = 0; end = writeback_index - 1; goto retry; } if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) mapping->writeback_index = done_index; return ret; }
static int f2fs_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 f2fs_sb_info *sbi = F2FS_I_SB(inode); struct page *page = NULL; struct page *ipage; pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT; struct dnode_of_data dn; int err = 0; trace_f2fs_write_begin(inode, pos, len, flags); f2fs_balance_fs(sbi); /* * We should check this at this moment to avoid deadlock on inode page * and #0 page. The locking rule for inline_data conversion should be: * lock_page(page #0) -> lock_page(inode_page) */ if (index != 0) { err = f2fs_convert_inline_inode(inode); if (err) goto fail; } repeat: page = grab_cache_page_write_begin(mapping, index, flags); if (!page) { err = -ENOMEM; goto fail; } *pagep = page; f2fs_lock_op(sbi); /* check inline_data */ ipage = get_node_page(sbi, inode->i_ino); if (IS_ERR(ipage)) { err = PTR_ERR(ipage); goto unlock_fail; } set_new_dnode(&dn, inode, ipage, ipage, 0); if (f2fs_has_inline_data(inode)) { if (pos + len <= MAX_INLINE_DATA) { read_inline_data(page, ipage); set_inode_flag(F2FS_I(inode), FI_DATA_EXIST); sync_inode_page(&dn); goto put_next; } err = f2fs_convert_inline_page(&dn, page); if (err) goto put_fail; } err = f2fs_get_block(&dn, index); if (err) goto put_fail; put_next: f2fs_put_dnode(&dn); f2fs_unlock_op(sbi); f2fs_wait_on_page_writeback(page, DATA); if (len == PAGE_CACHE_SIZE) goto out_update; if (PageUptodate(page)) goto out_clear; if ((pos & PAGE_CACHE_MASK) >= i_size_read(inode)) { unsigned start = pos & (PAGE_CACHE_SIZE - 1); unsigned end = start + len; /* Reading beyond i_size is simple: memset to zero */ zero_user_segments(page, 0, start, end, PAGE_CACHE_SIZE); goto out_update; } if (dn.data_blkaddr == NEW_ADDR) { zero_user_segment(page, 0, PAGE_CACHE_SIZE); } else { struct f2fs_io_info fio = { .sbi = sbi, .type = DATA, .rw = READ_SYNC, .blk_addr = dn.data_blkaddr, .page = page, .encrypted_page = NULL, }; err = f2fs_submit_page_bio(&fio); if (err) goto fail; lock_page(page); if (unlikely(!PageUptodate(page))) { err = -EIO; goto fail; } if (unlikely(page->mapping != mapping)) { f2fs_put_page(page, 1); goto repeat; } /* avoid symlink page */ if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) { err = f2fs_decrypt_one(inode, page); if (err) goto fail; } } out_update: SetPageUptodate(page); out_clear: clear_cold_data(page); return 0; put_fail: f2fs_put_dnode(&dn); unlock_fail: f2fs_unlock_op(sbi); fail: f2fs_put_page(page, 1); f2fs_write_failed(mapping, pos + len); return err; } static int f2fs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { struct inode *inode = page->mapping->host; trace_f2fs_write_end(inode, pos, len, copied); set_page_dirty(page); if (pos + copied > i_size_read(inode)) { i_size_write(inode, pos + copied); mark_inode_dirty(inode); update_inode_page(inode); } f2fs_put_page(page, 1); return copied; } static ssize_t check_direct_IO(struct inode *inode, int rw, const struct iovec *iov, loff_t offset, unsigned long nr_segs) { unsigned blocksize_mask = inode->i_sb->s_blocksize - 1; int seg, i; size_t size; unsigned long addr; ssize_t retval = -EINVAL; loff_t end = offset; if (offset & blocksize_mask) return -EINVAL; /* Check the memory alignment. Blocks cannot straddle pages */ for (seg = 0; seg < nr_segs; seg++) { addr = (unsigned long)iov[seg].iov_base; size = iov[seg].iov_len; end += size; if ((addr & blocksize_mask) || (size & blocksize_mask)) goto out; /* If this is a write we don't need to check anymore */ if (rw & WRITE) continue; /* * Check to make sure we don't have duplicate iov_base's in this * iovec, if so return EINVAL, otherwise we'll get csum errors * when reading back. */ for (i = seg + 1; i < nr_segs; i++) { if (iov[seg].iov_base == iov[i].iov_base) goto out; } } retval = 0; out: return retval; }