From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-alma10-1.taild15c8.ts.net [100.103.45.18]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 155234F4733 for ; Wed, 16 Sep 2026 12:07:25 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=100.103.45.18 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1789560457; cv=none; b=RAHpHoFz/9ATuGvAPW7Yw9n4xPuEZkbO9eic56ay5bjrwjaulJieLB6D2wYYKtljedTGlU/SN/mByWtvtfWXbUpGZiX5xJ0gLHZDQYYpIY3bVBHMFASxhZrTu2X8UDlRfIDVWX+XD2ohx8UPzXFKIEX97xrpyl7a0mMZGND9LMA= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1789560457; c=relaxed/simple; bh=95bUyCXLrjAs825q+QrBuAkWVKnhvhgvg+mG6UW9kDs=; h=Message-ID:Date:MIME-Version:Cc:Subject:To:References:From: In-Reply-To:Content-Type; b=OjzIPBLEztzdIf2QJdzaAbftvz6XUi4ZuHwSqap+orYpQwrTU3NmFDCfjUht4rFt2KQYW+ZVFcXs3l4gxQawZYZEfty28IZg4zjg9XfAX5R7bnBuh7K9RmfqGv6vYhw5bDyWlvDcKPRgM+PBCy2bXP/wGlUiwRP+3WuC+q6WixE= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=m8B2gB/P; arc=none smtp.client-ip=100.103.45.18 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="m8B2gB/P" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 619281F000FF; Wed, 16 Sep 2026 12:07:19 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel.org; s=k20260515; t=1789560441; bh=cXx2XndakrQF6L0r//qBtUy8tWLc5FZpfFzhIY8tJC4=; h=Date:Cc:Subject:To:References:From:In-Reply-To; b=m8B2gB/PIjeLdlbegwHeGUgsRbp1OS3nYTh99UnghWK5kSe2XzfYDjn2xRC3mX2B+ SGrcg84eKjVMKH8KJs9g4BfQn3YLFf7rEm9XfBQrqHE229JNnuBKoHqd2oJNSeOO46 jkm5iK39TpkdNfpxCqrVOZ0NL2q1y2aFKFHxHLj82WTmoQoLWT1Yu1JiY6QVwLuwty m06gFhGV+3T4WmA2YX4Vxuc4LzJK1/eCLfXNzgiTruLM7VlyEwSf/XdLDwCye1mhC+ 9/+ZEaSg0FT7UcxoXHFZPB5z1XZdaXB3lVWA03itDLiFo+kljkqfwg5f8mPYqBKPRA GDm+61ki1Y3bw== Message-ID: <51c3f1f9-7e91-4f9a-9f22-d1ba8df357c6@kernel.org> Date: Wed, 16 Sep 2026 20:07:17 +0800 Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 User-Agent: Mozilla Thunderbird Cc: chao@kernel.org, Barry Song , Juan Yescas , Dev Jain , linux-kernel@vger.kernel.org, David Hildenbrand , Bo Zhang , Kalesh Singh , Nanzhe Zhao , Pengfei Li , Ryan Roberts Subject: Re: [PATCH v2 04/14] f2fs: support atomic file large folios buffered write To: Nanzhe Zhao , linux-f2fs-devel@lists.sourceforge.net, Jaegeuk Kim References: <20260915041909.2903887-1-zhaonanzhe@xiaomi.com> <20260915041909.2903887-5-zhaonanzhe@xiaomi.com> Content-Language: en-US From: Chao Yu In-Reply-To: <20260915041909.2903887-5-zhaonanzhe@xiaomi.com> Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit On 9/15/26 12:18, Nanzhe Zhao wrote: > ioctl can convert an inode with large folio support into an atomic > file. Support large folio buffered writes for atomic files as well. > > Add a large folio atomic write_begin helper that reserves COW mappings > for the write range. For partial head and tail subpages, read the > existing data from either the COW inode or the original inode before > marking the subpage uptodate. > > Signed-off-by: Nanzhe Zhao > --- > fs/f2fs/data.c | 88 ++++++++++++++++++++++++++++++++++++++++++++++---- > 1 file changed, 81 insertions(+), 7 deletions(-) > > diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c > index a490df4f50b3..eb5fb8e52851 100644 > --- a/fs/f2fs/data.c > +++ b/fs/f2fs/data.c > @@ -4016,18 +4016,16 @@ static int __reserve_data_block(struct inode *inode, pgoff_t index, > } > > static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi, > - struct folio *folio, loff_t pos, unsigned int len, > + struct inode *inode, pgoff_t index, > block_t *blk_addr, bool *node_changed) > { > - struct inode *inode = folio->mapping->host; > struct inode *cow_inode = F2FS_I(inode)->cow_inode; > - pgoff_t index = folio->index; > int err = 0; > block_t ori_blk_addr = NULL_ADDR; > bool cow_has_reserved_block = false; > > /* If pos is beyond the end of file, reserve a new block in COW inode */ ^^^ Need to update comments here? there is no @pos in the function. > - if ((pos & PAGE_MASK) >= i_size_read(inode)) > + if ((index << PAGE_SHIFT) >= i_size_read(inode)) > goto reserve_block; > > /* Look for the block in COW inode first */ > @@ -4168,6 +4166,74 @@ static int prepare_large_folio_write_begin(struct inode *inode, > return 0; > } > > +static int prepare_large_folio_atomic_write_begin(struct inode *inode, > + struct address_space *mapping, struct folio *folio, loff_t pos, > + unsigned int len) > +{ > + struct f2fs_sb_info *sbi = F2FS_I_SB(inode); > + size_t ori_off = offset_in_folio(folio, pos); > + pgoff_t start, end, index; > + unsigned int orig_order; > + int err = 0; > + > + len = min_t(unsigned int, len, folio_size(folio) - ori_off); > + > + if (!f2fs_ffs_find_or_alloc(folio)) > + return -ENOMEM; > + > + /* Inline data must have been converted before reaching here. */ > + f2fs_bug_on(sbi, f2fs_has_inline_data(inode)); > + > + start = folio->index + (ori_off >> PAGE_SHIFT); > + end = folio->index + ((ori_off + len - 1) >> PAGE_SHIFT); > + > + for (index = start; index <= end; index++) { > + block_t blkaddr = NULL_ADDR; > + bool node_changed = false; > + size_t off = (index - folio->index) << PAGE_SHIFT; > + > + err = prepare_atomic_write_begin(sbi, inode, index, > + &blkaddr, &node_changed); > + if (err) > + return err; > + > + if (f2fs_ffs_test_blk_uptodate(folio, index)) > + goto balance; > + > + if (blkaddr == NEW_ADDR) { > + folio_zero_segment(folio, off, off + PAGE_SIZE); > + f2fs_ffs_mark_subrange_uptodate(folio, off, PAGE_SIZE); > + goto balance; > + } > + > + if (!f2fs_is_valid_blkaddr(sbi, blkaddr, > + DATA_GENERIC_ENHANCE_READ)) > + return -EFSCORRUPTED; > + > + err = f2fs_submit_page_read_sync(inode, folio, index, > + blkaddr); > + if (err) > + return err; > +balance: > + /* > + * Expand the 4K-page balance decision per subpage: check > + * right after each preallocated block. > + */ > + if (node_changed && !IS_NOQUOTA(inode) && !IS_NOQUOTA(inode) is not needed. > + has_not_enough_free_secs(sbi, 0, 0)) { > + orig_order = folio_order(folio); > + folio_unlock(folio); > + f2fs_balance_fs(sbi, true); > + folio_lock(folio); > + if (unlikely(folio->mapping != mapping || > + folio_order(folio) != orig_order)) > + return -EAGAIN; > + } Why can't we merge this logic w/ others? it seems duplicated. Thanks, > + } > + > + return 0; > +} > + > static int f2fs_write_begin(const struct kiocb *iocb, > struct address_space *mapping, > loff_t pos, unsigned len, struct folio **foliop, > @@ -4245,8 +4311,8 @@ static int f2fs_write_begin(const struct kiocb *iocb, > > *foliop = folio; > > - if (f2fs_is_atomic_file(inode)) > - err = prepare_atomic_write_begin(sbi, folio, pos, len, > + if (f2fs_is_atomic_file(inode) && !folio_test_large(folio)) > + err = prepare_atomic_write_begin(sbi, inode, folio->index, > &blkaddr, &need_balance); > else if (!folio_test_large(folio)) > err = prepare_write_begin(sbi, folio, pos, len, > @@ -4270,10 +4336,18 @@ static int f2fs_write_begin(const struct kiocb *iocb, > f2fs_folio_wait_writeback(folio, DATA, false, true); > > if (folio_test_large(folio)) { > - err = prepare_large_folio_write_begin(inode, > + if (f2fs_is_atomic_file(inode)) > + err = prepare_large_folio_atomic_write_begin(inode, > + mapping, folio, pos, len); > + else > + err = prepare_large_folio_write_begin(inode, > folio, pos, len); > if (!err) > return 0; > + if (err == -EAGAIN) { > + f2fs_folio_put(folio, true); > + goto repeat; > + } > goto put_folio; > } >