From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from casper.infradead.org (casper.infradead.org [90.155.50.34]) (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 3EC183FDB for ; Tue, 9 Nov 2021 08:33:52 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=infradead.org; s=casper.20170209; h=Content-Transfer-Encoding:MIME-Version: References:In-Reply-To:Message-Id:Date:Subject:Cc:To:From:Sender:Reply-To: Content-Type:Content-ID:Content-Description; bh=mfMDb5n97/RHD98fzJck6QJCWRVIOtc8ifMZjDMd/kQ=; b=Jeyxv3tsyyzZnJxRVCO2TB86Ws w+QW/DSGu6mPXAbKWCOMHiAmNN5rK3FhaDN94URftiwooYE6Kz+gz8a1HfSlssB02QBDy9aJwX46c NDXerTZam1l2Ml3fw83VloMPreSlSXJm/jzRom9zjYEnt43pMde3L43bArtupfVvuk4O+f8AQph7l Kj3jYG42Lvn+DXbfwPw5jj3lpKQh72Cd06FD0JbEYC1NX2yES5mwAwZHyF2oVjSOtBAbNtBoXMeDR vbug0yVOpp8HDFIdvP9bfctKCkHC9LPNUxlsH4CvmgS1IONxvcj5qU2yhGCBnm1dXQO4vmrrrzMZ9 YK5BQzmw==; Received: from [2001:4bb8:19a:7ee7:fb46:2fe1:8652:d9d4] (helo=localhost) by casper.infradead.org with esmtpsa (Exim 4.94.2 #2 (Red Hat Linux)) id 1mkMZd-000s62-5h; Tue, 09 Nov 2021 08:33:46 +0000 From: Christoph Hellwig To: Dan Williams Cc: Mike Snitzer , Ira Weiny , dm-devel@redhat.com, linux-xfs@vger.kernel.org, nvdimm@lists.linux.dev, linux-s390@vger.kernel.org, linux-fsdevel@vger.kernel.org, linux-erofs@lists.ozlabs.org, linux-ext4@vger.kernel.org, virtualization@lists.linux-foundation.org Subject: [PATCH 18/29] fsdax: decouple zeroing from the iomap buffered I/O code Date: Tue, 9 Nov 2021 09:32:58 +0100 Message-Id: <20211109083309.584081-19-hch@lst.de> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20211109083309.584081-1-hch@lst.de> References: <20211109083309.584081-1-hch@lst.de> Precedence: bulk X-Mailing-List: nvdimm@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-SRS-Rewrite: SMTP reverse-path rewritten from by casper.infradead.org. See http://www.infradead.org/rpr.html Unshare the DAX and iomap buffered I/O page zeroing code. This code previously did a IS_DAX check deep inside the iomap code, which in fact was the only DAX check in the code. Instead move these checks into the callers. Most callers already have DAX special casing anyway and XFS will need it for reflink support as well. Signed-off-by: Christoph Hellwig --- fs/dax.c | 77 ++++++++++++++++++++++++++++++++++-------- fs/ext2/inode.c | 6 ++-- fs/ext4/inode.c | 4 +-- fs/iomap/buffered-io.c | 35 +++++++------------ fs/xfs/xfs_iomap.c | 6 ++++ include/linux/dax.h | 6 +++- 6 files changed, 91 insertions(+), 43 deletions(-) diff --git a/fs/dax.c b/fs/dax.c index dc9ebeff850ab..5b52b878124ac 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1135,24 +1135,73 @@ static int dax_memzero(struct dax_device *dax_dev, pgoff_t pgoff, return rc; } -s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap) +static loff_t dax_zero_iter(struct iomap_iter *iter, bool *did_zero) { - pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); - long rc, id; - unsigned offset = offset_in_page(pos); - unsigned size = min_t(u64, PAGE_SIZE - offset, length); + const struct iomap *iomap = &iter->iomap; + const struct iomap *srcmap = iomap_iter_srcmap(iter); + loff_t pos = iter->pos; + loff_t length = iomap_length(iter); + loff_t written = 0; + + /* already zeroed? we're done. */ + if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) + return length; + + do { + unsigned offset = offset_in_page(pos); + unsigned size = min_t(u64, PAGE_SIZE - offset, length); + pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); + long rc; + int id; - id = dax_read_lock(); - if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE) - rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1); - else - rc = dax_memzero(iomap->dax_dev, pgoff, offset, size); - dax_read_unlock(id); + id = dax_read_lock(); + if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE) + rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1); + else + rc = dax_memzero(iomap->dax_dev, pgoff, offset, size); + dax_read_unlock(id); - if (rc < 0) - return rc; - return size; + if (rc < 0) + return rc; + pos += size; + length -= size; + written += size; + if (did_zero) + *did_zero = true; + } while (length > 0); + + return written; +} + +int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, + const struct iomap_ops *ops) +{ + struct iomap_iter iter = { + .inode = inode, + .pos = pos, + .len = len, + .flags = IOMAP_ZERO, + }; + int ret; + + while ((ret = iomap_iter(&iter, ops)) > 0) + iter.processed = dax_zero_iter(&iter, did_zero); + return ret; +} +EXPORT_SYMBOL_GPL(dax_zero_range); + +int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, + const struct iomap_ops *ops) +{ + unsigned int blocksize = i_blocksize(inode); + unsigned int off = pos & (blocksize - 1); + + /* Block boundary? Nothing to do */ + if (!off) + return 0; + return dax_zero_range(inode, pos, blocksize - off, did_zero, ops); } +EXPORT_SYMBOL_GPL(dax_truncate_page); static loff_t dax_iomap_iter(const struct iomap_iter *iomi, struct iov_iter *iter) diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 333fa62661d56..ae9993018a015 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1297,9 +1297,9 @@ static int ext2_setsize(struct inode *inode, loff_t newsize) inode_dio_wait(inode); if (IS_DAX(inode)) { - error = iomap_zero_range(inode, newsize, - PAGE_ALIGN(newsize) - newsize, NULL, - &ext2_iomap_ops); + error = dax_zero_range(inode, newsize, + PAGE_ALIGN(newsize) - newsize, NULL, + &ext2_iomap_ops); } else if (test_opt(inode->i_sb, NOBH)) error = nobh_truncate_page(inode->i_mapping, newsize, ext2_get_block); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0f06305167d5a..8c443b753b815 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3783,8 +3783,8 @@ static int ext4_block_zero_page_range(handle_t *handle, length = max; if (IS_DAX(inode)) { - return iomap_zero_range(inode, from, length, NULL, - &ext4_iomap_ops); + return dax_zero_range(inode, from, length, NULL, + &ext4_iomap_ops); } return __ext4_block_zero_page_range(handle, mapping, from, length); } diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 1753c26c8e76e..b1511255b4df8 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -870,26 +870,8 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, } EXPORT_SYMBOL_GPL(iomap_file_unshare); -static s64 __iomap_zero_iter(struct iomap_iter *iter, loff_t pos, u64 length) -{ - struct page *page; - int status; - unsigned offset = offset_in_page(pos); - unsigned bytes = min_t(u64, PAGE_SIZE - offset, length); - - status = iomap_write_begin(iter, pos, bytes, &page); - if (status) - return status; - - zero_user(page, offset, bytes); - mark_page_accessed(page); - - return iomap_write_end(iter, pos, bytes, bytes, page); -} - static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) { - struct iomap *iomap = &iter->iomap; const struct iomap *srcmap = iomap_iter_srcmap(iter); loff_t pos = iter->pos; loff_t length = iomap_length(iter); @@ -900,12 +882,19 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) return length; do { - s64 bytes; + unsigned offset = offset_in_page(pos); + size_t bytes = min_t(u64, PAGE_SIZE - offset, length); + struct page *page; + int status; - if (IS_DAX(iter->inode)) - bytes = dax_iomap_zero(pos, length, iomap); - else - bytes = __iomap_zero_iter(iter, pos, length); + status = iomap_write_begin(iter, pos, bytes, &page); + if (status) + return status; + + zero_user(page, offset, bytes); + mark_page_accessed(page); + + bytes = iomap_write_end(iter, pos, bytes, bytes, page); if (bytes < 0) return bytes; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index d6d71ae9f2ae4..604000b6243ec 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1321,6 +1321,9 @@ xfs_zero_range( { struct inode *inode = VFS_I(ip); + if (IS_DAX(inode)) + return dax_zero_range(inode, pos, len, did_zero, + &xfs_buffered_write_iomap_ops); return iomap_zero_range(inode, pos, len, did_zero, &xfs_buffered_write_iomap_ops); } @@ -1333,6 +1336,9 @@ xfs_truncate_page( { struct inode *inode = VFS_I(ip); + if (IS_DAX(inode)) + return dax_truncate_page(inode, pos, did_zero, + &xfs_buffered_write_iomap_ops); return iomap_truncate_page(inode, pos, did_zero, &xfs_buffered_write_iomap_ops); } diff --git a/include/linux/dax.h b/include/linux/dax.h index 324363b798ecd..a5cc2f1aa840e 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -14,6 +14,7 @@ typedef unsigned long dax_entry_t; struct dax_device; struct gendisk; struct iomap_ops; +struct iomap_iter; struct iomap; struct dax_operations { @@ -124,6 +125,10 @@ struct page *dax_layout_busy_page(struct address_space *mapping); struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end); dax_entry_t dax_lock_page(struct page *page); void dax_unlock_page(struct page *page, dax_entry_t cookie); +int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, + const struct iomap_ops *ops); +int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, + const struct iomap_ops *ops); #else static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk) { @@ -204,7 +209,6 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); -s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap); static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); -- 2.30.2 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 92EF6C47081 for ; Tue, 9 Nov 2021 08:34:01 +0000 (UTC) Received: from smtp1.osuosl.org (smtp1.osuosl.org [140.211.166.138]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 5BC68611C4 for ; Tue, 9 Nov 2021 08:34:01 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.1 mail.kernel.org 5BC68611C4 Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=lst.de Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=lists.linux-foundation.org Received: from localhost (localhost [127.0.0.1]) by smtp1.osuosl.org (Postfix) with ESMTP id 3870980EE0; Tue, 9 Nov 2021 08:34:01 +0000 (UTC) X-Virus-Scanned: amavisd-new at osuosl.org Received: from smtp1.osuosl.org ([127.0.0.1]) by localhost (smtp1.osuosl.org [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 9e0ny6zk8vTe; Tue, 9 Nov 2021 08:34:00 +0000 (UTC) Received: from lists.linuxfoundation.org (lf-lists.osuosl.org [IPv6:2605:bc80:3010:104::8cd3:938]) by smtp1.osuosl.org (Postfix) with ESMTPS id 6564880C6D; Tue, 9 Nov 2021 08:33:59 +0000 (UTC) Received: from lf-lists.osuosl.org (localhost [127.0.0.1]) by lists.linuxfoundation.org (Postfix) with ESMTP id 3C70EC0023; Tue, 9 Nov 2021 08:33:59 +0000 (UTC) Received: from smtp1.osuosl.org (smtp1.osuosl.org [IPv6:2605:bc80:3010::138]) by lists.linuxfoundation.org (Postfix) with ESMTP id 4D14BC000E for ; Tue, 9 Nov 2021 08:33:57 +0000 (UTC) Received: from localhost (localhost [127.0.0.1]) by smtp1.osuosl.org (Postfix) with ESMTP id 2EE1880ECD for ; Tue, 9 Nov 2021 08:33:57 +0000 (UTC) X-Virus-Scanned: amavisd-new at osuosl.org Received: from smtp1.osuosl.org ([127.0.0.1]) by localhost (smtp1.osuosl.org [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id zvybfs5raluh for ; Tue, 9 Nov 2021 08:33:56 +0000 (UTC) X-Greylist: from auto-whitelisted by SQLgrey-1.8.0 Received: from casper.infradead.org (casper.infradead.org [IPv6:2001:8b0:10b:1236::1]) by smtp1.osuosl.org (Postfix) with ESMTPS id 3561780E6E for ; Tue, 9 Nov 2021 08:33:56 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=infradead.org; s=casper.20170209; h=Content-Transfer-Encoding:MIME-Version: References:In-Reply-To:Message-Id:Date:Subject:Cc:To:From:Sender:Reply-To: Content-Type:Content-ID:Content-Description; bh=mfMDb5n97/RHD98fzJck6QJCWRVIOtc8ifMZjDMd/kQ=; b=Jeyxv3tsyyzZnJxRVCO2TB86Ws w+QW/DSGu6mPXAbKWCOMHiAmNN5rK3FhaDN94URftiwooYE6Kz+gz8a1HfSlssB02QBDy9aJwX46c NDXerTZam1l2Ml3fw83VloMPreSlSXJm/jzRom9zjYEnt43pMde3L43bArtupfVvuk4O+f8AQph7l Kj3jYG42Lvn+DXbfwPw5jj3lpKQh72Cd06FD0JbEYC1NX2yES5mwAwZHyF2oVjSOtBAbNtBoXMeDR vbug0yVOpp8HDFIdvP9bfctKCkHC9LPNUxlsH4CvmgS1IONxvcj5qU2yhGCBnm1dXQO4vmrrrzMZ9 YK5BQzmw==; Received: from [2001:4bb8:19a:7ee7:fb46:2fe1:8652:d9d4] (helo=localhost) by casper.infradead.org with esmtpsa (Exim 4.94.2 #2 (Red Hat Linux)) id 1mkMZd-000s62-5h; Tue, 09 Nov 2021 08:33:46 +0000 From: Christoph Hellwig To: Dan Williams Subject: [PATCH 18/29] fsdax: decouple zeroing from the iomap buffered I/O code Date: Tue, 9 Nov 2021 09:32:58 +0100 Message-Id: <20211109083309.584081-19-hch@lst.de> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20211109083309.584081-1-hch@lst.de> References: <20211109083309.584081-1-hch@lst.de> MIME-Version: 1.0 X-SRS-Rewrite: SMTP reverse-path rewritten from by casper.infradead.org. See http://www.infradead.org/rpr.html Cc: nvdimm@lists.linux.dev, Mike Snitzer , linux-s390@vger.kernel.org, linux-erofs@lists.ozlabs.org, virtualization@lists.linux-foundation.org, linux-xfs@vger.kernel.org, dm-devel@redhat.com, linux-fsdevel@vger.kernel.org, linux-ext4@vger.kernel.org, Ira Weiny X-BeenThere: virtualization@lists.linux-foundation.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: Linux virtualization List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Errors-To: virtualization-bounces@lists.linux-foundation.org Sender: "Virtualization" Unshare the DAX and iomap buffered I/O page zeroing code. This code previously did a IS_DAX check deep inside the iomap code, which in fact was the only DAX check in the code. Instead move these checks into the callers. Most callers already have DAX special casing anyway and XFS will need it for reflink support as well. Signed-off-by: Christoph Hellwig --- fs/dax.c | 77 ++++++++++++++++++++++++++++++++++-------- fs/ext2/inode.c | 6 ++-- fs/ext4/inode.c | 4 +-- fs/iomap/buffered-io.c | 35 +++++++------------ fs/xfs/xfs_iomap.c | 6 ++++ include/linux/dax.h | 6 +++- 6 files changed, 91 insertions(+), 43 deletions(-) diff --git a/fs/dax.c b/fs/dax.c index dc9ebeff850ab..5b52b878124ac 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1135,24 +1135,73 @@ static int dax_memzero(struct dax_device *dax_dev, pgoff_t pgoff, return rc; } -s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap) +static loff_t dax_zero_iter(struct iomap_iter *iter, bool *did_zero) { - pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); - long rc, id; - unsigned offset = offset_in_page(pos); - unsigned size = min_t(u64, PAGE_SIZE - offset, length); + const struct iomap *iomap = &iter->iomap; + const struct iomap *srcmap = iomap_iter_srcmap(iter); + loff_t pos = iter->pos; + loff_t length = iomap_length(iter); + loff_t written = 0; + + /* already zeroed? we're done. */ + if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) + return length; + + do { + unsigned offset = offset_in_page(pos); + unsigned size = min_t(u64, PAGE_SIZE - offset, length); + pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); + long rc; + int id; - id = dax_read_lock(); - if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE) - rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1); - else - rc = dax_memzero(iomap->dax_dev, pgoff, offset, size); - dax_read_unlock(id); + id = dax_read_lock(); + if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE) + rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1); + else + rc = dax_memzero(iomap->dax_dev, pgoff, offset, size); + dax_read_unlock(id); - if (rc < 0) - return rc; - return size; + if (rc < 0) + return rc; + pos += size; + length -= size; + written += size; + if (did_zero) + *did_zero = true; + } while (length > 0); + + return written; +} + +int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, + const struct iomap_ops *ops) +{ + struct iomap_iter iter = { + .inode = inode, + .pos = pos, + .len = len, + .flags = IOMAP_ZERO, + }; + int ret; + + while ((ret = iomap_iter(&iter, ops)) > 0) + iter.processed = dax_zero_iter(&iter, did_zero); + return ret; +} +EXPORT_SYMBOL_GPL(dax_zero_range); + +int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, + const struct iomap_ops *ops) +{ + unsigned int blocksize = i_blocksize(inode); + unsigned int off = pos & (blocksize - 1); + + /* Block boundary? Nothing to do */ + if (!off) + return 0; + return dax_zero_range(inode, pos, blocksize - off, did_zero, ops); } +EXPORT_SYMBOL_GPL(dax_truncate_page); static loff_t dax_iomap_iter(const struct iomap_iter *iomi, struct iov_iter *iter) diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 333fa62661d56..ae9993018a015 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1297,9 +1297,9 @@ static int ext2_setsize(struct inode *inode, loff_t newsize) inode_dio_wait(inode); if (IS_DAX(inode)) { - error = iomap_zero_range(inode, newsize, - PAGE_ALIGN(newsize) - newsize, NULL, - &ext2_iomap_ops); + error = dax_zero_range(inode, newsize, + PAGE_ALIGN(newsize) - newsize, NULL, + &ext2_iomap_ops); } else if (test_opt(inode->i_sb, NOBH)) error = nobh_truncate_page(inode->i_mapping, newsize, ext2_get_block); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0f06305167d5a..8c443b753b815 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3783,8 +3783,8 @@ static int ext4_block_zero_page_range(handle_t *handle, length = max; if (IS_DAX(inode)) { - return iomap_zero_range(inode, from, length, NULL, - &ext4_iomap_ops); + return dax_zero_range(inode, from, length, NULL, + &ext4_iomap_ops); } return __ext4_block_zero_page_range(handle, mapping, from, length); } diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 1753c26c8e76e..b1511255b4df8 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -870,26 +870,8 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, } EXPORT_SYMBOL_GPL(iomap_file_unshare); -static s64 __iomap_zero_iter(struct iomap_iter *iter, loff_t pos, u64 length) -{ - struct page *page; - int status; - unsigned offset = offset_in_page(pos); - unsigned bytes = min_t(u64, PAGE_SIZE - offset, length); - - status = iomap_write_begin(iter, pos, bytes, &page); - if (status) - return status; - - zero_user(page, offset, bytes); - mark_page_accessed(page); - - return iomap_write_end(iter, pos, bytes, bytes, page); -} - static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) { - struct iomap *iomap = &iter->iomap; const struct iomap *srcmap = iomap_iter_srcmap(iter); loff_t pos = iter->pos; loff_t length = iomap_length(iter); @@ -900,12 +882,19 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) return length; do { - s64 bytes; + unsigned offset = offset_in_page(pos); + size_t bytes = min_t(u64, PAGE_SIZE - offset, length); + struct page *page; + int status; - if (IS_DAX(iter->inode)) - bytes = dax_iomap_zero(pos, length, iomap); - else - bytes = __iomap_zero_iter(iter, pos, length); + status = iomap_write_begin(iter, pos, bytes, &page); + if (status) + return status; + + zero_user(page, offset, bytes); + mark_page_accessed(page); + + bytes = iomap_write_end(iter, pos, bytes, bytes, page); if (bytes < 0) return bytes; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index d6d71ae9f2ae4..604000b6243ec 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1321,6 +1321,9 @@ xfs_zero_range( { struct inode *inode = VFS_I(ip); + if (IS_DAX(inode)) + return dax_zero_range(inode, pos, len, did_zero, + &xfs_buffered_write_iomap_ops); return iomap_zero_range(inode, pos, len, did_zero, &xfs_buffered_write_iomap_ops); } @@ -1333,6 +1336,9 @@ xfs_truncate_page( { struct inode *inode = VFS_I(ip); + if (IS_DAX(inode)) + return dax_truncate_page(inode, pos, did_zero, + &xfs_buffered_write_iomap_ops); return iomap_truncate_page(inode, pos, did_zero, &xfs_buffered_write_iomap_ops); } diff --git a/include/linux/dax.h b/include/linux/dax.h index 324363b798ecd..a5cc2f1aa840e 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -14,6 +14,7 @@ typedef unsigned long dax_entry_t; struct dax_device; struct gendisk; struct iomap_ops; +struct iomap_iter; struct iomap; struct dax_operations { @@ -124,6 +125,10 @@ struct page *dax_layout_busy_page(struct address_space *mapping); struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end); dax_entry_t dax_lock_page(struct page *page); void dax_unlock_page(struct page *page, dax_entry_t cookie); +int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, + const struct iomap_ops *ops); +int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, + const struct iomap_ops *ops); #else static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk) { @@ -204,7 +209,6 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); -s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap); static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); -- 2.30.2 _______________________________________________ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 93AF7C433F5 for ; Tue, 9 Nov 2021 08:34:27 +0000 (UTC) Received: from lists.ozlabs.org (lists.ozlabs.org [112.213.38.117]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 27F7E6115A for ; Tue, 9 Nov 2021 08:34:27 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.1 mail.kernel.org 27F7E6115A Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=lst.de Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=lists.ozlabs.org Received: from boromir.ozlabs.org (localhost [IPv6:::1]) by lists.ozlabs.org (Postfix) with ESMTP id 4HpLr15Qyxz2yPd for ; Tue, 9 Nov 2021 19:34:25 +1100 (AEDT) Authentication-Results: lists.ozlabs.org; dkim=fail reason="signature verification failed" (2048-bit key; secure) header.d=infradead.org header.i=@infradead.org header.a=rsa-sha256 header.s=casper.20170209 header.b=Jeyxv3ts; dkim-atps=neutral Authentication-Results: lists.ozlabs.org; spf=none (no SPF record) smtp.mailfrom=casper.srs.infradead.org (client-ip=2001:8b0:10b:1236::1; helo=casper.infradead.org; envelope-from=batv+ffbfd99345897bc8db8d+6652+infradead.org+hch@casper.srs.infradead.org; receiver=) Authentication-Results: lists.ozlabs.org; dkim=pass (2048-bit key; secure) header.d=infradead.org header.i=@infradead.org header.a=rsa-sha256 header.s=casper.20170209 header.b=Jeyxv3ts; dkim-atps=neutral Received: from casper.infradead.org (casper.infradead.org [IPv6:2001:8b0:10b:1236::1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 4HpLqT3rJbz3058 for ; Tue, 9 Nov 2021 19:33:57 +1100 (AEDT) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=infradead.org; s=casper.20170209; h=Content-Transfer-Encoding:MIME-Version: References:In-Reply-To:Message-Id:Date:Subject:Cc:To:From:Sender:Reply-To: Content-Type:Content-ID:Content-Description; bh=mfMDb5n97/RHD98fzJck6QJCWRVIOtc8ifMZjDMd/kQ=; b=Jeyxv3tsyyzZnJxRVCO2TB86Ws w+QW/DSGu6mPXAbKWCOMHiAmNN5rK3FhaDN94URftiwooYE6Kz+gz8a1HfSlssB02QBDy9aJwX46c NDXerTZam1l2Ml3fw83VloMPreSlSXJm/jzRom9zjYEnt43pMde3L43bArtupfVvuk4O+f8AQph7l Kj3jYG42Lvn+DXbfwPw5jj3lpKQh72Cd06FD0JbEYC1NX2yES5mwAwZHyF2oVjSOtBAbNtBoXMeDR vbug0yVOpp8HDFIdvP9bfctKCkHC9LPNUxlsH4CvmgS1IONxvcj5qU2yhGCBnm1dXQO4vmrrrzMZ9 YK5BQzmw==; Received: from [2001:4bb8:19a:7ee7:fb46:2fe1:8652:d9d4] (helo=localhost) by casper.infradead.org with esmtpsa (Exim 4.94.2 #2 (Red Hat Linux)) id 1mkMZd-000s62-5h; Tue, 09 Nov 2021 08:33:46 +0000 From: Christoph Hellwig To: Dan Williams Subject: [PATCH 18/29] fsdax: decouple zeroing from the iomap buffered I/O code Date: Tue, 9 Nov 2021 09:32:58 +0100 Message-Id: <20211109083309.584081-19-hch@lst.de> X-Mailer: git-send-email 2.30.2 In-Reply-To: <20211109083309.584081-1-hch@lst.de> References: <20211109083309.584081-1-hch@lst.de> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-SRS-Rewrite: SMTP reverse-path rewritten from by casper.infradead.org. See http://www.infradead.org/rpr.html X-BeenThere: linux-erofs@lists.ozlabs.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Development of Linux EROFS file system List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: nvdimm@lists.linux.dev, Mike Snitzer , linux-s390@vger.kernel.org, linux-erofs@lists.ozlabs.org, virtualization@lists.linux-foundation.org, linux-xfs@vger.kernel.org, dm-devel@redhat.com, linux-fsdevel@vger.kernel.org, linux-ext4@vger.kernel.org, Ira Weiny Errors-To: linux-erofs-bounces+linux-erofs=archiver.kernel.org@lists.ozlabs.org Sender: "Linux-erofs" Unshare the DAX and iomap buffered I/O page zeroing code. This code previously did a IS_DAX check deep inside the iomap code, which in fact was the only DAX check in the code. Instead move these checks into the callers. Most callers already have DAX special casing anyway and XFS will need it for reflink support as well. Signed-off-by: Christoph Hellwig --- fs/dax.c | 77 ++++++++++++++++++++++++++++++++++-------- fs/ext2/inode.c | 6 ++-- fs/ext4/inode.c | 4 +-- fs/iomap/buffered-io.c | 35 +++++++------------ fs/xfs/xfs_iomap.c | 6 ++++ include/linux/dax.h | 6 +++- 6 files changed, 91 insertions(+), 43 deletions(-) diff --git a/fs/dax.c b/fs/dax.c index dc9ebeff850ab..5b52b878124ac 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1135,24 +1135,73 @@ static int dax_memzero(struct dax_device *dax_dev, pgoff_t pgoff, return rc; } -s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap) +static loff_t dax_zero_iter(struct iomap_iter *iter, bool *did_zero) { - pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); - long rc, id; - unsigned offset = offset_in_page(pos); - unsigned size = min_t(u64, PAGE_SIZE - offset, length); + const struct iomap *iomap = &iter->iomap; + const struct iomap *srcmap = iomap_iter_srcmap(iter); + loff_t pos = iter->pos; + loff_t length = iomap_length(iter); + loff_t written = 0; + + /* already zeroed? we're done. */ + if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) + return length; + + do { + unsigned offset = offset_in_page(pos); + unsigned size = min_t(u64, PAGE_SIZE - offset, length); + pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); + long rc; + int id; - id = dax_read_lock(); - if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE) - rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1); - else - rc = dax_memzero(iomap->dax_dev, pgoff, offset, size); - dax_read_unlock(id); + id = dax_read_lock(); + if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE) + rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1); + else + rc = dax_memzero(iomap->dax_dev, pgoff, offset, size); + dax_read_unlock(id); - if (rc < 0) - return rc; - return size; + if (rc < 0) + return rc; + pos += size; + length -= size; + written += size; + if (did_zero) + *did_zero = true; + } while (length > 0); + + return written; +} + +int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, + const struct iomap_ops *ops) +{ + struct iomap_iter iter = { + .inode = inode, + .pos = pos, + .len = len, + .flags = IOMAP_ZERO, + }; + int ret; + + while ((ret = iomap_iter(&iter, ops)) > 0) + iter.processed = dax_zero_iter(&iter, did_zero); + return ret; +} +EXPORT_SYMBOL_GPL(dax_zero_range); + +int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, + const struct iomap_ops *ops) +{ + unsigned int blocksize = i_blocksize(inode); + unsigned int off = pos & (blocksize - 1); + + /* Block boundary? Nothing to do */ + if (!off) + return 0; + return dax_zero_range(inode, pos, blocksize - off, did_zero, ops); } +EXPORT_SYMBOL_GPL(dax_truncate_page); static loff_t dax_iomap_iter(const struct iomap_iter *iomi, struct iov_iter *iter) diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 333fa62661d56..ae9993018a015 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1297,9 +1297,9 @@ static int ext2_setsize(struct inode *inode, loff_t newsize) inode_dio_wait(inode); if (IS_DAX(inode)) { - error = iomap_zero_range(inode, newsize, - PAGE_ALIGN(newsize) - newsize, NULL, - &ext2_iomap_ops); + error = dax_zero_range(inode, newsize, + PAGE_ALIGN(newsize) - newsize, NULL, + &ext2_iomap_ops); } else if (test_opt(inode->i_sb, NOBH)) error = nobh_truncate_page(inode->i_mapping, newsize, ext2_get_block); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0f06305167d5a..8c443b753b815 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3783,8 +3783,8 @@ static int ext4_block_zero_page_range(handle_t *handle, length = max; if (IS_DAX(inode)) { - return iomap_zero_range(inode, from, length, NULL, - &ext4_iomap_ops); + return dax_zero_range(inode, from, length, NULL, + &ext4_iomap_ops); } return __ext4_block_zero_page_range(handle, mapping, from, length); } diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 1753c26c8e76e..b1511255b4df8 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -870,26 +870,8 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, } EXPORT_SYMBOL_GPL(iomap_file_unshare); -static s64 __iomap_zero_iter(struct iomap_iter *iter, loff_t pos, u64 length) -{ - struct page *page; - int status; - unsigned offset = offset_in_page(pos); - unsigned bytes = min_t(u64, PAGE_SIZE - offset, length); - - status = iomap_write_begin(iter, pos, bytes, &page); - if (status) - return status; - - zero_user(page, offset, bytes); - mark_page_accessed(page); - - return iomap_write_end(iter, pos, bytes, bytes, page); -} - static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) { - struct iomap *iomap = &iter->iomap; const struct iomap *srcmap = iomap_iter_srcmap(iter); loff_t pos = iter->pos; loff_t length = iomap_length(iter); @@ -900,12 +882,19 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) return length; do { - s64 bytes; + unsigned offset = offset_in_page(pos); + size_t bytes = min_t(u64, PAGE_SIZE - offset, length); + struct page *page; + int status; - if (IS_DAX(iter->inode)) - bytes = dax_iomap_zero(pos, length, iomap); - else - bytes = __iomap_zero_iter(iter, pos, length); + status = iomap_write_begin(iter, pos, bytes, &page); + if (status) + return status; + + zero_user(page, offset, bytes); + mark_page_accessed(page); + + bytes = iomap_write_end(iter, pos, bytes, bytes, page); if (bytes < 0) return bytes; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index d6d71ae9f2ae4..604000b6243ec 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1321,6 +1321,9 @@ xfs_zero_range( { struct inode *inode = VFS_I(ip); + if (IS_DAX(inode)) + return dax_zero_range(inode, pos, len, did_zero, + &xfs_buffered_write_iomap_ops); return iomap_zero_range(inode, pos, len, did_zero, &xfs_buffered_write_iomap_ops); } @@ -1333,6 +1336,9 @@ xfs_truncate_page( { struct inode *inode = VFS_I(ip); + if (IS_DAX(inode)) + return dax_truncate_page(inode, pos, did_zero, + &xfs_buffered_write_iomap_ops); return iomap_truncate_page(inode, pos, did_zero, &xfs_buffered_write_iomap_ops); } diff --git a/include/linux/dax.h b/include/linux/dax.h index 324363b798ecd..a5cc2f1aa840e 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -14,6 +14,7 @@ typedef unsigned long dax_entry_t; struct dax_device; struct gendisk; struct iomap_ops; +struct iomap_iter; struct iomap; struct dax_operations { @@ -124,6 +125,10 @@ struct page *dax_layout_busy_page(struct address_space *mapping); struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end); dax_entry_t dax_lock_page(struct page *page); void dax_unlock_page(struct page *page, dax_entry_t cookie); +int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, + const struct iomap_ops *ops); +int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, + const struct iomap_ops *ops); #else static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk) { @@ -204,7 +209,6 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); -s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap); static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); -- 2.30.2 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 3404AC433F5 for ; Tue, 9 Nov 2021 09:00:41 +0000 (UTC) Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id BF87A61057 for ; Tue, 9 Nov 2021 09:00:40 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.1 mail.kernel.org BF87A61057 Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=lst.de Authentication-Results: mail.kernel.org; spf=tempfail smtp.mailfrom=redhat.com Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-281-EJNlc33wOaqDwd-jznFAKA-1; Tue, 09 Nov 2021 04:00:38 -0500 X-MC-Unique: EJNlc33wOaqDwd-jznFAKA-1 Received: from smtp.corp.redhat.com (int-mx07.intmail.prod.int.phx2.redhat.com [10.5.11.22]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id E484E1023F53; Tue, 9 Nov 2021 09:00:33 +0000 (UTC) Received: from colo-mx.corp.redhat.com (colo-mx02.intmail.prod.int.phx2.redhat.com [10.5.11.21]) by smtp.corp.redhat.com (Postfix) with ESMTPS id CB53E1048102; Tue, 9 Nov 2021 09:00:31 +0000 (UTC) Received: from lists01.pubmisc.prod.ext.phx2.redhat.com (lists01.pubmisc.prod.ext.phx2.redhat.com [10.5.19.33]) by colo-mx.corp.redhat.com (Postfix) with ESMTP id 777994EA37; Tue, 9 Nov 2021 09:00:31 +0000 (UTC) Received: from smtp.corp.redhat.com (int-mx01.intmail.prod.int.rdu2.redhat.com [10.11.54.1]) by lists01.pubmisc.prod.ext.phx2.redhat.com (8.13.8/8.13.8) with ESMTP id 1A98xX4i017425 for ; Tue, 9 Nov 2021 03:59:34 -0500 Received: by smtp.corp.redhat.com (Postfix) id CFEFF40CFD10; Tue, 9 Nov 2021 08:59:33 +0000 (UTC) Received: from mimecast-mx02.redhat.com (mimecast02.extmail.prod.ext.rdu2.redhat.com [10.11.55.18]) by smtp.corp.redhat.com (Postfix) with ESMTPS id CB48C40CFD02 for ; Tue, 9 Nov 2021 08:59:33 +0000 (UTC) Received: from us-smtp-1.mimecast.com (us-smtp-1.mimecast.com [207.211.31.81]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 6D1E4801212 for ; Tue, 9 Nov 2021 08:59:33 +0000 (UTC) Received: from casper.infradead.org (casper.infradead.org [90.155.50.34]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-361-j4et8X9NO5CUREAfA-SsWw-1; Tue, 09 Nov 2021 03:59:32 -0500 X-MC-Unique: j4et8X9NO5CUREAfA-SsWw-1 Received: from [2001:4bb8:19a:7ee7:fb46:2fe1:8652:d9d4] (helo=localhost) by casper.infradead.org with esmtpsa (Exim 4.94.2 #2 (Red Hat Linux)) id 1mkMZd-000s62-5h; Tue, 09 Nov 2021 08:33:46 +0000 From: Christoph Hellwig To: Dan Williams Date: Tue, 9 Nov 2021 09:32:58 +0100 Message-Id: <20211109083309.584081-19-hch@lst.de> In-Reply-To: <20211109083309.584081-1-hch@lst.de> References: <20211109083309.584081-1-hch@lst.de> MIME-Version: 1.0 X-SRS-Rewrite: SMTP reverse-path rewritten from by casper.infradead.org. See http://www.infradead.org/rpr.html X-Mimecast-Impersonation-Protect: Policy=CLT - Impersonation Protection Definition; Similar Internal Domain=false; Similar Monitored External Domain=false; Custom External Domain=false; Mimecast External Domain=false; Newly Observed Domain=false; Internal User Name=false; Custom Display Name List=false; Reply-to Address Mismatch=false; Targeted Threat Dictionary=false; Mimecast Threat Dictionary=false; Custom Threat Dictionary=false X-Scanned-By: MIMEDefang 2.84 on 10.11.54.1 X-loop: dm-devel@redhat.com Cc: nvdimm@lists.linux.dev, Mike Snitzer , linux-s390@vger.kernel.org, linux-erofs@lists.ozlabs.org, virtualization@lists.linux-foundation.org, linux-xfs@vger.kernel.org, dm-devel@redhat.com, linux-fsdevel@vger.kernel.org, linux-ext4@vger.kernel.org, Ira Weiny Subject: [dm-devel] [PATCH 18/29] fsdax: decouple zeroing from the iomap buffered I/O code X-BeenThere: dm-devel@redhat.com X-Mailman-Version: 2.1.12 Precedence: junk List-Id: device-mapper development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: dm-devel-bounces@redhat.com Errors-To: dm-devel-bounces@redhat.com X-Scanned-By: MIMEDefang 2.84 on 10.5.11.22 Authentication-Results: relay.mimecast.com; auth=pass smtp.auth=CUSA124A263 smtp.mailfrom=dm-devel-bounces@redhat.com X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Unshare the DAX and iomap buffered I/O page zeroing code. This code previously did a IS_DAX check deep inside the iomap code, which in fact was the only DAX check in the code. Instead move these checks into the callers. Most callers already have DAX special casing anyway and XFS will need it for reflink support as well. Signed-off-by: Christoph Hellwig --- fs/dax.c | 77 ++++++++++++++++++++++++++++++++++-------- fs/ext2/inode.c | 6 ++-- fs/ext4/inode.c | 4 +-- fs/iomap/buffered-io.c | 35 +++++++------------ fs/xfs/xfs_iomap.c | 6 ++++ include/linux/dax.h | 6 +++- 6 files changed, 91 insertions(+), 43 deletions(-) diff --git a/fs/dax.c b/fs/dax.c index dc9ebeff850ab..5b52b878124ac 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1135,24 +1135,73 @@ static int dax_memzero(struct dax_device *dax_dev, pgoff_t pgoff, return rc; } -s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap) +static loff_t dax_zero_iter(struct iomap_iter *iter, bool *did_zero) { - pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); - long rc, id; - unsigned offset = offset_in_page(pos); - unsigned size = min_t(u64, PAGE_SIZE - offset, length); + const struct iomap *iomap = &iter->iomap; + const struct iomap *srcmap = iomap_iter_srcmap(iter); + loff_t pos = iter->pos; + loff_t length = iomap_length(iter); + loff_t written = 0; + + /* already zeroed? we're done. */ + if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) + return length; + + do { + unsigned offset = offset_in_page(pos); + unsigned size = min_t(u64, PAGE_SIZE - offset, length); + pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); + long rc; + int id; - id = dax_read_lock(); - if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE) - rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1); - else - rc = dax_memzero(iomap->dax_dev, pgoff, offset, size); - dax_read_unlock(id); + id = dax_read_lock(); + if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE) + rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1); + else + rc = dax_memzero(iomap->dax_dev, pgoff, offset, size); + dax_read_unlock(id); - if (rc < 0) - return rc; - return size; + if (rc < 0) + return rc; + pos += size; + length -= size; + written += size; + if (did_zero) + *did_zero = true; + } while (length > 0); + + return written; +} + +int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, + const struct iomap_ops *ops) +{ + struct iomap_iter iter = { + .inode = inode, + .pos = pos, + .len = len, + .flags = IOMAP_ZERO, + }; + int ret; + + while ((ret = iomap_iter(&iter, ops)) > 0) + iter.processed = dax_zero_iter(&iter, did_zero); + return ret; +} +EXPORT_SYMBOL_GPL(dax_zero_range); + +int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, + const struct iomap_ops *ops) +{ + unsigned int blocksize = i_blocksize(inode); + unsigned int off = pos & (blocksize - 1); + + /* Block boundary? Nothing to do */ + if (!off) + return 0; + return dax_zero_range(inode, pos, blocksize - off, did_zero, ops); } +EXPORT_SYMBOL_GPL(dax_truncate_page); static loff_t dax_iomap_iter(const struct iomap_iter *iomi, struct iov_iter *iter) diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 333fa62661d56..ae9993018a015 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1297,9 +1297,9 @@ static int ext2_setsize(struct inode *inode, loff_t newsize) inode_dio_wait(inode); if (IS_DAX(inode)) { - error = iomap_zero_range(inode, newsize, - PAGE_ALIGN(newsize) - newsize, NULL, - &ext2_iomap_ops); + error = dax_zero_range(inode, newsize, + PAGE_ALIGN(newsize) - newsize, NULL, + &ext2_iomap_ops); } else if (test_opt(inode->i_sb, NOBH)) error = nobh_truncate_page(inode->i_mapping, newsize, ext2_get_block); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 0f06305167d5a..8c443b753b815 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3783,8 +3783,8 @@ static int ext4_block_zero_page_range(handle_t *handle, length = max; if (IS_DAX(inode)) { - return iomap_zero_range(inode, from, length, NULL, - &ext4_iomap_ops); + return dax_zero_range(inode, from, length, NULL, + &ext4_iomap_ops); } return __ext4_block_zero_page_range(handle, mapping, from, length); } diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 1753c26c8e76e..b1511255b4df8 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -870,26 +870,8 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, } EXPORT_SYMBOL_GPL(iomap_file_unshare); -static s64 __iomap_zero_iter(struct iomap_iter *iter, loff_t pos, u64 length) -{ - struct page *page; - int status; - unsigned offset = offset_in_page(pos); - unsigned bytes = min_t(u64, PAGE_SIZE - offset, length); - - status = iomap_write_begin(iter, pos, bytes, &page); - if (status) - return status; - - zero_user(page, offset, bytes); - mark_page_accessed(page); - - return iomap_write_end(iter, pos, bytes, bytes, page); -} - static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) { - struct iomap *iomap = &iter->iomap; const struct iomap *srcmap = iomap_iter_srcmap(iter); loff_t pos = iter->pos; loff_t length = iomap_length(iter); @@ -900,12 +882,19 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) return length; do { - s64 bytes; + unsigned offset = offset_in_page(pos); + size_t bytes = min_t(u64, PAGE_SIZE - offset, length); + struct page *page; + int status; - if (IS_DAX(iter->inode)) - bytes = dax_iomap_zero(pos, length, iomap); - else - bytes = __iomap_zero_iter(iter, pos, length); + status = iomap_write_begin(iter, pos, bytes, &page); + if (status) + return status; + + zero_user(page, offset, bytes); + mark_page_accessed(page); + + bytes = iomap_write_end(iter, pos, bytes, bytes, page); if (bytes < 0) return bytes; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index d6d71ae9f2ae4..604000b6243ec 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1321,6 +1321,9 @@ xfs_zero_range( { struct inode *inode = VFS_I(ip); + if (IS_DAX(inode)) + return dax_zero_range(inode, pos, len, did_zero, + &xfs_buffered_write_iomap_ops); return iomap_zero_range(inode, pos, len, did_zero, &xfs_buffered_write_iomap_ops); } @@ -1333,6 +1336,9 @@ xfs_truncate_page( { struct inode *inode = VFS_I(ip); + if (IS_DAX(inode)) + return dax_truncate_page(inode, pos, did_zero, + &xfs_buffered_write_iomap_ops); return iomap_truncate_page(inode, pos, did_zero, &xfs_buffered_write_iomap_ops); } diff --git a/include/linux/dax.h b/include/linux/dax.h index 324363b798ecd..a5cc2f1aa840e 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -14,6 +14,7 @@ typedef unsigned long dax_entry_t; struct dax_device; struct gendisk; struct iomap_ops; +struct iomap_iter; struct iomap; struct dax_operations { @@ -124,6 +125,10 @@ struct page *dax_layout_busy_page(struct address_space *mapping); struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end); dax_entry_t dax_lock_page(struct page *page); void dax_unlock_page(struct page *page, dax_entry_t cookie); +int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, + const struct iomap_ops *ops); +int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, + const struct iomap_ops *ops); #else static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk) { @@ -204,7 +209,6 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); -s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap); static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); -- 2.30.2 -- dm-devel mailing list dm-devel@redhat.com https://listman.redhat.com/mailman/listinfo/dm-devel