linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: xfs@oss.sgi.com
Cc: rpeterso@redhat.com, vishal.l.verma@intel.com,
	linux-fsdevel@vger.kernel.org
Subject: [PATCH 01/15] dax: export a low-level __dax_zero_page_range helper
Date: Mon,  9 May 2016 10:47:04 +0200	[thread overview]
Message-ID: <1462783638-4968-2-git-send-email-hch@lst.de> (raw)
In-Reply-To: <1462783638-4968-1-git-send-email-hch@lst.de>

This allows XFS to perform zeroing using the iomap infrastructure and
avoid buffer heads.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/dax.c            | 35 ++++++++++++++++++++---------------
 include/linux/dax.h |  7 +++++++
 2 files changed, 27 insertions(+), 15 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index 90322eb..6d5d744 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1082,6 +1082,23 @@ int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 }
 EXPORT_SYMBOL_GPL(dax_pfn_mkwrite);
 
+int __dax_zero_page_range(struct block_device *bdev, sector_t sector,
+		unsigned int offset, unsigned int length)
+{
+	struct blk_dax_ctl dax = {
+		.sector		= sector,
+		.size		= PAGE_CACHE_SIZE,
+	};
+
+	if (dax_map_atomic(bdev, &dax) < 0)
+		return PTR_ERR(dax.addr);
+	clear_pmem(dax.addr + offset, length);
+	wmb_pmem();
+	dax_unmap_atomic(bdev, &dax);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__dax_zero_page_range);
+
 /**
  * dax_zero_page_range - zero a range within a page of a DAX file
  * @inode: The file being truncated
@@ -1117,23 +1134,11 @@ int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length,
 	bh.b_bdev = inode->i_sb->s_bdev;
 	bh.b_size = PAGE_CACHE_SIZE;
 	err = get_block(inode, index, &bh, 0);
-	if (err < 0)
+	if (err < 0 || !buffer_written(&bh))
 		return err;
-	if (buffer_written(&bh)) {
-		struct block_device *bdev = bh.b_bdev;
-		struct blk_dax_ctl dax = {
-			.sector = to_sector(&bh, inode),
-			.size = PAGE_CACHE_SIZE,
-		};
 
-		if (dax_map_atomic(bdev, &dax) < 0)
-			return PTR_ERR(dax.addr);
-		clear_pmem(dax.addr + offset, length);
-		wmb_pmem();
-		dax_unmap_atomic(bdev, &dax);
-	}
-
-	return 0;
+	return __dax_zero_page_range(bh.b_bdev, to_sector(&bh, inode),
+			offset, length);
 }
 EXPORT_SYMBOL_GPL(dax_zero_page_range);
 
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 636dd59..8155b81 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -17,12 +17,19 @@ int __dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t,
 
 #ifdef CONFIG_FS_DAX
 struct page *read_dax_sector(struct block_device *bdev, sector_t n);
+int __dax_zero_page_range(struct block_device *bdev, sector_t sector,
+		unsigned int offset, unsigned int length);
 #else
 static inline struct page *read_dax_sector(struct block_device *bdev,
 		sector_t n)
 {
 	return ERR_PTR(-ENXIO);
 }
+static inline int __dax_zero_page_range(struct block_device *bdev,
+		sector_t sector, unsigned int offset, unsigned int length)
+{
+	return -ENXIO;
+}
 #endif
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-- 
2.1.4


  reply	other threads:[~2016-05-09  8:47 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-05-09  8:47 iomap infrastructure and multipage writes V4 Christoph Hellwig
2016-05-09  8:47 ` Christoph Hellwig [this message]
2016-05-11 22:43   ` [PATCH 01/15] dax: export a low-level __dax_zero_page_range helper Verma, Vishal L
2016-05-09  8:47 ` [PATCH 02/15] fs: move struct iomap from exportfs.h to a separate header Christoph Hellwig
2016-05-09  8:47 ` [PATCH 03/15] fs: introduce iomap infrastructure Christoph Hellwig
2016-05-09  8:47 ` [PATCH 04/15] fs: support DAX based iomap zeroing Christoph Hellwig
2016-05-09  8:47 ` [PATCH 05/15] xfs: make xfs_bmbt_to_iomap available outside of xfs_pnfs.c Christoph Hellwig
2016-05-09  8:47 ` [PATCH 06/15] xfs: reorder zeroing and flushing sequence in truncate Christoph Hellwig
2016-05-09  8:47 ` [PATCH 07/15] xfs: implement iomap based buffered write path Christoph Hellwig
2016-05-09  8:47 ` [PATCH 08/15] xfs: remove buffered write support from __xfs_get_blocks Christoph Hellwig
2016-05-09  8:47 ` [PATCH 09/15] fs: iomap based fiemap implementation Christoph Hellwig
2016-05-23 20:09   ` Bob Peterson
2016-05-24 13:10     ` Christoph Hellwig
2016-05-26 18:19       ` Bob Peterson
2016-05-26 22:57         ` Dave Chinner
2016-05-09  8:47 ` [PATCH 10/15] xfs: use iomap " Christoph Hellwig
2016-05-09  8:47 ` [PATCH 11/15] xfs: use iomap infrastructure for DAX zeroing Christoph Hellwig
2016-05-09  8:47 ` [PATCH 12/15] xfs: handle 64-bit length in xfs_iozero Christoph Hellwig
2016-05-09  8:47 ` [PATCH 13/15] xfs: use xfs_zero_range in xfs_zero_eof Christoph Hellwig
2016-05-09  8:47 ` [PATCH 14/15] xfs: split xfs_free_file_space in manageable pieces Christoph Hellwig
2016-05-09  8:47 ` [PATCH 15/15] xfs: kill xfs_zero_remaining_bytes Christoph Hellwig
2016-05-11 22:42 ` iomap infrastructure and multipage writes V4 Verma, Vishal L
2016-06-01  6:35 ` Dave Chinner
2016-06-01 12:31   ` Christoph Hellwig

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1462783638-4968-2-git-send-email-hch@lst.de \
    --to=hch@lst.de \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=rpeterso@redhat.com \
    --cc=vishal.l.verma@intel.com \
    --cc=xfs@oss.sgi.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).