linux-nvdimm.lists.01.org archive mirror
 help / color / mirror / Atom feed
From: Shiyang Ruan <ruansy.fnst@fujitsu.com>
To: <linux-kernel@vger.kernel.org>, <linux-xfs@vger.kernel.org>,
	<linux-nvdimm@lists.01.org>, <linux-fsdevel@vger.kernel.org>
Cc: darrick.wong@oracle.com, willy@infradead.org,
	viro@zeniv.linux.org.uk, david@fromorbit.com, hch@lst.de,
	rgoldwyn@suse.de, "Darrick J . Wong" <djwong@kernel.org>
Subject: [PATCH v6 1/7] fsdax: Introduce dax_iomap_cow_copy()
Date: Wed, 19 May 2021 14:00:39 +0800	[thread overview]
Message-ID: <20210519060045.1051226-2-ruansy.fnst@fujitsu.com> (raw)
In-Reply-To: <20210519060045.1051226-1-ruansy.fnst@fujitsu.com>

In the case where the iomap is a write operation and iomap is not equal
to srcmap after iomap_begin, we consider it is a CoW operation.

The destance extent which iomap indicated is new allocated extent.
So, it is needed to copy the data from srcmap to new allocated extent.
In theory, it is better to copy the head and tail ranges which is
outside of the non-aligned area instead of copying the whole aligned
range. But in dax page fault, it will always be an aligned range.  So,
we have to copy the whole range in this case.

Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
---
 fs/dax.c | 86 ++++++++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 81 insertions(+), 5 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index f661227b49cd..6396f091e60b 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1049,6 +1049,61 @@ static int dax_iomap_direct_access(struct iomap *iomap, loff_t pos, size_t size,
 	return rc;
 }
 
+/**
+ * dax_iomap_cow_copy(): Copy the data from source to destination before write.
+ * @pos:	address to do copy from.
+ * @length:	size of copy operation.
+ * @align_size:	aligned w.r.t align_size (either PMD_SIZE or PAGE_SIZE)
+ * @srcmap:	iomap srcmap
+ * @daddr:	destination address to copy to.
+ *
+ * This can be called from two places. Either during DAX write fault, to copy
+ * the length size data to daddr. Or, while doing normal DAX write operation,
+ * dax_iomap_actor() might call this to do the copy of either start or end
+ * unaligned address. In this case the rest of the copy of aligned ranges is
+ * taken care by dax_iomap_actor() itself.
+ * Also, note DAX fault will always result in aligned pos and pos + length.
+ */
+static int dax_iomap_cow_copy(loff_t pos, uint64_t length, size_t align_size,
+		struct iomap *srcmap, void *daddr)
+{
+	loff_t head_off = pos & (align_size - 1);
+	size_t size = ALIGN(head_off + length, align_size);
+	loff_t end = pos + length;
+	loff_t pg_end = round_up(end, align_size);
+	bool copy_all = head_off == 0 && end == pg_end;
+	void *saddr = 0;
+	int ret = 0;
+
+	ret = dax_iomap_direct_access(srcmap, pos, size, &saddr, NULL);
+	if (ret)
+		return ret;
+
+	if (copy_all) {
+		ret = copy_mc_to_kernel(daddr, saddr, length);
+		return ret ? -EIO : 0;
+	}
+
+	/* Copy the head part of the range.  Note: we pass offset as length. */
+	if (head_off) {
+		ret = copy_mc_to_kernel(daddr, saddr, head_off);
+		if (ret)
+			return -EIO;
+	}
+
+	/* Copy the tail part of the range */
+	if (end < pg_end) {
+		loff_t tail_off = head_off + length;
+		loff_t tail_len = pg_end - end;
+
+		ret = copy_mc_to_kernel(daddr + tail_off, saddr + tail_off,
+					tail_len);
+		if (ret)
+			return -EIO;
+	}
+	return 0;
+}
+
 /*
  * The user has performed a load from a hole in the file.  Allocating a new
  * page in the file would cause excessive storage usage for workloads with
@@ -1178,11 +1233,12 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 	struct dax_device *dax_dev = iomap->dax_dev;
 	struct iov_iter *iter = data;
 	loff_t end = pos + length, done = 0;
+	bool write = iov_iter_rw(iter) == WRITE;
 	ssize_t ret = 0;
 	size_t xfer;
 	int id;
 
-	if (iov_iter_rw(iter) == READ) {
+	if (!write) {
 		end = min(end, i_size_read(inode));
 		if (pos >= end)
 			return 0;
@@ -1191,7 +1247,12 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 			return iov_iter_zero(min(length, end - pos), iter);
 	}
 
-	if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED))
+	/*
+	 * In DAX mode, we allow either pure overwrites of written extents, or
+	 * writes to unwritten extents as part of a copy-on-write operation.
+	 */
+	if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED &&
+			!(iomap->flags & IOMAP_F_SHARED)))
 		return -EIO;
 
 	/*
@@ -1230,6 +1291,13 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 			break;
 		}
 
+		if (write && srcmap->addr != iomap->addr) {
+			ret = dax_iomap_cow_copy(pos, length, PAGE_SIZE, srcmap,
+						 kaddr);
+			if (ret)
+				break;
+		}
+
 		map_len = PFN_PHYS(map_len);
 		kaddr += offset;
 		map_len -= offset;
@@ -1241,7 +1309,7 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		 * validated via access_ok() in either vfs_read() or
 		 * vfs_write(), depending on which operation we are doing.
 		 */
-		if (iov_iter_rw(iter) == WRITE)
+		if (write)
 			xfer = dax_copy_from_iter(dax_dev, pgoff, kaddr,
 					map_len, iter);
 		else
@@ -1393,6 +1461,7 @@ static vm_fault_t dax_fault_actor(struct vm_fault *vmf, pfn_t *pfnp,
 	unsigned long entry_flags = pmd ? DAX_PMD : 0;
 	int err = 0;
 	pfn_t pfn;
+	void *kaddr;
 
 	/* if we are reading UNWRITTEN and HOLE, return a hole. */
 	if (!write &&
@@ -1403,18 +1472,25 @@ static vm_fault_t dax_fault_actor(struct vm_fault *vmf, pfn_t *pfnp,
 			return dax_pmd_load_hole(xas, vmf, iomap, entry);
 	}
 
-	if (iomap->type != IOMAP_MAPPED) {
+	if (iomap->type != IOMAP_MAPPED && !(iomap->flags & IOMAP_F_SHARED)) {
 		WARN_ON_ONCE(1);
 		return pmd ? VM_FAULT_FALLBACK : VM_FAULT_SIGBUS;
 	}
 
-	err = dax_iomap_direct_access(iomap, pos, size, NULL, &pfn);
+	err = dax_iomap_direct_access(iomap, pos, size, &kaddr, &pfn);
 	if (err)
 		return pmd ? VM_FAULT_FALLBACK : dax_fault_return(err);
 
 	*entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn, entry_flags,
 				  write && !sync);
 
+	if (write &&
+	    srcmap->addr != IOMAP_HOLE && srcmap->addr != iomap->addr) {
+		err = dax_iomap_cow_copy(pos, size, size, srcmap, kaddr);
+		if (err)
+			return dax_fault_return(err);
+	}
+
 	if (sync)
 		return dax_fault_synchronous_pfnp(pfnp, pfn);
 
-- 
2.31.1


_______________________________________________
Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org
To unsubscribe send an email to linux-nvdimm-leave@lists.01.org

  reply	other threads:[~2021-05-19  6:01 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-05-19  6:00 [PATCH v6 0/7] fsdax,xfs: Add reflink&dedupe support for fsdax Shiyang Ruan
2021-05-19  6:00 ` Shiyang Ruan [this message]
2021-05-19  6:00 ` [PATCH v6 2/7] fsdax: Replace mmap entry in case of CoW Shiyang Ruan
2021-05-19  6:00 ` [PATCH v6 3/7] fsdax: Add dax_iomap_cow_copy() for dax_iomap_zero Shiyang Ruan
2021-05-19  6:00 ` [PATCH v6 4/7] iomap: Introduce iomap_apply2() for operations on two files Shiyang Ruan
2021-05-19  6:00 ` [PATCH v6 5/7] fsdax: Dedup file range to use a compare function Shiyang Ruan
2021-05-19  6:00 ` [PATCH v6 6/7] fs/xfs: Handle CoW for fsdax write() path Shiyang Ruan
2021-05-19  6:00 ` [PATCH v6 7/7] fs/xfs: Add dax dedupe support Shiyang Ruan

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=20210519060045.1051226-2-ruansy.fnst@fujitsu.com \
    --to=ruansy.fnst@fujitsu.com \
    --cc=darrick.wong@oracle.com \
    --cc=david@fromorbit.com \
    --cc=djwong@kernel.org \
    --cc=hch@lst.de \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=rgoldwyn@suse.de \
    --cc=viro@zeniv.linux.org.uk \
    --cc=willy@infradead.org \
    --subject='Re: [PATCH v6 1/7] fsdax: Introduce dax_iomap_cow_copy()' \
    /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

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).