Linux-NVDIMM Archive on lore.kernel.org
 help / color / Atom feed
From: Shiyang Ruan <ruansy.fnst@cn.fujitsu.com>
To: linux-xfs@vger.kernel.org, linux-nvdimm@lists.01.org,
	darrick.wong@oracle.com
Cc: qi.fuli@fujitsu.com, gujx@cn.fujitsu.com, rgoldwyn@suse.de,
	david@fromorbit.com, linux-kernel@vger.kernel.org
Subject: [RFC PATCH 2/7] dax: copy data before write.
Date: Wed, 31 Jul 2019 19:49:30 +0800
Message-ID: <20190731114935.11030-3-ruansy.fnst@cn.fujitsu.com> (raw)
In-Reply-To: <20190731114935.11030-1-ruansy.fnst@cn.fujitsu.com>

Add dax_copy_edges() into each dax actor functions to perform COW in the
case of IOMAP_COW type is set.

Signed-off-by: Shiyang Ruan <ruansy.fnst@cn.fujitsu.com>
---
 fs/dax.c | 39 +++++++++++++++++++++++++++++++++------
 1 file changed, 33 insertions(+), 6 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index 450baafe2ea4..084cc21d47a4 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1098,11 +1098,12 @@ EXPORT_SYMBOL_GPL(__dax_zero_page_range);
  * 		    offset/offset+length are not page aligned.
  */
 static int dax_copy_edges(struct inode *inode, loff_t pos, loff_t length,
-			  struct iomap *srcmap, void *daddr)
+			  struct iomap *srcmap, void *daddr, bool pmd)
 {
-	unsigned offset = pos & (PAGE_SIZE - 1);
+	size_t page_size = pmd ? PMD_SIZE : PAGE_SIZE;
+	unsigned offset = pos & (page_size - 1);
 	loff_t end = pos + length;
-	loff_t pg_end = round_up(end, PAGE_SIZE);
+	loff_t pg_end = round_up(end, page_size);
 	void *saddr = 0;
 	int ret = 0;
 
@@ -1153,7 +1154,8 @@ 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))
+	if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED &&
+			 iomap->type != IOMAP_COW))
 		return -EIO;
 
 	/*
@@ -1192,6 +1194,13 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 			break;
 		}
 
+		if (iomap->type == IOMAP_COW) {
+			ret = dax_copy_edges(inode, pos, length, srcmap, kaddr,
+					     false);
+			if (ret)
+				break;
+		}
+
 		map_len = PFN_PHYS(map_len);
 		kaddr += offset;
 		map_len -= offset;
@@ -1300,6 +1309,7 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	vm_fault_t ret = 0;
 	void *entry;
 	pfn_t pfn;
+	void *kaddr;
 
 	trace_dax_pte_fault(inode, vmf, ret);
 	/*
@@ -1380,19 +1390,27 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	sync = dax_fault_is_synchronous(flags, vma, &iomap);
 
 	switch (iomap.type) {
+	case IOMAP_COW:
 	case IOMAP_MAPPED:
 		if (iomap.flags & IOMAP_F_NEW) {
 			count_vm_event(PGMAJFAULT);
 			count_memcg_event_mm(vma->vm_mm, PGMAJFAULT);
 			major = VM_FAULT_MAJOR;
 		}
-		error = dax_iomap_pfn(&iomap, pos, PAGE_SIZE, &pfn, NULL);
+		error = dax_iomap_pfn(&iomap, pos, PAGE_SIZE, &pfn, &kaddr);
 		if (error < 0)
 			goto error_finish_iomap;
 
 		entry = dax_insert_entry(&xas, mapping, vmf, entry, pfn,
 						 0, write && !sync);
 
+		if (iomap.type == IOMAP_COW) {
+			error = dax_copy_edges(inode, pos, PAGE_SIZE, &srcmap,
+					       kaddr, false);
+			if (error)
+				goto error_finish_iomap;
+		}
+
 		/*
 		 * If we are doing synchronous page fault and inode needs fsync,
 		 * we can insert PTE into page tables only after that happens.
@@ -1523,6 +1541,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	loff_t pos;
 	int error;
 	pfn_t pfn;
+	void *kaddr;
 
 	/*
 	 * Check whether offset isn't beyond end of file now. Caller is
@@ -1602,14 +1621,22 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	sync = dax_fault_is_synchronous(iomap_flags, vma, &iomap);
 
 	switch (iomap.type) {
+	case IOMAP_COW:
 	case IOMAP_MAPPED:
-		error = dax_iomap_pfn(&iomap, pos, PMD_SIZE, &pfn, NULL);
+		error = dax_iomap_pfn(&iomap, pos, PMD_SIZE, &pfn, &kaddr);
 		if (error < 0)
 			goto finish_iomap;
 
 		entry = dax_insert_entry(&xas, mapping, vmf, entry, pfn,
 						DAX_PMD, write && !sync);
 
+		if (iomap.type == IOMAP_COW) {
+			error = dax_copy_edges(inode, pos, PMD_SIZE, &srcmap,
+					       kaddr, true);
+			if (error)
+				goto unlock_entry;
+		}
+
 		/*
 		 * If we are doing synchronous page fault and inode needs fsync,
 		 * we can insert PMD into page tables only after that happens.
-- 
2.17.0



_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm

  parent reply index

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-07-31 11:49 [RFC PATCH 0/7] xfs: add reflink & dedupe support for fsdax Shiyang Ruan
2019-07-31 11:49 ` [RFC PATCH 1/7] dax: Introduce dax_copy_edges() for COW Shiyang Ruan
2019-07-31 11:49 ` Shiyang Ruan [this message]
2019-07-31 11:49 ` [RFC PATCH 3/7] dax: replace mmap entry in case of CoW Shiyang Ruan
2019-07-31 11:49 ` [RFC PATCH 4/7] fs: dedup file range to use a compare function Shiyang Ruan
2019-07-31 11:49 ` [RFC PATCH 5/7] dax: memcpy before zeroing range Shiyang Ruan
2019-07-31 11:49 ` [RFC PATCH 6/7] xfs: Add COW handle for fsdax Shiyang Ruan
2019-07-31 11:49 ` [RFC PATCH 7/7] xfs: Add dedupe support " Shiyang Ruan
2019-07-31 20:33 ` [RFC PATCH 0/7] xfs: add reflink & " Goldwyn Rodrigues
2019-08-01  1:37   ` Shiyang Ruan
2019-08-05  0:21     ` Dave Chinner
2019-10-09  6:31 ` Christoph Hellwig
2019-10-09 17:11   ` Darrick J. Wong
2019-10-10  7:30     ` Dave Chinner

Reply instructions:

You may reply publically 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=20190731114935.11030-3-ruansy.fnst@cn.fujitsu.com \
    --to=ruansy.fnst@cn.fujitsu.com \
    --cc=darrick.wong@oracle.com \
    --cc=david@fromorbit.com \
    --cc=gujx@cn.fujitsu.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=qi.fuli@fujitsu.com \
    --cc=rgoldwyn@suse.de \
    /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

Linux-NVDIMM Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-nvdimm/0 linux-nvdimm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-nvdimm linux-nvdimm/ https://lore.kernel.org/linux-nvdimm \
		linux-nvdimm@lists.01.org
	public-inbox-index linux-nvdimm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.01.lists.linux-nvdimm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git