Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
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>, <dan.j.williams@intel.com>,
        <willy@infradead.org>, <jack@suse.cz>, <viro@zeniv.linux.org.uk>,
        <linux-btrfs@vger.kernel.org>, <ocfs2-devel@oss.oracle.com>,
        <david@fromorbit.com>, <hch@lst.de>, <rgoldwyn@suse.de>,
        Goldwyn Rodrigues <rgoldwyn@suse.com>
Subject: [PATCH v2 05/10] fsdax: Replace mmap entry in case of CoW
Date:   Fri, 26 Feb 2021 08:20:25 +0800
Message-ID: <20210226002030.653855-6-ruansy.fnst@fujitsu.com>
In-Reply-To: <20210226002030.653855-1-ruansy.fnst@fujitsu.com>
References: <20210226002030.653855-1-ruansy.fnst@fujitsu.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 7BIT
Content-Type:   text/plain; charset=US-ASCII
Precedence: bulk

We replace the existing entry to the newly allocated one in case of CoW.
Also, we mark the entry as PAGECACHE_TAG_TOWRITE so writeback marks this
entry as writeprotected.  This helps us snapshots so new write
pagefaults after snapshots trigger a CoW.

Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
---
 fs/dax.c | 37 ++++++++++++++++++++++++++-----------
 1 file changed, 26 insertions(+), 11 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index 748dfb89fb41..ec4b733e0b59 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -722,6 +722,9 @@ static int copy_cow_page_dax(struct block_device *bdev, struct dax_device *dax_d
 	return 0;
 }
 
+#define DAX_IF_DIRTY		(1 << 0)
+#define DAX_IF_COW		(1 << 1)
+
 /*
  * By this point grab_mapping_entry() has ensured that we have a locked entry
  * of the appropriate size so we don't have to worry about downgrading PMDs to
@@ -729,16 +732,19 @@ static int copy_cow_page_dax(struct block_device *bdev, struct dax_device *dax_d
  * already in the tree, we will skip the insertion and just dirty the PMD as
  * appropriate.
  */
-static void *dax_insert_entry(struct xa_state *xas,
-		struct address_space *mapping, struct vm_fault *vmf,
-		void *entry, pfn_t pfn, unsigned long flags, bool dirty)
+static void *dax_insert_entry(struct xa_state *xas, struct vm_fault *vmf,
+		void *entry, pfn_t pfn, unsigned long flags,
+		unsigned int insert_flags)
 {
+	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
 	void *new_entry = dax_make_entry(pfn, flags);
+	bool dirty = insert_flags & DAX_IF_DIRTY;
+	bool cow = insert_flags & DAX_IF_COW;
 
 	if (dirty)
 		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 
-	if (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE)) {
+	if (cow || (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE))) {
 		unsigned long index = xas->xa_index;
 		/* we are replacing a zero page with block mapping */
 		if (dax_is_pmd_entry(entry))
@@ -750,7 +756,7 @@ static void *dax_insert_entry(struct xa_state *xas,
 
 	xas_reset(xas);
 	xas_lock_irq(xas);
-	if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
+	if (cow || dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
 		void *old;
 
 		dax_disassociate_entry(entry, mapping, false);
@@ -774,6 +780,9 @@ static void *dax_insert_entry(struct xa_state *xas,
 	if (dirty)
 		xas_set_mark(xas, PAGECACHE_TAG_DIRTY);
 
+	if (cow)
+		xas_set_mark(xas, PAGECACHE_TAG_TOWRITE);
+
 	xas_unlock_irq(xas);
 	return entry;
 }
@@ -1100,8 +1109,7 @@ static vm_fault_t dax_load_hole(struct xa_state *xas,
 	pfn_t pfn = pfn_to_pfn_t(my_zero_pfn(vaddr));
 	vm_fault_t ret;
 
-	*entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn,
-			DAX_ZERO_PAGE, false);
+	*entry = dax_insert_entry(xas, vmf, *entry, pfn, DAX_ZERO_PAGE, 0);
 
 	ret = vmf_insert_mixed(vmf->vma, vaddr, pfn);
 	trace_dax_load_hole(inode, vmf, ret);
@@ -1403,6 +1411,7 @@ static vm_fault_t dax_fault_actor(struct vm_fault *vmf, pfn_t *pfnp,
 	loff_t pos = (loff_t)xas->xa_offset << PAGE_SHIFT;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
 	bool sync = dax_fault_is_synchronous(flags, vmf->vma, iomap);
+	unsigned int insert_flags = 0;
 	vm_fault_t ret = 0;
 	int err = 0;
 	pfn_t pfn;
@@ -1426,8 +1435,14 @@ static vm_fault_t dax_fault_actor(struct vm_fault *vmf, pfn_t *pfnp,
 	if (err)
 		goto error_fault;
 
-	entry = dax_insert_entry(xas, mapping, vmf, entry, pfn, 0,
-				 write && !sync);
+	if (write) {
+		if (!sync)
+			insert_flags |= DAX_IF_DIRTY;
+		if (iomap->flags & IOMAP_F_SHARED)
+			insert_flags |= DAX_IF_COW;
+	}
+
+	entry = dax_insert_entry(xas, vmf, entry, pfn, 0, insert_flags);
 
 	if (write && srcmap->addr != iomap->addr) {
 		err = dax_iomap_cow_copy(pos, size, size, srcmap, kaddr, false);
@@ -1571,8 +1586,8 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 		goto fallback;
 
 	pfn = page_to_pfn_t(zero_page);
-	*entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn,
-			DAX_PMD | DAX_ZERO_PAGE, false);
+	*entry = dax_insert_entry(xas, vmf, *entry, pfn,
+				  DAX_PMD | DAX_ZERO_PAGE, 0);
 
 	if (arch_needs_pgtable_deposit()) {
 		pgtable = pte_alloc_one(vma->vm_mm);
-- 
2.30.1