linux-kernel - [PATCH v6 2/7] fsdax: Replace mmap entry in case of CoW

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20210519060045.1051226-3-ruansy.fnst@fujitsu.com>
Date:   Wed, 19 May 2021 14:00:40 +0800
From:   Shiyang Ruan <ruansy.fnst@...itsu.com>
To:     <linux-kernel@...r.kernel.org>, <linux-xfs@...r.kernel.org>,
        <linux-nvdimm@...ts.01.org>, <linux-fsdevel@...r.kernel.org>
CC:     <darrick.wong@...cle.com>, <dan.j.williams@...el.com>,
        <willy@...radead.org>, <viro@...iv.linux.org.uk>,
        <david@...morbit.com>, <hch@....de>, <rgoldwyn@...e.de>,
        Goldwyn Rodrigues <rgoldwyn@...e.com>,
        Ritesh Harjani <riteshh@...ux.ibm.com>,
        "Darrick J . Wong" <djwong@...nel.org>
Subject: [PATCH v6 2/7] fsdax: Replace mmap entry in case of CoW

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@...e.com>
Signed-off-by: Shiyang Ruan <ruansy.fnst@...itsu.com>
Reviewed-by: Christoph Hellwig <hch@....de>
Reviewed-by: Ritesh Harjani <riteshh@...ux.ibm.com>
Reviewed-by: Darrick J. Wong <djwong@...nel.org>
---
 fs/dax.c | 39 ++++++++++++++++++++++++++++-----------
 1 file changed, 28 insertions(+), 11 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index 6396f091e60b..98531c53d613 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -733,6 +733,10 @@ static int copy_cow_page_dax(struct block_device *bdev, struct dax_device *dax_d
 	return 0;
 }
 
+/* DAX Insert Flag: The state of the entry we insert */
+#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
@@ -740,16 +744,19 @@ 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))
@@ -761,7 +768,7 @@ 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);
@@ -785,6 +792,9 @@ 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;
 }
@@ -1120,8 +1130,7 @@ 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);
@@ -1148,8 +1157,8 @@ 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);
@@ -1459,6 +1468,7 @@ static vm_fault_t dax_fault_actor(struct vm_fault *vmf, pfn_t *pfnp,
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
 	bool sync = dax_fault_is_synchronous(flags, vmf->vma, iomap);
 	unsigned long entry_flags = pmd ? DAX_PMD : 0;
+	unsigned int insert_flags = 0;
 	int err = 0;
 	pfn_t pfn;
 	void *kaddr;
@@ -1481,8 +1491,15 @@ static vm_fault_t dax_fault_actor(struct vm_fault *vmf, pfn_t *pfnp,
 	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) {
+		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, entry_flags,
+				  insert_flags);
 
 	if (write &&
 	    srcmap->addr != IOMAP_HOLE && srcmap->addr != iomap->addr) {
-- 
2.31.1