Message-ID: <28fcec91d5a764aa58ce897cc6739a4bebdf7840.1738709036.git-series.apopple@nvidia.com>
Date: Wed,  5 Feb 2025 09:48:02 +1100
From: Alistair Popple <apopple@...dia.com>
To: akpm@...ux-foundation.org,
	dan.j.williams@...el.com,
	linux-mm@...ck.org
Cc: Alistair Popple <apopple@...dia.com>,
	Alison Schofield <alison.schofield@...el.com>,
	lina@...hilina.net,
	zhang.lyra@...il.com,
	gerald.schaefer@...ux.ibm.com,
	vishal.l.verma@...el.com,
	dave.jiang@...el.com,
	logang@...tatee.com,
	bhelgaas@...gle.com,
	jack@...e.cz,
	jgg@...pe.ca,
	catalin.marinas@....com,
	will@...nel.org,
	mpe@...erman.id.au,
	npiggin@...il.com,
	dave.hansen@...ux.intel.com,
	ira.weiny@...el.com,
	willy@...radead.org,
	djwong@...nel.org,
	tytso@....edu,
	linmiaohe@...wei.com,
	david@...hat.com,
	peterx@...hat.com,
	linux-doc@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	linux-arm-kernel@...ts.infradead.org,
	linuxppc-dev@...ts.ozlabs.org,
	nvdimm@...ts.linux.dev,
	linux-cxl@...r.kernel.org,
	linux-fsdevel@...r.kernel.org,
	linux-ext4@...r.kernel.org,
	linux-xfs@...r.kernel.org,
	jhubbard@...dia.com,
	hch@....de,
	david@...morbit.com,
	chenhuacai@...nel.org,
	kernel@...0n.name,
	loongarch@...ts.linux.dev
Subject: [PATCH v7 05/20] fs/dax: Create a common implementation to break DAX layouts

Prior to freeing a block file systems supporting FS DAX must check
that the associated pages are both unmapped from user-space and not
undergoing DMA or other access from eg. get_user_pages(). This is
achieved by unmapping the file range and scanning the FS DAX
page-cache to see if any pages within the mapping have an elevated
refcount.

This is done using two functions - dax_layout_busy_page_range() which
returns a page to wait for the refcount to become idle on. Rather than
open-code this introduce a common implementation to both unmap and
wait for the page to become idle.

Signed-off-by: Alistair Popple <apopple@...dia.com>
Reviewed-by: Dan Williams <dan.j.williams@...el.com>

---

Changes for v7:

 - Fix smatch warning, also reported by Dan and Darrick
 - Make sure xfs_break_layouts() can return -ERESTARTSYS, reported by
   Darrick
 - Use common definition of dax_page_is_idle()
 - Removed misplaced hunk changing madvise
 - Renamed dax_break_mapping() to dax_break_layout() suggested by Dan
 - Fix now unused variables in ext4

Changes for v5:

 - Don't wait for idle pages on non-DAX mappings

Changes for v4:

 - Fixed some build breakage due to missing symbol exports reported by
   John Hubbard (thanks!).
---
 fs/dax.c            | 33 +++++++++++++++++++++++++++++++++
 fs/ext4/inode.c     | 13 +------------
 fs/fuse/dax.c       | 27 +++------------------------
 fs/xfs/xfs_inode.c  | 26 +++++++-------------------
 fs/xfs/xfs_inode.h  |  2 +-
 include/linux/dax.h | 23 ++++++++++++++++++-----
 6 files changed, 63 insertions(+), 61 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index d010c10..710b280 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -845,6 +845,39 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
 	return ret;
 }
 
+static int wait_page_idle(struct page *page,
+			void (cb)(struct inode *),
+			struct inode *inode)
+{
+	return ___wait_var_event(page, dax_page_is_idle(page),
+				TASK_INTERRUPTIBLE, 0, 0, cb(inode));
+}
+
+/*
+ * Unmaps the inode and waits for any DMA to complete prior to deleting the
+ * DAX mapping entries for the range.
+ */
+int dax_break_layout(struct inode *inode, loff_t start, loff_t end,
+		void (cb)(struct inode *))
+{
+	struct page *page;
+	int error = 0;
+
+	if (!dax_mapping(inode->i_mapping))
+		return 0;
+
+	do {
+		page = dax_layout_busy_page_range(inode->i_mapping, start, end);
+		if (!page)
+			break;
+
+		error = wait_page_idle(page, cb, inode);
+	} while (error == 0);
+
+	return error;
+}
+EXPORT_SYMBOL_GPL(dax_break_layout);
+
 /*
  * Invalidate DAX entry if it is clean.
  */
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index cc1acb1..2342bac 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3911,21 +3911,10 @@ static void ext4_wait_dax_page(struct inode *inode)
 
 int ext4_break_layouts(struct inode *inode)
 {
-	struct page *page;
-	int error;
-
 	if (WARN_ON_ONCE(!rwsem_is_locked(&inode->i_mapping->invalidate_lock)))
 		return -EINVAL;
 
-	do {
-		page = dax_layout_busy_page(inode->i_mapping);
-		if (!page)
-			return 0;
-
-		error = dax_wait_page_idle(page, ext4_wait_dax_page, inode);
-	} while (error == 0);
-
-	return error;
+	return dax_break_layout_inode(inode, ext4_wait_dax_page);
 }
 
 /*
diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c
index bf6faa3..0502bf3 100644
--- a/fs/fuse/dax.c
+++ b/fs/fuse/dax.c
@@ -666,33 +666,12 @@ static void fuse_wait_dax_page(struct inode *inode)
 	filemap_invalidate_lock(inode->i_mapping);
 }
 
-/* Should be called with mapping->invalidate_lock held exclusively */
-static int __fuse_dax_break_layouts(struct inode *inode, bool *retry,
-				    loff_t start, loff_t end)
-{
-	struct page *page;
-
-	page = dax_layout_busy_page_range(inode->i_mapping, start, end);
-	if (!page)
-		return 0;
-
-	*retry = true;
-	return dax_wait_page_idle(page, fuse_wait_dax_page, inode);
-}
-
+/* Should be called with mapping->invalidate_lock held exclusively. */
 int fuse_dax_break_layouts(struct inode *inode, u64 dmap_start,
 				  u64 dmap_end)
 {
-	bool	retry;
-	int	ret;
-
-	do {
-		retry = false;
-		ret = __fuse_dax_break_layouts(inode, &retry, dmap_start,
-					       dmap_end);
-	} while (ret == 0 && retry);
-
-	return ret;
+	return dax_break_layout(inode, dmap_start, dmap_end,
+				fuse_wait_dax_page);
 }
 
 ssize_t fuse_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index a457c13..62c2ae3 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2732,21 +2732,17 @@ xfs_mmaplock_two_inodes_and_break_dax_layout(
 	struct xfs_inode	*ip2)
 {
 	int			error;
-	bool			retry;
 	struct page		*page;
 
 	if (ip1->i_ino > ip2->i_ino)
 		swap(ip1, ip2);
 
 again:
-	retry = false;
 	/* Lock the first inode */
 	xfs_ilock(ip1, XFS_MMAPLOCK_EXCL);
-	error = xfs_break_dax_layouts(VFS_I(ip1), &retry);
-	if (error || retry) {
+	error = xfs_break_dax_layouts(VFS_I(ip1));
+	if (error) {
 		xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL);
-		if (error == 0 && retry)
-			goto again;
 		return error;
 	}
 
@@ -2761,7 +2757,7 @@ xfs_mmaplock_two_inodes_and_break_dax_layout(
 	 * for this nested lock case.
 	 */
 	page = dax_layout_busy_page(VFS_I(ip2)->i_mapping);
-	if (page && page_ref_count(page) != 1) {
+	if (!dax_page_is_idle(page)) {
 		xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL);
 		xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL);
 		goto again;
@@ -3005,19 +3001,11 @@ xfs_wait_dax_page(
 
 int
 xfs_break_dax_layouts(
-	struct inode		*inode,
-	bool			*retry)
+	struct inode		*inode)
 {
-	struct page		*page;
-
 	xfs_assert_ilocked(XFS_I(inode), XFS_MMAPLOCK_EXCL);
 
-	page = dax_layout_busy_page(inode->i_mapping);
-	if (!page)
-		return 0;
-
-	*retry = true;
-	return dax_wait_page_idle(page, xfs_wait_dax_page, inode);
+	return dax_break_layout_inode(inode, xfs_wait_dax_page);
 }
 
 int
@@ -3035,8 +3023,8 @@ xfs_break_layouts(
 		retry = false;
 		switch (reason) {
 		case BREAK_UNMAP:
-			error = xfs_break_dax_layouts(inode, &retry);
-			if (error || retry)
+			error = xfs_break_dax_layouts(inode);
+			if (error)
 				break;
 			fallthrough;
 		case BREAK_WRITE:
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index c08093a..123dfa9 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -603,7 +603,7 @@ xfs_itruncate_extents(
 	return xfs_itruncate_extents_flags(tpp, ip, whichfork, new_size, 0);
 }
 
-int	xfs_break_dax_layouts(struct inode *inode, bool *retry);
+int	xfs_break_dax_layouts(struct inode *inode);
 int	xfs_break_layouts(struct inode *inode, uint *iolock,
 		enum layout_break_reason reason);
 
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 9b1ce98..a6b277f 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -207,12 +207,9 @@ int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
 int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
 		const struct iomap_ops *ops);
 
-static inline int dax_wait_page_idle(struct page *page,
-				void (cb)(struct inode *),
-				struct inode *inode)
+static inline bool dax_page_is_idle(struct page *page)
 {
-	return ___wait_var_event(page, page_ref_count(page) == 1,
-				TASK_INTERRUPTIBLE, 0, 0, cb(inode));
+	return page && page_ref_count(page) == 1;
 }
 
 #if IS_ENABLED(CONFIG_DAX)
@@ -228,6 +225,15 @@ static inline void dax_read_unlock(int id)
 {
 }
 #endif /* CONFIG_DAX */
+
+#if !IS_ENABLED(CONFIG_FS_DAX)
+static inline int __must_check dax_break_layout(struct inode *inode,
+			    loff_t start, loff_t end, void (cb)(struct inode *))
+{
+	return 0;
+}
+#endif
+
 bool dax_alive(struct dax_device *dax_dev);
 void *dax_get_private(struct dax_device *dax_dev);
 long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
@@ -251,6 +257,13 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 				      pgoff_t index);
+int __must_check dax_break_layout(struct inode *inode, loff_t start,
+				loff_t end, void (cb)(struct inode *));
+static inline int __must_check dax_break_layout_inode(struct inode *inode,
+						void (cb)(struct inode *))
+{
+	return dax_break_layout(inode, 0, LLONG_MAX, cb);
+}
 int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
 				  struct inode *dest, loff_t destoff,
 				  loff_t len, bool *is_same,
-- 
git-series 0.9.1

Powered by blists - more mailing lists