The patch titled
Subject: fs/dax: create a common implementation to break DAX layouts
has been added to the -mm mm-unstable branch. Its filename is
fs-dax-create-a-common-implementation-to-break-dax-layouts.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/fs-dax-create-a-common-implementation-to-break-dax-layouts.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Alistair Popple <apopple@xxxxxxxxxx>
Subject: fs/dax: create a common implementation to break DAX layouts
Date: Wed, 5 Feb 2025 09:48:02 +1100
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.
Link: https://lkml.kernel.org/r/28fcec91d5a764aa58ce897cc6739a4bebdf7840.1738709036.git-series.apopple@xxxxxxxxxx
Signed-off-by: Alistair Popple <apopple@xxxxxxxxxx>
Reviewed-by: Dan Williams <dan.j.williams@xxxxxxxxx>
Tested-by: Alison Schofield <alison.schofield@xxxxxxxxx>
Cc: Alexander Gordeev <agordeev@xxxxxxxxxxxxx>
Cc: Asahi Lina <lina@xxxxxxxxxxxxx>
Cc: Bjorn Helgaas <bhelgaas@xxxxxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: Christian Borntraeger <borntraeger@xxxxxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Chunyan Zhang <zhang.lyra@xxxxxxxxx>
Cc: "Darrick J. Wong" <djwong@xxxxxxxxxx>
Cc: Dave Chinner <david@xxxxxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Dave Jiang <dave.jiang@xxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Gerald Schaefer <gerald.schaefer@xxxxxxxxxxxxx>
Cc: Heiko Carstens <hca@xxxxxxxxxxxxx>
Cc: Huacai Chen <chenhuacai@xxxxxxxxxx>
Cc: Ira Weiny <ira.weiny@xxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxx>
Cc: John Hubbard <jhubbard@xxxxxxxxxx>
Cc: linmiaohe <linmiaohe@xxxxxxxxxx>
Cc: Logan Gunthorpe <logang@xxxxxxxxxxxx>
Cc: Mattew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Nicholas Piggin <npiggin@xxxxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Cc: Sven Schnelle <svens@xxxxxxxxxxxxx>
Cc: Ted Ts'o <tytso@xxxxxxx>
Cc: Vasily Gorbik <gor@xxxxxxxxxxxxx>
Cc: Vishal Verma <vishal.l.verma@xxxxxxxxx>
Cc: Vivek Goyal <vgoyal@xxxxxxxxxx>
Cc: WANG Xuerui <kernel@xxxxxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
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(-)
--- a/fs/dax.c~fs-dax-create-a-common-implementation-to-break-dax-layouts
+++ a/fs/dax.c
@@ -845,6 +845,39 @@ int dax_delete_mapping_entry(struct addr
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.
*/
--- a/fs/ext4/inode.c~fs-dax-create-a-common-implementation-to-break-dax-layouts
+++ a/fs/ext4/inode.c
@@ -3911,21 +3911,10 @@ static void ext4_wait_dax_page(struct in
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);
}
/*
--- a/fs/fuse/dax.c~fs-dax-create-a-common-implementation-to-break-dax-layouts
+++ a/fs/fuse/dax.c
@@ -666,33 +666,12 @@ static void fuse_wait_dax_page(struct in
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)
--- a/fs/xfs/xfs_inode.c~fs-dax-create-a-common-implementation-to-break-dax-layouts
+++ a/fs/xfs/xfs_inode.c
@@ -2732,21 +2732,17 @@ xfs_mmaplock_two_inodes_and_break_dax_la
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 @@ again:
* 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:
--- a/fs/xfs/xfs_inode.h~fs-dax-create-a-common-implementation-to-break-dax-layouts
+++ a/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);
--- a/include/linux/dax.h~fs-dax-create-a-common-implementation-to-break-dax-layouts
+++ a/include/linux/dax.h
@@ -207,12 +207,9 @@ int dax_zero_range(struct inode *inode,
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 i
{
}
#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
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,
_
Patches currently in -mm which might be from apopple@xxxxxxxxxx are
fuse-fix-dax-truncate-punch_hole-fault-path.patch
fs-dax-return-unmapped-busy-pages-from-dax_layout_busy_page_range.patch
fs-dax-dont-skip-locked-entries-when-scanning-entries.patch
fs-dax-refactor-wait-for-dax-idle-page.patch
fs-dax-create-a-common-implementation-to-break-dax-layouts.patch
fs-dax-always-remove-dax-page-cache-entries-when-breaking-layouts.patch
fs-dax-ensure-all-pages-are-idle-prior-to-filesystem-unmount.patch
fs-dax-remove-page_mapping_dax_shared-mapping-flag.patch
mm-gup-remove-redundant-check-for-pci-p2pdma-page.patch
mm-mm_init-move-p2pdma-page-refcount-initialisation-to-p2pdma.patch
mm-allow-compound-zone-device-pages.patch
mm-memory-enhance-insert_page_into_pte_locked-to-create-writable-mappings.patch
mm-memory-add-vmf_insert_page_mkwrite.patch
rmap-add-support-for-pud-sized-mappings-to-rmap.patch
huge_memory-add-vmf_insert_folio_pud.patch
huge_memory-add-vmf_insert_folio_pmd.patch
mm-gup-dont-allow-foll_longterm-pinning-of-fs-dax-pages.patch
fs-dax-properly-refcount-fs-dax-pages.patch
device-dax-properly-refcount-device-dax-pages-when-mapping.patch
