The patch titled
Subject: fs/dax: always remove DAX page-cache entries when breaking layouts
has been added to the -mm mm-unstable branch. Its filename is
fs-dax-always-remove-dax-page-cache-entries-when-breaking-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-always-remove-dax-page-cache-entries-when-breaking-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: always remove DAX page-cache entries when breaking layouts
Date: Tue, 7 Jan 2025 14:42:22 +1100
Prior to any truncation operations file systems call dax_break_mapping()
to ensure pages in the range are not under going DMA. Later DAX
page-cache entries will be removed by truncate_folio_batch_exceptionals()
in the generic page-cache code.
However this makes it possible for folios to be removed from the
page-cache even though they are still DMA busy if the file-system hasn't
called dax_break_mapping(). It also means they can never be waited on in
future because FS DAX will lose track of them once the page-cache entry
has been deleted.
Instead it is better to delete the FS DAX entry when the file-system calls
dax_break_mapping() as part of it's truncate operation. This ensures only
idle pages can be removed from the FS DAX page-cache and makes it easy to
detect if a file-system hasn't called dax_break_mapping() prior to a
truncate operation.
Link: https://lkml.kernel.org/r/fc4ce7ac0815bc33d00ca6626925a1012473ff7a.1736221254.git-series.apopple@xxxxxxxxxx
Signed-off-by: Alistair Popple <apopple@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/dax.c | 33 +++++++++++++++++++++++++++++++++
fs/xfs/xfs_inode.c | 6 ++++++
include/linux/dax.h | 2 ++
mm/truncate.c | 16 +++++++++++++++-
4 files changed, 56 insertions(+), 1 deletion(-)
--- a/fs/dax.c~fs-dax-always-remove-dax-page-cache-entries-when-breaking-layouts
+++ a/fs/dax.c
@@ -845,6 +845,36 @@ int dax_delete_mapping_entry(struct addr
return ret;
}
+void dax_delete_mapping_range(struct address_space *mapping,
+ loff_t start, loff_t end)
+{
+ void *entry;
+ pgoff_t start_idx = start >> PAGE_SHIFT;
+ pgoff_t end_idx;
+ XA_STATE(xas, &mapping->i_pages, start_idx);
+
+ /* If end == LLONG_MAX, all pages from start to till end of file */
+ if (end == LLONG_MAX)
+ end_idx = ULONG_MAX;
+ else
+ end_idx = end >> PAGE_SHIFT;
+
+ xas_lock_irq(&xas);
+ xas_for_each(&xas, entry, end_idx) {
+ if (!xa_is_value(entry))
+ continue;
+ entry = wait_entry_unlocked_exclusive(&xas, entry);
+ if (!entry)
+ continue;
+ dax_disassociate_entry(entry, mapping, true);
+ xas_store(&xas, NULL);
+ mapping->nrpages -= 1UL << dax_entry_order(entry);
+ put_unlocked_entry(&xas, entry, WAKE_ALL);
+ }
+ xas_unlock_irq(&xas);
+}
+EXPORT_SYMBOL_GPL(dax_delete_mapping_range);
+
static int wait_page_idle(struct page *page,
void (cb)(struct inode *),
struct inode *inode)
@@ -874,6 +904,9 @@ int dax_break_mapping(struct inode *inod
error = wait_page_idle(page, cb, inode);
} while (error == 0);
+ if (!page)
+ dax_delete_mapping_range(inode->i_mapping, start, end);
+
return error;
}
EXPORT_SYMBOL_GPL(dax_break_mapping);
--- a/fs/xfs/xfs_inode.c~fs-dax-always-remove-dax-page-cache-entries-when-breaking-layouts
+++ a/fs/xfs/xfs_inode.c
@@ -2746,6 +2746,12 @@ again:
goto again;
}
+ /*
+ * Normally xfs_break_dax_layouts() would delete the mapping entries as well so
+ * do that here.
+ */
+ dax_delete_mapping_range(VFS_I(ip2)->i_mapping, 0, LLONG_MAX);
+
return 0;
}
--- a/include/linux/dax.h~fs-dax-always-remove-dax-page-cache-entries-when-breaking-layouts
+++ a/include/linux/dax.h
@@ -263,6 +263,8 @@ vm_fault_t dax_iomap_fault(struct vm_fau
vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
unsigned int order, pfn_t pfn);
int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
+void dax_delete_mapping_range(struct address_space *mapping,
+ loff_t start, loff_t end);
int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
pgoff_t index);
int __must_check dax_break_mapping(struct inode *inode, loff_t start,
--- a/mm/truncate.c~fs-dax-always-remove-dax-page-cache-entries-when-breaking-layouts
+++ a/mm/truncate.c
@@ -78,8 +78,22 @@ static void truncate_folio_batch_excepti
if (dax_mapping(mapping)) {
for (i = j; i < nr; i++) {
- if (xa_is_value(fbatch->folios[i]))
+ if (xa_is_value(fbatch->folios[i])) {
+ /*
+ * File systems should already have called
+ * dax_break_mapping_entry() to remove all DAX
+ * entries while holding a lock to prevent
+ * establishing new entries. Therefore we
+ * shouldn't find any here.
+ */
+ WARN_ON_ONCE(1);
+
+ /*
+ * Delete the mapping so truncate_pagecache()
+ * doesn't loop forever.
+ */
dax_delete_mapping_entry(mapping, indices[i]);
+ }
}
goto out;
}
_
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
memremap-add-is_devdax_page-and-is_fsdax_page-helpers.patch
mm-gup-dont-allow-foll_longterm-pinning-of-fs-dax-pages.patch
proc-task_mmu-mark-devdax-and-fsdax-pages-as-always-unpinned.patch
mm-mlock-skip-zone_device-pmds-during-mlock.patch
fs-dax-properly-refcount-fs-dax-pages.patch
device-dax-properly-refcount-device-dax-pages-when-mapping.patch
mm-remove-pxx_devmap-callers.patch
mm-remove-devmap-related-functions-and-page-table-bits.patch
revert-riscv-mm-add-support-for-zone_device.patch
