linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Alistair Popple <apopple@nvidia.com>
To: akpm@linux-foundation.org, dan.j.williams@intel.com, linux-mm@kvack.org
Cc: Alistair Popple <apopple@nvidia.com>,
	Alison Schofield <alison.schofield@intel.com>,
	lina@asahilina.net, zhang.lyra@gmail.com,
	gerald.schaefer@linux.ibm.com, vishal.l.verma@intel.com,
	dave.jiang@intel.com, logang@deltatee.com, bhelgaas@google.com,
	jack@suse.cz, jgg@ziepe.ca, catalin.marinas@arm.com,
	will@kernel.org, mpe@ellerman.id.au, npiggin@gmail.com,
	dave.hansen@linux.intel.com, ira.weiny@intel.com,
	willy@infradead.org, djwong@kernel.org, tytso@mit.edu,
	linmiaohe@huawei.com, david@redhat.com, peterx@redhat.com,
	linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org,
	linuxppc-dev@lists.ozlabs.org, nvdimm@lists.linux.dev,
	linux-cxl@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-ext4@vger.kernel.org, linux-xfs@vger.kernel.org,
	jhubbard@nvidia.com, hch@lst.de, david@fromorbit.com,
	chenhuacai@kernel.org, kernel@xen0n.name,
	loongarch@lists.linux.dev
Subject: [PATCH v7 07/20] fs/dax: Ensure all pages are idle prior to filesystem unmount
Date: Wed,  5 Feb 2025 09:48:04 +1100	[thread overview]
Message-ID: <6f23832debd919787c57fc5ef19561a45c034bce.1738709036.git-series.apopple@nvidia.com> (raw)
In-Reply-To: <cover.472dfc700f28c65ecad7591096a1dc7878ff6172.1738709036.git-series.apopple@nvidia.com>

File systems call dax_break_mapping() prior to reallocating file system
blocks to ensure the page is not undergoing any DMA or other
accesses. Generally this is needed when a file is truncated to ensure that
if a block is reallocated nothing is writing to it. However filesystems
currently don't call this when an FS DAX inode is evicted.

This can cause problems when the file system is unmounted as a page can
continue to be under going DMA or other remote access after unmount. This
means if the file system is remounted any truncate or other operation which
requires the underlying file system block to be freed will not wait for the
remote access to complete. Therefore a busy block may be reallocated to a
new file leading to corruption.

Signed-off-by: Alistair Popple <apopple@nvidia.com>

---

Changes for v7:

 - Don't take locks during inode eviction as suggested by Darrick and
   therefore remove the callback for dax_break_mapping_uninterruptible().
 - Use common definition of dax_page_is_idle().
 - Fixed smatch suggestion in dax_break_mapping_uninterruptible().
 - Rename dax_break_mapping_uninterruptible() to dax_break_layout_final()
   as suggested by Dan.

Changes for v5:

 - Don't wait for pages to be idle in non-DAX mappings
---
 fs/dax.c            | 27 +++++++++++++++++++++++++++
 fs/ext4/inode.c     |  2 ++
 fs/xfs/xfs_super.c  | 12 ++++++++++++
 include/linux/dax.h |  5 +++++
 4 files changed, 46 insertions(+)

diff --git a/fs/dax.c b/fs/dax.c
index 39f1dc0..9c28eb3 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -883,6 +883,13 @@ static int wait_page_idle(struct page *page,
 				TASK_INTERRUPTIBLE, 0, 0, cb(inode));
 }
 
+static void wait_page_idle_uninterruptible(struct page *page,
+					struct inode *inode)
+{
+	___wait_var_event(page, dax_page_is_idle(page),
+			TASK_UNINTERRUPTIBLE, 0, 0, schedule());
+}
+
 /*
  * Unmaps the inode and waits for any DMA to complete prior to deleting the
  * DAX mapping entries for the range.
@@ -918,6 +925,26 @@ int dax_break_layout(struct inode *inode, loff_t start, loff_t end,
 }
 EXPORT_SYMBOL_GPL(dax_break_layout);
 
+void dax_break_layout_final(struct inode *inode)
+{
+	struct page *page;
+
+	if (!dax_mapping(inode->i_mapping))
+		return;
+
+	do {
+		page = dax_layout_busy_page_range(inode->i_mapping, 0,
+						LLONG_MAX);
+		if (!page)
+			break;
+
+		wait_page_idle_uninterruptible(page, inode);
+	} while (true);
+
+	dax_delete_mapping_range(inode->i_mapping, 0, LLONG_MAX);
+}
+EXPORT_SYMBOL_GPL(dax_break_layout_final);
+
 /*
  * Invalidate DAX entry if it is clean.
  */
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 2342bac..3cc8da6 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -181,6 +181,8 @@ void ext4_evict_inode(struct inode *inode)
 
 	trace_ext4_evict_inode(inode);
 
+	dax_break_layout_final(inode);
+
 	if (EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)
 		ext4_evict_ea_inode(inode);
 	if (inode->i_nlink) {
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index d92d7a0..22abe0e 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -751,6 +751,17 @@ xfs_fs_drop_inode(
 	return generic_drop_inode(inode);
 }
 
+STATIC void
+xfs_fs_evict_inode(
+	struct inode		*inode)
+{
+	if (IS_DAX(inode))
+		dax_break_layout_final(inode);
+
+	truncate_inode_pages_final(&inode->i_data);
+	clear_inode(inode);
+}
+
 static void
 xfs_mount_free(
 	struct xfs_mount	*mp)
@@ -1215,6 +1226,7 @@ static const struct super_operations xfs_super_operations = {
 	.destroy_inode		= xfs_fs_destroy_inode,
 	.dirty_inode		= xfs_fs_dirty_inode,
 	.drop_inode		= xfs_fs_drop_inode,
+	.evict_inode		= xfs_fs_evict_inode,
 	.put_super		= xfs_fs_put_super,
 	.sync_fs		= xfs_fs_sync_fs,
 	.freeze_fs		= xfs_fs_freeze,
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 2fbb262..2333c30 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -232,6 +232,10 @@ static inline int __must_check dax_break_layout(struct inode *inode,
 {
 	return 0;
 }
+
+static inline void dax_break_layout_final(struct inode *inode)
+{
+}
 #endif
 
 bool dax_alive(struct dax_device *dax_dev);
@@ -266,6 +270,7 @@ static inline int __must_check dax_break_layout_inode(struct inode *inode,
 {
 	return dax_break_layout(inode, 0, LLONG_MAX, cb);
 }
+void dax_break_layout_final(struct inode *inode);
 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


  parent reply	other threads:[~2025-02-04 22:50 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-02-04 22:47 [PATCH v7 00/20] fs/dax: Fix ZONE_DEVICE page reference counts Alistair Popple
2025-02-04 22:47 ` [PATCH v7 01/20] fuse: Fix dax truncate/punch_hole fault path Alistair Popple
2025-02-05  3:07   ` Balbir Singh
2025-02-04 22:47 ` [PATCH v7 02/20] fs/dax: Return unmapped busy pages from dax_layout_busy_page_range() Alistair Popple
2025-02-05  3:15   ` Balbir Singh
2025-02-04 22:48 ` [PATCH v7 03/20] fs/dax: Don't skip locked entries when scanning entries Alistair Popple
2025-02-04 22:48 ` [PATCH v7 04/20] fs/dax: Refactor wait for dax idle page Alistair Popple
2025-02-04 22:48 ` [PATCH v7 05/20] fs/dax: Create a common implementation to break DAX layouts Alistair Popple
2025-02-04 22:48 ` [PATCH v7 06/20] fs/dax: Always remove DAX page-cache entries when breaking layouts Alistair Popple
2025-02-04 22:48 ` Alistair Popple [this message]
2025-02-04 22:48 ` [PATCH v7 08/20] fs/dax: Remove PAGE_MAPPING_DAX_SHARED mapping flag Alistair Popple
2025-02-04 22:48 ` [PATCH v7 09/20] mm/gup: Remove redundant check for PCI P2PDMA page Alistair Popple
2025-02-04 22:48 ` [PATCH v7 10/20] mm/mm_init: Move p2pdma page refcount initialisation to p2pdma Alistair Popple
2025-02-04 22:48 ` [PATCH v7 11/20] mm: Allow compound zone device pages Alistair Popple
2025-02-04 22:48 ` [PATCH v7 12/20] mm/memory: Enhance insert_page_into_pte_locked() to create writable mappings Alistair Popple
2025-02-10 18:39   ` David Hildenbrand
2025-02-04 22:48 ` [PATCH v7 13/20] mm/memory: Add vmf_insert_page_mkwrite() Alistair Popple
2025-02-10 18:40   ` David Hildenbrand
2025-02-04 22:48 ` [PATCH v7 14/20] rmap: Add support for PUD sized mappings to rmap Alistair Popple
2025-02-10 18:41   ` David Hildenbrand
2025-02-04 22:48 ` [PATCH v7 15/20] huge_memory: Add vmf_insert_folio_pud() Alistair Popple
2025-02-10 18:43   ` David Hildenbrand
2025-02-04 22:48 ` [PATCH v7 16/20] huge_memory: Add vmf_insert_folio_pmd() Alistair Popple
2025-02-10 18:45   ` David Hildenbrand
2025-02-17  4:29     ` Alistair Popple
2025-02-17 19:58       ` David Hildenbrand
2025-02-04 22:48 ` [PATCH v7 17/20] mm/gup: Don't allow FOLL_LONGTERM pinning of FS DAX pages Alistair Popple
2025-02-04 22:48 ` [PATCH v7 18/20] dcssblk: Mark DAX broken, remove FS_DAX_LIMITED support Alistair Popple
2025-02-04 22:48 ` [PATCH v7 19/20] fs/dax: Properly refcount fs dax pages Alistair Popple
2025-02-06 21:06   ` Guenter Roeck
2025-02-10 19:01   ` David Hildenbrand
2025-02-04 22:48 ` [PATCH v7 20/20] device/dax: Properly refcount device dax pages when mapping Alistair Popple

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=6f23832debd919787c57fc5ef19561a45c034bce.1738709036.git-series.apopple@nvidia.com \
    --to=apopple@nvidia.com \
    --cc=akpm@linux-foundation.org \
    --cc=alison.schofield@intel.com \
    --cc=bhelgaas@google.com \
    --cc=catalin.marinas@arm.com \
    --cc=chenhuacai@kernel.org \
    --cc=dan.j.williams@intel.com \
    --cc=dave.hansen@linux.intel.com \
    --cc=dave.jiang@intel.com \
    --cc=david@fromorbit.com \
    --cc=david@redhat.com \
    --cc=djwong@kernel.org \
    --cc=gerald.schaefer@linux.ibm.com \
    --cc=hch@lst.de \
    --cc=ira.weiny@intel.com \
    --cc=jack@suse.cz \
    --cc=jgg@ziepe.ca \
    --cc=jhubbard@nvidia.com \
    --cc=kernel@xen0n.name \
    --cc=lina@asahilina.net \
    --cc=linmiaohe@huawei.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-cxl@vger.kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=logang@deltatee.com \
    --cc=loongarch@lists.linux.dev \
    --cc=mpe@ellerman.id.au \
    --cc=npiggin@gmail.com \
    --cc=nvdimm@lists.linux.dev \
    --cc=peterx@redhat.com \
    --cc=tytso@mit.edu \
    --cc=vishal.l.verma@intel.com \
    --cc=will@kernel.org \
    --cc=willy@infradead.org \
    --cc=zhang.lyra@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox