| 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
| ||
|
Date: Thu, 15 Sep 2022 20:35:38 -0700
From: Dan Williams <dan.j.williams@...el.com>
To: akpm@...ux-foundation.org
Cc: Matthew Wilcox <willy@...radead.org>, Jan Kara <jack@...e.cz>,
"Darrick J. Wong" <djwong@...nel.org>,
Jason Gunthorpe <jgg@...dia.com>,
Christoph Hellwig <hch@....de>,
John Hubbard <jhubbard@...dia.com>,
linux-fsdevel@...r.kernel.org, nvdimm@...ts.linux.dev,
linux-xfs@...r.kernel.org, linux-mm@...ck.org,
linux-ext4@...r.kernel.org
Subject: [PATCH v2 05/18] xfs: Add xfs_break_layouts() to the inode eviction
path
In preparation for moving DAX pages to be 0-based rather than 1-based
for the idle refcount, the fsdax core wants to have all mappings in a
"zapped" state before truncate. For typical pages this happens naturally
via unmap_mapping_range(), for DAX pages some help is needed to record
this state in the 'struct address_space' of the inode(s) where the page
is mapped.
That "zapped" state is recorded in DAX entries as a side effect of
xfs_break_layouts(). Arrange for it to be called before all truncation
events which already happens for truncate() and PUNCH_HOLE, but not
truncate_inode_pages_final(). Arrange for xfs_break_layouts() before
truncate_inode_pages_final().
Cc: Matthew Wilcox <willy@...radead.org>
Cc: Jan Kara <jack@...e.cz>
Cc: "Darrick J. Wong" <djwong@...nel.org>
Cc: Jason Gunthorpe <jgg@...dia.com>
Cc: Christoph Hellwig <hch@....de>
Cc: John Hubbard <jhubbard@...dia.com>
Signed-off-by: Dan Williams <dan.j.williams@...el.com>
---
fs/xfs/xfs_file.c | 13 +++++++++----
fs/xfs/xfs_inode.c | 3 ++-
fs/xfs/xfs_inode.h | 6 ++++--
fs/xfs/xfs_super.c | 22 ++++++++++++++++++++++
4 files changed, 37 insertions(+), 7 deletions(-)
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 556e28d06788..d3ff692d5546 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -816,7 +816,8 @@ xfs_wait_dax_page(
int
xfs_break_dax_layouts(
struct inode *inode,
- bool *retry)
+ bool *retry,
+ int state)
{
struct page *page;
@@ -827,8 +828,8 @@ xfs_break_dax_layouts(
return 0;
*retry = true;
- return ___wait_var_event(page, dax_page_idle(page), TASK_INTERRUPTIBLE,
- 0, 0, xfs_wait_dax_page(inode));
+ return ___wait_var_event(page, dax_page_idle(page), state, 0, 0,
+ xfs_wait_dax_page(inode));
}
int
@@ -839,14 +840,18 @@ xfs_break_layouts(
{
bool retry;
int error;
+ int state = TASK_INTERRUPTIBLE;
ASSERT(xfs_isilocked(XFS_I(inode), XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL));
do {
retry = false;
switch (reason) {
+ case BREAK_UNMAP_FINAL:
+ state = TASK_UNINTERRUPTIBLE;
+ fallthrough;
case BREAK_UNMAP:
- error = xfs_break_dax_layouts(inode, &retry);
+ error = xfs_break_dax_layouts(inode, &retry, state);
if (error || retry)
break;
fallthrough;
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 28493c8e9bb2..72ce1cb72736 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -3452,6 +3452,7 @@ xfs_mmaplock_two_inodes_and_break_dax_layout(
struct xfs_inode *ip1,
struct xfs_inode *ip2)
{
+ int state = TASK_INTERRUPTIBLE;
int error;
bool retry;
struct page *page;
@@ -3463,7 +3464,7 @@ xfs_mmaplock_two_inodes_and_break_dax_layout(
retry = false;
/* Lock the first inode */
xfs_ilock(ip1, XFS_MMAPLOCK_EXCL);
- error = xfs_break_dax_layouts(VFS_I(ip1), &retry);
+ error = xfs_break_dax_layouts(VFS_I(ip1), &retry, state);
if (error || retry) {
xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL);
if (error == 0 && retry)
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index fa780f08dc89..e4994eb6e521 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -454,11 +454,13 @@ static inline bool xfs_inode_has_large_extent_counts(struct xfs_inode *ip)
* layout-holder has a consistent view of the file's extent map. While
* BREAK_WRITE breaks can be satisfied by recalling FL_LAYOUT leases,
* BREAK_UNMAP breaks additionally require waiting for busy dax-pages to
- * go idle.
+ * go idle. BREAK_UNMAP_FINAL is an uninterruptible version of
+ * BREAK_UNMAP.
*/
enum layout_break_reason {
BREAK_WRITE,
BREAK_UNMAP,
+ BREAK_UNMAP_FINAL,
};
/*
@@ -531,7 +533,7 @@ xfs_itruncate_extents(
}
/* from xfs_file.c */
-int xfs_break_dax_layouts(struct inode *inode, bool *retry);
+int xfs_break_dax_layouts(struct inode *inode, bool *retry, int state);
int xfs_break_layouts(struct inode *inode, uint *iolock,
enum layout_break_reason reason);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 9ac59814bbb6..ebb4a6eba3fc 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -725,6 +725,27 @@ xfs_fs_drop_inode(
return generic_drop_inode(inode);
}
+STATIC void
+xfs_fs_evict_inode(
+ struct inode *inode)
+{
+ struct xfs_inode *ip = XFS_I(inode);
+ uint iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
+ long error;
+
+ xfs_ilock(ip, iolock);
+
+ error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP_FINAL);
+
+ /* The final layout break is uninterruptible */
+ ASSERT_ALWAYS(!error);
+
+ truncate_inode_pages_final(&inode->i_data);
+ clear_inode(inode);
+
+ xfs_iunlock(ip, iolock);
+}
+
static void
xfs_mount_free(
struct xfs_mount *mp)
@@ -1144,6 +1165,7 @@ 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,
Powered by blists - more mailing lists