This patch is inspired by Dan's "mm, dax, pmem: Introduce
dev_pagemap_failure()"[1]. With the help of dax_holder and
->notify_failure() mechanism, the pmem driver is able to ask filesystem
(or mapped device) on it to unmap all files in use and notify processes
who are using those files.
Call trace:
trigger unbind
-> unbind_store()
-> ... (skip)
-> devres_release_all()
-> kill_dax()
-> dax_holder_notify_failure(dax_dev, 0, U64_MAX, MF_MEM_PRE_REMOVE)
-> xfs_dax_notify_failure()
`-> freeze_super()
`-> do xfs rmap
` -> mf_dax_kill_procs()
` -> collect_procs_fsdax() // all associated
` -> unmap_and_kill()
` -> invalidate_inode_pages2() // drop file's cache
`-> thaw_super()
Introduce MF_MEM_PRE_REMOVE to let filesystem know this is a remove
event. Freeze the filesystem to prevent new dax mapping being created.
And do not shutdown filesystem directly if something not supported, or
if failure range includes metadata area. Make sure all files and
processes are handled correctly. Also drop the cache of associated
files before pmem is removed.
[1]: https://lore.kernel.org/linux-mm/161604050314.1463742.14151665140035795571.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx/
Signed-off-by: Shiyang Ruan <ruansy.fnst@xxxxxxxxxxx>
---
drivers/dax/super.c | 3 +-
fs/xfs/xfs_notify_failure.c | 56 +++++++++++++++++++++++++++++++++----
include/linux/mm.h | 1 +
mm/memory-failure.c | 17 ++++++++---
4 files changed, 67 insertions(+), 10 deletions(-)
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index c4c4728a36e4..2e1a35e82fce 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -323,7 +323,8 @@ void kill_dax(struct dax_device *dax_dev)
return;
if (dax_dev->holder_data != NULL)
- dax_holder_notify_failure(dax_dev, 0, U64_MAX, 0);
+ dax_holder_notify_failure(dax_dev, 0, U64_MAX,
+ MF_MEM_PRE_REMOVE);
clear_bit(DAXDEV_ALIVE, &dax_dev->flags);
synchronize_srcu(&dax_srcu);
diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c
index 1e2eddb8f90f..1b4eff43f9b5 100644
--- a/fs/xfs/xfs_notify_failure.c
+++ b/fs/xfs/xfs_notify_failure.c
@@ -22,6 +22,7 @@
#include <linux/mm.h>
#include <linux/dax.h>
+#include <linux/fs.h>
struct xfs_failure_info {
xfs_agblock_t startblock;
@@ -73,10 +74,16 @@ xfs_dax_failure_fn(
struct xfs_mount *mp = cur->bc_mp;
struct xfs_inode *ip;
struct xfs_failure_info *notify = data;
+ struct address_space *mapping;
+ pgoff_t pgoff;
+ unsigned long pgcnt;
int error = 0;
if (XFS_RMAP_NON_INODE_OWNER(rec->rm_owner) ||
(rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK))) {
+ /* The device is about to be removed. Not a really failure. */
+ if (notify->mf_flags & MF_MEM_PRE_REMOVE)
+ return 0;
notify->want_shutdown = true;
return 0;
}
@@ -92,10 +99,18 @@ xfs_dax_failure_fn(
return 0;
}
- error = mf_dax_kill_procs(VFS_I(ip)->i_mapping,
- xfs_failure_pgoff(mp, rec, notify),
- xfs_failure_pgcnt(mp, rec, notify),
- notify->mf_flags);
+ mapping = VFS_I(ip)->i_mapping;
+ pgoff = xfs_failure_pgoff(mp, rec, notify);
+ pgcnt = xfs_failure_pgcnt(mp, rec, notify);
+
+ /* Continue the rmap query if the inode isn't a dax file. */
+ if (dax_mapping(mapping))
+ error = mf_dax_kill_procs(mapping, pgoff, pgcnt,
+ notify->mf_flags);
+
+ /* Invalidate the cache anyway. */
+ invalidate_inode_pages2_range(mapping, pgoff, pgoff + pgcnt - 1);
+
xfs_irele(ip);
return error;
}
@@ -164,11 +179,25 @@ xfs_dax_notify_ddev_failure(
}
xfs_trans_cancel(tp);
+
+ /* Unfreeze filesystem anyway if it is freezed before. */
+ if (mf_flags & MF_MEM_PRE_REMOVE) {
+ error = thaw_super(mp->m_super);
+ if (error)
+ return error;
+ }
+
+ /*
+ * Determine how to shutdown the filesystem according to the
+ * error code and flags.
+ */
if (error || notify.want_shutdown) {
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK);
if (!error)
error = -EFSCORRUPTED;
- }
+ } else if (mf_flags & MF_MEM_PRE_REMOVE)
+ xfs_force_shutdown(mp, SHUTDOWN_FORCE_UMOUNT);
+
return error;
}
@@ -182,6 +211,7 @@ xfs_dax_notify_failure(
struct xfs_mount *mp = dax_holder(dax_dev);
u64 ddev_start;
u64 ddev_end;
+ int error;
if (!(mp->m_super->s_flags & SB_BORN)) {
xfs_warn(mp, "filesystem is not ready for notify_failure()!");
@@ -196,6 +226,8 @@ xfs_dax_notify_failure(
if (mp->m_logdev_targp && mp->m_logdev_targp->bt_daxdev == dax_dev &&
mp->m_logdev_targp != mp->m_ddev_targp) {
+ if (mf_flags & MF_MEM_PRE_REMOVE)
+ return 0;
xfs_err(mp, "ondisk log corrupt, shutting down fs!");
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_ONDISK);
return -EFSCORRUPTED;
@@ -209,6 +241,12 @@ xfs_dax_notify_failure(
ddev_start = mp->m_ddev_targp->bt_dax_part_off;
ddev_end = ddev_start + bdev_nr_bytes(mp->m_ddev_targp->bt_bdev) - 1;
+ /* Notify failure on the whole device. */
+ if (offset == 0 && len == U64_MAX) {
+ offset = ddev_start;
+ len = bdev_nr_bytes(mp->m_ddev_targp->bt_bdev);
+ }
+
/* Ignore the range out of filesystem area */
if (offset + len - 1 < ddev_start)
return -ENXIO;
@@ -225,6 +263,14 @@ xfs_dax_notify_failure(
if (offset + len - 1 > ddev_end)
len = ddev_end - offset + 1;
+ if (mf_flags & MF_MEM_PRE_REMOVE) {
+ xfs_info(mp, "device is about to be removed!");
+ /* Freeze the filesystem to prevent new mappings created. */
+ error = freeze_super(mp->m_super);
+ if (error)
+ return error;
+ }
+
return xfs_dax_notify_ddev_failure(mp, BTOBB(offset), BTOBB(len),
mf_flags);
}
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1f79667824eb..ac3f22c20e1d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3436,6 +3436,7 @@ enum mf_flags {
MF_UNPOISON = 1 << 4,
MF_SW_SIMULATED = 1 << 5,
MF_NO_RETRY = 1 << 6,
+ MF_MEM_PRE_REMOVE = 1 << 7,
};
int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
unsigned long count, int mf_flags);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index fae9baf3be16..6e6acec45568 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -623,7 +623,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
*/
static void collect_procs_fsdax(struct page *page,
struct address_space *mapping, pgoff_t pgoff,
- struct list_head *to_kill)
+ struct list_head *to_kill, bool pre_remove)
{
struct vm_area_struct *vma;
struct task_struct *tsk;
@@ -631,8 +631,15 @@ static void collect_procs_fsdax(struct page *page,
i_mmap_lock_read(mapping);
read_lock(&tasklist_lock);
for_each_process(tsk) {
- struct task_struct *t = task_early_kill(tsk, true);
+ struct task_struct *t = tsk;
+ /*
+ * Search for all tasks while MF_MEM_PRE_REMOVE, because the
+ * current may not be the one accessing the fsdax page.
+ * Otherwise, search for the current task.
+ */
+ if (!pre_remove)
+ t = task_early_kill(tsk, true);
if (!t)
continue;
vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
@@ -1732,6 +1739,7 @@ int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
dax_entry_t cookie;
struct page *page;
size_t end = index + count;
+ bool pre_remove = mf_flags & MF_MEM_PRE_REMOVE;
mf_flags |= MF_ACTION_REQUIRED | MF_MUST_KILL;
@@ -1743,9 +1751,10 @@ int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
if (!page)
goto unlock;
- SetPageHWPoison(page);
+ if (!pre_remove)
+ SetPageHWPoison(page);
- collect_procs_fsdax(page, mapping, index, &to_kill);
+ collect_procs_fsdax(page, mapping, index, &to_kill, pre_remove);
unmap_and_kill(&to_kill, page_to_pfn(page), mapping,
index, mf_flags);
unlock:
--
2.39.2
