The patch titled
Subject: ksm: stop hotremove lockdep warning
has been added to the -mm tree. Its filename is
ksm-stop-hotremove-lockdep-warning.patch
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/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Hugh Dickins <hughd@xxxxxxxxxx>
Subject: ksm: stop hotremove lockdep warning
Complaints are rare, but lockdep still does not understand the way
ksm_memory_callback(MEM_GOING_OFFLINE) takes ksm_thread_mutex, and holds
it until the ksm_memory_callback(MEM_OFFLINE): that appears to be a
problem because notifier callbacks are made under down_read of
blocking_notifier_head->rwsem (so first the mutex is taken while holding
the rwsem, then later the rwsem is taken while still holding the mutex);
but is not in fact a problem because mem_hotplug_mutex is held throughout
the dance.
There was an attempt to fix this with mutex_lock_nested(); but if that
happened to fool lockdep two years ago, apparently it does so no longer.
I had hoped to eradicate this issue in extending KSM page migration not to
need the ksm_thread_mutex. But then realized that although the page
migration itself is safe, we do still need to lock out ksmd and other
users of get_ksm_page() while offlining memory - at some point between
MEM_GOING_OFFLINE and MEM_OFFLINE, the struct pages themselves may vanish,
and get_ksm_page()'s accesses to them become a violation.
So, give up on holding ksm_thread_mutex itself from MEM_GOING_OFFLINE to
MEM_OFFLINE, and add a KSM_RUN_OFFLINE flag, and wait_while_offlining()
checks, to achieve the same lockout without being caught by lockdep. This
is less elegant for KSM, but it's more important to keep lockdep useful to
other users - and I apologize for how long it took to fix.
Signed-off-by: Hugh Dickins <hughd@xxxxxxxxxx>
Reported-by: Gerald Schaefer <gerald.schaefer@xxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Petr Holasek <pholasek@xxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Izik Eidus <izik.eidus@xxxxxxxxxxxxxxxxxx>
Cc: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/ksm.c | 55 +++++++++++++++++++++++++++++++++++++++--------------
1 file changed, 41 insertions(+), 14 deletions(-)
diff -puN mm/ksm.c~ksm-stop-hotremove-lockdep-warning mm/ksm.c
--- a/mm/ksm.c~ksm-stop-hotremove-lockdep-warning
+++ a/mm/ksm.c
@@ -226,7 +226,9 @@ static unsigned int ksm_merge_across_nod
#define KSM_RUN_STOP 0
#define KSM_RUN_MERGE 1
#define KSM_RUN_UNMERGE 2
-static unsigned int ksm_run = KSM_RUN_STOP;
+#define KSM_RUN_OFFLINE 4
+static unsigned long ksm_run = KSM_RUN_STOP;
+static void wait_while_offlining(void);
static DECLARE_WAIT_QUEUE_HEAD(ksm_thread_wait);
static DEFINE_MUTEX(ksm_thread_mutex);
@@ -1700,6 +1702,7 @@ static int ksm_scan_thread(void *nothing
while (!kthread_should_stop()) {
mutex_lock(&ksm_thread_mutex);
+ wait_while_offlining();
if (ksmd_should_run())
ksm_do_scan(ksm_thread_pages_to_scan);
mutex_unlock(&ksm_thread_mutex);
@@ -2056,6 +2059,22 @@ void ksm_migrate_page(struct page *newpa
#endif /* CONFIG_MIGRATION */
#ifdef CONFIG_MEMORY_HOTREMOVE
+static int just_wait(void *word)
+{
+ schedule();
+ return 0;
+}
+
+static void wait_while_offlining(void)
+{
+ while (ksm_run & KSM_RUN_OFFLINE) {
+ mutex_unlock(&ksm_thread_mutex);
+ wait_on_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE),
+ just_wait, TASK_UNINTERRUPTIBLE);
+ mutex_lock(&ksm_thread_mutex);
+ }
+}
+
static void ksm_check_stable_tree(unsigned long start_pfn,
unsigned long end_pfn)
{
@@ -2098,15 +2117,15 @@ static int ksm_memory_callback(struct no
switch (action) {
case MEM_GOING_OFFLINE:
/*
- * Keep it very simple for now: just lock out ksmd and
- * MADV_UNMERGEABLE while any memory is going offline.
- * mutex_lock_nested() is necessary because lockdep was alarmed
- * that here we take ksm_thread_mutex inside notifier chain
- * mutex, and later take notifier chain mutex inside
- * ksm_thread_mutex to unlock it. But that's safe because both
- * are inside mem_hotplug_mutex.
+ * Prevent ksm_do_scan(), unmerge_and_remove_all_rmap_items()
+ * and remove_all_stable_nodes() while memory is going offline:
+ * it is unsafe for them to touch the stable tree at this time.
+ * But unmerge_ksm_pages(), rmap lookups and other entry points
+ * which do not need the ksm_thread_mutex are all safe.
*/
- mutex_lock_nested(&ksm_thread_mutex, SINGLE_DEPTH_NESTING);
+ mutex_lock(&ksm_thread_mutex);
+ ksm_run |= KSM_RUN_OFFLINE;
+ mutex_unlock(&ksm_thread_mutex);
break;
case MEM_OFFLINE:
@@ -2122,11 +2141,20 @@ static int ksm_memory_callback(struct no
/* fallthrough */
case MEM_CANCEL_OFFLINE:
+ mutex_lock(&ksm_thread_mutex);
+ ksm_run &= ~KSM_RUN_OFFLINE;
mutex_unlock(&ksm_thread_mutex);
+
+ smp_mb(); /* wake_up_bit advises this */
+ wake_up_bit(&ksm_run, ilog2(KSM_RUN_OFFLINE));
break;
}
return NOTIFY_OK;
}
+#else
+static void wait_while_offlining(void)
+{
+}
#endif /* CONFIG_MEMORY_HOTREMOVE */
#ifdef CONFIG_SYSFS
@@ -2189,7 +2217,7 @@ KSM_ATTR(pages_to_scan);
static ssize_t run_show(struct kobject *kobj, struct kobj_attribute *attr,
char *buf)
{
- return sprintf(buf, "%u\n", ksm_run);
+ return sprintf(buf, "%lu\n", ksm_run);
}
static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr,
@@ -2212,6 +2240,7 @@ static ssize_t run_store(struct kobject
*/
mutex_lock(&ksm_thread_mutex);
+ wait_while_offlining();
if (ksm_run != flags) {
ksm_run = flags;
if (flags & KSM_RUN_UNMERGE) {
@@ -2254,6 +2283,7 @@ static ssize_t merge_across_nodes_store(
return -EINVAL;
mutex_lock(&ksm_thread_mutex);
+ wait_while_offlining();
if (ksm_merge_across_nodes != knob) {
if (ksm_pages_shared || remove_all_stable_nodes())
err = -EBUSY;
@@ -2366,10 +2396,7 @@ static int __init ksm_init(void)
#endif /* CONFIG_SYSFS */
#ifdef CONFIG_MEMORY_HOTREMOVE
- /*
- * Choose a high priority since the callback takes ksm_thread_mutex:
- * later callbacks could only be taking locks which nest within that.
- */
+ /* There is no significance to this priority 100 */
hotplug_memory_notifier(ksm_memory_callback, 100);
#endif
return 0;
_
Patches currently in -mm which might be from hughd@xxxxxxxxxx are
linux-next.patch
revert-x86-mm-make-spurious_fault-check-explicitly-check-the-present-bit.patch
pageattr-prevent-pse-and-gloabl-leftovers-to-confuse-pmd-pte_present-and-pmd_huge.patch
mm-memcg-only-evict-file-pages-when-we-have-plenty.patch
mm-vmscan-save-work-scanning-almost-empty-lru-lists.patch
mm-vmscan-clarify-how-swappiness-highest-priority-memcg-interact.patch
mm-vmscan-improve-comment-on-low-page-cache-handling.patch
mm-vmscan-clean-up-get_scan_count.patch
mm-vmscan-clean-up-get_scan_count-fix.patch
mm-vmscan-compaction-works-against-zones-not-lruvecs.patch
mm-vmscan-compaction-works-against-zones-not-lruvecs-fix.patch
mm-reduce-rmap-overhead-for-ex-ksm-page-copies-created-on-swap-faults.patch
mm-page_allocc-__setup_per_zone_wmarks-make-min_pages-unsigned-long.patch
mm-vmscanc-__zone_reclaim-replace-max_t-with-max.patch
mmksm-use-new-hashtable-implementation.patch
mm-make-madvisemadv_willneed-support-swap-file-prefetch.patch
mm-make-madvisemadv_willneed-support-swap-file-prefetch-fix.patch
mm-make-madvisemadv_willneed-support-swap-file-prefetch-fix-fix.patch
mm-avoid-calling-pgdat_balanced-needlessly.patch
mm-numa-fix-minor-typo-in-numa_next_scan.patch
mm-numa-take-thp-into-account-when-migrating-pages-for-numa-balancing.patch
mm-numa-handle-side-effects-in-count_vm_numa_events-for-config_numa_balancing.patch
mm-move-page-flags-layout-to-separate-header.patch
mm-fold-page-_last_nid-into-page-flags-where-possible.patch
mm-numa-cleanup-flow-of-transhuge-page-migration.patch
mm-dont-inline-page_mapping.patch
swap-make-each-swap-partition-have-one-address_space.patch
swap-make-each-swap-partition-have-one-address_space-fix.patch
swap-add-per-partition-lock-for-swapfile.patch
memcg-reduce-the-size-of-struct-memcg-244-fold.patch
memcg-reduce-the-size-of-struct-memcg-244-fold-fix.patch
ksm-allow-trees-per-numa-node.patch
ksm-add-sysfs-abi-documentation.patch
ksm-trivial-tidyups.patch
ksm-reorganize-ksm_check_stable_tree.patch
ksm-get_ksm_page-locked.patch
ksm-remove-old-stable-nodes-more-thoroughly.patch
ksm-make-ksm-page-migration-possible.patch
ksm-make-merge_across_nodes-migration-safe.patch
ksm-enable-ksm-page-migration.patch
mm-remove-offlining-arg-to-migrate_pages.patch
ksm-stop-hotremove-lockdep-warning.patch
mm-prevent-addition-of-pages-to-swap-if-may_writepage-is-unset.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
