The patch titled
Subject: mm,hwpoison,hugetlb,memory_hotplug: hotremove memory section with hwpoisoned hugepage
has been added to the -mm mm-unstable branch. Its filename is
mmhwpoisonhugetlbmemory_hotplug-hotremove-memory-section-with-hwpoisoned-hugepage.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mmhwpoisonhugetlbmemory_hotplug-hotremove-memory-section-with-hwpoisoned-hugepage.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: Naoya Horiguchi <naoya.horiguchi@xxxxxxx>
Subject: mm,hwpoison,hugetlb,memory_hotplug: hotremove memory section with hwpoisoned hugepage
Date: Mon, 24 Oct 2022 15:20:09 +0900
Patch series "mm, hwpoison: improve handling workload related to hugetlb
and memory_hotplug", v7.
This patchset tries to solve the issue among memory_hotplug, hugetlb and hwpoison.
In this patchset, memory hotplug handles hwpoison pages like below:
- hwpoison pages should not prevent memory hotremove,
- memory block with hwpoison pages should not be onlined.
This patch (of 4):
HWPoisoned page is not supposed to be accessed once marked, but currently
such accesses can happen during memory hotremove because
do_migrate_range() can be called before dissolve_free_huge_pages() is
called.
Clear HPageMigratable for hwpoisoned hugepages to prevent them from being
migrated. This should be done in hugetlb_lock to avoid race against
isolate_hugetlb().
get_hwpoison_huge_page() needs to have a flag to show it's called from
unpoison to take refcount of hwpoisoned hugepages, so add it.
Link: https://lkml.kernel.org/r/20221024062012.1520887-1-naoya.horiguchi@xxxxxxxxx
Link: https://lkml.kernel.org/r/20221024062012.1520887-2-naoya.horiguchi@xxxxxxxxx
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@xxxxxxx>
Reported-by: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Reviewed-by: Oscar Salvador <osalvador@xxxxxxx>
Reviewed-by: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Jane Chu <jane.chu@xxxxxxxxxx>
Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Cc: Yang Shi <shy828301@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/hugetlb.h | 19 +++++++++++++++----
include/linux/mm.h | 6 ++++--
mm/hugetlb.c | 9 +++++----
mm/memory-failure.c | 19 +++++++++++++++----
4 files changed, 39 insertions(+), 14 deletions(-)
--- a/include/linux/hugetlb.h~mmhwpoisonhugetlbmemory_hotplug-hotremove-memory-section-with-hwpoisoned-hugepage
+++ a/include/linux/hugetlb.h
@@ -183,8 +183,9 @@ bool hugetlb_reserve_pages(struct inode
long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
long freed);
int isolate_hugetlb(struct page *page, struct list_head *list);
-int get_hwpoison_huge_page(struct page *page, bool *hugetlb);
-int get_huge_page_for_hwpoison(unsigned long pfn, int flags);
+int get_hwpoison_huge_page(struct page *page, bool *hugetlb, bool unpoison);
+int get_huge_page_for_hwpoison(unsigned long pfn, int flags,
+ bool *migratable_cleared);
void putback_active_hugepage(struct page *page);
void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason);
void free_huge_page(struct page *page);
@@ -391,12 +392,13 @@ static inline int isolate_hugetlb(struct
return -EBUSY;
}
-static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb)
+static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb, bool unpoison)
{
return 0;
}
-static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags)
+static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags,
+ bool *migratable_cleared)
{
return 0;
}
@@ -614,6 +616,10 @@ void folio_clear_hugetlb_##flname(struct
} \
static inline void ClearHPage##uname(struct page *page) \
{ clear_bit(HPG_##flname, &(page->private)); }
+
+#define TESTCLEARHPAGEFLAG(uname, flname) \
+static inline int TestClearHPage##uname(struct page *page) \
+ { return test_and_clear_bit(HPG_##flname, &(page->private)); }
#else
#define TESTHPAGEFLAG(uname, flname) \
static inline bool \
@@ -635,6 +641,10 @@ folio_clear_hugetlb_##flname(struct foli
{ } \
static inline void ClearHPage##uname(struct page *page) \
{ }
+
+#define TESTCLEARHPAGEFLAG(uname, flname) \
+static inline int TestClearHPage##uname(struct page *page) \
+ { return 0; }
#endif
#define HPAGEFLAG(uname, flname) \
@@ -647,6 +657,7 @@ static inline void ClearHPage##uname(str
*/
HPAGEFLAG(RestoreReserve, restore_reserve)
HPAGEFLAG(Migratable, migratable)
+ TESTCLEARHPAGEFLAG(Migratable, migratable)
HPAGEFLAG(Temporary, temporary)
HPAGEFLAG(Freed, freed)
HPAGEFLAG(VmemmapOptimized, vmemmap_optimized)
--- a/include/linux/mm.h~mmhwpoisonhugetlbmemory_hotplug-hotremove-memory-section-with-hwpoisoned-hugepage
+++ a/include/linux/mm.h
@@ -3246,9 +3246,11 @@ extern void shake_page(struct page *p);
extern atomic_long_t num_poisoned_pages __read_mostly;
extern int soft_offline_page(unsigned long pfn, int flags);
#ifdef CONFIG_MEMORY_FAILURE
-extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags);
+extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags,
+ bool *migratable_cleared);
#else
-static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags)
+static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags,
+ bool *migratable_cleared)
{
return 0;
}
--- a/mm/hugetlb.c~mmhwpoisonhugetlbmemory_hotplug-hotremove-memory-section-with-hwpoisoned-hugepage
+++ a/mm/hugetlb.c
@@ -7288,7 +7288,7 @@ unlock:
return ret;
}
-int get_hwpoison_huge_page(struct page *page, bool *hugetlb)
+int get_hwpoison_huge_page(struct page *page, bool *hugetlb, bool unpoison)
{
int ret = 0;
@@ -7298,7 +7298,7 @@ int get_hwpoison_huge_page(struct page *
*hugetlb = true;
if (HPageFreed(page))
ret = 0;
- else if (HPageMigratable(page))
+ else if (HPageMigratable(page) || unpoison)
ret = get_page_unless_zero(page);
else
ret = -EBUSY;
@@ -7307,12 +7307,13 @@ int get_hwpoison_huge_page(struct page *
return ret;
}
-int get_huge_page_for_hwpoison(unsigned long pfn, int flags)
+int get_huge_page_for_hwpoison(unsigned long pfn, int flags,
+ bool *migratable_cleared)
{
int ret;
spin_lock_irq(&hugetlb_lock);
- ret = __get_huge_page_for_hwpoison(pfn, flags);
+ ret = __get_huge_page_for_hwpoison(pfn, flags, migratable_cleared);
spin_unlock_irq(&hugetlb_lock);
return ret;
}
--- a/mm/memory-failure.c~mmhwpoisonhugetlbmemory_hotplug-hotremove-memory-section-with-hwpoisoned-hugepage
+++ a/mm/memory-failure.c
@@ -1249,7 +1249,7 @@ static int __get_hwpoison_page(struct pa
int ret = 0;
bool hugetlb = false;
- ret = get_hwpoison_huge_page(head, &hugetlb);
+ ret = get_hwpoison_huge_page(head, &hugetlb, false);
if (hugetlb)
return ret;
@@ -1339,7 +1339,7 @@ static int __get_unpoison_page(struct pa
int ret = 0;
bool hugetlb = false;
- ret = get_hwpoison_huge_page(head, &hugetlb);
+ ret = get_hwpoison_huge_page(head, &hugetlb, true);
if (hugetlb)
return ret;
@@ -1790,7 +1790,8 @@ void hugetlb_clear_page_hwpoison(struct
* -EBUSY - the hugepage is busy (try to retry)
* -EHWPOISON - the hugepage is already hwpoisoned
*/
-int __get_huge_page_for_hwpoison(unsigned long pfn, int flags)
+int __get_huge_page_for_hwpoison(unsigned long pfn, int flags,
+ bool *migratable_cleared)
{
struct page *page = pfn_to_page(pfn);
struct page *head = compound_head(page);
@@ -1820,6 +1821,13 @@ int __get_huge_page_for_hwpoison(unsigne
goto out;
}
+ /*
+ * Clearing HPageMigratable for hwpoisoned hugepages to prevent them
+ * from being migrated by memory hotremove.
+ */
+ if (count_increased)
+ *migratable_cleared = TestClearHPageMigratable(head);
+
return ret;
out:
if (count_increased)
@@ -1839,10 +1847,11 @@ static int try_memory_failure_hugetlb(un
struct page *p = pfn_to_page(pfn);
struct page *head;
unsigned long page_flags;
+ bool migratable_cleared = false;
*hugetlb = 1;
retry:
- res = get_huge_page_for_hwpoison(pfn, flags);
+ res = get_huge_page_for_hwpoison(pfn, flags, &migratable_cleared);
if (res == 2) { /* fallback to normal page handling */
*hugetlb = 0;
return 0;
@@ -1866,6 +1875,8 @@ retry:
if (hwpoison_filter(p)) {
hugetlb_clear_page_hwpoison(head);
+ if (migratable_cleared)
+ SetHPageMigratable(head);
unlock_page(head);
if (res == 1)
put_page(head);
_
Patches currently in -mm which might be from naoya.horiguchi@xxxxxxx are
mmhwpoisonhugetlbmemory_hotplug-hotremove-memory-section-with-hwpoisoned-hugepage.patch
mm-hwpoison-move-definitions-of-num_poisoned_pages_-to-memory-failurec.patch
mm-hwpoison-pass-pfn-to-num_poisoned_pages_.patch
mm-hwpoison-introduce-per-memory_block-hwpoison-counter.patch
