Hi,
This patchset tries to solve the issue among memory_hotplug, hugetlb and
hwpoison. Based on the review over v2 by Miaohe (thank you!), 1/4 takes
another approach to prevent hwpoisoned hugepages to be migrated (i.e.
the corrupted data is accessed) in memory hotremove.
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.
Any comments and feedbacks would be appreciated.
Thanks,
Naoya Horiguchi
v1: https://lore.kernel.org/linux-mm/[email protected]/T
v2: https://lore.kernel.org/linux-mm/[email protected]/T
---
Summary:
Naoya Horiguchi (4):
mm,hwpoison,hugetlb,memory_hotplug: hotremove memory section with hwpoisoned hugepage
mm/hwpoison: move definitions of num_poisoned_pages_* to memory-failure.c
mm/hwpoison: pass pfn to num_poisoned_pages_*()
mm/hwpoison: introduce per-memory_block hwpoison counter
arch/parisc/kernel/pdt.c | 5 ++--
drivers/base/memory.c | 36 +++++++++++++++++++++++++++++
include/linux/hugetlb.h | 4 ++--
include/linux/memory.h | 3 +++
include/linux/mm.h | 13 +++++++++++
include/linux/swapops.h | 24 ++------------------
mm/hugetlb.c | 4 ++--
mm/internal.h | 8 -------
mm/memory-failure.c | 59 +++++++++++++++++++++++++++---------------------
mm/sparse.c | 2 --
10 files changed, 93 insertions(+), 65 deletions(-)
From: Naoya Horiguchi <[email protected]>
Currently PageHWPoison flag does not behave well when experiencing memory
hotremove/hotplug. Any data field in struct page is unreliable when the
associated memory is offlined, and the current mechanism can't tell whether
a memory section is onlined because a new memory devices is installed or
because previous failed offline operations are undone. Especially if
there's a hwpoisoned memory, it's unclear what the best option is.
So introduce a new mechanism to make struct memory_block remember that
a memory block has hwpoisoned memory inside it. And make any online event
fail if the onlined memory block contains hwpoison. struct memory_block
is freed and reallocated over ACPI-based hotremove/hotplug, but not over
sysfs-based hotremove/hotplug. So it's desirable to implement hwpoison
counter on this struct.
Note that clear_hwpoisoned_pages() is relocated to be called earlier than
now, just before unregistering struct memory_block. Otherwise, the
per-memory_block hwpoison counter is freed and we fail to adjust global
hwpoison counter properly.
Signed-off-by: Naoya Horiguchi <[email protected]>
---
drivers/base/memory.c | 36 ++++++++++++++++++++++++++++++++++++
include/linux/memory.h | 3 +++
include/linux/mm.h | 8 ++++++++
mm/internal.h | 8 --------
mm/memory-failure.c | 31 ++++++++++---------------------
mm/sparse.c | 2 --
6 files changed, 57 insertions(+), 31 deletions(-)
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 9aa0da991cfb..c9bde4c4ffdf 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -183,6 +183,9 @@ static int memory_block_online(struct memory_block *mem)
struct zone *zone;
int ret;
+ if (atomic_long_read(&mem->nr_hwpoison))
+ return -EHWPOISON;
+
zone = zone_for_pfn_range(mem->online_type, mem->nid, mem->group,
start_pfn, nr_pages);
@@ -864,6 +867,7 @@ void remove_memory_block_devices(unsigned long start, unsigned long size)
mem = find_memory_block_by_id(block_id);
if (WARN_ON_ONCE(!mem))
continue;
+ clear_hwpoisoned_pages(atomic_long_read(&mem->nr_hwpoison));
unregister_memory_block_under_nodes(mem);
remove_memory_block(mem);
}
@@ -1164,3 +1168,35 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func,
}
return ret;
}
+
+#ifdef CONFIG_MEMORY_FAILURE
+
+void memblk_nr_poison_inc(unsigned long pfn)
+{
+ const unsigned long block_id = pfn_to_block_id(pfn);
+ struct memory_block *mem = find_memory_block_by_id(block_id);
+
+ if (mem)
+ atomic_long_inc(&mem->nr_hwpoison);
+}
+
+void memblk_nr_poison_sub(unsigned long pfn, long i)
+{
+ const unsigned long block_id = pfn_to_block_id(pfn);
+ struct memory_block *mem = find_memory_block_by_id(block_id);
+
+ if (mem)
+ atomic_long_sub(i, &mem->nr_hwpoison);
+}
+
+unsigned long memblk_nr_poison(unsigned long pfn)
+{
+ const unsigned long block_id = pfn_to_block_id(pfn);
+ struct memory_block *mem = find_memory_block_by_id(block_id);
+
+ if (mem)
+ return atomic_long_read(&mem->nr_hwpoison);
+ return 0;
+}
+
+#endif
diff --git a/include/linux/memory.h b/include/linux/memory.h
index aa619464a1df..74e6b3ad947f 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -85,6 +85,9 @@ struct memory_block {
unsigned long nr_vmemmap_pages;
struct memory_group *group; /* group (if any) for this block */
struct list_head group_next; /* next block inside memory group */
+#ifdef CONFIG_MEMORY_FAILURE
+ atomic_long_t nr_hwpoison;
+#endif
};
int arch_get_memory_phys_device(unsigned long start_pfn);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2bb5d1596041..2fe42bb9a517 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3280,6 +3280,10 @@ 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 void num_poisoned_pages_inc(unsigned long pfn);
+extern void memblk_nr_poison_inc(unsigned long pfn);
+extern void memblk_nr_poison_sub(unsigned long pfn, long i);
+extern unsigned long memblk_nr_poison(unsigned long pfn);
+extern void clear_hwpoisoned_pages(long nr_poison);
#else
static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags)
{
@@ -3289,6 +3293,10 @@ static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags)
static inline void num_poisoned_pages_inc(unsigned long pfn)
{
}
+
+static inline void clear_hwpoisoned_pages(long nr_poison)
+{
+}
#endif
#ifndef arch_memory_failure
diff --git a/mm/internal.h b/mm/internal.h
index b3002e03c28f..42ba8b96cab5 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -708,14 +708,6 @@ extern u64 hwpoison_filter_flags_value;
extern u64 hwpoison_filter_memcg;
extern u32 hwpoison_filter_enable;
-#ifdef CONFIG_MEMORY_FAILURE
-void clear_hwpoisoned_pages(struct page *memmap, int nr_pages);
-#else
-static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
-{
-}
-#endif
-
extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long,
unsigned long, unsigned long,
unsigned long, unsigned long);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index a069d43bc87f..03479895086d 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -74,14 +74,17 @@ atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
static bool hw_memory_failure __read_mostly = false;
-static inline void num_poisoned_pages_inc(unsigned long pfn)
+void num_poisoned_pages_inc(unsigned long pfn)
{
atomic_long_inc(&num_poisoned_pages);
+ memblk_nr_poison_inc(pfn);
}
static inline void num_poisoned_pages_sub(unsigned long pfn, long i)
{
atomic_long_sub(i, &num_poisoned_pages);
+ if (pfn != -1UL)
+ memblk_nr_poison_sub(pfn, i);
}
/*
@@ -2414,6 +2417,10 @@ int unpoison_memory(unsigned long pfn)
unlock_mutex:
mutex_unlock(&mf_mutex);
if (!ret || freeit) {
+ /*
+ * TODO: per-memory_block counter might break when the page
+ * size to be unpoisoned is larger than a memory_block.
+ */
num_poisoned_pages_sub(pfn, count);
unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n",
page_to_pfn(p), &unpoison_rs);
@@ -2618,25 +2625,7 @@ int soft_offline_page(unsigned long pfn, int flags)
return ret;
}
-void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
+void clear_hwpoisoned_pages(long nr_poison)
{
- int i, total = 0;
-
- /*
- * A further optimization is to have per section refcounted
- * num_poisoned_pages. But that would need more space per memmap, so
- * for now just do a quick global check to speed up this routine in the
- * absence of bad pages.
- */
- if (atomic_long_read(&num_poisoned_pages) == 0)
- return;
-
- for (i = 0; i < nr_pages; i++) {
- if (PageHWPoison(&memmap[i])) {
- total++;
- ClearPageHWPoison(&memmap[i]);
- }
- }
- if (total)
- num_poisoned_pages_sub(total);
+ num_poisoned_pages_sub(-1UL, nr_poison);
}
diff --git a/mm/sparse.c b/mm/sparse.c
index e5a8a3a0edd7..2779b419ef2a 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -926,8 +926,6 @@ void sparse_remove_section(struct mem_section *ms, unsigned long pfn,
unsigned long nr_pages, unsigned long map_offset,
struct vmem_altmap *altmap)
{
- clear_hwpoisoned_pages(pfn_to_page(pfn) + map_offset,
- nr_pages - map_offset);
section_deactivate(pfn, nr_pages, altmap);
}
#endif /* CONFIG_MEMORY_HOTPLUG */
--
2.25.1
From: Naoya Horiguchi <[email protected]>
These interfaces will be used by drivers/base/core.c by later patch, so as a
preparatory work move them to more common header file visible to the file.
Signed-off-by: Naoya Horiguchi <[email protected]>
---
ChangeLog v2 -> v3:
- added declaration of num_poisoned_pages_inc() in #ifdef CONFIG_MEMORY_FAILURE
---
arch/parisc/kernel/pdt.c | 3 +--
include/linux/mm.h | 5 +++++
include/linux/swapops.h | 24 ++----------------------
mm/memory-failure.c | 10 ++++++++++
4 files changed, 18 insertions(+), 24 deletions(-)
diff --git a/arch/parisc/kernel/pdt.c b/arch/parisc/kernel/pdt.c
index e391b175f5ec..fdc880e2575a 100644
--- a/arch/parisc/kernel/pdt.c
+++ b/arch/parisc/kernel/pdt.c
@@ -18,8 +18,7 @@
#include <linux/kthread.h>
#include <linux/initrd.h>
#include <linux/pgtable.h>
-#include <linux/swap.h>
-#include <linux/swapops.h>
+#include <linux/mm.h>
#include <asm/pdc.h>
#include <asm/pdcpat.h>
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c2277f5aba9e..80a2d800f272 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3279,11 +3279,16 @@ 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 void num_poisoned_pages_inc(void);
#else
static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags)
{
return 0;
}
+
+static inline void num_poisoned_pages_inc(void)
+{
+}
#endif
#ifndef arch_memory_failure
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index a91dd08e107b..3e58a812399a 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -581,8 +581,6 @@ static inline int is_pmd_migration_entry(pmd_t pmd)
#ifdef CONFIG_MEMORY_FAILURE
-extern atomic_long_t num_poisoned_pages __read_mostly;
-
/*
* Support for hardware poisoned pages
*/
@@ -610,17 +608,7 @@ static inline struct page *hwpoison_entry_to_page(swp_entry_t entry)
return p;
}
-static inline void num_poisoned_pages_inc(void)
-{
- atomic_long_inc(&num_poisoned_pages);
-}
-
-static inline void num_poisoned_pages_sub(long i)
-{
- atomic_long_sub(i, &num_poisoned_pages);
-}
-
-#else /* CONFIG_MEMORY_FAILURE */
+#else
static inline swp_entry_t make_hwpoison_entry(struct page *page)
{
@@ -636,15 +624,7 @@ static inline struct page *hwpoison_entry_to_page(swp_entry_t entry)
{
return NULL;
}
-
-static inline void num_poisoned_pages_inc(void)
-{
-}
-
-static inline void num_poisoned_pages_sub(long i)
-{
-}
-#endif /* CONFIG_MEMORY_FAILURE */
+#endif
static inline int non_swap_entry(swp_entry_t entry)
{
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 5942e1c0407e..aa6ce685b863 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -74,6 +74,16 @@ atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
static bool hw_memory_failure __read_mostly = false;
+static inline void num_poisoned_pages_inc(void)
+{
+ atomic_long_inc(&num_poisoned_pages);
+}
+
+static inline void num_poisoned_pages_sub(long i)
+{
+ atomic_long_sub(i, &num_poisoned_pages);
+}
+
/*
* Return values:
* 1: the page is dissolved (if needed) and taken off from buddy,
--
2.25.1
From: Naoya Horiguchi <[email protected]>
No functional change.
Signed-off-by: Naoya Horiguchi <[email protected]>
Reviewed-by: Miaohe Lin <[email protected]>
---
ChangeLog v2 -> v3:
- added declaration of num_poisoned_pages_inc() in #ifdef CONFIG_MEMORY_FAILURE
---
arch/parisc/kernel/pdt.c | 2 +-
include/linux/mm.h | 4 ++--
mm/memory-failure.c | 12 ++++++------
3 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/arch/parisc/kernel/pdt.c b/arch/parisc/kernel/pdt.c
index fdc880e2575a..80943a00e245 100644
--- a/arch/parisc/kernel/pdt.c
+++ b/arch/parisc/kernel/pdt.c
@@ -231,7 +231,7 @@ void __init pdc_pdt_init(void)
/* mark memory page bad */
memblock_reserve(pdt_entry[i] & PAGE_MASK, PAGE_SIZE);
- num_poisoned_pages_inc();
+ num_poisoned_pages_inc(addr >> PAGE_SHIFT);
}
}
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 80a2d800f272..2bb5d1596041 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3279,14 +3279,14 @@ 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 void num_poisoned_pages_inc(void);
+extern void num_poisoned_pages_inc(unsigned long pfn);
#else
static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags)
{
return 0;
}
-static inline void num_poisoned_pages_inc(void)
+static inline void num_poisoned_pages_inc(unsigned long pfn)
{
}
#endif
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index aa6ce685b863..a069d43bc87f 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -74,12 +74,12 @@ atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
static bool hw_memory_failure __read_mostly = false;
-static inline void num_poisoned_pages_inc(void)
+static inline void num_poisoned_pages_inc(unsigned long pfn)
{
atomic_long_inc(&num_poisoned_pages);
}
-static inline void num_poisoned_pages_sub(long i)
+static inline void num_poisoned_pages_sub(unsigned long pfn, long i)
{
atomic_long_sub(i, &num_poisoned_pages);
}
@@ -125,7 +125,7 @@ static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, boo
if (release)
put_page(page);
page_ref_inc(page);
- num_poisoned_pages_inc();
+ num_poisoned_pages_inc(page_to_pfn(page));
return true;
}
@@ -1194,7 +1194,7 @@ static void action_result(unsigned long pfn, enum mf_action_page_type type,
{
trace_memory_failure_event(pfn, type, result);
- num_poisoned_pages_inc();
+ num_poisoned_pages_inc(pfn);
pr_err("%#lx: recovery action for %s: %s\n",
pfn, action_page_types[type], action_name[result]);
}
@@ -1741,7 +1741,7 @@ static int hugetlb_set_page_hwpoison(struct page *hpage, struct page *page)
llist_add(&raw_hwp->node, head);
/* the first error event will be counted in action_result(). */
if (ret)
- num_poisoned_pages_inc();
+ num_poisoned_pages_inc(page_to_pfn(page));
} else {
/*
* Failed to save raw error info. We no longer trace all
@@ -2414,7 +2414,7 @@ int unpoison_memory(unsigned long pfn)
unlock_mutex:
mutex_unlock(&mf_mutex);
if (!ret || freeit) {
- num_poisoned_pages_sub(count);
+ num_poisoned_pages_sub(pfn, count);
unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n",
page_to_pfn(p), &unpoison_rs);
}
--
2.25.1
From: Naoya Horiguchi <[email protected]>
Currently PageHWPoison flag does not behave well when experiencing memory
hotremove/hotplug. Any data field in struct page is unreliable when the
associated memory is offlined, and the current mechanism can't tell whether
a memory section is onlined because a new memory devices is installed or
because previous failed offline operations are undone. Especially if
there's a hwpoisoned memory, it's unclear what the best option is.
So introduce a new mechanism to make struct memory_block remember that
a memory block has hwpoisoned memory inside it. And make any online event
fail if the onlined memory block contains hwpoison. struct memory_block
is freed and reallocated over ACPI-based hotremove/hotplug, but not over
sysfs-based hotremove/hotplug. So it's desirable to implement hwpoison
counter on this struct.
Note that clear_hwpoisoned_pages() is relocated to be called earlier than
now, just before unregistering struct memory_block. Otherwise, the
per-memory_block hwpoison counter is freed and we fail to adjust global
hwpoison counter properly.
Signed-off-by: Naoya Horiguchi <[email protected]>
---
ChangeLog v3 -> v4:
- fixed build error (https://lore.kernel.org/linux-mm/[email protected]/)
by using memblk_nr_poison() to access to the member ->nr_hwpoison
---
drivers/base/memory.c | 41 +++++++++++++++++++++++++++++++++++++++++
include/linux/memory.h | 3 +++
include/linux/mm.h | 8 ++++++++
mm/internal.h | 8 --------
mm/memory-failure.c | 31 ++++++++++---------------------
mm/sparse.c | 2 --
6 files changed, 62 insertions(+), 31 deletions(-)
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 9aa0da991cfb..f470bbfc68d0 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -183,6 +183,9 @@ static int memory_block_online(struct memory_block *mem)
struct zone *zone;
int ret;
+ if (memblk_nr_poison(start_pfn))
+ return -EHWPOISON;
+
zone = zone_for_pfn_range(mem->online_type, mem->nid, mem->group,
start_pfn, nr_pages);
@@ -864,6 +867,7 @@ void remove_memory_block_devices(unsigned long start, unsigned long size)
mem = find_memory_block_by_id(block_id);
if (WARN_ON_ONCE(!mem))
continue;
+ clear_hwpoisoned_pages(memblk_nr_poison(start));
unregister_memory_block_under_nodes(mem);
remove_memory_block(mem);
}
@@ -1164,3 +1168,40 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func,
}
return ret;
}
+
+#ifdef CONFIG_MEMORY_FAILURE
+
+void memblk_nr_poison_inc(unsigned long pfn)
+{
+ const unsigned long block_id = pfn_to_block_id(pfn);
+ struct memory_block *mem = find_memory_block_by_id(block_id);
+
+ if (mem)
+ atomic_long_inc(&mem->nr_hwpoison);
+}
+
+void memblk_nr_poison_sub(unsigned long pfn, long i)
+{
+ const unsigned long block_id = pfn_to_block_id(pfn);
+ struct memory_block *mem = find_memory_block_by_id(block_id);
+
+ if (mem)
+ atomic_long_sub(i, &mem->nr_hwpoison);
+}
+
+unsigned long memblk_nr_poison(unsigned long pfn)
+{
+ const unsigned long block_id = pfn_to_block_id(pfn);
+ struct memory_block *mem = find_memory_block_by_id(block_id);
+
+ if (mem)
+ return atomic_long_read(&mem->nr_hwpoison);
+ return 0;
+}
+
+#else
+unsigned long memblk_nr_poison(unsigned long pfn)
+{
+ return 0;
+}
+#endif
diff --git a/include/linux/memory.h b/include/linux/memory.h
index aa619464a1df..74e6b3ad947f 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -85,6 +85,9 @@ struct memory_block {
unsigned long nr_vmemmap_pages;
struct memory_group *group; /* group (if any) for this block */
struct list_head group_next; /* next block inside memory group */
+#ifdef CONFIG_MEMORY_FAILURE
+ atomic_long_t nr_hwpoison;
+#endif
};
int arch_get_memory_phys_device(unsigned long start_pfn);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2bb5d1596041..5445943bbb4b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3280,6 +3280,9 @@ 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 void num_poisoned_pages_inc(unsigned long pfn);
+extern void memblk_nr_poison_inc(unsigned long pfn);
+extern void memblk_nr_poison_sub(unsigned long pfn, long i);
+extern void clear_hwpoisoned_pages(long nr_poison);
#else
static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags)
{
@@ -3289,7 +3292,12 @@ static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags)
static inline void num_poisoned_pages_inc(unsigned long pfn)
{
}
+
+static inline void clear_hwpoisoned_pages(long nr_poison)
+{
+}
#endif
+extern unsigned long memblk_nr_poison(unsigned long pfn);
#ifndef arch_memory_failure
static inline int arch_memory_failure(unsigned long pfn, int flags)
diff --git a/mm/internal.h b/mm/internal.h
index b3002e03c28f..42ba8b96cab5 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -708,14 +708,6 @@ extern u64 hwpoison_filter_flags_value;
extern u64 hwpoison_filter_memcg;
extern u32 hwpoison_filter_enable;
-#ifdef CONFIG_MEMORY_FAILURE
-void clear_hwpoisoned_pages(struct page *memmap, int nr_pages);
-#else
-static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
-{
-}
-#endif
-
extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long,
unsigned long, unsigned long,
unsigned long, unsigned long);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index a069d43bc87f..03479895086d 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -74,14 +74,17 @@ atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
static bool hw_memory_failure __read_mostly = false;
-static inline void num_poisoned_pages_inc(unsigned long pfn)
+void num_poisoned_pages_inc(unsigned long pfn)
{
atomic_long_inc(&num_poisoned_pages);
+ memblk_nr_poison_inc(pfn);
}
static inline void num_poisoned_pages_sub(unsigned long pfn, long i)
{
atomic_long_sub(i, &num_poisoned_pages);
+ if (pfn != -1UL)
+ memblk_nr_poison_sub(pfn, i);
}
/*
@@ -2414,6 +2417,10 @@ int unpoison_memory(unsigned long pfn)
unlock_mutex:
mutex_unlock(&mf_mutex);
if (!ret || freeit) {
+ /*
+ * TODO: per-memory_block counter might break when the page
+ * size to be unpoisoned is larger than a memory_block.
+ */
num_poisoned_pages_sub(pfn, count);
unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n",
page_to_pfn(p), &unpoison_rs);
@@ -2618,25 +2625,7 @@ int soft_offline_page(unsigned long pfn, int flags)
return ret;
}
-void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
+void clear_hwpoisoned_pages(long nr_poison)
{
- int i, total = 0;
-
- /*
- * A further optimization is to have per section refcounted
- * num_poisoned_pages. But that would need more space per memmap, so
- * for now just do a quick global check to speed up this routine in the
- * absence of bad pages.
- */
- if (atomic_long_read(&num_poisoned_pages) == 0)
- return;
-
- for (i = 0; i < nr_pages; i++) {
- if (PageHWPoison(&memmap[i])) {
- total++;
- ClearPageHWPoison(&memmap[i]);
- }
- }
- if (total)
- num_poisoned_pages_sub(total);
+ num_poisoned_pages_sub(-1UL, nr_poison);
}
diff --git a/mm/sparse.c b/mm/sparse.c
index e5a8a3a0edd7..2779b419ef2a 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -926,8 +926,6 @@ void sparse_remove_section(struct mem_section *ms, unsigned long pfn,
unsigned long nr_pages, unsigned long map_offset,
struct vmem_altmap *altmap)
{
- clear_hwpoisoned_pages(pfn_to_page(pfn) + map_offset,
- nr_pages - map_offset);
section_deactivate(pfn, nr_pages, altmap);
}
#endif /* CONFIG_MEMORY_HOTPLUG */
--
2.37.3.518.g79f2338b37
There seems another build error in aarch64 with MEMORY_HOTPLUG disabled.
https://lore.kernel.org/lkml/[email protected]/
, so let me revise this patch again to handle it.
- Naoya Horiguchi
---
From: Naoya Horiguchi <[email protected]>
Date: Fri, 23 Sep 2022 22:51:20 +0900
Subject: [PATCH v5 4/4] mm/hwpoison: introduce per-memory_block hwpoison counter
Currently PageHWPoison flag does not behave well when experiencing memory
hotremove/hotplug. Any data field in struct page is unreliable when the
associated memory is offlined, and the current mechanism can't tell whether
a memory section is onlined because a new memory devices is installed or
because previous failed offline operations are undone. Especially if
there's a hwpoisoned memory, it's unclear what the best option is.
So introduce a new mechanism to make struct memory_block remember that
a memory block has hwpoisoned memory inside it. And make any online event
fail if the onlined memory block contains hwpoison. struct memory_block
is freed and reallocated over ACPI-based hotremove/hotplug, but not over
sysfs-based hotremove/hotplug. So it's desirable to implement hwpoison
counter on this struct.
Note that clear_hwpoisoned_pages() is relocated to be called earlier than
now, just before unregistering struct memory_block. Otherwise, the
per-memory_block hwpoison counter is freed and we fail to adjust global
hwpoison counter properly.
Signed-off-by: Naoya Horiguchi <[email protected]>
Reported-by: kernel test robot <[email protected]>
---
ChangeLog v4 -> v5:
- add Reported-by of lkp bot,
- check both CONFIG_MEMORY_FAILURE and CONFIG_MEMORY_HOTPLUG in introduced #ifdefs,
intending to fix "undefined reference" errors in aarch64.
ChangeLog v3 -> v4:
- fix build error (https://lore.kernel.org/linux-mm/[email protected]/)
by using memblk_nr_poison() to access to the member ->nr_hwpoison
---
drivers/base/memory.c | 34 ++++++++++++++++++++++++++++++++++
include/linux/memory.h | 3 +++
include/linux/mm.h | 24 ++++++++++++++++++++++++
mm/internal.h | 8 --------
mm/memory-failure.c | 31 ++++++++++---------------------
mm/sparse.c | 2 --
6 files changed, 71 insertions(+), 31 deletions(-)
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 9aa0da991cfb..99e0e789616c 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -183,6 +183,9 @@ static int memory_block_online(struct memory_block *mem)
struct zone *zone;
int ret;
+ if (memblk_nr_poison(start_pfn))
+ return -EHWPOISON;
+
zone = zone_for_pfn_range(mem->online_type, mem->nid, mem->group,
start_pfn, nr_pages);
@@ -864,6 +867,7 @@ void remove_memory_block_devices(unsigned long start, unsigned long size)
mem = find_memory_block_by_id(block_id);
if (WARN_ON_ONCE(!mem))
continue;
+ clear_hwpoisoned_pages(memblk_nr_poison(start));
unregister_memory_block_under_nodes(mem);
remove_memory_block(mem);
}
@@ -1164,3 +1168,33 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func,
}
return ret;
}
+
+#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
+void memblk_nr_poison_inc(unsigned long pfn)
+{
+ const unsigned long block_id = pfn_to_block_id(pfn);
+ struct memory_block *mem = find_memory_block_by_id(block_id);
+
+ if (mem)
+ atomic_long_inc(&mem->nr_hwpoison);
+}
+
+void memblk_nr_poison_sub(unsigned long pfn, long i)
+{
+ const unsigned long block_id = pfn_to_block_id(pfn);
+ struct memory_block *mem = find_memory_block_by_id(block_id);
+
+ if (mem)
+ atomic_long_sub(i, &mem->nr_hwpoison);
+}
+
+unsigned long memblk_nr_poison(unsigned long pfn)
+{
+ const unsigned long block_id = pfn_to_block_id(pfn);
+ struct memory_block *mem = find_memory_block_by_id(block_id);
+
+ if (mem)
+ return atomic_long_read(&mem->nr_hwpoison);
+ return 0;
+}
+#endif
diff --git a/include/linux/memory.h b/include/linux/memory.h
index aa619464a1df..ad8cd9bb3239 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -85,6 +85,9 @@ struct memory_block {
unsigned long nr_vmemmap_pages;
struct memory_group *group; /* group (if any) for this block */
struct list_head group_next; /* next block inside memory group */
+#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
+ atomic_long_t nr_hwpoison;
+#endif
};
int arch_get_memory_phys_device(unsigned long start_pfn);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2bb5d1596041..936864d6f8be 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3280,6 +3280,7 @@ 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 void num_poisoned_pages_inc(unsigned long pfn);
+extern void clear_hwpoisoned_pages(long nr_poison);
#else
static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags)
{
@@ -3289,6 +3290,29 @@ static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags)
static inline void num_poisoned_pages_inc(unsigned long pfn)
{
}
+
+static inline void clear_hwpoisoned_pages(long nr_poison)
+{
+}
+#endif
+
+#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
+extern void memblk_nr_poison_inc(unsigned long pfn);
+extern void memblk_nr_poison_sub(unsigned long pfn, long i);
+extern unsigned long memblk_nr_poison(unsigned long pfn);
+#else
+static inline void memblk_nr_poison_inc(unsigned long pfn)
+{
+}
+
+static inline void memblk_nr_poison_sub(unsigned long pfn, long i)
+{
+}
+
+static inline unsigned long memblk_nr_poison(unsigned long pfn)
+{
+ return 0;
+}
#endif
#ifndef arch_memory_failure
diff --git a/mm/internal.h b/mm/internal.h
index b3002e03c28f..42ba8b96cab5 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -708,14 +708,6 @@ extern u64 hwpoison_filter_flags_value;
extern u64 hwpoison_filter_memcg;
extern u32 hwpoison_filter_enable;
-#ifdef CONFIG_MEMORY_FAILURE
-void clear_hwpoisoned_pages(struct page *memmap, int nr_pages);
-#else
-static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
-{
-}
-#endif
-
extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long,
unsigned long, unsigned long,
unsigned long, unsigned long);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index a069d43bc87f..03479895086d 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -74,14 +74,17 @@ atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
static bool hw_memory_failure __read_mostly = false;
-static inline void num_poisoned_pages_inc(unsigned long pfn)
+void num_poisoned_pages_inc(unsigned long pfn)
{
atomic_long_inc(&num_poisoned_pages);
+ memblk_nr_poison_inc(pfn);
}
static inline void num_poisoned_pages_sub(unsigned long pfn, long i)
{
atomic_long_sub(i, &num_poisoned_pages);
+ if (pfn != -1UL)
+ memblk_nr_poison_sub(pfn, i);
}
/*
@@ -2414,6 +2417,10 @@ int unpoison_memory(unsigned long pfn)
unlock_mutex:
mutex_unlock(&mf_mutex);
if (!ret || freeit) {
+ /*
+ * TODO: per-memory_block counter might break when the page
+ * size to be unpoisoned is larger than a memory_block.
+ */
num_poisoned_pages_sub(pfn, count);
unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n",
page_to_pfn(p), &unpoison_rs);
@@ -2618,25 +2625,7 @@ int soft_offline_page(unsigned long pfn, int flags)
return ret;
}
-void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
+void clear_hwpoisoned_pages(long nr_poison)
{
- int i, total = 0;
-
- /*
- * A further optimization is to have per section refcounted
- * num_poisoned_pages. But that would need more space per memmap, so
- * for now just do a quick global check to speed up this routine in the
- * absence of bad pages.
- */
- if (atomic_long_read(&num_poisoned_pages) == 0)
- return;
-
- for (i = 0; i < nr_pages; i++) {
- if (PageHWPoison(&memmap[i])) {
- total++;
- ClearPageHWPoison(&memmap[i]);
- }
- }
- if (total)
- num_poisoned_pages_sub(total);
+ num_poisoned_pages_sub(-1UL, nr_poison);
}
diff --git a/mm/sparse.c b/mm/sparse.c
index e5a8a3a0edd7..2779b419ef2a 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -926,8 +926,6 @@ void sparse_remove_section(struct mem_section *ms, unsigned long pfn,
unsigned long nr_pages, unsigned long map_offset,
struct vmem_altmap *altmap)
{
- clear_hwpoisoned_pages(pfn_to_page(pfn) + map_offset,
- nr_pages - map_offset);
section_deactivate(pfn, nr_pages, altmap);
}
#endif /* CONFIG_MEMORY_HOTPLUG */
--
2.37.3.518.g79f2338b37
> /*
> @@ -2414,6 +2417,10 @@ int unpoison_memory(unsigned long pfn)
> unlock_mutex:
> mutex_unlock(&mf_mutex);
> if (!ret || freeit) {
> + /*
> + * TODO: per-memory_block counter might break when the page
> + * size to be unpoisoned is larger than a memory_block.
> + */
Hmm, but that happens easily e.g., with 1 GiB hugetlb page and 128 MiB
memory section/block size. What would be the right thing to do here? The
TODO should rather spell that out instead of just stating the problem.
--
Thanks,
David / dhildenb
On Sat, Sep 24, 2022 at 07:53:15PM +0800, Miaohe Lin wrote:
> On 2022/9/21 17:13, Naoya Horiguchi wrote:
> > From: Naoya Horiguchi <[email protected]>
> >
> > These interfaces will be used by drivers/base/core.c by later patch, so as a
> > preparatory work move them to more common header file visible to the file.
> >
> > Signed-off-by: Naoya Horiguchi <[email protected]>
> > ---
> > ChangeLog v2 -> v3:
> > - added declaration of num_poisoned_pages_inc() in #ifdef CONFIG_MEMORY_FAILURE
> > ---
> > arch/parisc/kernel/pdt.c | 3 +--
> > include/linux/mm.h | 5 +++++
> > include/linux/swapops.h | 24 ++----------------------
> > mm/memory-failure.c | 10 ++++++++++
> > 4 files changed, 18 insertions(+), 24 deletions(-)
> >
> > diff --git a/arch/parisc/kernel/pdt.c b/arch/parisc/kernel/pdt.c
> > index e391b175f5ec..fdc880e2575a 100644
> > --- a/arch/parisc/kernel/pdt.c
> > +++ b/arch/parisc/kernel/pdt.c
> > @@ -18,8 +18,7 @@
> > #include <linux/kthread.h>
> > #include <linux/initrd.h>
> > #include <linux/pgtable.h>
> > -#include <linux/swap.h>
>
> Is header file "linux/swap.h" already unneeded before the code change? It seems there's
> no code change in that file.
Maybe yes. I updated this line too because it's introduced together
swapops.h by the following commit.
commit 0e5a7ff6e36ad58933d076ddcac36ff14d014692
Author: Helge Deller <[email protected]>
Date: Fri Jul 24 19:17:52 2020 +0200
parisc: Report bad pages as HardwareCorrupted
>
> > -#include <linux/swapops.h>
> > +#include <linux/mm.h>
> >
> > #include <asm/pdc.h>
> > #include <asm/pdcpat.h>
> > diff --git a/include/linux/mm.h b/include/linux/mm.h
> > index c2277f5aba9e..80a2d800f272 100644
> > --- a/include/linux/mm.h
> > +++ b/include/linux/mm.h
> > @@ -3279,11 +3279,16 @@ 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 void num_poisoned_pages_inc(void);
> > #else
> > static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags)
> > {
> > return 0;
> > }
> > +
> > +static inline void num_poisoned_pages_inc(void)
> > +{
> > +}
> > #endif
> >
> > #ifndef arch_memory_failure
> > diff --git a/include/linux/swapops.h b/include/linux/swapops.h
> > index a91dd08e107b..3e58a812399a 100644
> > --- a/include/linux/swapops.h
> > +++ b/include/linux/swapops.h
> > @@ -581,8 +581,6 @@ static inline int is_pmd_migration_entry(pmd_t pmd)
> >
> > #ifdef CONFIG_MEMORY_FAILURE
> >
> > -extern atomic_long_t num_poisoned_pages __read_mostly;
> > -
> > /*
> > * Support for hardware poisoned pages
> > */
> > @@ -610,17 +608,7 @@ static inline struct page *hwpoison_entry_to_page(swp_entry_t entry)
> > return p;
> > }
> >
> > -static inline void num_poisoned_pages_inc(void)
> > -{
> > - atomic_long_inc(&num_poisoned_pages);
> > -}
> > -
> > -static inline void num_poisoned_pages_sub(long i)
> > -{
> > - atomic_long_sub(i, &num_poisoned_pages);
> > -}
> > -
> > -#else /* CONFIG_MEMORY_FAILURE */
> > +#else
> >
> > static inline swp_entry_t make_hwpoison_entry(struct page *page)
> > {
> > @@ -636,15 +624,7 @@ static inline struct page *hwpoison_entry_to_page(swp_entry_t entry)
> > {
> > return NULL;
> > }
> > -
> > -static inline void num_poisoned_pages_inc(void)
> > -{
> > -}
> > -
> > -static inline void num_poisoned_pages_sub(long i)
> > -{
> > -}
> > -#endif /* CONFIG_MEMORY_FAILURE */
> > +#endif
> >
> > static inline int non_swap_entry(swp_entry_t entry)
> > {
> > diff --git a/mm/memory-failure.c b/mm/memory-failure.c
> > index 5942e1c0407e..aa6ce685b863 100644
> > --- a/mm/memory-failure.c
> > +++ b/mm/memory-failure.c
> > @@ -74,6 +74,16 @@ atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
> >
> > static bool hw_memory_failure __read_mostly = false;
> >
> > +static inline void num_poisoned_pages_inc(void)
>
> This function is defined as "static inline" while it's "extern void num_poisoned_pages_inc(void)"
> in the header file. Is this expected?
No. 4/4 effectively fixes it, but I should've done this in this patch.
Thank you,
- Naoya Horiguchi
>
> Thanks,
> Miaohe Lin
>
> > +{
> > + atomic_long_inc(&num_poisoned_pages);
> > +}
> > +
> > +static inline void num_poisoned_pages_sub(long i)
> > +{
> > + atomic_long_sub(i, &num_poisoned_pages);
> > +}
> > +
> > /*
> > * Return values:
> > * 1: the page is dissolved (if needed) and taken off from buddy,
> >
>
On Sat, Sep 24, 2022 at 08:27:35PM +0800, Miaohe Lin wrote:
> On 2022/9/23 22:12, Naoya Horiguchi wrote:
> > There seems another build error in aarch64 with MEMORY_HOTPLUG disabled.
> > https://lore.kernel.org/lkml/[email protected]/
> > , so let me revise this patch again to handle it.
> >
> > - Naoya Horiguchi
> >
> > ---
> > From: Naoya Horiguchi <[email protected]>
> > Date: Fri, 23 Sep 2022 22:51:20 +0900
> > Subject: [PATCH v5 4/4] mm/hwpoison: introduce per-memory_block hwpoison counter
> >
> > Currently PageHWPoison flag does not behave well when experiencing memory
> > hotremove/hotplug. Any data field in struct page is unreliable when the
> > associated memory is offlined, and the current mechanism can't tell whether
> > a memory section is onlined because a new memory devices is installed or
> > because previous failed offline operations are undone. Especially if
> > there's a hwpoisoned memory, it's unclear what the best option is.
> >
> > So introduce a new mechanism to make struct memory_block remember that
> > a memory block has hwpoisoned memory inside it. And make any online event
> > fail if the onlined memory block contains hwpoison. struct memory_block
> > is freed and reallocated over ACPI-based hotremove/hotplug, but not over
> > sysfs-based hotremove/hotplug. So it's desirable to implement hwpoison
> > counter on this struct.
> >
> > Note that clear_hwpoisoned_pages() is relocated to be called earlier than
> > now, just before unregistering struct memory_block. Otherwise, the
> > per-memory_block hwpoison counter is freed and we fail to adjust global
> > hwpoison counter properly.
> >
> > Signed-off-by: Naoya Horiguchi <[email protected]>
> > Reported-by: kernel test robot <[email protected]>
>
> LGTM with some nits below. Thanks.
>
> Reviewed-by: Miaohe Lin <[email protected]>
Thank you.
>
> > ---
> > ChangeLog v4 -> v5:
> > - add Reported-by of lkp bot,
> > - check both CONFIG_MEMORY_FAILURE and CONFIG_MEMORY_HOTPLUG in introduced #ifdefs,
> > intending to fix "undefined reference" errors in aarch64.
> >
> > ChangeLog v3 -> v4:
> > - fix build error (https://lore.kernel.org/linux-mm/[email protected]/)
> > by using memblk_nr_poison() to access to the member ->nr_hwpoison
> > ---
> > drivers/base/memory.c | 34 ++++++++++++++++++++++++++++++++++
> > include/linux/memory.h | 3 +++
> > include/linux/mm.h | 24 ++++++++++++++++++++++++
> > mm/internal.h | 8 --------
> > mm/memory-failure.c | 31 ++++++++++---------------------
> > mm/sparse.c | 2 --
> > 6 files changed, 71 insertions(+), 31 deletions(-)
> >
> > diff --git a/drivers/base/memory.c b/drivers/base/memory.c
> > index 9aa0da991cfb..99e0e789616c 100644
> > --- a/drivers/base/memory.c
> > +++ b/drivers/base/memory.c
> > @@ -183,6 +183,9 @@ static int memory_block_online(struct memory_block *mem)
> > struct zone *zone;
> > int ret;
> >
> > + if (memblk_nr_poison(start_pfn))
> > + return -EHWPOISON;
> > +
> > zone = zone_for_pfn_range(mem->online_type, mem->nid, mem->group,
> > start_pfn, nr_pages);
> >
> > @@ -864,6 +867,7 @@ void remove_memory_block_devices(unsigned long start, unsigned long size)
> > mem = find_memory_block_by_id(block_id);
> > if (WARN_ON_ONCE(!mem))
> > continue;
> > + clear_hwpoisoned_pages(memblk_nr_poison(start));
>
> clear_hwpoisoned_pages seems not a proper name now? PageHWPoison info is kept now. But this should be trivial.
>
Right, I think that the name num_poisoned_pages_sub() is clear enough, so
I'll open this function.
> > unregister_memory_block_under_nodes(mem);
> > remove_memory_block(mem);
> > }
> > @@ -1164,3 +1168,33 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func,
> > }
> > return ret;
> > }
> > +
> > +#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
> > +void memblk_nr_poison_inc(unsigned long pfn)
> > +{
> > + const unsigned long block_id = pfn_to_block_id(pfn);
> > + struct memory_block *mem = find_memory_block_by_id(block_id);
> > +
> > + if (mem)
> > + atomic_long_inc(&mem->nr_hwpoison);
> > +}
> > +
> > +void memblk_nr_poison_sub(unsigned long pfn, long i)
> > +{
> > + const unsigned long block_id = pfn_to_block_id(pfn);
> > + struct memory_block *mem = find_memory_block_by_id(block_id);
> > +
> > + if (mem)
> > + atomic_long_sub(i, &mem->nr_hwpoison);
> > +}
> > +
> > +unsigned long memblk_nr_poison(unsigned long pfn)
>
> memblk_nr_poison() is only used inside this file. Make it static?
Thanks, I'll add it.
Thanks,
Naoya Horiguchi
On Mon, Sep 26, 2022 at 10:05:05AM +0200, David Hildenbrand wrote:
> > /*
> > @@ -2414,6 +2417,10 @@ int unpoison_memory(unsigned long pfn)
> > unlock_mutex:
> > mutex_unlock(&mf_mutex);
> > if (!ret || freeit) {
> > + /*
> > + * TODO: per-memory_block counter might break when the page
> > + * size to be unpoisoned is larger than a memory_block.
> > + */
>
> Hmm, but that happens easily e.g., with 1 GiB hugetlb page and 128 MiB
> memory section/block size. What would be the right thing to do here? The
> TODO should rather spell that out instead of just stating the problem.
What should we need here is to cancel the per-memory_block hwpoison counts
in each memory block associated with the hugepage to be unpoisoned.
I found that it can be done with additional several lines of code, so
v6 will contain them. Then, this TODO comment is no longer needed.
Thanks,
Naoya Horiguchi