From: Andrew Morton <akpm@linux-foundation.org>
To: mm-commits@vger.kernel.org, songmuchun@bytedance.com,
shy828301@gmail.com, osalvador@suse.de, mike.kravetz@oracle.com,
lkp@intel.com, linmiaohe@huawei.com, jane.chu@oracle.com,
david@redhat.com, naoya.horiguchi@nec.com,
akpm@linux-foundation.org
Subject: [merged mm-stable] mm-hwpoison-introduce-per-memory_block-hwpoison-counter.patch removed from -mm tree
Date: Tue, 08 Nov 2022 17:39:35 -0800 [thread overview]
Message-ID: <20221109013935.75B6EC433C1@smtp.kernel.org> (raw)
The quilt patch titled
Subject: mm/hwpoison: introduce per-memory_block hwpoison counter
has been removed from the -mm tree. Its filename was
mm-hwpoison-introduce-per-memory_block-hwpoison-counter.patch
This patch was dropped because it was merged into the mm-stable branch
of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
------------------------------------------------------
From: Naoya Horiguchi <naoya.horiguchi@nec.com>
Subject: mm/hwpoison: introduce per-memory_block hwpoison counter
Date: Mon, 24 Oct 2022 15:20:12 +0900
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 block 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 onlining memory block contains hwpoison. struct memory_block
is freed and reallocated over ACPI-based hotremove/hotplug, but not over
sysfs-based hotremove/hotplug. So the new counter can distinguish these
cases.
Link: https://lkml.kernel.org/r/20221024062012.1520887-5-naoya.horiguchi@linux.dev
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Reported-by: kernel test robot <lkp@intel.com>
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jane Chu <jane.chu@oracle.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
drivers/base/memory.c | 38 ++++++++++++++++++++++++++++++++++++++
include/linux/memory.h | 3 +++
include/linux/mm.h | 20 +++++++++++++++++++-
mm/internal.h | 8 --------
mm/memory-failure.c | 36 +++++++++++-------------------------
mm/sparse.c | 2 --
6 files changed, 71 insertions(+), 36 deletions(-)
--- a/drivers/base/memory.c~mm-hwpoison-introduce-per-memory_block-hwpoison-counter
+++ a/drivers/base/memory.c
@@ -175,6 +175,15 @@ int memory_notify(unsigned long val, voi
return blocking_notifier_call_chain(&memory_chain, val, v);
}
+#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
+static unsigned long memblk_nr_poison(struct memory_block *mem);
+#else
+static inline unsigned long memblk_nr_poison(struct memory_block *mem)
+{
+ return 0;
+}
+#endif
+
static int memory_block_online(struct memory_block *mem)
{
unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
@@ -183,6 +192,9 @@ static int memory_block_online(struct me
struct zone *zone;
int ret;
+ if (memblk_nr_poison(mem))
+ return -EHWPOISON;
+
zone = zone_for_pfn_range(mem->online_type, mem->nid, mem->group,
start_pfn, nr_pages);
@@ -864,6 +876,7 @@ void remove_memory_block_devices(unsigne
mem = find_memory_block_by_id(block_id);
if (WARN_ON_ONCE(!mem))
continue;
+ num_poisoned_pages_sub(-1UL, memblk_nr_poison(mem));
unregister_memory_block_under_nodes(mem);
remove_memory_block(mem);
}
@@ -1164,3 +1177,28 @@ int walk_dynamic_memory_groups(int nid,
}
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);
+}
+
+static unsigned long memblk_nr_poison(struct memory_block *mem)
+{
+ return atomic_long_read(&mem->nr_hwpoison);
+}
+#endif
--- a/include/linux/memory.h~mm-hwpoison-introduce-per-memory_block-hwpoison-counter
+++ a/include/linux/memory.h
@@ -84,6 +84,9 @@ 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);
--- a/include/linux/mm.h~mm-hwpoison-introduce-per-memory_block-hwpoison-counter
+++ a/include/linux/mm.h
@@ -3279,7 +3279,8 @@ extern int soft_offline_page(unsigned lo
#ifdef CONFIG_MEMORY_FAILURE
extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags,
bool *migratable_cleared);
-extern void num_poisoned_pages_inc(unsigned long pfn);
+void num_poisoned_pages_inc(unsigned long pfn);
+void num_poisoned_pages_sub(unsigned long pfn, long i);
#else
static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags,
bool *migratable_cleared)
@@ -3290,6 +3291,23 @@ static inline int __get_huge_page_for_hw
static inline void num_poisoned_pages_inc(unsigned long pfn)
{
}
+
+static inline void num_poisoned_pages_sub(unsigned long pfn, long i)
+{
+}
+#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);
+#else
+static inline void memblk_nr_poison_inc(unsigned long pfn)
+{
+}
+
+static inline void memblk_nr_poison_sub(unsigned long pfn, long i)
+{
+}
#endif
#ifndef arch_memory_failure
--- a/mm/internal.h~mm-hwpoison-introduce-per-memory_block-hwpoison-counter
+++ a/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);
--- a/mm/memory-failure.c~mm-hwpoison-introduce-per-memory_block-hwpoison-counter
+++ a/mm/memory-failure.c
@@ -77,11 +77,14 @@ static bool hw_memory_failure __read_mos
inline 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)
+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);
}
/*
@@ -1706,6 +1709,8 @@ static unsigned long __free_raw_hwp_page
if (move_flag)
SetPageHWPoison(p->page);
+ else
+ num_poisoned_pages_sub(page_to_pfn(p->page), 1);
kfree(p);
count++;
}
@@ -2332,6 +2337,7 @@ int unpoison_memory(unsigned long pfn)
int ret = -EBUSY;
int freeit = 0;
unsigned long count = 1;
+ bool huge = false;
static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
@@ -2380,6 +2386,7 @@ int unpoison_memory(unsigned long pfn)
ret = get_hwpoison_page(p, MF_UNPOISON);
if (!ret) {
if (PageHuge(p)) {
+ huge = true;
count = free_raw_hwp_pages(page, false);
if (count == 0) {
ret = -EBUSY;
@@ -2395,6 +2402,7 @@ int unpoison_memory(unsigned long pfn)
pfn, &unpoison_rs);
} else {
if (PageHuge(p)) {
+ huge = true;
count = free_raw_hwp_pages(page, false);
if (count == 0) {
ret = -EBUSY;
@@ -2414,7 +2422,8 @@ int unpoison_memory(unsigned long pfn)
unlock_mutex:
mutex_unlock(&mf_mutex);
if (!ret || freeit) {
- num_poisoned_pages_sub(pfn, count);
+ if (!huge)
+ num_poisoned_pages_sub(pfn, 1);
unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n",
page_to_pfn(p), &unpoison_rs);
}
@@ -2609,26 +2618,3 @@ retry:
return ret;
}
-
-void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
-{
- 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(0, total);
-}
--- a/mm/sparse.c~mm-hwpoison-introduce-per-memory_block-hwpoison-counter
+++ a/mm/sparse.c
@@ -926,8 +926,6 @@ void sparse_remove_section(struct mem_se
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 */
_
Patches currently in -mm which might be from naoya.horiguchi@nec.com are
reply other threads:[~2022-11-09 1:41 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20221109013935.75B6EC433C1@smtp.kernel.org \
--to=akpm@linux-foundation.org \
--cc=david@redhat.com \
--cc=jane.chu@oracle.com \
--cc=linmiaohe@huawei.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lkp@intel.com \
--cc=mike.kravetz@oracle.com \
--cc=mm-commits@vger.kernel.org \
--cc=naoya.horiguchi@nec.com \
--cc=osalvador@suse.de \
--cc=shy828301@gmail.com \
--cc=songmuchun@bytedance.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.