mirrors
/
linux-stable
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
1
0
Fork 0
Code Issues Releases Wiki Activity

mm,hwpoison: make get_hwpoison_page() call get_any_page() 

__get_hwpoison_page() could fail to grab refcount by some race condition,
so it's helpful if we can handle it by retrying.  We already have retry
logic, so make get_hwpoison_page() call get_any_page() when called from
memory_failure().

As a result, get_hwpoison_page() can return negative values (i.e.  error
code), so some callers are also changed to handle error cases.
soft_offline_page() does nothing for -EBUSY because that's enough and
users in userspace can easily handle it.  unpoison_memory() is also
unchanged because it's broken and need thorough fixes (will be done
later).

Link: https://lkml.kernel.org/r/20210603233632.2964832-3-nao.horiguchi@gmail.com
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Naoya Horiguchi 2021-06-28 19:43:17 -07:00 committed by Linus Torvalds
parent a3f5d80ea4
commit 0ed950d1f2
2 changed files with 114 additions and 88 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
mm/hugetlb.c
View File

@ -5938,6 +5938,8 @@ int get_hwpoison_huge_page(struct page *page, bool *hugetlb)
*hugetlb = true;
if (HPageFreed(page) || HPageMigratable(page))
ret = get_page_unless_zero(page);
else
ret = -EBUSY;
}
spin_unlock_irq(&hugetlb_lock);
return ret;

200
mm/memory-failure.c
View File

@ -1117,13 +1117,6 @@ static inline bool HWPoisonHandlable(struct page *page)
return PageLRU(page) || __PageMovable(page);
}
/**
* __get_hwpoison_page() - Get refcount for memory error handling:
* @page: raw error page (hit by memory error)
*
* Return: return 0 if failed to grab the refcount, otherwise true (some
* non-zero value.)
*/
static int __get_hwpoison_page(struct page *page)
{
struct page *head = compound_head(page);
@ -1168,15 +1161,6 @@ static int __get_hwpoison_page(struct page *page)
return 0;
}
/*
* Safely get reference count of an arbitrary page.
*
* Returns 0 for a free page, 1 for an in-use page,
* -EIO for a page-type we cannot handle and -EBUSY if we raced with an
* allocation.
* We only incremented refcount in case the page was already in-use and it
* is a known type we can handle.
*/
static int get_any_page(struct page *p, unsigned long flags)
{
int ret = 0, pass = 0;
@ -1186,50 +1170,77 @@ static int get_any_page(struct page *p, unsigned long flags)
count_increased = true;
try_again:
if (!count_increased && !__get_hwpoison_page(p)) {
if (page_count(p)) {
/* We raced with an allocation, retry. */
if (pass++ < 3)
goto try_again;
ret = -EBUSY;
} else if (!PageHuge(p) && !is_free_buddy_page(p)) {
/* We raced with put_page, retry. */
if (pass++ < 3)
goto try_again;
ret = -EIO;
}
} else {
if (PageHuge(p) || HWPoisonHandlable(p)) {
ret = 1;
} else {
/*
* A page we cannot handle. Check whether we can turn
* it into something we can handle.
*/
if (pass++ < 3) {
put_page(p);
shake_page(p, 1);
count_increased = false;
goto try_again;
if (!count_increased) {
ret = __get_hwpoison_page(p);
if (!ret) {
if (page_count(p)) {
/* We raced with an allocation, retry. */
if (pass++ < 3)
goto try_again;
ret = -EBUSY;
} else if (!PageHuge(p) && !is_free_buddy_page(p)) {
/* We raced with put_page, retry. */
if (pass++ < 3)
goto try_again;
ret = -EIO;
}
put_page(p);
ret = -EIO;
goto out;
} else if (ret == -EBUSY) {
/* We raced with freeing huge page to buddy, retry. */
if (pass++ < 3)
goto try_again;
goto out;
}
}
if (PageHuge(p) || HWPoisonHandlable(p)) {
ret = 1;
} else {
/*
* A page we cannot handle. Check whether we can turn
* it into something we can handle.
*/
if (pass++ < 3) {
put_page(p);
shake_page(p, 1);
count_increased = false;
goto try_again;
}
put_page(p);
ret = -EIO;
}
out:
return ret;
}
static int get_hwpoison_page(struct page *p, unsigned long flags,
enum mf_flags ctxt)
/**
* get_hwpoison_page() - Get refcount for memory error handling
* @p: Raw error page (hit by memory error)
* @flags: Flags controlling behavior of error handling
*
* get_hwpoison_page() takes a page refcount of an error page to handle memory
* error on it, after checking that the error page is in a well-defined state
* (defined as a page-type we can successfully handle the memor error on it,
* such as LRU page and hugetlb page).
*
* Memory error handling could be triggered at any time on any type of page,
* so it's prone to race with typical memory management lifecycle (like
* allocation and free). So to avoid such races, get_hwpoison_page() takes
* extra care for the error page's state (as done in __get_hwpoison_page()),
* and has some retry logic in get_any_page().
*
* Return: 0 on failure,
* 1 on success for in-use pages in a well-defined state,
* -EIO for pages on which we can not handle memory errors,
* -EBUSY when get_hwpoison_page() has raced with page lifecycle
* operations like allocation and free.
*/
static int get_hwpoison_page(struct page *p, unsigned long flags)
{
int ret;
zone_pcp_disable(page_zone(p));
if (ctxt == MF_SOFT_OFFLINE)
ret = get_any_page(p, flags);
else
ret = __get_hwpoison_page(p);
ret = get_any_page(p, flags);
zone_pcp_enable(page_zone(p));
return ret;
@ -1418,27 +1429,33 @@ static int memory_failure_hugetlb(unsigned long pfn, int flags)
num_poisoned_pages_inc();
if (!(flags & MF_COUNT_INCREASED) && !get_hwpoison_page(p, flags, 0)) {
/*
* Check "filter hit" and "race with other subpage."
*/
lock_page(head);
if (PageHWPoison(head)) {
if ((hwpoison_filter(p) && TestClearPageHWPoison(p))
|| (p != head && TestSetPageHWPoison(head))) {
num_poisoned_pages_dec();
unlock_page(head);
return 0;
if (!(flags & MF_COUNT_INCREASED)) {
res = get_hwpoison_page(p, flags);
if (!res) {
/*
* Check "filter hit" and "race with other subpage."
*/
lock_page(head);
if (PageHWPoison(head)) {
if ((hwpoison_filter(p) && TestClearPageHWPoison(p))
|| (p != head && TestSetPageHWPoison(head))) {
num_poisoned_pages_dec();
unlock_page(head);
return 0;
}
}
unlock_page(head);
res = MF_FAILED;
if (!dissolve_free_huge_page(p) && take_page_off_buddy(p)) {
page_ref_inc(p);
res = MF_RECOVERED;
}
action_result(pfn, MF_MSG_FREE_HUGE, res);
return res == MF_RECOVERED ? 0 : -EBUSY;
} else if (res < 0) {
action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED);
return -EBUSY;
}
unlock_page(head);
res = MF_FAILED;
if (!dissolve_free_huge_page(p) && take_page_off_buddy(p)) {
page_ref_inc(p);
res = MF_RECOVERED;
}
action_result(pfn, MF_MSG_FREE_HUGE, res);
return res == MF_RECOVERED ? 0 : -EBUSY;
}
lock_page(head);
@ -1641,28 +1658,35 @@ try_again:
* In fact it's dangerous to directly bump up page count from 0,
* that may make page_ref_freeze()/page_ref_unfreeze() mismatch.
*/
if (!(flags & MF_COUNT_INCREASED) && !get_hwpoison_page(p, flags, 0)) {
if (is_free_buddy_page(p)) {
if (take_page_off_buddy(p)) {
page_ref_inc(p);
res = MF_RECOVERED;
} else {
/* We lost the race, try again */
if (retry) {
ClearPageHWPoison(p);
num_poisoned_pages_dec();
retry = false;
goto try_again;
if (!(flags & MF_COUNT_INCREASED)) {
res = get_hwpoison_page(p, flags);
if (!res) {
if (is_free_buddy_page(p)) {
if (take_page_off_buddy(p)) {
page_ref_inc(p);
res = MF_RECOVERED;
} else {
/* We lost the race, try again */
if (retry) {
ClearPageHWPoison(p);
num_poisoned_pages_dec();
retry = false;
goto try_again;
}
res = MF_FAILED;
}
res = MF_FAILED;
action_result(pfn, MF_MSG_BUDDY, res);
res = res == MF_RECOVERED ? 0 : -EBUSY;
} else {
action_result(pfn, MF_MSG_KERNEL_HIGH_ORDER, MF_IGNORED);
res = -EBUSY;
}
action_result(pfn, MF_MSG_BUDDY, res);
res = res == MF_RECOVERED ? 0 : -EBUSY;
} else {
action_result(pfn, MF_MSG_KERNEL_HIGH_ORDER, MF_IGNORED);
goto unlock_mutex;
} else if (res < 0) {
action_result(pfn, MF_MSG_UNKNOWN, MF_IGNORED);
res = -EBUSY;
goto unlock_mutex;
}
goto unlock_mutex;
}
if (PageTransHuge(hpage)) {
@ -1940,7 +1964,7 @@ int unpoison_memory(unsigned long pfn)
return 0;
}
if (!get_hwpoison_page(p, flags, 0)) {
if (!get_hwpoison_page(p, flags)) {
if (TestClearPageHWPoison(p))
num_poisoned_pages_dec();
unpoison_pr_info("Unpoison: Software-unpoisoned free page %#lx\n",
@ -2156,7 +2180,7 @@ int soft_offline_page(unsigned long pfn, int flags)
retry:
get_online_mems();
ret = get_hwpoison_page(page, flags, MF_SOFT_OFFLINE);
ret = get_hwpoison_page(page, flags);
put_online_mems();
if (ret > 0) {