mm/memory-failure: fix redundant updates for already poisoned pages
commit3be306cccd
upstream. Duplicate memory errors can be reported by multiple sources. Passing an already poisoned page to action_result() causes issues: * The amount of hardware corrupted memory is incorrectly updated. * Per NUMA node MF stats are incorrectly updated. * Redundant "already poisoned" messages are printed. Avoid those issues by: * Skipping hardware corrupted memory updates for already poisoned pages. * Skipping per NUMA node MF stats updates for already poisoned pages. * Dropping redundant "already poisoned" messages. Make MF_MSG_ALREADY_POISONED consistent with other action_page_types and make calls to action_result() consistent for already poisoned normal pages and huge pages. Link: https://lkml.kernel.org/r/aLCiHMy12Ck3ouwC@hpe.com Fixes:b8b9488d50
("mm/memory-failure: improve memory failure action_result messages") Signed-off-by: Kyle Meyer <kyle.meyer@hpe.com> Reviewed-by: Jiaqi Yan <jiaqiyan@google.com> Acked-by: David Hildenbrand <david@redhat.com> Reviewed-by: Jane Chu <jane.chu@oracle.com> Acked-by: Miaohe Lin <linmiaohe@huawei.com> Cc: Borislav Betkov <bp@alien8.de> Cc: Kyle Meyer <kyle.meyer@hpe.com> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Rapoport <rppt@kernel.org> Cc: Naoya Horiguchi <nao.horiguchi@gmail.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Russ Anderson <russ.anderson@hpe.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
parent
7618fd443a
commit
de84f2978d
|
@ -948,7 +948,7 @@ static const char * const action_page_types[] = {
|
|||
[MF_MSG_BUDDY] = "free buddy page",
|
||||
[MF_MSG_DAX] = "dax page",
|
||||
[MF_MSG_UNSPLIT_THP] = "unsplit thp",
|
||||
[MF_MSG_ALREADY_POISONED] = "already poisoned",
|
||||
[MF_MSG_ALREADY_POISONED] = "already poisoned page",
|
||||
[MF_MSG_UNKNOWN] = "unknown page",
|
||||
};
|
||||
|
||||
|
@ -1341,9 +1341,10 @@ static int action_result(unsigned long pfn, enum mf_action_page_type type,
|
|||
{
|
||||
trace_memory_failure_event(pfn, type, result);
|
||||
|
||||
num_poisoned_pages_inc(pfn);
|
||||
|
||||
update_per_node_mf_stats(pfn, result);
|
||||
if (type != MF_MSG_ALREADY_POISONED) {
|
||||
num_poisoned_pages_inc(pfn);
|
||||
update_per_node_mf_stats(pfn, result);
|
||||
}
|
||||
|
||||
pr_err("%#lx: recovery action for %s: %s\n",
|
||||
pfn, action_page_types[type], action_name[result]);
|
||||
|
@ -2086,12 +2087,11 @@ retry:
|
|||
*hugetlb = 0;
|
||||
return 0;
|
||||
} else if (res == -EHWPOISON) {
|
||||
pr_err("%#lx: already hardware poisoned\n", pfn);
|
||||
if (flags & MF_ACTION_REQUIRED) {
|
||||
folio = page_folio(p);
|
||||
res = kill_accessing_process(current, folio_pfn(folio), flags);
|
||||
action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED);
|
||||
}
|
||||
action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED);
|
||||
return res;
|
||||
} else if (res == -EBUSY) {
|
||||
if (!(flags & MF_NO_RETRY)) {
|
||||
|
@ -2273,7 +2273,6 @@ try_again:
|
|||
goto unlock_mutex;
|
||||
|
||||
if (TestSetPageHWPoison(p)) {
|
||||
pr_err("%#lx: already hardware poisoned\n", pfn);
|
||||
res = -EHWPOISON;
|
||||
if (flags & MF_ACTION_REQUIRED)
|
||||
res = kill_accessing_process(current, pfn, flags);
|
||||
|
|
Loading…
Reference in New Issue