summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorNaoya Horiguchi <n-horiguchi@ah.jp.nec.com>2010-05-28 09:29:20 +0900
committerAndi Kleen <ak@linux.intel.com>2010-08-11 09:22:46 +0200
commit93f70f900da36fbc19c13c2aa04b2e468c8d00fb (patch)
tree7868f891bca0ed18c9806771a68feac0b4010517 /mm
parentc9fbdd5f131440981b124883656ea21fb12cde4a (diff)
downloadlinux-93f70f900da36fbc19c13c2aa04b2e468c8d00fb.tar.bz2
HWPOISON, hugetlb: isolate corrupted hugepage
If error hugepage is not in-use, we can fully recovery from error by dequeuing it from freelist, so return RECOVERY. Otherwise whether or not we can recovery depends on user processes, so return DELAYED. Dependency: "HWPOISON, hugetlb: enable error handling path for hugepage" Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Andrew Morton <akpm@linux-foundation.org> Acked-by: Fengguang Wu <fengguang.wu@intel.com> Signed-off-by: Andi Kleen <ak@linux.intel.com>
Diffstat (limited to 'mm')
-rw-r--r--mm/hugetlb.c16
-rw-r--r--mm/memory-failure.c28
2 files changed, 36 insertions, 8 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index aa3c51739378..8c163f64cf10 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2825,3 +2825,19 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
hugetlb_put_quota(inode->i_mapping, (chg - freed));
hugetlb_acct_memory(h, -(chg - freed));
}
+
+/*
+ * This function is called from memory failure code.
+ * Assume the caller holds page lock of the head page.
+ */
+void __isolate_hwpoisoned_huge_page(struct page *hpage)
+{
+ struct hstate *h = page_hstate(hpage);
+ int nid = page_to_nid(hpage);
+
+ spin_lock(&hugetlb_lock);
+ list_del(&hpage->lru);
+ h->free_huge_pages--;
+ h->free_huge_pages_node[nid]--;
+ spin_unlock(&hugetlb_lock);
+}
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 473f15a3356d..d0b420aba726 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -690,17 +690,29 @@ static int me_swapcache_clean(struct page *p, unsigned long pfn)
/*
* Huge pages. Needs work.
* Issues:
- * No rmap support so we cannot find the original mapper. In theory could walk
- * all MMs and look for the mappings, but that would be non atomic and racy.
- * Need rmap for hugepages for this. Alternatively we could employ a heuristic,
- * like just walking the current process and hoping it has it mapped (that
- * should be usually true for the common "shared database cache" case)
- * Should handle free huge pages and dequeue them too, but this needs to
- * handle huge page accounting correctly.
+ * - Error on hugepage is contained in hugepage unit (not in raw page unit.)
+ * To narrow down kill region to one page, we need to break up pmd.
+ * - To support soft-offlining for hugepage, we need to support hugepage
+ * migration.
*/
static int me_huge_page(struct page *p, unsigned long pfn)
{
- return FAILED;
+ struct page *hpage = compound_head(p);
+ /*
+ * We can safely recover from error on free or reserved (i.e.
+ * not in-use) hugepage by dequeuing it from freelist.
+ * To check whether a hugepage is in-use or not, we can't use
+ * page->lru because it can be used in other hugepage operations,
+ * such as __unmap_hugepage_range() and gather_surplus_pages().
+ * So instead we use page_mapping() and PageAnon().
+ * We assume that this function is called with page lock held,
+ * so there is no race between isolation and mapping/unmapping.
+ */
+ if (!(page_mapping(hpage) || PageAnon(hpage))) {
+ __isolate_hwpoisoned_huge_page(hpage);
+ return RECOVERED;
+ }
+ return DELAYED;
}
/*