mm/madvise: enable (soft|hard) offline of HugeTLB pages at PGD level

Though migrating gigantic HugeTLB pages does not sound much like real
world use case, they can be affected by memory errors.  Hence migration
at the PGD level HugeTLB pages should be supported just to enable soft
and hard offline use cases.

While allocating the new gigantic HugeTLB page, it should not matter
whether new page comes from the same node or not.  There would be very
few gigantic pages on the system afterall, we should not be bothered
about node locality when trying to save a big page from crashing.

This change renames dequeu_huge_page_node() function as dequeue_huge
_page_node_exact() preserving it's original functionality.  Now the new
dequeue_huge_page_node() function scans through all available online nodes
to allocate a huge page for the NUMA_NO_NODE case and just falls back
calling dequeu_huge_page_node_exact() for all other cases.

[arnd@arndb.de: make hstate_is_gigantic() inline]
  Link: http://lkml.kernel.org/r/20170522124748.3911296-1-arnd@arndb.de
Link: http://lkml.kernel.org/r/20170516100509.20122-1-khandual@linux.vnet.ibm.com
Signed-off-by: Anshuman Khandual <khandual@linux.vnet.ibm.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/hugetlb.h

@@ -466,7 +466,11 @@ extern int dissolve_free_huge_pages(unsigned long start_pfn,
 static inline bool hugepage_migration_supported(struct hstate *h)
 {
 #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
-	return huge_page_shift(h) == PMD_SHIFT;
+	if ((huge_page_shift(h) == PMD_SHIFT) ||
+		(huge_page_shift(h) == PGDIR_SHIFT))
+		return true;
+	else
+		return false;
 #else
 	return false;
 #endif
@@ -518,6 +522,11 @@ struct hstate {};
 #define vma_mmu_pagesize(v) PAGE_SIZE
 #define huge_page_order(h) 0
 #define huge_page_shift(h) PAGE_SHIFT
+static inline bool hstate_is_gigantic(struct hstate *h)
+{
+	return false;
+}
+
 static inline unsigned int pages_per_huge_page(struct hstate *h)
 {
 	return 1;

mm/hugetlb.c

@@ -867,7 +867,7 @@ static void enqueue_huge_page(struct hstate *h, struct page *page)
 	h->free_huge_pages_node[nid]++;
 }
 
-static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
+static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
 {
 	struct page *page;
 
@@ -887,6 +887,22 @@ static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
 	return page;
 }
 
+static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
+{
+	struct page *page;
+	int node;
+
+	if (nid != NUMA_NO_NODE)
+		return dequeue_huge_page_node_exact(h, nid);
+
+	for_each_online_node(node) {
+		page = dequeue_huge_page_node_exact(h, node);
+		if (page)
+			return page;
+	}
+	return NULL;
+}
+
 /* Movability of hugepages depends on migration support. */
 static inline gfp_t htlb_alloc_mask(struct hstate *h)
 {

mm/memory-failure.c

@@ -1492,11 +1492,16 @@ EXPORT_SYMBOL(unpoison_memory);
 static struct page *new_page(struct page *p, unsigned long private, int **x)
 {
 	int nid = page_to_nid(p);
-	if (PageHuge(p))
-		return alloc_huge_page_node(page_hstate(compound_head(p)),
-						   nid);
-	else
+	if (PageHuge(p)) {
+		struct hstate *hstate = page_hstate(compound_head(p));
+
+		if (hstate_is_gigantic(hstate))
+			return alloc_huge_page_node(hstate, NUMA_NO_NODE);
+
+		return alloc_huge_page_node(hstate, nid);
+	} else {
 		return __alloc_pages_node(nid, GFP_HIGHUSER_MOVABLE, 0);
+	}
 }
 
 /*