1 files changed, 112 insertions, 182 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 1a88006ec634..bc48ee783dd9 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -20,9 +20,9 @@
 #include <linux/slab.h>
 #include <linux/sched/signal.h>
 #include <linux/rmap.h>
+#include <linux/string_helpers.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
-#include <linux/page-isolation.h>
 #include <linux/jhash.h>
 
 #include <asm/page.h>
@@ -872,7 +872,7 @@ static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
 	struct page *page;
 
 	list_for_each_entry(page, &h->hugepage_freelists[nid], lru)
-		if (!is_migrate_isolate_page(page))
+		if (!PageHWPoison(page))
 			break;
 	/*
 	 * if 'non-isolated free hugepage' not found on the list,
@@ -887,19 +887,39 @@ static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
 	return page;
 }
 
-static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
+static struct page *dequeue_huge_page_nodemask(struct hstate *h, gfp_t gfp_mask, int nid,
+		nodemask_t *nmask)
 {
-	struct page *page;
-	int node;
+	unsigned int cpuset_mems_cookie;
+	struct zonelist *zonelist;
+	struct zone *zone;
+	struct zoneref *z;
+	int node = -1;
 
-	if (nid != NUMA_NO_NODE)
-		return dequeue_huge_page_node_exact(h, nid);
+	zonelist = node_zonelist(nid, gfp_mask);
+
+retry_cpuset:
+	cpuset_mems_cookie = read_mems_allowed_begin();
+	for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nmask) {
+		struct page *page;
+
+		if (!cpuset_zone_allowed(zone, gfp_mask))
+			continue;
+		/*
+		 * no need to ask again on the same node. Pool is node rather than
+		 * zone aware
+		 */
+		if (zone_to_nid(zone) == node)
+			continue;
+		node = zone_to_nid(zone);
 
-	for_each_online_node(node) {
 		page = dequeue_huge_page_node_exact(h, node);
 		if (page)
 			return page;
 	}
+	if (unlikely(read_mems_allowed_retry(cpuset_mems_cookie)))
+		goto retry_cpuset;
+
 	return NULL;
 }
 
@@ -917,15 +937,11 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 				unsigned long address, int avoid_reserve,
 				long chg)
 {
-	struct page *page = NULL;
+	struct page *page;
 	struct mempolicy *mpol;
-	nodemask_t *nodemask;
 	gfp_t gfp_mask;
+	nodemask_t *nodemask;
 	int nid;
-	struct zonelist *zonelist;
-	struct zone *zone;
-	struct zoneref *z;
-	unsigned int cpuset_mems_cookie;
 
 	/*
 	 * A child process with MAP_PRIVATE mappings created by their parent
@@ -940,32 +956,15 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 	if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0)
 		goto err;
 
-retry_cpuset:
-	cpuset_mems_cookie = read_mems_allowed_begin();
 	gfp_mask = htlb_alloc_mask(h);
 	nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
-	zonelist = node_zonelist(nid, gfp_mask);
-
-	for_each_zone_zonelist_nodemask(zone, z, zonelist,
-						MAX_NR_ZONES - 1, nodemask) {
-		if (cpuset_zone_allowed(zone, gfp_mask)) {
-			page = dequeue_huge_page_node(h, zone_to_nid(zone));
-			if (page) {
-				if (avoid_reserve)
-					break;
-				if (!vma_has_reserves(vma, chg))
-					break;
-
-				SetPagePrivate(page);
-				h->resv_huge_pages--;
-				break;
-			}
-		}
+	page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask);
+	if (page && !avoid_reserve && vma_has_reserves(vma, chg)) {
+		SetPagePrivate(page);
+		h->resv_huge_pages--;
 	}
 
 	mpol_cond_put(mpol);
-	if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie)))
-		goto retry_cpuset;
 	return page;
 
 err:
@@ -1385,7 +1384,7 @@ static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 
 	page = __alloc_pages_node(nid,
 		htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE|
-						__GFP_REPEAT|__GFP_NOWARN,
+						__GFP_RETRY_MAYFAIL|__GFP_NOWARN,
 		huge_page_order(h));
 	if (page) {
 		prep_new_huge_page(h, page, nid);
@@ -1460,7 +1459,7 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
  * number of free hugepages would be reduced below the number of reserved
  * hugepages.
  */
-static int dissolve_free_huge_page(struct page *page)
+int dissolve_free_huge_page(struct page *page)
 {
 	int rc = 0;
 
@@ -1473,6 +1472,14 @@ static int dissolve_free_huge_page(struct page *page)
 			rc = -EBUSY;
 			goto out;
 		}
+		/*
+		 * Move PageHWPoison flag from head page to the raw error page,
+		 * which makes any subpages rather than the error page reusable.
+		 */
+		if (PageHWPoison(head) && page != head) {
+			SetPageHWPoison(page);
+			ClearPageHWPoison(head);
+		}
 		list_del(&head->lru);
 		h->free_huge_pages--;
 		h->free_huge_pages_node[nid]--;
@@ -1513,82 +1520,19 @@ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
 	return rc;
 }
 
-/*
- * There are 3 ways this can get called:
- * 1. With vma+addr: we use the VMA's memory policy
- * 2. With !vma, but nid=NUMA_NO_NODE:  We try to allocate a huge
- *    page from any node, and let the buddy allocator itself figure
- *    it out.
- * 3. With !vma, but nid!=NUMA_NO_NODE.  We allocate a huge page
- *    strictly from 'nid'
- */
 static struct page *__hugetlb_alloc_buddy_huge_page(struct hstate *h,
-		struct vm_area_struct *vma, unsigned long addr, int nid)
+		gfp_t gfp_mask, int nid, nodemask_t *nmask)
 {
 	int order = huge_page_order(h);
-	gfp_t gfp = htlb_alloc_mask(h)|__GFP_COMP|__GFP_REPEAT|__GFP_NOWARN;
-	unsigned int cpuset_mems_cookie;
-
-	/*
-	 * We need a VMA to get a memory policy.  If we do not
-	 * have one, we use the 'nid' argument.
-	 *
-	 * The mempolicy stuff below has some non-inlined bits
-	 * and calls ->vm_ops.  That makes it hard to optimize at
-	 * compile-time, even when NUMA is off and it does
-	 * nothing.  This helps the compiler optimize it out.
-	 */
-	if (!IS_ENABLED(CONFIG_NUMA) || !vma) {
-		/*
-		 * If a specific node is requested, make sure to
-		 * get memory from there, but only when a node
-		 * is explicitly specified.
-		 */
-		if (nid != NUMA_NO_NODE)
-			gfp |= __GFP_THISNODE;
-		/*
-		 * Make sure to call something that can handle
-		 * nid=NUMA_NO_NODE
-		 */
-		return alloc_pages_node(nid, gfp, order);
-	}
-
-	/*
-	 * OK, so we have a VMA.  Fetch the mempolicy and try to
-	 * allocate a huge page with it.  We will only reach this
-	 * when CONFIG_NUMA=y.
-	 */
-	do {
-		struct page *page;
-		struct mempolicy *mpol;
-		int nid;
-		nodemask_t *nodemask;
-
-		cpuset_mems_cookie = read_mems_allowed_begin();
-		nid = huge_node(vma, addr, gfp, &mpol, &nodemask);
-		mpol_cond_put(mpol);
-		page = __alloc_pages_nodemask(gfp, order, nid, nodemask);
-		if (page)
-			return page;
-	} while (read_mems_allowed_retry(cpuset_mems_cookie));
 
-	return NULL;
+	gfp_mask |= __GFP_COMP|__GFP_RETRY_MAYFAIL|__GFP_NOWARN;
+	if (nid == NUMA_NO_NODE)
+		nid = numa_mem_id();
+	return __alloc_pages_nodemask(gfp_mask, order, nid, nmask);
 }
 
-/*
- * There are two ways to allocate a huge page:
- * 1. When you have a VMA and an address (like a fault)
- * 2. When you have no VMA (like when setting /proc/.../nr_hugepages)
- *
- * 'vma' and 'addr' are only for (1).  'nid' is always NUMA_NO_NODE in
- * this case which signifies that the allocation should be done with
- * respect for the VMA's memory policy.
- *
- * For (2), we ignore 'vma' and 'addr' and use 'nid' exclusively. This
- * implies that memory policies will not be taken in to account.
- */
-static struct page *__alloc_buddy_huge_page(struct hstate *h,
-		struct vm_area_struct *vma, unsigned long addr, int nid)
+static struct page *__alloc_buddy_huge_page(struct hstate *h, gfp_t gfp_mask,
+		int nid, nodemask_t *nmask)
 {
 	struct page *page;
 	unsigned int r_nid;
@@ -1597,15 +1541,6 @@ static struct page *__alloc_buddy_huge_page(struct hstate *h,
 		return NULL;
 
 	/*
-	 * Make sure that anyone specifying 'nid' is not also specifying a VMA.
-	 * This makes sure the caller is picking _one_ of the modes with which
-	 * we can call this function, not both.
-	 */
-	if (vma || (addr != -1)) {
-		VM_WARN_ON_ONCE(addr == -1);
-		VM_WARN_ON_ONCE(nid != NUMA_NO_NODE);
-	}
-	/*
 	 * Assume we will successfully allocate the surplus page to
 	 * prevent racing processes from causing the surplus to exceed
 	 * overcommit
@@ -1638,7 +1573,7 @@ static struct page *__alloc_buddy_huge_page(struct hstate *h,
 	}
 	spin_unlock(&hugetlb_lock);
 
-	page = __hugetlb_alloc_buddy_huge_page(h, vma, addr, nid);
+	page = __hugetlb_alloc_buddy_huge_page(h, gfp_mask, nid, nmask);
 
 	spin_lock(&hugetlb_lock);
 	if (page) {
@@ -1663,26 +1598,23 @@ static struct page *__alloc_buddy_huge_page(struct hstate *h,
 }
 
 /*
- * Allocate a huge page from 'nid'.  Note, 'nid' may be
- * NUMA_NO_NODE, which means that it may be allocated
- * anywhere.
- */
-static
-struct page *__alloc_buddy_huge_page_no_mpol(struct hstate *h, int nid)
-{
-	unsigned long addr = -1;
-
-	return __alloc_buddy_huge_page(h, NULL, addr, nid);
-}
-
-/*
  * Use the VMA's mpolicy to allocate a huge page from the buddy.
  */
 static
 struct page *__alloc_buddy_huge_page_with_mpol(struct hstate *h,
 		struct vm_area_struct *vma, unsigned long addr)
 {
-	return __alloc_buddy_huge_page(h, vma, addr, NUMA_NO_NODE);
+	struct page *page;
+	struct mempolicy *mpol;
+	gfp_t gfp_mask = htlb_alloc_mask(h);
+	int nid;
+	nodemask_t *nodemask;
+
+	nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask);
+	page = __alloc_buddy_huge_page(h, gfp_mask, nid, nodemask);
+	mpol_cond_put(mpol);
+
+	return page;
 }
 
 /*
@@ -1692,19 +1624,46 @@ struct page *__alloc_buddy_huge_page_with_mpol(struct hstate *h,
  */
 struct page *alloc_huge_page_node(struct hstate *h, int nid)
 {
+	gfp_t gfp_mask = htlb_alloc_mask(h);
 	struct page *page = NULL;
 
+	if (nid != NUMA_NO_NODE)
+		gfp_mask |= __GFP_THISNODE;
+
 	spin_lock(&hugetlb_lock);
 	if (h->free_huge_pages - h->resv_huge_pages > 0)
-		page = dequeue_huge_page_node(h, nid);
+		page = dequeue_huge_page_nodemask(h, gfp_mask, nid, NULL);
 	spin_unlock(&hugetlb_lock);
 
 	if (!page)
-		page = __alloc_buddy_huge_page_no_mpol(h, nid);
+		page = __alloc_buddy_huge_page(h, gfp_mask, nid, NULL);
 
 	return page;
 }
 
+
+struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
+		nodemask_t *nmask)
+{
+	gfp_t gfp_mask = htlb_alloc_mask(h);
+
+	spin_lock(&hugetlb_lock);
+	if (h->free_huge_pages - h->resv_huge_pages > 0) {
+		struct page *page;
+
+		page = dequeue_huge_page_nodemask(h, gfp_mask, preferred_nid, nmask);
+		if (page) {
+			spin_unlock(&hugetlb_lock);
+			return page;
+		}
+	}
+	spin_unlock(&hugetlb_lock);
+
+	/* No reservations, try to overcommit */
+
+	return __alloc_buddy_huge_page(h, gfp_mask, preferred_nid, nmask);
+}
+
 /*
  * Increase the hugetlb pool such that it can accommodate a reservation
  * of size 'delta'.
@@ -1730,12 +1689,14 @@ static int gather_surplus_pages(struct hstate *h, int delta)
 retry:
 	spin_unlock(&hugetlb_lock);
 	for (i = 0; i < needed; i++) {
-		page = __alloc_buddy_huge_page_no_mpol(h, NUMA_NO_NODE);
+		page = __alloc_buddy_huge_page(h, htlb_alloc_mask(h),
+				NUMA_NO_NODE, NULL);
 		if (!page) {
 			alloc_ok = false;
 			break;
 		}
 		list_add(&page->lru, &surplus_list);
+		cond_resched();
 	}
 	allocated += i;
 
@@ -2204,8 +2165,16 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
 		} else if (!alloc_fresh_huge_page(h,
 					 &node_states[N_MEMORY]))
 			break;
+		cond_resched();
+	}
+	if (i < h->max_huge_pages) {
+		char buf[32];
+
+		string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32);
+		pr_warn("HugeTLB: allocating %lu of page size %s failed.  Only allocated %lu hugepages.\n",
+			h->max_huge_pages, buf, i);
+		h->max_huge_pages = i;
 	}
-	h->max_huge_pages = i;
 }
 
 static void __init hugetlb_init_hstates(void)
@@ -2223,26 +2192,16 @@ static void __init hugetlb_init_hstates(void)
 	VM_BUG_ON(minimum_order == UINT_MAX);
 }
 
-static char * __init memfmt(char *buf, unsigned long n)
-{
-	if (n >= (1UL << 30))
-		sprintf(buf, "%lu GB", n >> 30);
-	else if (n >= (1UL << 20))
-		sprintf(buf, "%lu MB", n >> 20);
-	else
-		sprintf(buf, "%lu KB", n >> 10);
-	return buf;
-}
-
 static void __init report_hugepages(void)
 {
 	struct hstate *h;
 
 	for_each_hstate(h) {
 		char buf[32];
+
+		string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32);
 		pr_info("HugeTLB registered %s page size, pre-allocated %ld pages\n",
-			memfmt(buf, huge_page_size(h)),
-			h->free_huge_pages);
+			buf, h->free_huge_pages);
 	}
 }
 
@@ -2801,6 +2760,11 @@ static int __init hugetlb_init(void)
 		return 0;
 
 	if (!size_to_hstate(default_hstate_size)) {
+		if (default_hstate_size != 0) {
+			pr_err("HugeTLB: unsupported default_hugepagesz %lu. Reverting to %lu\n",
+			       default_hstate_size, HPAGE_SIZE);
+		}
+
 		default_hstate_size = HPAGE_SIZE;
 		if (!size_to_hstate(default_hstate_size))
 			hugetlb_add_hstate(HUGETLB_PAGE_ORDER);
@@ -4739,40 +4703,6 @@ follow_huge_pgd(struct mm_struct *mm, unsigned long address, pgd_t *pgd, int fla
 	return pte_page(*(pte_t *)pgd) + ((address & ~PGDIR_MASK) >> PAGE_SHIFT);
 }
 
-#ifdef CONFIG_MEMORY_FAILURE
-
-/*
- * This function is called from memory failure code.
- */
-int dequeue_hwpoisoned_huge_page(struct page *hpage)
-{
-	struct hstate *h = page_hstate(hpage);
-	int nid = page_to_nid(hpage);
-	int ret = -EBUSY;
-
-	spin_lock(&hugetlb_lock);
-	/*
-	 * Just checking !page_huge_active is not enough, because that could be
-	 * an isolated/hwpoisoned hugepage (which have >0 refcount).
-	 */
-	if (!page_huge_active(hpage) && !page_count(hpage)) {
-		/*
-		 * Hwpoisoned hugepage isn't linked to activelist or freelist,
-		 * but dangling hpage->lru can trigger list-debug warnings
-		 * (this happens when we call unpoison_memory() on it),
-		 * so let it point to itself with list_del_init().
-		 */
-		list_del_init(&hpage->lru);
-		set_page_refcounted(hpage);
-		h->free_huge_pages--;
-		h->free_huge_pages_node[nid]--;
-		ret = 0;
-	}
-	spin_unlock(&hugetlb_lock);
-	return ret;
-}
-#endif
-
 bool isolate_huge_page(struct page *page, struct list_head *list)
 {
 	bool ret = true;