1 files changed, 163 insertions, 70 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index c03273807182..96991ded82fe 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -423,14 +423,14 @@ static void clear_huge_page(struct page *page,
         }
 }
 
-static void copy_gigantic_page(struct page *dst, struct page *src,
+static void copy_user_gigantic_page(struct page *dst, struct page *src,
                            unsigned long addr, struct vm_area_struct *vma)
 {
         int i;
         struct hstate *h = hstate_vma(vma);
         struct page *dst_base = dst;
         struct page *src_base = src;
-        might_sleep();
+
         for (i = 0; i < pages_per_huge_page(h); ) {
                 cond_resched();
                 copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma);
@@ -440,14 +440,15 @@ static void copy_gigantic_page(struct page *dst, struct page *src,
                 src = mem_map_next(src, src_base, i);
         }
 }
-static void copy_huge_page(struct page *dst, struct page *src,
+
+static void copy_user_huge_page(struct page *dst, struct page *src,
                            unsigned long addr, struct vm_area_struct *vma)
 {
         int i;
         struct hstate *h = hstate_vma(vma);
 
         if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) {
-                copy_gigantic_page(dst, src, addr, vma);
+                copy_user_gigantic_page(dst, src, addr, vma);
                 return;
         }
 
@@ -458,6 +459,40 @@ static void copy_huge_page(struct page *dst, struct page *src,
         }
 }
 
+static void copy_gigantic_page(struct page *dst, struct page *src)
+{
+        int i;
+        struct hstate *h = page_hstate(src);
+        struct page *dst_base = dst;
+        struct page *src_base = src;
+
+        for (i = 0; i < pages_per_huge_page(h); ) {
+                cond_resched();
+                copy_highpage(dst, src);
+
+                i++;
+                dst = mem_map_next(dst, dst_base, i);
+                src = mem_map_next(src, src_base, i);
+        }
+}
+
+void copy_huge_page(struct page *dst, struct page *src)
+{
+        int i;
+        struct hstate *h = page_hstate(src);
+
+        if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) {
+                copy_gigantic_page(dst, src);
+                return;
+        }
+
+        might_sleep();
+        for (i = 0; i < pages_per_huge_page(h); i++) {
+                cond_resched();
+                copy_highpage(dst + i, src + i);
+        }
+}
+
 static void enqueue_huge_page(struct hstate *h, struct page *page)
 {
         int nid = page_to_nid(page);
@@ -466,11 +501,24 @@ 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)
+{
+        struct page *page;
+
+        if (list_empty(&h->hugepage_freelists[nid]))
+                return NULL;
+        page = list_entry(h->hugepage_freelists[nid].next, struct page, lru);
+        list_del(&page->lru);
+        set_page_refcounted(page);
+        h->free_huge_pages--;
+        h->free_huge_pages_node[nid]--;
+        return page;
+}
+
 static struct page *dequeue_huge_page_vma(struct hstate *h,
                                 struct vm_area_struct *vma,
                                 unsigned long address, int avoid_reserve)
 {
-        int nid;
         struct page *page = NULL;
         struct mempolicy *mpol;
         nodemask_t *nodemask;
@@ -496,19 +544,13 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 
         for_each_zone_zonelist_nodemask(zone, z, zonelist,
                                                 MAX_NR_ZONES - 1, nodemask) {
-                nid = zone_to_nid(zone);
-                if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask) &&
-                    !list_empty(&h->hugepage_freelists[nid])) {
-                        page = list_entry(h->hugepage_freelists[nid].next,
-                                          struct page, lru);
-                        list_del(&page->lru);
-                        h->free_huge_pages--;
-                        h->free_huge_pages_node[nid]--;
-
-                        if (!avoid_reserve)
-                                decrement_hugepage_resv_vma(h, vma);
-
-                        break;
+                if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask)) {
+                        page = dequeue_huge_page_node(h, zone_to_nid(zone));
+                        if (page) {
+                                if (!avoid_reserve)
+                                        decrement_hugepage_resv_vma(h, vma);
+                                break;
+                        }
                 }
         }
 err:
@@ -770,11 +812,10 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
         return ret;
 }
 
-static struct page *alloc_buddy_huge_page(struct hstate *h,
-                        struct vm_area_struct *vma, unsigned long address)
+static struct page *alloc_buddy_huge_page(struct hstate *h, int nid)
 {
         struct page *page;
-        unsigned int nid;
+        unsigned int r_nid;
 
         if (h->order >= MAX_ORDER)
                 return NULL;
@@ -812,9 +853,14 @@ static struct page *alloc_buddy_huge_page(struct hstate *h,
         }
         spin_unlock(&hugetlb_lock);
 
-        page = alloc_pages(htlb_alloc_mask|__GFP_COMP|
-                                        __GFP_REPEAT|__GFP_NOWARN,
-                                        huge_page_order(h));
+        if (nid == NUMA_NO_NODE)
+                page = alloc_pages(htlb_alloc_mask|__GFP_COMP|
+                                   __GFP_REPEAT|__GFP_NOWARN,
+                                   huge_page_order(h));
+        else
+                page = alloc_pages_exact_node(nid,
+                        htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
+                        __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h));
 
         if (page && arch_prepare_hugepage(page)) {
                 __free_pages(page, huge_page_order(h));
@@ -823,19 +869,13 @@ static struct page *alloc_buddy_huge_page(struct hstate *h,
 
         spin_lock(&hugetlb_lock);
         if (page) {
-                /*
-                 * This page is now managed by the hugetlb allocator and has
-                 * no users -- drop the buddy allocator's reference.
-                 */
-                put_page_testzero(page);
-                VM_BUG_ON(page_count(page));
-                nid = page_to_nid(page);
+                r_nid = page_to_nid(page);
                 set_compound_page_dtor(page, free_huge_page);
                 /*
                  * We incremented the global counters already
                  */
-                h->nr_huge_pages_node[nid]++;
-                h->surplus_huge_pages_node[nid]++;
+                h->nr_huge_pages_node[r_nid]++;
+                h->surplus_huge_pages_node[r_nid]++;
                 __count_vm_event(HTLB_BUDDY_PGALLOC);
         } else {
                 h->nr_huge_pages--;
@@ -848,6 +888,25 @@ static struct page *alloc_buddy_huge_page(struct hstate *h,
 }
 
 /*
+ * This allocation function is useful in the context where vma is irrelevant.
+ * E.g. soft-offlining uses this function because it only cares physical
+ * address of error page.
+ */
+struct page *alloc_huge_page_node(struct hstate *h, int nid)
+{
+        struct page *page;
+
+        spin_lock(&hugetlb_lock);
+        page = dequeue_huge_page_node(h, nid);
+        spin_unlock(&hugetlb_lock);
+
+        if (!page)
+                page = alloc_buddy_huge_page(h, nid);
+
+        return page;
+}
+
+/*
  * Increase the hugetlb pool such that it can accomodate a reservation
  * of size 'delta'.
  */
@@ -871,17 +930,14 @@ 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(h, NULL, 0);
-                if (!page) {
+                page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
+                if (!page)
                         /*
                          * We were not able to allocate enough pages to
                          * satisfy the entire reservation so we free what
                          * we've allocated so far.
                          */
-                        spin_lock(&hugetlb_lock);
-                        needed = 0;
                         goto free;
-                }
 
                 list_add(&page->lru, &surplus_list);
         }
@@ -908,31 +964,31 @@ retry:
         needed += allocated;
         h->resv_huge_pages += delta;
         ret = 0;
-free:
+
+        spin_unlock(&hugetlb_lock);
         /* Free the needed pages to the hugetlb pool */
         list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
                 if ((--needed) < 0)
                         break;
                 list_del(&page->lru);
+                /*
+                 * This page is now managed by the hugetlb allocator and has
+                 * no users -- drop the buddy allocator's reference.
+                 */
+                put_page_testzero(page);
+                VM_BUG_ON(page_count(page));
                 enqueue_huge_page(h, page);
         }
 
         /* Free unnecessary surplus pages to the buddy allocator */
+free:
         if (!list_empty(&surplus_list)) {
-                spin_unlock(&hugetlb_lock);
                 list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
                         list_del(&page->lru);
-                        /*
-                         * The page has a reference count of zero already, so
-                         * call free_huge_page directly instead of using
-                         * put_page.  This must be done with hugetlb_lock
-                         * unlocked which is safe because free_huge_page takes
-                         * hugetlb_lock before deciding how to free the page.
-                         */
-                        free_huge_page(page);
+                        put_page(page);
                 }
-                spin_lock(&hugetlb_lock);
         }
+        spin_lock(&hugetlb_lock);
 
         return ret;
 }
@@ -1052,14 +1108,13 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
         spin_unlock(&hugetlb_lock);
 
         if (!page) {
-                page = alloc_buddy_huge_page(h, vma, addr);
+                page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
                 if (!page) {
                         hugetlb_put_quota(inode->i_mapping, chg);
                         return ERR_PTR(-VM_FAULT_SIGBUS);
                 }
         }
 
-        set_page_refcounted(page);
         set_page_private(page, (unsigned long) mapping);
 
         vma_commit_reservation(h, vma, addr);
@@ -2153,6 +2208,19 @@ nomem:
         return -ENOMEM;
 }
 
+static int is_hugetlb_entry_migration(pte_t pte)
+{
+        swp_entry_t swp;
+
+        if (huge_pte_none(pte) || pte_present(pte))
+                return 0;
+        swp = pte_to_swp_entry(pte);
+        if (non_swap_entry(swp) && is_migration_entry(swp)) {
+                return 1;
+        } else
+                return 0;
+}
+
 static int is_hugetlb_entry_hwpoisoned(pte_t pte)
 {
         swp_entry_t swp;
@@ -2383,7 +2451,7 @@ retry_avoidcopy:
         if (unlikely(anon_vma_prepare(vma)))
                 return VM_FAULT_OOM;
 
-        copy_huge_page(new_page, old_page, address, vma);
+        copy_user_huge_page(new_page, old_page, address, vma);
         __SetPageUptodate(new_page);
 
         /*
@@ -2515,22 +2583,20 @@ retry:
                         hugepage_add_new_anon_rmap(page, vma, address);
                 }
         } else {
+                /*
+                 * If memory error occurs between mmap() and fault, some process
+                 * don't have hwpoisoned swap entry for errored virtual address.
+                 * So we need to block hugepage fault by PG_hwpoison bit check.
+                 */
+                if (unlikely(PageHWPoison(page))) {
+                        ret = VM_FAULT_HWPOISON | 
+                              VM_FAULT_SET_HINDEX(h - hstates);
+                        goto backout_unlocked;
+                }
                 page_dup_rmap(page);
         }
 
         /*
-         * Since memory error handler replaces pte into hwpoison swap entry
-         * at the time of error handling, a process which reserved but not have
-         * the mapping to the error hugepage does not have hwpoison swap entry.
-         * So we need to block accesses from such a process by checking
-         * PG_hwpoison bit here.
-         */
-        if (unlikely(PageHWPoison(page))) {
-                ret = VM_FAULT_HWPOISON;
-                goto backout_unlocked;
-        }
-
-        /*
          * If we are going to COW a private mapping later, we examine the
          * pending reservations for this page now. This will ensure that
          * any allocations necessary to record that reservation occur outside
@@ -2587,8 +2653,12 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
         ptep = huge_pte_offset(mm, address);
         if (ptep) {
                 entry = huge_ptep_get(ptep);
-                if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
-                        return VM_FAULT_HWPOISON;
+                if (unlikely(is_hugetlb_entry_migration(entry))) {
+                        migration_entry_wait(mm, (pmd_t *)ptep, address);
+                        return 0;
+                } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
+                        return VM_FAULT_HWPOISON_LARGE | 
+                               VM_FAULT_SET_HINDEX(h - hstates);
         }
 
         ptep = huge_pte_alloc(mm, address, huge_page_size(h));
@@ -2878,18 +2948,41 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
         hugetlb_acct_memory(h, -(chg - freed));
 }
 
+#ifdef CONFIG_MEMORY_FAILURE
+
+/* Should be called in hugetlb_lock */
+static int is_hugepage_on_freelist(struct page *hpage)
+{
+        struct page *page;
+        struct page *tmp;
+        struct hstate *h = page_hstate(hpage);
+        int nid = page_to_nid(hpage);
+
+        list_for_each_entry_safe(page, tmp, &h->hugepage_freelists[nid], lru)
+                if (page == hpage)
+                        return 1;
+        return 0;
+}
+
 /*
  * 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)
+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);
-        list_del(&hpage->lru);
-        h->free_huge_pages--;
-        h->free_huge_pages_node[nid]--;
+        if (is_hugepage_on_freelist(hpage)) {
+                list_del(&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