Merge tag 'asoc-v5.4-2' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie...

[linux-2.6-block.git] / mm / mempolicy.c

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 932c26845e3e33933710de5bcc7743db5af0737a..65e0874fce1736a65f8ced74f2a94d3e23d718c9 100644 (file)
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -403,7 +403,7 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = {
        },
 };
 
-static void migrate_page_add(struct page *page, struct list_head *pagelist,
+static int migrate_page_add(struct page *page, struct list_head *pagelist,
                                unsigned long flags);
 
 struct queue_pages {
@@ -463,12 +463,11 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
        flags = qp->flags;
        /* go to thp migration */
        if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
-               if (!vma_migratable(walk->vma)) {
+               if (!vma_migratable(walk->vma) ||
+                   migrate_page_add(page, qp->pagelist, flags)) {
                        ret = 1;
                        goto unlock;
                }
-
-               migrate_page_add(page, qp->pagelist, flags);
        } else
                ret = -EIO;
 unlock:
@@ -532,7 +531,14 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
                                has_unmovable = true;
                                break;
                        }
-                       migrate_page_add(page, qp->pagelist, flags);
+
+                       /*
+                        * Do not abort immediately since there may be
+                        * temporary off LRU pages in the range.  Still
+                        * need migrate other LRU pages.
+                        */
+                       if (migrate_page_add(page, qp->pagelist, flags))
+                               has_unmovable = true;
                } else
                        break;
        }
@@ -961,7 +967,7 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask,
 /*
  * page migration, thp tail pages can be passed.
  */
-static void migrate_page_add(struct page *page, struct list_head *pagelist,
+static int migrate_page_add(struct page *page, struct list_head *pagelist,
                                unsigned long flags)
 {
        struct page *head = compound_head(page);
@@ -974,8 +980,19 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist,
                        mod_node_page_state(page_pgdat(head),
                                NR_ISOLATED_ANON + page_is_file_cache(head),
                                hpage_nr_pages(head));
+               } else if (flags & MPOL_MF_STRICT) {
+                       /*
+                        * Non-movable page may reach here.  And, there may be
+                        * temporary off LRU pages or non-LRU movable pages.
+                        * Treat them as unmovable pages since they can't be
+                        * isolated, so they can't be moved at the moment.  It
+                        * should return -EIO for this case too.
+                        */
+                       return -EIO;
                }
        }
+
+       return 0;
 }
 
 /* page allocation callback for NUMA node migration */
@@ -1163,8 +1180,8 @@ static struct page *new_page(struct page *page, unsigned long start)
        } else if (PageTransHuge(page)) {
                struct page *thp;
 
-               thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address,
-                                        HPAGE_PMD_ORDER);
+               thp = alloc_pages_vma(GFP_TRANSHUGE, HPAGE_PMD_ORDER, vma,
+                               address, numa_node_id());
                if (!thp)
                        return NULL;
                prep_transhuge_page(thp);
@@ -1178,9 +1195,10 @@ static struct page *new_page(struct page *page, unsigned long start)
 }
 #else
 
-static void migrate_page_add(struct page *page, struct list_head *pagelist,
+static int migrate_page_add(struct page *page, struct list_head *pagelist,
                                unsigned long flags)
 {
+       return -EIO;
 }
 
 int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
@@ -1716,7 +1734,7 @@ struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
  * freeing by another task.  It is the caller's responsibility to free the
  * extra reference for shared policies.
  */
-static struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
+struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
                                                unsigned long addr)
 {
        struct mempolicy *pol = __get_vma_policy(vma, addr);
@@ -2065,7 +2083,6 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
  *     @vma:  Pointer to VMA or NULL if not available.
  *     @addr: Virtual Address of the allocation. Must be inside the VMA.
  *     @node: Which node to prefer for allocation (modulo policy).
- *     @hugepage: for hugepages try only the preferred node if possible
  *
  *     This function allocates a page from the kernel page pool and applies
  *     a NUMA policy associated with the VMA or the current process.
@@ -2076,7 +2093,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
  */
 struct page *
 alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
-               unsigned long addr, int node, bool hugepage)
+               unsigned long addr, int node)
 {
        struct mempolicy *pol;
        struct page *page;
@@ -2094,31 +2111,6 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
                goto out;
        }
 
-       if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) {
-               int hpage_node = node;
-
-               /*
-                * For hugepage allocation and non-interleave policy which
-                * allows the current node (or other explicitly preferred
-                * node) we only try to allocate from the current/preferred
-                * node and don't fall back to other nodes, as the cost of
-                * remote accesses would likely offset THP benefits.
-                *
-                * If the policy is interleave, or does not allow the current
-                * node in its nodemask, we allocate the standard way.
-                */
-               if (pol->mode == MPOL_PREFERRED && !(pol->flags & MPOL_F_LOCAL))
-                       hpage_node = pol->v.preferred_node;
-
-               nmask = policy_nodemask(gfp, pol);
-               if (!nmask || node_isset(hpage_node, *nmask)) {
-                       mpol_cond_put(pol);
-                       page = __alloc_pages_node(hpage_node,
-                                               gfp | __GFP_THISNODE, order);
-                       goto out;
-               }
-       }
-
        nmask = policy_nodemask(gfp, pol);
        preferred_nid = policy_node(gfp, pol, node);
        page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask);