hugetlb_cgroup: add reservation accounting for private mappings

[platform/kernel/linux-rpi.git] / mm / hugetlb.c

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ffc52d9..5b6d83e 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -650,6 +650,25 @@ static void set_vma_private_data(struct vm_area_struct *vma,
        vma->vm_private_data = (void *)value;
 }
 
+static void
+resv_map_set_hugetlb_cgroup_uncharge_info(struct resv_map *resv_map,
+                                         struct hugetlb_cgroup *h_cg,
+                                         struct hstate *h)
+{
+#ifdef CONFIG_CGROUP_HUGETLB
+       if (!h_cg || !h) {
+               resv_map->reservation_counter = NULL;
+               resv_map->pages_per_hpage = 0;
+               resv_map->css = NULL;
+       } else {
+               resv_map->reservation_counter =
+                       &h_cg->rsvd_hugepage[hstate_index(h)];
+               resv_map->pages_per_hpage = pages_per_huge_page(h);
+               resv_map->css = &h_cg->css;
+       }
+#endif
+}
+
 struct resv_map *resv_map_alloc(void)
 {
        struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL);
@@ -666,6 +685,13 @@ struct resv_map *resv_map_alloc(void)
        INIT_LIST_HEAD(&resv_map->regions);
 
        resv_map->adds_in_progress = 0;
+       /*
+        * Initialize these to 0. On shared mappings, 0's here indicate these
+        * fields don't do cgroup accounting. On private mappings, these will be
+        * re-initialized to the proper values, to indicate that hugetlb cgroup
+        * reservations are to be un-charged from here.
+        */
+       resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, NULL, NULL);
 
        INIT_LIST_HEAD(&resv_map->region_cache);
        list_add(&rg->link, &resv_map->region_cache);
@@ -3296,9 +3322,7 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma)
        end = vma_hugecache_offset(h, vma, vma->vm_end);
 
        reserve = (end - start) - region_count(resv, start, end);
-
-       kref_put(&resv->refs, resv_map_release);
-
+       hugetlb_cgroup_uncharge_counter(resv, start, end);
        if (reserve) {
                /*
                 * Decrement reserve counts.  The global reserve count may be
@@ -3307,6 +3331,8 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma)
                gbl_reserve = hugepage_subpool_put_pages(spool, reserve);
                hugetlb_acct_memory(h, -gbl_reserve);
        }
+
+       kref_put(&resv->refs, resv_map_release);
 }
 
 static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr)
@@ -4691,6 +4717,7 @@ int hugetlb_reserve_pages(struct inode *inode,
        struct hstate *h = hstate_inode(inode);
        struct hugepage_subpool *spool = subpool_inode(inode);
        struct resv_map *resv_map;
+       struct hugetlb_cgroup *h_cg;
        long gbl_reserve;
 
        /* This should never happen */
@@ -4724,12 +4751,26 @@ int hugetlb_reserve_pages(struct inode *inode,
                chg = region_chg(resv_map, from, to);
 
        } else {
+               /* Private mapping. */
                resv_map = resv_map_alloc();
                if (!resv_map)
                        return -ENOMEM;
 
                chg = to - from;
 
+               if (hugetlb_cgroup_charge_cgroup_rsvd(
+                           hstate_index(h), chg * pages_per_huge_page(h),
+                           &h_cg)) {
+                       kref_put(&resv_map->refs, resv_map_release);
+                       return -ENOMEM;
+               }
+
+               /*
+                * Since this branch handles private mappings, we attach the
+                * counter to uncharge for this reservation off resv_map.
+                */
+               resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, h_cg, h);
+
                set_vma_resv_map(vma, resv_map);
                set_vma_resv_flags(vma, HPAGE_RESV_OWNER);
        }