memcg, THP, swap: make mem_cgroup_swapout() support THP

This patch makes mem_cgroup_swapout() works for the transparent huge
page (THP).  Which will move the memory cgroup charge from memory to
swap for a THP.

This will be used for the THP swap support.  Where a THP may be swapped
out as a whole to a set of (HPAGE_PMD_NR) continuous swap slots on the
swap device.

Link: http://lkml.kernel.org/r/20170724051840.2309-11-ying.huang@intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Rik van Riel <riel@redhat.com>
Cc: Ross Zwisler <ross.zwisler@intel.com> [for brd.c, zram_drv.c, pmem.c]
Cc: Shaohua Li <shli@kernel.org>
Cc: Vishal L Verma <vishal.l.verma@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e7f47a38fe4fa104379b4a44cae036f377eacd77..c1f9b79817d7ff7faed87a5067039a2166bf79c3 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4654,8 +4654,8 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 /*
- * We don't consider swapping or file mapped pages because THP does not
- * support them for now.
+ * We don't consider PMD mapped swapping or file mapped pages because THP does
+ * not support them for now.
  * Caller should make sure that pmd_trans_huge(pmd) is true.
  */
 static enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma,
@@ -5913,6 +5913,7 @@ static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg)
 void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 {
        struct mem_cgroup *memcg, *swap_memcg;
+       unsigned int nr_entries;
        unsigned short oldid;
 
        VM_BUG_ON_PAGE(PageLRU(page), page);
@@ -5933,19 +5934,24 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
         * ancestor for the swap instead and transfer the memory+swap charge.
         */
        swap_memcg = mem_cgroup_id_get_online(memcg);
-       oldid = swap_cgroup_record(entry, mem_cgroup_id(swap_memcg), 1);
+       nr_entries = hpage_nr_pages(page);
+       /* Get references for the tail pages, too */
+       if (nr_entries > 1)
+               mem_cgroup_id_get_many(swap_memcg, nr_entries - 1);
+       oldid = swap_cgroup_record(entry, mem_cgroup_id(swap_memcg),
+                                  nr_entries);
        VM_BUG_ON_PAGE(oldid, page);
-       mem_cgroup_swap_statistics(swap_memcg, 1);
+       mem_cgroup_swap_statistics(swap_memcg, nr_entries);
 
        page->mem_cgroup = NULL;
 
        if (!mem_cgroup_is_root(memcg))
-               page_counter_uncharge(&memcg->memory, 1);
+               page_counter_uncharge(&memcg->memory, nr_entries);
 
        if (memcg != swap_memcg) {
                if (!mem_cgroup_is_root(swap_memcg))
-                       page_counter_charge(&swap_memcg->memsw, 1);
-               page_counter_uncharge(&memcg->memsw, 1);
+                       page_counter_charge(&swap_memcg->memsw, nr_entries);
+               page_counter_uncharge(&memcg->memsw, nr_entries);
        }
 
        /*
@@ -5955,7 +5961,8 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
         * only synchronisation we have for udpating the per-CPU variables.
         */
        VM_BUG_ON(!irqs_disabled());
-       mem_cgroup_charge_statistics(memcg, page, false, -1);
+       mem_cgroup_charge_statistics(memcg, page, PageTransHuge(page),
+                                    -nr_entries);
        memcg_check_events(memcg, page);
 
        if (!mem_cgroup_is_root(memcg))