Merge branch 'akpm' (patches from Andrew Morton)

Merge a bunch of fixes from Andrew Morton.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  fs/proc/task_mmu.c: fix buffer overflow in add_page_map()
  arch: *: Kconfig: add "kernel/Kconfig.freezer" to "arch/*/Kconfig"
  ocfs2: fix null pointer dereference in ocfs2_dir_foreach_blk_id()
  x86 get_unmapped_area(): use proper mmap base for bottom-up direction
  ocfs2: fix NULL pointer dereference in ocfs2_duplicate_clusters_by_page
  ocfs2: Revert 40bd62e to avoid regression in extended allocation
  drivers/rtc/rtc-stmp3xxx.c: provide timeout for potentially endless loop polling a HW bit
  hugetlb: fix lockdep splat caused by pmd sharing
  aoe: adjust ref of head for compound page tails
  microblaze: fix clone syscall
  mm: save soft-dirty bits on file pages
  mm: save soft-dirty bits on swapped pages
  memcg: don't initialize kmem-cache destroying work for root caches

5 files changed, 48 insertions, 13 deletions

diff --git a/mm/fremap.c b/mm/fremap.c
index 87da3590c61e..5bff08147768 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -57,17 +57,22 @@ static int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma,
                 unsigned long addr, unsigned long pgoff, pgprot_t prot)
 {
         int err = -ENOMEM;
-        pte_t *pte;
+        pte_t *pte, ptfile;
         spinlock_t *ptl;
 
         pte = get_locked_pte(mm, addr, &ptl);
         if (!pte)
                 goto out;
 
-        if (!pte_none(*pte))
+        ptfile = pgoff_to_pte(pgoff);
+
+        if (!pte_none(*pte)) {
+                if (pte_present(*pte) && pte_soft_dirty(*pte))
+                        pte_file_mksoft_dirty(ptfile);
                 zap_pte(mm, vma, addr, pte);
+        }
 
-        set_pte_at(mm, addr, pte, pgoff_to_pte(pgoff));
+        set_pte_at(mm, addr, pte, ptfile);
         /*
          * We don't need to run update_mmu_cache() here because the "file pte"
          * being installed by install_file_pte() is not a real pte - it's a
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c290a1cf3862..c5792a5d87ce 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3195,11 +3195,11 @@ int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s,
         if (!s->memcg_params)
                 return -ENOMEM;
 
-        INIT_WORK(&s->memcg_params->destroy,
-                        kmem_cache_destroy_work_func);
         if (memcg) {
                 s->memcg_params->memcg = memcg;
                 s->memcg_params->root_cache = root_cache;
+                INIT_WORK(&s->memcg_params->destroy,
+                                kmem_cache_destroy_work_func);
         } else
                 s->memcg_params->is_root_cache = true;
 
diff --git a/mm/memory.c b/mm/memory.c
index 1ce2e2a734fc..40268410732a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1141,9 +1141,12 @@ again:
                                 continue;
                         if (unlikely(details) && details->nonlinear_vma
                             && linear_page_index(details->nonlinear_vma,
-                                                addr) != page->index)
-                                set_pte_at(mm, addr, pte,
-                                           pgoff_to_pte(page->index));
+                                                addr) != page->index) {
+                                pte_t ptfile = pgoff_to_pte(page->index);
+                                if (pte_soft_dirty(ptent))
+                                        pte_file_mksoft_dirty(ptfile);
+                                set_pte_at(mm, addr, pte, ptfile);
+                        }
                         if (PageAnon(page))
                                 rss[MM_ANONPAGES]--;
                         else {
@@ -3115,6 +3118,8 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
                 exclusive = 1;
         }
         flush_icache_page(vma, page);
+        if (pte_swp_soft_dirty(orig_pte))
+                pte = pte_mksoft_dirty(pte);
         set_pte_at(mm, address, page_table, pte);
         if (page == swapcache)
                 do_page_add_anon_rmap(page, vma, address, exclusive);
@@ -3408,6 +3413,8 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
                 entry = mk_pte(page, vma->vm_page_prot);
                 if (flags & FAULT_FLAG_WRITE)
                         entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+                else if (pte_file(orig_pte) && pte_file_soft_dirty(orig_pte))
+                        pte_mksoft_dirty(entry);
                 if (anon) {
                         inc_mm_counter_fast(mm, MM_ANONPAGES);
                         page_add_new_anon_rmap(page, vma, address);
diff --git a/mm/rmap.c b/mm/rmap.c
index cd356df4f71a..b2e29acd7e3d 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1236,6 +1236,7 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
                            swp_entry_to_pte(make_hwpoison_entry(page)));
         } else if (PageAnon(page)) {
                 swp_entry_t entry = { .val = page_private(page) };
+                pte_t swp_pte;
 
                 if (PageSwapCache(page)) {
                         /*
@@ -1264,7 +1265,10 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
                         BUG_ON(TTU_ACTION(flags) != TTU_MIGRATION);
                         entry = make_migration_entry(page, pte_write(pteval));
                 }
-                set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
+                swp_pte = swp_entry_to_pte(entry);
+                if (pte_soft_dirty(pteval))
+                        swp_pte = pte_swp_mksoft_dirty(swp_pte);
+                set_pte_at(mm, address, pte, swp_pte);
                 BUG_ON(pte_file(*pte));
         } else if (IS_ENABLED(CONFIG_MIGRATION) &&
                    (TTU_ACTION(flags) == TTU_MIGRATION)) {
@@ -1401,8 +1405,12 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
                 pteval = ptep_clear_flush(vma, address, pte);
 
                 /* If nonlinear, store the file page offset in the pte. */
-                if (page->index != linear_page_index(vma, address))
-                        set_pte_at(mm, address, pte, pgoff_to_pte(page->index));
+                if (page->index != linear_page_index(vma, address)) {
+                        pte_t ptfile = pgoff_to_pte(page->index);
+                        if (pte_soft_dirty(pteval))
+                                pte_file_mksoft_dirty(ptfile);
+                        set_pte_at(mm, address, pte, ptfile);
+                }
 
                 /* Move the dirty bit to the physical page now the pte is gone. */
                 if (pte_dirty(pteval))
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 36af6eeaa67e..6cf2e60983b7 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -866,6 +866,21 @@ unsigned int count_swap_pages(int type, int free)
 }
 #endif /* CONFIG_HIBERNATION */
 
+static inline int maybe_same_pte(pte_t pte, pte_t swp_pte)
+{
+#ifdef CONFIG_MEM_SOFT_DIRTY
+        /*
+         * When pte keeps soft dirty bit the pte generated
+         * from swap entry does not has it, still it's same
+         * pte from logical point of view.
+         */
+        pte_t swp_pte_dirty = pte_swp_mksoft_dirty(swp_pte);
+        return pte_same(pte, swp_pte) || pte_same(pte, swp_pte_dirty);
+#else
+        return pte_same(pte, swp_pte);
+#endif
+}
+
 /*
  * No need to decide whether this PTE shares the swap entry with others,
  * just let do_wp_page work it out if a write is requested later - to
@@ -892,7 +907,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
         }
 
         pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
-        if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) {
+        if (unlikely(!maybe_same_pte(*pte, swp_entry_to_pte(entry)))) {
                 mem_cgroup_cancel_charge_swapin(memcg);
                 ret = 0;
                 goto out;
@@ -947,7 +962,7 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
                  * swapoff spends a _lot_ of time in this loop!
                  * Test inline before going to call unuse_pte.
                  */
-                if (unlikely(pte_same(*pte, swp_pte))) {
+                if (unlikely(maybe_same_pte(*pte, swp_pte))) {
                         pte_unmap(pte);
                         ret = unuse_pte(vma, pmd, addr, entry, page);
                         if (ret)