Linux-libre 4.5.3-gnupck-4.5.3-gnu

6 files changed, 80 insertions, 35 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e10a4fee8..a7db0a2db 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1919,10 +1919,9 @@ int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
 		 * page fault if needed.
 		 */
 		return 0;
-	if (vma->vm_ops)
+	if (vma->vm_ops || (vm_flags & VM_NO_THP))
 		/* khugepaged not yet working on file or special mappings */
 		return 0;
-	VM_BUG_ON_VMA(vm_flags & VM_NO_THP, vma);
 	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
 	hend = vma->vm_end & HPAGE_PMD_MASK;
 	if (hstart < hend)
@@ -2310,8 +2309,7 @@ static bool hugepage_vma_check(struct vm_area_struct *vma)
 		return false;
 	if (is_vma_temporary_stack(vma))
 		return false;
-	VM_BUG_ON_VMA(vma->vm_flags & VM_NO_THP, vma);
-	return true;
+	return !(vma->vm_flags & VM_NO_THP);
 }
 
 static void collapse_huge_page(struct mm_struct *mm,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index caf3bf73b..a65ad1d59 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -207,6 +207,7 @@ static void mem_cgroup_oom_notify(struct mem_cgroup *memcg);
 /* "mc" and its members are protected by cgroup_mutex */
 static struct move_charge_struct {
 	spinlock_t	  lock; /* for from, to */
+	struct mm_struct  *mm;
 	struct mem_cgroup *from;
 	struct mem_cgroup *to;
 	unsigned long flags;
@@ -4730,6 +4731,8 @@ static void __mem_cgroup_clear_mc(void)
 
 static void mem_cgroup_clear_mc(void)
 {
+	struct mm_struct *mm = mc.mm;
+
 	/*
 	 * we must clear moving_task before waking up waiters at the end of
 	 * task migration.
@@ -4739,7 +4742,10 @@ static void mem_cgroup_clear_mc(void)
 	spin_lock(&mc.lock);
 	mc.from = NULL;
 	mc.to = NULL;
+	mc.mm = NULL;
 	spin_unlock(&mc.lock);
+
+	mmput(mm);
 }
 
 static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
@@ -4796,6 +4802,7 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
 		VM_BUG_ON(mc.moved_swap);
 
 		spin_lock(&mc.lock);
+		mc.mm = mm;
 		mc.from = from;
 		mc.to = memcg;
 		mc.flags = move_flags;
@@ -4805,8 +4812,9 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
 		ret = mem_cgroup_precharge_mc(mm);
 		if (ret)
 			mem_cgroup_clear_mc();
+	} else {
+		mmput(mm);
 	}
-	mmput(mm);
 	return ret;
 }
 
@@ -4915,11 +4923,11 @@ put:			/* get_mctgt_type() gets the page */
 	return ret;
 }
 
-static void mem_cgroup_move_charge(struct mm_struct *mm)
+static void mem_cgroup_move_charge(void)
 {
 	struct mm_walk mem_cgroup_move_charge_walk = {
 		.pmd_entry = mem_cgroup_move_charge_pte_range,
-		.mm = mm,
+		.mm = mc.mm,
 	};
 
 	lru_add_drain_all();
@@ -4931,7 +4939,7 @@ static void mem_cgroup_move_charge(struct mm_struct *mm)
 	atomic_inc(&mc.from->moving_account);
 	synchronize_rcu();
 retry:
-	if (unlikely(!down_read_trylock(&mm->mmap_sem))) {
+	if (unlikely(!down_read_trylock(&mc.mm->mmap_sem))) {
 		/*
 		 * Someone who are holding the mmap_sem might be waiting in
 		 * waitq. So we cancel all extra charges, wake up all waiters,
@@ -4948,23 +4956,16 @@ retry:
 	 * additional charge, the page walk just aborts.
 	 */
 	walk_page_range(0, ~0UL, &mem_cgroup_move_charge_walk);
-	up_read(&mm->mmap_sem);
+	up_read(&mc.mm->mmap_sem);
 	atomic_dec(&mc.from->moving_account);
 }
 
-static void mem_cgroup_move_task(struct cgroup_taskset *tset)
+static void mem_cgroup_move_task(void)
 {
-	struct cgroup_subsys_state *css;
-	struct task_struct *p = cgroup_taskset_first(tset, &css);
-	struct mm_struct *mm = get_task_mm(p);
-
-	if (mm) {
-		if (mc.to)
-			mem_cgroup_move_charge(mm);
-		mmput(mm);
-	}
-	if (mc.to)
+	if (mc.to) {
+		mem_cgroup_move_charge();
 		mem_cgroup_clear_mc();
+	}
 }
 #else	/* !CONFIG_MMU */
 static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
@@ -4974,7 +4975,7 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
 static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset)
 {
 }
-static void mem_cgroup_move_task(struct cgroup_taskset *tset)
+static void mem_cgroup_move_task(void)
 {
 }
 #endif
@@ -5246,7 +5247,7 @@ struct cgroup_subsys memory_cgrp_subsys = {
 	.css_reset = mem_cgroup_css_reset,
 	.can_attach = mem_cgroup_can_attach,
 	.cancel_attach = mem_cgroup_cancel_attach,
-	.attach = mem_cgroup_move_task,
+	.post_attach = mem_cgroup_move_task,
 	.bind = mem_cgroup_bind,
 	.dfl_cftypes = memory_files,
 	.legacy_cftypes = mem_cgroup_legacy_files,
diff --git a/mm/memory.c b/mm/memory.c
index 3f7de66ed..869aa2cb2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -792,6 +792,46 @@ out:
 	return pfn_to_page(pfn);
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
+				pmd_t pmd)
+{
+	unsigned long pfn = pmd_pfn(pmd);
+
+	/*
+	 * There is no pmd_special() but there may be special pmds, e.g.
+	 * in a direct-access (dax) mapping, so let's just replicate the
+	 * !HAVE_PTE_SPECIAL case from vm_normal_page() here.
+	 */
+	if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
+		if (vma->vm_flags & VM_MIXEDMAP) {
+			if (!pfn_valid(pfn))
+				return NULL;
+			goto out;
+		} else {
+			unsigned long off;
+			off = (addr - vma->vm_start) >> PAGE_SHIFT;
+			if (pfn == vma->vm_pgoff + off)
+				return NULL;
+			if (!is_cow_mapping(vma->vm_flags))
+				return NULL;
+		}
+	}
+
+	if (is_zero_pfn(pfn))
+		return NULL;
+	if (unlikely(pfn > highest_memmap_pfn))
+		return NULL;
+
+	/*
+	 * NOTE! We still have PageReserved() pages in the page tables.
+	 * eg. VDSO mappings can cause them to exist.
+	 */
+out:
+	return pfn_to_page(pfn);
+}
+#endif
+
 /*
  * copy one vm_area from one task to the other. Assumes the page tables
  * already present in the new task to be cleared in the whole range
diff --git a/mm/migrate.c b/mm/migrate.c
index 3ad0fea5c..625741faa 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -967,7 +967,13 @@ out:
 		dec_zone_page_state(page, NR_ISOLATED_ANON +
 				page_is_file_cache(page));
 		/* Soft-offlined page shouldn't go through lru cache list */
-		if (reason == MR_MEMORY_FAILURE) {
+		if (reason == MR_MEMORY_FAILURE && rc == MIGRATEPAGE_SUCCESS) {
+			/*
+			 * With this release, we free successfully migrated
+			 * page and set PG_HWPoison on just freed page
+			 * intentionally. Although it's rather weird, it's how
+			 * HWPoison flag works at the moment.
+			 */
 			put_page(page);
 			if (!test_set_page_hwpoison(page))
 				num_poisoned_pages_inc();
diff --git a/mm/slub.c b/mm/slub.c
index 5328e64b9..741e50759 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2815,6 +2815,7 @@ struct detached_freelist {
 	void *tail;
 	void *freelist;
 	int cnt;
+	struct kmem_cache *s;
 };
 
 /*
@@ -2829,8 +2830,9 @@ struct detached_freelist {
  * synchronization primitive.  Look ahead in the array is limited due
  * to performance reasons.
  */
-static int build_detached_freelist(struct kmem_cache *s, size_t size,
-				   void **p, struct detached_freelist *df)
+static inline
+int build_detached_freelist(struct kmem_cache *s, size_t size,
+			    void **p, struct detached_freelist *df)
 {
 	size_t first_skipped_index = 0;
 	int lookahead = 3;
@@ -2846,8 +2848,11 @@ static int build_detached_freelist(struct kmem_cache *s, size_t size,
 	if (!object)
 		return 0;
 
+	/* Support for memcg, compiler can optimize this out */
+	df->s = cache_from_obj(s, object);
+
 	/* Start new detached freelist */
-	set_freepointer(s, object, NULL);
+	set_freepointer(df->s, object, NULL);
 	df->page = virt_to_head_page(object);
 	df->tail = object;
 	df->freelist = object;
@@ -2862,7 +2867,7 @@ static int build_detached_freelist(struct kmem_cache *s, size_t size,
 		/* df->page is always set at this point */
 		if (df->page == virt_to_head_page(object)) {
 			/* Opportunity build freelist */
-			set_freepointer(s, object, df->freelist);
+			set_freepointer(df->s, object, df->freelist);
 			df->freelist = object;
 			df->cnt++;
 			p[size] = NULL; /* mark object processed */
@@ -2881,25 +2886,20 @@ static int build_detached_freelist(struct kmem_cache *s, size_t size,
 	return first_skipped_index;
 }
 
-
 /* Note that interrupts must be enabled when calling this function. */
-void kmem_cache_free_bulk(struct kmem_cache *orig_s, size_t size, void **p)
+void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
 {
 	if (WARN_ON(!size))
 		return;
 
 	do {
 		struct detached_freelist df;
-		struct kmem_cache *s;
-
-		/* Support for memcg */
-		s = cache_from_obj(orig_s, p[size - 1]);
 
 		size = build_detached_freelist(s, size, p, &df);
 		if (unlikely(!df.page))
 			continue;
 
-		slab_free(s, df.page, df.freelist, df.tail, df.cnt, _RET_IP_);
+		slab_free(df.s, df.page, df.freelist, df.tail, df.cnt,_RET_IP_);
 	} while (likely(size));
 }
 EXPORT_SYMBOL(kmem_cache_free_bulk);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index f406a4765..0da572753 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2564,7 +2564,7 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 		sc->gfp_mask |= __GFP_HIGHMEM;
 
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
-					requested_highidx, sc->nodemask) {
+					gfp_zone(sc->gfp_mask), sc->nodemask) {
 		enum zone_type classzone_idx;
 
 		if (!populated_zone(zone))