Merge branch 'cgroup/for-3.7-fixes' into cgroup/for-3.8

This is to receive device_cgroup fixes so that further device_cgroup
changes can be made in cgroup/for-3.8.

Signed-off-by: Tejun Heo <tj@kernel.org>

9 files changed, 63 insertions, 29 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index 2c4ce17651d8..9eef55838fca 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -346,7 +346,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
 	 * pages requested were isolated. If there were any failures, 0 is
 	 * returned and CMA will fail.
 	 */
-	if (strict && nr_strict_required != total_isolated)
+	if (strict && nr_strict_required > total_isolated)
 		total_isolated = 0;
 
 	if (locked)
diff --git a/mm/fremap.c b/mm/fremap.c
index 3899a86851ce..a0aaf0e56800 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -169,7 +169,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	if (vma->vm_private_data && !(vma->vm_flags & VM_NONLINEAR))
 		goto out;
 
-	if (!vma->vm_ops->remap_pages)
+	if (!vma->vm_ops || !vma->vm_ops->remap_pages)
 		goto out;
 
 	if (start < vma->vm_start || start + size > vma->vm_end)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index a863af26c79c..40f17c34b415 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -17,6 +17,7 @@
 #include <linux/khugepaged.h>
 #include <linux/freezer.h>
 #include <linux/mman.h>
+#include <linux/pagemap.h>
 #include <asm/tlb.h>
 #include <asm/pgalloc.h>
 #include "internal.h"
diff --git a/mm/memblock.c b/mm/memblock.c
index 931eef145af5..625905523c2a 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -930,6 +930,30 @@ int __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t si
 	return memblock_overlaps_region(&memblock.reserved, base, size) >= 0;
 }
 
+void __init_memblock memblock_trim_memory(phys_addr_t align)
+{
+	int i;
+	phys_addr_t start, end, orig_start, orig_end;
+	struct memblock_type *mem = &memblock.memory;
+
+	for (i = 0; i < mem->cnt; i++) {
+		orig_start = mem->regions[i].base;
+		orig_end = mem->regions[i].base + mem->regions[i].size;
+		start = round_up(orig_start, align);
+		end = round_down(orig_end, align);
+
+		if (start == orig_start && end == orig_end)
+			continue;
+
+		if (start < end) {
+			mem->regions[i].base = start;
+			mem->regions[i].size = end - start;
+		} else {
+			memblock_remove_region(mem, i);
+			i--;
+		}
+	}
+}
 
 void __init_memblock memblock_set_current_limit(phys_addr_t limit)
 {
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 0b78fb9ea65b..d04a8a54c294 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1536,9 +1536,8 @@ asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len,
  *
  * Returns effective policy for a VMA at specified address.
  * Falls back to @task or system default policy, as necessary.
- * Current or other task's task mempolicy and non-shared vma policies
- * are protected by the task's mmap_sem, which must be held for read by
- * the caller.
+ * Current or other task's task mempolicy and non-shared vma policies must be
+ * protected by task_lock(task) by the caller.
  * Shared policies [those marked as MPOL_F_SHARED] require an extra reference
  * count--added by the get_policy() vm_op, as appropriate--to protect against
  * freeing by another task.  It is the caller's responsibility to free the
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 479a1e751a73..8a5ac8c686b0 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -196,28 +196,28 @@ static int do_mmu_notifier_register(struct mmu_notifier *mn,
 	BUG_ON(atomic_read(&mm->mm_users) <= 0);
 
 	/*
-	* Verify that mmu_notifier_init() already run and the global srcu is
-	* initialized.
-	*/
+	 * Verify that mmu_notifier_init() already run and the global srcu is
+	 * initialized.
+	 */
 	BUG_ON(!srcu.per_cpu_ref);
 
+	ret = -ENOMEM;
+	mmu_notifier_mm = kmalloc(sizeof(struct mmu_notifier_mm), GFP_KERNEL);
+	if (unlikely(!mmu_notifier_mm))
+		goto out;
+
 	if (take_mmap_sem)
 		down_write(&mm->mmap_sem);
 	ret = mm_take_all_locks(mm);
 	if (unlikely(ret))
-		goto out;
+		goto out_clean;
 
 	if (!mm_has_notifiers(mm)) {
-		mmu_notifier_mm = kmalloc(sizeof(struct mmu_notifier_mm),
-					GFP_KERNEL);
-		if (unlikely(!mmu_notifier_mm)) {
-			ret = -ENOMEM;
-			goto out_of_mem;
-		}
 		INIT_HLIST_HEAD(&mmu_notifier_mm->list);
 		spin_lock_init(&mmu_notifier_mm->lock);
 
 		mm->mmu_notifier_mm = mmu_notifier_mm;
+		mmu_notifier_mm = NULL;
 	}
 	atomic_inc(&mm->mm_count);
 
@@ -233,12 +233,12 @@ static int do_mmu_notifier_register(struct mmu_notifier *mn,
 	hlist_add_head(&mn->hlist, &mm->mmu_notifier_mm->list);
 	spin_unlock(&mm->mmu_notifier_mm->lock);
 
-out_of_mem:
 	mm_drop_all_locks(mm);
-out:
+out_clean:
 	if (take_mmap_sem)
 		up_write(&mm->mmap_sem);
-
+	kfree(mmu_notifier_mm);
+out:
 	BUG_ON(atomic_read(&mm->mm_users) <= 0);
 	return ret;
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index bb90971182bd..5b74de6702e0 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1809,10 +1809,10 @@ static void __paginginit init_zone_allows_reclaim(int nid)
 	int i;
 
 	for_each_online_node(i)
-		if (node_distance(nid, i) <= RECLAIM_DISTANCE) {
+		if (node_distance(nid, i) <= RECLAIM_DISTANCE)
 			node_set(i, NODE_DATA(nid)->reclaim_nodes);
+		else
 			zone_reclaim_mode = 1;
-		}
 }
 
 #else	/* CONFIG_NUMA */
@@ -5825,7 +5825,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 	ret = start_isolate_page_range(pfn_max_align_down(start),
 				       pfn_max_align_up(end), migratetype);
 	if (ret)
-		goto done;
+		return ret;
 
 	ret = __alloc_contig_migrate_range(&cc, start, end);
 	if (ret)
diff --git a/mm/rmap.c b/mm/rmap.c
index 7df7984d476c..2ee1ef0f317b 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -56,6 +56,7 @@
 #include <linux/mmu_notifier.h>
 #include <linux/migrate.h>
 #include <linux/hugetlb.h>
+#include <linux/backing-dev.h>
 
 #include <asm/tlbflush.h>
 
@@ -926,11 +927,8 @@ int page_mkclean(struct page *page)
 
 	if (page_mapped(page)) {
 		struct address_space *mapping = page_mapping(page);
-		if (mapping) {
+		if (mapping)
 			ret = page_mkclean_file(mapping, page);
-			if (page_test_and_clear_dirty(page_to_pfn(page), 1))
-				ret = 1;
-		}
 	}
 
 	return ret;
@@ -1116,6 +1114,7 @@ void page_add_file_rmap(struct page *page)
  */
 void page_remove_rmap(struct page *page)
 {
+	struct address_space *mapping = page_mapping(page);
 	bool anon = PageAnon(page);
 	bool locked;
 	unsigned long flags;
@@ -1138,8 +1137,19 @@ void page_remove_rmap(struct page *page)
 	 * this if the page is anon, so about to be freed; but perhaps
 	 * not if it's in swapcache - there might be another pte slot
 	 * containing the swap entry, but page not yet written to swap.
+	 *
+	 * And we can skip it on file pages, so long as the filesystem
+	 * participates in dirty tracking; but need to catch shm and tmpfs
+	 * and ramfs pages which have been modified since creation by read
+	 * fault.
+	 *
+	 * Note that mapping must be decided above, before decrementing
+	 * mapcount (which luckily provides a barrier): once page is unmapped,
+	 * it could be truncated and page->mapping reset to NULL at any moment.
+	 * Note also that we are relying on page_mapping(page) to set mapping
+	 * to &swapper_space when PageSwapCache(page).
 	 */
-	if ((!anon || PageSwapCache(page)) &&
+	if (mapping && !mapping_cap_account_dirty(mapping) &&
 	    page_test_and_clear_dirty(page_to_pfn(page), 1))
 		set_page_dirty(page);
 	/*
diff --git a/mm/slob.c b/mm/slob.c
index a08e4681fd0d..1e921c5e9576 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -429,7 +429,7 @@ static __always_inline void *
 __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller)
 {
 	unsigned int *m;
-	int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
+	int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
 	void *ret;
 
 	gfp &= gfp_allowed_mask;
@@ -502,7 +502,7 @@ void kfree(const void *block)
 
 	sp = virt_to_page(block);
 	if (PageSlab(sp)) {
-		int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
+		int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
 		unsigned int *m = (unsigned int *)(block - align);
 		slob_free(m, *m + align);
 	} else
@@ -521,7 +521,7 @@ size_t ksize(const void *block)
 
 	sp = virt_to_page(block);
 	if (PageSlab(sp)) {
-		int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
+		int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
 		unsigned int *m = (unsigned int *)(block - align);
 		return SLOB_UNITS(*m) * SLOB_UNIT;
 	} else