Merge remote-tracking branch 'korg/linux-3.0.y' into cm-13.0

Conflicts:
	crypto/algapi.c
	drivers/gpu/drm/i915/i915_debugfs.c
	drivers/gpu/drm/i915/intel_display.c
	drivers/video/fbmem.c
	include/linux/nls.h
	kernel/cgroup.c
	kernel/signal.c
	kernel/timeconst.pl
	net/ipv4/ping.c

Change-Id: I1f532925d1743df74d66bcdd6fc92f05c72ee0dd

13 files changed, 263 insertions, 80 deletions

diff --git a/mm/fadvise.c b/mm/fadvise.c
index 8d723c9e8b7..35b2bb089a1 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -17,6 +17,7 @@
 #include <linux/fadvise.h>
 #include <linux/writeback.h>
 #include <linux/syscalls.h>
+#include <linux/swap.h>
 
 #include <asm/unistd.h>
 
@@ -123,9 +124,22 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
 		start_index = (offset+(PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT;
 		end_index = (endbyte >> PAGE_CACHE_SHIFT);
 
-		if (end_index >= start_index)
-			invalidate_mapping_pages(mapping, start_index,
+		if (end_index >= start_index) {
+			unsigned long count = invalidate_mapping_pages(mapping,
+						start_index, end_index);
+
+			/*
+			 * If fewer pages were invalidated than expected then
+			 * it is possible that some of the pages were on
+			 * a per-cpu pagevec for a remote CPU. Drain all
+			 * pagevecs and try again.
+			 */
+			if (count < (end_index - start_index + 1)) {
+				lru_add_drain_all();
+				invalidate_mapping_pages(mapping, start_index,
 						end_index);
+			}
+		}
 		break;
 	default:
 		ret = -EINVAL;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index a9ab45ec7d5..78f71869c4c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1838,6 +1838,8 @@ static void collapse_huge_page(struct mm_struct *mm,
 		goto out;
 
 	vma = find_vma(mm, address);
+	if (!vma)
+		goto out;
 	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
 	hend = vma->vm_end & HPAGE_PMD_MASK;
 	if (address < hstart || address + HPAGE_PMD_SIZE > hend)
@@ -1893,7 +1895,12 @@ static void collapse_huge_page(struct mm_struct *mm,
 		pte_unmap(pte);
 		spin_lock(&mm->page_table_lock);
 		BUG_ON(!pmd_none(*pmd));
-		set_pmd_at(mm, address, pmd, _pmd);
+		/*
+		 * We can only use set_pmd_at when establishing
+		 * hugepmds and never for establishing regular pmds that
+		 * points to regular pagetables. Use pmd_populate for that
+		 */
+		pmd_populate(mm, pmd, pmd_pgtable(_pmd));
 		spin_unlock(&mm->page_table_lock);
 		anon_vma_unlock(vma->anon_vma);
 		goto out;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 037f077b986..6fdad258877 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -602,6 +602,23 @@ int PageHuge(struct page *page)
 
 EXPORT_SYMBOL_GPL(PageHuge);
 
+pgoff_t __basepage_index(struct page *page)
+{
+	struct page *page_head = compound_head(page);
+	pgoff_t index = page_index(page_head);
+	unsigned long compound_idx;
+
+	if (!PageHuge(page_head))
+		return page_index(page);
+
+	if (compound_order(page_head) >= MAX_ORDER)
+		compound_idx = page_to_pfn(page) - page_to_pfn(page_head);
+	else
+		compound_idx = page - page_head;
+
+	return (index << compound_order(page_head)) + compound_idx;
+}
+
 static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 {
 	struct page *page;
@@ -2006,8 +2023,12 @@ int hugetlb_report_node_meminfo(int nid, char *buf)
 /* Return the number pages of memory we physically have, in PAGE_SIZE units. */
 unsigned long hugetlb_total_pages(void)
 {
-	struct hstate *h = &default_hstate;
-	return h->nr_huge_pages * pages_per_huge_page(h);
+	struct hstate *h;
+	unsigned long nr_total_pages = 0;
+
+	for_each_hstate(h)
+		nr_total_pages += h->nr_huge_pages * pages_per_huge_page(h);
+	return nr_total_pages;
 }
 
 static int hugetlb_acct_memory(struct hstate *h, long delta)
@@ -2658,7 +2679,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (ptep) {
 		entry = huge_ptep_get(ptep);
 		if (unlikely(is_hugetlb_entry_migration(entry))) {
-			migration_entry_wait(mm, (pmd_t *)ptep, address);
+			migration_entry_wait_huge(mm, ptep);
 			return 0;
 		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
 			return VM_FAULT_HWPOISON_LARGE | 
@@ -2796,7 +2817,17 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			break;
 		}
 
-		if (absent ||
+		/*
+		 * We need call hugetlb_fault for both hugepages under migration
+		 * (in which case hugetlb_fault waits for the migration,) and
+		 * hwpoisoned hugepages (in which case we need to prevent the
+		 * caller from accessing to them.) In order to do this, we use
+		 * here is_swap_pte instead of is_hugetlb_entry_migration and
+		 * is_hugetlb_entry_hwpoisoned. This is because it simply covers
+		 * both cases, and because we can't follow correct pages
+		 * directly from any kind of swap entries.
+		 */
+		if (absent || is_swap_pte(huge_ptep_get(pte)) ||
 		    ((flags & FOLL_WRITE) && !pte_write(huge_ptep_get(pte)))) {
 			int ret;
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 57cdf5ad692..d7b51d5bc0b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4433,7 +4433,13 @@ static int compare_thresholds(const void *a, const void *b)
 	const struct mem_cgroup_threshold *_a = a;
 	const struct mem_cgroup_threshold *_b = b;
 
-	return _a->threshold - _b->threshold;
+	if (_a->threshold > _b->threshold)
+		return 1;
+
+	if (_a->threshold < _b->threshold)
+		return -1;
+
+	return 0;
 }
 
 static int mem_cgroup_oom_notify_cb(struct mem_cgroup *mem)
diff --git a/mm/memory.c b/mm/memory.c
index 6204ce20090..5331e67685d 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2374,6 +2374,53 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 }
 EXPORT_SYMBOL(remap_pfn_range);
 
+/**
+ * vm_iomap_memory - remap memory to userspace
+ * @vma: user vma to map to
+ * @start: start of area
+ * @len: size of area
+ *
+ * This is a simplified io_remap_pfn_range() for common driver use. The
+ * driver just needs to give us the physical memory range to be mapped,
+ * we'll figure out the rest from the vma information.
+ *
+ * NOTE! Some drivers might want to tweak vma->vm_page_prot first to get
+ * whatever write-combining details or similar.
+ */
+int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len)
+{
+	unsigned long vm_len, pfn, pages;
+
+	/* Check that the physical memory area passed in looks valid */
+	if (start + len < start)
+		return -EINVAL;
+	/*
+	 * You *really* shouldn't map things that aren't page-aligned,
+	 * but we've historically allowed it because IO memory might
+	 * just have smaller alignment.
+	 */
+	len += start & ~PAGE_MASK;
+	pfn = start >> PAGE_SHIFT;
+	pages = (len + ~PAGE_MASK) >> PAGE_SHIFT;
+	if (pfn + pages < pfn)
+		return -EINVAL;
+
+	/* We start the mapping 'vm_pgoff' pages into the area */
+	if (vma->vm_pgoff > pages)
+		return -EINVAL;
+	pfn += vma->vm_pgoff;
+	pages -= vma->vm_pgoff;
+
+	/* Can we fit all of the mapping? */
+	vm_len = vma->vm_end - vma->vm_start;
+	if (vm_len >> PAGE_SHIFT > pages)
+		return -EINVAL;
+
+	/* Ok, let it rip */
+	return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot);
+}
+EXPORT_SYMBOL(vm_iomap_memory);
+
 static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 				     unsigned long addr, unsigned long end,
 				     pte_fn_t fn, void *data)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 9fcd1b92f94..94463bcfbe7 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -453,19 +453,20 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
 
 	zone->present_pages += onlined_pages;
 	zone->zone_pgdat->node_present_pages += onlined_pages;
-	if (need_zonelists_rebuild)
-		build_all_zonelists(zone);
-	else
-		zone_pcp_update(zone);
+	if (onlined_pages) {
+		node_set_state(zone_to_nid(zone), N_HIGH_MEMORY);
+		if (need_zonelists_rebuild)
+			build_all_zonelists(zone);
+		else
+			zone_pcp_update(zone);
+	}
 
 	mutex_unlock(&zonelists_mutex);
 
 	init_per_zone_wmark_min();
 
-	if (onlined_pages) {
+	if (onlined_pages)
 		kswapd_run(zone_to_nid(zone));
-		node_set_state(zone_to_nid(zone), N_HIGH_MEMORY);
-	}
 
 	vm_total_pages = nr_free_pagecache_pages();
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 480714b6f3f..3e315a7e4c8 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -147,7 +147,7 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
 	if (PageHuge(new))
 		pte = pte_mkhuge(pte);
 #endif
-	flush_cache_page(vma, addr, pte_pfn(pte));
+	flush_dcache_page(new);
 	set_pte_at(mm, addr, ptep, pte);
 
 	if (PageHuge(new)) {
@@ -184,15 +184,14 @@ static void remove_migration_ptes(struct page *old, struct page *new)
  *
  * This function is called from do_swap_page().
  */
-void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
-				unsigned long address)
+static void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
+				spinlock_t *ptl)
 {
-	pte_t *ptep, pte;
-	spinlock_t *ptl;
+	pte_t pte;
 	swp_entry_t entry;
 	struct page *page;
 
-	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
+	spin_lock(ptl);
 	pte = *ptep;
 	if (!is_swap_pte(pte))
 		goto out;
@@ -220,6 +219,20 @@ out:
 	pte_unmap_unlock(ptep, ptl);
 }
 
+void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
+				unsigned long address)
+{
+	spinlock_t *ptl = pte_lockptr(mm, pmd);
+	pte_t *ptep = pte_offset_map(pmd, address);
+	__migration_entry_wait(mm, ptep, ptl);
+}
+
+void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte)
+{
+	spinlock_t *ptl = &(mm)->page_table_lock;
+	__migration_entry_wait(mm, pte, ptl);
+}
+
 #ifdef CONFIG_BLOCK
 /* Returns true if all buffers are successfully locked */
 static bool buffer_migrate_lock_buffers(struct buffer_head *head,
diff --git a/mm/mmap.c b/mm/mmap.c
index d49736ff8a8..d1cf520e511 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1581,7 +1581,7 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 	if (mm) {
 		/* Check the cache first. */
 		/* (Cache hit rate is typically around 35%.) */
-		vma = mm->mmap_cache;
+		vma = ACCESS_ONCE(mm->mmap_cache);
 		if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) {
 			struct rb_node * rb_node;
 
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 71c78115c45..2b52947e48f 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -14,10 +14,14 @@
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/err.h>
+#include <linux/srcu.h>
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 
+/* global SRCU for all MMs */
+static struct srcu_struct srcu;
+
 /*
  * This function can't run concurrently against mmu_notifier_register
  * because mm->mm_users > 0 during mmu_notifier_register and exit_mmap
@@ -25,32 +29,32 @@
  * in parallel despite there being no task using this mm any more,
  * through the vmas outside of the exit_mmap context, such as with
  * vmtruncate. This serializes against mmu_notifier_unregister with
- * the mmu_notifier_mm->lock in addition to RCU and it serializes
- * against the other mmu notifiers with RCU. struct mmu_notifier_mm
+ * the mmu_notifier_mm->lock in addition to SRCU and it serializes
+ * against the other mmu notifiers with SRCU. struct mmu_notifier_mm
  * can't go away from under us as exit_mmap holds an mm_count pin
  * itself.
  */
 void __mmu_notifier_release(struct mm_struct *mm)
 {
 	struct mmu_notifier *mn;
-	struct hlist_node *n;
+	struct hlist_node *node;
+	int id;
 
 	/*
-	 * RCU here will block mmu_notifier_unregister until
+	 * SRCU here will block mmu_notifier_unregister until
 	 * ->release returns.
 	 */
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist)
+	id = srcu_read_lock(&srcu);
+	hlist_for_each_entry_rcu(mn, node, &mm->mmu_notifier_mm->list, hlist)
 		/*
-		 * if ->release runs before mmu_notifier_unregister it
-		 * must be handled as it's the only way for the driver
-		 * to flush all existing sptes and stop the driver
-		 * from establishing any more sptes before all the
-		 * pages in the mm are freed.
+		 * If ->release runs before mmu_notifier_unregister it must be
+		 * handled, as it's the only way for the driver to flush all
+		 * existing sptes and stop the driver from establishing any more
+		 * sptes before all the pages in the mm are freed.
 		 */
 		if (mn->ops->release)
 			mn->ops->release(mn, mm);
-	rcu_read_unlock();
+	srcu_read_unlock(&srcu, id);
 
 	spin_lock(&mm->mmu_notifier_mm->lock);
 	while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) {
@@ -59,24 +63,24 @@ void __mmu_notifier_release(struct mm_struct *mm)
 				 hlist);
 		/*
 		 * We arrived before mmu_notifier_unregister so
-		 * mmu_notifier_unregister will do nothing other than
-		 * to wait ->release to finish and
-		 * mmu_notifier_unregister to return.
+		 * mmu_notifier_unregister will do nothing other than to wait
+		 * for ->release to finish and for mmu_notifier_unregister to
+		 * return.
 		 */
 		hlist_del_init_rcu(&mn->hlist);
 	}
 	spin_unlock(&mm->mmu_notifier_mm->lock);
 
 	/*
-	 * synchronize_rcu here prevents mmu_notifier_release to
-	 * return to exit_mmap (which would proceed freeing all pages
-	 * in the mm) until the ->release method returns, if it was
-	 * invoked by mmu_notifier_unregister.
+	 * synchronize_srcu here prevents mmu_notifier_release from returning to
+	 * exit_mmap (which would proceed with freeing all pages in the mm)
+	 * until the ->release method returns, if it was invoked by
+	 * mmu_notifier_unregister.
 	 *
-	 * The mmu_notifier_mm can't go away from under us because one
-	 * mm_count is hold by exit_mmap.
+	 * The mmu_notifier_mm can't go away from under us because one mm_count
+	 * is held by exit_mmap.
 	 */
-	synchronize_rcu();
+	synchronize_srcu(&srcu);
 }
 
 /*
@@ -89,14 +93,14 @@ int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
 {
 	struct mmu_notifier *mn;
 	struct hlist_node *n;
-	int young = 0;
+	int young = 0, id;
 
-	rcu_read_lock();
+	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->clear_flush_young)
 			young |= mn->ops->clear_flush_young(mn, mm, address);
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&srcu, id);
 
 	return young;
 }
@@ -106,9 +110,9 @@ int __mmu_notifier_test_young(struct mm_struct *mm,
 {
 	struct mmu_notifier *mn;
 	struct hlist_node *n;
-	int young = 0;
+	int young = 0, id;
 
-	rcu_read_lock();
+	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->test_young) {
 			young = mn->ops->test_young(mn, mm, address);
@@ -116,7 +120,7 @@ int __mmu_notifier_test_young(struct mm_struct *mm,
 				break;
 		}
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&srcu, id);
 
 	return young;
 }
@@ -126,8 +130,9 @@ void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address,
 {
 	struct mmu_notifier *mn;
 	struct hlist_node *n;
+	int id;
 
-	rcu_read_lock();
+	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->change_pte)
 			mn->ops->change_pte(mn, mm, address, pte);
@@ -138,7 +143,7 @@ void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address,
 		else if (mn->ops->invalidate_page)
 			mn->ops->invalidate_page(mn, mm, address);
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&srcu, id);
 }
 
 void __mmu_notifier_invalidate_page(struct mm_struct *mm,
@@ -146,13 +151,14 @@ void __mmu_notifier_invalidate_page(struct mm_struct *mm,
 {
 	struct mmu_notifier *mn;
 	struct hlist_node *n;
+	int id;
 
-	rcu_read_lock();
+	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->invalidate_page)
 			mn->ops->invalidate_page(mn, mm, address);
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&srcu, id);
 }
 
 void __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
@@ -160,13 +166,14 @@ void __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
 {
 	struct mmu_notifier *mn;
 	struct hlist_node *n;
+	int id;
 
-	rcu_read_lock();
+	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->invalidate_range_start)
 			mn->ops->invalidate_range_start(mn, mm, start, end);
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&srcu, id);
 }
 
 void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
@@ -174,13 +181,14 @@ void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 {
 	struct mmu_notifier *mn;
 	struct hlist_node *n;
+	int id;
 
-	rcu_read_lock();
+	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
 		if (mn->ops->invalidate_range_end)
 			mn->ops->invalidate_range_end(mn, mm, start, end);
 	}
-	rcu_read_unlock();
+	srcu_read_unlock(&srcu, id);
 }
 
 static int do_mmu_notifier_register(struct mmu_notifier *mn,
@@ -192,6 +200,12 @@ 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.
+	*/
+	BUG_ON(!srcu.per_cpu_ref);
+
 	ret = -ENOMEM;
 	mmu_notifier_mm = kmalloc(sizeof(struct mmu_notifier_mm), GFP_KERNEL);
 	if (unlikely(!mmu_notifier_mm))
@@ -274,8 +288,8 @@ void __mmu_notifier_mm_destroy(struct mm_struct *mm)
 /*
  * This releases the mm_count pin automatically and frees the mm
  * structure if it was the last user of it. It serializes against
- * running mmu notifiers with RCU and against mmu_notifier_unregister
- * with the unregister lock + RCU. All sptes must be dropped before
+ * running mmu notifiers with SRCU and against mmu_notifier_unregister
+ * with the unregister lock + SRCU. All sptes must be dropped before
  * calling mmu_notifier_unregister. ->release or any other notifier
  * method may be invoked concurrently with mmu_notifier_unregister,
  * and only after mmu_notifier_unregister returned we're guaranteed
@@ -287,33 +301,44 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm)
 
 	if (!hlist_unhashed(&mn->hlist)) {
 		/*
-		 * RCU here will force exit_mmap to wait ->release to finish
-		 * before freeing the pages.
+		 * SRCU here will force exit_mmap to wait for ->release to
+		 * finish before freeing the pages.
 		 */
-		rcu_read_lock();
+		int id;
 
+		id = srcu_read_lock(&srcu);
 		/*
-		 * exit_mmap will block in mmu_notifier_release to
-		 * guarantee ->release is called before freeing the
-		 * pages.
+		 * exit_mmap will block in mmu_notifier_release to guarantee
+		 * that ->release is called before freeing the pages.
 		 */
 		if (mn->ops->release)
 			mn->ops->release(mn, mm);
-		rcu_read_unlock();
+		srcu_read_unlock(&srcu, id);
 
 		spin_lock(&mm->mmu_notifier_mm->lock);
-		hlist_del_rcu(&mn->hlist);
+		/*
+		 * Can not use list_del_rcu() since __mmu_notifier_release
+		 * can delete it before we hold the lock.
+		 */
+		hlist_del_init_rcu(&mn->hlist);
 		spin_unlock(&mm->mmu_notifier_mm->lock);
 	}
 
 	/*
-	 * Wait any running method to finish, of course including
+	 * Wait for any running method to finish, of course including
 	 * ->release if it was run by mmu_notifier_relase instead of us.
 	 */
-	synchronize_rcu();
+	synchronize_srcu(&srcu);
 
 	BUG_ON(atomic_read(&mm->mm_count) <= 0);
 
 	mmdrop(mm);
 }
 EXPORT_SYMBOL_GPL(mmu_notifier_unregister);
+
+static int __init mmu_notifier_init(void)
+{
+	return init_srcu_struct(&srcu);
+}
+
+module_init(mmu_notifier_init);
diff --git a/mm/nommu.c b/mm/nommu.c
index 5ff9b35883e..92429242a19 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -808,7 +808,7 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 	struct vm_area_struct *vma;
 
 	/* check the cache first */
-	vma = mm->mmap_cache;
+	vma = ACCESS_ONCE(mm->mmap_cache);
 	if (vma && vma->vm_start <= addr && vma->vm_end > addr)
 		return vma;
 
@@ -1826,6 +1826,16 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 }
 EXPORT_SYMBOL(remap_pfn_range);
 
+int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len)
+{
+	unsigned long pfn = start >> PAGE_SHIFT;
+	unsigned long vm_len = vma->vm_end - vma->vm_start;
+
+	pfn += vma->vm_pgoff;
+	return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot);
+}
+EXPORT_SYMBOL(vm_iomap_memory);
+
 int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
 			unsigned long pgoff)
 {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d1a7b6d35dc..9450436fe1f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4379,10 +4379,11 @@ static void __meminit calculate_node_totalpages(struct pglist_data *pgdat,
  * round what is now in bits to nearest long in bits, then return it in
  * bytes.
  */
-static unsigned long __init usemap_size(unsigned long zonesize)
+static unsigned long __init usemap_size(unsigned long zone_start_pfn, unsigned long zonesize)
 {
 	unsigned long usemapsize;
 
+	zonesize += zone_start_pfn & (pageblock_nr_pages-1);
 	usemapsize = roundup(zonesize, pageblock_nr_pages);
 	usemapsize = usemapsize >> pageblock_order;
 	usemapsize *= NR_PAGEBLOCK_BITS;
@@ -4392,17 +4393,19 @@ static unsigned long __init usemap_size(unsigned long zonesize)
 }
 
 static void __init setup_usemap(struct pglist_data *pgdat,
-				struct zone *zone, unsigned long zonesize)
+				struct zone *zone,
+				unsigned long zone_start_pfn,
+				unsigned long zonesize)
 {
-	unsigned long usemapsize = usemap_size(zonesize);
+	unsigned long usemapsize = usemap_size(zone_start_pfn, zonesize);
 	zone->pageblock_flags = NULL;
 	if (usemapsize)
 		zone->pageblock_flags = alloc_bootmem_node_nopanic(pgdat,
 								   usemapsize);
 }
 #else
-static inline void setup_usemap(struct pglist_data *pgdat,
-				struct zone *zone, unsigned long zonesize) {}
+static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone,
+				unsigned long zone_start_pfn, unsigned long zonesize) {}
 #endif /* CONFIG_SPARSEMEM */
 
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
@@ -4530,7 +4533,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 			continue;
 
 		set_pageblock_order(pageblock_default_order());
-		setup_usemap(pgdat, zone, size);
+		setup_usemap(pgdat, zone, zone_start_pfn, size);
 		ret = init_currently_empty_zone(zone, zone_start_pfn,
 						size, MEMMAP_EARLY);
 		BUG_ON(ret);
@@ -5850,6 +5853,10 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 		zone->free_area[order].nr_free--;
 		__mod_zone_page_state(zone, NR_FREE_PAGES,
 				      - (1UL << order));
+#ifdef CONFIG_HIGHMEM
+		if (PageHighMem(page))
+			totalhigh_pages -= 1 << order;
+#endif
 		for (i = 0; i < (1 << order); i++)
 			SetPageReserved((page+i));
 		pfn += (1 << order);
diff --git a/mm/shmem.c b/mm/shmem.c
index 818947be0d9..a858b67b426 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2514,6 +2514,7 @@ static int shmem_remount_fs(struct super_block *sb, int *flags, char *data)
 	unsigned long inodes;
 	int error = -EINVAL;
 
+	config.mpol = NULL;
 	if (shmem_parse_options(data, &config, true))
 		return error;
 
@@ -2539,8 +2540,13 @@ static int shmem_remount_fs(struct super_block *sb, int *flags, char *data)
 	sbinfo->max_inodes  = config.max_inodes;
 	sbinfo->free_inodes = config.max_inodes - inodes;
 
-	mpol_put(sbinfo->mpol);
-	sbinfo->mpol        = config.mpol;	/* transfers initial ref */
+	/*
+	 * Preserve previous mempolicy unless mpol remount option was specified.
+	 */
+	if (config.mpol) {
+		mpol_put(sbinfo->mpol);
+		sbinfo->mpol = config.mpol;	/* transfers initial ref */
+	}
 out:
 	spin_unlock(&sbinfo->stat_lock);
 	return error;
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 10e9198778c..43b957e5754 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -315,8 +315,24 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		 * Swap entry may have been freed since our caller observed it.
 		 */
 		err = swapcache_prepare(entry);
-		if (err == -EEXIST) {	/* seems racy */
+		if (err == -EEXIST) {
 			radix_tree_preload_end();
+			/*
+			 * We might race against get_swap_page() and stumble
+			 * across a SWAP_HAS_CACHE swap_map entry whose page
+			 * has not been brought into the swapcache yet, while
+			 * the other end is scheduled away waiting on discard
+			 * I/O completion at scan_swap_map().
+			 *
+			 * In order to avoid turning this transitory state
+			 * into a permanent loop around this -EEXIST case
+			 * if !CONFIG_PREEMPT and the I/O completion happens
+			 * to be waiting on the CPU waitqueue where we are now
+			 * busy looping, we just conditionally invoke the
+			 * scheduler here, if there are some more important
+			 * tasks to run.
+			 */
+			cond_resched();
 			continue;
 		}
 		if (err) {		/* swp entry is obsolete ? */