12 files changed, 74 insertions, 46 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index c0018f2d50e0..5f0a3c91fdac 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1828,7 +1828,7 @@ repeat:
                 page = __page_cache_alloc(gfp | __GFP_COLD);
                 if (!page)
                         return ERR_PTR(-ENOMEM);
-                err = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL);
+                err = add_to_page_cache_lru(page, mapping, index, gfp);
                 if (unlikely(err)) {
                         page_cache_release(page);
                         if (err == -EEXIST)
@@ -1925,10 +1925,7 @@ static struct page *wait_on_page_read(struct page *page)
  * @gfp:        the page allocator flags to use if allocating
  *
  * This is the same as "read_mapping_page(mapping, index, NULL)", but with
- * any new page allocations done using the specified allocation flags. Note
- * that the Radix tree operations will still use GFP_KERNEL, so you can't
- * expect to do this atomically or anything like that - but you can pass in
- * other page requirements.
+ * any new page allocations done using the specified allocation flags.
  *
  * If the page does not get brought uptodate, return -EIO.
  */
@@ -2407,7 +2404,6 @@ static ssize_t generic_perform_write(struct file *file,
                                                 iov_iter_count(i));
 
 again:
-
                 /*
                  * Bring in the user page that we will copy from _first_.
                  * Otherwise there's a nasty deadlock on copying from the
@@ -2463,7 +2459,10 @@ again:
                 written += copied;
 
                 balance_dirty_pages_ratelimited(mapping);
-
+                if (fatal_signal_pending(current)) {
+                        status = -EINTR;
+                        break;
+                }
         } while (iov_iter_count(i));
 
         return written ? written : status;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 4298abaae153..36b3d988b4ef 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2259,12 +2259,8 @@ static void khugepaged_do_scan(struct page **hpage)
 
 static void khugepaged_alloc_sleep(void)
 {
-        DEFINE_WAIT(wait);
-        add_wait_queue(&khugepaged_wait, &wait);
-        schedule_timeout_interruptible(
-                msecs_to_jiffies(
-                        khugepaged_alloc_sleep_millisecs));
-        remove_wait_queue(&khugepaged_wait, &wait);
+        wait_event_freezable_timeout(khugepaged_wait, false,
+                        msecs_to_jiffies(khugepaged_alloc_sleep_millisecs));
 }
 
 #ifndef CONFIG_NUMA
@@ -2313,14 +2309,10 @@ static void khugepaged_loop(void)
                 if (unlikely(kthread_should_stop()))
                         break;
                 if (khugepaged_has_work()) {
-                        DEFINE_WAIT(wait);
                         if (!khugepaged_scan_sleep_millisecs)
                                 continue;
-                        add_wait_queue(&khugepaged_wait, &wait);
-                        schedule_timeout_interruptible(
-                                msecs_to_jiffies(
-                                        khugepaged_scan_sleep_millisecs));
-                        remove_wait_queue(&khugepaged_wait, &wait);
+                        wait_event_freezable_timeout(khugepaged_wait, false,
+                            msecs_to_jiffies(khugepaged_scan_sleep_millisecs));
                 } else if (khugepaged_enabled())
                         wait_event_freezable(khugepaged_wait,
                                              khugepaged_wait_event());
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index bb28a5f9db8d..73f17c0293c0 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -576,6 +576,7 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order)
         __SetPageHead(page);
         for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
                 __SetPageTail(p);
+                set_page_count(p, 0);
                 p->first_page = page;
         }
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6aff93c98aca..b63f5f7dfa07 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4907,9 +4907,9 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
                 int cpu;
                 enable_swap_cgroup();
                 parent = NULL;
-                root_mem_cgroup = memcg;
                 if (mem_cgroup_soft_limit_tree_init())
                         goto free_out;
+                root_mem_cgroup = memcg;
                 for_each_possible_cpu(cpu) {
                         struct memcg_stock_pcp *stock =
                                                 &per_cpu(memcg_stock, cpu);
@@ -4948,7 +4948,6 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
         return &memcg->css;
 free_out:
         __mem_cgroup_free(memcg);
-        root_mem_cgroup = NULL;
         return ERR_PTR(error);
 }
 
diff --git a/mm/migrate.c b/mm/migrate.c
index 578e29174fa6..177aca424a06 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -871,9 +871,9 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 
         if (anon_vma)
                 put_anon_vma(anon_vma);
-out:
         unlock_page(hpage);
 
+out:
         if (rc != -EAGAIN) {
                 list_del(&hpage->lru);
                 put_page(hpage);
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 76f2c5ae908e..069b64e521fc 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -176,7 +176,7 @@ static bool oom_unkillable_task(struct task_struct *p,
 unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
                       const nodemask_t *nodemask, unsigned long totalpages)
 {
-        int points;
+        long points;
 
         if (oom_unkillable_task(p, mem, nodemask))
                 return 0;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 71252486bc6f..50f08241f981 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -411,8 +411,13 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty)
  *
  * Returns @bdi's dirty limit in pages. The term "dirty" in the context of
  * dirty balancing includes all PG_dirty, PG_writeback and NFS unstable pages.
- * And the "limit" in the name is not seriously taken as hard limit in
- * balance_dirty_pages().
+ *
+ * Note that balance_dirty_pages() will only seriously take it as a hard limit
+ * when sleeping max_pause per page is not enough to keep the dirty pages under
+ * control. For example, when the device is completely stalled due to some error
+ * conditions, or when there are 1000 dd tasks writing to a slow 10MB/s USB key.
+ * In the other normal situations, it acts more gently by throttling the tasks
+ * more (rather than completely block them) when the bdi dirty pages go high.
  *
  * It allocates high/low dirty limits to fast/slow devices, in order to prevent
  * - starving fast devices
@@ -594,6 +599,13 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi,
          */
         if (unlikely(bdi_thresh > thresh))
                 bdi_thresh = thresh;
+        /*
+         * It's very possible that bdi_thresh is close to 0 not because the
+         * device is slow, but that it has remained inactive for long time.
+         * Honour such devices a reasonable good (hopefully IO efficient)
+         * threshold, so that the occasional writes won't be blocked and active
+         * writes can rampup the threshold quickly.
+         */
         bdi_thresh = max(bdi_thresh, (limit - dirty) / 8);
         /*
          * scale global setpoint to bdi's:
@@ -977,8 +989,7 @@ static unsigned long bdi_max_pause(struct backing_dev_info *bdi,
          *
          * 8 serves as the safety ratio.
          */
-        if (bdi_dirty)
-                t = min(t, bdi_dirty * HZ / (8 * bw + 1));
+        t = min(t, bdi_dirty * HZ / (8 * bw + 1));
 
         /*
          * The pause time will be settled within range (max_pause/4, max_pause).
@@ -1136,6 +1147,19 @@ pause:
                 if (task_ratelimit)
                         break;
 
+                /*
+                 * In the case of an unresponding NFS server and the NFS dirty
+                 * pages exceeds dirty_thresh, give the other good bdi's a pipe
+                 * to go through, so that tasks on them still remain responsive.
+                 *
+                 * In theory 1 page is enough to keep the comsumer-producer
+                 * pipe going: the flusher cleans 1 page => the task dirties 1
+                 * more page. However bdi_dirty has accounting errors.  So use
+                 * the larger and more IO friendly bdi_stat_error.
+                 */
+                if (bdi_dirty <= bdi_stat_error(bdi))
+                        break;
+
                 if (fatal_signal_pending(current))
                         break;
         }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9dd443d89d8b..2b8ba3aebf6e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -356,8 +356,8 @@ void prep_compound_page(struct page *page, unsigned long order)
         __SetPageHead(page);
         for (i = 1; i < nr_pages; i++) {
                 struct page *p = page + i;
-
                 __SetPageTail(p);
+                set_page_count(p, 0);
                 p->first_page = page;
         }
 }
@@ -3377,9 +3377,15 @@ static void setup_zone_migrate_reserve(struct zone *zone)
         unsigned long block_migratetype;
         int reserve;
 
-        /* Get the start pfn, end pfn and the number of blocks to reserve */
+        /*
+         * Get the start pfn, end pfn and the number of blocks to reserve
+         * We have to be careful to be aligned to pageblock_nr_pages to
+         * make sure that we always check pfn_valid for the first page in
+         * the block.
+         */
         start_pfn = zone->zone_start_pfn;
         end_pfn = start_pfn + zone->spanned_pages;
+        start_pfn = roundup(start_pfn, pageblock_nr_pages);
         reserve = roundup(min_wmark_pages(zone), pageblock_nr_pages) >>
                                                         pageblock_order;
 
diff --git a/mm/percpu.c b/mm/percpu.c
index 3bb810a72006..716eb4acf2fc 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1023,9 +1023,11 @@ phys_addr_t per_cpu_ptr_to_phys(void *addr)
                 if (!is_vmalloc_addr(addr))
                         return __pa(addr);
                 else
-                        return page_to_phys(vmalloc_to_page(addr));
+                        return page_to_phys(vmalloc_to_page(addr)) +
+                               offset_in_page(addr);
         } else
-                return page_to_phys(pcpu_addr_to_page(addr));
+                return page_to_phys(pcpu_addr_to_page(addr)) +
+                       offset_in_page(addr);
 }
 
 /**
diff --git a/mm/slab.c b/mm/slab.c
index 708efe886154..83311c9aaf9d 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -595,6 +595,7 @@ static enum {
         PARTIAL_AC,
         PARTIAL_L3,
         EARLY,
+        LATE,
         FULL
 } g_cpucache_up;
 
@@ -671,7 +672,7 @@ static void init_node_lock_keys(int q)
 {
         struct cache_sizes *s = malloc_sizes;
 
-        if (g_cpucache_up != FULL)
+        if (g_cpucache_up < LATE)
                 return;
 
         for (s = malloc_sizes; s->cs_size != ULONG_MAX; s++) {
@@ -1666,6 +1667,8 @@ void __init kmem_cache_init_late(void)
 {
         struct kmem_cache *cachep;
 
+        g_cpucache_up = LATE;
+
         /* Annotate slab for lockdep -- annotate the malloc caches */
         init_lock_keys();
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index e583f770dfee..21fdf46ad5aa 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1315,7 +1315,7 @@ static struct vm_struct *__get_vm_area_node(unsigned long size,
                 unsigned long align, unsigned long flags, unsigned long start,
                 unsigned long end, int node, gfp_t gfp_mask, void *caller)
 {
-        static struct vmap_area *va;
+        struct vmap_area *va;
         struct vm_struct *area;
 
         BUG_ON(in_interrupt());
@@ -1658,6 +1658,8 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
                 goto fail;
 
         addr = __vmalloc_area_node(area, gfp_mask, prot, node, caller);
+        if (!addr)
+                return NULL;
 
         /*
          * In this function, newly allocated vm_struct is not added
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a1893c050795..f54a05b7a61d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -183,7 +183,7 @@ static unsigned long zone_nr_lru_pages(struct zone *zone,
  */
 void register_shrinker(struct shrinker *shrinker)
 {
-        shrinker->nr = 0;
+        atomic_long_set(&shrinker->nr_in_batch, 0);
         down_write(&shrinker_rwsem);
         list_add_tail(&shrinker->list, &shrinker_list);
         up_write(&shrinker_rwsem);
@@ -247,25 +247,26 @@ unsigned long shrink_slab(struct shrink_control *shrink,
 
         list_for_each_entry(shrinker, &shrinker_list, list) {
                 unsigned long long delta;
-                unsigned long total_scan;
-                unsigned long max_pass;
+                long total_scan;
+                long max_pass;
                 int shrink_ret = 0;
                 long nr;
                 long new_nr;
                 long batch_size = shrinker->batch ? shrinker->batch
                                                   : SHRINK_BATCH;
 
+                max_pass = do_shrinker_shrink(shrinker, shrink, 0);
+                if (max_pass <= 0)
+                        continue;
+
                 /*
                  * copy the current shrinker scan count into a local variable
                  * and zero it so that other concurrent shrinker invocations
                  * don't also do this scanning work.
                  */
-                do {
-                        nr = shrinker->nr;
-                } while (cmpxchg(&shrinker->nr, nr, 0) != nr);
+                nr = atomic_long_xchg(&shrinker->nr_in_batch, 0);
 
                 total_scan = nr;
-                max_pass = do_shrinker_shrink(shrinker, shrink, 0);
                 delta = (4 * nr_pages_scanned) / shrinker->seeks;
                 delta *= max_pass;
                 do_div(delta, lru_pages + 1);
@@ -325,12 +326,11 @@ unsigned long shrink_slab(struct shrink_control *shrink,
                  * manner that handles concurrent updates. If we exhausted the
                  * scan, there is no need to do an update.
                  */
-                do {
-                        nr = shrinker->nr;
-                        new_nr = total_scan + nr;
-                        if (total_scan <= 0)
-                                break;
-                } while (cmpxchg(&shrinker->nr, nr, new_nr) != nr);
+                if (total_scan > 0)
+                        new_nr = atomic_long_add_return(total_scan,
+                                        &shrinker->nr_in_batch);
+                else
+                        new_nr = atomic_long_read(&shrinker->nr_in_batch);
 
                 trace_mm_shrink_slab_end(shrinker, shrink_ret, nr, new_nr);
         }