5 files changed, 25 insertions, 9 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 5a16423a512c..ae8f708e3d75 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2498,7 +2498,6 @@ retry_avoidcopy:
                 if (outside_reserve) {
                         BUG_ON(huge_pte_none(pte));
                         if (unmap_ref_private(mm, vma, old_page, address)) {
-                                BUG_ON(page_count(old_page) != 1);
                                 BUG_ON(huge_pte_none(pte));
                                 spin_lock(&mm->page_table_lock);
                                 ptep = huge_pte_offset(mm, address & huge_page_mask(h));
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 31ab9c3f0178..b659260c56ad 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4507,6 +4507,12 @@ static void mem_cgroup_usage_unregister_event(struct cgroup *cgrp,
 swap_buffers:
         /* Swap primary and spare array */
         thresholds->spare = thresholds->primary;
+        /* If all events are unregistered, free the spare array */
+        if (!new) {
+                kfree(thresholds->spare);
+                thresholds->spare = NULL;
+        }
+
         rcu_assign_pointer(thresholds->primary, new);
 
         /* To be sure that nobody uses thresholds */
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index e53bb8a256b1..1983fb1c7026 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -82,8 +82,7 @@ void __init free_bootmem_late(unsigned long addr, unsigned long size)
 
 static void __init __free_pages_memory(unsigned long start, unsigned long end)
 {
-        int i;
-        unsigned long start_aligned, end_aligned;
+        unsigned long i, start_aligned, end_aligned;
         int order = ilog2(BITS_PER_LONG);
 
         start_aligned = (start + (BITS_PER_LONG - 1)) & ~(BITS_PER_LONG - 1);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a712fb9e04ce..918330f71dba 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5203,7 +5203,7 @@ int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
         int ret;
 
         ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
-        if (!write || (ret == -EINVAL))
+        if (!write || (ret < 0))
                 return ret;
         for_each_populated_zone(zone) {
                 for_each_possible_cpu(cpu) {
diff --git a/mm/percpu.c b/mm/percpu.c
index f47af9123af7..bb4be7435ce3 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1132,20 +1132,20 @@ static void pcpu_dump_alloc_info(const char *lvl,
                 for (alloc_end += gi->nr_units / upa;
                      alloc < alloc_end; alloc++) {
                         if (!(alloc % apl)) {
-                                printk("\n");
+                                printk(KERN_CONT "\n");
                                 printk("%spcpu-alloc: ", lvl);
                         }
-                        printk("[%0*d] ", group_width, group);
+                        printk(KERN_CONT "[%0*d] ", group_width, group);
 
                         for (unit_end += upa; unit < unit_end; unit++)
                                 if (gi->cpu_map[unit] != NR_CPUS)
-                                        printk("%0*d ", cpu_width,
+                                        printk(KERN_CONT "%0*d ", cpu_width,
                                                gi->cpu_map[unit]);
                                 else
-                                        printk("%s ", empty_str);
+                                        printk(KERN_CONT "%s ", empty_str);
                 }
         }
-        printk("\n");
+        printk(KERN_CONT "\n");
 }
 
 /**
@@ -1650,6 +1650,16 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
                 areas[group] = ptr;
 
                 base = min(ptr, base);
+        }
+
+        /*
+         * Copy data and free unused parts.  This should happen after all
+         * allocations are complete; otherwise, we may end up with
+         * overlapping groups.
+         */
+        for (group = 0; group < ai->nr_groups; group++) {
+                struct pcpu_group_info *gi = &ai->groups[group];
+                void *ptr = areas[group];
 
                 for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) {
                         if (gi->cpu_map[i] == NR_CPUS) {
@@ -1885,6 +1895,8 @@ void __init setup_per_cpu_areas(void)
         fc = __alloc_bootmem(unit_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
         if (!ai || !fc)
                 panic("Failed to allocate memory for percpu areas.");
+        /* kmemleak tracks the percpu allocations separately */
+        kmemleak_free(fc);
 
         ai->dyn_size = unit_size;
         ai->unit_size = unit_size;