Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

10 files changed, 105 insertions, 40 deletions

diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index 9eebfadeeee1..a67c26e0f360 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -217,7 +217,7 @@ void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
 
         if (hugetlb_cgroup_disabled())
                 return;
-        VM_BUG_ON(!spin_is_locked(&hugetlb_lock));
+        lockdep_assert_held(&hugetlb_lock);
         h_cg = hugetlb_cgroup_from_page(page);
         if (unlikely(!h_cg))
                 return;
diff --git a/mm/memblock.c b/mm/memblock.c
index 6d2f219a48b0..70fad0c0dafb 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -192,8 +192,7 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
                                         phys_addr_t align, phys_addr_t start,
                                         phys_addr_t end, int nid)
 {
-        int ret;
-        phys_addr_t kernel_end;
+        phys_addr_t kernel_end, ret;
 
         /* pump up @end */
         if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ec4dcf1b9562..085dc6d2f876 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2534,6 +2534,8 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
         unsigned long long size;
         int ret = 0;
 
+        if (mem_cgroup_is_root(memcg))
+                goto done;
 retry:
         if (consume_stock(memcg, nr_pages))
                 goto done;
@@ -2611,9 +2613,7 @@ nomem:
         if (!(gfp_mask & __GFP_NOFAIL))
                 return -ENOMEM;
 bypass:
-        memcg = root_mem_cgroup;
-        ret = -EINTR;
-        goto retry;
+        return -EINTR;
 
 done_restock:
         if (batch > nr_pages)
@@ -2626,6 +2626,9 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
         unsigned long bytes = nr_pages * PAGE_SIZE;
 
+        if (mem_cgroup_is_root(memcg))
+                return;
+
         res_counter_uncharge(&memcg->res, bytes);
         if (do_swap_account)
                 res_counter_uncharge(&memcg->memsw, bytes);
@@ -2640,6 +2643,9 @@ static void __mem_cgroup_cancel_local_charge(struct mem_cgroup *memcg,
 {
         unsigned long bytes = nr_pages * PAGE_SIZE;
 
+        if (mem_cgroup_is_root(memcg))
+                return;
+
         res_counter_uncharge_until(&memcg->res, memcg->res.parent, bytes);
         if (do_swap_account)
                 res_counter_uncharge_until(&memcg->memsw,
@@ -4093,6 +4099,46 @@ out:
         return retval;
 }
 
+static unsigned long mem_cgroup_recursive_stat(struct mem_cgroup *memcg,
+                                               enum mem_cgroup_stat_index idx)
+{
+        struct mem_cgroup *iter;
+        long val = 0;
+
+        /* Per-cpu values can be negative, use a signed accumulator */
+        for_each_mem_cgroup_tree(iter, memcg)
+                val += mem_cgroup_read_stat(iter, idx);
+
+        if (val < 0) /* race ? */
+                val = 0;
+        return val;
+}
+
+static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
+{
+        u64 val;
+
+        if (!mem_cgroup_is_root(memcg)) {
+                if (!swap)
+                        return res_counter_read_u64(&memcg->res, RES_USAGE);
+                else
+                        return res_counter_read_u64(&memcg->memsw, RES_USAGE);
+        }
+
+        /*
+         * Transparent hugepages are still accounted for in MEM_CGROUP_STAT_RSS
+         * as well as in MEM_CGROUP_STAT_RSS_HUGE.
+         */
+        val = mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_CACHE);
+        val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_RSS);
+
+        if (swap)
+                val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_SWAP);
+
+        return val << PAGE_SHIFT;
+}
+
+
 static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
                                struct cftype *cft)
 {
@@ -4102,8 +4148,12 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
 
         switch (type) {
         case _MEM:
+                if (name == RES_USAGE)
+                        return mem_cgroup_usage(memcg, false);
                 return res_counter_read_u64(&memcg->res, name);
         case _MEMSWAP:
+                if (name == RES_USAGE)
+                        return mem_cgroup_usage(memcg, true);
                 return res_counter_read_u64(&memcg->memsw, name);
         case _KMEM:
                 return res_counter_read_u64(&memcg->kmem, name);
@@ -4572,10 +4622,7 @@ static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap)
         if (!t)
                 goto unlock;
 
-        if (!swap)
-                usage = res_counter_read_u64(&memcg->res, RES_USAGE);
-        else
-                usage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
+        usage = mem_cgroup_usage(memcg, swap);
 
         /*
          * current_threshold points to threshold just below or equal to usage.
@@ -4673,10 +4720,10 @@ static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg,
 
         if (type == _MEM) {
                 thresholds = &memcg->thresholds;
-                usage = res_counter_read_u64(&memcg->res, RES_USAGE);
+                usage = mem_cgroup_usage(memcg, false);
         } else if (type == _MEMSWAP) {
                 thresholds = &memcg->memsw_thresholds;
-                usage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
+                usage = mem_cgroup_usage(memcg, true);
         } else
                 BUG();
 
@@ -4762,10 +4809,10 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
 
         if (type == _MEM) {
                 thresholds = &memcg->thresholds;
-                usage = res_counter_read_u64(&memcg->res, RES_USAGE);
+                usage = mem_cgroup_usage(memcg, false);
         } else if (type == _MEMSWAP) {
                 thresholds = &memcg->memsw_thresholds;
-                usage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
+                usage = mem_cgroup_usage(memcg, true);
         } else
                 BUG();
 
@@ -5525,9 +5572,9 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
                  * core guarantees its existence.
                  */
         } else {
-                res_counter_init(&memcg->res, &root_mem_cgroup->res);
-                res_counter_init(&memcg->memsw, &root_mem_cgroup->memsw);
-                res_counter_init(&memcg->kmem, &root_mem_cgroup->kmem);
+                res_counter_init(&memcg->res, NULL);
+                res_counter_init(&memcg->memsw, NULL);
+                res_counter_init(&memcg->kmem, NULL);
                 /*
                  * Deeper hierachy with use_hierarchy == false doesn't make
                  * much sense so let cgroup subsystem know about this
@@ -5969,8 +6016,9 @@ static void __mem_cgroup_clear_mc(void)
         /* we must fixup refcnts and charges */
         if (mc.moved_swap) {
                 /* uncharge swap account from the old cgroup */
-                res_counter_uncharge(&mc.from->memsw,
-                                     PAGE_SIZE * mc.moved_swap);
+                if (!mem_cgroup_is_root(mc.from))
+                        res_counter_uncharge(&mc.from->memsw,
+                                             PAGE_SIZE * mc.moved_swap);
 
                 for (i = 0; i < mc.moved_swap; i++)
                         css_put(&mc.from->css);
@@ -5979,8 +6027,9 @@ static void __mem_cgroup_clear_mc(void)
                  * we charged both to->res and to->memsw, so we should
                  * uncharge to->res.
                  */
-                res_counter_uncharge(&mc.to->res,
-                                     PAGE_SIZE * mc.moved_swap);
+                if (!mem_cgroup_is_root(mc.to))
+                        res_counter_uncharge(&mc.to->res,
+                                             PAGE_SIZE * mc.moved_swap);
                 /* we've already done css_get(mc.to) */
                 mc.moved_swap = 0;
         }
@@ -6345,7 +6394,8 @@ void mem_cgroup_uncharge_swap(swp_entry_t entry)
         rcu_read_lock();
         memcg = mem_cgroup_lookup(id);
         if (memcg) {
-                res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
+                if (!mem_cgroup_is_root(memcg))
+                        res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
                 mem_cgroup_swap_statistics(memcg, false);
                 css_put(&memcg->css);
         }
@@ -6509,12 +6559,15 @@ static void uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout,
 {
         unsigned long flags;
 
-        if (nr_mem)
-                res_counter_uncharge(&memcg->res, nr_mem * PAGE_SIZE);
-        if (nr_memsw)
-                res_counter_uncharge(&memcg->memsw, nr_memsw * PAGE_SIZE);
-
-        memcg_oom_recover(memcg);
+        if (!mem_cgroup_is_root(memcg)) {
+                if (nr_mem)
+                        res_counter_uncharge(&memcg->res,
+                                             nr_mem * PAGE_SIZE);
+                if (nr_memsw)
+                        res_counter_uncharge(&memcg->memsw,
+                                             nr_memsw * PAGE_SIZE);
+                memcg_oom_recover(memcg);
+        }
 
         local_irq_save(flags);
         __this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS], nr_anon);
diff --git a/mm/memory.c b/mm/memory.c
index ab3537bcfed2..adeac306610f 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -751,7 +751,7 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
         unsigned long pfn = pte_pfn(pte);
 
         if (HAVE_PTE_SPECIAL) {
-                if (likely(!pte_special(pte) || pte_numa(pte)))
+                if (likely(!pte_special(pte)))
                         goto check_pfn;
                 if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
                         return NULL;
@@ -777,15 +777,14 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
                 }
         }
 
+        if (is_zero_pfn(pfn))
+                return NULL;
 check_pfn:
         if (unlikely(pfn > highest_memmap_pfn)) {
                 print_bad_pte(vma, addr, pte, NULL);
                 return NULL;
         }
 
-        if (is_zero_pfn(pfn))
-                return NULL;
-
         /*
          * NOTE! We still have PageReserved() pages in the page tables.
          * eg. VDSO mappings can cause them to exist.
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index 3707c71ae4cd..51108165f829 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -108,7 +108,7 @@ static int pcpu_alloc_pages(struct pcpu_chunk *chunk,
                             int page_start, int page_end)
 {
         const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD;
-        unsigned int cpu;
+        unsigned int cpu, tcpu;
         int i;
 
         for_each_possible_cpu(cpu) {
@@ -116,14 +116,23 @@ static int pcpu_alloc_pages(struct pcpu_chunk *chunk,
                         struct page **pagep = &pages[pcpu_page_idx(cpu, i)];
 
                         *pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0);
-                        if (!*pagep) {
-                                pcpu_free_pages(chunk, pages, populated,
-                                                page_start, page_end);
-                                return -ENOMEM;
-                        }
+                        if (!*pagep)
+                                goto err;
                 }
         }
         return 0;
+
+err:
+        while (--i >= page_start)
+                __free_page(pages[pcpu_page_idx(cpu, i)]);
+
+        for_each_possible_cpu(tcpu) {
+                if (tcpu == cpu)
+                        break;
+                for (i = page_start; i < page_end; i++)
+                        __free_page(pages[pcpu_page_idx(tcpu, i)]);
+        }
+        return -ENOMEM;
 }
 
 /**
@@ -263,6 +272,7 @@ err:
                 __pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start),
                                    page_end - page_start);
         }
+        pcpu_post_unmap_tlb_flush(chunk, page_start, page_end);
         return err;
 }
 
diff --git a/mm/percpu.c b/mm/percpu.c
index 2139e30a4b44..da997f9800bd 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1932,6 +1932,8 @@ void __init setup_per_cpu_areas(void)
 
         if (pcpu_setup_first_chunk(ai, fc) < 0)
                 panic("Failed to initialize percpu areas.");
+
+        pcpu_free_alloc_info(ai);
 }
 
 #endif  /* CONFIG_SMP */
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index a8b919925934..dfb79e028ecb 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -195,7 +195,7 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
         pmd_t entry = *pmdp;
         if (pmd_numa(entry))
                 entry = pmd_mknonnuma(entry);
-        set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(*pmdp));
+        set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(entry));
         flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
diff --git a/mm/zbud.c b/mm/zbud.c
index a05790b1915e..f26e7fcc7fa2 100644
--- a/mm/zbud.c
+++ b/mm/zbud.c
@@ -195,6 +195,7 @@ static struct zpool_driver zbud_zpool_driver = {
         .total_size =   zbud_zpool_total_size,
 };
 
+MODULE_ALIAS("zpool-zbud");
 #endif /* CONFIG_ZPOOL */
 
 /*****************
diff --git a/mm/zpool.c b/mm/zpool.c
index e40612a1df00..739cdf0d183a 100644
--- a/mm/zpool.c
+++ b/mm/zpool.c
@@ -150,7 +150,7 @@ struct zpool *zpool_create_pool(char *type, gfp_t gfp, struct zpool_ops *ops)
         driver = zpool_get_driver(type);
 
         if (!driver) {
-                request_module(type);
+                request_module("zpool-%s", type);
                 driver = zpool_get_driver(type);
         }
 
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 4e2fc83cb394..94f38fac5e81 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -315,6 +315,7 @@ static struct zpool_driver zs_zpool_driver = {
         .total_size =   zs_zpool_total_size,
 };
 
+MODULE_ALIAS("zpool-zsmalloc");
 #endif /* CONFIG_ZPOOL */
 
 /* per-cpu VM mapping areas for zspage accesses that cross page boundaries */