Merge branch 'akpm' (Andrew's patch-bomb)

Merge Andrew's second set of patches:
 - MM
 - a few random fixes
 - a couple of RTC leftovers

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (120 commits)
  rtc/rtc-88pm80x: remove unneed devm_kfree
  rtc/rtc-88pm80x: assign ret only when rtc_register_driver fails
  mm: hugetlbfs: close race during teardown of hugetlbfs shared page tables
  tmpfs: distribute interleave better across nodes
  mm: remove redundant initialization
  mm: warn if pg_data_t isn't initialized with zero
  mips: zero out pg_data_t when it's allocated
  memcg: gix memory accounting scalability in shrink_page_list
  mm/sparse: remove index_init_lock
  mm/sparse: more checks on mem_section number
  mm/sparse: optimize sparse_index_alloc
  memcg: add mem_cgroup_from_css() helper
  memcg: further prevent OOM with too many dirty pages
  memcg: prevent OOM with too many dirty pages
  mm: mmu_notifier: fix freed page still mapped in secondary MMU
  mm: memcg: only check anon swapin page charges for swap cache
  mm: memcg: only check swap cache pages for repeated charging
  mm: memcg: split swapin charge function into private and public part
  mm: memcg: remove needless !mm fixup to init_mm when charging
  mm: memcg: remove unneeded shmem charge type
  ...

1 files changed, 47 insertions, 6 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index c8569f826b71..0cb3fe8d8e72 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3156,6 +3156,23 @@ void netdev_rx_handler_unregister(struct net_device *dev)
 }
 EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);
 
+/*
+ * Limit the use of PFMEMALLOC reserves to those protocols that implement
+ * the special handling of PFMEMALLOC skbs.
+ */
+static bool skb_pfmemalloc_protocol(struct sk_buff *skb)
+{
+        switch (skb->protocol) {
+        case __constant_htons(ETH_P_ARP):
+        case __constant_htons(ETH_P_IP):
+        case __constant_htons(ETH_P_IPV6):
+        case __constant_htons(ETH_P_8021Q):
+                return true;
+        default:
+                return false;
+        }
+}
+
 static int __netif_receive_skb(struct sk_buff *skb)
 {
         struct packet_type *ptype, *pt_prev;
@@ -3165,14 +3182,27 @@ static int __netif_receive_skb(struct sk_buff *skb)
         bool deliver_exact = false;
         int ret = NET_RX_DROP;
         __be16 type;
+        unsigned long pflags = current->flags;
 
         net_timestamp_check(!netdev_tstamp_prequeue, skb);
 
         trace_netif_receive_skb(skb);
 
+        /*
+         * PFMEMALLOC skbs are special, they should
+         * - be delivered to SOCK_MEMALLOC sockets only
+         * - stay away from userspace
+         * - have bounded memory usage
+         *
+         * Use PF_MEMALLOC as this saves us from propagating the allocation
+         * context down to all allocation sites.
+         */
+        if (sk_memalloc_socks() && skb_pfmemalloc(skb))
+                current->flags |= PF_MEMALLOC;
+
         /* if we've gotten here through NAPI, check netpoll */
         if (netpoll_receive_skb(skb))
-                return NET_RX_DROP;
+                goto out;
 
         orig_dev = skb->dev;
 
@@ -3192,7 +3222,7 @@ another_round:
         if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) {
                 skb = vlan_untag(skb);
                 if (unlikely(!skb))
-                        goto out;
+                        goto unlock;
         }
 
 #ifdef CONFIG_NET_CLS_ACT
@@ -3202,6 +3232,9 @@ another_round:
         }
 #endif
 
+        if (sk_memalloc_socks() && skb_pfmemalloc(skb))
+                goto skip_taps;
+
         list_for_each_entry_rcu(ptype, &ptype_all, list) {
                 if (!ptype->dev || ptype->dev == skb->dev) {
                         if (pt_prev)
@@ -3210,13 +3243,18 @@ another_round:
                 }
         }
 
+skip_taps:
 #ifdef CONFIG_NET_CLS_ACT
         skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
         if (!skb)
-                goto out;
+                goto unlock;
 ncls:
 #endif
 
+        if (sk_memalloc_socks() && skb_pfmemalloc(skb)
+                                && !skb_pfmemalloc_protocol(skb))
+                goto drop;
+
         rx_handler = rcu_dereference(skb->dev->rx_handler);
         if (vlan_tx_tag_present(skb)) {
                 if (pt_prev) {
@@ -3226,7 +3264,7 @@ ncls:
                 if (vlan_do_receive(&skb, !rx_handler))
                         goto another_round;
                 else if (unlikely(!skb))
-                        goto out;
+                        goto unlock;
         }
 
         if (rx_handler) {
@@ -3236,7 +3274,7 @@ ncls:
                 }
                 switch (rx_handler(&skb)) {
                 case RX_HANDLER_CONSUMED:
-                        goto out;
+                        goto unlock;
                 case RX_HANDLER_ANOTHER:
                         goto another_round;
                 case RX_HANDLER_EXACT:
@@ -3269,6 +3307,7 @@ ncls:
                 else
                         ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
         } else {
+drop:
                 atomic_long_inc(&skb->dev->rx_dropped);
                 kfree_skb(skb);
                 /* Jamal, now you will not able to escape explaining
@@ -3277,8 +3316,10 @@ ncls:
                 ret = NET_RX_DROP;
         }
 
-out:
+unlock:
         rcu_read_unlock();
+out:
+        tsk_restore_flags(current, pflags, PF_MEMALLOC);
         return ret;
 }