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

Pull networking fixes from David Miller:

 1) mlx4 doesn't check fully for supported valid RSS hash function, fix
    from Amir Vadai

 2) Off by one in ibmveth_change_mtu(), from David Gibson

 3) Prevent altera chip from reporting false error interrupts in some
    circumstances, from Chee Nouk Phoon

 4) Get rid of that stupid endless loop trying to allocate a FIN packet
    in TCP, and in the process kill deadlocks.  From Eric Dumazet

 5) Fix get_rps_cpus() crash due to wrong invalid-cpu value, also from
    Eric Dumazet

 6) Fix two bugs in async rhashtable resizing, from Thomas Graf

 7) Fix topology server listener socket namespace bug in TIPC, from Ying
    Xue

 8) Add some missing HAS_DMA kconfig dependencies, from Geert
    Uytterhoeven

 9) bgmac driver intends to force re-polling but does so by returning
    the wrong value from it's ->poll() handler.  Fix from Rafał Miłecki

10) When the creater of an rhashtable configures a max size for it,
    don't bark in the logs and drop insertions when that is exceeded.
    Fix from Johannes Berg

11) Recover from out of order packets in ppp mppe properly, from Sylvain
    Rochet

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (41 commits)
  bnx2x: really disable TPA if 'disable_tpa' option is set
  net:treewide: Fix typo in drivers/net
  net/mlx4_en: Prevent setting invalid RSS hash function
  mdio-mux-gpio: use new gpiod_get_array and gpiod_put_array functions
  netfilter; Add some missing default cases to switch statements in nft_reject.
  ppp: mppe: discard late packet in stateless mode
  ppp: mppe: sanity error path rework
  net/bonding: Make DRV macros private
  net: rfs: fix crash in get_rps_cpus()
  altera tse: add support for fixed-links.
  pxa168: fix double deallocation of managed resources
  net: fix crash in build_skb()
  net: eth: altera: Resolve false errors from MSGDMA to TSE
  ehea: Fix memory hook reference counting crashes
  net/tg3: Release IRQs on permanent error
  net: mdio-gpio: support access that may sleep
  inet: fix possible panic in reqsk_queue_unlink()
  rhashtable: don't attempt to grow when at max_size
  bgmac: fix requests for extra polling calls from NAPI
  tcp: avoid looping in tcp_send_fin()
  ...

2 files changed, 30 insertions, 12 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 1796cef55ab5..c7ba0388f1be 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3079,7 +3079,7 @@ static struct rps_dev_flow *
 set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 	    struct rps_dev_flow *rflow, u16 next_cpu)
 {
-	if (next_cpu != RPS_NO_CPU) {
+	if (next_cpu < nr_cpu_ids) {
 #ifdef CONFIG_RFS_ACCEL
 		struct netdev_rx_queue *rxqueue;
 		struct rps_dev_flow_table *flow_table;
@@ -3184,7 +3184,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		 * If the desired CPU (where last recvmsg was done) is
 		 * different from current CPU (one in the rx-queue flow
 		 * table entry), switch if one of the following holds:
-		 *   - Current CPU is unset (equal to RPS_NO_CPU).
+		 *   - Current CPU is unset (>= nr_cpu_ids).
 		 *   - Current CPU is offline.
 		 *   - The current CPU's queue tail has advanced beyond the
 		 *     last packet that was enqueued using this table entry.
@@ -3192,14 +3192,14 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		 *     have been dequeued, thus preserving in order delivery.
 		 */
 		if (unlikely(tcpu != next_cpu) &&
-		    (tcpu == RPS_NO_CPU || !cpu_online(tcpu) ||
+		    (tcpu >= nr_cpu_ids || !cpu_online(tcpu) ||
 		     ((int)(per_cpu(softnet_data, tcpu).input_queue_head -
 		      rflow->last_qtail)) >= 0)) {
 			tcpu = next_cpu;
 			rflow = set_rps_cpu(dev, skb, rflow, next_cpu);
 		}
 
-		if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) {
+		if (tcpu < nr_cpu_ids && cpu_online(tcpu)) {
 			*rflowp = rflow;
 			cpu = tcpu;
 			goto done;
@@ -3240,14 +3240,14 @@ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index,
 	struct rps_dev_flow_table *flow_table;
 	struct rps_dev_flow *rflow;
 	bool expire = true;
-	int cpu;
+	unsigned int cpu;
 
 	rcu_read_lock();
 	flow_table = rcu_dereference(rxqueue->rps_flow_table);
 	if (flow_table && flow_id <= flow_table->mask) {
 		rflow = &flow_table->flows[flow_id];
 		cpu = ACCESS_ONCE(rflow->cpu);
-		if (rflow->filter == filter_id && cpu != RPS_NO_CPU &&
+		if (rflow->filter == filter_id && cpu < nr_cpu_ids &&
 		    ((int)(per_cpu(softnet_data, cpu).input_queue_head -
 			   rflow->last_qtail) <
 		     (int)(10 * flow_table->mask)))
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index d1967dab9cc6..3cfff2a3d651 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -280,13 +280,14 @@ nodata:
 EXPORT_SYMBOL(__alloc_skb);
 
 /**
- * build_skb - build a network buffer
+ * __build_skb - build a network buffer
  * @data: data buffer provided by caller
- * @frag_size: size of fragment, or 0 if head was kmalloced
+ * @frag_size: size of data, or 0 if head was kmalloced
  *
  * Allocate a new &sk_buff. Caller provides space holding head and
  * skb_shared_info. @data must have been allocated by kmalloc() only if
- * @frag_size is 0, otherwise data should come from the page allocator.
+ * @frag_size is 0, otherwise data should come from the page allocator
+ *  or vmalloc()
  * The return is the new skb buffer.
  * On a failure the return is %NULL, and @data is not freed.
  * Notes :
@@ -297,7 +298,7 @@ EXPORT_SYMBOL(__alloc_skb);
  *  before giving packet to stack.
  *  RX rings only contains data buffers, not full skbs.
  */
-struct sk_buff *build_skb(void *data, unsigned int frag_size)
+struct sk_buff *__build_skb(void *data, unsigned int frag_size)
 {
 	struct skb_shared_info *shinfo;
 	struct sk_buff *skb;
@@ -311,7 +312,6 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 
 	memset(skb, 0, offsetof(struct sk_buff, tail));
 	skb->truesize = SKB_TRUESIZE(size);
-	skb->head_frag = frag_size != 0;
 	atomic_set(&skb->users, 1);
 	skb->head = data;
 	skb->data = data;
@@ -328,6 +328,23 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
 
 	return skb;
 }
+
+/* build_skb() is wrapper over __build_skb(), that specifically
+ * takes care of skb->head and skb->pfmemalloc
+ * This means that if @frag_size is not zero, then @data must be backed
+ * by a page fragment, not kmalloc() or vmalloc()
+ */
+struct sk_buff *build_skb(void *data, unsigned int frag_size)
+{
+	struct sk_buff *skb = __build_skb(data, frag_size);
+
+	if (skb && frag_size) {
+		skb->head_frag = 1;
+		if (virt_to_head_page(data)->pfmemalloc)
+			skb->pfmemalloc = 1;
+	}
+	return skb;
+}
 EXPORT_SYMBOL(build_skb);
 
 struct netdev_alloc_cache {
@@ -348,7 +365,8 @@ static struct page *__page_frag_refill(struct netdev_alloc_cache *nc,
 	gfp_t gfp = gfp_mask;
 
 	if (order) {
-		gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY;
+		gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY |
+			    __GFP_NOMEMALLOC;
 		page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, order);
 		nc->frag.size = PAGE_SIZE << (page ? order : 0);
 	}