Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core

Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:

 * Fix include order for bison/flex-generated C files, from Ben Hutchings

 * Build fixes and documentation corrections from David Ahern

 * Group parsing support, from Jiri Olsa

 * UI/gtk refactorings and improvements from Namhyung Kim

 * NULL deref fix for perf script, from Namhyung Kim

 * Assorted cleanups from Robert Richter

 * Let O= makes handle relative paths, from Steven Rostedt

 * perf script python fixes, from Feng Tang.

 * Improve 'perf lock' error message when the needed tracepoints
   are not present, from David Ahern.

 * Initial bash completion support, from Frederic Weisbecker

 * Allow building without libelf, from Namhyung Kim.

 * Support DWARF CFI based unwind to have callchains when %bp
   based unwinding is not possible, from Jiri Olsa.

 * Symbol resolution fixes, while fixing support PPC64 files with an .opt ELF
   section was the end goal, several fixes for code that handles all
   architectures and cleanups are included, from Cody Schafer.

 * Add a description for the JIT interface, from Andi Kleen.

 * Assorted fixes for Documentation and build in 32 bit, from Robert Richter

 * Add support for non-tracepoint events in perf script python, from Feng Tang

 * Cache the libtraceevent event_format associated to each evsel early, so that we
   avoid relookups, i.e. calling pevent_find_event repeatedly when processing
   tracepoint events.

   [ This is to reduce the surface contact with libtraceevents and make clear what
     is that the perf tools needs from that lib: so far parsing the common and per
     event fields. ]

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 89 insertions, 11 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 1cb0d8a6aa6..0cb3fe8d8e7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1172,6 +1172,7 @@ static int __dev_open(struct net_device *dev)
 		net_dmaengine_get();
 		dev_set_rx_mode(dev);
 		dev_activate(dev);
+		add_device_randomness(dev->dev_addr, dev->addr_len);
 	}
 
 	return ret;
@@ -1632,6 +1633,8 @@ static inline int deliver_skb(struct sk_buff *skb,
 			      struct packet_type *pt_prev,
 			      struct net_device *orig_dev)
 {
+	if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC)))
+		return -ENOMEM;
 	atomic_inc(&skb->users);
 	return pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
 }
@@ -1691,7 +1694,8 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
 	rcu_read_unlock();
 }
 
-/* netif_setup_tc - Handle tc mappings on real_num_tx_queues change
+/**
+ * netif_setup_tc - Handle tc mappings on real_num_tx_queues change
  * @dev: Network device
  * @txq: number of queues available
  *
@@ -1793,6 +1797,18 @@ int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq)
 EXPORT_SYMBOL(netif_set_real_num_rx_queues);
 #endif
 
+/**
+ * netif_get_num_default_rss_queues - default number of RSS queues
+ *
+ * This routine should set an upper limit on the number of RSS queues
+ * used by default by multiqueue devices.
+ */
+int netif_get_num_default_rss_queues(void)
+{
+	return min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus());
+}
+EXPORT_SYMBOL(netif_get_num_default_rss_queues);
+
 static inline void __netif_reschedule(struct Qdisc *q)
 {
 	struct softnet_data *sd;
@@ -2459,6 +2475,23 @@ static DEFINE_PER_CPU(int, xmit_recursion);
 #define RECURSION_LIMIT 10
 
 /**
+ *	dev_loopback_xmit - loop back @skb
+ *	@skb: buffer to transmit
+ */
+int dev_loopback_xmit(struct sk_buff *skb)
+{
+	skb_reset_mac_header(skb);
+	__skb_pull(skb, skb_network_offset(skb));
+	skb->pkt_type = PACKET_LOOPBACK;
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
+	WARN_ON(!skb_dst(skb));
+	skb_dst_force(skb);
+	netif_rx_ni(skb);
+	return 0;
+}
+EXPORT_SYMBOL(dev_loopback_xmit);
+
+/**
  *	dev_queue_xmit - transmit a buffer
  *	@skb: buffer to transmit
  *
@@ -3123,6 +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;
@@ -3132,17 +3182,28 @@ 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;
 
-	if (!skb->skb_iif)
-		skb->skb_iif = skb->dev->ifindex;
 	orig_dev = skb->dev;
 
 	skb_reset_network_header(skb);
@@ -3154,13 +3215,14 @@ static int __netif_receive_skb(struct sk_buff *skb)
 	rcu_read_lock();
 
 another_round:
+	skb->skb_iif = skb->dev->ifindex;
 
 	__this_cpu_inc(softnet_data.processed);
 
 	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
@@ -3170,6 +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)
@@ -3178,13 +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) {
@@ -3194,7 +3264,7 @@ ncls:
 		if (vlan_do_receive(&skb, !rx_handler))
 			goto another_round;
 		else if (unlikely(!skb))
-			goto out;
+			goto unlock;
 	}
 
 	if (rx_handler) {
@@ -3204,7 +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:
@@ -3232,8 +3302,12 @@ ncls:
 	}
 
 	if (pt_prev) {
-		ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
+		if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC)))
+			ret = -ENOMEM;
+		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
@@ -3242,8 +3316,10 @@ ncls:
 		ret = NET_RX_DROP;
 	}
 
-out:
+unlock:
 	rcu_read_unlock();
+out:
+	tsk_restore_flags(current, pflags, PF_MEMALLOC);
 	return ret;
 }
 
@@ -4767,6 +4843,7 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa)
 	err = ops->ndo_set_mac_address(dev, sa);
 	if (!err)
 		call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+	add_device_randomness(dev->dev_addr, dev->addr_len);
 	return err;
 }
 EXPORT_SYMBOL(dev_set_mac_address);
@@ -5545,6 +5622,7 @@ int register_netdevice(struct net_device *dev)
 	dev_init_scheduler(dev);
 	dev_hold(dev);
 	list_netdevice(dev);
+	add_device_randomness(dev->dev_addr, dev->addr_len);
 
 	/* Notify protocols, that a new device appeared. */
 	ret = call_netdevice_notifiers(NETDEV_REGISTER, dev);
@@ -5646,7 +5724,7 @@ int netdev_refcnt_read(const struct net_device *dev)
 }
 EXPORT_SYMBOL(netdev_refcnt_read);
 
-/*
+/**
  * netdev_wait_allrefs - wait until all references are gone.
  *
  * This is called when unregistering network devices.