net: Use queue aware tests throughout.

This effectively "flips the switch" by making the core networking
and multiqueue-aware drivers use the new TX multiqueue structures.

Non-multiqueue drivers need no changes.  The interfaces they use such
as netif_stop_queue() degenerate into an operation on TX queue zero.
So everything "just works" for them.

Code that really wants to do "X" to all TX queues now invokes a
routine that does so, such as netif_tx_wake_all_queues(),
netif_tx_stop_all_queues(), etc.

pktgen and netpoll required a little bit more surgery than the others.

In particular the pktgen changes, whilst functional, could be largely
improved.  The initial check in pktgen_xmit() will sometimes check the
wrong queue, which is mostly harmless.  The thing to do is probably to
invoke fill_packet() earlier.

The bulk of the netpoll changes is to make the code operate solely on
the TX queue indicated by by the SKB queue mapping.

Setting of the SKB queue mapping is entirely confined inside of
net/core/dev.c:dev_pick_tx().  If we end up needing any kind of
special semantics (drops, for example) it will be implemented here.

Finally, we now have a "real_num_tx_queues" which is where the driver
indicates how many TX queues are actually active.

With IGB changes from Jeff Kirsher.

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 44 insertions, 25 deletions

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index fdf537707e51..906802db4ed4 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2123,6 +2123,24 @@ static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow)
         }
 }
 #endif
+static void set_cur_queue_map(struct pktgen_dev *pkt_dev)
+{
+        if (pkt_dev->queue_map_min < pkt_dev->queue_map_max) {
+                __u16 t;
+                if (pkt_dev->flags & F_QUEUE_MAP_RND) {
+                        t = random32() %
+                                (pkt_dev->queue_map_max -
+                                 pkt_dev->queue_map_min + 1)
+                                + pkt_dev->queue_map_min;
+                } else {
+                        t = pkt_dev->cur_queue_map + 1;
+                        if (t > pkt_dev->queue_map_max)
+                                t = pkt_dev->queue_map_min;
+                }
+                pkt_dev->cur_queue_map = t;
+        }
+}
+
 /* Increment/randomize headers according to flags and current values
  * for IP src/dest, UDP src/dst port, MAC-Addr src/dst
  */
@@ -2325,19 +2343,7 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev)
                 pkt_dev->cur_pkt_size = t;
         }
 
-        if (pkt_dev->queue_map_min < pkt_dev->queue_map_max) {
-                __u16 t;
-                if (pkt_dev->flags & F_QUEUE_MAP_RND) {
-                        t = random32() %
-                                (pkt_dev->queue_map_max - pkt_dev->queue_map_min + 1)
-                                + pkt_dev->queue_map_min;
-                } else {
-                        t = pkt_dev->cur_queue_map + 1;
-                        if (t > pkt_dev->queue_map_max)
-                                t = pkt_dev->queue_map_min;
-                }
-                pkt_dev->cur_queue_map = t;
-        }
+        set_cur_queue_map(pkt_dev);
 
         pkt_dev->flows[flow].count++;
 }
@@ -2458,7 +2464,7 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
         __be16 *vlan_encapsulated_proto = NULL;  /* packet type ID field (or len) for VLAN tag */
         __be16 *svlan_tci = NULL;                /* Encapsulates priority and SVLAN ID */
         __be16 *svlan_encapsulated_proto = NULL; /* packet type ID field (or len) for SVLAN tag */
-
+        u16 queue_map;
 
         if (pkt_dev->nr_labels)
                 protocol = htons(ETH_P_MPLS_UC);
@@ -2469,6 +2475,7 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
         /* Update any of the values, used when we're incrementing various
          * fields.
          */
+        queue_map = pkt_dev->cur_queue_map;
         mod_cur_headers(pkt_dev);
 
         datalen = (odev->hard_header_len + 16) & ~0xf;
@@ -2507,7 +2514,7 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
         skb->network_header = skb->tail;
         skb->transport_header = skb->network_header + sizeof(struct iphdr);
         skb_put(skb, sizeof(struct iphdr) + sizeof(struct udphdr));
-        skb_set_queue_mapping(skb, pkt_dev->cur_queue_map);
+        skb_set_queue_mapping(skb, queue_map);
         iph = ip_hdr(skb);
         udph = udp_hdr(skb);
 
@@ -2797,6 +2804,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
         __be16 *vlan_encapsulated_proto = NULL;  /* packet type ID field (or len) for VLAN tag */
         __be16 *svlan_tci = NULL;                /* Encapsulates priority and SVLAN ID */
         __be16 *svlan_encapsulated_proto = NULL; /* packet type ID field (or len) for SVLAN tag */
+        u16 queue_map;
 
         if (pkt_dev->nr_labels)
                 protocol = htons(ETH_P_MPLS_UC);
@@ -2807,6 +2815,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
         /* Update any of the values, used when we're incrementing various
          * fields.
          */
+        queue_map = pkt_dev->cur_queue_map;
         mod_cur_headers(pkt_dev);
 
         skb = alloc_skb(pkt_dev->cur_pkt_size + 64 + 16 +
@@ -2844,7 +2853,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
         skb->network_header = skb->tail;
         skb->transport_header = skb->network_header + sizeof(struct ipv6hdr);
         skb_put(skb, sizeof(struct ipv6hdr) + sizeof(struct udphdr));
-        skb_set_queue_mapping(skb, pkt_dev->cur_queue_map);
+        skb_set_queue_mapping(skb, queue_map);
         iph = ipv6_hdr(skb);
         udph = udp_hdr(skb);
 
@@ -3263,7 +3272,9 @@ static void pktgen_rem_thread(struct pktgen_thread *t)
 static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev)
 {
         struct net_device *odev = NULL;
+        struct netdev_queue *txq;
         __u64 idle_start = 0;
+        u16 queue_map;
         int ret;
 
         odev = pkt_dev->odev;
@@ -3285,9 +3296,15 @@ static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev)
                 }
         }
 
-        if ((netif_queue_stopped(odev) ||
-             (pkt_dev->skb &&
-              netif_subqueue_stopped(odev, pkt_dev->skb))) ||
+        if (!pkt_dev->skb) {
+                set_cur_queue_map(pkt_dev);
+                queue_map = pkt_dev->cur_queue_map;
+        } else {
+                queue_map = skb_get_queue_mapping(pkt_dev->skb);
+        }
+
+        txq = netdev_get_tx_queue(odev, queue_map);
+        if (netif_tx_queue_stopped(txq) ||
             need_resched()) {
                 idle_start = getCurUs();
 
@@ -3303,8 +3320,7 @@ static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev)
 
                 pkt_dev->idle_acc += getCurUs() - idle_start;
 
-                if (netif_queue_stopped(odev) ||
-                    netif_subqueue_stopped(odev, pkt_dev->skb)) {
+                if (netif_tx_queue_stopped(txq)) {
                         pkt_dev->next_tx_us = getCurUs();       /* TODO */
                         pkt_dev->next_tx_ns = 0;
                         goto out;       /* Try the next interface */
@@ -3331,9 +3347,12 @@ static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev)
                 }
         }
 
-        netif_tx_lock_bh(odev);
-        if (!netif_queue_stopped(odev) &&
-            !netif_subqueue_stopped(odev, pkt_dev->skb)) {
+        /* fill_packet() might have changed the queue */
+        queue_map = skb_get_queue_mapping(pkt_dev->skb);
+        txq = netdev_get_tx_queue(odev, queue_map);
+
+        __netif_tx_lock_bh(txq);
+        if (!netif_tx_queue_stopped(txq)) {
 
                 atomic_inc(&(pkt_dev->skb->users));
               retry_now:
@@ -3377,7 +3396,7 @@ static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev)
                 pkt_dev->next_tx_ns = 0;
         }
 
-        netif_tx_unlock_bh(odev);
+        __netif_tx_unlock_bh(txq);
 
         /* If pkt_dev->count is zero, then run forever */
         if ((pkt_dev->count != 0) && (pkt_dev->sofar >= pkt_dev->count)) {