net: allow large number of tx queues

netif_alloc_netdev_queues() uses kcalloc() to allocate memory
for the "struct netdev_queue *_tx" array.

For large number of tx queues, kcalloc() might fail, so this
patch does a fallback to vzalloc().

As vmalloc() adds overhead on a critical network path, add __GFP_REPEAT
to kzalloc() flags to do this fallback only when really needed.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 19 insertions, 7 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index fa007dba6beb..722f633926e0 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -130,6 +130,7 @@
 #include <linux/cpu_rmap.h>
 #include <linux/static_key.h>
 #include <linux/hashtable.h>
+#include <linux/vmalloc.h>
 
 #include "net-sysfs.h"
 
@@ -5253,17 +5254,28 @@ static void netdev_init_one_queue(struct net_device *dev,
 #endif
 }
 
+static void netif_free_tx_queues(struct net_device *dev)
+{
+        if (is_vmalloc_addr(dev->_tx))
+                vfree(dev->_tx);
+        else
+                kfree(dev->_tx);
+}
+
 static int netif_alloc_netdev_queues(struct net_device *dev)
 {
         unsigned int count = dev->num_tx_queues;
         struct netdev_queue *tx;
+        size_t sz = count * sizeof(*tx);
 
-        BUG_ON(count < 1);
-
-        tx = kcalloc(count, sizeof(struct netdev_queue), GFP_KERNEL);
-        if (!tx)
-                return -ENOMEM;
+        BUG_ON(count < 1 || count > 0xffff);
 
+        tx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+        if (!tx) {
+                tx = vzalloc(sz);
+                if (!tx)
+                        return -ENOMEM;
+        }
         dev->_tx = tx;
 
         netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL);
@@ -5811,7 +5823,7 @@ free_all:
 
 free_pcpu:
         free_percpu(dev->pcpu_refcnt);
-        kfree(dev->_tx);
+        netif_free_tx_queues(dev);
 #ifdef CONFIG_RPS
         kfree(dev->_rx);
 #endif
@@ -5836,7 +5848,7 @@ void free_netdev(struct net_device *dev)
 
         release_net(dev_net(dev));
 
-        kfree(dev->_tx);
+        netif_free_tx_queues(dev);
 #ifdef CONFIG_RPS
         kfree(dev->_rx);
 #endif