net: extend net_device allocation to vmalloc()

Joby Poriyath provided a xen-netback patch to reduce the size of
xenvif structure as some netdev allocation could fail under
memory pressure/fragmentation.

This patch is handling the problem at the core level, allowing
any netdev structures to use vmalloc() if kmalloc() failed.

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>
Reported-by: Joby Poriyath <joby.poriyath@citrix.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 24 insertions, 11 deletions

diff --git a/Documentation/networking/netdevices.txt b/Documentation/networking/netdevices.txt
index c7ecc7080494..0b1cf6b2a592 100644
--- a/Documentation/networking/netdevices.txt
+++ b/Documentation/networking/netdevices.txt
@@ -10,12 +10,12 @@ network devices.
 struct net_device allocation rules
 ==================================
 Network device structures need to persist even after module is unloaded and
-must be allocated with kmalloc.  If device has registered successfully,
-it will be freed on last use by free_netdev.  This is required to handle the
-pathologic case cleanly (example: rmmod mydriver </sys/class/net/myeth/mtu )
+must be allocated with alloc_netdev_mqs() and friends.
+If device has registered successfully, it will be freed on last use
+by free_netdev(). This is required to handle the pathologic case cleanly
+(example: rmmod mydriver </sys/class/net/myeth/mtu )
 
-There are routines in net_init.c to handle the common cases of
-alloc_etherdev, alloc_netdev.  These reserve extra space for driver
+alloc_netdev_mqs()/alloc_netdev() reserve extra space for driver
 private data which gets freed when the network device is freed. If
 separately allocated data is attached to the network device
 (netdev_priv(dev)) then it is up to the module exit handler to free that.
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index cb1d918ecdf1..e6353cafbf05 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1800,6 +1800,7 @@ static inline void unregister_netdevice(struct net_device *dev)
 
 int netdev_refcnt_read(const struct net_device *dev);
 void free_netdev(struct net_device *dev);
+void netdev_freemem(struct net_device *dev);
 void synchronize_net(void);
 int init_dummy_netdev(struct net_device *dev);
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 0054c8c75f50..0e6136546a8c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6196,6 +6196,16 @@ void netdev_set_default_ethtool_ops(struct net_device *dev,
 }
 EXPORT_SYMBOL_GPL(netdev_set_default_ethtool_ops);
 
+void netdev_freemem(struct net_device *dev)
+{
+        char *addr = (char *)dev - dev->padded;
+
+        if (is_vmalloc_addr(addr))
+                vfree(addr);
+        else
+                kfree(addr);
+}
+
 /**
  *      alloc_netdev_mqs - allocate network device
  *      @sizeof_priv:   size of private data to allocate space for
@@ -6239,7 +6249,9 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
         /* ensure 32-byte alignment of whole construct */
         alloc_size += NETDEV_ALIGN - 1;
 
-        p = kzalloc(alloc_size, GFP_KERNEL);
+        p = kzalloc(alloc_size, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+        if (!p)
+                p = vzalloc(alloc_size);
         if (!p)
                 return NULL;
 
@@ -6248,7 +6260,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 
         dev->pcpu_refcnt = alloc_percpu(int);
         if (!dev->pcpu_refcnt)
-                goto free_p;
+                goto free_dev;
 
         if (dev_addr_init(dev))
                 goto free_pcpu;
@@ -6301,8 +6313,8 @@ free_pcpu:
         kfree(dev->_rx);
 #endif
 
-free_p:
-        kfree(p);
+free_dev:
+        netdev_freemem(dev);
         return NULL;
 }
 EXPORT_SYMBOL(alloc_netdev_mqs);
@@ -6339,7 +6351,7 @@ void free_netdev(struct net_device *dev)
 
         /*  Compatibility with error handling in drivers */
         if (dev->reg_state == NETREG_UNINITIALIZED) {
-                kfree((char *)dev - dev->padded);
+                netdev_freemem(dev);
                 return;
         }
 
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index d954b56b4e47..d03f2c9750fa 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1263,7 +1263,7 @@ static void netdev_release(struct device *d)
         BUG_ON(dev->reg_state != NETREG_RELEASED);
 
         kfree(dev->ifalias);
-        kfree((char *)dev - dev->padded);
+        netdev_freemem(dev);
 }
 
 static const void *net_namespace(struct device *d)