From 1059590254fa9dce9cafc4f07d1103dbec415e76 Mon Sep 17 00:00:00 2001
From: Pankaj Gupta <pagupta@redhat.com>
Date: Mon, 12 Jan 2015 11:41:28 +0530
Subject: [PATCH 1/2] net: allow large number of rx queues
netif_alloc_rx_queues() uses kcalloc() to allocate memory
for "struct netdev_queue *_rx" array.
If we are doing large rx queue allocation kcalloc() might
fail, so this patch does a fallback to vzalloc().
Similar implementation is done for tx queue allocation in
netif_alloc_netdev_queues().
We avoid failure of high order memory allocation
with the help of vzalloc(), this allows us to do large
rx and tx queue allocation which in turn helps us to
increase the number of queues in tun.
As vmalloc() adds overhead on a critical network path,
__GFP_REPEAT flag is used with kzalloc() to do this fallback
only when really needed.
Signed-off-by: Pankaj Gupta <pagupta@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: David Gibson <dgibson@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/core/dev.c | 13 ++++++++-----
1 file changed, 8 insertions(+), 5 deletions(-)
diff --git a/net/core/dev.c b/net/core/dev.c
index 683d493aa1bf..805456147c30 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6172,13 +6172,16 @@ static int netif_alloc_rx_queues(struct net_device *dev)
{
unsigned int i, count = dev->num_rx_queues;
struct netdev_rx_queue *rx;
+ size_t sz = count * sizeof(*rx);
BUG_ON(count < 1);
- rx = kcalloc(count, sizeof(struct netdev_rx_queue), GFP_KERNEL);
- if (!rx)
- return -ENOMEM;
-
+ rx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+ if (!rx) {
+ rx = vzalloc(sz);
+ if (!rx)
+ return -ENOMEM;
+ }
dev->_rx = rx;
for (i = 0; i < count; i++)
@@ -6808,7 +6811,7 @@ void free_netdev(struct net_device *dev)
netif_free_tx_queues(dev);
#ifdef CONFIG_SYSFS
- kfree(dev->_rx);
+ kvfree(dev->_rx);
#endif
kfree(rcu_dereference_protected(dev->ingress_queue, 1));
From baf71c5c1f80d82e92924050a60b5baaf97e3094 Mon Sep 17 00:00:00 2001
From: Pankaj Gupta <pagupta@redhat.com>
Date: Mon, 12 Jan 2015 11:41:29 +0530
Subject: [PATCH 2/2] tuntap: Increase the number of queues in tun.
Networking under kvm works best if we allocate a per-vCPU RX and TX
queue in a virtual NIC. This requires a per-vCPU queue on the host side.
It is now safe to increase the maximum number of queues.
Preceding patch: 'net: allow large number of rx queues'
made sure this won't cause failures due to high order memory
allocations. Increase it to 256: this is the max number of vCPUs
KVM supports.
Size of tun_struct changes from 8512 to 10496 after this patch. This keeps
pages allocated for tun_struct before and after the patch to 3.
Signed-off-by: Pankaj Gupta <pagupta@redhat.com>
Reviewed-by: David Gibson <dgibson@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/tun.c | 7 +++----
1 file changed, 3 insertions(+), 4 deletions(-)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index c0df872f5b8c..74fdf1158448 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -124,10 +124,9 @@ struct tap_filter {
unsigned char addr[FLT_EXACT_COUNT][ETH_ALEN];
};
-/* DEFAULT_MAX_NUM_RSS_QUEUES were chosen to let the rx/tx queues allocated for
- * the netdevice to be fit in one page. So we can make sure the success of
- * memory allocation. TODO: increase the limit. */
-#define MAX_TAP_QUEUES DEFAULT_MAX_NUM_RSS_QUEUES
+/* MAX_TAP_QUEUES 256 is chosen to allow rx/tx queues to be equal
+ * to max number of VCPUs in guest. */
+#define MAX_TAP_QUEUES 256
#define MAX_TAP_FLOWS 4096
#define TUN_FLOW_EXPIRE (3 * HZ)