summaryrefslogtreecommitdiffstats
path: root/net/netlink
diff options
context:
space:
mode:
authorArad, Ronen <ronen.arad@intel.com>2015-10-15 01:55:17 -0700
committerDavid S. Miller <davem@davemloft.net>2015-10-18 19:34:12 -0700
commitdb65a3aaf29ecce2e34271d52e8d2336b97bd9fe (patch)
tree582af5d934c64a5e74dd5813f118607818255526 /net/netlink
parentc7c49b8fde26b74277188bdc6c9dca38db6fa35b (diff)
downloadlinux-db65a3aaf29ecce2e34271d52e8d2336b97bd9fe.tar.bz2
netlink: Trim skb to alloc size to avoid MSG_TRUNC
netlink_dump() allocates skb based on the calculated min_dump_alloc or a per socket max_recvmsg_len. min_alloc_size is maximum space required for any single netdev attributes as calculated by rtnl_calcit(). max_recvmsg_len tracks the user provided buffer to netlink_recvmsg. It is capped at 16KiB. The intention is to avoid small allocations and to minimize the number of calls required to obtain dump information for all net devices. netlink_dump packs as many small messages as could fit within an skb that was sized for the largest single netdev information. The actual space available within an skb is larger than what is requested. It could be much larger and up to near 2x with align to next power of 2 approach. Allowing netlink_dump to use all the space available within the allocated skb increases the buffer size a user has to provide to avoid truncaion (i.e. MSG_TRUNG flag set). It was observed that with many VLANs configured on at least one netdev, a larger buffer of near 64KiB was necessary to avoid "Message truncated" error in "ip link" or "bridge [-c[ompressvlans]] vlan show" when min_alloc_size was only little over 32KiB. This patch trims skb to allocated size in order to allow the user to avoid truncation with more reasonable buffer size. Signed-off-by: Ronen Arad <ronen.arad@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/netlink')
-rw-r--r--net/netlink/af_netlink.c34
1 files changed, 22 insertions, 12 deletions
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 8f060d7f9a0e..0a49a8c7c564 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2785,6 +2785,7 @@ static int netlink_dump(struct sock *sk)
struct sk_buff *skb = NULL;
struct nlmsghdr *nlh;
int len, err = -ENOBUFS;
+ int alloc_min_size;
int alloc_size;
mutex_lock(nlk->cb_mutex);
@@ -2793,9 +2794,6 @@ static int netlink_dump(struct sock *sk)
goto errout_skb;
}
- cb = &nlk->cb;
- alloc_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE);
-
if (!netlink_rx_is_mmaped(sk) &&
atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
goto errout_skb;
@@ -2805,23 +2803,35 @@ static int netlink_dump(struct sock *sk)
* to reduce number of system calls on dump operations, if user
* ever provided a big enough buffer.
*/
- if (alloc_size < nlk->max_recvmsg_len) {
- skb = netlink_alloc_skb(sk,
- nlk->max_recvmsg_len,
- nlk->portid,
+ cb = &nlk->cb;
+ alloc_min_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE);
+
+ if (alloc_min_size < nlk->max_recvmsg_len) {
+ alloc_size = nlk->max_recvmsg_len;
+ skb = netlink_alloc_skb(sk, alloc_size, nlk->portid,
GFP_KERNEL |
__GFP_NOWARN |
__GFP_NORETRY);
- /* available room should be exact amount to avoid MSG_TRUNC */
- if (skb)
- skb_reserve(skb, skb_tailroom(skb) -
- nlk->max_recvmsg_len);
}
- if (!skb)
+ if (!skb) {
+ alloc_size = alloc_min_size;
skb = netlink_alloc_skb(sk, alloc_size, nlk->portid,
GFP_KERNEL);
+ }
if (!skb)
goto errout_skb;
+
+ /* Trim skb to allocated size. User is expected to provide buffer as
+ * large as max(min_dump_alloc, 16KiB (mac_recvmsg_len capped at
+ * netlink_recvmsg())). dump will pack as many smaller messages as
+ * could fit within the allocated skb. skb is typically allocated
+ * with larger space than required (could be as much as near 2x the
+ * requested size with align to next power of 2 approach). Allowing
+ * dump to use the excess space makes it difficult for a user to have a
+ * reasonable static buffer based on the expected largest dump of a
+ * single netdev. The outcome is MSG_TRUNC error.
+ */
+ skb_reserve(skb, skb_tailroom(skb) - alloc_size);
netlink_skb_set_owner_r(skb, sk);
len = cb->dump(skb, cb);