diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-09-03 08:08:17 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-09-03 08:08:17 -0700 |
commit | dd5cdb48edfd34401799056a9acf61078d773f90 (patch) | |
tree | 8e251fb4a4c196540fe9b6a6d8b13275f93a057c /net/netlink/af_netlink.c | |
parent | 1e1a4e8f439113b7820bc7150569f685e1cc2b43 (diff) | |
parent | 62da98656b62a5ca57f22263705175af8ded5aa1 (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Another merge window, another set of networking changes. I've heard
rumblings that the lightweight tunnels infrastructure has been voted
networking change of the year. But what do I know?
1) Add conntrack support to openvswitch, from Joe Stringer.
2) Initial support for VRF (Virtual Routing and Forwarding), which
allows the segmentation of routing paths without using multiple
devices. There are some semantic kinks to work out still, but
this is a reasonably strong foundation. From David Ahern.
3) Remove spinlock fro act_bpf fast path, from Alexei Starovoitov.
4) Ignore route nexthops with a link down state in ipv6, just like
ipv4. From Andy Gospodarek.
5) Remove spinlock from fast path of act_gact and act_mirred, from
Eric Dumazet.
6) Document the DSA layer, from Florian Fainelli.
7) Add netconsole support to bcmgenet, systemport, and DSA. Also
from Florian Fainelli.
8) Add Mellanox Switch Driver and core infrastructure, from Jiri
Pirko.
9) Add support for "light weight tunnels", which allow for
encapsulation and decapsulation without bearing the overhead of a
full blown netdevice. From Thomas Graf, Jiri Benc, and a cast of
others.
10) Add Identifier Locator Addressing support for ipv6, from Tom
Herbert.
11) Support fragmented SKBs in iwlwifi, from Johannes Berg.
12) Allow perf PMUs to be accessed from eBPF programs, from Kaixu Xia.
13) Add BQL support to 3c59x driver, from Loganaden Velvindron.
14) Stop using a zero TX queue length to mean that a device shouldn't
have a qdisc attached, use an explicit flag instead. From Phil
Sutter.
15) Use generic geneve netdevice infrastructure in openvswitch, from
Pravin B Shelar.
16) Add infrastructure to avoid re-forwarding a packet in software
that was already forwarded by a hardware switch. From Scott
Feldman.
17) Allow AF_PACKET fanout function to be implemented in a bpf
program, from Willem de Bruijn"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1458 commits)
netfilter: nf_conntrack: make nf_ct_zone_dflt built-in
netfilter: nf_dup{4, 6}: fix build error when nf_conntrack disabled
net: fec: clear receive interrupts before processing a packet
ipv6: fix exthdrs offload registration in out_rt path
xen-netback: add support for multicast control
bgmac: Update fixed_phy_register()
sock, diag: fix panic in sock_diag_put_filterinfo
flow_dissector: Use 'const' where possible.
flow_dissector: Fix function argument ordering dependency
ixgbe: Resolve "initialized field overwritten" warnings
ixgbe: Remove bimodal SR-IOV disabling
ixgbe: Add support for reporting 2.5G link speed
ixgbe: fix bounds checking in ixgbe_setup_tc for 82598
ixgbe: support for ethtool set_rxfh
ixgbe: Avoid needless PHY access on copper phys
ixgbe: cleanup to use cached mask value
ixgbe: Remove second instance of lan_id variable
ixgbe: use kzalloc for allocating one thing
flow: Move __get_hash_from_flowi{4,6} into flow_dissector.c
ixgbe: Remove unused PCI bus types
...
Diffstat (limited to 'net/netlink/af_netlink.c')
-rw-r--r-- | net/netlink/af_netlink.c | 59 |
1 files changed, 42 insertions, 17 deletions
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index a774985489e2..50889be1517d 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -84,6 +84,7 @@ struct listeners { #define NETLINK_F_BROADCAST_SEND_ERROR 0x4 #define NETLINK_F_RECV_NO_ENOBUFS 0x8 #define NETLINK_F_LISTEN_ALL_NSID 0x10 +#define NETLINK_F_CAP_ACK 0x20 static inline int netlink_is_kernel(struct sock *sk) { @@ -593,16 +594,6 @@ netlink_current_frame(const struct netlink_ring *ring, return netlink_lookup_frame(ring, ring->head, status); } -static struct nl_mmap_hdr * -netlink_previous_frame(const struct netlink_ring *ring, - enum nl_mmap_status status) -{ - unsigned int prev; - - prev = ring->head ? ring->head - 1 : ring->frame_max; - return netlink_lookup_frame(ring, prev, status); -} - static void netlink_increment_head(struct netlink_ring *ring) { ring->head = ring->head != ring->frame_max ? ring->head + 1 : 0; @@ -610,11 +601,11 @@ static void netlink_increment_head(struct netlink_ring *ring) static void netlink_forward_ring(struct netlink_ring *ring) { - unsigned int head = ring->head, pos = head; + unsigned int head = ring->head; const struct nl_mmap_hdr *hdr; do { - hdr = __netlink_lookup_frame(ring, pos); + hdr = __netlink_lookup_frame(ring, ring->head); if (hdr->nm_status == NL_MMAP_STATUS_UNUSED) break; if (hdr->nm_status != NL_MMAP_STATUS_SKIP) @@ -623,6 +614,21 @@ static void netlink_forward_ring(struct netlink_ring *ring) } while (ring->head != head); } +static bool netlink_has_valid_frame(struct netlink_ring *ring) +{ + unsigned int head = ring->head, pos = head; + const struct nl_mmap_hdr *hdr; + + do { + hdr = __netlink_lookup_frame(ring, pos); + if (hdr->nm_status == NL_MMAP_STATUS_VALID) + return true; + pos = pos != 0 ? pos - 1 : ring->frame_max; + } while (pos != head); + + return false; +} + static bool netlink_dump_space(struct netlink_sock *nlk) { struct netlink_ring *ring = &nlk->rx_ring; @@ -670,8 +676,7 @@ static unsigned int netlink_poll(struct file *file, struct socket *sock, spin_lock_bh(&sk->sk_receive_queue.lock); if (nlk->rx_ring.pg_vec) { - netlink_forward_ring(&nlk->rx_ring); - if (!netlink_previous_frame(&nlk->rx_ring, NL_MMAP_STATUS_UNUSED)) + if (netlink_has_valid_frame(&nlk->rx_ring)) mask |= POLLIN | POLLRDNORM; } spin_unlock_bh(&sk->sk_receive_queue.lock); @@ -2258,6 +2263,13 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname, nlk->flags &= ~NETLINK_F_LISTEN_ALL_NSID; err = 0; break; + case NETLINK_CAP_ACK: + if (val) + nlk->flags |= NETLINK_F_CAP_ACK; + else + nlk->flags &= ~NETLINK_F_CAP_ACK; + err = 0; + break; default: err = -ENOPROTOOPT; } @@ -2332,6 +2344,16 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname, netlink_table_ungrab(); break; } + case NETLINK_CAP_ACK: + if (len < sizeof(int)) + return -EINVAL; + len = sizeof(int); + val = nlk->flags & NETLINK_F_CAP_ACK ? 1 : 0; + if (put_user(len, optlen) || + put_user(val, optval)) + return -EFAULT; + err = 0; + break; default: err = -ENOPROTOOPT; } @@ -2873,9 +2895,12 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err) struct nlmsghdr *rep; struct nlmsgerr *errmsg; size_t payload = sizeof(*errmsg); + struct netlink_sock *nlk = nlk_sk(NETLINK_CB(in_skb).sk); - /* error messages get the original request appened */ - if (err) + /* Error messages get the original request appened, unless the user + * requests to cap the error message. + */ + if (!(nlk->flags & NETLINK_F_CAP_ACK) && err) payload += nlmsg_len(nlh); skb = netlink_alloc_skb(in_skb->sk, nlmsg_total_size(payload), @@ -2898,7 +2923,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err) NLMSG_ERROR, payload, 0); errmsg = nlmsg_data(rep); errmsg->error = err; - memcpy(&errmsg->msg, nlh, err ? nlh->nlmsg_len : sizeof(*nlh)); + memcpy(&errmsg->msg, nlh, payload > sizeof(*errmsg) ? nlh->nlmsg_len : sizeof(*nlh)); netlink_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid, MSG_DONTWAIT); } EXPORT_SYMBOL(netlink_ack); |