diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2014-12-11 14:27:06 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-12-11 14:27:06 -0800 |
commit | 70e71ca0af244f48a5dcf56dc435243792e3a495 (patch) | |
tree | f7d9c4c4d9a857a00043e9bf6aa2d6f533a34778 /net/core/filter.c | |
parent | bae41e45b7400496b9bf0c70c6004419d9987819 (diff) | |
parent | 00c83b01d58068dfeb2e1351cca6fccf2a83fa8f (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
1) New offloading infrastructure and example 'rocker' driver for
offloading of switching and routing to hardware.
This work was done by a large group of dedicated individuals, not
limited to: Scott Feldman, Jiri Pirko, Thomas Graf, John Fastabend,
Jamal Hadi Salim, Andy Gospodarek, Florian Fainelli, Roopa Prabhu
2) Start making the networking operate on IOV iterators instead of
modifying iov objects in-situ during transfers. Thanks to Al Viro
and Herbert Xu.
3) A set of new netlink interfaces for the TIPC stack, from Richard
Alpe.
4) Remove unnecessary looping during ipv6 routing lookups, from Martin
KaFai Lau.
5) Add PAUSE frame generation support to gianfar driver, from Matei
Pavaluca.
6) Allow for larger reordering levels in TCP, which are easily
achievable in the real world right now, from Eric Dumazet.
7) Add a variable of napi_schedule that doesn't need to disable cpu
interrupts, from Eric Dumazet.
8) Use a doubly linked list to optimize neigh_parms_release(), from
Nicolas Dichtel.
9) Various enhancements to the kernel BPF verifier, and allow eBPF
programs to actually be attached to sockets. From Alexei
Starovoitov.
10) Support TSO/LSO in sunvnet driver, from David L Stevens.
11) Allow controlling ECN usage via routing metrics, from Florian
Westphal.
12) Remote checksum offload, from Tom Herbert.
13) Add split-header receive, BQL, and xmit_more support to amd-xgbe
driver, from Thomas Lendacky.
14) Add MPLS support to openvswitch, from Simon Horman.
15) Support wildcard tunnel endpoints in ipv6 tunnels, from Steffen
Klassert.
16) Do gro flushes on a per-device basis using a timer, from Eric
Dumazet. This tries to resolve the conflicting goals between the
desired handling of bulk vs. RPC-like traffic.
17) Allow userspace to ask for the CPU upon what a packet was
received/steered, via SO_INCOMING_CPU. From Eric Dumazet.
18) Limit GSO packets to half the current congestion window, from Eric
Dumazet.
19) Add a generic helper so that all drivers set their RSS keys in a
consistent way, from Eric Dumazet.
20) Add xmit_more support to enic driver, from Govindarajulu
Varadarajan.
21) Add VLAN packet scheduler action, from Jiri Pirko.
22) Support configurable RSS hash functions via ethtool, from Eyal
Perry.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1820 commits)
Fix race condition between vxlan_sock_add and vxlan_sock_release
net/macb: fix compilation warning for print_hex_dump() called with skb->mac_header
net/mlx4: Add support for A0 steering
net/mlx4: Refactor QUERY_PORT
net/mlx4_core: Add explicit error message when rule doesn't meet configuration
net/mlx4: Add A0 hybrid steering
net/mlx4: Add mlx4_bitmap zone allocator
net/mlx4: Add a check if there are too many reserved QPs
net/mlx4: Change QP allocation scheme
net/mlx4_core: Use tasklet for user-space CQ completion events
net/mlx4_core: Mask out host side virtualization features for guests
net/mlx4_en: Set csum level for encapsulated packets
be2net: Export tunnel offloads only when a VxLAN tunnel is created
gianfar: Fix dma check map error when DMA_API_DEBUG is enabled
cxgb4/csiostor: Don't use MASTER_MUST for fw_hello call
net: fec: only enable mdio interrupt before phy device link up
net: fec: clear all interrupt events to support i.MX6SX
net: fec: reset fep link status in suspend function
net: sock: fix access via invalid file descriptor
net: introduce helper macro for_each_cmsghdr
...
Diffstat (limited to 'net/core/filter.c')
-rw-r--r-- | net/core/filter.c | 97 |
1 files changed, 95 insertions, 2 deletions
diff --git a/net/core/filter.c b/net/core/filter.c index 647b12265e18..ec9baea10c16 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -44,6 +44,7 @@ #include <linux/ratelimit.h> #include <linux/seccomp.h> #include <linux/if_vlan.h> +#include <linux/bpf.h> /** * sk_filter - run a packet through a socket filter @@ -813,8 +814,12 @@ static void bpf_release_orig_filter(struct bpf_prog *fp) static void __bpf_prog_release(struct bpf_prog *prog) { - bpf_release_orig_filter(prog); - bpf_prog_free(prog); + if (prog->aux->prog_type == BPF_PROG_TYPE_SOCKET_FILTER) { + bpf_prog_put(prog); + } else { + bpf_release_orig_filter(prog); + bpf_prog_free(prog); + } } static void __sk_filter_release(struct sk_filter *fp) @@ -1088,6 +1093,94 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) } EXPORT_SYMBOL_GPL(sk_attach_filter); +#ifdef CONFIG_BPF_SYSCALL +int sk_attach_bpf(u32 ufd, struct sock *sk) +{ + struct sk_filter *fp, *old_fp; + struct bpf_prog *prog; + + if (sock_flag(sk, SOCK_FILTER_LOCKED)) + return -EPERM; + + prog = bpf_prog_get(ufd); + if (IS_ERR(prog)) + return PTR_ERR(prog); + + if (prog->aux->prog_type != BPF_PROG_TYPE_SOCKET_FILTER) { + /* valid fd, but invalid program type */ + bpf_prog_put(prog); + return -EINVAL; + } + + fp = kmalloc(sizeof(*fp), GFP_KERNEL); + if (!fp) { + bpf_prog_put(prog); + return -ENOMEM; + } + fp->prog = prog; + + atomic_set(&fp->refcnt, 0); + + if (!sk_filter_charge(sk, fp)) { + __sk_filter_release(fp); + return -ENOMEM; + } + + old_fp = rcu_dereference_protected(sk->sk_filter, + sock_owned_by_user(sk)); + rcu_assign_pointer(sk->sk_filter, fp); + + if (old_fp) + sk_filter_uncharge(sk, old_fp); + + return 0; +} + +/* allow socket filters to call + * bpf_map_lookup_elem(), bpf_map_update_elem(), bpf_map_delete_elem() + */ +static const struct bpf_func_proto *sock_filter_func_proto(enum bpf_func_id func_id) +{ + switch (func_id) { + case BPF_FUNC_map_lookup_elem: + return &bpf_map_lookup_elem_proto; + case BPF_FUNC_map_update_elem: + return &bpf_map_update_elem_proto; + case BPF_FUNC_map_delete_elem: + return &bpf_map_delete_elem_proto; + default: + return NULL; + } +} + +static bool sock_filter_is_valid_access(int off, int size, enum bpf_access_type type) +{ + /* skb fields cannot be accessed yet */ + return false; +} + +static struct bpf_verifier_ops sock_filter_ops = { + .get_func_proto = sock_filter_func_proto, + .is_valid_access = sock_filter_is_valid_access, +}; + +static struct bpf_prog_type_list tl = { + .ops = &sock_filter_ops, + .type = BPF_PROG_TYPE_SOCKET_FILTER, +}; + +static int __init register_sock_filter_ops(void) +{ + bpf_register_prog_type(&tl); + return 0; +} +late_initcall(register_sock_filter_ops); +#else +int sk_attach_bpf(u32 ufd, struct sock *sk) +{ + return -EOPNOTSUPP; +} +#endif int sk_detach_filter(struct sock *sk) { int ret = -ENOENT; |