diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-15 11:56:19 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-11-15 11:56:19 -0800 |
commit | 5bbcc0f595fadb4cac0eddc4401035ec0bd95b09 (patch) | |
tree | 3b65e490cc36a6c6fecac1fa24d9e0ac9ced4455 /kernel/bpf/lpm_trie.c | |
parent | 892204e06cb9e89fbc4b299a678f9ca358e97cac (diff) | |
parent | 50895b9de1d3e0258e015e8e55128d835d9a9f19 (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Highlights:
1) Maintain the TCP retransmit queue using an rbtree, with 1GB
windows at 100Gb this really has become necessary. From Eric
Dumazet.
2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.
3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
Lunn.
4) Add meter action support to openvswitch, from Andy Zhou.
5) Add a data meta pointer for BPF accessible packets, from Daniel
Borkmann.
6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.
7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.
8) More work to move the RTNL mutex down, from Florian Westphal.
9) Add 'bpftool' utility, to help with bpf program introspection.
From Jakub Kicinski.
10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
Dangaard Brouer.
11) Support 'blocks' of transformations in the packet scheduler which
can span multiple network devices, from Jiri Pirko.
12) TC flower offload support in cxgb4, from Kumar Sanghvi.
13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
Leitner.
14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.
15) Add RED qdisc offloadability, and use it in mlxsw driver. From
Nogah Frankel.
16) eBPF based device controller for cgroup v2, from Roman Gushchin.
17) Add some fundamental tracepoints for TCP, from Song Liu.
18) Remove garbage collection from ipv6 route layer, this is a
significant accomplishment. From Wei Wang.
19) Add multicast route offload support to mlxsw, from Yotam Gigi"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
tcp: highest_sack fix
geneve: fix fill_info when link down
bpf: fix lockdep splat
net: cdc_ncm: GetNtbFormat endian fix
openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
netem: remove unnecessary 64 bit modulus
netem: use 64 bit divide by rate
tcp: Namespace-ify sysctl_tcp_default_congestion_control
net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
ipv6: set all.accept_dad to 0 by default
uapi: fix linux/tls.h userspace compilation error
usbnet: ipheth: prevent TX queue timeouts when device not ready
vhost_net: conditionally enable tx polling
uapi: fix linux/rxrpc.h userspace compilation errors
net: stmmac: fix LPI transitioning for dwmac4
atm: horizon: Fix irq release error
net-sysfs: trigger netlink notification on ifalias change via sysfs
openvswitch: Using kfree_rcu() to simplify the code
openvswitch: Make local function ovs_nsh_key_attr_size() static
openvswitch: Fix return value check in ovs_meter_cmd_features()
...
Diffstat (limited to 'kernel/bpf/lpm_trie.c')
-rw-r--r-- | kernel/bpf/lpm_trie.c | 98 |
1 files changed, 94 insertions, 4 deletions
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 1b767844a76f..885e45479680 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -389,10 +389,99 @@ out: return ret; } -static int trie_delete_elem(struct bpf_map *map, void *key) +/* Called from syscall or from eBPF program */ +static int trie_delete_elem(struct bpf_map *map, void *_key) { - /* TODO */ - return -ENOSYS; + struct lpm_trie *trie = container_of(map, struct lpm_trie, map); + struct bpf_lpm_trie_key *key = _key; + struct lpm_trie_node __rcu **trim, **trim2; + struct lpm_trie_node *node, *parent; + unsigned long irq_flags; + unsigned int next_bit; + size_t matchlen = 0; + int ret = 0; + + if (key->prefixlen > trie->max_prefixlen) + return -EINVAL; + + raw_spin_lock_irqsave(&trie->lock, irq_flags); + + /* Walk the tree looking for an exact key/length match and keeping + * track of the path we traverse. We will need to know the node + * we wish to delete, and the slot that points to the node we want + * to delete. We may also need to know the nodes parent and the + * slot that contains it. + */ + trim = &trie->root; + trim2 = trim; + parent = NULL; + while ((node = rcu_dereference_protected( + *trim, lockdep_is_held(&trie->lock)))) { + matchlen = longest_prefix_match(trie, node, key); + + if (node->prefixlen != matchlen || + node->prefixlen == key->prefixlen) + break; + + parent = node; + trim2 = trim; + next_bit = extract_bit(key->data, node->prefixlen); + trim = &node->child[next_bit]; + } + + if (!node || node->prefixlen != key->prefixlen || + (node->flags & LPM_TREE_NODE_FLAG_IM)) { + ret = -ENOENT; + goto out; + } + + trie->n_entries--; + + /* If the node we are removing has two children, simply mark it + * as intermediate and we are done. + */ + if (rcu_access_pointer(node->child[0]) && + rcu_access_pointer(node->child[1])) { + node->flags |= LPM_TREE_NODE_FLAG_IM; + goto out; + } + + /* If the parent of the node we are about to delete is an intermediate + * node, and the deleted node doesn't have any children, we can delete + * the intermediate parent as well and promote its other child + * up the tree. Doing this maintains the invariant that all + * intermediate nodes have exactly 2 children and that there are no + * unnecessary intermediate nodes in the tree. + */ + if (parent && (parent->flags & LPM_TREE_NODE_FLAG_IM) && + !node->child[0] && !node->child[1]) { + if (node == rcu_access_pointer(parent->child[0])) + rcu_assign_pointer( + *trim2, rcu_access_pointer(parent->child[1])); + else + rcu_assign_pointer( + *trim2, rcu_access_pointer(parent->child[0])); + kfree_rcu(parent, rcu); + kfree_rcu(node, rcu); + goto out; + } + + /* The node we are removing has either zero or one child. If there + * is a child, move it into the removed node's slot then delete + * the node. Otherwise just clear the slot and delete the node. + */ + if (node->child[0]) + rcu_assign_pointer(*trim, rcu_access_pointer(node->child[0])); + else if (node->child[1]) + rcu_assign_pointer(*trim, rcu_access_pointer(node->child[1])); + else + RCU_INIT_POINTER(*trim, NULL); + kfree_rcu(node, rcu); + +out: + raw_spin_unlock_irqrestore(&trie->lock, irq_flags); + + return ret; } #define LPM_DATA_SIZE_MAX 256 @@ -406,7 +495,8 @@ static int trie_delete_elem(struct bpf_map *map, void *key) #define LPM_KEY_SIZE_MAX LPM_KEY_SIZE(LPM_DATA_SIZE_MAX) #define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN) -#define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE) +#define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE | \ + BPF_F_RDONLY | BPF_F_WRONLY) static struct bpf_map *trie_alloc(union bpf_attr *attr) { |