summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
authorEmmanuel Grumbach <emmanuel.grumbach@intel.com>2015-10-25 13:38:20 +0300
committerEmmanuel Grumbach <emmanuel.grumbach@intel.com>2015-10-25 13:38:20 +0300
commit10d15322ed26652263a579bcb59dfd49ab8a30de (patch)
treeb1497de1b8ffd34b991cdf6e21de1c7a0a65f1de /net/core
parent0316d30ea3e66379cd30ed70a114bc282159bb4c (diff)
parente5a9f8d04660da7ef3a98260aa74c3976f9cb4cd (diff)
downloadlinux-10d15322ed26652263a579bcb59dfd49ab8a30de.tar.xz
Merge remote-tracking branch 'mac80211-next/master' into next
Diffstat (limited to 'net/core')
-rw-r--r--net/core/dev.c18
-rw-r--r--net/core/dst.c14
-rw-r--r--net/core/fib_rules.c14
-rw-r--r--net/core/filter.c79
-rw-r--r--net/core/lwtunnel.c4
-rw-r--r--net/core/neighbour.c45
-rw-r--r--net/core/net-sysfs.c14
-rw-r--r--net/core/netpoll.c29
-rw-r--r--net/core/request_sock.c88
-rw-r--r--net/core/rtnetlink.c30
-rw-r--r--net/core/skbuff.c9
-rw-r--r--net/core/sock.c45
-rw-r--r--net/core/sock_diag.c14
-rw-r--r--net/core/utils.c49
14 files changed, 223 insertions, 229 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index ee0d6286f934..a229bf0d649d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2974,6 +2974,7 @@ static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
new_index = skb_tx_hash(dev, skb);
if (queue_index != new_index && sk &&
+ sk_fullsock(sk) &&
rcu_access_pointer(sk->sk_dst_cache))
sk_tx_queue_set(sk, new_index);
@@ -4723,6 +4724,8 @@ void napi_disable(struct napi_struct *n)
while (test_and_set_bit(NAPI_STATE_SCHED, &n->state))
msleep(1);
+ while (test_and_set_bit(NAPI_STATE_NPSVC, &n->state))
+ msleep(1);
hrtimer_cancel(&n->timer);
@@ -4865,8 +4868,7 @@ struct netdev_adjacent {
struct rcu_head rcu;
};
-static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev,
- struct net_device *adj_dev,
+static struct netdev_adjacent *__netdev_find_adj(struct net_device *adj_dev,
struct list_head *adj_list)
{
struct netdev_adjacent *adj;
@@ -4892,7 +4894,7 @@ bool netdev_has_upper_dev(struct net_device *dev,
{
ASSERT_RTNL();
- return __netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper);
+ return __netdev_find_adj(upper_dev, &dev->all_adj_list.upper);
}
EXPORT_SYMBOL(netdev_has_upper_dev);
@@ -5154,7 +5156,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
struct netdev_adjacent *adj;
int ret;
- adj = __netdev_find_adj(dev, adj_dev, dev_list);
+ adj = __netdev_find_adj(adj_dev, dev_list);
if (adj) {
adj->ref_nr++;
@@ -5210,7 +5212,7 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev,
{
struct netdev_adjacent *adj;
- adj = __netdev_find_adj(dev, adj_dev, dev_list);
+ adj = __netdev_find_adj(adj_dev, dev_list);
if (!adj) {
pr_err("tried to remove device %s from %s\n",
@@ -5331,10 +5333,10 @@ static int __netdev_upper_dev_link(struct net_device *dev,
return -EBUSY;
/* To prevent loops, check if dev is not upper device to upper_dev. */
- if (__netdev_find_adj(upper_dev, dev, &upper_dev->all_adj_list.upper))
+ if (__netdev_find_adj(dev, &upper_dev->all_adj_list.upper))
return -EBUSY;
- if (__netdev_find_adj(dev, upper_dev, &dev->adj_list.upper))
+ if (__netdev_find_adj(upper_dev, &dev->adj_list.upper))
return -EEXIST;
if (master && netdev_master_upper_dev_get(dev))
@@ -5612,7 +5614,7 @@ void *netdev_lower_dev_get_private(struct net_device *dev,
if (!lower_dev)
return NULL;
- lower = __netdev_find_adj(dev, lower_dev, &dev->adj_list.lower);
+ lower = __netdev_find_adj(lower_dev, &dev->adj_list.lower);
if (!lower)
return NULL;
diff --git a/net/core/dst.c b/net/core/dst.c
index 0771c8cb9307..2a1818065e12 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -144,12 +144,12 @@ loop:
mutex_unlock(&dst_gc_mutex);
}
-int dst_discard_sk(struct sock *sk, struct sk_buff *skb)
+int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
{
kfree_skb(skb);
return 0;
}
-EXPORT_SYMBOL(dst_discard_sk);
+EXPORT_SYMBOL(dst_discard_out);
const u32 dst_default_metrics[RTAX_MAX + 1] = {
/* This initializer is needed to force linker to place this variable
@@ -177,7 +177,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops,
dst->xfrm = NULL;
#endif
dst->input = dst_discard;
- dst->output = dst_discard_sk;
+ dst->output = dst_discard_out;
dst->error = 0;
dst->obsolete = initial_obsolete;
dst->header_len = 0;
@@ -224,7 +224,7 @@ static void ___dst_free(struct dst_entry *dst)
*/
if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) {
dst->input = dst_discard;
- dst->output = dst_discard_sk;
+ dst->output = dst_discard_out;
}
dst->obsolete = DST_OBSOLETE_DEAD;
}
@@ -352,7 +352,7 @@ static struct dst_ops md_dst_ops = {
.family = AF_UNSPEC,
};
-static int dst_md_discard_sk(struct sock *sk, struct sk_buff *skb)
+static int dst_md_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
{
WARN_ONCE(1, "Attempting to call output on metadata dst\n");
kfree_skb(skb);
@@ -375,7 +375,7 @@ static void __metadata_dst_init(struct metadata_dst *md_dst, u8 optslen)
DST_METADATA | DST_NOCACHE | DST_NOCOUNT);
dst->input = dst_md_discard;
- dst->output = dst_md_discard_sk;
+ dst->output = dst_md_discard_out;
memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst));
}
@@ -430,7 +430,7 @@ static void dst_ifdown(struct dst_entry *dst, struct net_device *dev,
if (!unregister) {
dst->input = dst_discard;
- dst->output = dst_discard_sk;
+ dst->output = dst_discard_out;
} else {
dst->dev = dev_net(dst->dev)->loopback_dev;
dev_hold(dst->dev);
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index bf77e3639ce0..365de66436ac 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -631,15 +631,17 @@ static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb,
{
int idx = 0;
struct fib_rule *rule;
+ int err = 0;
rcu_read_lock();
list_for_each_entry_rcu(rule, &ops->rules_list, list) {
if (idx < cb->args[1])
goto skip;
- if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq, RTM_NEWRULE,
- NLM_F_MULTI, ops) < 0)
+ err = fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, RTM_NEWRULE,
+ NLM_F_MULTI, ops);
+ if (err)
break;
skip:
idx++;
@@ -648,7 +650,7 @@ skip:
cb->args[1] = idx;
rules_ops_put(ops);
- return skb->len;
+ return err;
}
static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
@@ -664,7 +666,9 @@ static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
if (ops == NULL)
return -EAFNOSUPPORT;
- return dump_rules(skb, cb, ops);
+ dump_rules(skb, cb, ops);
+
+ return skb->len;
}
rcu_read_lock();
diff --git a/net/core/filter.c b/net/core/filter.c
index da3f3d94d6e9..0b00094932ab 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -49,16 +49,17 @@
#include <net/sch_generic.h>
#include <net/cls_cgroup.h>
#include <net/dst_metadata.h>
+#include <net/dst.h>
/**
* sk_filter - run a packet through a socket filter
* @sk: sock associated with &sk_buff
* @skb: buffer to filter
*
- * Run the filter code and then cut skb->data to correct size returned by
- * SK_RUN_FILTER. If pkt_len is 0 we toss packet. If skb->len is smaller
+ * Run the eBPF program and then cut skb->data to correct size returned by
+ * the program. If pkt_len is 0 we toss packet. If skb->len is smaller
* than pkt_len we keep whole skb->data. This is the socket level
- * wrapper to SK_RUN_FILTER. It returns 0 if the packet should
+ * wrapper to BPF_PROG_RUN. It returns 0 if the packet should
* be accepted or -EPERM if the packet should be tossed.
*
*/
@@ -82,7 +83,7 @@ int sk_filter(struct sock *sk, struct sk_buff *skb)
rcu_read_lock();
filter = rcu_dereference(sk->sk_filter);
if (filter) {
- unsigned int pkt_len = SK_RUN_FILTER(filter, skb);
+ unsigned int pkt_len = bpf_prog_run_save_cb(filter->prog, skb);
err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM;
}
@@ -148,12 +149,6 @@ static u64 __get_raw_cpu_id(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
return raw_smp_processor_id();
}
-/* note that this only generates 32-bit random numbers */
-static u64 __get_random_u32(u64 ctx, u64 a, u64 x, u64 r4, u64 r5)
-{
- return prandom_u32();
-}
-
static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg,
struct bpf_insn *insn_buf)
{
@@ -312,7 +307,8 @@ static bool convert_bpf_extensions(struct sock_filter *fp,
*insn = BPF_EMIT_CALL(__get_raw_cpu_id);
break;
case SKF_AD_OFF + SKF_AD_RANDOM:
- *insn = BPF_EMIT_CALL(__get_random_u32);
+ *insn = BPF_EMIT_CALL(bpf_user_rnd_u32);
+ bpf_user_rnd_init_once();
break;
}
break;
@@ -478,9 +474,9 @@ do_pass:
bpf_src = BPF_X;
} else {
insn->dst_reg = BPF_REG_A;
- insn->src_reg = BPF_REG_X;
insn->imm = fp->k;
bpf_src = BPF_SRC(fp->code);
+ insn->src_reg = bpf_src == BPF_X ? BPF_REG_X : 0;
}
/* Common case where 'jump_false' is next insn. */
@@ -1001,7 +997,7 @@ static struct bpf_prog *bpf_prepare_filter(struct bpf_prog *fp,
int err;
fp->bpf_func = NULL;
- fp->jited = false;
+ fp->jited = 0;
err = bpf_check_classic(fp->insns, fp->len);
if (err) {
@@ -1083,16 +1079,18 @@ EXPORT_SYMBOL_GPL(bpf_prog_create);
* @pfp: the unattached filter that is created
* @fprog: the filter program
* @trans: post-classic verifier transformation handler
+ * @save_orig: save classic BPF program
*
* This function effectively does the same as bpf_prog_create(), only
* that it builds up its insns buffer from user space provided buffer.
* It also allows for passing a bpf_aux_classic_check_t handler.
*/
int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
- bpf_aux_classic_check_t trans)
+ bpf_aux_classic_check_t trans, bool save_orig)
{
unsigned int fsize = bpf_classic_proglen(fprog);
struct bpf_prog *fp;
+ int err;
/* Make sure new filter is there and in the right amounts. */
if (fprog->filter == NULL)
@@ -1108,12 +1106,16 @@ int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
}
fp->len = fprog->len;
- /* Since unattached filters are not copied back to user
- * space through sk_get_filter(), we do not need to hold
- * a copy here, and can spare us the work.
- */
fp->orig_prog = NULL;
+ if (save_orig) {
+ err = bpf_prog_store_orig_filter(fp, fprog);
+ if (err) {
+ __bpf_prog_free(fp);
+ return -ENOMEM;
+ }
+ }
+
/* bpf_prepare_filter() already takes care of freeing
* memory in case something goes wrong.
*/
@@ -1404,9 +1406,6 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5)
if (unlikely(!dev))
return -EINVAL;
- if (unlikely(!(dev->flags & IFF_UP)))
- return -EINVAL;
-
skb2 = skb_clone(skb, GFP_ATOMIC);
if (unlikely(!skb2))
return -ENOMEM;
@@ -1458,6 +1457,7 @@ int skb_do_redirect(struct sk_buff *skb)
return dev_forward_skb(dev, skb);
skb->dev = dev;
+ skb_sender_cpu_clear(skb);
return dev_queue_xmit(skb);
}
@@ -1481,6 +1481,25 @@ static const struct bpf_func_proto bpf_get_cgroup_classid_proto = {
.arg1_type = ARG_PTR_TO_CTX,
};
+static u64 bpf_get_route_realm(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+#ifdef CONFIG_IP_ROUTE_CLASSID
+ const struct dst_entry *dst;
+
+ dst = skb_dst((struct sk_buff *) (unsigned long) r1);
+ if (dst)
+ return dst->tclassid;
+#endif
+ return 0;
+}
+
+static const struct bpf_func_proto bpf_get_route_realm_proto = {
+ .func = bpf_get_route_realm,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+};
+
static u64 bpf_skb_vlan_push(u64 r1, u64 r2, u64 vlan_tci, u64 r4, u64 r5)
{
struct sk_buff *skb = (struct sk_buff *) (long) r1;
@@ -1621,7 +1640,8 @@ sk_filter_func_proto(enum bpf_func_id func_id)
case BPF_FUNC_ktime_get_ns:
return &bpf_ktime_get_ns_proto;
case BPF_FUNC_trace_printk:
- return bpf_get_trace_printk_proto();
+ if (capable(CAP_SYS_ADMIN))
+ return bpf_get_trace_printk_proto();
default:
return NULL;
}
@@ -1651,6 +1671,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id)
return bpf_get_skb_set_tunnel_key_proto();
case BPF_FUNC_redirect:
return &bpf_redirect_proto;
+ case BPF_FUNC_get_route_realm:
+ return &bpf_get_route_realm_proto;
default:
return sk_filter_func_proto(func_id);
}
@@ -1702,6 +1724,7 @@ static bool tc_cls_act_is_valid_access(int off, int size,
switch (off) {
case offsetof(struct __sk_buff, mark):
case offsetof(struct __sk_buff, tc_index):
+ case offsetof(struct __sk_buff, priority):
case offsetof(struct __sk_buff, cb[0]) ...
offsetof(struct __sk_buff, cb[4]):
break;
@@ -1714,7 +1737,8 @@ static bool tc_cls_act_is_valid_access(int off, int size,
static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg,
int src_reg, int ctx_off,
- struct bpf_insn *insn_buf)
+ struct bpf_insn *insn_buf,
+ struct bpf_prog *prog)
{
struct bpf_insn *insn = insn_buf;
@@ -1743,8 +1767,12 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg,
case offsetof(struct __sk_buff, priority):
BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, priority) != 4);
- *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
- offsetof(struct sk_buff, priority));
+ if (type == BPF_WRITE)
+ *insn++ = BPF_STX_MEM(BPF_W, dst_reg, src_reg,
+ offsetof(struct sk_buff, priority));
+ else
+ *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg,
+ offsetof(struct sk_buff, priority));
break;
case offsetof(struct __sk_buff, ingress_ifindex):
@@ -1801,6 +1829,7 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg,
offsetof(struct __sk_buff, cb[4]):
BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, data) < 20);
+ prog->cb_access = 1;
ctx_off -= offsetof(struct __sk_buff, cb[0]);
ctx_off += offsetof(struct sk_buff, cb);
ctx_off += offsetof(struct qdisc_skb_cb, data);
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index dfb1a9ca0835..299cfc24d888 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -180,7 +180,7 @@ int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b)
}
EXPORT_SYMBOL(lwtunnel_cmp_encap);
-int lwtunnel_output(struct sock *sk, struct sk_buff *skb)
+int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
const struct lwtunnel_encap_ops *ops;
@@ -199,7 +199,7 @@ int lwtunnel_output(struct sock *sk, struct sk_buff *skb)
rcu_read_lock();
ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
if (likely(ops && ops->output))
- ret = ops->output(sk, skb);
+ ret = ops->output(net, sk, skb);
rcu_read_unlock();
if (ret == -EOPNOTSUPP)
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 2b515ba7e94f..1aa8437ed6c4 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2235,14 +2235,53 @@ static void neigh_update_notify(struct neighbour *neigh)
__neigh_notify(neigh, RTM_NEWNEIGH, 0);
}
+static bool neigh_master_filtered(struct net_device *dev, int master_idx)
+{
+ struct net_device *master;
+
+ if (!master_idx)
+ return false;
+
+ master = netdev_master_upper_dev_get(dev);
+ if (!master || master->ifindex != master_idx)
+ return true;
+
+ return false;
+}
+
+static bool neigh_ifindex_filtered(struct net_device *dev, int filter_idx)
+{
+ if (filter_idx && dev->ifindex != filter_idx)
+ return true;
+
+ return false;
+}
+
static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
+ const struct nlmsghdr *nlh = cb->nlh;
+ struct nlattr *tb[NDA_MAX + 1];
struct neighbour *n;
int rc, h, s_h = cb->args[1];
int idx, s_idx = idx = cb->args[2];
struct neigh_hash_table *nht;
+ int filter_master_idx = 0, filter_idx = 0;
+ unsigned int flags = NLM_F_MULTI;
+ int err;
+
+ err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL);
+ if (!err) {
+ if (tb[NDA_IFINDEX])
+ filter_idx = nla_get_u32(tb[NDA_IFINDEX]);
+
+ if (tb[NDA_MASTER])
+ filter_master_idx = nla_get_u32(tb[NDA_MASTER]);
+
+ if (filter_idx || filter_master_idx)
+ flags |= NLM_F_DUMP_FILTERED;
+ }
rcu_read_lock_bh();
nht = rcu_dereference_bh(tbl->nht);
@@ -2255,12 +2294,16 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
n = rcu_dereference_bh(n->next)) {
if (!net_eq(dev_net(n->dev), net))
continue;
+ if (neigh_ifindex_filtered(n->dev, filter_idx))
+ continue;
+ if (neigh_master_filtered(n->dev, filter_master_idx))
+ continue;
if (idx < s_idx)
goto next;
if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
RTM_NEWNEIGH,
- NLM_F_MULTI) < 0) {
+ flags) < 0) {
rc = -1;
goto out;
}
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 49b599062af1..f88a62ab019d 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -31,7 +31,6 @@
static const char fmt_hex[] = "%#x\n";
static const char fmt_long_hex[] = "%#lx\n";
static const char fmt_dec[] = "%d\n";
-static const char fmt_udec[] = "%u\n";
static const char fmt_ulong[] = "%lu\n";
static const char fmt_u64[] = "%llu\n";
@@ -202,7 +201,7 @@ static ssize_t speed_show(struct device *dev,
if (netif_running(netdev)) {
struct ethtool_cmd cmd;
if (!__ethtool_get_settings(netdev, &cmd))
- ret = sprintf(buf, fmt_udec, ethtool_cmd_speed(&cmd));
+ ret = sprintf(buf, fmt_dec, ethtool_cmd_speed(&cmd));
}
rtnl_unlock();
return ret;
@@ -472,7 +471,7 @@ static ssize_t phys_switch_id_show(struct device *dev,
if (dev_isalive(netdev)) {
struct switchdev_attr attr = {
- .id = SWITCHDEV_ATTR_PORT_PARENT_ID,
+ .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
.flags = SWITCHDEV_F_NO_RECURSE,
};
@@ -1478,6 +1477,15 @@ static int of_dev_node_match(struct device *dev, const void *data)
return ret == 0 ? dev->of_node == data : ret;
}
+/*
+ * of_find_net_device_by_node - lookup the net device for the device node
+ * @np: OF device node
+ *
+ * Looks up the net_device structure corresponding with the device node.
+ * If successful, returns a pointer to the net_device with the embedded
+ * struct device refcount incremented by one, or NULL on failure. The
+ * refcount must be dropped when done with the net_device.
+ */
struct net_device *of_find_net_device_by_node(struct device_node *np)
{
struct device *dev;
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 6aa3db8dfc3b..94acfc89ad97 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -140,36 +140,42 @@ static void queue_process(struct work_struct *work)
* case. Further, we test the poll_owner to avoid recursion on UP
* systems where the lock doesn't exist.
*/
-static int poll_one_napi(struct napi_struct *napi, int budget)
+static void poll_one_napi(struct napi_struct *napi)
{
- int work;
+ int work = 0;
/* net_rx_action's ->poll() invocations and our's are
* synchronized by this test which is only made while
* holding the napi->poll_lock.
*/
if (!test_bit(NAPI_STATE_SCHED, &napi->state))
- return budget;
+ return;
- set_bit(NAPI_STATE_NPSVC, &napi->state);
+ /* If we set this bit but see that it has already been set,
+ * that indicates that napi has been disabled and we need
+ * to abort this operation
+ */
+ if (test_and_set_bit(NAPI_STATE_NPSVC, &napi->state))
+ return;
- work = napi->poll(napi, budget);
- WARN_ONCE(work > budget, "%pF exceeded budget in poll\n", napi->poll);
+ /* We explicilty pass the polling call a budget of 0 to
+ * indicate that we are clearing the Tx path only.
+ */
+ work = napi->poll(napi, 0);
+ WARN_ONCE(work, "%pF exceeded budget in poll\n", napi->poll);
trace_napi_poll(napi);
clear_bit(NAPI_STATE_NPSVC, &napi->state);
-
- return budget - work;
}
-static void poll_napi(struct net_device *dev, int budget)
+static void poll_napi(struct net_device *dev)
{
struct napi_struct *napi;
list_for_each_entry(napi, &dev->napi_list, dev_list) {
if (napi->poll_owner != smp_processor_id() &&
spin_trylock(&napi->poll_lock)) {
- budget = poll_one_napi(napi, budget);
+ poll_one_napi(napi);
spin_unlock(&napi->poll_lock);
}
}
@@ -179,7 +185,6 @@ static void netpoll_poll_dev(struct net_device *dev)
{
const struct net_device_ops *ops;
struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo);
- int budget = 0;
/* Don't do any rx activity if the dev_lock mutex is held
* the dev_open/close paths use this to block netpoll activity
@@ -202,7 +207,7 @@ static void netpoll_poll_dev(struct net_device *dev)
/* Process pending work on NIC */
ops->ndo_poll_controller(dev);
- poll_napi(dev, budget);
+ poll_napi(dev);
up(&ni->dev_lock);
diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index b42f0e26f89e..5d26056b6d8f 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -37,90 +37,16 @@
int sysctl_max_syn_backlog = 256;
EXPORT_SYMBOL(sysctl_max_syn_backlog);
-int reqsk_queue_alloc(struct request_sock_queue *queue,
- unsigned int nr_table_entries)
+void reqsk_queue_alloc(struct request_sock_queue *queue)
{
- size_t lopt_size = sizeof(struct listen_sock);
- struct listen_sock *lopt = NULL;
+ spin_lock_init(&queue->rskq_lock);
- nr_table_entries = min_t(u32, nr_table_entries, sysctl_max_syn_backlog);
- nr_table_entries = max_t(u32, nr_table_entries, 8);
- nr_table_entries = roundup_pow_of_two(nr_table_entries + 1);
- lopt_size += nr_table_entries * sizeof(struct request_sock *);
+ spin_lock_init(&queue->fastopenq.lock);
+ queue->fastopenq.rskq_rst_head = NULL;
+ queue->fastopenq.rskq_rst_tail = NULL;
+ queue->fastopenq.qlen = 0;
- if (lopt_size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
- lopt = kzalloc(lopt_size, GFP_KERNEL |
- __GFP_NOWARN |
- __GFP_NORETRY);
- if (!lopt)
- lopt = vzalloc(lopt_size);
- if (!lopt)
- return -ENOMEM;
-
- get_random_bytes(&lopt->hash_rnd, sizeof(lopt->hash_rnd));
- spin_lock_init(&queue->syn_wait_lock);
queue->rskq_accept_head = NULL;
- lopt->nr_table_entries = nr_table_entries;
- lopt->max_qlen_log = ilog2(nr_table_entries);
-
- spin_lock_bh(&queue->syn_wait_lock);
- queue->listen_opt = lopt;
- spin_unlock_bh(&queue->syn_wait_lock);
-
- return 0;
-}
-
-void __reqsk_queue_destroy(struct request_sock_queue *queue)
-{
- /* This is an error recovery path only, no locking needed */
- kvfree(queue->listen_opt);
-}
-
-static inline struct listen_sock *reqsk_queue_yank_listen_sk(
- struct request_sock_queue *queue)
-{
- struct listen_sock *lopt;
-
- spin_lock_bh(&queue->syn_wait_lock);
- lopt = queue->listen_opt;
- queue->listen_opt = NULL;
- spin_unlock_bh(&queue->syn_wait_lock);
-
- return lopt;
-}
-
-void reqsk_queue_destroy(struct request_sock_queue *queue)
-{
- /* make all the listen_opt local to us */
- struct listen_sock *lopt = reqsk_queue_yank_listen_sk(queue);
-
- if (listen_sock_qlen(lopt) != 0) {
- unsigned int i;
-
- for (i = 0; i < lopt->nr_table_entries; i++) {
- struct request_sock *req;
-
- spin_lock_bh(&queue->syn_wait_lock);
- while ((req = lopt->syn_table[i]) != NULL) {
- lopt->syn_table[i] = req->dl_next;
- /* Because of following del_timer_sync(),
- * we must release the spinlock here
- * or risk a dead lock.
- */
- spin_unlock_bh(&queue->syn_wait_lock);
- atomic_inc(&lopt->qlen_dec);
- if (del_timer_sync(&req->rsk_timer))
- reqsk_put(req);
- reqsk_put(req);
- spin_lock_bh(&queue->syn_wait_lock);
- }
- spin_unlock_bh(&queue->syn_wait_lock);
- }
- }
-
- if (WARN_ON(listen_sock_qlen(lopt) != 0))
- pr_err("qlen %u\n", listen_sock_qlen(lopt));
- kvfree(lopt);
}
/*
@@ -174,7 +100,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
struct sock *lsk = req->rsk_listener;
struct fastopen_queue *fastopenq;
- fastopenq = inet_csk(lsk)->icsk_accept_queue.fastopenq;
+ fastopenq = &inet_csk(lsk)->icsk_accept_queue.fastopenq;
tcp_sk(sk)->fastopen_rsk = NULL;
spin_lock_bh(&fastopenq->lock);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e5452296ec2f..24775953fa68 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -96,7 +96,7 @@ int rtnl_is_locked(void)
EXPORT_SYMBOL(rtnl_is_locked);
#ifdef CONFIG_PROVE_LOCKING
-int lockdep_rtnl_is_held(void)
+bool lockdep_rtnl_is_held(void)
{
return lockdep_is_held(&rtnl_mutex);
}
@@ -1025,7 +1025,7 @@ static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev)
{
int err;
struct switchdev_attr attr = {
- .id = SWITCHDEV_ATTR_PORT_PARENT_ID,
+ .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID,
.flags = SWITCHDEV_F_NO_RECURSE,
};
@@ -3047,6 +3047,7 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
u32 portid = NETLINK_CB(cb->skb).portid;
u32 seq = cb->nlh->nlmsg_seq;
u32 filter_mask = 0;
+ int err;
if (nlmsg_len(cb->nlh) > sizeof(struct ifinfomsg)) {
struct nlattr *extfilt;
@@ -3067,20 +3068,25 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
struct net_device *br_dev = netdev_master_upper_dev_get(dev);
if (br_dev && br_dev->netdev_ops->ndo_bridge_getlink) {
- if (idx >= cb->args[0] &&
- br_dev->netdev_ops->ndo_bridge_getlink(
- skb, portid, seq, dev, filter_mask,
- NLM_F_MULTI) < 0)
- break;
+ if (idx >= cb->args[0]) {
+ err = br_dev->netdev_ops->ndo_bridge_getlink(
+ skb, portid, seq, dev,
+ filter_mask, NLM_F_MULTI);
+ if (err < 0 && err != -EOPNOTSUPP)
+ break;
+ }
idx++;
}
if (ops->ndo_bridge_getlink) {
- if (idx >= cb->args[0] &&
- ops->ndo_bridge_getlink(skb, portid, seq, dev,
- filter_mask,
- NLM_F_MULTI) < 0)
- break;
+ if (idx >= cb->args[0]) {
+ err = ops->ndo_bridge_getlink(skb, portid,
+ seq, dev,
+ filter_mask,
+ NLM_F_MULTI);
+ if (err < 0 && err != -EOPNOTSUPP)
+ break;
+ }
idx++;
}
}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index dad4dd37e2aa..fab4599ba8b2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2958,11 +2958,12 @@ EXPORT_SYMBOL_GPL(skb_append_pagefrags);
*/
unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len)
{
+ unsigned char *data = skb->data;
+
BUG_ON(len > skb->len);
- skb->len -= len;
- BUG_ON(skb->len < skb->data_len);
- skb_postpull_rcsum(skb, skb->data, len);
- return skb->data += len;
+ __skb_pull(skb, len);
+ skb_postpull_rcsum(skb, data, len);
+ return skb->data;
}
EXPORT_SYMBOL_GPL(skb_pull_rcsum);
diff --git a/net/core/sock.c b/net/core/sock.c
index ca2984afe16e..dcc7d62654d5 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -988,6 +988,10 @@ set_rcvbuf:
sk->sk_max_pacing_rate);
break;
+ case SO_INCOMING_CPU:
+ sk->sk_incoming_cpu = val;
+ break;
+
default:
ret = -ENOPROTOOPT;
break;
@@ -1852,6 +1856,32 @@ struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size,
}
EXPORT_SYMBOL(sock_alloc_send_skb);
+int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
+ struct sockcm_cookie *sockc)
+{
+ struct cmsghdr *cmsg;
+
+ for_each_cmsghdr(cmsg, msg) {
+ if (!CMSG_OK(msg, cmsg))
+ return -EINVAL;
+ if (cmsg->cmsg_level != SOL_SOCKET)
+ continue;
+ switch (cmsg->cmsg_type) {
+ case SO_MARK:
+ if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
+ return -EPERM;
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
+ return -EINVAL;
+ sockc->mark = *(u32 *)CMSG_DATA(cmsg);
+ break;
+ default:
+ return -EINVAL;
+ }
+ }
+ return 0;
+}
+EXPORT_SYMBOL(sock_cmsg_send);
+
/* On 32bit arches, an skb frag is limited to 2^15 */
#define SKB_FRAG_PAGE_ORDER get_order(32768)
@@ -2353,6 +2383,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
sk->sk_max_pacing_rate = ~0U;
sk->sk_pacing_rate = ~0U;
+ sk->sk_incoming_cpu = -1;
/*
* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.txt for details)
@@ -2740,10 +2771,8 @@ static void req_prot_cleanup(struct request_sock_ops *rsk_prot)
return;
kfree(rsk_prot->slab_name);
rsk_prot->slab_name = NULL;
- if (rsk_prot->slab) {
- kmem_cache_destroy(rsk_prot->slab);
- rsk_prot->slab = NULL;
- }
+ kmem_cache_destroy(rsk_prot->slab);
+ rsk_prot->slab = NULL;
}
static int req_prot_init(const struct proto *prot)
@@ -2760,7 +2789,7 @@ static int req_prot_init(const struct proto *prot)
rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name,
rsk_prot->obj_size, 0,
- 0, NULL);
+ prot->slab_flags, NULL);
if (!rsk_prot->slab) {
pr_crit("%s: Can't create request sock SLAB cache!\n",
@@ -2828,10 +2857,8 @@ void proto_unregister(struct proto *prot)
list_del(&prot->node);
mutex_unlock(&proto_list_mutex);
- if (prot->slab != NULL) {
- kmem_cache_destroy(prot->slab);
- prot->slab = NULL;
- }
+ kmem_cache_destroy(prot->slab);
+ prot->slab = NULL;
req_prot_cleanup(prot->rsk_prot);
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index 817622f3dbb7..0c1d58d43f67 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -1,3 +1,5 @@
+/* License: GPL */
+
#include <linux/mutex.h>
#include <linux/socket.h>
#include <linux/skbuff.h>
@@ -323,14 +325,4 @@ static int __init sock_diag_init(void)
BUG_ON(!broadcast_wq);
return register_pernet_subsys(&diag_net_ops);
}
-
-static void __exit sock_diag_exit(void)
-{
- unregister_pernet_subsys(&diag_net_ops);
- destroy_workqueue(broadcast_wq);
-}
-
-module_init(sock_diag_init);
-module_exit(sock_diag_exit);
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_SOCK_DIAG);
+device_initcall(sock_diag_init);
diff --git a/net/core/utils.c b/net/core/utils.c
index 3dffce953c39..3d17ca8b4744 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -348,52 +348,3 @@ void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb,
}
}
EXPORT_SYMBOL(inet_proto_csum_replace_by_diff);
-
-struct __net_random_once_work {
- struct work_struct work;
- struct static_key *key;
-};
-
-static void __net_random_once_deferred(struct work_struct *w)
-{
- struct __net_random_once_work *work =
- container_of(w, struct __net_random_once_work, work);
- BUG_ON(!static_key_enabled(work->key));
- static_key_slow_dec(work->key);
- kfree(work);
-}
-
-static void __net_random_once_disable_jump(struct static_key *key)
-{
- struct __net_random_once_work *w;
-
- w = kmalloc(sizeof(*w), GFP_ATOMIC);
- if (!w)
- return;
-
- INIT_WORK(&w->work, __net_random_once_deferred);
- w->key = key;
- schedule_work(&w->work);
-}
-
-bool __net_get_random_once(void *buf, int nbytes, bool *done,
- struct static_key *once_key)
-{
- static DEFINE_SPINLOCK(lock);
- unsigned long flags;
-
- spin_lock_irqsave(&lock, flags);
- if (*done) {
- spin_unlock_irqrestore(&lock, flags);
- return false;
- }
-
- get_random_bytes(buf, nbytes);
- *done = true;
- spin_unlock_irqrestore(&lock, flags);
-
- __net_random_once_disable_jump(once_key);
-
- return true;
-}
-EXPORT_SYMBOL(__net_get_random_once);