aboutsummaryrefslogtreecommitdiffstats
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/dev.c78
-rw-r--r--net/core/filter.c32
-rw-r--r--net/core/flow_dissector.c10
-rw-r--r--net/core/gro_cells.c1
-rw-r--r--net/core/neighbour.c7
-rw-r--r--net/core/netpoll.c3
-rw-r--r--net/core/rtnetlink.c5
-rw-r--r--net/core/skbuff.c7
-rw-r--r--net/core/skmsg.c3
-rw-r--r--net/core/sock.c1
-rw-r--r--net/core/sysctl_net_core.c20
11 files changed, 109 insertions, 58 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index 77d43ae2a7bb..722d50dbf8a4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2175,6 +2175,20 @@ static bool remove_xps_queue_cpu(struct net_device *dev,
return active;
}
+static void reset_xps_maps(struct net_device *dev,
+ struct xps_dev_maps *dev_maps,
+ bool is_rxqs_map)
+{
+ if (is_rxqs_map) {
+ static_key_slow_dec_cpuslocked(&xps_rxqs_needed);
+ RCU_INIT_POINTER(dev->xps_rxqs_map, NULL);
+ } else {
+ RCU_INIT_POINTER(dev->xps_cpus_map, NULL);
+ }
+ static_key_slow_dec_cpuslocked(&xps_needed);
+ kfree_rcu(dev_maps, rcu);
+}
+
static void clean_xps_maps(struct net_device *dev, const unsigned long *mask,
struct xps_dev_maps *dev_maps, unsigned int nr_ids,
u16 offset, u16 count, bool is_rxqs_map)
@@ -2186,18 +2200,15 @@ static void clean_xps_maps(struct net_device *dev, const unsigned long *mask,
j < nr_ids;)
active |= remove_xps_queue_cpu(dev, dev_maps, j, offset,
count);
- if (!active) {
- if (is_rxqs_map) {
- RCU_INIT_POINTER(dev->xps_rxqs_map, NULL);
- } else {
- RCU_INIT_POINTER(dev->xps_cpus_map, NULL);
+ if (!active)
+ reset_xps_maps(dev, dev_maps, is_rxqs_map);
- for (i = offset + (count - 1); count--; i--)
- netdev_queue_numa_node_write(
- netdev_get_tx_queue(dev, i),
- NUMA_NO_NODE);
+ if (!is_rxqs_map) {
+ for (i = offset + (count - 1); count--; i--) {
+ netdev_queue_numa_node_write(
+ netdev_get_tx_queue(dev, i),
+ NUMA_NO_NODE);
}
- kfree_rcu(dev_maps, rcu);
}
}
@@ -2234,10 +2245,6 @@ static void netif_reset_xps_queues(struct net_device *dev, u16 offset,
false);
out_no_maps:
- if (static_key_enabled(&xps_rxqs_needed))
- static_key_slow_dec_cpuslocked(&xps_rxqs_needed);
-
- static_key_slow_dec_cpuslocked(&xps_needed);
mutex_unlock(&xps_map_mutex);
cpus_read_unlock();
}
@@ -2355,9 +2362,12 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
if (!new_dev_maps)
goto out_no_new_maps;
- static_key_slow_inc_cpuslocked(&xps_needed);
- if (is_rxqs_map)
- static_key_slow_inc_cpuslocked(&xps_rxqs_needed);
+ if (!dev_maps) {
+ /* Increment static keys at most once per type */
+ static_key_slow_inc_cpuslocked(&xps_needed);
+ if (is_rxqs_map)
+ static_key_slow_inc_cpuslocked(&xps_rxqs_needed);
+ }
for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids),
j < nr_ids;) {
@@ -2455,13 +2465,8 @@ out_no_new_maps:
}
/* free map if not active */
- if (!active) {
- if (is_rxqs_map)
- RCU_INIT_POINTER(dev->xps_rxqs_map, NULL);
- else
- RCU_INIT_POINTER(dev->xps_cpus_map, NULL);
- kfree_rcu(dev_maps, rcu);
- }
+ if (!active)
+ reset_xps_maps(dev, dev_maps, is_rxqs_map);
out_no_maps:
mutex_unlock(&xps_map_mutex);
@@ -3272,7 +3277,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *de
}
skb = next;
- if (netif_xmit_stopped(txq) && skb) {
+ if (netif_tx_queue_stopped(txq) && skb) {
rc = NETDEV_TX_BUSY;
break;
}
@@ -5009,7 +5014,7 @@ static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemallo
struct net_device *orig_dev = skb->dev;
struct packet_type *pt_prev = NULL;
- list_del(&skb->list);
+ skb_list_del_init(skb);
__netif_receive_skb_core(skb, pfmemalloc, &pt_prev);
if (!pt_prev)
continue;
@@ -5165,7 +5170,7 @@ static void netif_receive_skb_list_internal(struct list_head *head)
INIT_LIST_HEAD(&sublist);
list_for_each_entry_safe(skb, next, head, list) {
net_timestamp_check(netdev_tstamp_prequeue, skb);
- list_del(&skb->list);
+ skb_list_del_init(skb);
if (!skb_defer_rx_timestamp(skb))
list_add_tail(&skb->list, &sublist);
}
@@ -5176,7 +5181,7 @@ static void netif_receive_skb_list_internal(struct list_head *head)
rcu_read_lock();
list_for_each_entry_safe(skb, next, head, list) {
xdp_prog = rcu_dereference(skb->dev->xdp_prog);
- list_del(&skb->list);
+ skb_list_del_init(skb);
if (do_xdp_generic(xdp_prog, skb) == XDP_PASS)
list_add_tail(&skb->list, &sublist);
}
@@ -5195,7 +5200,7 @@ static void netif_receive_skb_list_internal(struct list_head *head)
if (cpu >= 0) {
/* Will be handled, remove from list */
- list_del(&skb->list);
+ skb_list_del_init(skb);
enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
}
}
@@ -5655,6 +5660,10 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
skb->vlan_tci = 0;
skb->dev = napi->dev;
skb->skb_iif = 0;
+
+ /* eth_type_trans() assumes pkt_type is PACKET_HOST */
+ skb->pkt_type = PACKET_HOST;
+
skb->encapsulation = 0;
skb_shinfo(skb)->gso_type = 0;
skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
@@ -5966,11 +5975,14 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
if (work_done)
timeout = n->dev->gro_flush_timeout;
+ /* When the NAPI instance uses a timeout and keeps postponing
+ * it, we need to bound somehow the time packets are kept in
+ * the GRO layer
+ */
+ napi_gro_flush(n, !!timeout);
if (timeout)
hrtimer_start(&n->timer, ns_to_ktime(timeout),
HRTIMER_MODE_REL_PINNED);
- else
- napi_gro_flush(n, false);
}
if (unlikely(!list_empty(&n->poll_list))) {
/* If n->poll_list is not empty, we need to mask irqs */
@@ -6197,8 +6209,8 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
napi->skb = NULL;
napi->poll = poll;
if (weight > NAPI_POLL_WEIGHT)
- pr_err_once("netif_napi_add() called with weight %d on device %s\n",
- weight, dev->name);
+ netdev_err_once(dev, "%s() called with weight %d\n", __func__,
+ weight);
napi->weight = weight;
list_add(&napi->dev_list, &dev->napi_list);
napi->dev = dev;
diff --git a/net/core/filter.c b/net/core/filter.c
index e521c5ebc7d1..8d2c629501e2 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4852,18 +4852,17 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
} else {
struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr;
struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr;
- u16 hnum = ntohs(tuple->ipv6.dport);
int sdif = inet6_sdif(skb);
if (proto == IPPROTO_TCP)
sk = __inet6_lookup(net, &tcp_hashinfo, skb, 0,
src6, tuple->ipv6.sport,
- dst6, hnum,
+ dst6, ntohs(tuple->ipv6.dport),
dif, sdif, &refcounted);
else if (likely(ipv6_bpf_stub))
sk = ipv6_bpf_stub->udp6_lib_lookup(net,
src6, tuple->ipv6.sport,
- dst6, hnum,
+ dst6, tuple->ipv6.dport,
dif, sdif,
&udp_table, skb);
#endif
@@ -4891,22 +4890,23 @@ bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
struct net *net;
family = len == sizeof(tuple->ipv4) ? AF_INET : AF_INET6;
- if (unlikely(family == AF_UNSPEC || netns_id > U32_MAX || flags))
+ if (unlikely(family == AF_UNSPEC || flags ||
+ !((s32)netns_id < 0 || netns_id <= S32_MAX)))
goto out;
if (skb->dev)
caller_net = dev_net(skb->dev);
else
caller_net = sock_net(skb->sk);
- if (netns_id) {
+ if ((s32)netns_id < 0) {
+ net = caller_net;
+ sk = sk_lookup(net, tuple, skb, family, proto);
+ } else {
net = get_net_ns_by_id(caller_net, netns_id);
if (unlikely(!net))
goto out;
sk = sk_lookup(net, tuple, skb, family, proto);
put_net(net);
- } else {
- net = caller_net;
- sk = sk_lookup(net, tuple, skb, family, proto);
}
if (sk)
@@ -5436,8 +5436,8 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type
if (size != size_default)
return false;
break;
- case bpf_ctx_range(struct __sk_buff, flow_keys):
- if (size != sizeof(struct bpf_flow_keys *))
+ case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
+ if (size != sizeof(__u64))
return false;
break;
default:
@@ -5465,7 +5465,7 @@ static bool sk_filter_is_valid_access(int off, int size,
case bpf_ctx_range(struct __sk_buff, data):
case bpf_ctx_range(struct __sk_buff, data_meta):
case bpf_ctx_range(struct __sk_buff, data_end):
- case bpf_ctx_range(struct __sk_buff, flow_keys):
+ case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
case bpf_ctx_range_till(struct __sk_buff, family, local_port):
return false;
}
@@ -5490,7 +5490,7 @@ static bool cg_skb_is_valid_access(int off, int size,
switch (off) {
case bpf_ctx_range(struct __sk_buff, tc_classid):
case bpf_ctx_range(struct __sk_buff, data_meta):
- case bpf_ctx_range(struct __sk_buff, flow_keys):
+ case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
return false;
case bpf_ctx_range(struct __sk_buff, data):
case bpf_ctx_range(struct __sk_buff, data_end):
@@ -5531,7 +5531,7 @@ static bool lwt_is_valid_access(int off, int size,
case bpf_ctx_range(struct __sk_buff, tc_classid):
case bpf_ctx_range_till(struct __sk_buff, family, local_port):
case bpf_ctx_range(struct __sk_buff, data_meta):
- case bpf_ctx_range(struct __sk_buff, flow_keys):
+ case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
return false;
}
@@ -5757,7 +5757,7 @@ static bool tc_cls_act_is_valid_access(int off, int size,
case bpf_ctx_range(struct __sk_buff, data_end):
info->reg_type = PTR_TO_PACKET_END;
break;
- case bpf_ctx_range(struct __sk_buff, flow_keys):
+ case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
case bpf_ctx_range_till(struct __sk_buff, family, local_port):
return false;
}
@@ -5959,7 +5959,7 @@ static bool sk_skb_is_valid_access(int off, int size,
switch (off) {
case bpf_ctx_range(struct __sk_buff, tc_classid):
case bpf_ctx_range(struct __sk_buff, data_meta):
- case bpf_ctx_range(struct __sk_buff, flow_keys):
+ case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
return false;
}
@@ -6040,7 +6040,7 @@ static bool flow_dissector_is_valid_access(int off, int size,
case bpf_ctx_range(struct __sk_buff, data_end):
info->reg_type = PTR_TO_PACKET_END;
break;
- case bpf_ctx_range(struct __sk_buff, flow_keys):
+ case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
info->reg_type = PTR_TO_FLOW_KEYS;
break;
case bpf_ctx_range(struct __sk_buff, tc_classid):
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 676f3ad629f9..af68207ee56c 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -783,6 +783,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
/* Pass parameters to the BPF program */
cb->qdisc_cb.flow_keys = &flow_keys;
flow_keys.nhoff = nhoff;
+ flow_keys.thoff = nhoff;
bpf_compute_data_pointers((struct sk_buff *)skb);
result = BPF_PROG_RUN(attached, skb);
@@ -790,9 +791,12 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
/* Restore state */
memcpy(cb, &cb_saved, sizeof(cb_saved));
+ flow_keys.nhoff = clamp_t(u16, flow_keys.nhoff, 0, skb->len);
+ flow_keys.thoff = clamp_t(u16, flow_keys.thoff,
+ flow_keys.nhoff, skb->len);
+
__skb_flow_bpf_to_target(&flow_keys, flow_dissector,
target_container);
- key_control->thoff = min_t(u16, key_control->thoff, skb->len);
rcu_read_unlock();
return result == BPF_OK;
}
@@ -1166,8 +1170,8 @@ ip_proto_again:
break;
}
- if (dissector_uses_key(flow_dissector,
- FLOW_DISSECTOR_KEY_PORTS)) {
+ if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS) &&
+ !(key_control->flags & FLOW_DIS_IS_FRAGMENT)) {
key_ports = skb_flow_dissector_target(flow_dissector,
FLOW_DISSECTOR_KEY_PORTS,
target_container);
diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c
index 4b54e5f107c6..acf45ddbe924 100644
--- a/net/core/gro_cells.c
+++ b/net/core/gro_cells.c
@@ -84,6 +84,7 @@ void gro_cells_destroy(struct gro_cells *gcells)
for_each_possible_cpu(i) {
struct gro_cell *cell = per_cpu_ptr(gcells->cells, i);
+ napi_disable(&cell->napi);
netif_napi_del(&cell->napi);
__skb_queue_purge(&cell->napi_skbs);
}
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 41954e42a2de..5fa32c064baf 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2494,11 +2494,16 @@ static int neigh_valid_dump_req(const struct nlmsghdr *nlh,
ndm = nlmsg_data(nlh);
if (ndm->ndm_pad1 || ndm->ndm_pad2 || ndm->ndm_ifindex ||
- ndm->ndm_state || ndm->ndm_flags || ndm->ndm_type) {
+ ndm->ndm_state || ndm->ndm_type) {
NL_SET_ERR_MSG(extack, "Invalid values in header for neighbor dump request");
return -EINVAL;
}
+ if (ndm->ndm_flags & ~NTF_PROXY) {
+ NL_SET_ERR_MSG(extack, "Invalid flags in header for neighbor dump request");
+ return -EINVAL;
+ }
+
err = nlmsg_parse_strict(nlh, sizeof(struct ndmsg), tb, NDA_MAX,
NULL, extack);
} else {
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 5da9552b186b..2b9fdbc43205 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -717,7 +717,8 @@ int netpoll_setup(struct netpoll *np)
read_lock_bh(&idev->lock);
list_for_each_entry(ifp, &idev->addr_list, if_list) {
- if (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL)
+ if (!!(ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL) !=
+ !!(ipv6_addr_type(&np->remote_ip.in6) & IPV6_ADDR_LINKLOCAL))
continue;
np->local_ip.in6 = ifp->addr;
err = 0;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e01274bd5e3e..7819f7804eeb 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3367,7 +3367,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
cb->seq = 0;
}
ret = dumpit(skb, cb);
- if (ret < 0)
+ if (ret)
break;
}
cb->family = idx;
@@ -3800,6 +3800,9 @@ int ndo_dflt_fdb_dump(struct sk_buff *skb,
{
int err;
+ if (dev->type != ARPHRD_ETHER)
+ return -EINVAL;
+
netif_addr_lock_bh(dev);
err = nlmsg_populate_fdb(skb, cb, dev, idx, &dev->uc);
if (err)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 946de0e24c87..a8217e221e19 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4854,6 +4854,11 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
nf_reset(skb);
nf_reset_trace(skb);
+#ifdef CONFIG_NET_SWITCHDEV
+ skb->offload_fwd_mark = 0;
+ skb->offload_mr_fwd_mark = 0;
+#endif
+
if (!xnet)
return;
@@ -4944,6 +4949,8 @@ static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb)
*
* This is a helper to do that correctly considering GSO_BY_FRAGS.
*
+ * @skb: GSO skb
+ *
* @seg_len: The segmented length (from skb_gso_*_seglen). In the
* GSO_BY_FRAGS case this will be [header sizes + GSO_BY_FRAGS].
*
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 56a99d0c9aa0..b7dbb3c976cd 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -94,6 +94,9 @@ int sk_msg_clone(struct sock *sk, struct sk_msg *dst, struct sk_msg *src,
}
while (len) {
+ if (sk_msg_full(dst))
+ return -ENOSPC;
+
sge_len = sge->length - off;
sge_off = sge->offset + off;
if (sge_len > len)
diff --git a/net/core/sock.c b/net/core/sock.c
index 6fcc4bc07d19..080a880a1761 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3279,6 +3279,7 @@ int sock_load_diag_module(int family, int protocol)
#ifdef CONFIG_INET
if (family == AF_INET &&
+ protocol != IPPROTO_RAW &&
!rcu_access_pointer(inet_protos[protocol]))
return -ENOENT;
#endif
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 37b4667128a3..d67ec17f2cc8 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -28,6 +28,8 @@ static int two __maybe_unused = 2;
static int min_sndbuf = SOCK_MIN_SNDBUF;
static int min_rcvbuf = SOCK_MIN_RCVBUF;
static int max_skb_frags = MAX_SKB_FRAGS;
+static long long_one __maybe_unused = 1;
+static long long_max __maybe_unused = LONG_MAX;
static int net_msg_warn; /* Unused, but still a sysctl */
@@ -289,6 +291,17 @@ proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write,
return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
}
+
+static int
+proc_dolongvec_minmax_bpf_restricted(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ return proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
+}
#endif
static struct ctl_table net_core_table[] = {
@@ -398,10 +411,11 @@ static struct ctl_table net_core_table[] = {
{
.procname = "bpf_jit_limit",
.data = &bpf_jit_limit,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(long),
.mode = 0600,
- .proc_handler = proc_dointvec_minmax_bpf_restricted,
- .extra1 = &one,
+ .proc_handler = proc_dolongvec_minmax_bpf_restricted,
+ .extra1 = &long_one,
+ .extra2 = &long_max,
},
#endif
{
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.