aboutsummaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/Makefile1
-rw-r--r--net/core/dev.c18
-rw-r--r--net/core/drop_monitor.c2
-rw-r--r--net/core/filter.c77
-rw-r--r--net/core/gro.c9
-rw-r--r--net/core/lwt_bpf.c5
-rw-r--r--net/core/net-traces.c2
-rw-r--r--net/core/net_namespace.c13
-rw-r--r--net/core/netpoll.c2
-rw-r--r--net/core/rtnetlink.c74
-rw-r--r--net/core/rtnl_net_debug.c131
-rw-r--r--net/core/skbuff.c2
-rw-r--r--net/core/sock.c19
-rw-r--r--net/core/sock_map.c23
-rw-r--r--net/core/sysctl_net_core.c18
-rw-r--r--net/core/tso.c2
16 files changed, 313 insertions, 85 deletions
diff --git a/net/core/Makefile b/net/core/Makefile
index c3ebbaf9c81e..5a72a87ee0f1 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -45,3 +45,4 @@ obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o
obj-$(CONFIG_OF) += of_net.o
obj-$(CONFIG_NET_TEST) += net_test.o
obj-$(CONFIG_NET_DEVMEM) += devmem.o
+obj-$(CONFIG_DEBUG_NET_SMALL_RTNL) += rtnl_net_debug.o
diff --git a/net/core/dev.c b/net/core/dev.c
index 1e740faf9e78..ea5fbcd133ae 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3512,7 +3512,7 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb,
if (gso_segs > READ_ONCE(dev->gso_max_segs))
return features & ~NETIF_F_GSO_MASK;
- if (unlikely(skb->len >= READ_ONCE(dev->gso_max_size)))
+ if (unlikely(skb->len >= netif_get_gso_max_size(dev, skb)))
return features & ~NETIF_F_GSO_MASK;
if (!skb_shinfo(skb)->gso_type) {
@@ -3758,7 +3758,7 @@ static void qdisc_pkt_len_init(struct sk_buff *skb)
sizeof(_tcphdr), &_tcphdr);
if (likely(th))
hdr_len += __tcp_hdrlen(th);
- } else {
+ } else if (shinfo->gso_type & SKB_GSO_UDP_L4) {
struct udphdr _udphdr;
if (skb_header_pointer(skb, hdr_len,
@@ -3766,10 +3766,14 @@ static void qdisc_pkt_len_init(struct sk_buff *skb)
hdr_len += sizeof(struct udphdr);
}
- if (shinfo->gso_type & SKB_GSO_DODGY)
- gso_segs = DIV_ROUND_UP(skb->len - hdr_len,
- shinfo->gso_size);
+ if (unlikely(shinfo->gso_type & SKB_GSO_DODGY)) {
+ int payload = skb->len - hdr_len;
+ /* Malicious packet. */
+ if (payload <= 0)
+ return;
+ gso_segs = DIV_ROUND_UP(payload, shinfo->gso_size);
+ }
qdisc_skb_cb(skb)->pkt_len += (gso_segs - 1) * hdr_len;
}
}
@@ -5249,7 +5253,7 @@ int netif_rx(struct sk_buff *skb)
}
EXPORT_SYMBOL(netif_rx);
-static __latent_entropy void net_tx_action(struct softirq_action *h)
+static __latent_entropy void net_tx_action(void)
{
struct softnet_data *sd = this_cpu_ptr(&softnet_data);
@@ -6920,7 +6924,7 @@ static int napi_threaded_poll(void *data)
return 0;
}
-static __latent_entropy void net_rx_action(struct softirq_action *h)
+static __latent_entropy void net_rx_action(void)
{
struct softnet_data *sd = this_cpu_ptr(&softnet_data);
unsigned long time_limit = jiffies +
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 2e0ae3328232..6efd4cccc9dd 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -37,7 +37,7 @@
#include <trace/events/napi.h>
#include <trace/events/devlink.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#define TRACE_ON 1
#define TRACE_OFF 0
diff --git a/net/core/filter.c b/net/core/filter.c
index 0f4d9f3b206e..bd0d08bf76bb 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -42,7 +42,7 @@
#include <linux/errno.h>
#include <linux/timer.h>
#include <linux/uaccess.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <linux/filter.h>
#include <linux/ratelimit.h>
#include <linux/seccomp.h>
@@ -1266,8 +1266,8 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp)
* so we need to keep the user BPF around until the 2nd
* pass. At this time, the user BPF is stored in fp->insns.
*/
- old_prog = kmemdup(fp->insns, old_len * sizeof(struct sock_filter),
- GFP_KERNEL | __GFP_NOWARN);
+ old_prog = kmemdup_array(fp->insns, old_len, sizeof(struct sock_filter),
+ GFP_KERNEL | __GFP_NOWARN);
if (!old_prog) {
err = -ENOMEM;
goto out_err;
@@ -6280,20 +6280,25 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb,
int ret = BPF_MTU_CHK_RET_FRAG_NEEDED;
struct net_device *dev = skb->dev;
int skb_len, dev_len;
- int mtu;
+ int mtu = 0;
- if (unlikely(flags & ~(BPF_MTU_CHK_SEGS)))
- return -EINVAL;
+ if (unlikely(flags & ~(BPF_MTU_CHK_SEGS))) {
+ ret = -EINVAL;
+ goto out;
+ }
- if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len)))
- return -EINVAL;
+ if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len))) {
+ ret = -EINVAL;
+ goto out;
+ }
dev = __dev_via_ifindex(dev, ifindex);
- if (unlikely(!dev))
- return -ENODEV;
+ if (unlikely(!dev)) {
+ ret = -ENODEV;
+ goto out;
+ }
mtu = READ_ONCE(dev->mtu);
-
dev_len = mtu + dev->hard_header_len;
/* If set use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */
@@ -6311,15 +6316,12 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb,
*/
if (skb_is_gso(skb)) {
ret = BPF_MTU_CHK_RET_SUCCESS;
-
if (flags & BPF_MTU_CHK_SEGS &&
!skb_gso_validate_network_len(skb, mtu))
ret = BPF_MTU_CHK_RET_SEGS_TOOBIG;
}
out:
- /* BPF verifier guarantees valid pointer */
*mtu_len = mtu;
-
return ret;
}
@@ -6329,19 +6331,21 @@ BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp,
struct net_device *dev = xdp->rxq->dev;
int xdp_len = xdp->data_end - xdp->data;
int ret = BPF_MTU_CHK_RET_SUCCESS;
- int mtu, dev_len;
+ int mtu = 0, dev_len;
/* XDP variant doesn't support multi-buffer segment check (yet) */
- if (unlikely(flags))
- return -EINVAL;
+ if (unlikely(flags)) {
+ ret = -EINVAL;
+ goto out;
+ }
dev = __dev_via_ifindex(dev, ifindex);
- if (unlikely(!dev))
- return -ENODEV;
+ if (unlikely(!dev)) {
+ ret = -ENODEV;
+ goto out;
+ }
mtu = READ_ONCE(dev->mtu);
-
- /* Add L2-header as dev MTU is L3 size */
dev_len = mtu + dev->hard_header_len;
/* Use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */
@@ -6351,10 +6355,8 @@ BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp,
xdp_len += len_diff; /* minus result pass check */
if (xdp_len > dev_len)
ret = BPF_MTU_CHK_RET_FRAG_NEEDED;
-
- /* BPF verifier guarantees valid pointer */
+out:
*mtu_len = mtu;
-
return ret;
}
@@ -6364,7 +6366,8 @@ static const struct bpf_func_proto bpf_skb_check_mtu_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
- .arg3_type = ARG_PTR_TO_INT,
+ .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
+ .arg3_size = sizeof(u32),
.arg4_type = ARG_ANYTHING,
.arg5_type = ARG_ANYTHING,
};
@@ -6375,7 +6378,8 @@ static const struct bpf_func_proto bpf_xdp_check_mtu_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
.arg2_type = ARG_ANYTHING,
- .arg3_type = ARG_PTR_TO_INT,
+ .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
+ .arg3_size = sizeof(u32),
.arg4_type = ARG_ANYTHING,
.arg5_type = ARG_ANYTHING,
};
@@ -8597,13 +8601,16 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type
if (off + size > offsetofend(struct __sk_buff, cb[4]))
return false;
break;
+ 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):
+ if (info->is_ldsx || size != size_default)
+ return false;
+ break;
case bpf_ctx_range_till(struct __sk_buff, remote_ip6[0], remote_ip6[3]):
case bpf_ctx_range_till(struct __sk_buff, local_ip6[0], local_ip6[3]):
case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4):
case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4):
- 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):
if (size != size_default)
return false;
break;
@@ -9047,6 +9054,14 @@ static bool xdp_is_valid_access(int off, int size,
}
}
return false;
+ } else {
+ switch (off) {
+ case offsetof(struct xdp_md, data_meta):
+ case offsetof(struct xdp_md, data):
+ case offsetof(struct xdp_md, data_end):
+ if (info->is_ldsx)
+ return false;
+ }
}
switch (off) {
@@ -9372,12 +9387,12 @@ static bool flow_dissector_is_valid_access(int off, int size,
switch (off) {
case bpf_ctx_range(struct __sk_buff, data):
- if (size != size_default)
+ if (info->is_ldsx || size != size_default)
return false;
info->reg_type = PTR_TO_PACKET;
return true;
case bpf_ctx_range(struct __sk_buff, data_end):
- if (size != size_default)
+ if (info->is_ldsx || size != size_default)
return false;
info->reg_type = PTR_TO_PACKET_END;
return true;
diff --git a/net/core/gro.c b/net/core/gro.c
index 802b4a062400..d1f44084e978 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -98,7 +98,6 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
unsigned int headlen = skb_headlen(skb);
unsigned int len = skb_gro_len(skb);
unsigned int delta_truesize;
- unsigned int gro_max_size;
unsigned int new_truesize;
struct sk_buff *lp;
int segs;
@@ -112,12 +111,8 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
if (p->pp_recycle != skb->pp_recycle)
return -ETOOMANYREFS;
- /* pairs with WRITE_ONCE() in netif_set_gro(_ipv4)_max_size() */
- gro_max_size = p->protocol == htons(ETH_P_IPV6) ?
- READ_ONCE(p->dev->gro_max_size) :
- READ_ONCE(p->dev->gro_ipv4_max_size);
-
- if (unlikely(p->len + len >= gro_max_size || NAPI_GRO_CB(skb)->flush))
+ if (unlikely(p->len + len >= netif_get_gro_max_size(p->dev, p) ||
+ NAPI_GRO_CB(skb)->flush))
return -E2BIG;
if (unlikely(p->len + len >= GRO_LEGACY_MAX_SIZE)) {
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index 1a14f915b7a4..e0ca24a58810 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -10,6 +10,7 @@
#include <linux/bpf.h>
#include <net/lwtunnel.h>
#include <net/gre.h>
+#include <net/ip.h>
#include <net/ip6_route.h>
#include <net/ipv6_stubs.h>
#include <net/inet_dscp.h>
@@ -91,12 +92,12 @@ static int bpf_lwt_input_reroute(struct sk_buff *skb)
if (skb->protocol == htons(ETH_P_IP)) {
struct net_device *dev = skb_dst(skb)->dev;
- struct iphdr *iph = ip_hdr(skb);
+ const struct iphdr *iph = ip_hdr(skb);
dev_hold(dev);
skb_dst_drop(skb);
err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
- iph->tos, dev);
+ ip4h_dscp(iph), dev);
dev_put(dev);
} else if (skb->protocol == htons(ETH_P_IPV6)) {
skb_dst_drop(skb);
diff --git a/net/core/net-traces.c b/net/core/net-traces.c
index 6aef976bc1da..f2fa34b1d78d 100644
--- a/net/core/net-traces.c
+++ b/net/core/net-traces.c
@@ -23,7 +23,7 @@
#include <linux/net_dropmon.h>
#include <linux/slab.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <asm/bitops.h>
#define CREATE_TRACE_POINTS
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 11e4dd4f09ed..a5bc1fd8b034 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -317,6 +317,7 @@ static __net_init void preinit_net_sysctl(struct net *net)
*/
net->core.sysctl_optmem_max = 128 * 1024;
net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED;
+ net->core.sysctl_tstamp_allow_data = 1;
}
/* init code that must occur even if setup_net() is not called. */
@@ -334,6 +335,12 @@ static __net_init void preinit_net(struct net *net, struct user_namespace *user_
idr_init(&net->netns_ids);
spin_lock_init(&net->nsid_lock);
mutex_init(&net->ipv4.ra_mutex);
+
+#ifdef CONFIG_DEBUG_NET_SMALL_RTNL
+ mutex_init(&net->rtnl_mutex);
+ lock_set_cmp_fn(&net->rtnl_mutex, rtnl_net_lock_cmp_fn, NULL);
+#endif
+
preinit_net_sysctl(net);
}
@@ -697,11 +704,11 @@ struct net *get_net_ns_by_fd(int fd)
struct fd f = fdget(fd);
struct net *net = ERR_PTR(-EINVAL);
- if (!f.file)
+ if (!fd_file(f))
return ERR_PTR(-EBADF);
- if (proc_ns_file(f.file)) {
- struct ns_common *ns = get_proc_ns(file_inode(f.file));
+ if (proc_ns_file(fd_file(f))) {
+ struct ns_common *ns = get_proc_ns(file_inode(fd_file(f)));
if (ns->ops == &netns_operations)
net = get_net(container_of(ns, struct net, ns));
}
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index ca52cbe0f63c..aa49b92e9194 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -34,7 +34,7 @@
#include <net/addrconf.h>
#include <net/ndisc.h>
#include <net/ip6_checksum.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <trace/events/napi.h>
#include <linux/kconfig.h>
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index f0a520987085..6d68247aea70 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -179,6 +179,76 @@ bool lockdep_rtnl_is_held(void)
EXPORT_SYMBOL(lockdep_rtnl_is_held);
#endif /* #ifdef CONFIG_PROVE_LOCKING */
+#ifdef CONFIG_DEBUG_NET_SMALL_RTNL
+void __rtnl_net_lock(struct net *net)
+{
+ ASSERT_RTNL();
+
+ mutex_lock(&net->rtnl_mutex);
+}
+EXPORT_SYMBOL(__rtnl_net_lock);
+
+void __rtnl_net_unlock(struct net *net)
+{
+ ASSERT_RTNL();
+
+ mutex_unlock(&net->rtnl_mutex);
+}
+EXPORT_SYMBOL(__rtnl_net_unlock);
+
+void rtnl_net_lock(struct net *net)
+{
+ rtnl_lock();
+ __rtnl_net_lock(net);
+}
+EXPORT_SYMBOL(rtnl_net_lock);
+
+void rtnl_net_unlock(struct net *net)
+{
+ __rtnl_net_unlock(net);
+ rtnl_unlock();
+}
+EXPORT_SYMBOL(rtnl_net_unlock);
+
+static int rtnl_net_cmp_locks(const struct net *net_a, const struct net *net_b)
+{
+ if (net_eq(net_a, net_b))
+ return 0;
+
+ /* always init_net first */
+ if (net_eq(net_a, &init_net))
+ return -1;
+
+ if (net_eq(net_b, &init_net))
+ return 1;
+
+ /* otherwise lock in ascending order */
+ return net_a < net_b ? -1 : 1;
+}
+
+int rtnl_net_lock_cmp_fn(const struct lockdep_map *a, const struct lockdep_map *b)
+{
+ const struct net *net_a, *net_b;
+
+ net_a = container_of(a, struct net, rtnl_mutex.dep_map);
+ net_b = container_of(b, struct net, rtnl_mutex.dep_map);
+
+ return rtnl_net_cmp_locks(net_a, net_b);
+}
+
+bool rtnl_net_is_locked(struct net *net)
+{
+ return rtnl_is_locked() && mutex_is_locked(&net->rtnl_mutex);
+}
+EXPORT_SYMBOL(rtnl_net_is_locked);
+
+bool lockdep_rtnl_net_is_held(struct net *net)
+{
+ return lockdep_rtnl_is_held() && lockdep_is_held(&net->rtnl_mutex);
+}
+EXPORT_SYMBOL(lockdep_rtnl_net_is_held);
+#endif
+
static struct rtnl_link __rcu *__rcu *rtnl_msg_handlers[RTNL_FAMILY_MAX + 1];
static inline int rtm_msgindex(int msgtype)
@@ -1118,6 +1188,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
+ nla_total_size(MAX_ADDR_LEN) /* IFLA_PERM_ADDRESS */
+ rtnl_devlink_port_size(dev)
+ rtnl_dpll_pin_size(dev)
+ + nla_total_size(8) /* IFLA_MAX_PACING_OFFLOAD_HORIZON */
+ 0;
}
@@ -1867,6 +1938,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
READ_ONCE(dev->tso_max_size)) ||
nla_put_u32(skb, IFLA_TSO_MAX_SEGS,
READ_ONCE(dev->tso_max_segs)) ||
+ nla_put_uint(skb, IFLA_MAX_PACING_OFFLOAD_HORIZON,
+ READ_ONCE(dev->max_pacing_offload_horizon)) ||
#ifdef CONFIG_RPS
nla_put_u32(skb, IFLA_NUM_RX_QUEUES,
READ_ONCE(dev->num_rx_queues)) ||
@@ -1975,6 +2048,7 @@ nla_put_failure:
}
static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
+ [IFLA_UNSPEC] = { .strict_start_type = IFLA_DPLL_PIN },
[IFLA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ-1 },
[IFLA_ADDRESS] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
[IFLA_BROADCAST] = { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
diff --git a/net/core/rtnl_net_debug.c b/net/core/rtnl_net_debug.c
new file mode 100644
index 000000000000..e90a32242e22
--- /dev/null
+++ b/net/core/rtnl_net_debug.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Copyright Amazon.com Inc. or its affiliates. */
+
+#include <linux/init.h>
+#include <linux/netdevice.h>
+#include <linux/notifier.h>
+#include <linux/rtnetlink.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+
+static int rtnl_net_debug_event(struct notifier_block *nb,
+ unsigned long event, void *ptr)
+{
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct net *net = dev_net(dev);
+ enum netdev_cmd cmd = event;
+
+ /* Keep enum and don't add default to trigger -Werror=switch */
+ switch (cmd) {
+ case NETDEV_UP:
+ case NETDEV_DOWN:
+ case NETDEV_REBOOT:
+ case NETDEV_CHANGE:
+ case NETDEV_REGISTER:
+ case NETDEV_UNREGISTER:
+ case NETDEV_CHANGEMTU:
+ case NETDEV_CHANGEADDR:
+ case NETDEV_PRE_CHANGEADDR:
+ case NETDEV_GOING_DOWN:
+ case NETDEV_CHANGENAME:
+ case NETDEV_FEAT_CHANGE:
+ case NETDEV_BONDING_FAILOVER:
+ case NETDEV_PRE_UP:
+ case NETDEV_PRE_TYPE_CHANGE:
+ case NETDEV_POST_TYPE_CHANGE:
+ case NETDEV_POST_INIT:
+ case NETDEV_PRE_UNINIT:
+ case NETDEV_RELEASE:
+ case NETDEV_NOTIFY_PEERS:
+ case NETDEV_JOIN:
+ case NETDEV_CHANGEUPPER:
+ case NETDEV_RESEND_IGMP:
+ case NETDEV_PRECHANGEMTU:
+ case NETDEV_CHANGEINFODATA:
+ case NETDEV_BONDING_INFO:
+ case NETDEV_PRECHANGEUPPER:
+ case NETDEV_CHANGELOWERSTATE:
+ case NETDEV_UDP_TUNNEL_PUSH_INFO:
+ case NETDEV_UDP_TUNNEL_DROP_INFO:
+ case NETDEV_CHANGE_TX_QUEUE_LEN:
+ case NETDEV_CVLAN_FILTER_PUSH_INFO:
+ case NETDEV_CVLAN_FILTER_DROP_INFO:
+ case NETDEV_SVLAN_FILTER_PUSH_INFO:
+ case NETDEV_SVLAN_FILTER_DROP_INFO:
+ case NETDEV_OFFLOAD_XSTATS_ENABLE:
+ case NETDEV_OFFLOAD_XSTATS_DISABLE:
+ case NETDEV_OFFLOAD_XSTATS_REPORT_USED:
+ case NETDEV_OFFLOAD_XSTATS_REPORT_DELTA:
+ case NETDEV_XDP_FEAT_CHANGE:
+ ASSERT_RTNL();
+ break;
+
+ /* Once an event fully supports RTNL_NET, move it here
+ * and remove "if (0)" below.
+ *
+ * case NETDEV_XXX:
+ * ASSERT_RTNL_NET(net);
+ * break;
+ */
+ }
+
+ /* Just to avoid unused-variable error for dev and net. */
+ if (0)
+ ASSERT_RTNL_NET(net);
+
+ return NOTIFY_DONE;
+}
+
+static int rtnl_net_debug_net_id;
+
+static int __net_init rtnl_net_debug_net_init(struct net *net)
+{
+ struct notifier_block *nb;
+
+ nb = net_generic(net, rtnl_net_debug_net_id);
+ nb->notifier_call = rtnl_net_debug_event;
+
+ return register_netdevice_notifier_net(net, nb);
+}
+
+static void __net_exit rtnl_net_debug_net_exit(struct net *net)
+{
+ struct notifier_block *nb;
+
+ nb = net_generic(net, rtnl_net_debug_net_id);
+ unregister_netdevice_notifier_net(net, nb);
+}
+
+static struct pernet_operations rtnl_net_debug_net_ops __net_initdata = {
+ .init = rtnl_net_debug_net_init,
+ .exit = rtnl_net_debug_net_exit,
+ .id = &rtnl_net_debug_net_id,
+ .size = sizeof(struct notifier_block),
+};
+
+static struct notifier_block rtnl_net_debug_block = {
+ .notifier_call = rtnl_net_debug_event,
+};
+
+static int __init rtnl_net_debug_init(void)
+{
+ int ret;
+
+ ret = register_pernet_device(&rtnl_net_debug_net_ops);
+ if (ret)
+ return ret;
+
+ ret = register_netdevice_notifier(&rtnl_net_debug_block);
+ if (ret)
+ unregister_pernet_subsys(&rtnl_net_debug_net_ops);
+
+ return ret;
+}
+
+static void __exit rtnl_net_debug_exit(void)
+{
+ unregister_netdevice_notifier(&rtnl_net_debug_block);
+ unregister_pernet_device(&rtnl_net_debug_net_ops);
+}
+
+subsys_initcall(rtnl_net_debug_init);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 74149dc4ee31..00afeb90c23a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5506,7 +5506,7 @@ static bool skb_may_tx_timestamp(struct sock *sk, bool tsonly)
{
bool ret;
- if (likely(READ_ONCE(sysctl_tstamp_allow_data) || tsonly))
+ if (likely(tsonly || READ_ONCE(sock_net(sk)->core.sysctl_tstamp_allow_data)))
return true;
read_lock_bh(&sk->sk_callback_lock);
diff --git a/net/core/sock.c b/net/core/sock.c
index bbb57b5af0b1..083d438d8b6f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -85,7 +85,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/errqueue.h>
@@ -286,8 +286,6 @@ EXPORT_SYMBOL(sysctl_rmem_max);
__u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX;
__u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
-int sysctl_tstamp_allow_data __read_mostly = 1;
-
DEFINE_STATIC_KEY_FALSE(memalloc_socks_key);
EXPORT_SYMBOL_GPL(memalloc_socks_key);
@@ -2899,6 +2897,8 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg,
{
u32 tsflags;
+ BUILD_BUG_ON(SOF_TIMESTAMPING_LAST == (1 << 31));
+
switch (cmsg->cmsg_type) {
case SO_MARK:
if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) &&
@@ -2927,6 +2927,17 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg,
return -EINVAL;
sockc->transmit_time = get_unaligned((u64 *)CMSG_DATA(cmsg));
break;
+ case SCM_TS_OPT_ID:
+ if (sk_is_tcp(sk))
+ return -EINVAL;
+ tsflags = READ_ONCE(sk->sk_tsflags);
+ if (!(tsflags & SOF_TIMESTAMPING_OPT_ID))
+ return -EINVAL;
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
+ return -EINVAL;
+ sockc->ts_opt_id = *(u32 *)CMSG_DATA(cmsg);
+ sockc->tsflags |= SOCKCM_FLAG_TS_OPT_ID;
+ break;
/* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */
case SCM_RIGHTS:
case SCM_CREDENTIALS:
@@ -3497,7 +3508,7 @@ static void sock_def_destruct(struct sock *sk)
void sk_send_sigurg(struct sock *sk)
{
if (sk->sk_socket && sk->sk_socket->file)
- if (send_sigurg(&sk->sk_socket->file->f_owner))
+ if (send_sigurg(sk->sk_socket->file))
sk_wake_async(sk, SOCK_WAKE_URG, POLL_PRI);
}
EXPORT_SYMBOL(sk_send_sigurg);
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 724b6856fcc3..242c91a6e3d3 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -67,46 +67,39 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog)
{
- u32 ufd = attr->target_fd;
struct bpf_map *map;
- struct fd f;
int ret;
if (attr->attach_flags || attr->replace_bpf_fd)
return -EINVAL;
- f = fdget(ufd);
+ CLASS(fd, f)(attr->target_fd);
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
mutex_lock(&sockmap_mutex);
ret = sock_map_prog_update(map, prog, NULL, NULL, attr->attach_type);
mutex_unlock(&sockmap_mutex);
- fdput(f);
return ret;
}
int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
{
- u32 ufd = attr->target_fd;
struct bpf_prog *prog;
struct bpf_map *map;
- struct fd f;
int ret;
if (attr->attach_flags || attr->replace_bpf_fd)
return -EINVAL;
- f = fdget(ufd);
+ CLASS(fd, f)(attr->target_fd);
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
prog = bpf_prog_get(attr->attach_bpf_fd);
- if (IS_ERR(prog)) {
- ret = PTR_ERR(prog);
- goto put_map;
- }
+ if (IS_ERR(prog))
+ return PTR_ERR(prog);
if (prog->type != ptype) {
ret = -EINVAL;
@@ -118,8 +111,6 @@ int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
mutex_unlock(&sockmap_mutex);
put_prog:
bpf_prog_put(prog);
-put_map:
- fdput(f);
return ret;
}
@@ -1551,18 +1542,17 @@ int sock_map_bpf_prog_query(const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
__u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
- u32 prog_cnt = 0, flags = 0, ufd = attr->target_fd;
+ u32 prog_cnt = 0, flags = 0;
struct bpf_prog **pprog;
struct bpf_prog *prog;
struct bpf_map *map;
- struct fd f;
u32 id = 0;
int ret;
if (attr->query.query_flags)
return -EINVAL;
- f = fdget(ufd);
+ CLASS(fd, f)(attr->target_fd);
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
@@ -1594,7 +1584,6 @@ end:
copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt)))
ret = -EFAULT;
- fdput(f);
return ret;
}
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 86a2476678c4..b60fac380cec 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -491,15 +491,6 @@ static struct ctl_table net_core_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
- {
- .procname = "tstamp_allow_data",
- .data = &sysctl_tstamp_allow_data,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec_minmax,
- .extra1 = SYSCTL_ZERO,
- .extra2 = SYSCTL_ONE
- },
#ifdef CONFIG_RPS
{
.procname = "rps_sock_flow_entries",
@@ -665,6 +656,15 @@ static struct ctl_table netns_core_table[] = {
.extra2 = SYSCTL_ONE,
.proc_handler = proc_dou8vec_minmax,
},
+ {
+ .procname = "tstamp_allow_data",
+ .data = &init_net.core.sysctl_tstamp_allow_data,
+ .maxlen = sizeof(u8),
+ .mode = 0644,
+ .proc_handler = proc_dou8vec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE
+ },
/* sysctl_core_net_init() will set the values after this
* to readonly in network namespaces
*/
diff --git a/net/core/tso.c b/net/core/tso.c
index e00796e3b146..6df997b9076e 100644
--- a/net/core/tso.c
+++ b/net/core/tso.c
@@ -3,7 +3,7 @@
#include <linux/if_vlan.h>
#include <net/ip.h>
#include <net/tso.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
void tso_build_hdr(const struct sk_buff *skb, char *hdr, struct tso_t *tso,
int size, bool is_last)
Powered by cgit, Gruvboxed by Blaster4385.