summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/dev.c11
-rw-r--r--net/core/dev_addr_lists.c10
-rw-r--r--net/core/drop_monitor.c1
-rw-r--r--net/core/filter.c10
-rw-r--r--net/core/flow_dissector.c32
-rw-r--r--net/core/flow_offload.c48
-rw-r--r--net/core/net-sysfs.c2
-rw-r--r--net/core/rtnetlink.c3
-rw-r--r--net/core/skmsg.c23
-rw-r--r--net/core/sock.c6
-rw-r--r--net/core/sock_map.c53
-rw-r--r--net/core/sock_reuseport.c1
-rw-r--r--net/core/sysctl_net_core.c2
-rw-r--r--net/core/xdp.c1
14 files changed, 140 insertions, 63 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index 6bc2388141f6..7a774ebf64e2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4192,10 +4192,12 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
local_bh_disable();
+ dev_xmit_recursion_inc();
HARD_TX_LOCK(dev, txq, smp_processor_id());
if (!netif_xmit_frozen_or_drv_stopped(txq))
ret = netdev_start_xmit(skb, dev, txq, false);
HARD_TX_UNLOCK(dev, txq);
+ dev_xmit_recursion_dec();
local_bh_enable();
@@ -5599,7 +5601,7 @@ static void flush_backlog(struct work_struct *work)
skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
if (skb->dev->reg_state == NETREG_UNREGISTERING) {
__skb_unlink(skb, &sd->input_pkt_queue);
- kfree_skb(skb);
+ dev_kfree_skb_irq(skb);
input_queue_head_incr(sd);
}
}
@@ -9547,6 +9549,13 @@ int register_netdevice(struct net_device *dev)
rcu_barrier();
dev->reg_state = NETREG_UNREGISTERED;
+ /* We should put the kobject that hold in
+ * netdev_unregister_kobject(), otherwise
+ * the net device cannot be freed when
+ * driver calls free_netdev(), because the
+ * kobject is being hold.
+ */
+ kobject_put(&dev->dev.kobj);
}
/*
* Prevent userspace races by waiting until the network
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index 6393ba930097..54cd568e7c2f 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -690,6 +690,15 @@ void dev_uc_unsync(struct net_device *to, struct net_device *from)
if (to->addr_len != from->addr_len)
return;
+ /* netif_addr_lock_bh() uses lockdep subclass 0, this is okay for two
+ * reasons:
+ * 1) This is always called without any addr_list_lock, so as the
+ * outermost one here, it must be 0.
+ * 2) This is called by some callers after unlinking the upper device,
+ * so the dev->lower_level becomes 1 again.
+ * Therefore, the subclass for 'from' is 0, for 'to' is either 1 or
+ * larger.
+ */
netif_addr_lock_bh(from);
netif_addr_lock_nested(to);
__hw_addr_unsync(&to->uc, &from->uc, to->addr_len);
@@ -911,6 +920,7 @@ void dev_mc_unsync(struct net_device *to, struct net_device *from)
if (to->addr_len != from->addr_len)
return;
+ /* See the above comments inside dev_uc_unsync(). */
netif_addr_lock_bh(from);
netif_addr_lock_nested(to);
__hw_addr_unsync(&to->mc, &from->mc, to->addr_len);
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 2ee7bc4c9e03..b09bebeadf0b 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -1721,3 +1721,4 @@ module_exit(exit_net_drop_monitor);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Neil Horman <nhorman@tuxdriver.com>");
MODULE_ALIAS_GENL_FAMILY("NET_DM");
+MODULE_DESCRIPTION("Monitoring code for network dropped packet alerts");
diff --git a/net/core/filter.c b/net/core/filter.c
index 73395384afe2..82e1b5b06167 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5853,12 +5853,16 @@ BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb)
{
unsigned int iphdr_len;
- if (skb->protocol == cpu_to_be16(ETH_P_IP))
+ switch (skb_protocol(skb, true)) {
+ case cpu_to_be16(ETH_P_IP):
iphdr_len = sizeof(struct iphdr);
- else if (skb->protocol == cpu_to_be16(ETH_P_IPV6))
+ break;
+ case cpu_to_be16(ETH_P_IPV6):
iphdr_len = sizeof(struct ipv6hdr);
- else
+ break;
+ default:
return 0;
+ }
if (skb_headlen(skb) < iphdr_len)
return 0;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index d02df0b6d0d9..142a8824f0a8 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -70,10 +70,10 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
EXPORT_SYMBOL(skb_flow_dissector_init);
#ifdef CONFIG_BPF_SYSCALL
-int flow_dissector_bpf_prog_attach(struct net *net, struct bpf_prog *prog)
+int flow_dissector_bpf_prog_attach_check(struct net *net,
+ struct bpf_prog *prog)
{
enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR;
- struct bpf_prog *attached;
if (net == &init_net) {
/* BPF flow dissector in the root namespace overrides
@@ -86,26 +86,17 @@ int flow_dissector_bpf_prog_attach(struct net *net, struct bpf_prog *prog)
for_each_net(ns) {
if (ns == &init_net)
continue;
- if (rcu_access_pointer(ns->bpf.progs[type]))
+ if (rcu_access_pointer(ns->bpf.run_array[type]))
return -EEXIST;
}
} else {
/* Make sure root flow dissector is not attached
* when attaching to the non-root namespace.
*/
- if (rcu_access_pointer(init_net.bpf.progs[type]))
+ if (rcu_access_pointer(init_net.bpf.run_array[type]))
return -EEXIST;
}
- attached = rcu_dereference_protected(net->bpf.progs[type],
- lockdep_is_held(&netns_bpf_mutex));
- if (attached == prog)
- /* The same program cannot be attached twice */
- return -EINVAL;
-
- rcu_assign_pointer(net->bpf.progs[type], prog);
- if (attached)
- bpf_prog_put(attached);
return 0;
}
#endif /* CONFIG_BPF_SYSCALL */
@@ -903,7 +894,6 @@ bool __skb_flow_dissect(const struct net *net,
struct flow_dissector_key_addrs *key_addrs;
struct flow_dissector_key_tags *key_tags;
struct flow_dissector_key_vlan *key_vlan;
- struct bpf_prog *attached = NULL;
enum flow_dissect_ret fdret;
enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX;
bool mpls_el = false;
@@ -960,14 +950,14 @@ bool __skb_flow_dissect(const struct net *net,
WARN_ON_ONCE(!net);
if (net) {
enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR;
+ struct bpf_prog_array *run_array;
rcu_read_lock();
- attached = rcu_dereference(init_net.bpf.progs[type]);
-
- if (!attached)
- attached = rcu_dereference(net->bpf.progs[type]);
+ run_array = rcu_dereference(init_net.bpf.run_array[type]);
+ if (!run_array)
+ run_array = rcu_dereference(net->bpf.run_array[type]);
- if (attached) {
+ if (run_array) {
struct bpf_flow_keys flow_keys;
struct bpf_flow_dissector ctx = {
.flow_keys = &flow_keys,
@@ -975,6 +965,7 @@ bool __skb_flow_dissect(const struct net *net,
.data_end = data + hlen,
};
__be16 n_proto = proto;
+ struct bpf_prog *prog;
if (skb) {
ctx.skb = skb;
@@ -985,7 +976,8 @@ bool __skb_flow_dissect(const struct net *net,
n_proto = skb->protocol;
}
- ret = bpf_flow_dissect(attached, &ctx, n_proto, nhoff,
+ prog = READ_ONCE(run_array->items[0].prog);
+ ret = bpf_flow_dissect(prog, &ctx, n_proto, nhoff,
hlen, flags);
__skb_flow_bpf_to_target(&flow_keys, flow_dissector,
target_container);
diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c
index 0cfc35e6be28..2076219b8ba5 100644
--- a/net/core/flow_offload.c
+++ b/net/core/flow_offload.c
@@ -4,6 +4,7 @@
#include <net/flow_offload.h>
#include <linux/rtnetlink.h>
#include <linux/mutex.h>
+#include <linux/rhashtable.h>
struct flow_rule *flow_rule_alloc(unsigned int num_actions)
{
@@ -372,14 +373,15 @@ int flow_indr_dev_register(flow_indr_block_bind_cb_t *cb, void *cb_priv)
}
EXPORT_SYMBOL(flow_indr_dev_register);
-static void __flow_block_indr_cleanup(flow_setup_cb_t *setup_cb, void *cb_priv,
+static void __flow_block_indr_cleanup(void (*release)(void *cb_priv),
+ void *cb_priv,
struct list_head *cleanup_list)
{
struct flow_block_cb *this, *next;
list_for_each_entry_safe(this, next, &flow_block_indr_list, indr.list) {
- if (this->cb == setup_cb &&
- this->cb_priv == cb_priv) {
+ if (this->release == release &&
+ this->indr.cb_priv == cb_priv) {
list_move(&this->indr.list, cleanup_list);
return;
}
@@ -397,7 +399,7 @@ static void flow_block_indr_notify(struct list_head *cleanup_list)
}
void flow_indr_dev_unregister(flow_indr_block_bind_cb_t *cb, void *cb_priv,
- flow_setup_cb_t *setup_cb)
+ void (*release)(void *cb_priv))
{
struct flow_indr_dev *this, *next, *indr_dev = NULL;
LIST_HEAD(cleanup_list);
@@ -418,7 +420,7 @@ void flow_indr_dev_unregister(flow_indr_block_bind_cb_t *cb, void *cb_priv,
return;
}
- __flow_block_indr_cleanup(setup_cb, cb_priv, &cleanup_list);
+ __flow_block_indr_cleanup(release, cb_priv, &cleanup_list);
mutex_unlock(&flow_indr_block_lock);
flow_block_indr_notify(&cleanup_list);
@@ -429,32 +431,37 @@ EXPORT_SYMBOL(flow_indr_dev_unregister);
static void flow_block_indr_init(struct flow_block_cb *flow_block,
struct flow_block_offload *bo,
struct net_device *dev, void *data,
+ void *cb_priv,
void (*cleanup)(struct flow_block_cb *block_cb))
{
flow_block->indr.binder_type = bo->binder_type;
flow_block->indr.data = data;
+ flow_block->indr.cb_priv = cb_priv;
flow_block->indr.dev = dev;
flow_block->indr.cleanup = cleanup;
}
-static void __flow_block_indr_binding(struct flow_block_offload *bo,
- struct net_device *dev, void *data,
- void (*cleanup)(struct flow_block_cb *block_cb))
+struct flow_block_cb *flow_indr_block_cb_alloc(flow_setup_cb_t *cb,
+ void *cb_ident, void *cb_priv,
+ void (*release)(void *cb_priv),
+ struct flow_block_offload *bo,
+ struct net_device *dev, void *data,
+ void *indr_cb_priv,
+ void (*cleanup)(struct flow_block_cb *block_cb))
{
struct flow_block_cb *block_cb;
- list_for_each_entry(block_cb, &bo->cb_list, list) {
- switch (bo->command) {
- case FLOW_BLOCK_BIND:
- flow_block_indr_init(block_cb, bo, dev, data, cleanup);
- list_add(&block_cb->indr.list, &flow_block_indr_list);
- break;
- case FLOW_BLOCK_UNBIND:
- list_del(&block_cb->indr.list);
- break;
- }
- }
+ block_cb = flow_block_cb_alloc(cb, cb_ident, cb_priv, release);
+ if (IS_ERR(block_cb))
+ goto out;
+
+ flow_block_indr_init(block_cb, bo, dev, data, indr_cb_priv, cleanup);
+ list_add(&block_cb->indr.list, &flow_block_indr_list);
+
+out:
+ return block_cb;
}
+EXPORT_SYMBOL(flow_indr_block_cb_alloc);
int flow_indr_dev_setup_offload(struct net_device *dev,
enum tc_setup_type type, void *data,
@@ -465,9 +472,8 @@ int flow_indr_dev_setup_offload(struct net_device *dev,
mutex_lock(&flow_indr_block_lock);
list_for_each_entry(this, &flow_block_indr_dev_list, list)
- this->cb(dev, this->cb_priv, type, bo);
+ this->cb(dev, this->cb_priv, type, bo, data, cleanup);
- __flow_block_indr_binding(bo, dev, data, cleanup);
mutex_unlock(&flow_indr_block_lock);
return list_empty(&bo->cb_list) ? -EOPNOTSUPP : 0;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index e353b822bb15..7bd6440c63bf 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1108,7 +1108,7 @@ static ssize_t tx_timeout_show(struct netdev_queue *queue, char *buf)
trans_timeout = queue->trans_timeout;
spin_unlock_irq(&queue->_xmit_lock);
- return sprintf(buf, "%lu", trans_timeout);
+ return sprintf(buf, fmt_ulong, trans_timeout);
}
static unsigned int get_netdev_queue_index(struct netdev_queue *queue)
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 9aedc15736ad..85a4b0101f76 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3343,7 +3343,8 @@ replay:
*/
if (err < 0) {
/* If device is not registered at all, free it now */
- if (dev->reg_state == NETREG_UNINITIALIZED)
+ if (dev->reg_state == NETREG_UNINITIALIZED ||
+ dev->reg_state == NETREG_UNREGISTERED)
free_netdev(dev);
goto out;
}
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 351afbf6bfba..6a32a1fd34f8 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -683,7 +683,7 @@ static struct sk_psock *sk_psock_from_strp(struct strparser *strp)
return container_of(parser, struct sk_psock, parser);
}
-static void sk_psock_skb_redirect(struct sk_psock *psock, struct sk_buff *skb)
+static void sk_psock_skb_redirect(struct sk_buff *skb)
{
struct sk_psock *psock_other;
struct sock *sk_other;
@@ -715,12 +715,11 @@ static void sk_psock_skb_redirect(struct sk_psock *psock, struct sk_buff *skb)
}
}
-static void sk_psock_tls_verdict_apply(struct sk_psock *psock,
- struct sk_buff *skb, int verdict)
+static void sk_psock_tls_verdict_apply(struct sk_buff *skb, int verdict)
{
switch (verdict) {
case __SK_REDIRECT:
- sk_psock_skb_redirect(psock, skb);
+ sk_psock_skb_redirect(skb);
break;
case __SK_PASS:
case __SK_DROP:
@@ -741,8 +740,8 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb)
ret = sk_psock_bpf_run(psock, prog, skb);
ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
}
+ sk_psock_tls_verdict_apply(skb, ret);
rcu_read_unlock();
- sk_psock_tls_verdict_apply(psock, skb, ret);
return ret;
}
EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read);
@@ -770,7 +769,7 @@ static void sk_psock_verdict_apply(struct sk_psock *psock,
}
goto out_free;
case __SK_REDIRECT:
- sk_psock_skb_redirect(psock, skb);
+ sk_psock_skb_redirect(skb);
break;
case __SK_DROP:
/* fall-through */
@@ -782,11 +781,18 @@ out_free:
static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
{
- struct sk_psock *psock = sk_psock_from_strp(strp);
+ struct sk_psock *psock;
struct bpf_prog *prog;
int ret = __SK_DROP;
+ struct sock *sk;
rcu_read_lock();
+ sk = strp->sk;
+ psock = sk_psock(sk);
+ if (unlikely(!psock)) {
+ kfree_skb(skb);
+ goto out;
+ }
prog = READ_ONCE(psock->progs.skb_verdict);
if (likely(prog)) {
skb_orphan(skb);
@@ -794,8 +800,9 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
ret = sk_psock_bpf_run(psock, prog, skb);
ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
}
- rcu_read_unlock();
sk_psock_verdict_apply(psock, skb, ret);
+out:
+ rcu_read_unlock();
}
static int sk_psock_strp_read_done(struct strparser *strp, int err)
diff --git a/net/core/sock.c b/net/core/sock.c
index 6c4acf1f0220..2e5b7870e5d3 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -718,7 +718,7 @@ bool sk_mc_loop(struct sock *sk)
return inet6_sk(sk)->mc_loop;
#endif
}
- WARN_ON(1);
+ WARN_ON_ONCE(1);
return true;
}
EXPORT_SYMBOL(sk_mc_loop);
@@ -1767,6 +1767,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
cgroup_sk_alloc(&sk->sk_cgrp_data);
sock_update_classid(&sk->sk_cgrp_data);
sock_update_netprioidx(&sk->sk_cgrp_data);
+ sk_tx_queue_clear(sk);
}
return sk;
@@ -1925,7 +1926,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
/* sk->sk_memcg will be populated at accept() time */
newsk->sk_memcg = NULL;
- cgroup_sk_alloc(&newsk->sk_cgrp_data);
+ cgroup_sk_clone(&newsk->sk_cgrp_data);
rcu_read_lock();
filter = rcu_dereference(sk->sk_filter);
@@ -1990,6 +1991,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
*/
sk_refcnt_debug_inc(newsk);
sk_set_socket(newsk, NULL);
+ sk_tx_queue_clear(newsk);
RCU_INIT_POINTER(newsk->sk_wq, NULL);
if (newsk->sk_prot->sockets_allocated)
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 4059f94e9bb5..0971f17e8e54 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -70,11 +70,49 @@ int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog)
struct fd f;
int ret;
+ if (attr->attach_flags || attr->replace_bpf_fd)
+ return -EINVAL;
+
f = fdget(ufd);
map = __bpf_map_get(f);
if (IS_ERR(map))
return PTR_ERR(map);
- ret = sock_map_prog_update(map, prog, attr->attach_type);
+ ret = sock_map_prog_update(map, prog, NULL, attr->attach_type);
+ 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);
+ 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 (prog->type != ptype) {
+ ret = -EINVAL;
+ goto put_prog;
+ }
+
+ ret = sock_map_prog_update(map, NULL, prog, attr->attach_type);
+put_prog:
+ bpf_prog_put(prog);
+put_map:
fdput(f);
return ret;
}
@@ -1203,27 +1241,32 @@ static struct sk_psock_progs *sock_map_progs(struct bpf_map *map)
}
int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
- u32 which)
+ struct bpf_prog *old, u32 which)
{
struct sk_psock_progs *progs = sock_map_progs(map);
+ struct bpf_prog **pprog;
if (!progs)
return -EOPNOTSUPP;
switch (which) {
case BPF_SK_MSG_VERDICT:
- psock_set_prog(&progs->msg_parser, prog);
+ pprog = &progs->msg_parser;
break;
case BPF_SK_SKB_STREAM_PARSER:
- psock_set_prog(&progs->skb_parser, prog);
+ pprog = &progs->skb_parser;
break;
case BPF_SK_SKB_STREAM_VERDICT:
- psock_set_prog(&progs->skb_verdict, prog);
+ pprog = &progs->skb_verdict;
break;
default:
return -EOPNOTSUPP;
}
+ if (old)
+ return psock_replace_prog(pprog, prog, old);
+
+ psock_set_prog(pprog, prog);
return 0;
}
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index adcb3aea576d..bbdd3c7b6cb5 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -101,6 +101,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse)
more_reuse->prog = reuse->prog;
more_reuse->reuseport_id = reuse->reuseport_id;
more_reuse->bind_inany = reuse->bind_inany;
+ more_reuse->has_conns = reuse->has_conns;
memcpy(more_reuse->socks, reuse->socks,
reuse->num_socks * sizeof(struct sock *));
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index f93f8ace6c56..6ada114bbcca 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -274,7 +274,7 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write,
ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
if (write && !ret) {
if (jit_enable < 2 ||
- (jit_enable == 2 && bpf_dump_raw_ok())) {
+ (jit_enable == 2 && bpf_dump_raw_ok(current_cred()))) {
*(int *)table->data = jit_enable;
if (jit_enable == 2)
pr_warn("bpf_jit_enable = 2 was set! NEVER use this in production, only for JIT debugging!\n");
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 90f44f382115..3c45f99e26d5 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -462,6 +462,7 @@ struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp)
xdpf->len = totsize - metasize;
xdpf->headroom = 0;
xdpf->metasize = metasize;
+ xdpf->frame_sz = PAGE_SIZE;
xdpf->mem.type = MEM_TYPE_PAGE_ORDER0;
xsk_buff_free(xdp);
generated by cgit (git 2.34.1) at 2025-04-11 10:07:51 +0000