summaryrefslogtreecommitdiff
path: root/net/core
diff options
context:
space:
mode:
Diffstat (limited to 'net/core')
-rw-r--r--net/core/datagram.c2
-rw-r--r--net/core/dev.c93
-rw-r--r--net/core/dev.h3
-rw-r--r--net/core/filter.c44
-rw-r--r--net/core/gso_test.c2
-rw-r--r--net/core/page_pool_user.c3
-rw-r--r--net/core/request_sock.c3
-rw-r--r--net/core/rtnetlink.c30
-rw-r--r--net/core/skmsg.c7
-rw-r--r--net/core/sock.c34
10 files changed, 141 insertions, 80 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 103d46fa0eeb..a8b625abe242 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -751,7 +751,7 @@ size_t memcpy_to_iter_csum(void *iter_to, size_t progress,
size_t len, void *from, void *priv2)
{
__wsum *csum = priv2;
- __wsum next = csum_partial_copy_nocheck(from, iter_to, len);
+ __wsum next = csum_partial_copy_nocheck(from + progress, iter_to, len);
*csum = csum_block_add(*csum, next, progress);
return 0;
diff --git a/net/core/dev.c b/net/core/dev.c
index f01a9b858347..a892f7265189 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -336,7 +336,7 @@ int netdev_name_node_alt_create(struct net_device *dev, const char *name)
return -ENOMEM;
netdev_name_node_add(net, name_node);
/* The node that holds dev->name acts as a head of per-device list. */
- list_add_tail(&name_node->list, &dev->name_node->list);
+ list_add_tail_rcu(&name_node->list, &dev->name_node->list);
return 0;
}
@@ -6177,8 +6177,13 @@ static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
clear_bit(NAPI_STATE_SCHED, &napi->state);
}
-static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool prefer_busy_poll,
- u16 budget)
+enum {
+ NAPI_F_PREFER_BUSY_POLL = 1,
+ NAPI_F_END_ON_RESCHED = 2,
+};
+
+static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock,
+ unsigned flags, u16 budget)
{
bool skip_schedule = false;
unsigned long timeout;
@@ -6198,7 +6203,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool
local_bh_disable();
- if (prefer_busy_poll) {
+ if (flags & NAPI_F_PREFER_BUSY_POLL) {
napi->defer_hard_irqs_count = READ_ONCE(napi->dev->napi_defer_hard_irqs);
timeout = READ_ONCE(napi->dev->gro_flush_timeout);
if (napi->defer_hard_irqs_count && timeout) {
@@ -6222,23 +6227,23 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool
local_bh_enable();
}
-void napi_busy_loop(unsigned int napi_id,
- bool (*loop_end)(void *, unsigned long),
- void *loop_end_arg, bool prefer_busy_poll, u16 budget)
+static void __napi_busy_loop(unsigned int napi_id,
+ bool (*loop_end)(void *, unsigned long),
+ void *loop_end_arg, unsigned flags, u16 budget)
{
unsigned long start_time = loop_end ? busy_loop_current_time() : 0;
int (*napi_poll)(struct napi_struct *napi, int budget);
void *have_poll_lock = NULL;
struct napi_struct *napi;
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
restart:
napi_poll = NULL;
- rcu_read_lock();
-
napi = napi_by_id(napi_id);
if (!napi)
- goto out;
+ return;
if (!IS_ENABLED(CONFIG_PREEMPT_RT))
preempt_disable();
@@ -6254,14 +6259,14 @@ restart:
*/
if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED |
NAPIF_STATE_IN_BUSY_POLL)) {
- if (prefer_busy_poll)
+ if (flags & NAPI_F_PREFER_BUSY_POLL)
set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
goto count;
}
if (cmpxchg(&napi->state, val,
val | NAPIF_STATE_IN_BUSY_POLL |
NAPIF_STATE_SCHED) != val) {
- if (prefer_busy_poll)
+ if (flags & NAPI_F_PREFER_BUSY_POLL)
set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
goto count;
}
@@ -6281,12 +6286,15 @@ count:
break;
if (unlikely(need_resched())) {
+ if (flags & NAPI_F_END_ON_RESCHED)
+ break;
if (napi_poll)
- busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
+ busy_poll_stop(napi, have_poll_lock, flags, budget);
if (!IS_ENABLED(CONFIG_PREEMPT_RT))
preempt_enable();
rcu_read_unlock();
cond_resched();
+ rcu_read_lock();
if (loop_end(loop_end_arg, start_time))
return;
goto restart;
@@ -6294,10 +6302,31 @@ count:
cpu_relax();
}
if (napi_poll)
- busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
+ busy_poll_stop(napi, have_poll_lock, flags, budget);
if (!IS_ENABLED(CONFIG_PREEMPT_RT))
preempt_enable();
-out:
+}
+
+void napi_busy_loop_rcu(unsigned int napi_id,
+ bool (*loop_end)(void *, unsigned long),
+ void *loop_end_arg, bool prefer_busy_poll, u16 budget)
+{
+ unsigned flags = NAPI_F_END_ON_RESCHED;
+
+ if (prefer_busy_poll)
+ flags |= NAPI_F_PREFER_BUSY_POLL;
+
+ __napi_busy_loop(napi_id, loop_end, loop_end_arg, flags, budget);
+}
+
+void napi_busy_loop(unsigned int napi_id,
+ bool (*loop_end)(void *, unsigned long),
+ void *loop_end_arg, bool prefer_busy_poll, u16 budget)
+{
+ unsigned flags = prefer_busy_poll ? NAPI_F_PREFER_BUSY_POLL : 0;
+
+ rcu_read_lock();
+ __napi_busy_loop(napi_id, loop_end, loop_end_arg, flags, budget);
rcu_read_unlock();
}
EXPORT_SYMBOL(napi_busy_loop);
@@ -9074,28 +9103,6 @@ bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b)
}
EXPORT_SYMBOL(netdev_port_same_parent_id);
-static void netdev_dpll_pin_assign(struct net_device *dev, struct dpll_pin *dpll_pin)
-{
-#if IS_ENABLED(CONFIG_DPLL)
- rtnl_lock();
- dev->dpll_pin = dpll_pin;
- rtnl_unlock();
-#endif
-}
-
-void netdev_dpll_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin)
-{
- WARN_ON(!dpll_pin);
- netdev_dpll_pin_assign(dev, dpll_pin);
-}
-EXPORT_SYMBOL(netdev_dpll_pin_set);
-
-void netdev_dpll_pin_clear(struct net_device *dev)
-{
- netdev_dpll_pin_assign(dev, NULL);
-}
-EXPORT_SYMBOL(netdev_dpll_pin_clear);
-
/**
* dev_change_proto_down - set carrier according to proto_down.
*
@@ -11551,6 +11558,7 @@ static struct pernet_operations __net_initdata netdev_net_ops = {
static void __net_exit default_device_exit_net(struct net *net)
{
+ struct netdev_name_node *name_node, *tmp;
struct net_device *dev, *aux;
/*
* Push all migratable network devices back to the
@@ -11573,6 +11581,14 @@ static void __net_exit default_device_exit_net(struct net *net)
snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex);
if (netdev_name_in_use(&init_net, fb_name))
snprintf(fb_name, IFNAMSIZ, "dev%%d");
+
+ netdev_for_each_altname_safe(dev, name_node, tmp)
+ if (netdev_name_in_use(&init_net, name_node->name)) {
+ netdev_name_node_del(name_node);
+ synchronize_rcu();
+ __netdev_name_node_alt_destroy(name_node);
+ }
+
err = dev_change_net_namespace(dev, &init_net, fb_name);
if (err) {
pr_emerg("%s: failed to move %s to init_net: %d\n",
@@ -11643,11 +11659,12 @@ static void __init net_dev_struct_check(void)
CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_tx, 160);
/* TXRX read-mostly hotpath */
+ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, lstats);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, hard_header_len);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, features);
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, ip6_ptr);
- CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 30);
+ CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 38);
/* RX read-mostly hotpath */
CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ptype_specific);
diff --git a/net/core/dev.h b/net/core/dev.h
index cf93e188785b..7480b4c84298 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -63,6 +63,9 @@ int dev_change_name(struct net_device *dev, const char *newname);
#define netdev_for_each_altname(dev, namenode) \
list_for_each_entry((namenode), &(dev)->name_node->list, list)
+#define netdev_for_each_altname_safe(dev, namenode, next) \
+ list_for_each_entry_safe((namenode), (next), &(dev)->name_node->list, \
+ list)
int netdev_name_node_alt_create(struct net_device *dev, const char *name);
int netdev_name_node_alt_destroy(struct net_device *dev, const char *name);
diff --git a/net/core/filter.c b/net/core/filter.c
index 24061f29c9dd..ef3e78b6a39c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -83,6 +83,7 @@
#include <net/netfilter/nf_conntrack_bpf.h>
#include <net/netkit.h>
#include <linux/un.h>
+#include <net/xdp_sock_drv.h>
#include "dev.h"
@@ -4092,10 +4093,46 @@ static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset)
memset(skb_frag_address(frag) + skb_frag_size(frag), 0, offset);
skb_frag_size_add(frag, offset);
sinfo->xdp_frags_size += offset;
+ if (rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL)
+ xsk_buff_get_tail(xdp)->data_end += offset;
return 0;
}
+static void bpf_xdp_shrink_data_zc(struct xdp_buff *xdp, int shrink,
+ struct xdp_mem_info *mem_info, bool release)
+{
+ struct xdp_buff *zc_frag = xsk_buff_get_tail(xdp);
+
+ if (release) {
+ xsk_buff_del_tail(zc_frag);
+ __xdp_return(NULL, mem_info, false, zc_frag);
+ } else {
+ zc_frag->data_end -= shrink;
+ }
+}
+
+static bool bpf_xdp_shrink_data(struct xdp_buff *xdp, skb_frag_t *frag,
+ int shrink)
+{
+ struct xdp_mem_info *mem_info = &xdp->rxq->mem;
+ bool release = skb_frag_size(frag) == shrink;
+
+ if (mem_info->type == MEM_TYPE_XSK_BUFF_POOL) {
+ bpf_xdp_shrink_data_zc(xdp, shrink, mem_info, release);
+ goto out;
+ }
+
+ if (release) {
+ struct page *page = skb_frag_page(frag);
+
+ __xdp_return(page_address(page), mem_info, false, NULL);
+ }
+
+out:
+ return release;
+}
+
static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset)
{
struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
@@ -4110,12 +4147,7 @@ static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset)
len_free += shrink;
offset -= shrink;
-
- if (skb_frag_size(frag) == shrink) {
- struct page *page = skb_frag_page(frag);
-
- __xdp_return(page_address(page), &xdp->rxq->mem,
- false, NULL);
+ if (bpf_xdp_shrink_data(xdp, frag, shrink)) {
n_frags_free++;
} else {
skb_frag_size_sub(frag, shrink);
diff --git a/net/core/gso_test.c b/net/core/gso_test.c
index 4c2e77bd12f4..358c44680d91 100644
--- a/net/core/gso_test.c
+++ b/net/core/gso_test.c
@@ -225,7 +225,7 @@ static void gso_test_func(struct kunit *test)
segs = skb_segment(skb, features);
if (IS_ERR(segs)) {
- KUNIT_FAIL(test, "segs error %lld", PTR_ERR(segs));
+ KUNIT_FAIL(test, "segs error %pe", segs);
goto free_gso_skb;
} else if (!segs) {
KUNIT_FAIL(test, "no segments");
diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
index ffe5244e5597..278294aca66a 100644
--- a/net/core/page_pool_user.c
+++ b/net/core/page_pool_user.c
@@ -94,11 +94,12 @@ netdev_nl_page_pool_get_dump(struct sk_buff *skb, struct netlink_callback *cb,
state->pp_id = pool->user.id;
err = fill(skb, pool, info);
if (err)
- break;
+ goto out;
}
state->pp_id = 0;
}
+out:
mutex_unlock(&page_pools_lock);
rtnl_unlock();
diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index f35c2e998406..63de5c635842 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -33,9 +33,6 @@
void reqsk_queue_alloc(struct request_sock_queue *queue)
{
- spin_lock_init(&queue->rskq_lock);
-
- spin_lock_init(&queue->fastopenq.lock);
queue->fastopenq.rskq_rst_head = NULL;
queue->fastopenq.rskq_rst_tail = NULL;
queue->fastopenq.qlen = 0;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index f6f29eb03ec2..bd50e9fe3234 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1020,14 +1020,17 @@ static size_t rtnl_xdp_size(void)
static size_t rtnl_prop_list_size(const struct net_device *dev)
{
struct netdev_name_node *name_node;
- size_t size;
+ unsigned int cnt = 0;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(name_node, &dev->name_node->list, list)
+ cnt++;
+ rcu_read_unlock();
- if (list_empty(&dev->name_node->list))
+ if (!cnt)
return 0;
- size = nla_total_size(0);
- list_for_each_entry(name_node, &dev->name_node->list, list)
- size += nla_total_size(ALTIFNAMSIZ);
- return size;
+
+ return nla_total_size(0) + cnt * nla_total_size(ALTIFNAMSIZ);
}
static size_t rtnl_proto_down_size(const struct net_device *dev)
@@ -1054,7 +1057,7 @@ static size_t rtnl_dpll_pin_size(const struct net_device *dev)
{
size_t size = nla_total_size(0); /* nest IFLA_DPLL_PIN */
- size += dpll_msg_pin_handle_size(netdev_dpll_pin(dev));
+ size += dpll_netdev_pin_handle_size(dev);
return size;
}
@@ -1789,7 +1792,7 @@ static int rtnl_fill_dpll_pin(struct sk_buff *skb,
if (!dpll_pin_nest)
return -EMSGSIZE;
- ret = dpll_msg_add_pin_handle(skb, netdev_dpll_pin(dev));
+ ret = dpll_netdev_add_pin_handle(skb, dev);
if (ret < 0)
goto nest_cancel;
@@ -5166,10 +5169,9 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct net *net = sock_net(skb->sk);
struct ifinfomsg *ifm;
struct net_device *dev;
- struct nlattr *br_spec, *attr = NULL;
+ struct nlattr *br_spec, *attr, *br_flags_attr = NULL;
int rem, err = -EOPNOTSUPP;
u16 flags = 0;
- bool have_flags = false;
if (nlmsg_len(nlh) < sizeof(*ifm))
return -EINVAL;
@@ -5187,11 +5189,11 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
if (br_spec) {
nla_for_each_nested(attr, br_spec, rem) {
- if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !have_flags) {
+ if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !br_flags_attr) {
if (nla_len(attr) < sizeof(flags))
return -EINVAL;
- have_flags = true;
+ br_flags_attr = attr;
flags = nla_get_u16(attr);
}
@@ -5235,8 +5237,8 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
}
}
- if (have_flags)
- memcpy(nla_data(attr), &flags, sizeof(flags));
+ if (br_flags_attr)
+ memcpy(nla_data(br_flags_attr), &flags, sizeof(flags));
out:
return err;
}
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 93ecfceac1bc..4d75ef9d24bf 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -1226,8 +1226,11 @@ static void sk_psock_verdict_data_ready(struct sock *sk)
rcu_read_lock();
psock = sk_psock(sk);
- if (psock)
- psock->saved_data_ready(sk);
+ if (psock) {
+ read_lock_bh(&sk->sk_callback_lock);
+ sk_psock_data_ready(sk, psock);
+ read_unlock_bh(&sk->sk_callback_lock);
+ }
rcu_read_unlock();
}
}
diff --git a/net/core/sock.c b/net/core/sock.c
index 158dbdebce6a..5e78798456fd 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -107,6 +107,7 @@
#include <linux/interrupt.h>
#include <linux/poll.h>
#include <linux/tcp.h>
+#include <linux/udp.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/user_namespace.h>
@@ -1187,6 +1188,17 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
*/
WRITE_ONCE(sk->sk_txrehash, (u8)val);
return 0;
+ case SO_PEEK_OFF:
+ {
+ int (*set_peek_off)(struct sock *sk, int val);
+
+ set_peek_off = READ_ONCE(sock->ops)->set_peek_off;
+ if (set_peek_off)
+ ret = set_peek_off(sk, val);
+ else
+ ret = -EOPNOTSUPP;
+ return ret;
+ }
}
sockopt_lock_sock(sk);
@@ -1429,18 +1441,6 @@ set_sndbuf:
sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool);
break;
- case SO_PEEK_OFF:
- {
- int (*set_peek_off)(struct sock *sk, int val);
-
- set_peek_off = READ_ONCE(sock->ops)->set_peek_off;
- if (set_peek_off)
- ret = set_peek_off(sk, val);
- else
- ret = -EOPNOTSUPP;
- break;
- }
-
case SO_NOFCS:
sock_valbool_flag(sk, SOCK_NOFCS, valbool);
break;
@@ -4144,8 +4144,14 @@ bool sk_busy_loop_end(void *p, unsigned long start_time)
{
struct sock *sk = p;
- return !skb_queue_empty_lockless(&sk->sk_receive_queue) ||
- sk_busy_loop_timeout(sk, start_time);
+ if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
+ return true;
+
+ if (sk_is_udp(sk) &&
+ !skb_queue_empty_lockless(&udp_sk(sk)->reader_queue))
+ return true;
+
+ return sk_busy_loop_timeout(sk, start_time);
}
EXPORT_SYMBOL(sk_busy_loop_end);
#endif /* CONFIG_NET_RX_BUSY_POLL */
generated by cgit v1.2.3-70-g09d2 (git 2.48.1) at 2025-03-27 10:15:08 +0000