summaryrefslogtreecommitdiff
path: root/net/core/sock.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/core/sock.c')
-rw-r--r--net/core/sock.c227
1 files changed, 177 insertions, 50 deletions
diff --git a/net/core/sock.c b/net/core/sock.c
index be84885f9290..3b409bc8ef6d 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -148,6 +148,8 @@
#include <linux/ethtool.h>
+#include <uapi/linux/pidfd.h>
+
#include "dev.h"
static DEFINE_MUTEX(proto_list_mutex);
@@ -454,6 +456,13 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen,
return 0;
}
+static bool sk_set_prio_allowed(const struct sock *sk, int val)
+{
+ return ((val >= TC_PRIO_BESTEFFORT && val <= TC_PRIO_INTERACTIVE) ||
+ sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) ||
+ sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN));
+}
+
static bool sock_needs_netstamp(const struct sock *sk)
{
switch (sk->sk_family) {
@@ -931,6 +940,7 @@ int sock_set_timestamping(struct sock *sk, int optname,
WRITE_ONCE(sk->sk_tsflags, val);
sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW);
+ sock_valbool_flag(sk, SOCK_TIMESTAMPING_ANY, !!(val & TSFLAGS_ANY));
if (val & SOF_TIMESTAMPING_RX_SOFTWARE)
sock_enable_timestamp(sk,
@@ -941,6 +951,20 @@ int sock_set_timestamping(struct sock *sk, int optname,
return 0;
}
+#if defined(CONFIG_CGROUP_BPF)
+void bpf_skops_tx_timestamping(struct sock *sk, struct sk_buff *skb, int op)
+{
+ struct bpf_sock_ops_kern sock_ops;
+
+ memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
+ sock_ops.op = op;
+ sock_ops.is_fullsock = 1;
+ sock_ops.sk = sk;
+ bpf_skops_init_skb(&sock_ops, skb, 0);
+ __cgroup_bpf_run_filter_sock_ops(sk, &sock_ops, CGROUP_SOCK_OPS);
+}
+#endif
+
void sock_set_keepalive(struct sock *sk)
{
lock_sock(sk);
@@ -1193,22 +1217,11 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
/* handle options which do not require locking the socket. */
switch (optname) {
case SO_PRIORITY:
- if ((val >= 0 && val <= 6) ||
- sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_RAW) ||
- sockopt_ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+ if (sk_set_prio_allowed(sk, val)) {
sock_set_priority(sk, val);
return 0;
}
return -EPERM;
- case SO_PASSSEC:
- assign_bit(SOCK_PASSSEC, &sock->flags, valbool);
- return 0;
- case SO_PASSCRED:
- assign_bit(SOCK_PASSCRED, &sock->flags, valbool);
- return 0;
- case SO_PASSPIDFD:
- assign_bit(SOCK_PASSPIDFD, &sock->flags, valbool);
- return 0;
case SO_TYPE:
case SO_PROTOCOL:
case SO_DOMAIN:
@@ -1256,6 +1269,8 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
return 0;
}
case SO_TXREHASH:
+ if (!sk_is_tcp(sk))
+ return -EOPNOTSUPP;
if (val < -1 || val > 1)
return -EINVAL;
if ((u8)val == SOCK_TXREHASH_DEFAULT)
@@ -1517,6 +1532,10 @@ set_sndbuf:
sock_valbool_flag(sk, SOCK_RCVMARK, valbool);
break;
+ case SO_RCVPRIORITY:
+ sock_valbool_flag(sk, SOCK_RCVPRIORITY, valbool);
+ break;
+
case SO_RXQ_OVFL:
sock_valbool_flag(sk, SOCK_RXQ_OVFL, valbool);
break;
@@ -1533,6 +1552,33 @@ set_sndbuf:
sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool);
break;
+ case SO_PASSCRED:
+ if (sk_may_scm_recv(sk))
+ sk->sk_scm_credentials = valbool;
+ else
+ ret = -EOPNOTSUPP;
+ break;
+
+ case SO_PASSSEC:
+ if (IS_ENABLED(CONFIG_SECURITY_NETWORK) && sk_may_scm_recv(sk))
+ sk->sk_scm_security = valbool;
+ else
+ ret = -EOPNOTSUPP;
+ break;
+
+ case SO_PASSPIDFD:
+ if (sk_is_unix(sk))
+ sk->sk_scm_pidfd = valbool;
+ else
+ ret = -EOPNOTSUPP;
+ break;
+
+ case SO_PASSRIGHTS:
+ if (sk_is_unix(sk))
+ sk->sk_scm_rights = valbool;
+ else
+ ret = -EOPNOTSUPP;
+ break;
case SO_INCOMING_CPU:
reuseport_update_incoming_cpu(sk, val);
@@ -1829,11 +1875,24 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
break;
case SO_PASSCRED:
- v.val = !!test_bit(SOCK_PASSCRED, &sock->flags);
+ if (!sk_may_scm_recv(sk))
+ return -EOPNOTSUPP;
+
+ v.val = sk->sk_scm_credentials;
break;
case SO_PASSPIDFD:
- v.val = !!test_bit(SOCK_PASSPIDFD, &sock->flags);
+ if (!sk_is_unix(sk))
+ return -EOPNOTSUPP;
+
+ v.val = sk->sk_scm_pidfd;
+ break;
+
+ case SO_PASSRIGHTS:
+ if (!sk_is_unix(sk))
+ return -EOPNOTSUPP;
+
+ v.val = sk->sk_scm_rights;
break;
case SO_PEERCRED:
@@ -1855,6 +1914,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
{
struct pid *peer_pid;
struct file *pidfd_file = NULL;
+ unsigned int flags = 0;
int pidfd;
if (len > sizeof(pidfd))
@@ -1867,7 +1927,14 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
if (!peer_pid)
return -ENODATA;
- pidfd = pidfd_prepare(peer_pid, 0, &pidfd_file);
+ /* The use of PIDFD_STALE requires stashing of struct pid
+ * on pidfs with pidfs_register_pid() and only AF_UNIX
+ * were prepared for this.
+ */
+ if (sk->sk_family == AF_UNIX)
+ flags = PIDFD_STALE;
+
+ pidfd = pidfd_prepare(peer_pid, flags, &pidfd_file);
put_pid(peer_pid);
if (pidfd < 0)
return pidfd;
@@ -1930,7 +1997,10 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
break;
case SO_PASSSEC:
- v.val = !!test_bit(SOCK_PASSSEC, &sock->flags);
+ if (!IS_ENABLED(CONFIG_SECURITY_NETWORK) || !sk_may_scm_recv(sk))
+ return -EOPNOTSUPP;
+
+ v.val = sk->sk_scm_security;
break;
case SO_PEERSEC:
@@ -1945,6 +2015,10 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
v.val = sock_flag(sk, SOCK_RCVMARK);
break;
+ case SO_RCVPRIORITY:
+ v.val = sock_flag(sk, SOCK_RCVPRIORITY);
+ break;
+
case SO_RXQ_OVFL:
v.val = sock_flag(sk, SOCK_RXQ_OVFL);
break;
@@ -2028,7 +2102,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
v.val = READ_ONCE(sk->sk_napi_id);
/* aggregate non-NAPI IDs down to 0 */
- if (v.val < MIN_NAPI_ID)
+ if (!napi_id_valid(v.val))
v.val = 0;
break;
@@ -2074,6 +2148,9 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
break;
case SO_TXREHASH:
+ if (!sk_is_tcp(sk))
+ return -EOPNOTSUPP;
+
/* Paired with WRITE_ONCE() in sk_setsockopt() */
v.val = READ_ONCE(sk->sk_txrehash);
break;
@@ -2102,6 +2179,8 @@ lenout:
*/
static inline void sock_lock_init(struct sock *sk)
{
+ sk_owner_clear(sk);
+
if (sk->sk_kern_sock)
sock_lock_init_class_and_name(
sk,
@@ -2198,6 +2277,9 @@ static void sk_prot_free(struct proto *prot, struct sock *sk)
cgroup_sk_free(&sk->sk_cgrp_data);
mem_cgroup_sk_free(sk);
security_sk_free(sk);
+
+ sk_owner_put(sk);
+
if (slab != NULL)
kmem_cache_free(slab, sk);
else
@@ -2233,6 +2315,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
get_net_track(net, &sk->ns_tracker, priority);
sock_inuse_add(net, 1);
} else {
+ net_passive_inc(net);
__netns_tracker_alloc(net, &sk->ns_tracker,
false, priority);
}
@@ -2257,6 +2340,7 @@ EXPORT_SYMBOL(sk_alloc);
static void __sk_destruct(struct rcu_head *head)
{
struct sock *sk = container_of(head, struct sock, sk_rcu);
+ struct net *net = sock_net(sk);
struct sk_filter *filter;
if (sk->sk_destruct)
@@ -2288,14 +2372,28 @@ static void __sk_destruct(struct rcu_head *head)
put_cred(sk->sk_peer_cred);
put_pid(sk->sk_peer_pid);
- if (likely(sk->sk_net_refcnt))
- put_net_track(sock_net(sk), &sk->ns_tracker);
- else
- __netns_tracker_free(sock_net(sk), &sk->ns_tracker, false);
-
+ if (likely(sk->sk_net_refcnt)) {
+ put_net_track(net, &sk->ns_tracker);
+ } else {
+ __netns_tracker_free(net, &sk->ns_tracker, false);
+ net_passive_dec(net);
+ }
sk_prot_free(sk->sk_prot_creator, sk);
}
+void sk_net_refcnt_upgrade(struct sock *sk)
+{
+ struct net *net = sock_net(sk);
+
+ WARN_ON_ONCE(sk->sk_net_refcnt);
+ __netns_tracker_free(net, &sk->ns_tracker, false);
+ net_passive_dec(net);
+ sk->sk_net_refcnt = 1;
+ get_net_track(net, &sk->ns_tracker, GFP_KERNEL);
+ sock_inuse_add(net, 1);
+}
+EXPORT_SYMBOL_GPL(sk_net_refcnt_upgrade);
+
void sk_destruct(struct sock *sk)
{
bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE);
@@ -2392,6 +2490,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
* is not properly dismantling its kernel sockets at netns
* destroy time.
*/
+ net_passive_inc(sock_net(newsk));
__netns_tracker_alloc(sock_net(newsk), &newsk->ns_tracker,
false, priority);
}
@@ -2444,17 +2543,14 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
*/
if (!is_charged)
RCU_INIT_POINTER(newsk->sk_filter, NULL);
- sk_free_unlock_clone(newsk);
- newsk = NULL;
- goto out;
+
+ goto free;
}
+
RCU_INIT_POINTER(newsk->sk_reuseport_cb, NULL);
- if (bpf_sk_storage_clone(sk, newsk)) {
- sk_free_unlock_clone(newsk);
- newsk = NULL;
- goto out;
- }
+ if (bpf_sk_storage_clone(sk, newsk))
+ goto free;
/* Clear sk_user_data if parent had the pointer tagged
* as not suitable for copying when cloning.
@@ -2484,18 +2580,17 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
net_enable_timestamp();
out:
return newsk;
-}
-EXPORT_SYMBOL_GPL(sk_clone_lock);
-
-void sk_free_unlock_clone(struct sock *sk)
-{
+free:
/* It is still raw copy of parent, so invalidate
- * destructor and make plain sk_free() */
- sk->sk_destruct = NULL;
- bh_unlock_sock(sk);
- sk_free(sk);
+ * destructor and make plain sk_free()
+ */
+ newsk->sk_destruct = NULL;
+ bh_unlock_sock(newsk);
+ sk_free(newsk);
+ newsk = NULL;
+ goto out;
}
-EXPORT_SYMBOL_GPL(sk_free_unlock_clone);
+EXPORT_SYMBOL_GPL(sk_clone_lock);
static u32 sk_dst_gso_max_size(struct sock *sk, struct dst_entry *dst)
{
@@ -2520,8 +2615,12 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
u32 max_segs = 1;
sk->sk_route_caps = dst->dev->features;
- if (sk_is_tcp(sk))
+ if (sk_is_tcp(sk)) {
+ struct inet_connection_sock *icsk = inet_csk(sk);
+
sk->sk_route_caps |= NETIF_F_GSO;
+ icsk->icsk_ack.dst_quick_ack = dst_metric(dst, RTAX_QUICKACK);
+ }
if (sk->sk_route_caps & NETIF_F_GSO)
sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE;
if (unlikely(sk->sk_gso_disabled))
@@ -2791,6 +2890,22 @@ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
}
EXPORT_SYMBOL(sock_kmalloc);
+/*
+ * Duplicate the input "src" memory block using the socket's
+ * option memory buffer.
+ */
+void *sock_kmemdup(struct sock *sk, const void *src,
+ int size, gfp_t priority)
+{
+ void *mem;
+
+ mem = sock_kmalloc(sk, size, priority);
+ if (mem)
+ memcpy(mem, src, size);
+ return mem;
+}
+EXPORT_SYMBOL(sock_kmemdup);
+
/* Free an option memory block. Note, we actually want the inline
* here as this allows gcc to detect the nullify and fold away the
* condition entirely.
@@ -2945,6 +3060,18 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg,
case SCM_RIGHTS:
case SCM_CREDENTIALS:
break;
+ case SO_PRIORITY:
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
+ return -EINVAL;
+ if (!sk_set_prio_allowed(sk, *(u32 *)CMSG_DATA(cmsg)))
+ return -EPERM;
+ sockc->priority = *(u32 *)CMSG_DATA(cmsg);
+ break;
+ case SCM_DEVMEM_DMABUF:
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32)))
+ return -EINVAL;
+ sockc->dmabuf_id = *(u32 *)CMSG_DATA(cmsg);
+ break;
default:
return -EINVAL;
}
@@ -3157,16 +3284,16 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind)
{
struct mem_cgroup *memcg = mem_cgroup_sockets_enabled ? sk->sk_memcg : NULL;
struct proto *prot = sk->sk_prot;
- bool charged = false;
+ bool charged = true;
long allocated;
sk_memory_allocated_add(sk, amt);
allocated = sk_memory_allocated(sk);
if (memcg) {
- if (!mem_cgroup_charge_skmem(memcg, amt, gfp_memcg_charge()))
+ charged = mem_cgroup_charge_skmem(memcg, amt, gfp_memcg_charge());
+ if (!charged)
goto suppress_allocation;
- charged = true;
}
/* Under limit. */
@@ -3251,7 +3378,7 @@ suppress_allocation:
sk_memory_allocated_sub(sk, amt);
- if (charged)
+ if (memcg && charged)
mem_cgroup_uncharge_skmem(memcg, amt);
return 0;
@@ -3526,14 +3653,14 @@ EXPORT_SYMBOL(sk_reset_timer);
void sk_stop_timer(struct sock *sk, struct timer_list* timer)
{
- if (del_timer(timer))
+ if (timer_delete(timer))
__sock_put(sk);
}
EXPORT_SYMBOL(sk_stop_timer);
void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer)
{
- if (del_timer_sync(timer))
+ if (timer_delete_sync(timer))
__sock_put(sk);
}
EXPORT_SYMBOL(sk_stop_timer_sync);
@@ -3861,7 +3988,7 @@ void sk_get_meminfo(const struct sock *sk, u32 *mem)
mem[SK_MEMINFO_RCVBUF] = READ_ONCE(sk->sk_rcvbuf);
mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk);
mem[SK_MEMINFO_SNDBUF] = READ_ONCE(sk->sk_sndbuf);
- mem[SK_MEMINFO_FWD_ALLOC] = sk_forward_alloc_get(sk);
+ mem[SK_MEMINFO_FWD_ALLOC] = READ_ONCE(sk->sk_forward_alloc);
mem[SK_MEMINFO_WMEM_QUEUED] = READ_ONCE(sk->sk_wmem_queued);
mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len);
@@ -3927,7 +4054,7 @@ static int assign_proto_idx(struct proto *prot)
{
prot->inuse_idx = find_first_zero_bit(proto_inuse_idx, PROTO_INUSE_NR);
- if (unlikely(prot->inuse_idx == PROTO_INUSE_NR - 1)) {
+ if (unlikely(prot->inuse_idx == PROTO_INUSE_NR)) {
pr_err("PROTO_INUSE_NR exhausted\n");
return -ENOSPC;
}
@@ -3938,7 +4065,7 @@ static int assign_proto_idx(struct proto *prot)
static void release_proto_idx(struct proto *prot)
{
- if (prot->inuse_idx != PROTO_INUSE_NR - 1)
+ if (prot->inuse_idx != PROTO_INUSE_NR)
clear_bit(prot->inuse_idx, proto_inuse_idx);
}
#else
generated by cgit (git 2.34.1) at 2025-06-07 04:12:38 +0000