Merge: core: stable backport from upstream for 10.2 phase 1

CKI KWF Bot · CKI KWF Bot · commit 67e16a0f3de8 · 2025-10-30T10:14:35.000Z
MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-10/-/merge_requests/1557 JIRA: https://issues.redhat.com/browse/RHEL-115597 A bunch of fixes from net, addressing non critical issues in core networking. Signed-off-by: Paolo Abeni <pabeni@redhat.com> Approved-by: Eder Zulian <ezulian@redhat.com> Approved-by: Hangbin Liu <haliu@redhat.com> Approved-by: Florian Westphal <fwestpha@redhat.com> Approved-by: Davide Caratti <dcaratti@redhat.com> Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com> Merged-by: CKI GitLab Kmaint Pipeline Bot <26919896-cki-kmaint-pipeline-bot@users.noreply.gitlab.com>
diff --git a/include/net/sock.h b/include/net/sock.h
@@ -285,6 +285,7 @@ struct sk_filter;
   *	@sk_ack_backlog: current listen backlog
   *	@sk_max_ack_backlog: listen backlog set in listen()
   *	@sk_uid: user id of owner
+  *	@sk_ino: inode number (zero if orphaned)
   *	@sk_prefer_busy_poll: prefer busypolling over softirq processing
   *	@sk_busy_poll_budget: napi processing budget when busypolling
   *	@sk_priority: %SO_PRIORITY setting
@@ -512,6 +513,7 @@ struct sock {
 	u32			sk_ack_backlog;
 	u32			sk_max_ack_backlog;
 	kuid_t			sk_uid;
+	unsigned long		sk_ino;
 	spinlock_t		sk_peer_lock;
 	int			sk_bind_phc;
 	struct pid		*sk_peer_pid;
@@ -2027,6 +2029,13 @@ static inline int sk_rx_queue_get(const struct sock *sk)
 static inline void sk_set_socket(struct sock *sk, struct socket *sock)
 {
 	sk->sk_socket = sock;
+	if (sock) {
+		WRITE_ONCE(sk->sk_uid, SOCK_INODE(sock)->i_uid);
+		WRITE_ONCE(sk->sk_ino, SOCK_INODE(sock)->i_ino);
+	} else {
+		/* Note: sk_uid is unchanged. */
+		WRITE_ONCE(sk->sk_ino, 0);
+	}
 }
 
 static inline wait_queue_head_t *sk_sleep(struct sock *sk)
@@ -2057,14 +2066,17 @@ static inline void sock_graft(struct sock *sk, struct socket *parent)
 	rcu_assign_pointer(sk->sk_wq, &parent->wq);
 	parent->sk = sk;
 	sk_set_socket(sk, parent);
-	sk->sk_uid = SOCK_INODE(parent)->i_uid;
 	security_sock_graft(sk, parent);
 	write_unlock_bh(&sk->sk_callback_lock);
 }
 
+static inline unsigned long sock_i_ino(const struct sock *sk)
+{
+	/* Paired with WRITE_ONCE() in sock_graft() and sock_orphan() */
+	return READ_ONCE(sk->sk_ino);
+}
+
 kuid_t sock_i_uid(struct sock *sk);
-unsigned long __sock_i_ino(struct sock *sk);
-unsigned long sock_i_ino(struct sock *sk);
 
 static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk)
 {
@@ -2970,8 +2982,11 @@ int sock_ioctl_inout(struct sock *sk, unsigned int cmd,
 int sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg);
 static inline bool sk_is_readable(struct sock *sk)
 {
-	if (sk->sk_prot->sock_is_readable)
-		return sk->sk_prot->sock_is_readable(sk);
+	const struct proto *prot = READ_ONCE(sk->sk_prot);
+
+	if (prot->sock_is_readable)
+		return prot->sock_is_readable(sk);
+
 	return false;
 }
 #endif	/* _SOCK_H */
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
@@ -90,10 +90,12 @@ static void est_timer(struct timer_list *t)
 	rate = (b_packets - est->last_packets) << (10 - est->intvl_log);
 	rate = (rate >> est->ewma_log) - (est->avpps >> est->ewma_log);
 
+	preempt_disable_nested();
 	write_seqcount_begin(&est->seq);
 	est->avbps += brate;
 	est->avpps += rate;
 	write_seqcount_end(&est->seq);
+	preempt_enable_nested();
 
 	est->last_bytes = b_bytes;
 	est->last_packets = b_packets;
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
@@ -196,6 +196,16 @@ static const struct genl_multicast_group netdev_nl_mcgrps[] = {
 	[NETDEV_NLGRP_PAGE_POOL] = { "page-pool", },
 };
 
+static void __netdev_nl_sock_priv_init(void *priv)
+{
+	netdev_nl_sock_priv_init(priv);
+}
+
+static void __netdev_nl_sock_priv_destroy(void *priv)
+{
+	netdev_nl_sock_priv_destroy(priv);
+}
+
 struct genl_family netdev_nl_family __ro_after_init = {
 	.name		= NETDEV_FAMILY_NAME,
 	.version	= NETDEV_FAMILY_VERSION,
@@ -207,6 +217,6 @@ struct genl_family netdev_nl_family __ro_after_init = {
 	.mcgrps		= netdev_nl_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(netdev_nl_mcgrps),
 	.sock_priv_size	= sizeof(struct list_head),
-	.sock_priv_init	= (void *)netdev_nl_sock_priv_init,
-	.sock_priv_destroy = (void *)netdev_nl_sock_priv_destroy,
+	.sock_priv_init	= __netdev_nl_sock_priv_init,
+	.sock_priv_destroy = __netdev_nl_sock_priv_destroy,
 };
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
@@ -175,8 +175,7 @@ netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi,
 	if (!hdr)
 		return -EMSGSIZE;
 
-	if (napi->napi_id >= MIN_NAPI_ID &&
-	    nla_put_u32(rsp, NETDEV_A_NAPI_ID, napi->napi_id))
+	if (nla_put_u32(rsp, NETDEV_A_NAPI_ID, napi->napi_id))
 		goto nla_put_failure;
 
 	if (nla_put_u32(rsp, NETDEV_A_NAPI_IFINDEX, napi->dev->ifindex))
@@ -262,6 +261,8 @@ netdev_nl_napi_dump_one(struct net_device *netdev, struct sk_buff *rsp,
 		return err;
 
 	list_for_each_entry(napi, &netdev->napi_list, dev_list) {
+		if (napi->napi_id < MIN_NAPI_ID)
+			continue;
 		if (ctx->napi_id && napi->napi_id >= ctx->napi_id)
 			continue;
 
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
@@ -784,6 +784,13 @@ int netpoll_setup(struct netpoll *np)
 	if (err)
 		goto put;
 	rtnl_unlock();
+
+	/* Make sure all NAPI polls which started before dev->npinfo
+	 * was visible have exited before we start calling NAPI poll.
+	 * NAPI skips locking if dev->npinfo is NULL.
+	 */
+	synchronize_rcu();
+
 	return 0;
 
 put:
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
@@ -6158,9 +6158,6 @@ int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len)
 	if (!pskb_may_pull(skb, write_len))
 		return -ENOMEM;
 
-	if (!skb_frags_readable(skb))
-		return -EFAULT;
-
 	if (!skb_cloned(skb) || skb_clone_writable(skb, write_len))
 		return 0;
 
diff --git a/net/core/sock.c b/net/core/sock.c
@@ -2725,28 +2725,6 @@ kuid_t sock_i_uid(struct sock *sk)
 }
 EXPORT_SYMBOL(sock_i_uid);
 
-unsigned long __sock_i_ino(struct sock *sk)
-{
-	unsigned long ino;
-
-	read_lock(&sk->sk_callback_lock);
-	ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0;
-	read_unlock(&sk->sk_callback_lock);
-	return ino;
-}
-EXPORT_SYMBOL(__sock_i_ino);
-
-unsigned long sock_i_ino(struct sock *sk)
-{
-	unsigned long ino;
-
-	local_bh_disable();
-	ino = __sock_i_ino(sk);
-	local_bh_enable();
-	return ino;
-}
-EXPORT_SYMBOL(sock_i_ino);
-
 /*
  * Allocate a skb from the socket's send buffer.
  */
@@ -3182,16 +3160,16 @@ 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. */
@@ -3276,7 +3254,7 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind)
 
 	sk_memory_allocated_sub(sk, amt);
 
-	if (charged)
+	if (memcg && charged)
 		mem_cgroup_uncharge_skmem(memcg, amt);
 
 	return 0;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
@@ -3505,7 +3505,6 @@ void mptcp_sock_graft(struct sock *sk, struct socket *parent)
 	write_lock_bh(&sk->sk_callback_lock);
 	rcu_assign_pointer(sk->sk_wq, &parent->wq);
 	sk_set_socket(sk, parent);
-	sk->sk_uid = SOCK_INODE(parent)->i_uid;
 	write_unlock_bh(&sk->sk_callback_lock);
 }
 
diff --git a/net/netlink/diag.c b/net/netlink/diag.c
@@ -168,7 +168,7 @@ static int __netlink_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
 				 NETLINK_CB(cb->skb).portid,
 				 cb->nlh->nlmsg_seq,
 				 NLM_F_MULTI,
-				 __sock_i_ino(sk)) < 0) {
+				 sock_i_ino(sk)) < 0) {
 			ret = 1;
 			break;
 		}
diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py
@@ -2426,6 +2426,17 @@ def print_kernel_family_struct_src(family, cw):
     if not kernel_can_gen_family_struct(family):
         return
 
+    if 'sock-priv' in family.kernel_family:
+        # Generate "trampolines" to make CFI happy
+        cw.write_func("static void", f"__{family.c_name}_nl_sock_priv_init",
+                      [f"{family.c_name}_nl_sock_priv_init(priv);"],
+                      ["void *priv"])
+        cw.nl()
+        cw.write_func("static void", f"__{family.c_name}_nl_sock_priv_destroy",
+                      [f"{family.c_name}_nl_sock_priv_destroy(priv);"],
+                      ["void *priv"])
+        cw.nl()
+
     cw.block_start(f"struct genl_family {family.ident_name}_nl_family __ro_after_init =")
     cw.p('.name\t\t= ' + family.fam_key + ',')
     cw.p('.version\t= ' + family.ver_key + ',')
@@ -2443,9 +2454,8 @@ def print_kernel_family_struct_src(family, cw):
         cw.p(f'.n_mcgrps\t= ARRAY_SIZE({family.c_name}_nl_mcgrps),')
     if 'sock-priv' in family.kernel_family:
         cw.p(f'.sock_priv_size\t= sizeof({family.kernel_family["sock-priv"]}),')
-        # Force cast here, actual helpers take pointer to the real type.
-        cw.p(f'.sock_priv_init\t= (void *){family.c_name}_nl_sock_priv_init,')
-        cw.p(f'.sock_priv_destroy = (void *){family.c_name}_nl_sock_priv_destroy,')
+        cw.p(f'.sock_priv_init\t= __{family.c_name}_nl_sock_priv_init,')
+        cw.p(f'.sock_priv_destroy = __{family.c_name}_nl_sock_priv_destroy,')
     cw.block_end(';')
 
 

Original file line number	Diff line number	Diff line change
`@@ -3505,7 +3505,6 @@ void mptcp_sock_graft(struct sock sk, struct socket parent)`
`3505`	`3505`	`write_lock_bh(&sk->sk_callback_lock);`
`3506`	`3506`	`rcu_assign_pointer(sk->sk_wq, &parent->wq);`
`3507`	`3507`	`sk_set_socket(sk, parent);`
`3508`		`- sk->sk_uid = SOCK_INODE(parent)->i_uid;`
`3509`	`3508`	`write_unlock_bh(&sk->sk_callback_lock);`
`3510`	`3509`	`}`
`3511`	`3510`
Original file line number	Diff line number	Diff line change
`@@ -168,7 +168,7 @@ static int __netlink_diag_dump(struct sk_buff skb, struct netlink_callback cb,`
`168`	`168`	`NETLINK_CB(cb->skb).portid,`
`169`	`169`	`cb->nlh->nlmsg_seq,`
`170`	`170`	`NLM_F_MULTI,`
`171`		`- __sock_i_ino(sk)) < 0) {`
	`171`	`+ sock_i_ino(sk)) < 0) {`
`172`	`172`	`ret = 1;`
`173`	`173`	`break;`
`174`	`174`	`}`