[PATCH -stable 1/1] ipvs: separate destination availability state

[Julian Anastasov <ja@ssi.bg>]

From: Yizhou Zhao <zhaoyz24@mails.tsinghua.edu.cn>

commit cdcc4e46180df8161f4d2f3c6fd6beaf6990133d upstream.

IPVS configuration paths update destination availability while connection
accounting updates destination overload state. The two independent states
share dest->flags, so their read-modify-write updates can race and lose one
another.

Keep OVERLOAD in flags, where the preceding patch serializes its updates
with dst_lock, and move AVAILABLE to cflags. This keeps configuration-
controlled availability out of the scheduler hot cacheline until a
scheduler needs to check it. It also prevents availability updates from
clobbering overload state.

The destination status bits are not exposed through the IPVS sockopt or
netlink interfaces, so keep their definitions in the internal IPVS header.

Readers can still observe stale destination state; this does not provide a
cross-field snapshot.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Cc: stable@vger.kernel.org
Reported-by: Yizhou Zhao <zhaoyz24@mails.tsinghua.edu.cn>
Reported-by: Yuxiang Yang <yangyx22@mails.tsinghua.edu.cn>
Reported-by: Ao Wang <wangao@seu.edu.cn>
Reported-by: Xuewei Feng <fengxw06@126.com>
Reported-by: Qi Li <qli01@tsinghua.edu.cn>
Reported-by: Ke Xu <xuke@tsinghua.edu.cn>
Link: https://lore.kernel.org/all/8913381c-1e02-35c7-0ec4-61de5a12fd35@ssi.bg/
Assisted-by: Claude-Code:GLM-5.2
Suggested-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Yizhou Zhao <zhaoyz24@mails.tsinghua.edu.cn>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
(cherry picked from commit cdcc4e46180df8161f4d2f3c6fd6beaf6990133d)
[ Julian: Backport by removing the hunks from ip_vs_xmit.c ]
Signed-off-by: Julian Anastasov <ja@ssi.bg>
---
 include/net/ip_vs.h              | 7 +++++++
 include/uapi/linux/ip_vs.h       | 6 ------
 net/netfilter/ipvs/ip_vs_conn.c  | 4 ++--
 net/netfilter/ipvs/ip_vs_core.c  | 6 +++---
 net/netfilter/ipvs/ip_vs_ctl.c   | 4 ++--
 net/netfilter/ipvs/ip_vs_dh.c    | 4 ++--
 net/netfilter/ipvs/ip_vs_lblc.c  | 2 +-
 net/netfilter/ipvs/ip_vs_lblcr.c | 8 ++++----
 8 files changed, 21 insertions(+), 20 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index b65009a226e0..94dfc3a265ee 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -34,6 +34,12 @@
 #define IP_VS_HDR_INVERSE	1
 #define IP_VS_HDR_ICMP		2
 
+/* Destination Server Flags */
+#define IP_VS_DEST_F_OVERLOAD	0x0002		/* server is overloaded */
+
+/* Destination Server Config Flags */
+#define IP_VS_DEST_CF_AVAILABLE	0x0001		/* server is available */
+
 /* Generic access of ipvs struct */
 static inline struct netns_ipvs *net_ipvs(struct net* net)
 {
@@ -725,6 +731,7 @@ struct ip_vs_dest {
 	volatile unsigned int	flags;		/* dest status flags */
 	atomic_t		conn_flags;	/* flags to copy to conn */
 	atomic_t		weight;		/* server weight */
+	unsigned long		cflags;		/* config flags */
 	atomic_t		last_weight;	/* server latest weight */
 	__u16			tun_type;	/* tunnel type */
 	__be16			tun_port;	/* tunnel port */
diff --git a/include/uapi/linux/ip_vs.h b/include/uapi/linux/ip_vs.h
index 1ed234e7f251..2c37c6ac7525 100644
--- a/include/uapi/linux/ip_vs.h
+++ b/include/uapi/linux/ip_vs.h
@@ -28,12 +28,6 @@
 #define IP_VS_SVC_F_SCHED_SH_FALLBACK	IP_VS_SVC_F_SCHED1 /* SH fallback */
 #define IP_VS_SVC_F_SCHED_SH_PORT	IP_VS_SVC_F_SCHED2 /* SH use port */
 
-/*
- *      Destination Server Flags
- */
-#define IP_VS_DEST_F_AVAILABLE	0x0001		/* server is available */
-#define IP_VS_DEST_F_OVERLOAD	0x0002		/* server is overloaded */
-
 /*
  *      IPVS sync daemon states
  */
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index e42fed876596..7da11628073b 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -759,7 +759,7 @@ int ip_vs_check_template(struct ip_vs_conn *ct, struct ip_vs_dest *cdest)
 	 * Checking the dest server status.
 	 */
 	if ((dest == NULL) ||
-	    !(dest->flags & IP_VS_DEST_F_AVAILABLE) ||
+	    !(dest->cflags & IP_VS_DEST_CF_AVAILABLE) ||
 	    expire_quiescent_template(ipvs, dest) ||
 	    (cdest && (dest != cdest))) {
 		IP_VS_DBG_BUF(9, "check_template: dest not available for "
@@ -1408,7 +1408,7 @@ void ip_vs_expire_nodest_conn_flush(struct netns_ipvs *ipvs)
 				continue;
 
 			dest = cp->dest;
-			if (!dest || (dest->flags & IP_VS_DEST_F_AVAILABLE))
+			if (!dest || (dest->cflags & IP_VS_DEST_CF_AVAILABLE))
 				continue;
 
 			if (atomic_read(&cp->n_control))
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index d121ea3d16bc..1f62ca2f7330 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -124,7 +124,7 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 	struct ip_vs_dest *dest = cp->dest;
 	struct netns_ipvs *ipvs = cp->ipvs;
 
-	if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
+	if (dest && (dest->cflags & IP_VS_DEST_CF_AVAILABLE)) {
 		struct ip_vs_cpu_stats *s;
 		struct ip_vs_service *svc;
 
@@ -160,7 +160,7 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
 	struct ip_vs_dest *dest = cp->dest;
 	struct netns_ipvs *ipvs = cp->ipvs;
 
-	if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
+	if (dest && (dest->cflags & IP_VS_DEST_CF_AVAILABLE)) {
 		struct ip_vs_cpu_stats *s;
 		struct ip_vs_service *svc;
 
@@ -2030,7 +2030,7 @@ ip_vs_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state
 	}
 
 	/* Check the server status */
-	if (cp && cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
+	if (cp && cp->dest && !(cp->dest->cflags & IP_VS_DEST_CF_AVAILABLE)) {
 		/* the destination server is not available */
 		if (sysctl_expire_nodest_conn(ipvs)) {
 			bool old_ct = ip_vs_conn_uses_old_conntrack(cp, skb);
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 5dea5a14e85f..c0257ef4d8b0 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1058,7 +1058,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 	}
 
 	/* set the dest status flags */
-	dest->flags |= IP_VS_DEST_F_AVAILABLE;
+	dest->cflags |= IP_VS_DEST_CF_AVAILABLE;
 
 	if (READ_ONCE(dest->u_threshold) != udest->u_threshold ||
 	    READ_ONCE(dest->l_threshold) != udest->l_threshold) {
@@ -1325,7 +1325,7 @@ static void __ip_vs_unlink_dest(struct ip_vs_service *svc,
 				struct ip_vs_dest *dest,
 				int svcupd)
 {
-	dest->flags &= ~IP_VS_DEST_F_AVAILABLE;
+	dest->cflags &= ~IP_VS_DEST_CF_AVAILABLE;
 
 	/*
 	 *  Remove it from the d-linked destination list.
diff --git a/net/netfilter/ipvs/ip_vs_dh.c b/net/netfilter/ipvs/ip_vs_dh.c
index 75f4c231f4a0..f04d2530a093 100644
--- a/net/netfilter/ipvs/ip_vs_dh.c
+++ b/net/netfilter/ipvs/ip_vs_dh.c
@@ -220,8 +220,8 @@ ip_vs_dh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
 
 	s = (struct ip_vs_dh_state *) svc->sched_data;
 	dest = ip_vs_dh_get(svc->af, s, &iph->daddr);
-	if (!dest
-	    || !(dest->flags & IP_VS_DEST_F_AVAILABLE)
+	if (!dest ||
+	    !(dest->cflags & IP_VS_DEST_CF_AVAILABLE)
 	    || atomic_read(&dest->weight) <= 0
 	    || is_overloaded(dest)) {
 		ip_vs_scheduler_err(svc, "no destination available");
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index 156181a3bacd..9bb1e05063dc 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -503,7 +503,7 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb,
 		 */
 
 		dest = en->dest;
-		if ((dest->flags & IP_VS_DEST_F_AVAILABLE) &&
+		if ((dest->cflags & IP_VS_DEST_CF_AVAILABLE) &&
 		    atomic_read(&dest->weight) > 0 && !is_overloaded(dest, svc))
 			goto out;
 	}
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index a021e6aba3d7..1a53c1254fe5 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -170,8 +170,8 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set)
 		if (least->flags & IP_VS_DEST_F_OVERLOAD)
 			continue;
 
-		if ((atomic_read(&least->weight) > 0)
-		    && (least->flags & IP_VS_DEST_F_AVAILABLE)) {
+		if ((atomic_read(&least->weight) > 0) &&
+		    (least->cflags & IP_VS_DEST_CF_AVAILABLE)) {
 			loh = ip_vs_dest_conn_overhead(least);
 			goto nextstage;
 		}
@@ -187,8 +187,8 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set)
 
 		doh = ip_vs_dest_conn_overhead(dest);
 		if (((__s64)loh * atomic_read(&dest->weight) >
-		     (__s64)doh * atomic_read(&least->weight))
-		    && (dest->flags & IP_VS_DEST_F_AVAILABLE)) {
+		     (__s64)doh * atomic_read(&least->weight)) &&
+		    (dest->cflags & IP_VS_DEST_CF_AVAILABLE)) {
 			least = dest;
 			loh = doh;
 		}
-- 
2.55.0