sunrpc: add netlink upcall for the auth.unix.ip cache

Add netlink-based cache upcall support for the ip_map (auth.unix.ip)
cache, using the sunrpc generic netlink family.

Add ip-map attribute-set (seqno, class, addr, domain, negative, expiry),
ip-map-reqs wrapper, and ip-map-get-reqs / ip-map-set-reqs operations
to the sunrpc_cache YAML spec and generated headers.

Implement sunrpc_nl_ip_map_get_reqs_dumpit() which snapshots pending
ip_map cache requests and sends each entry's seqno, class name, and
IP address over netlink.

Implement sunrpc_nl_ip_map_set_reqs_doit() which parses ip_map cache
responses from userspace (class, addr, expiry, and domain name or
negative flag) and updates the cache via __ip_map_lookup() /
__ip_map_update().

Wire up ip_map_notify() callback in ip_map_cache_template so cache
misses trigger SUNRPC_CMD_CACHE_NOTIFY multicast events with
SUNRPC_CACHE_TYPE_IP_MAP.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>

Documentation/netlink/specs/sunrpc_cache.yaml

@@ -20,6 +20,35 @@ attribute-sets:
         name: cache-type
         type: u32
         enum: cache-type
+  -
+    name: ip-map
+    attributes:
+      -
+        name: seqno
+        type: u64
+      -
+        name: class
+        type: string
+      -
+        name: addr
+        type: string
+      -
+        name: domain
+        type: string
+      -
+        name: negative
+        type: flag
+      -
+        name: expiry
+        type: u64
+  -
+    name: ip-map-reqs
+    attributes:
+      -
+        name: requests
+        type: nest
+        nested-attributes: ip-map
+        multi-attr: true
 
 operations:
   list:
@@ -31,6 +60,24 @@ operations:
       event:
         attributes:
           - cache-type
+    -
+      name: ip-map-get-reqs
+      doc: Dump all pending ip_map requests
+      attribute-set: ip-map-reqs
+      flags: [admin-perm]
+      dump:
+          request:
+            attributes:
+              - requests
+    -
+      name: ip-map-set-reqs
+      doc: Respond to one or more ip_map requests
+      attribute-set: ip-map-reqs
+      flags: [admin-perm]
+      do:
+          request:
+            attributes:
+              - requests
 
 mcast-groups:
   list:

include/uapi/linux/sunrpc_netlink.h

@@ -22,8 +22,29 @@ enum {
 	SUNRPC_A_CACHE_NOTIFY_MAX = (__SUNRPC_A_CACHE_NOTIFY_MAX - 1)
 };
 
+enum {
+	SUNRPC_A_IP_MAP_SEQNO = 1,
+	SUNRPC_A_IP_MAP_CLASS,
+	SUNRPC_A_IP_MAP_ADDR,
+	SUNRPC_A_IP_MAP_DOMAIN,
+	SUNRPC_A_IP_MAP_NEGATIVE,
+	SUNRPC_A_IP_MAP_EXPIRY,
+
+	__SUNRPC_A_IP_MAP_MAX,
+	SUNRPC_A_IP_MAP_MAX = (__SUNRPC_A_IP_MAP_MAX - 1)
+};
+
+enum {
+	SUNRPC_A_IP_MAP_REQS_REQUESTS = 1,
+
+	__SUNRPC_A_IP_MAP_REQS_MAX,
+	SUNRPC_A_IP_MAP_REQS_MAX = (__SUNRPC_A_IP_MAP_REQS_MAX - 1)
+};
+
 enum {
 	SUNRPC_CMD_CACHE_NOTIFY = 1,
+	SUNRPC_CMD_IP_MAP_GET_REQS,
+	SUNRPC_CMD_IP_MAP_SET_REQS,
 
 	__SUNRPC_CMD_MAX,
 	SUNRPC_CMD_MAX = (__SUNRPC_CMD_MAX - 1)

net/sunrpc/netlink.c

@@ -12,8 +12,42 @@
 
 #include <uapi/linux/sunrpc_netlink.h>
 
+/* Common nested types */
+const struct nla_policy sunrpc_ip_map_nl_policy[SUNRPC_A_IP_MAP_EXPIRY + 1] = {
+	[SUNRPC_A_IP_MAP_SEQNO] = { .type = NLA_U64, },
+	[SUNRPC_A_IP_MAP_CLASS] = { .type = NLA_NUL_STRING, },
+	[SUNRPC_A_IP_MAP_ADDR] = { .type = NLA_NUL_STRING, },
+	[SUNRPC_A_IP_MAP_DOMAIN] = { .type = NLA_NUL_STRING, },
+	[SUNRPC_A_IP_MAP_NEGATIVE] = { .type = NLA_FLAG, },
+	[SUNRPC_A_IP_MAP_EXPIRY] = { .type = NLA_U64, },
+};
+
+/* SUNRPC_CMD_IP_MAP_GET_REQS - dump */
+static const struct nla_policy sunrpc_ip_map_get_reqs_nl_policy[SUNRPC_A_IP_MAP_REQS_REQUESTS + 1] = {
+	[SUNRPC_A_IP_MAP_REQS_REQUESTS] = NLA_POLICY_NESTED(sunrpc_ip_map_nl_policy),
+};
+
+/* SUNRPC_CMD_IP_MAP_SET_REQS - do */
+static const struct nla_policy sunrpc_ip_map_set_reqs_nl_policy[SUNRPC_A_IP_MAP_REQS_REQUESTS + 1] = {
+	[SUNRPC_A_IP_MAP_REQS_REQUESTS] = NLA_POLICY_NESTED(sunrpc_ip_map_nl_policy),
+};
+
 /* Ops table for sunrpc */
 static const struct genl_split_ops sunrpc_nl_ops[] = {
+	{
+		.cmd		= SUNRPC_CMD_IP_MAP_GET_REQS,
+		.dumpit		= sunrpc_nl_ip_map_get_reqs_dumpit,
+		.policy		= sunrpc_ip_map_get_reqs_nl_policy,
+		.maxattr	= SUNRPC_A_IP_MAP_REQS_REQUESTS,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= SUNRPC_CMD_IP_MAP_SET_REQS,
+		.doit		= sunrpc_nl_ip_map_set_reqs_doit,
+		.policy		= sunrpc_ip_map_set_reqs_nl_policy,
+		.maxattr	= SUNRPC_A_IP_MAP_REQS_REQUESTS,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
 };
 
 static const struct genl_multicast_group sunrpc_nl_mcgrps[] = {

net/sunrpc/netlink.h

@@ -12,6 +12,14 @@
 
 #include <uapi/linux/sunrpc_netlink.h>
 
+/* Common nested types */
+extern const struct nla_policy sunrpc_ip_map_nl_policy[SUNRPC_A_IP_MAP_EXPIRY + 1];
+
+int sunrpc_nl_ip_map_get_reqs_dumpit(struct sk_buff *skb,
+				     struct netlink_callback *cb);
+int sunrpc_nl_ip_map_set_reqs_doit(struct sk_buff *skb,
+				   struct genl_info *info);
+
 enum {
 	SUNRPC_NLGRP_NONE,
 	SUNRPC_NLGRP_EXPORTD,

net/sunrpc/svcauth_unix.c

@@ -17,11 +17,14 @@
 #include <net/ipv6.h>
 #include <linux/kernel.h>
 #include <linux/user_namespace.h>
+#include <net/genetlink.h>
+#include <uapi/linux/sunrpc_netlink.h>
 #include <trace/events/sunrpc.h>
 
 #define RPCDBG_FACILITY	RPCDBG_AUTH
 
 #include "netns.h"
+#include "netlink.h"
 
 /*
  * AUTHUNIX and AUTHNULL credentials are both handled here.
@@ -1017,12 +1020,255 @@ struct auth_ops svcauth_unix = {
 	.set_client	= svcauth_unix_set_client,
 };
 
+static int ip_map_notify(struct cache_detail *cd, struct cache_head *h)
+{
+	return sunrpc_cache_notify(cd, h, SUNRPC_CACHE_TYPE_IP_MAP);
+}
+
+/**
+ * sunrpc_nl_ip_map_get_reqs_dumpit - dump pending ip_map requests
+ * @skb: reply buffer
+ * @cb: netlink metadata and command arguments
+ *
+ * Walk the ip_map cache's pending request list and create a netlink
+ * message with a nested entry for each cache_request, containing the
+ * seqno, class and addr.
+ *
+ * Uses cb->args[0] as a seqno cursor for dump continuation across
+ * multiple netlink messages.
+ *
+ * Returns the size of the reply or a negative errno.
+ */
+int sunrpc_nl_ip_map_get_reqs_dumpit(struct sk_buff *skb,
+				     struct netlink_callback *cb)
+{
+	struct sunrpc_net *sn;
+	struct cache_detail *cd;
+	struct cache_head **items;
+	u64 *seqnos;
+	int cnt, i, emitted;
+	void *hdr;
+	int ret;
+
+	sn = net_generic(sock_net(skb->sk), sunrpc_net_id);
+
+	cd = sn->ip_map_cache;
+	if (!cd)
+		return -ENODEV;
+
+	cnt = sunrpc_cache_requests_count(cd);
+	if (!cnt)
+		return 0;
+
+	items = kcalloc(cnt, sizeof(*items), GFP_KERNEL);
+	seqnos = kcalloc(cnt, sizeof(*seqnos), GFP_KERNEL);
+	if (!items || !seqnos) {
+		ret = -ENOMEM;
+		goto out_alloc;
+	}
+
+	cnt = sunrpc_cache_requests_snapshot(cd, items, seqnos, cnt,
+					     cb->args[0]);
+	if (!cnt) {
+		ret = 0;
+		goto out_alloc;
+	}
+
+	hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid,
+			  cb->nlh->nlmsg_seq, &sunrpc_nl_family,
+			  NLM_F_MULTI, SUNRPC_CMD_IP_MAP_GET_REQS);
+	if (!hdr) {
+		ret = -ENOBUFS;
+		goto out_put;
+	}
+
+	emitted = 0;
+	for (i = 0; i < cnt; i++) {
+		struct ip_map *im;
+		struct nlattr *nest;
+		char text_addr[40];
+
+		im = container_of(items[i], struct ip_map, h);
+
+		if (ipv6_addr_v4mapped(&im->m_addr))
+			snprintf(text_addr, 20, "%pI4",
+				 &im->m_addr.s6_addr32[3]);
+		else
+			snprintf(text_addr, 40, "%pI6", &im->m_addr);
+
+		nest = nla_nest_start(skb, SUNRPC_A_IP_MAP_REQS_REQUESTS);
+		if (!nest)
+			break;
+
+		if (nla_put_u64_64bit(skb, SUNRPC_A_IP_MAP_SEQNO,
+				      seqnos[i], 0) ||
+		    nla_put_string(skb, SUNRPC_A_IP_MAP_CLASS,
+				   im->m_class) ||
+		    nla_put_string(skb, SUNRPC_A_IP_MAP_ADDR, text_addr)) {
+			nla_nest_cancel(skb, nest);
+			break;
+		}
+
+		nla_nest_end(skb, nest);
+		cb->args[0] = seqnos[i];
+		emitted++;
+	}
+
+	if (!emitted) {
+		genlmsg_cancel(skb, hdr);
+		ret = -EMSGSIZE;
+		goto out_put;
+	}
+
+	genlmsg_end(skb, hdr);
+	ret = skb->len;
+out_put:
+	for (i = 0; i < cnt; i++)
+		cache_put(items[i], cd);
+out_alloc:
+	kfree(seqnos);
+	kfree(items);
+	return ret;
+}
+
+/**
+ * sunrpc_nl_parse_one_ip_map - parse one ip_map entry from netlink
+ * @cd: cache_detail for the ip_map cache
+ * @attr: nested attribute containing ip_map fields
+ *
+ * Parses one ip_map entry from a netlink message and updates the
+ * cache. Mirrors the logic in ip_map_parse().
+ *
+ * Returns 0 on success or a negative errno.
+ */
+static int sunrpc_nl_parse_one_ip_map(struct cache_detail *cd,
+				      struct nlattr *attr)
+{
+	struct nlattr *tb[SUNRPC_A_IP_MAP_EXPIRY + 1];
+	union {
+		struct sockaddr		sa;
+		struct sockaddr_in	s4;
+		struct sockaddr_in6	s6;
+	} address;
+	struct sockaddr_in6 sin6;
+	struct ip_map *ipmp;
+	struct auth_domain *dom = NULL;
+	struct unix_domain *udom = NULL;
+	struct timespec64 boot;
+	time64_t expiry;
+	char class[8];
+	int err;
+	int len;
+
+	err = nla_parse_nested(tb, SUNRPC_A_IP_MAP_EXPIRY, attr,
+			       sunrpc_ip_map_nl_policy, NULL);
+	if (err)
+		return err;
+
+	/* class (required) */
+	if (!tb[SUNRPC_A_IP_MAP_CLASS])
+		return -EINVAL;
+	len = nla_len(tb[SUNRPC_A_IP_MAP_CLASS]);
+	if (len <= 0 || len > sizeof(class))
+		return -EINVAL;
+	nla_strscpy(class, tb[SUNRPC_A_IP_MAP_CLASS], sizeof(class));
+
+	/* addr (required) */
+	if (!tb[SUNRPC_A_IP_MAP_ADDR])
+		return -EINVAL;
+	if (rpc_pton(cd->net, nla_data(tb[SUNRPC_A_IP_MAP_ADDR]),
+		     nla_len(tb[SUNRPC_A_IP_MAP_ADDR]) - 1,
+		     &address.sa, sizeof(address)) == 0)
+		return -EINVAL;
+
+	switch (address.sa.sa_family) {
+	case AF_INET:
+		sin6.sin6_family = AF_INET6;
+		ipv6_addr_set_v4mapped(address.s4.sin_addr.s_addr,
+				       &sin6.sin6_addr);
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		memcpy(&sin6, &address.s6, sizeof(sin6));
+		break;
+#endif
+	default:
+		return -EINVAL;
+	}
+
+	/* expiry (required, wallclock seconds) */
+	if (!tb[SUNRPC_A_IP_MAP_EXPIRY])
+		return -EINVAL;
+	getboottime64(&boot);
+	expiry = nla_get_u64(tb[SUNRPC_A_IP_MAP_EXPIRY]) - boot.tv_sec;
+
+	/* domain name or negative */
+	if (tb[SUNRPC_A_IP_MAP_NEGATIVE]) {
+		udom = NULL;
+	} else if (tb[SUNRPC_A_IP_MAP_DOMAIN]) {
+		dom = unix_domain_find(nla_data(tb[SUNRPC_A_IP_MAP_DOMAIN]));
+		if (!dom)
+			return -ENOENT;
+		udom = container_of(dom, struct unix_domain, h);
+	} else {
+		return -EINVAL;
+	}
+
+	ipmp = __ip_map_lookup(cd, class, &sin6.sin6_addr);
+	if (ipmp)
+		err = __ip_map_update(cd, ipmp, udom, expiry);
+	else
+		err = -ENOMEM;
+
+	if (dom)
+		auth_domain_put(dom);
+
+	cache_flush();
+	return err;
+}
+
+/**
+ * sunrpc_nl_ip_map_set_reqs_doit - respond to ip_map requests
+ * @skb: reply buffer
+ * @info: netlink metadata and command arguments
+ *
+ * Parse one or more ip_map cache responses from userspace and
+ * update the ip_map cache accordingly.
+ *
+ * Returns 0 on success or a negative errno.
+ */
+int sunrpc_nl_ip_map_set_reqs_doit(struct sk_buff *skb,
+				   struct genl_info *info)
+{
+	struct sunrpc_net *sn;
+	struct cache_detail *cd;
+	const struct nlattr *attr;
+	int rem, ret = 0;
+
+	sn = net_generic(genl_info_net(info), sunrpc_net_id);
+
+	cd = sn->ip_map_cache;
+	if (!cd)
+		return -ENODEV;
+
+	nlmsg_for_each_attr_type(attr, SUNRPC_A_IP_MAP_REQS_REQUESTS,
+				 info->nlhdr, GENL_HDRLEN, rem) {
+		ret = sunrpc_nl_parse_one_ip_map(cd,
+						 (struct nlattr *)attr);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
 static const struct cache_detail ip_map_cache_template = {
 	.owner		= THIS_MODULE,
 	.hash_size	= IP_HASHMAX,
 	.name		= "auth.unix.ip",
 	.cache_put	= ip_map_put,
 	.cache_upcall	= ip_map_upcall,
+	.cache_notify	= ip_map_notify,
 	.cache_request	= ip_map_request,
 	.cache_parse	= ip_map_parse,
 	.cache_show	= ip_map_show,