* [PATCH v2 net-next 22/23] rtnetlink: Move input checking for rtnl_fdb_dump to helper
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Move the existing input checking for rtnl_fdb_dump into a helper,
valid_fdb_dump_legacy. This function will retain the current
logic that works around the 2 headers that userspace has been
allowed to send up to this point.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/core/rtnetlink.c | 53 ++++++++++++++++++++++++++++++++--------------------
1 file changed, 33 insertions(+), 20 deletions(-)
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index f6d2609cfa9f..c7509c789fb6 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3799,22 +3799,13 @@ int ndo_dflt_fdb_dump(struct sk_buff *skb,
}
EXPORT_SYMBOL(ndo_dflt_fdb_dump);
-static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
+static int valid_fdb_dump_legacy(const struct nlmsghdr *nlh,
+ int *br_idx, int *brport_idx,
+ struct netlink_ext_ack *extack)
{
- struct net_device *dev;
+ struct ifinfomsg *ifm = nlmsg_data(nlh);
struct nlattr *tb[IFLA_MAX+1];
- struct net_device *br_dev = NULL;
- const struct net_device_ops *ops = NULL;
- const struct net_device_ops *cops = NULL;
- struct ifinfomsg *ifm = nlmsg_data(cb->nlh);
- struct net *net = sock_net(skb->sk);
- struct hlist_head *head;
- int brport_idx = 0;
- int br_idx = 0;
- int h, s_h;
- int idx = 0, s_idx;
- int err = 0;
- int fidx = 0;
+ int err;
/* A hack to preserve kernel<->userspace interface.
* Before Linux v4.12 this code accepted ndmsg since iproute2 v3.3.0.
@@ -3823,20 +3814,42 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
* Fortunately these sizes don't conflict with the size of ifinfomsg
* with an optional attribute.
*/
- if (nlmsg_len(cb->nlh) != sizeof(struct ndmsg) &&
- (nlmsg_len(cb->nlh) != sizeof(struct ndmsg) +
+ if (nlmsg_len(nlh) != sizeof(struct ndmsg) &&
+ (nlmsg_len(nlh) != sizeof(struct ndmsg) +
nla_attr_size(sizeof(u32)))) {
- err = nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb,
- IFLA_MAX, ifla_policy, cb->extack);
+ err = nlmsg_parse(nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX,
+ ifla_policy, extack);
if (err < 0) {
return -EINVAL;
} else if (err == 0) {
if (tb[IFLA_MASTER])
- br_idx = nla_get_u32(tb[IFLA_MASTER]);
+ *br_idx = nla_get_u32(tb[IFLA_MASTER]);
}
- brport_idx = ifm->ifi_index;
+ *brport_idx = ifm->ifi_index;
}
+ return 0;
+}
+
+static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+ struct net_device *dev;
+ struct net_device *br_dev = NULL;
+ const struct net_device_ops *ops = NULL;
+ const struct net_device_ops *cops = NULL;
+ struct net *net = sock_net(skb->sk);
+ struct hlist_head *head;
+ int brport_idx = 0;
+ int br_idx = 0;
+ int h, s_h;
+ int idx = 0, s_idx;
+ int err = 0;
+ int fidx = 0;
+
+ err = valid_fdb_dump_legacy(cb->nlh, &br_idx, &brport_idx,
+ cb->extack);
+ if (err < 0)
+ return err;
if (br_idx) {
br_dev = __dev_get_by_index(net, br_idx);
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 23/23] rtnetlink: Update rtnl_fdb_dump for strict data checking
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Update rtnl_fdb_dump for strict data checking. If the flag is set,
the dump request is expected to have an ndmsg struct as the header
potentially followed by one or more attributes. Any data passed in the
header or as an attribute is taken as a request to influence the data
returned. Only values supported by the dump handler are allowed to be
non-0 or set in the request. At the moment only the NDA_IFINDEX and
NDA_MASTER attributes are supported.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/core/rtnetlink.c | 62 ++++++++++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 60 insertions(+), 2 deletions(-)
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index c7509c789fb6..c894c4af8981 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3799,6 +3799,60 @@ int ndo_dflt_fdb_dump(struct sk_buff *skb,
}
EXPORT_SYMBOL(ndo_dflt_fdb_dump);
+static int valid_fdb_dump_strict(const struct nlmsghdr *nlh,
+ int *br_idx, int *brport_idx,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[NDA_MAX + 1];
+ struct ndmsg *ndm;
+ int err, i;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ndm))) {
+ NL_SET_ERR_MSG(extack, "Invalid header for fdb dump request");
+ return -EINVAL;
+ }
+
+ ndm = nlmsg_data(nlh);
+ if (ndm->ndm_pad1 || ndm->ndm_pad2 || ndm->ndm_state ||
+ ndm->ndm_flags || ndm->ndm_type) {
+ NL_SET_ERR_MSG(extack, "Invalid values in header for fbd dump request");
+ return -EINVAL;
+ }
+
+ err = nlmsg_parse_strict(nlh, sizeof(struct ndmsg), tb, NDA_MAX,
+ NULL, extack);
+ if (err < 0)
+ return err;
+
+ *brport_idx = ndm->ndm_ifindex;
+ for (i = 0; i <= NDA_MAX; ++i) {
+ if (!tb[i])
+ continue;
+
+ switch (i) {
+ case NDA_IFINDEX:
+ if (nla_len(tb[i]) != sizeof(u32)) {
+ NL_SET_ERR_MSG(extack, "Invalid IFINDEX attribute in fdb dump request");
+ return -EINVAL;
+ }
+ *brport_idx = nla_get_u32(tb[NDA_IFINDEX]);
+ break;
+ case NDA_MASTER:
+ if (nla_len(tb[i]) != sizeof(u32)) {
+ NL_SET_ERR_MSG(extack, "Invalid MASTER attribute in fdb dump request");
+ return -EINVAL;
+ }
+ *br_idx = nla_get_u32(tb[NDA_MASTER]);
+ break;
+ default:
+ NL_SET_ERR_MSG(extack, "Unsupported attribute in fdb dump request");
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
static int valid_fdb_dump_legacy(const struct nlmsghdr *nlh,
int *br_idx, int *brport_idx,
struct netlink_ext_ack *extack)
@@ -3846,8 +3900,12 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
int err = 0;
int fidx = 0;
- err = valid_fdb_dump_legacy(cb->nlh, &br_idx, &brport_idx,
- cb->extack);
+ if (cb->strict_check)
+ err = valid_fdb_dump_strict(cb->nlh, &br_idx, &brport_idx,
+ cb->extack);
+ else
+ err = valid_fdb_dump_legacy(cb->nlh, &br_idx, &brport_idx,
+ cb->extack);
if (err < 0)
return err;
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 19/23] net/ipv6: Update ip6addrlbl_dump for strict data checking
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Update ip6addrlbl_dump for strict data checking. If the flag is set,
the dump request is expected to have an ifaddrlblmsg struct as the
header. All elements of the struct are expected to be 0 and no
attributes can be appended.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/ipv6/addrlabel.c | 34 +++++++++++++++++++++++++++++++++-
1 file changed, 33 insertions(+), 1 deletion(-)
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index 1d6ced37ad71..0d1ee82ee55b 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -458,20 +458,52 @@ static int ip6addrlbl_fill(struct sk_buff *skb,
return 0;
}
+static int ip6addrlbl_valid_dump_req(const struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ struct ifaddrlblmsg *ifal;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifal))) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid header for address label dump request");
+ return -EINVAL;
+ }
+
+ ifal = nlmsg_data(nlh);
+ if (ifal->__ifal_reserved || ifal->ifal_prefixlen ||
+ ifal->ifal_flags || ifal->ifal_index || ifal->ifal_seq) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for address label dump request");
+ return -EINVAL;
+ }
+
+ if (nlmsg_attrlen(nlh, sizeof(*ifal))) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid data after header for address label dump requewst");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
+ const struct nlmsghdr *nlh = cb->nlh;
struct net *net = sock_net(skb->sk);
struct ip6addrlbl_entry *p;
int idx = 0, s_idx = cb->args[0];
int err;
+ if (cb->strict_check) {
+ err = ip6addrlbl_valid_dump_req(nlh, cb->extack);
+ if (err < 0)
+ return err;
+ }
+
rcu_read_lock();
hlist_for_each_entry_rcu(p, &net->ipv6.ip6addrlbl_table.head, list) {
if (idx >= s_idx) {
err = ip6addrlbl_fill(skb, p,
net->ipv6.ip6addrlbl_table.seq,
NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq,
+ nlh->nlmsg_seq,
RTM_NEWADDRLABEL,
NLM_F_MULTI);
if (err < 0)
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 20/23] net: Update netconf dump handlers for strict data checking
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Update inet_netconf_dump_devconf, inet6_netconf_dump_devconf, and
mpls_netconf_dump_devconf for strict data checking. If the flag is set,
the dump request is expected to have an netconfmsg struct as the header.
The struct only has the family member and no attributes can be appended.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/ipv4/devinet.c | 22 +++++++++++++++++++---
net/ipv6/addrconf.c | 22 +++++++++++++++++++---
net/mpls/af_mpls.c | 18 +++++++++++++++++-
3 files changed, 55 insertions(+), 7 deletions(-)
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 6f2bbd04e950..d122ebbe5980 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -2086,6 +2086,7 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb,
static int inet_netconf_dump_devconf(struct sk_buff *skb,
struct netlink_callback *cb)
{
+ const struct nlmsghdr *nlh = cb->nlh;
struct net *net = sock_net(skb->sk);
int h, s_h;
int idx, s_idx;
@@ -2093,6 +2094,21 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb,
struct in_device *in_dev;
struct hlist_head *head;
+ if (cb->strict_check) {
+ struct netlink_ext_ack *extack = cb->extack;
+ struct netconfmsg *ncm;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ncm))) {
+ NL_SET_ERR_MSG(extack, "ipv4: Invalid header for netconf dump request");
+ return -EINVAL;
+ }
+
+ if (nlmsg_attrlen(nlh, sizeof(*ncm))) {
+ NL_SET_ERR_MSG(extack, "ipv4: Invalid data after header in netconf dump request");
+ return -EINVAL;
+ }
+ }
+
s_h = cb->args[0];
s_idx = idx = cb->args[1];
@@ -2112,7 +2128,7 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb,
if (inet_netconf_fill_devconf(skb, dev->ifindex,
&in_dev->cnf,
NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq,
+ nlh->nlmsg_seq,
RTM_NEWNETCONF,
NLM_F_MULTI,
NETCONFA_ALL) < 0) {
@@ -2129,7 +2145,7 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb,
if (inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL,
net->ipv4.devconf_all,
NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq,
+ nlh->nlmsg_seq,
RTM_NEWNETCONF, NLM_F_MULTI,
NETCONFA_ALL) < 0)
goto done;
@@ -2140,7 +2156,7 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb,
if (inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT,
net->ipv4.devconf_dflt,
NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq,
+ nlh->nlmsg_seq,
RTM_NEWNETCONF, NLM_F_MULTI,
NETCONFA_ALL) < 0)
goto done;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index ce071d85ad00..2496b12bf721 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -666,6 +666,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb,
static int inet6_netconf_dump_devconf(struct sk_buff *skb,
struct netlink_callback *cb)
{
+ const struct nlmsghdr *nlh = cb->nlh;
struct net *net = sock_net(skb->sk);
int h, s_h;
int idx, s_idx;
@@ -673,6 +674,21 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb,
struct inet6_dev *idev;
struct hlist_head *head;
+ if (cb->strict_check) {
+ struct netlink_ext_ack *extack = cb->extack;
+ struct netconfmsg *ncm;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ncm))) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid header for netconf dump request");
+ return -EINVAL;
+ }
+
+ if (nlmsg_attrlen(nlh, sizeof(*ncm))) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid data after header in netconf dump request");
+ return -EINVAL;
+ }
+ }
+
s_h = cb->args[0];
s_idx = idx = cb->args[1];
@@ -692,7 +708,7 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb,
if (inet6_netconf_fill_devconf(skb, dev->ifindex,
&idev->cnf,
NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq,
+ nlh->nlmsg_seq,
RTM_NEWNETCONF,
NLM_F_MULTI,
NETCONFA_ALL) < 0) {
@@ -709,7 +725,7 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb,
if (inet6_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL,
net->ipv6.devconf_all,
NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq,
+ nlh->nlmsg_seq,
RTM_NEWNETCONF, NLM_F_MULTI,
NETCONFA_ALL) < 0)
goto done;
@@ -720,7 +736,7 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb,
if (inet6_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT,
net->ipv6.devconf_dflt,
NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq,
+ nlh->nlmsg_seq,
RTM_NEWNETCONF, NLM_F_MULTI,
NETCONFA_ALL) < 0)
goto done;
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 0458c8aa5c11..7f891ffffc05 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -1263,6 +1263,7 @@ static int mpls_netconf_get_devconf(struct sk_buff *in_skb,
static int mpls_netconf_dump_devconf(struct sk_buff *skb,
struct netlink_callback *cb)
{
+ const struct nlmsghdr *nlh = cb->nlh;
struct net *net = sock_net(skb->sk);
struct hlist_head *head;
struct net_device *dev;
@@ -1270,6 +1271,21 @@ static int mpls_netconf_dump_devconf(struct sk_buff *skb,
int idx, s_idx;
int h, s_h;
+ if (cb->strict_check) {
+ struct netlink_ext_ack *extack = cb->extack;
+ struct netconfmsg *ncm;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ncm))) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid header for netconf dump request");
+ return -EINVAL;
+ }
+
+ if (nlmsg_attrlen(nlh, sizeof(*ncm))) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid data after header in netconf dump request");
+ return -EINVAL;
+ }
+ }
+
s_h = cb->args[0];
s_idx = idx = cb->args[1];
@@ -1286,7 +1302,7 @@ static int mpls_netconf_dump_devconf(struct sk_buff *skb,
goto cont;
if (mpls_netconf_fill_devconf(skb, mdev,
NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq,
+ nlh->nlmsg_seq,
RTM_NEWNETCONF,
NLM_F_MULTI,
NETCONFA_ALL) < 0) {
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 21/23] net/bridge: Update br_mdb_dump for strict data checking
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Update br_mdb_dump for strict data checking. If the flag is set,
the dump request is expected to have a br_port_msg struct as the
header. All elements of the struct are expected to be 0 and no
attributes can be appended.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/bridge/br_mdb.c | 30 ++++++++++++++++++++++++++++++
1 file changed, 30 insertions(+)
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index a4a848bf827b..a7ea2d431714 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -162,6 +162,29 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
return err;
}
+static int br_mdb_valid_dump_req(const struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ struct br_port_msg *bpm;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*bpm))) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid header for mdb dump request");
+ return -EINVAL;
+ }
+
+ bpm = nlmsg_data(nlh);
+ if (bpm->ifindex) {
+ NL_SET_ERR_MSG_MOD(extack, "Filtering by device index is not supported for mdb dump request");
+ return -EINVAL;
+ }
+ if (nlmsg_attrlen(nlh, sizeof(*bpm))) {
+ NL_SET_ERR_MSG(extack, "Invalid data after header in mdb dump request");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int br_mdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net_device *dev;
@@ -169,6 +192,13 @@ static int br_mdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
struct nlmsghdr *nlh = NULL;
int idx = 0, s_idx;
+ if (cb->strict_check) {
+ int err = br_mdb_valid_dump_req(cb->nlh, cb->extack);
+
+ if (err < 0)
+ return err;
+ }
+
s_idx = cb->args[0];
rcu_read_lock();
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 18/23] net/fib_rules: Update fib_nl_dumprule for strict data checking
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Update fib_nl_dumprule for strict data checking. If the flag is set,
the dump request is expected to have fib_rule_hdr struct as the header.
All elements of the struct are expected to be 0 and no attributes can
be appended.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/core/fib_rules.c | 36 +++++++++++++++++++++++++++++++++++-
1 file changed, 35 insertions(+), 1 deletion(-)
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 0ff3953f64aa..ffbb827723a2 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -1063,13 +1063,47 @@ static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb,
return err;
}
+static int fib_valid_dumprule_req(const struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ struct fib_rule_hdr *frh;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) {
+ NL_SET_ERR_MSG(extack, "Invalid header for fib rule dump request");
+ return -EINVAL;
+ }
+
+ frh = nlmsg_data(nlh);
+ if (frh->dst_len || frh->src_len || frh->tos || frh->table ||
+ frh->res1 || frh->res2 || frh->action || frh->flags) {
+ NL_SET_ERR_MSG(extack,
+ "Invalid values in header for fib rule dump request");
+ return -EINVAL;
+ }
+
+ if (nlmsg_attrlen(nlh, sizeof(*frh))) {
+ NL_SET_ERR_MSG(extack, "Invalid data after header in fib rule dump request");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
{
+ const struct nlmsghdr *nlh = cb->nlh;
struct net *net = sock_net(skb->sk);
struct fib_rules_ops *ops;
int idx = 0, family;
- family = rtnl_msg_family(cb->nlh);
+ if (cb->strict_check) {
+ int err = fib_valid_dumprule_req(nlh, cb->extack);
+
+ if (err < 0)
+ return err;
+ }
+
+ family = rtnl_msg_family(nlh);
if (family != AF_UNSPEC) {
/* Protocol specific dump request */
ops = lookup_rules_ops(net, family);
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 17/23] net/namespace: Update rtnl_net_dumpid for strict data checking
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Update rtnl_net_dumpid for strict data checking. If the flag is set,
the dump request is expected to have an rtgenmsg struct as the header
which has the family as the only element. No data may be appended.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/core/net_namespace.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 670c84b1bfc2..fefe72774aeb 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -853,6 +853,12 @@ static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb)
.s_idx = cb->args[0],
};
+ if (cb->strict_check &&
+ nlmsg_attrlen(cb->nlh, sizeof(struct rtgenmsg))) {
+ NL_SET_ERR_MSG(cb->extack, "Unknown data in network namespace id dump request");
+ return -EINVAL;
+ }
+
spin_lock_bh(&net->nsid_lock);
idr_for_each(&net->netns_ids, rtnl_net_dumpid_one, &net_cb);
spin_unlock_bh(&net->nsid_lock);
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 16/23] net/neighbor: Update neightbl_dump_info for strict data checking
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Update neightbl_dump_info for strict data checking. If the flag is set,
the dump request is expected to have an ndtmsg struct as the header.
All elements of the struct are expected to be 0 and no attributes can
be appended.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/core/neighbour.c | 38 +++++++++++++++++++++++++++++++++++---
1 file changed, 35 insertions(+), 3 deletions(-)
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 7c8a3a0ee059..dc1389b8beb1 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2164,15 +2164,47 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh,
return err;
}
+static int neightbl_valid_dump_info(const struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ struct ndtmsg *ndtm;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ndtm))) {
+ NL_SET_ERR_MSG(extack, "Invalid header for neighbor table dump request");
+ return -EINVAL;
+ }
+
+ ndtm = nlmsg_data(nlh);
+ if (ndtm->ndtm_pad1 || ndtm->ndtm_pad2) {
+ NL_SET_ERR_MSG(extack, "Invalid values in header for neighbor table dump request");
+ return -EINVAL;
+ }
+
+ if (nlmsg_attrlen(nlh, sizeof(*ndtm))) {
+ NL_SET_ERR_MSG(extack, "Invalid data after header in neighbor table dump request");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
{
+ const struct nlmsghdr *nlh = cb->nlh;
struct net *net = sock_net(skb->sk);
int family, tidx, nidx = 0;
int tbl_skip = cb->args[0];
int neigh_skip = cb->args[1];
struct neigh_table *tbl;
- family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family;
+ if (cb->strict_check) {
+ int err = neightbl_valid_dump_info(nlh, cb->extack);
+
+ if (err < 0)
+ return err;
+ }
+
+ family = ((struct rtgenmsg *)nlmsg_data(nlh))->rtgen_family;
for (tidx = 0; tidx < NEIGH_NR_TABLES; tidx++) {
struct neigh_parms *p;
@@ -2185,7 +2217,7 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
continue;
if (neightbl_fill_info(skb, tbl, NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq, RTM_NEWNEIGHTBL,
+ nlh->nlmsg_seq, RTM_NEWNEIGHTBL,
NLM_F_MULTI) < 0)
break;
@@ -2200,7 +2232,7 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
if (neightbl_fill_param_info(skb, tbl, p,
NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq,
+ nlh->nlmsg_seq,
RTM_NEWNEIGHTBL,
NLM_F_MULTI) < 0)
goto out;
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 14/23] rtnetlink: Update fib dumps for strict data checking
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Add helper to check netlink message for route dumps. If the strict flag
is set the dump request is expected to have an rtmsg struct as the header.
All elements of the struct are expected to be 0 with the exception of
rtm_flags (which is used by both ipv4 and ipv6 dumps) and no attributes
can be appended. rtm_flags can only have RTM_F_CLONED and RTM_F_PREFIX
set.
Update inet_dump_fib, inet6_dump_fib, mpls_dump_routes, ipmr_rtm_dumproute,
and ip6mr_rtm_dumproute to call this helper if strict data checking is
enabled.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/ip_fib.h | 2 ++
net/ipv4/fib_frontend.c | 42 ++++++++++++++++++++++++++++++++++++++++--
net/ipv4/ipmr.c | 7 +++++++
net/ipv6/ip6_fib.c | 8 ++++++++
net/ipv6/ip6mr.c | 9 +++++++++
net/mpls/af_mpls.c | 8 ++++++++
6 files changed, 74 insertions(+), 2 deletions(-)
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index f7c109e37298..9846b79c9ee1 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -452,4 +452,6 @@ static inline void fib_proc_exit(struct net *net)
u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr);
+int ip_valid_fib_dump_req(const struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack);
#endif /* _NET_FIB_H */
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 30e2bcc3ef2a..038f511c73fa 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -802,8 +802,40 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
return err;
}
+int ip_valid_fib_dump_req(const struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ struct rtmsg *rtm;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) {
+ NL_SET_ERR_MSG(extack, "Invalid header for FIB dump request");
+ return -EINVAL;
+ }
+
+ rtm = nlmsg_data(nlh);
+ if (rtm->rtm_dst_len || rtm->rtm_src_len || rtm->rtm_tos ||
+ rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope ||
+ rtm->rtm_type) {
+ NL_SET_ERR_MSG(extack, "Invalid values in header for FIB dump request");
+ return -EINVAL;
+ }
+ if (rtm->rtm_flags & ~(RTM_F_CLONED | RTM_F_PREFIX)) {
+ NL_SET_ERR_MSG(extack, "Invalid flags for FIB dump request");
+ return -EINVAL;
+ }
+
+ if (nlmsg_attrlen(nlh, sizeof(*rtm))) {
+ NL_SET_ERR_MSG(extack, "Invalid data after header in FIB dump request");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ip_valid_fib_dump_req);
+
static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
{
+ const struct nlmsghdr *nlh = cb->nlh;
struct net *net = sock_net(skb->sk);
unsigned int h, s_h;
unsigned int e = 0, s_e;
@@ -811,8 +843,14 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
struct hlist_head *head;
int dumped = 0, err;
- if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) &&
- ((struct rtmsg *) nlmsg_data(cb->nlh))->rtm_flags & RTM_F_CLONED)
+ if (cb->strict_check) {
+ err = ip_valid_fib_dump_req(nlh, cb->extack);
+ if (err < 0)
+ return err;
+ }
+
+ if (nlmsg_len(nlh) >= sizeof(struct rtmsg) &&
+ ((struct rtmsg *)nlmsg_data(nlh))->rtm_flags & RTM_F_CLONED)
return skb->len;
s_h = cb->args[0];
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index e7322e407bb4..91b0d5671649 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2527,6 +2527,13 @@ static int ipmr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
{
+ if (cb->strict_check) {
+ int err = ip_valid_fib_dump_req(cb->nlh, cb->extack);
+
+ if (err < 0)
+ return err;
+ }
+
return mr_rtm_dumproute(skb, cb, ipmr_mr_table_iter,
_ipmr_fill_mroute, &mfc_unres_lock);
}
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index cf709eadc932..e14d244c551f 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -564,6 +564,7 @@ static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb,
static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
{
+ const struct nlmsghdr *nlh = cb->nlh;
struct net *net = sock_net(skb->sk);
unsigned int h, s_h;
unsigned int e = 0, s_e;
@@ -573,6 +574,13 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
struct hlist_head *head;
int res = 0;
+ if (cb->strict_check) {
+ int err = ip_valid_fib_dump_req(nlh, cb->extack);
+
+ if (err < 0)
+ return err;
+ }
+
s_h = cb->args[0];
s_e = cb->args[1];
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 6f07b8380425..d7563ef76518 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2457,6 +2457,15 @@ static void mrt6msg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt)
static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
{
+ const struct nlmsghdr *nlh = cb->nlh;
+
+ if (cb->strict_check) {
+ int err = ip_valid_fib_dump_req(nlh, cb->extack);
+
+ if (err < 0)
+ return err;
+ }
+
return mr_rtm_dumproute(skb, cb, ip6mr_mr_table_iter,
_ip6mr_fill_mroute, &mfc_unres_lock);
}
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 55a30ee3d820..0458c8aa5c11 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -2017,6 +2017,7 @@ static int mpls_dump_route(struct sk_buff *skb, u32 portid, u32 seq, int event,
static int mpls_dump_routes(struct sk_buff *skb, struct netlink_callback *cb)
{
+ const struct nlmsghdr *nlh = cb->nlh;
struct net *net = sock_net(skb->sk);
struct mpls_route __rcu **platform_label;
size_t platform_labels;
@@ -2024,6 +2025,13 @@ static int mpls_dump_routes(struct sk_buff *skb, struct netlink_callback *cb)
ASSERT_RTNL();
+ if (cb->strict_check) {
+ int err = ip_valid_fib_dump_req(nlh, cb->extack);
+
+ if (err < 0)
+ return err;
+ }
+
index = cb->args[0];
if (index < MPLS_LABEL_FIRST_UNRESERVED)
index = MPLS_LABEL_FIRST_UNRESERVED;
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 15/23] net/neighbor: Update neigh_dump_info for strict data checking
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Update neigh_dump_info for strict data checking. If the flag is set,
the dump request is expected to have an ndmsg struct as the header
potentially followed by one or more attributes. Any data passed in the
header or as an attribute is taken as a request to influence the data
returned. Only values supported by the dump handler are allowed to be
non-0 or set in the request. At the moment only the NDA_IFINDEX and
NDA_MASTER attributes are supported.
Existing code does not fail the dump if nlmsg_parse fails. That behavior
is kept for non-strict checking.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/core/neighbour.c | 82 ++++++++++++++++++++++++++++++++++++++++++----------
1 file changed, 67 insertions(+), 15 deletions(-)
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index b06f794bf91e..7c8a3a0ee059 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2426,11 +2426,73 @@ static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb,
}
+static int neigh_valid_dump_req(const struct nlmsghdr *nlh,
+ bool strict_check,
+ struct neigh_dump_filter *filter,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[NDA_MAX + 1];
+ int err, i;
+
+ if (strict_check) {
+ struct ndmsg *ndm;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ndm))) {
+ NL_SET_ERR_MSG(extack, "Invalid header for neighbor dump request");
+ return -EINVAL;
+ }
+
+ ndm = nlmsg_data(nlh);
+ if (ndm->ndm_pad1 || ndm->ndm_pad2 || ndm->ndm_ifindex ||
+ ndm->ndm_state || ndm->ndm_flags || ndm->ndm_type) {
+ NL_SET_ERR_MSG(extack, "Invalid values in header for neighbor dump request");
+ return -EINVAL;
+ }
+
+ err = nlmsg_parse_strict(nlh, sizeof(struct ndmsg), tb, NDA_MAX,
+ NULL, extack);
+ } else {
+ err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX,
+ NULL, extack);
+ }
+ if (err < 0)
+ return err;
+
+ for (i = 0; i <= NDA_MAX; ++i) {
+ if (!tb[i])
+ continue;
+
+ /* all new attributes should require strict_check */
+ switch (i) {
+ case NDA_IFINDEX:
+ if (nla_len(tb[i]) != sizeof(u32)) {
+ NL_SET_ERR_MSG(extack, "Invalid IFINDEX attribute in neighbor dump request");
+ return -EINVAL;
+ }
+ filter->dev_idx = nla_get_u32(tb[i]);
+ break;
+ case NDA_MASTER:
+ if (nla_len(tb[i]) != sizeof(u32)) {
+ NL_SET_ERR_MSG(extack, "Invalid MASTER attribute in neighbor dump request");
+ return -EINVAL;
+ }
+ filter->master_idx = nla_get_u32(tb[i]);
+ break;
+ default:
+ if (strict_check) {
+ NL_SET_ERR_MSG(extack, "Unsupported attribute in neighbor dump request");
+ return -EINVAL;
+ }
+ }
+ }
+
+ return 0;
+}
+
static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
{
const struct nlmsghdr *nlh = cb->nlh;
struct neigh_dump_filter filter = {};
- struct nlattr *tb[NDA_MAX + 1];
struct neigh_table *tbl;
int t, family, s_t;
int proxy = 0;
@@ -2445,20 +2507,10 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
((struct ndmsg *)nlmsg_data(nlh))->ndm_flags == NTF_PROXY)
proxy = 1;
- err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL,
- cb->extack);
- if (!err) {
- if (tb[NDA_IFINDEX]) {
- if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32))
- return -EINVAL;
- filter.dev_idx = nla_get_u32(tb[NDA_IFINDEX]);
- }
- if (tb[NDA_MASTER]) {
- if (nla_len(tb[NDA_MASTER]) != sizeof(u32))
- return -EINVAL;
- filter.master_idx = nla_get_u32(tb[NDA_MASTER]);
- }
- }
+ err = neigh_valid_dump_req(nlh, cb->strict_check, &filter, cb->extack);
+ if (err < 0 && cb->strict_check)
+ return err;
+
s_t = cb->args[0];
for (t = 0; t < NEIGH_NR_TABLES; t++) {
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 11/23] rtnetlink: Update rtnl_stats_dump for strict data checking
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Update rtnl_stats_dump for strict data checking. If the flag is set,
the dump request is expected to have an if_stats_msg struct as the header.
All elements of the struct are expected to be 0 except filter_mask which
must be non-0 (legacy behavior). No attributes are supported.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/core/rtnetlink.c | 24 ++++++++++++++++++++++--
1 file changed, 22 insertions(+), 2 deletions(-)
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e38e1f178611..f6d2609cfa9f 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -4680,6 +4680,7 @@ static int rtnl_stats_get(struct sk_buff *skb, struct nlmsghdr *nlh,
static int rtnl_stats_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
+ struct netlink_ext_ack *extack = cb->extack;
int h, s_h, err, s_idx, s_idxattr, s_prividx;
struct net *net = sock_net(skb->sk);
unsigned int flags = NLM_F_MULTI;
@@ -4696,13 +4697,32 @@ static int rtnl_stats_dump(struct sk_buff *skb, struct netlink_callback *cb)
cb->seq = net->dev_base_seq;
- if (nlmsg_len(cb->nlh) < sizeof(*ifsm))
+ if (nlmsg_len(cb->nlh) < sizeof(*ifsm)) {
+ NL_SET_ERR_MSG(extack, "Invalid header for stats dump");
return -EINVAL;
+ }
ifsm = nlmsg_data(cb->nlh);
+
+ /* only requests using NLM_F_DUMP_PROPER_HDR can pass data to
+ * influence the dump. The legacy exception is filter_mask.
+ */
+ if (cb->strict_check) {
+ if (ifsm->pad1 || ifsm->pad2 || ifsm->ifindex) {
+ NL_SET_ERR_MSG(extack, "Invalid values in header for stats dump request");
+ return -EINVAL;
+ }
+ if (nlmsg_attrlen(cb->nlh, sizeof(*ifsm))) {
+ NL_SET_ERR_MSG(extack, "Invalid attributes after stats header");
+ return -EINVAL;
+ }
+ }
+
filter_mask = ifsm->filter_mask;
- if (!filter_mask)
+ if (!filter_mask) {
+ NL_SET_ERR_MSG(extack, "Filter mask must be set for stats dump");
return -EINVAL;
+ }
for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
idx = 0;
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 10/23] rtnetlink: Update rtnl_bridge_getlink for strict data checking
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Update rtnl_bridge_getlink for strict data checking. If the flag is set,
the dump request is expected to have an ifinfomsg struct as the header
potentially followed by one or more attributes. Any data passed in the
header or as an attribute is taken as a request to influence the data
returned. Only values supported by the dump handler are allowed to be
non-0 or set in the request. At the moment only the IFLA_EXT_MASK
attribute is supported.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/core/rtnetlink.c | 70 ++++++++++++++++++++++++++++++++++++++++++----------
1 file changed, 57 insertions(+), 13 deletions(-)
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 12fd52105005..e38e1f178611 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -4021,28 +4021,72 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
}
EXPORT_SYMBOL_GPL(ndo_dflt_bridge_getlink);
+static int valid_bridge_getlink_req(const struct nlmsghdr *nlh,
+ bool strict_check, u32 *filter_mask,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[IFLA_MAX+1];
+ int err, i;
+
+ if (strict_check) {
+ struct ifinfomsg *ifm;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+ NL_SET_ERR_MSG(extack, "Invalid header for bridge link dump");
+ return -EINVAL;
+ }
+
+ ifm = nlmsg_data(nlh);
+ if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags ||
+ ifm->ifi_change || ifm->ifi_index) {
+ NL_SET_ERR_MSG(extack, "Invalid values in header for bridge link dump request");
+ return -EINVAL;
+ }
+
+ err = nlmsg_parse_strict(nlh, sizeof(struct ifinfomsg), tb,
+ IFLA_MAX, ifla_policy, extack);
+ } else {
+ err = nlmsg_parse(nlh, sizeof(struct ifinfomsg), tb,
+ IFLA_MAX, ifla_policy, extack);
+ }
+ if (err < 0)
+ return err;
+
+ /* new attributes should only be added with strict checking */
+ for (i = 0; i <= IFLA_MAX; ++i) {
+ if (!tb[i])
+ continue;
+
+ switch (i) {
+ case IFLA_EXT_MASK:
+ *filter_mask = nla_get_u32(tb[i]);
+ break;
+ default:
+ if (strict_check) {
+ NL_SET_ERR_MSG(extack, "Unsupported attribute in bridge link dump request");
+ return -EINVAL;
+ }
+ }
+ }
+
+ return 0;
+}
+
static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb)
{
+ const struct nlmsghdr *nlh = cb->nlh;
struct net *net = sock_net(skb->sk);
struct net_device *dev;
int idx = 0;
u32 portid = NETLINK_CB(cb->skb).portid;
- u32 seq = cb->nlh->nlmsg_seq;
+ u32 seq = nlh->nlmsg_seq;
u32 filter_mask = 0;
int err;
- if (nlmsg_len(cb->nlh) > sizeof(struct ifinfomsg)) {
- struct nlattr *extfilt;
-
- extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct ifinfomsg),
- IFLA_EXT_MASK);
- if (extfilt) {
- if (nla_len(extfilt) < sizeof(filter_mask))
- return -EINVAL;
-
- filter_mask = nla_get_u32(extfilt);
- }
- }
+ err = valid_bridge_getlink_req(nlh, cb->strict_check, &filter_mask,
+ cb->extack);
+ if (err < 0 && cb->strict_check)
+ return err;
rcu_read_lock();
for_each_netdev_rcu(net, dev) {
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 09/23] rtnetlink: Update rtnl_dump_ifinfo for strict data checking
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Update rtnl_dump_ifinfo for strict data checking. If the flag is set,
the dump request is expected to have an ifinfomsg struct as the header
potentially followed by one or more attributes. Any data passed in the
header or as an attribute is taken as a request to influence the data
returned. Only values supported by the dump handler are allowed to be
non-0 or set in the request. At the moment only the IFA_TARGET_NETNSID,
IFLA_EXT_MASK, IFLA_MASTER, and IFLA_LINKINFO attributes are supported.
Existing code does not fail the dump if nlmsg_parse fails. That behavior
is kept for non-strict checking.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/core/rtnetlink.c | 113 +++++++++++++++++++++++++++++++++++++--------------
1 file changed, 83 insertions(+), 30 deletions(-)
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 4486e8b7d9d0..12fd52105005 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1878,8 +1878,52 @@ struct net *rtnl_get_net_ns_capable(struct sock *sk, int netnsid)
}
EXPORT_SYMBOL_GPL(rtnl_get_net_ns_capable);
+static int rtnl_valid_dump_ifinfo_req(const struct nlmsghdr *nlh,
+ bool strict_check, struct nlattr **tb,
+ struct netlink_ext_ack *extack)
+{
+ int hdrlen;
+
+ if (strict_check) {
+ struct ifinfomsg *ifm;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+ NL_SET_ERR_MSG(extack, "Invalid header for link dump");
+ return -EINVAL;
+ }
+
+ ifm = nlmsg_data(nlh);
+ if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags ||
+ ifm->ifi_change) {
+ NL_SET_ERR_MSG(extack, "Invalid values in header for link dump request");
+ return -EINVAL;
+ }
+ if (ifm->ifi_index) {
+ NL_SET_ERR_MSG(extack, "Filter by device index not supported for link dumps");
+ return -EINVAL;
+ }
+
+ return nlmsg_parse_strict(nlh, sizeof(*ifm), tb, IFLA_MAX,
+ ifla_policy, extack);
+ }
+
+ /* A hack to preserve kernel<->userspace interface.
+ * The correct header is ifinfomsg. It is consistent with rtnl_getlink.
+ * However, before Linux v3.9 the code here assumed rtgenmsg and that's
+ * what iproute2 < v3.9.0 used.
+ * We can detect the old iproute2. Even including the IFLA_EXT_MASK
+ * attribute, its netlink message is shorter than struct ifinfomsg.
+ */
+ hdrlen = nlmsg_len(nlh) < sizeof(struct ifinfomsg) ?
+ sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
+
+ return nlmsg_parse(nlh, hdrlen, tb, IFLA_MAX, ifla_policy, extack);
+}
+
static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
{
+ struct netlink_ext_ack *extack = cb->extack;
+ const struct nlmsghdr *nlh = cb->nlh;
struct net *net = sock_net(skb->sk);
struct net *tgt_net = net;
int h, s_h;
@@ -1892,44 +1936,54 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
unsigned int flags = NLM_F_MULTI;
int master_idx = 0;
int netnsid = -1;
- int err;
- int hdrlen;
+ int err, i;
s_h = cb->args[0];
s_idx = cb->args[1];
- /* A hack to preserve kernel<->userspace interface.
- * The correct header is ifinfomsg. It is consistent with rtnl_getlink.
- * However, before Linux v3.9 the code here assumed rtgenmsg and that's
- * what iproute2 < v3.9.0 used.
- * We can detect the old iproute2. Even including the IFLA_EXT_MASK
- * attribute, its netlink message is shorter than struct ifinfomsg.
- */
- hdrlen = nlmsg_len(cb->nlh) < sizeof(struct ifinfomsg) ?
- sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
+ err = rtnl_valid_dump_ifinfo_req(nlh, cb->strict_check, tb, extack);
+ if (err < 0) {
+ if (cb->strict_check)
+ return err;
+
+ goto walk_entries;
+ }
+
+ for (i = 0; i <= IFLA_MAX; ++i) {
+ if (!tb[i])
+ continue;
- if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX,
- ifla_policy, cb->extack) >= 0) {
- if (tb[IFLA_TARGET_NETNSID]) {
- netnsid = nla_get_s32(tb[IFLA_TARGET_NETNSID]);
+ /* new attributes should only be added with strict checking */
+ switch (i) {
+ case IFLA_TARGET_NETNSID:
+ netnsid = nla_get_s32(tb[i]);
tgt_net = rtnl_get_net_ns_capable(skb->sk, netnsid);
- if (IS_ERR(tgt_net))
+ if (IS_ERR(tgt_net)) {
+ NL_SET_ERR_MSG(extack, "Invalid target network namespace id");
return PTR_ERR(tgt_net);
+ }
+ break;
+ case IFLA_EXT_MASK:
+ ext_filter_mask = nla_get_u32(tb[i]);
+ break;
+ case IFLA_MASTER:
+ master_idx = nla_get_u32(tb[i]);
+ break;
+ case IFLA_LINKINFO:
+ kind_ops = linkinfo_to_kind_ops(tb[i]);
+ break;
+ default:
+ if (cb->strict_check) {
+ NL_SET_ERR_MSG(extack, "Unsupported attribute in link dump request");
+ return -EINVAL;
+ }
}
-
- if (tb[IFLA_EXT_MASK])
- ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
-
- if (tb[IFLA_MASTER])
- master_idx = nla_get_u32(tb[IFLA_MASTER]);
-
- if (tb[IFLA_LINKINFO])
- kind_ops = linkinfo_to_kind_ops(tb[IFLA_LINKINFO]);
-
- if (master_idx || kind_ops)
- flags |= NLM_F_DUMP_FILTERED;
}
+ if (master_idx || kind_ops)
+ flags |= NLM_F_DUMP_FILTERED;
+
+walk_entries:
for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
idx = 0;
head = &tgt_net->dev_index_head[h];
@@ -1941,8 +1995,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
err = rtnl_fill_ifinfo(skb, dev, net,
RTM_NEWLINK,
NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq, 0,
- flags,
+ nlh->nlmsg_seq, 0, flags,
ext_filter_mask, 0, NULL, 0,
netnsid);
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 13/23] rtnetlink: Update ipmr_rtm_dumplink for strict data checking
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Update ipmr_rtm_dumplink for strict data checking. If the flag is set,
the dump request is expected to have an ifinfomsg struct as the header.
All elements of the struct are expected to be 0 and no attributes can
be appended.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/ipv4/ipmr.c | 32 ++++++++++++++++++++++++++++++++
1 file changed, 32 insertions(+)
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 5660adcf7a04..e7322e407bb4 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2710,6 +2710,31 @@ static bool ipmr_fill_vif(struct mr_table *mrt, u32 vifid, struct sk_buff *skb)
return true;
}
+static int ipmr_valid_dumplink(const struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ struct ifinfomsg *ifm;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+ NL_SET_ERR_MSG(extack, "ipv4: Invalid header for ipmr link dump");
+ return -EINVAL;
+ }
+
+ if (nlmsg_attrlen(nlh, sizeof(*ifm))) {
+ NL_SET_ERR_MSG(extack, "Invalid data after header in ipmr link dump");
+ return -EINVAL;
+ }
+
+ ifm = nlmsg_data(nlh);
+ if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags ||
+ ifm->ifi_change || ifm->ifi_index) {
+ NL_SET_ERR_MSG(extack, "Invalid values in header for ipmr link dump request");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int ipmr_rtm_dumplink(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
@@ -2718,6 +2743,13 @@ static int ipmr_rtm_dumplink(struct sk_buff *skb, struct netlink_callback *cb)
unsigned int e = 0, s_e;
struct mr_table *mrt;
+ if (cb->strict_check) {
+ int err = ipmr_valid_dumplink(cb->nlh, cb->extack);
+
+ if (err < 0)
+ return err;
+ }
+
s_t = cb->args[0];
s_e = cb->args[1];
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 12/23] rtnetlink: Update inet6_dump_ifinfo for strict data checking
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Update inet6_dump_ifinfo for strict data checking. If the flag is
set, the dump request is expected to have an ifinfomsg struct as
the header. All elements of the struct are expected to be 0 and no
attributes can be appended.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/ipv6/addrconf.c | 35 +++++++++++++++++++++++++++++++++++
1 file changed, 35 insertions(+)
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 095d3f56f0a9..ce071d85ad00 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5644,6 +5644,31 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev,
return -EMSGSIZE;
}
+static int inet6_valid_dump_ifinfo(const struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ struct ifinfomsg *ifm;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid header for link dump request");
+ return -EINVAL;
+ }
+
+ if (nlmsg_attrlen(nlh, sizeof(*ifm))) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid data after header");
+ return -EINVAL;
+ }
+
+ ifm = nlmsg_data(nlh);
+ if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags ||
+ ifm->ifi_change || ifm->ifi_index) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for dump request");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
@@ -5653,6 +5678,16 @@ static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
struct inet6_dev *idev;
struct hlist_head *head;
+ /* only requests using strict checking can pass data to
+ * influence the dump
+ */
+ if (cb->strict_check) {
+ int err = inet6_valid_dump_ifinfo(cb->nlh, cb->extack);
+
+ if (err < 0)
+ return err;
+ }
+
s_h = cb->args[0];
s_idx = cb->args[1];
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 07/23] net/ipv4: Update inet_dump_ifaddr for strict data checking
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Update inet_dump_ifaddr for strict data checking. If the flag is set,
the dump request is expected to have an ifaddrmsg struct as the header
potentially followed by one or more attributes. Any data passed in the
header or as an attribute is taken as a request to influence the data
returned. Only values supported by the dump handler are allowed to be
non-0 or set in the request. At the moment only the IFA_TARGET_NETNSID
attribute is supported. Follow on patches can support for other fields
(e.g., honor ifa_index and only return data for the given device index).
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/ipv4/devinet.c | 72 +++++++++++++++++++++++++++++++++++++++++++++---------
1 file changed, 61 insertions(+), 11 deletions(-)
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index ab2b11df5ea4..6f2bbd04e950 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1660,17 +1660,70 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa,
return -EMSGSIZE;
}
+static int inet_valid_dump_ifaddr_req(const struct nlmsghdr *nlh,
+ struct inet_fill_args *fillargs,
+ struct net **tgt_net, struct sock *sk,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[IFA_MAX+1];
+ struct ifaddrmsg *ifm;
+ int err, i;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+ NL_SET_ERR_MSG(extack, "ipv4: Invalid header for address dump request");
+ return -EINVAL;
+ }
+
+ ifm = nlmsg_data(nlh);
+ if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) {
+ NL_SET_ERR_MSG(extack, "ipv4: Invalid values in header for address dump request");
+ return -EINVAL;
+ }
+ if (ifm->ifa_index) {
+ NL_SET_ERR_MSG(extack, "ipv4: Filter by device index not supported for address dump");
+ return -EINVAL;
+ }
+
+ err = nlmsg_parse_strict(nlh, sizeof(*ifm), tb, IFA_MAX,
+ ifa_ipv4_policy, extack);
+ if (err < 0)
+ return err;
+
+ for (i = 0; i <= IFA_MAX; ++i) {
+ if (!tb[i])
+ continue;
+
+ if (i == IFA_TARGET_NETNSID) {
+ struct net *net;
+
+ fillargs->netnsid = nla_get_s32(tb[i]);
+
+ net = rtnl_get_net_ns_capable(sk, fillargs->netnsid);
+ if (IS_ERR(net)) {
+ NL_SET_ERR_MSG(extack, "ipv4: Invalid target network namespace id");
+ return PTR_ERR(net);
+ }
+ *tgt_net = net;
+ } else {
+ NL_SET_ERR_MSG(extack, "ipv4: Unsupported attribute in dump request");
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
{
+ const struct nlmsghdr *nlh = cb->nlh;
struct inet_fill_args fillargs = {
.portid = NETLINK_CB(cb->skb).portid,
- .seq = cb->nlh->nlmsg_seq,
+ .seq = nlh->nlmsg_seq,
.event = RTM_NEWADDR,
.flags = NLM_F_MULTI,
.netnsid = -1,
};
struct net *net = sock_net(skb->sk);
- struct nlattr *tb[IFA_MAX+1];
struct net *tgt_net = net;
int h, s_h;
int idx, s_idx;
@@ -1684,16 +1737,13 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
s_idx = idx = cb->args[1];
s_ip_idx = ip_idx = cb->args[2];
- if (nlmsg_parse(cb->nlh, sizeof(struct ifaddrmsg), tb, IFA_MAX,
- ifa_ipv4_policy, cb->extack) >= 0) {
- if (tb[IFA_TARGET_NETNSID]) {
- fillargs.netnsid = nla_get_s32(tb[IFA_TARGET_NETNSID]);
+ if (cb->strict_check) {
+ int err;
- tgt_net = rtnl_get_net_ns_capable(skb->sk,
- fillargs.netnsid);
- if (IS_ERR(tgt_net))
- return PTR_ERR(tgt_net);
- }
+ err = inet_valid_dump_ifaddr_req(nlh, &fillargs, &tgt_net,
+ skb->sk, cb->extack);
+ if (err < 0)
+ return err;
}
for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 08/23] net/ipv6: Update inet6_dump_addr for strict data checking
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Update inet6_dump_addr for strict data checking. If the flag is set, the
dump request is expected to have an ifaddrmsg struct as the header
potentially followed by one or more attributes. Any data passed in the
header or as an attribute is taken as a request to influence the data
returned. Only values suppored by the dump handler are allowed to be
non-0 or set in the request. At the moment only the IFA_TARGET_NETNSID
attribute is supported. Follow on patches can add support for other fields
(e.g., honor ifa_index and only return data for the given device index).
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/ipv6/addrconf.c | 69 +++++++++++++++++++++++++++++++++++++++++++++--------
1 file changed, 59 insertions(+), 10 deletions(-)
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index afa279170ba5..095d3f56f0a9 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4998,9 +4998,62 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
return err;
}
+static int inet6_valid_dump_ifaddr_req(const struct nlmsghdr *nlh,
+ struct inet6_fill_args *fillargs,
+ struct net **tgt_net, struct sock *sk,
+ struct netlink_ext_ack *extack)
+{
+ struct nlattr *tb[IFA_MAX+1];
+ struct ifaddrmsg *ifm;
+ int err, i;
+
+ if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid header for address dump request");
+ return -EINVAL;
+ }
+
+ ifm = nlmsg_data(nlh);
+ if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for address dump request");
+ return -EINVAL;
+ }
+ if (ifm->ifa_index) {
+ NL_SET_ERR_MSG_MOD(extack, "Filter by device index not supported for address dump");
+ return -EINVAL;
+ }
+
+ err = nlmsg_parse_strict(nlh, sizeof(*ifm), tb, IFA_MAX,
+ ifa_ipv6_policy, extack);
+ if (err < 0)
+ return err;
+
+ for (i = 0; i <= IFA_MAX; ++i) {
+ if (!tb[i])
+ continue;
+
+ if (i == IFA_TARGET_NETNSID) {
+ struct net *net;
+
+ fillargs->netnsid = nla_get_s32(tb[i]);
+ net = rtnl_get_net_ns_capable(sk, fillargs->netnsid);
+ if (IS_ERR(net)) {
+ NL_SET_ERR_MSG_MOD(extack, "Invalid target network namespace id");
+ return PTR_ERR(net);
+ }
+ *tgt_net = net;
+ } else {
+ NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in dump request");
+ return -EINVAL;
+ }
+ }
+
+ return 0;
+}
+
static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
enum addr_type_t type)
{
+ const struct nlmsghdr *nlh = cb->nlh;
struct inet6_fill_args fillargs = {
.portid = NETLINK_CB(cb->skb).portid,
.seq = cb->nlh->nlmsg_seq,
@@ -5009,7 +5062,6 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
.type = type,
};
struct net *net = sock_net(skb->sk);
- struct nlattr *tb[IFA_MAX+1];
struct net *tgt_net = net;
int h, s_h;
int idx, ip_idx;
@@ -5022,16 +5074,13 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
s_idx = idx = cb->args[1];
s_ip_idx = ip_idx = cb->args[2];
- if (nlmsg_parse(cb->nlh, sizeof(struct ifaddrmsg), tb, IFA_MAX,
- ifa_ipv6_policy, cb->extack) >= 0) {
- if (tb[IFA_TARGET_NETNSID]) {
- fillargs.netnsid = nla_get_s32(tb[IFA_TARGET_NETNSID]);
+ if (cb->strict_check) {
+ int err;
- tgt_net = rtnl_get_net_ns_capable(skb->sk,
- fillargs.netnsid);
- if (IS_ERR(tgt_net))
- return PTR_ERR(tgt_net);
- }
+ err = inet6_valid_dump_ifaddr_req(nlh, &fillargs, &tgt_net,
+ skb->sk, cb->extack);
+ if (err < 0)
+ return err;
}
rcu_read_lock();
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 06/23] netlink: Add new socket option to enable strict checking on dumps
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Add a new socket option, NETLINK_DUMP_STRICT_CHK, that userspace
can use via setsockopt to request strict checking of headers and
attributes on dump requests.
To get dump features such as kernel side filtering based on data in
the header or attributes appended to the dump request, userspace
must call setsockopt() for NETLINK_DUMP_STRICT_CHK and a non-zero
value. Since the netlink sock and its flags are private to the
af_netlink code, the strict checking flag is passed to dump handlers
via a flag in the netlink_callback struct.
For old userspace on new kernel there is no impact as all of the data
checks in later patches are wrapped in a check on the new strict flag.
For new userspace on old kernel, the setsockopt will fail and even if
new userspace sets data in the headers and appended attributes the
kernel will silently ignore it. Moving forward when the setsockopt
succeeds, the new userspace on old kernel means the dump request can
pass an attribute the kernel does not understand. The dump will then
fail as the older kernel does not understand it.
New userspace on new kernel setting the socket option gets the benefit
of the improved data dump.
Kernel side the NETLINK_DUMP_STRICT_CHK uapi is converted to a generic
NETLINK_F_STRICT_CHK flag which can potentially be leveraged for tighter
checking on the NEW, DEL, and SET commands.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/linux/netlink.h | 1 +
include/uapi/linux/netlink.h | 1 +
net/netlink/af_netlink.c | 21 ++++++++++++++++++++-
net/netlink/af_netlink.h | 1 +
4 files changed, 23 insertions(+), 1 deletion(-)
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 88c8a2d83eb3..72580f1a72a2 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -179,6 +179,7 @@ struct netlink_callback {
struct netlink_ext_ack *extack;
u16 family;
u16 min_dump_alloc;
+ bool strict_check;
unsigned int prev_seq, seq;
long args[6];
};
diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h
index 776bc92e9118..486ed1f0c0bc 100644
--- a/include/uapi/linux/netlink.h
+++ b/include/uapi/linux/netlink.h
@@ -155,6 +155,7 @@ enum nlmsgerr_attrs {
#define NETLINK_LIST_MEMBERSHIPS 9
#define NETLINK_CAP_ACK 10
#define NETLINK_EXT_ACK 11
+#define NETLINK_DUMP_STRICT_CHK 12
struct nl_pktinfo {
__u32 group;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 7ac585f33a9e..e613a9f89600 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1706,6 +1706,13 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
nlk->flags &= ~NETLINK_F_EXT_ACK;
err = 0;
break;
+ case NETLINK_DUMP_STRICT_CHK:
+ if (val)
+ nlk->flags |= NETLINK_F_STRICT_CHK;
+ else
+ nlk->flags &= ~NETLINK_F_STRICT_CHK;
+ err = 0;
+ break;
default:
err = -ENOPROTOOPT;
}
@@ -1799,6 +1806,15 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname,
return -EFAULT;
err = 0;
break;
+ case NETLINK_DUMP_STRICT_CHK:
+ if (len < sizeof(int))
+ return -EINVAL;
+ len = sizeof(int);
+ val = nlk->flags & NETLINK_F_STRICT_CHK ? 1 : 0;
+ if (put_user(len, optlen) || put_user(val, optval))
+ return -EFAULT;
+ err = 0;
+ break;
default:
err = -ENOPROTOOPT;
}
@@ -2282,9 +2298,9 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
const struct nlmsghdr *nlh,
struct netlink_dump_control *control)
{
+ struct netlink_sock *nlk, *nlk2;
struct netlink_callback *cb;
struct sock *sk;
- struct netlink_sock *nlk;
int ret;
refcount_inc(&skb->users);
@@ -2318,6 +2334,9 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
cb->min_dump_alloc = control->min_dump_alloc;
cb->skb = skb;
+ nlk2 = nlk_sk(NETLINK_CB(skb).sk);
+ cb->strict_check = !!(nlk2->flags & NETLINK_F_STRICT_CHK);
+
if (control->start) {
ret = control->start(cb);
if (ret)
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index 962de7b3c023..5f454c8de6a4 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -15,6 +15,7 @@
#define NETLINK_F_LISTEN_ALL_NSID 0x10
#define NETLINK_F_CAP_ACK 0x20
#define NETLINK_F_EXT_ACK 0x40
+#define NETLINK_F_STRICT_CHK 0x80
#define NLGRPSZ(x) (ALIGN(x, sizeof(unsigned long) * 8) / 8)
#define NLGRPLONGS(x) (NLGRPSZ(x)/sizeof(unsigned long))
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 05/23] net/ipv6: Refactor address dump to push inet6_fill_args to in6_dump_addrs
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Pull the inet6_fill_args arg up to in6_dump_addrs and move netnsid
into it.
Signed-off-by: David Ahern <dsahern@gmail.com>
Acked-by: Christian Brauner <christian@brauner.io>
---
net/ipv6/addrconf.c | 57 ++++++++++++++++++++++++++++-------------------------
1 file changed, 30 insertions(+), 27 deletions(-)
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 2f8aa4fd5e55..afa279170ba5 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -4793,12 +4793,19 @@ static inline int inet6_ifaddr_msgsize(void)
+ nla_total_size(4) /* IFA_RT_PRIORITY */;
}
+enum addr_type_t {
+ UNICAST_ADDR,
+ MULTICAST_ADDR,
+ ANYCAST_ADDR,
+};
+
struct inet6_fill_args {
u32 portid;
u32 seq;
int event;
unsigned int flags;
int netnsid;
+ enum addr_type_t type;
};
static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa,
@@ -4930,39 +4937,28 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca,
return 0;
}
-enum addr_type_t {
- UNICAST_ADDR,
- MULTICAST_ADDR,
- ANYCAST_ADDR,
-};
-
/* called with rcu_read_lock() */
static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
- struct netlink_callback *cb, enum addr_type_t type,
- int s_ip_idx, int *p_ip_idx, int netnsid)
+ struct netlink_callback *cb,
+ int s_ip_idx, int *p_ip_idx,
+ struct inet6_fill_args *fillargs)
{
- struct inet6_fill_args fillargs = {
- .portid = NETLINK_CB(cb->skb).portid,
- .seq = cb->nlh->nlmsg_seq,
- .flags = NLM_F_MULTI,
- .netnsid = netnsid,
- };
struct ifmcaddr6 *ifmca;
struct ifacaddr6 *ifaca;
int err = 1;
int ip_idx = *p_ip_idx;
read_lock_bh(&idev->lock);
- switch (type) {
+ switch (fillargs->type) {
case UNICAST_ADDR: {
struct inet6_ifaddr *ifa;
- fillargs.event = RTM_NEWADDR;
+ fillargs->event = RTM_NEWADDR;
/* unicast address incl. temp addr */
list_for_each_entry(ifa, &idev->addr_list, if_list) {
if (++ip_idx < s_ip_idx)
continue;
- err = inet6_fill_ifaddr(skb, ifa, &fillargs);
+ err = inet6_fill_ifaddr(skb, ifa, fillargs);
if (err < 0)
break;
nl_dump_check_consistent(cb, nlmsg_hdr(skb));
@@ -4970,26 +4966,26 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
break;
}
case MULTICAST_ADDR:
- fillargs.event = RTM_GETMULTICAST;
+ fillargs->event = RTM_GETMULTICAST;
/* multicast address */
for (ifmca = idev->mc_list; ifmca;
ifmca = ifmca->next, ip_idx++) {
if (ip_idx < s_ip_idx)
continue;
- err = inet6_fill_ifmcaddr(skb, ifmca, &fillargs);
+ err = inet6_fill_ifmcaddr(skb, ifmca, fillargs);
if (err < 0)
break;
}
break;
case ANYCAST_ADDR:
- fillargs.event = RTM_GETANYCAST;
+ fillargs->event = RTM_GETANYCAST;
/* anycast address */
for (ifaca = idev->ac_list; ifaca;
ifaca = ifaca->aca_next, ip_idx++) {
if (ip_idx < s_ip_idx)
continue;
- err = inet6_fill_ifacaddr(skb, ifaca, &fillargs);
+ err = inet6_fill_ifacaddr(skb, ifaca, fillargs);
if (err < 0)
break;
}
@@ -5005,10 +5001,16 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb,
static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
enum addr_type_t type)
{
+ struct inet6_fill_args fillargs = {
+ .portid = NETLINK_CB(cb->skb).portid,
+ .seq = cb->nlh->nlmsg_seq,
+ .flags = NLM_F_MULTI,
+ .netnsid = -1,
+ .type = type,
+ };
struct net *net = sock_net(skb->sk);
struct nlattr *tb[IFA_MAX+1];
struct net *tgt_net = net;
- int netnsid = -1;
int h, s_h;
int idx, ip_idx;
int s_idx, s_ip_idx;
@@ -5023,9 +5025,10 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
if (nlmsg_parse(cb->nlh, sizeof(struct ifaddrmsg), tb, IFA_MAX,
ifa_ipv6_policy, cb->extack) >= 0) {
if (tb[IFA_TARGET_NETNSID]) {
- netnsid = nla_get_s32(tb[IFA_TARGET_NETNSID]);
+ fillargs.netnsid = nla_get_s32(tb[IFA_TARGET_NETNSID]);
- tgt_net = rtnl_get_net_ns_capable(skb->sk, netnsid);
+ tgt_net = rtnl_get_net_ns_capable(skb->sk,
+ fillargs.netnsid);
if (IS_ERR(tgt_net))
return PTR_ERR(tgt_net);
}
@@ -5046,8 +5049,8 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
if (!idev)
goto cont;
- if (in6_dump_addrs(idev, skb, cb, type,
- s_ip_idx, &ip_idx, netnsid) < 0)
+ if (in6_dump_addrs(idev, skb, cb, s_ip_idx, &ip_idx,
+ &fillargs) < 0)
goto done;
cont:
idx++;
@@ -5058,7 +5061,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
cb->args[0] = h;
cb->args[1] = idx;
cb->args[2] = ip_idx;
- if (netnsid >= 0)
+ if (fillargs.netnsid >= 0)
put_net(tgt_net);
return skb->len;
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 04/23] netlink: Add strict version of nlmsg_parse and nla_parse
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
nla_parse is currently lenient on message parsing, allowing type to be 0
or greater than max expected and only logging a message
"netlink: %d bytes leftover after parsing attributes in process `%s'."
if the netlink message has unknown data at the end after parsing. What this
could mean is that the header at the front of the attributes is actually
wrong and the parsing is shifted from what is expected.
Add a new strict version that actually fails with EINVAL if there are any
bytes remaining after the parsing loop completes, if the atttrbitue type
is 0 or greater than max expected.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/netlink.h | 17 +++++++++++++++++
lib/nlattr.c | 48 ++++++++++++++++++++++++++++++++++++------------
2 files changed, 53 insertions(+), 12 deletions(-)
diff --git a/include/net/netlink.h b/include/net/netlink.h
index 9522a0bf1f3a..f1db8e594847 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -373,6 +373,9 @@ int nla_validate(const struct nlattr *head, int len, int maxtype,
int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head,
int len, const struct nla_policy *policy,
struct netlink_ext_ack *extack);
+int nla_parse_strict(struct nlattr **tb, int maxtype, const struct nlattr *head,
+ int len, const struct nla_policy *policy,
+ struct netlink_ext_ack *extack);
int nla_policy_len(const struct nla_policy *, int);
struct nlattr *nla_find(const struct nlattr *head, int len, int attrtype);
size_t nla_strlcpy(char *dst, const struct nlattr *nla, size_t dstsize);
@@ -525,6 +528,20 @@ static inline int nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen,
nlmsg_attrlen(nlh, hdrlen), policy, extack);
}
+static inline int nlmsg_parse_strict(const struct nlmsghdr *nlh, int hdrlen,
+ struct nlattr *tb[], int maxtype,
+ const struct nla_policy *policy,
+ struct netlink_ext_ack *extack)
+{
+ if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) {
+ NL_SET_ERR_MSG(extack, "Invalid header length");
+ return -EINVAL;
+ }
+
+ return nla_parse_strict(tb, maxtype, nlmsg_attrdata(nlh, hdrlen),
+ nlmsg_attrlen(nlh, hdrlen), policy, extack);
+}
+
/**
* nlmsg_find_attr - find a specific attribute in a netlink message
* @nlh: netlink message header
diff --git a/lib/nlattr.c b/lib/nlattr.c
index 1e900bb414ef..d26de6156b97 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -391,9 +391,10 @@ EXPORT_SYMBOL(nla_policy_len);
*
* Returns 0 on success or a negative error code.
*/
-int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head,
- int len, const struct nla_policy *policy,
- struct netlink_ext_ack *extack)
+static int __nla_parse(struct nlattr **tb, int maxtype,
+ const struct nlattr *head, int len,
+ bool strict, const struct nla_policy *policy,
+ struct netlink_ext_ack *extack)
{
const struct nlattr *nla;
int rem;
@@ -403,27 +404,50 @@ int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head,
nla_for_each_attr(nla, head, len, rem) {
u16 type = nla_type(nla);
- if (type > 0 && type <= maxtype) {
- if (policy) {
- int err = validate_nla(nla, maxtype, policy,
- extack);
-
- if (err < 0)
- return err;
+ if (type == 0 || type > maxtype) {
+ if (strict) {
+ NL_SET_ERR_MSG(extack, "Unknown attribute type");
+ return -EINVAL;
}
+ continue;
+ }
+ if (policy) {
+ int err = validate_nla(nla, maxtype, policy, extack);
- tb[type] = (struct nlattr *)nla;
+ if (err < 0)
+ return err;
}
+
+ tb[type] = (struct nlattr *)nla;
}
- if (unlikely(rem > 0))
+ if (unlikely(rem > 0)) {
pr_warn_ratelimited("netlink: %d bytes leftover after parsing attributes in process `%s'.\n",
rem, current->comm);
+ NL_SET_ERR_MSG(extack, "bytes leftover after parsing attributes");
+ if (strict)
+ return -EINVAL;
+ }
return 0;
}
+
+int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head,
+ int len, const struct nla_policy *policy,
+ struct netlink_ext_ack *extack)
+{
+ return __nla_parse(tb, maxtype, head, len, false, policy, extack);
+}
EXPORT_SYMBOL(nla_parse);
+int nla_parse_strict(struct nlattr **tb, int maxtype, const struct nlattr *head,
+ int len, const struct nla_policy *policy,
+ struct netlink_ext_ack *extack)
+{
+ return __nla_parse(tb, maxtype, head, len, true, policy, extack);
+}
+EXPORT_SYMBOL(nla_parse_strict);
+
/**
* nla_find - Find a specific attribute in a stream of attributes
* @head: head of attribute stream
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 02/23] netlink: Add extack message to nlmsg_parse for invalid header length
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Give a user a reason why EINVAL is returned in nlmsg_parse.
Signed-off-by: David Ahern <dsahern@gmail.com>
Acked-by: Christian Brauner <christian@brauner.io>
---
include/net/netlink.h | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/include/net/netlink.h b/include/net/netlink.h
index 589683091f16..9522a0bf1f3a 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -516,8 +516,10 @@ static inline int nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen,
const struct nla_policy *policy,
struct netlink_ext_ack *extack)
{
- if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen))
+ if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) {
+ NL_SET_ERR_MSG(extack, "Invalid header length");
return -EINVAL;
+ }
return nla_parse(tb, maxtype, nlmsg_attrdata(nlh, hdrlen),
nlmsg_attrlen(nlh, hdrlen), policy, extack);
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 01/23] netlink: Pass extack to dump handlers
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Declare extack in netlink_dump and pass to dump handlers via
netlink_callback. Add any extack message after the dump_done_errno
allowing error messages to be returned. This will be useful when
strict checking is done on dump requests, returning why the dump
fails EINVAL.
Signed-off-by: David Ahern <dsahern@gmail.com>
Acked-by: Christian Brauner <christian@brauner.io>
---
include/linux/netlink.h | 1 +
net/netlink/af_netlink.c | 12 +++++++++++-
2 files changed, 12 insertions(+), 1 deletion(-)
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 71f121b66ca8..88c8a2d83eb3 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -176,6 +176,7 @@ struct netlink_callback {
void *data;
/* the module that dump function belong to */
struct module *module;
+ struct netlink_ext_ack *extack;
u16 family;
u16 min_dump_alloc;
unsigned int prev_seq, seq;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index e3a0538ec0be..7ac585f33a9e 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2171,6 +2171,7 @@ EXPORT_SYMBOL(__nlmsg_put);
static int netlink_dump(struct sock *sk)
{
struct netlink_sock *nlk = nlk_sk(sk);
+ struct netlink_ext_ack extack = {};
struct netlink_callback *cb;
struct sk_buff *skb = NULL;
struct nlmsghdr *nlh;
@@ -2222,8 +2223,11 @@ static int netlink_dump(struct sock *sk)
skb_reserve(skb, skb_tailroom(skb) - alloc_size);
netlink_skb_set_owner_r(skb, sk);
- if (nlk->dump_done_errno > 0)
+ if (nlk->dump_done_errno > 0) {
+ cb->extack = &extack;
nlk->dump_done_errno = cb->dump(skb, cb);
+ cb->extack = NULL;
+ }
if (nlk->dump_done_errno > 0 ||
skb_tailroom(skb) < nlmsg_total_size(sizeof(nlk->dump_done_errno))) {
@@ -2246,6 +2250,12 @@ static int netlink_dump(struct sock *sk)
memcpy(nlmsg_data(nlh), &nlk->dump_done_errno,
sizeof(nlk->dump_done_errno));
+ if (extack._msg && nlk->flags & NETLINK_F_EXT_ACK) {
+ nlh->nlmsg_flags |= NLM_F_ACK_TLVS;
+ if (!nla_put_string(skb, NLMSGERR_ATTR_MSG, extack._msg))
+ nlmsg_end(skb, nlh);
+ }
+
if (sk_filter(sk, skb))
kfree_skb(skb);
else
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 03/23] net: Add extack to nlmsg_parse
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
In-Reply-To: <20181008031644.15989-1-dsahern@kernel.org>
From: David Ahern <dsahern@gmail.com>
Make sure extack is passed to nlmsg_parse where easy to do so.
Most of these are dump handlers and leveraging the extack in
the netlink_callback.
Signed-off-by: David Ahern <dsahern@gmail.com>
Acked-by: Christian Brauner <christian@brauner.io>
---
net/core/devlink.c | 2 +-
net/core/neighbour.c | 3 ++-
net/core/rtnetlink.c | 4 ++--
net/ipv4/devinet.c | 9 +++++----
net/ipv6/addrconf.c | 2 +-
net/ipv6/route.c | 2 +-
net/mpls/af_mpls.c | 2 +-
net/netfilter/ipvs/ip_vs_ctl.c | 2 +-
net/sched/act_api.c | 2 +-
net/sched/cls_api.c | 6 ++++--
net/sched/sch_api.c | 2 +-
net/xfrm/xfrm_user.c | 2 +-
12 files changed, 21 insertions(+), 17 deletions(-)
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 938f68ee92f0..6dae81d65d5c 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3504,7 +3504,7 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
start_offset = *((u64 *)&cb->args[0]);
err = nlmsg_parse(cb->nlh, GENL_HDRLEN + devlink_nl_family.hdrsize,
- attrs, DEVLINK_ATTR_MAX, ops->policy, NULL);
+ attrs, DEVLINK_ATTR_MAX, ops->policy, cb->extack);
if (err)
goto out;
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index fb023df48b83..b06f794bf91e 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2445,7 +2445,8 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb)
((struct ndmsg *)nlmsg_data(nlh))->ndm_flags == NTF_PROXY)
proxy = 1;
- err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL, NULL);
+ err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL,
+ cb->extack);
if (!err) {
if (tb[NDA_IFINDEX]) {
if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32))
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 5564eee1e980..4486e8b7d9d0 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1909,7 +1909,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
sizeof(struct rtgenmsg) : sizeof(struct ifinfomsg);
if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX,
- ifla_policy, NULL) >= 0) {
+ ifla_policy, cb->extack) >= 0) {
if (tb[IFLA_TARGET_NETNSID]) {
netnsid = nla_get_s32(tb[IFLA_TARGET_NETNSID]);
tgt_net = rtnl_get_net_ns_capable(skb->sk, netnsid);
@@ -3774,7 +3774,7 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
(nlmsg_len(cb->nlh) != sizeof(struct ndmsg) +
nla_attr_size(sizeof(u32)))) {
err = nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb,
- IFLA_MAX, ifla_policy, NULL);
+ IFLA_MAX, ifla_policy, cb->extack);
if (err < 0) {
return -EINVAL;
} else if (err == 0) {
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 44d931a3cd50..ab2b11df5ea4 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -782,7 +782,8 @@ static void set_ifa_lifetime(struct in_ifaddr *ifa, __u32 valid_lft,
}
static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
- __u32 *pvalid_lft, __u32 *pprefered_lft)
+ __u32 *pvalid_lft, __u32 *pprefered_lft,
+ struct netlink_ext_ack *extack)
{
struct nlattr *tb[IFA_MAX+1];
struct in_ifaddr *ifa;
@@ -792,7 +793,7 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
int err;
err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy,
- NULL);
+ extack);
if (err < 0)
goto errout;
@@ -897,7 +898,7 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
ASSERT_RTNL();
- ifa = rtm_to_ifaddr(net, nlh, &valid_lft, &prefered_lft);
+ ifa = rtm_to_ifaddr(net, nlh, &valid_lft, &prefered_lft, extack);
if (IS_ERR(ifa))
return PTR_ERR(ifa);
@@ -1684,7 +1685,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
s_ip_idx = ip_idx = cb->args[2];
if (nlmsg_parse(cb->nlh, sizeof(struct ifaddrmsg), tb, IFA_MAX,
- ifa_ipv4_policy, NULL) >= 0) {
+ ifa_ipv4_policy, cb->extack) >= 0) {
if (tb[IFA_TARGET_NETNSID]) {
fillargs.netnsid = nla_get_s32(tb[IFA_TARGET_NETNSID]);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index a9a317322388..2f8aa4fd5e55 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5021,7 +5021,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
s_ip_idx = ip_idx = cb->args[2];
if (nlmsg_parse(cb->nlh, sizeof(struct ifaddrmsg), tb, IFA_MAX,
- ifa_ipv6_policy, NULL) >= 0) {
+ ifa_ipv6_policy, cb->extack) >= 0) {
if (tb[IFA_TARGET_NETNSID]) {
netnsid = nla_get_s32(tb[IFA_TARGET_NETNSID]);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 74d97addf1af..7c38e0e058ae 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4117,7 +4117,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
int err;
err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy,
- NULL);
+ extack);
if (err < 0)
goto errout;
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 8fbe6cdbe255..55a30ee3d820 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -1223,7 +1223,7 @@ static int mpls_netconf_get_devconf(struct sk_buff *in_skb,
int err;
err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX,
- devconf_mpls_policy, NULL);
+ devconf_mpls_policy, extack);
if (err < 0)
goto errout;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 62eefea48973..83395bf6dc35 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3234,7 +3234,7 @@ static int ip_vs_genl_dump_dests(struct sk_buff *skb,
/* Try to find the service for which to dump destinations */
if (nlmsg_parse(cb->nlh, GENL_HDRLEN, attrs, IPVS_CMD_ATTR_MAX,
- ip_vs_cmd_policy, NULL))
+ ip_vs_cmd_policy, cb->extack))
goto out_err;
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 55153da00278..9c1b0729aebf 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -1452,7 +1452,7 @@ static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb)
u32 act_count = 0;
ret = nlmsg_parse(cb->nlh, sizeof(struct tcamsg), tb, TCA_ROOT_MAX,
- tcaa_policy, NULL);
+ tcaa_policy, cb->extack);
if (ret < 0)
return ret;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index d670d3066ebd..43c8559aca56 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1727,7 +1727,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb)
if (nlmsg_len(cb->nlh) < sizeof(*tcm))
return skb->len;
- err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, NULL, NULL);
+ err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, NULL,
+ cb->extack);
if (err)
return err;
@@ -2054,7 +2055,8 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
if (nlmsg_len(cb->nlh) < sizeof(*tcm))
return skb->len;
- err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, NULL, NULL);
+ err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, NULL,
+ cb->extack);
if (err)
return err;
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index da1963b19dec..cf5c714ae786 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1671,7 +1671,7 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb)
ASSERT_RTNL();
err = nlmsg_parse(nlh, sizeof(struct tcmsg), tca, TCA_MAX,
- rtm_tca_policy, NULL);
+ rtm_tca_policy, cb->extack);
if (err < 0)
return err;
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index df7ca2dabc48..ca7a207b81a9 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1007,7 +1007,7 @@ static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb)
int err;
err = nlmsg_parse(cb->nlh, 0, attrs, XFRMA_MAX, xfrma_policy,
- NULL);
+ cb->extack);
if (err < 0)
return err;
--
2.11.0
^ permalink raw reply related
* [PATCH v2 net-next 00/23] rtnetlink: Add support for rigid checking of data in dump request
From: David Ahern @ 2018-10-08 3:16 UTC (permalink / raw)
To: netdev, davem; +Cc: christian, jbenc, stephen, David Ahern
From: David Ahern <dsahern@gmail.com>
There are many use cases where a user wants to influence what is
returned in a dump for some rtnetlink command: one is wanting data
for a different namespace than the one the request is received and
another is limiting the amount of data returned in the dump to a
specific set of interest to userspace, reducing the cpu overhead of
both kernel and userspace. Unfortunately, the kernel has historically
not been strict with checking for the proper header or checking the
values passed in the header. This lenient implementation has allowed
iproute2 and other packages to pass any struct or data in the dump
request as long as the family is the first byte. For example, ifinfomsg
struct is used by iproute2 for all generic dump requests - links,
addresses, routes and rules when it is really only valid for link
requests.
There is 1 is example where the kernel deals with the wrong struct: link
dumps after VF support was added. Older iproute2 was sending rtgenmsg as
the header instead of ifinfomsg so a patch was added to try and detect
old userspace vs new:
e5eca6d41f53 ("rtnetlink: fix userspace API breakage for iproute2 < v3.9.0")
The latest example is Christian's patch set wanting to return addresses for
a target namespace. It guesses the header struct is an ifaddrmsg and if it
guesses wrong a netlink warning is generated in the kernel log on every
address dump which is unacceptable.
Another example where the kernel is a bit lenient is route dumps: iproute2
can send either a request with either ifinfomsg or a rtmsg as the header
struct, yet the kernel always treats the header as an rtmsg (see
inet_dump_fib and rtm_flags check). The header inconsistency impacts the
ability to add kernel side filters for route dumps - a necessary feature
for scale setups with 100k+ routes.
How to resolve the problem of not breaking old userspace yet be able to
move forward with new features such as kernel side filtering which are
crucial for efficient operation at high scale?
This patch set addresses the problem by adding a new socket flag,
NETLINK_DUMP_STRICT_CHK, that userspace can use with setsockopt to
request strict checking of headers and attributes on dump requests and
hence unlock the ability to use kernel side filters as they are added.
Kernel side, the dump handlers are updated to verify the message contains
at least the expected header struct:
RTM_GETLINK: ifinfomsg
RTM_GETADDR: ifaddrmsg
RTM_GETMULTICAST: ifaddrmsg
RTM_GETANYCAST: ifaddrmsg
RTM_GETADDRLABEL: ifaddrlblmsg
RTM_GETROUTE: rtmsg
RTM_GETSTATS: if_stats_msg
RTM_GETNEIGH: ndmsg
RTM_GETNEIGHTBL: ndtmsg
RTM_GETNSID: rtgenmsg
RTM_GETRULE: fib_rule_hdr
RTM_GETNETCONF: netconfmsg
RTM_GETMDB: br_port_msg
And then every field in the header struct should be 0 with the exception
of the family. There are a few exceptions to this rule where the kernel
already influences the data returned by values in the struct. Next the
message should not contain attributes unless the kernel implements
filtering for it. Any unexpected data causes the dump to fail with EINVAL.
If the new flag is honored by the kernel and the dump contents adjusted
by any data passed in the request, the dump handler can set the
NLM_F_DUMP_FILTERED flag in the netlink message header.
For old userspace on new kernel there is no impact as all checks are
wrapped in a check on the new strict flag. For new userspace on old
kernel, the data in the headers and any appended attributes are
silently ignored though the setsockopt failing is the clue to userspace
the feature is not supported. New userspace on new kernel gets the
requested data dump.
iproute2 patches can be found here:
https://github.com/dsahern/iproute2 dump-enhancements
Major changes since v1
- inner header is supposed to be 4-bytes aligned. So for dumps that
should not have attributes appended changed the check to use:
if (nlmsg_attrlen(nlh, sizeof(hdr)))
Only impacts patches with headers that are not multiples of 4-bytes
(rtgenmsg, netconfmsg), but applied the change to all patches not
calling nlmsg_parse for consistency.
- Added nlmsg_parse_strict and nla_parse_strict for tighter control on
attribute parsing. There should be no unknown attribute types or extra
bytes.
- Moved validation to a helper in most cases
Changes since rfc-v2
- dropped the NLM_F_DUMP_FILTERED flag from target nsid dumps per
Jiri's objections
- changed the opt-in uapi from a netlink message flag to a socket
flag. setsockopt provides an api for userspace to definitively
know if the kernel supports strict checking on dumps.
- re-ordered patches to peel off the extack on dumps if needed to
keep this set size within limits
- misc cleanups in patches based on testing
David Ahern (23):
netlink: Pass extack to dump handlers
netlink: Add extack message to nlmsg_parse for invalid header length
net: Add extack to nlmsg_parse
netlink: Add strict version of nlmsg_parse and nla_parse
net/ipv6: Refactor address dump to push inet6_fill_args to
in6_dump_addrs
netlink: Add new socket option to enable strict checking on dumps
net/ipv4: Update inet_dump_ifaddr for strict data checking
net/ipv6: Update inet6_dump_addr for strict data checking
rtnetlink: Update rtnl_dump_ifinfo for strict data checking
rtnetlink: Update rtnl_bridge_getlink for strict data checking
rtnetlink: Update rtnl_stats_dump for strict data checking
rtnetlink: Update inet6_dump_ifinfo for strict data checking
rtnetlink: Update ipmr_rtm_dumplink for strict data checking
rtnetlink: Update fib dumps for strict data checking
net/neighbor: Update neigh_dump_info for strict data checking
net/neighbor: Update neightbl_dump_info for strict data checking
net/namespace: Update rtnl_net_dumpid for strict data checking
net/fib_rules: Update fib_nl_dumprule for strict data checking
net/ipv6: Update ip6addrlbl_dump for strict data checking
net: Update netconf dump handlers for strict data checking
net/bridge: Update br_mdb_dump for strict data checking
rtnetlink: Move input checking for rtnl_fdb_dump to helper
rtnetlink: Update rtnl_fdb_dump for strict data checking
include/linux/netlink.h | 2 +
include/net/ip_fib.h | 2 +
include/net/netlink.h | 21 ++-
include/uapi/linux/netlink.h | 1 +
lib/nlattr.c | 48 +++++--
net/bridge/br_mdb.c | 30 ++++
net/core/devlink.c | 2 +-
net/core/fib_rules.c | 36 ++++-
net/core/neighbour.c | 119 ++++++++++++---
net/core/net_namespace.c | 6 +
net/core/rtnetlink.c | 318 ++++++++++++++++++++++++++++++++---------
net/ipv4/devinet.c | 101 ++++++++++---
net/ipv4/fib_frontend.c | 42 +++++-
net/ipv4/ipmr.c | 39 +++++
net/ipv6/addrconf.c | 177 ++++++++++++++++++-----
net/ipv6/addrlabel.c | 34 ++++-
net/ipv6/ip6_fib.c | 8 ++
net/ipv6/ip6mr.c | 9 ++
net/ipv6/route.c | 2 +-
net/mpls/af_mpls.c | 28 +++-
net/netfilter/ipvs/ip_vs_ctl.c | 2 +-
net/netlink/af_netlink.c | 33 ++++-
net/netlink/af_netlink.h | 1 +
net/sched/act_api.c | 2 +-
net/sched/cls_api.c | 6 +-
net/sched/sch_api.c | 2 +-
net/xfrm/xfrm_user.c | 2 +-
27 files changed, 908 insertions(+), 165 deletions(-)
--
2.11.0
^ permalink raw reply
* Re: [RFC PATCH bpf-next v4 4/7] bpf: add bpf queue and stack maps
From: Mauricio Vasquez @ 2018-10-08 3:15 UTC (permalink / raw)
To: Alexei Starovoitov; +Cc: Alexei Starovoitov, Daniel Borkmann, netdev
In-Reply-To: <86a2498d-4e2e-7fb9-5139-9738e3796b01@polito.it>
On 10/04/2018 10:40 PM, Mauricio Vasquez wrote:
>
>
> On 10/04/2018 06:57 PM, Alexei Starovoitov wrote:
>> On Thu, Oct 04, 2018 at 07:12:44PM +0200, Mauricio Vasquez B wrote:
>>> Implement two new kind of maps that support the peek, push and pop
>>> operations.
>>>
>>> A use case for this is to keep track of a pool of elements, like
>>> network ports in a SNAT.
>>>
>>> Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it>
>>> ---
>>> include/linux/bpf.h | 7 +
>>> include/linux/bpf_types.h | 2
>>> include/uapi/linux/bpf.h | 35 ++++-
>>> kernel/bpf/Makefile | 2
>>> kernel/bpf/core.c | 3
>>> kernel/bpf/helpers.c | 43 ++++++
>>> kernel/bpf/queue_stack_maps.c | 300
>>> +++++++++++++++++++++++++++++++++++++++++
>>> kernel/bpf/syscall.c | 31 +++-
>>> kernel/bpf/verifier.c | 14 +-
>>> net/core/filter.c | 6 +
>>> 10 files changed, 424 insertions(+), 19 deletions(-)
>>> create mode 100644 kernel/bpf/queue_stack_maps.c
>>>
>>> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
>>> index 98c7eeb6d138..cad3bc5cffd1 100644
>>> --- a/include/linux/bpf.h
>>> +++ b/include/linux/bpf.h
>>> @@ -40,6 +40,9 @@ struct bpf_map_ops {
>>> int (*map_update_elem)(struct bpf_map *map, void *key, void
>>> *value, u64 flags);
>>> int (*map_delete_elem)(struct bpf_map *map, void *key);
>>> void *(*map_lookup_and_delete_elem)(struct bpf_map *map, void
>>> *key);
>>> + int (*map_push_elem)(struct bpf_map *map, void *value, u64 flags);
>>> + int (*map_pop_elem)(struct bpf_map *map, void *value);
>>> + int (*map_peek_elem)(struct bpf_map *map, void *value);
>>> /* funcs called by prog_array and perf_event_array map */
>>> void *(*map_fd_get_ptr)(struct bpf_map *map, struct file
>>> *map_file,
>>> @@ -139,6 +142,7 @@ enum bpf_arg_type {
>>> ARG_CONST_MAP_PTR, /* const argument used as pointer to
>>> bpf_map */
>>> ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */
>>> ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */
>>> + ARG_PTR_TO_UNINIT_MAP_VALUE, /* pointer to valid memory used
>>> to store a map value */
>>> /* the following constraints used to prototype bpf_memcmp()
>>> and other
>>> * functions that access data on eBPF program stack
>>> @@ -825,6 +829,9 @@ static inline int
>>> bpf_fd_reuseport_array_update_elem(struct bpf_map *map,
>>> extern const struct bpf_func_proto bpf_map_lookup_elem_proto;
>>> extern const struct bpf_func_proto bpf_map_update_elem_proto;
>>> extern const struct bpf_func_proto bpf_map_delete_elem_proto;
>>> +extern const struct bpf_func_proto bpf_map_push_elem_proto;
>>> +extern const struct bpf_func_proto bpf_map_pop_elem_proto;
>>> +extern const struct bpf_func_proto bpf_map_peek_elem_proto;
>>> extern const struct bpf_func_proto bpf_get_prandom_u32_proto;
>>> extern const struct bpf_func_proto bpf_get_smp_processor_id_proto;
>>> diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
>>> index 658509daacd4..a2ec73aa1ec7 100644
>>> --- a/include/linux/bpf_types.h
>>> +++ b/include/linux/bpf_types.h
>>> @@ -69,3 +69,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops)
>>> BPF_MAP_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, reuseport_array_ops)
>>> #endif
>>> #endif
>>> +BPF_MAP_TYPE(BPF_MAP_TYPE_QUEUE, queue_map_ops)
>>> +BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops)
>>> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
>>> index 3bb94aa2d408..bfa042273fad 100644
>>> --- a/include/uapi/linux/bpf.h
>>> +++ b/include/uapi/linux/bpf.h
>>> @@ -129,6 +129,8 @@ enum bpf_map_type {
>>> BPF_MAP_TYPE_CGROUP_STORAGE,
>>> BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
>>> BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
>>> + BPF_MAP_TYPE_QUEUE,
>>> + BPF_MAP_TYPE_STACK,
>>> };
>>> enum bpf_prog_type {
>>> @@ -463,6 +465,28 @@ union bpf_attr {
>>> * Return
>>> * 0 on success, or a negative error in case of failure.
>>> *
>>> + * int bpf_map_push_elem(struct bpf_map *map, const void *value,
>>> u64 flags)
>>> + * Description
>>> + * Push an element *value* in *map*. *flags* is one of:
>>> + *
>>> + * **BPF_EXIST**
>>> + * If the queue/stack is full, the oldest element is
>>> removed to
>>> + * make room for this.
>>> + * Return
>>> + * 0 on success, or a negative error in case of failure.
>>> + *
>>> + * int bpf_map_pop_elem(struct bpf_map *map, void *value)
>>> + * Description
>>> + * Pop an element from *map*.
>>> + * Return
>>> + * 0 on success, or a negative error in case of failure.
>>> + *
>>> + * int bpf_map_peek_elem(struct bpf_map *map, void *value)
>>> + * Description
>>> + * Get an element from *map* without removing it.
>>> + * Return
>>> + * 0 on success, or a negative error in case of failure.
>>> + *
>>> * int bpf_probe_read(void *dst, u32 size, const void *src)
>>> * Description
>>> * For tracing programs, safely attempt to read *size*
>>> bytes from
>>> @@ -790,14 +814,14 @@ union bpf_attr {
>>> *
>>> * int ret;
>>> * struct bpf_tunnel_key key = {};
>>> - *
>>> + *
>>> * ret = bpf_skb_get_tunnel_key(skb, &key,
>>> sizeof(key), 0);
>>> * if (ret < 0)
>>> * return TC_ACT_SHOT; // drop packet
>>> - *
>>> + *
>>> * if (key.remote_ipv4 != 0x0a000001)
>>> * return TC_ACT_SHOT; // drop packet
>>> - *
>>> + *
>>> * return TC_ACT_OK; // accept packet
>>> *
>>> * This interface can also be used with all encapsulation
>>> devices
>>> @@ -2304,7 +2328,10 @@ union bpf_attr {
>>> FN(skb_ancestor_cgroup_id), \
>>> FN(sk_lookup_tcp), \
>>> FN(sk_lookup_udp), \
>>> - FN(sk_release),
>>> + FN(sk_release), \
>>> + FN(map_push_elem), \
>>> + FN(map_pop_elem), \
>>> + FN(map_peek_elem),
>>> /* integer value in 'imm' field of BPF_CALL instruction selects
>>> which helper
>>> * function eBPF program intends to call
>>> diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
>>> index 0488b8258321..17afae9e65f3 100644
>>> --- a/kernel/bpf/Makefile
>>> +++ b/kernel/bpf/Makefile
>>> @@ -3,7 +3,7 @@ obj-y := core.o
>>> obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o
>>> helpers.o tnum.o
>>> obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o
>>> percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
>>> -obj-$(CONFIG_BPF_SYSCALL) += local_storage.o
>>> +obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o
>>> obj-$(CONFIG_BPF_SYSCALL) += disasm.o
>>> obj-$(CONFIG_BPF_SYSCALL) += btf.o
>>> ifeq ($(CONFIG_NET),y)
>>> diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
>>> index 3f5bf1af0826..8d2db076d123 100644
>>> --- a/kernel/bpf/core.c
>>> +++ b/kernel/bpf/core.c
>>> @@ -1783,6 +1783,9 @@ BPF_CALL_0(bpf_user_rnd_u32)
>>> const struct bpf_func_proto bpf_map_lookup_elem_proto __weak;
>>> const struct bpf_func_proto bpf_map_update_elem_proto __weak;
>>> const struct bpf_func_proto bpf_map_delete_elem_proto __weak;
>>> +const struct bpf_func_proto bpf_map_push_elem_proto __weak;
>>> +const struct bpf_func_proto bpf_map_pop_elem_proto __weak;
>>> +const struct bpf_func_proto bpf_map_peek_elem_proto __weak;
>>> const struct bpf_func_proto bpf_get_prandom_u32_proto __weak;
>>> const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;
>>> diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
>>> index 6502115e8f55..ab0d5e3f9892 100644
>>> --- a/kernel/bpf/helpers.c
>>> +++ b/kernel/bpf/helpers.c
>>> @@ -76,6 +76,49 @@ const struct bpf_func_proto
>>> bpf_map_delete_elem_proto = {
>>> .arg2_type = ARG_PTR_TO_MAP_KEY,
>>> };
>>> +BPF_CALL_3(bpf_map_push_elem, struct bpf_map *, map, void *,
>>> value, u64, flags)
>>> +{
>>> + return map->ops->map_push_elem(map, value, flags);
>>> +}
>>> +
>>> +const struct bpf_func_proto bpf_map_push_elem_proto = {
>>> + .func = bpf_map_push_elem,
>>> + .gpl_only = false,
>>> + .pkt_access = true,
>>> + .ret_type = RET_INTEGER,
>>> + .arg1_type = ARG_CONST_MAP_PTR,
>>> + .arg2_type = ARG_PTR_TO_MAP_VALUE,
>>> + .arg3_type = ARG_ANYTHING,
>>> +};
>>> +
>>> +BPF_CALL_2(bpf_map_pop_elem, struct bpf_map *, map, void *, value)
>>> +{
>>> + return map->ops->map_pop_elem(map, value);
>>> +}
>>> +
>>> +const struct bpf_func_proto bpf_map_pop_elem_proto = {
>>> + .func = bpf_map_pop_elem,
>>> + .gpl_only = false,
>>> + .pkt_access = true,
>>> + .ret_type = RET_INTEGER,
>>> + .arg1_type = ARG_CONST_MAP_PTR,
>>> + .arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE,
>>> +};
>>> +
>>> +BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value)
>>> +{
>>> + return map->ops->map_peek_elem(map, value);
>>> +}
>>> +
>>> +const struct bpf_func_proto bpf_map_peek_elem_proto = {
>>> + .func = bpf_map_pop_elem,
>>> + .gpl_only = false,
>>> + .pkt_access = true,
>>> + .ret_type = RET_INTEGER,
>>> + .arg1_type = ARG_CONST_MAP_PTR,
>>> + .arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE,
>>> +};
>>> +
>>> const struct bpf_func_proto bpf_get_prandom_u32_proto = {
>>> .func = bpf_user_rnd_u32,
>>> .gpl_only = false,
>>> diff --git a/kernel/bpf/queue_stack_maps.c
>>> b/kernel/bpf/queue_stack_maps.c
>>> new file mode 100644
>>> index 000000000000..a597c5ba68f6
>>> --- /dev/null
>>> +++ b/kernel/bpf/queue_stack_maps.c
>>> @@ -0,0 +1,300 @@
>>> +// SPDX-License-Identifier: GPL-2.0
>>> +/*
>>> + * queue_stack_maps.c: BPF queue and stack maps
>>> + *
>>> + * Copyright (c) 2018 Politecnico di Torino
>>> + */
>>> +#include <linux/bpf.h>
>>> +#include <linux/list.h>
>>> +#include <linux/slab.h>
>>> +#include "percpu_freelist.h"
>>> +
>>> +#define QUEUE_STACK_CREATE_FLAG_MASK \
>>> + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
>>> +
>>> +
>>> +struct bpf_queue_stack {
>>> + struct bpf_map map;
>>> + raw_spinlock_t lock;
>>> + u32 head, tail;
>>> + u32 index_mask;
>>> + u32 count;
>>> +
>>> + char elements[0] __aligned(8);
>>> +};
>>> +
>>> +static struct bpf_queue_stack *bpf_queue_stack(struct bpf_map *map)
>>> +{
>>> + return container_of(map, struct bpf_queue_stack, map);
>>> +}
>>> +
>>> +static bool queue_stack_map_is_empty(struct bpf_queue_stack *qs)
>>> +{
>>> + return qs->count == 0;
>>> +}
>>> +
>>> +static bool queue_stack_map_is_full(struct bpf_queue_stack *qs)
>>> +{
>>> + return qs->count == qs->map.max_entries;
>>> +}
>>> +
>>> +/* Called from syscall */
>>> +static int queue_stack_map_alloc_check(union bpf_attr *attr)
>>> +{
>>> + /* check sanity of attributes */
>>> + if (attr->max_entries == 0 || attr->key_size != 0 ||
>>> + attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK)
>>> + return -EINVAL;
>>> +
>>> + if (attr->value_size > KMALLOC_MAX_SIZE)
>>> + /* if value_size is bigger, the user space won't be able to
>>> + * access the elements.
>>> + */
>>> + return -E2BIG;
>>> +
>>> + return 0;
>>> +}
>>> +
>>> +static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr)
>>> +{
>>> + int ret, numa_node = bpf_map_attr_numa_node(attr);
>>> + u32 max_entries, value_size, index_mask;
>>> + u64 queue_size, cost, mask64;
>>> + struct bpf_queue_stack *qs;
>>> +
>>> + max_entries = attr->max_entries;
>>> + value_size = attr->value_size;
>>> +
>>> + /* From arraymap.c:
>>> + * On 32 bit archs roundup_pow_of_two() with max_entries that has
>>> + * upper most bit set in u32 space is undefined behavior due to
>>> + * resulting 1U << 32, so do it manually here in u64 space.
>>> + */
>>> + mask64 = fls_long(max_entries - 1);
>>> + mask64 = 1ULL << mask64;
>>> + mask64 -= 1;
>>> +
>>> + index_mask = mask64;
>>> +
>>> + /* Round up queue size to nearest power of 2 */
>>> + max_entries = index_mask + 1;
>> what's the point of roundup ?
>
> If the size of the buffer is power of two we can wrap the indexes with
> an AND operation instead of MOD.
>
>> The memory waste becomes quite large when max_entries are high.
> Yes, you are right, we have the different choices described below.
>
>>
>> If queue/stack is sized to exact max_entries,
>> then 'count' can be removed too, right?
>
> If we don't use 'count' and we want to use the AND operation for
> wrapping indexes, the max entries should be 2^ - 1 because a slot is
> lost to distinguish between full/empty queue/stack.
>
> Just to summarize, we have these options:
> 1. Allow any size, round up, use the AND operation and 'count' (current).
> 2. Allow only power of 2 sizes, use the AND operation and 'count'.
> 3. Allow any size, no roundup, use the MOD operation and leaving an
> empty slot.
>
> I prefer 1 or 2, but I don't have a strong opinion, maybe allowing
> only power of two max entries could be too limiting.
> Another consideration: is this really too bad to waste memory when
> user requires a size far away of the next power of 2?
>
>>> + /* Check for overflows. */
>>> + if (max_entries < attr->max_entries)
>>> + return ERR_PTR(-E2BIG);
>>> +
>>> + queue_size = sizeof(*qs) + (u64) value_size * max_entries;
>>> +
>>> + cost = queue_size;
>>> + if (cost >= U32_MAX - PAGE_SIZE)
>>> + return ERR_PTR(-E2BIG);
>>> +
>>> + cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
>>> +
>>> + ret = bpf_map_precharge_memlock(cost);
>>> + if (ret < 0)
>>> + return ERR_PTR(ret);
>>> +
>>> + qs = bpf_map_area_alloc(queue_size, numa_node);
>>> + if (!qs)
>>> + return ERR_PTR(-ENOMEM);
>>> +
>>> + memset(qs, 0, sizeof(*qs));
>>> +
>>> + bpf_map_init_from_attr(&qs->map, attr);
>>> +
>>> + qs->map.pages = cost;
>>> + qs->index_mask = index_mask;
>>> +
>>> + raw_spin_lock_init(&qs->lock);
>>> +
>>> + return &qs->map;
>>> +}
>>> +
>>> +/* Called when map->refcnt goes to zero, either from workqueue or
>>> from syscall */
>>> +static void queue_stack_map_free(struct bpf_map *map)
>>> +{
>>> + struct bpf_queue_stack *qs = bpf_queue_stack(map);
>>> +
>>> + /* at this point bpf_prog->aux->refcnt == 0 and this
>>> map->refcnt == 0,
>>> + * so the programs (can be more than one that used this map) were
>>> + * disconnected from events. Wait for outstanding critical
>>> sections in
>>> + * these programs to complete
>>> + */
>>> + synchronize_rcu();
>>> +
>>> + bpf_map_area_free(qs);
>>> +}
>>> +
>>> +static int __queue_map_get(struct bpf_map *map, void *value, bool
>>> delete)
>>> +{
>>> + struct bpf_queue_stack *qs = bpf_queue_stack(map);
>>> + unsigned long flags;
>>> + int err = 0;
>>> + void *ptr;
>>> +
>>> + raw_spin_lock_irqsave(&qs->lock, flags);
>>> +
>>> + if (queue_stack_map_is_empty(qs)) {
>>> + err = -ENOENT;
>>> + goto out;
>>> + }
>>> +
>>> + ptr = &qs->elements[qs->tail * qs->map.value_size];
>>> + memcpy(value, ptr, qs->map.value_size);
>>> +
>>> + if (delete) {
>>> + qs->tail = (qs->tail + 1) & qs->index_mask;
>>> + qs->count--;
>>> + }
>>> +
>>> +out:
>>> + raw_spin_unlock_irqrestore(&qs->lock, flags);
>>> + return err;
>>> +}
>>> +
>>> +
>>> +static int __stack_map_get(struct bpf_map *map, void *value, bool
>>> delete)
>>> +{
>>> + struct bpf_queue_stack *qs = bpf_queue_stack(map);
>>> + unsigned long flags;
>>> + int err = 0;
>>> + void *ptr;
>>> + u32 index;
>>> +
>>> + raw_spin_lock_irqsave(&qs->lock, flags);
>>> +
>>> + if (queue_stack_map_is_empty(qs)) {
>>> + err = -ENOENT;
>>> + goto out;
>>> + }
>>> +
>>> + index = (qs->head - 1) & qs->index_mask;
>>> + ptr = &qs->elements[index * qs->map.value_size];
>>> + memcpy(value, ptr, qs->map.value_size);
>>> +
>>> + if (delete) {
>>> + qs->head = (qs->head - 1) & qs->index_mask;
>>> + qs->count--;
>>> + }
>>> +
>>> +out:
>>> + raw_spin_unlock_irqrestore(&qs->lock, flags);
>>> + return err;
>>> +}
>>> +
>>> +/* Called from syscall or from eBPF program */
>>> +static int queue_map_peek_elem(struct bpf_map *map, void *value)
>>> +{
>>> + return __queue_map_get(map, value, false);
>>> +}
>>> +
>>> +/* Called from syscall or from eBPF program */
>>> +static int stack_map_peek_elem(struct bpf_map *map, void *value)
>>> +{
>>> + return __stack_map_get(map, value, false);
>>> +}
>>> +
>>> +/* Called from syscall or from eBPF program */
>>> +static int queue_map_pop_elem(struct bpf_map *map, void *value)
>>> +{
>>> + return __queue_map_get(map, value, true);
>>> +}
>>> +
>>> +/* Called from syscall or from eBPF program */
>>> +static int stack_map_pop_elem(struct bpf_map *map, void *value)
>>> +{
>>> + return __stack_map_get(map, value, true);
>>> +}
>>> +
>>> +/* Called from syscall or from eBPF program */
>>> +static int queue_stack_map_push_elem(struct bpf_map *map, void *value,
>>> + u64 flags)
>>> +{
>>> + struct bpf_queue_stack *qs = bpf_queue_stack(map);
>>> + unsigned long irq_flags;
>>> + int err = 0;
>>> + void *dst;
>>> +
>>> + /* BPF_EXIST is used to force making room for a new element in
>>> case the
>>> + * map is full
>>> + */
>>> + bool replace = (flags & BPF_EXIST);
>>> +
>>> + /* Check supported flags for queue and stack maps */
>>> + if (flags & BPF_NOEXIST || flags > BPF_EXIST)
>>> + return -EINVAL;
>>> +
>>> + raw_spin_lock_irqsave(&qs->lock, irq_flags);
>>> +
>>> + if (queue_stack_map_is_full(qs)) {
>>> + if (!replace) {
>>> + err = -E2BIG;
>> ENOSPC is probably more accurate ?
> Agree.
Well, actually I don't, I just realized that other maps are returning
E2BIG when the max_entries is reached so probably we want to keep equal
across all maps.
>>> + goto out;
>>> + }
>>> + /* advance tail pointer to overwrite oldest element */
>> 'oldest' is ambiguous here.
>> For queue it's true, but for stack it's the last element.
>> Since stack is poping from the head, push w/exist flag will keep
>> overwriting the last element.
>
> No actually, pushing with exist flag advances the tail index, hence
> overwrites the oldest element in a stack map.
> It is like shifting the whole stack a position.
>
>
>> Pls explain it more clearly in helper description in bpf.h
>
> Will do.
>>
>>> + qs->tail = (qs->tail + 1) & qs->index_mask;
>>> + qs->count--;
>>> + }
>>> +
>>> + dst = &qs->elements[qs->head * qs->map.value_size];
>>> + memcpy(dst, value, qs->map.value_size);
>>> +
>>> + qs->head = (qs->head + 1) & qs->index_mask;
>>> + qs->count++;
>>> +
>>> +out:
>>> + raw_spin_unlock_irqrestore(&qs->lock, irq_flags);
>>> + return err;
>>> +}
>>> +
>>> +/* Called from syscall or from eBPF program */
>>> +static void *queue_stack_map_lookup_elem(struct bpf_map *map, void
>>> *key)
>>> +{
>>> + return NULL;
>>> +}
>>> +
>>> +/* Called from syscall or from eBPF program */
>>> +static int queue_stack_map_update_elem(struct bpf_map *map, void *key,
>>> + void *value, u64 flags)
>>> +{
>>> + return -EINVAL;
>>> +}
>>> +
>>> +/* Called from syscall or from eBPF program */
>>> +static int queue_stack_map_delete_elem(struct bpf_map *map, void *key)
>>> +{
>>> + return -EINVAL;
>>> +}
>>> +
>>> +/* Called from syscall */
>>> +static int queue_stack_map_get_next_key(struct bpf_map *map, void
>>> *key,
>>> + void *next_key)
>>> +{
>>> + return -EINVAL;
>>> +}
>>> +
>>> +const struct bpf_map_ops queue_map_ops = {
>>> + .map_alloc_check = queue_stack_map_alloc_check,
>>> + .map_alloc = queue_stack_map_alloc,
>>> + .map_free = queue_stack_map_free,
>>> + .map_lookup_elem = queue_stack_map_lookup_elem,
>>> + .map_update_elem = queue_stack_map_update_elem,
>>> + .map_delete_elem = queue_stack_map_delete_elem,
>>> + .map_push_elem = queue_stack_map_push_elem,
>>> + .map_pop_elem = queue_map_pop_elem,
>>> + .map_peek_elem = queue_map_peek_elem,
>>> + .map_get_next_key = queue_stack_map_get_next_key,
>>> +};
>>> +
>>> +const struct bpf_map_ops stack_map_ops = {
>>> + .map_alloc_check = queue_stack_map_alloc_check,
>>> + .map_alloc = queue_stack_map_alloc,
>>> + .map_free = queue_stack_map_free,
>>> + .map_lookup_elem = queue_stack_map_lookup_elem,
>>> + .map_update_elem = queue_stack_map_update_elem,
>>> + .map_delete_elem = queue_stack_map_delete_elem,
>>> + .map_push_elem = queue_stack_map_push_elem,
>>> + .map_pop_elem = stack_map_pop_elem,
>>> + .map_peek_elem = stack_map_peek_elem,
>>> + .map_get_next_key = queue_stack_map_get_next_key,
>>> +};
>>> diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
>>> index 50957e243bfb..c46bf2d38be3 100644
>>> --- a/kernel/bpf/syscall.c
>>> +++ b/kernel/bpf/syscall.c
>>> @@ -727,6 +727,9 @@ static int map_lookup_elem(union bpf_attr *attr)
>>> err = bpf_fd_htab_map_lookup_elem(map, key, value);
>>> } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
>>> err = bpf_fd_reuseport_array_lookup_elem(map, key, value);
>>> + } else if (map->map_type == BPF_MAP_TYPE_QUEUE ||
>>> + map->map_type == BPF_MAP_TYPE_STACK) {
>>> + err = map->ops->map_peek_elem(map, value);
>>> } else {
>>> rcu_read_lock();
>>> ptr = map->ops->map_lookup_elem(map, key);
>>> @@ -841,6 +844,9 @@ static int map_update_elem(union bpf_attr *attr)
>>> /* rcu_read_lock() is not needed */
>>> err = bpf_fd_reuseport_array_update_elem(map, key, value,
>>> attr->flags);
>>> + } else if (map->map_type == BPF_MAP_TYPE_QUEUE ||
>>> + map->map_type == BPF_MAP_TYPE_STACK) {
>>> + err = map->ops->map_push_elem(map, value, attr->flags);
>>> } else {
>>> rcu_read_lock();
>>> err = map->ops->map_update_elem(map, key, value,
>>> attr->flags);
>>> @@ -1001,11 +1007,6 @@ static int map_lookup_and_delete_elem(union
>>> bpf_attr *attr)
>>> goto err_put;
>>> }
>>> - if (!map->ops->map_lookup_and_delete_elem) {
>>> - err = -ENOTSUPP;
>>> - goto err_put;
>>> - }
>>> -
>>> key = __bpf_copy_key(ukey, map->key_size);
>>> if (IS_ERR(key)) {
>>> err = PTR_ERR(key);
>>> @@ -1028,12 +1029,22 @@ static int map_lookup_and_delete_elem(union
>>> bpf_attr *attr)
>>> */
>>> preempt_disable();
>>> __this_cpu_inc(bpf_prog_active);
>>> - rcu_read_lock();
>>> - ptr = map->ops->map_lookup_and_delete_elem(map, key);
>>> - if (ptr)
>>> - memcpy(value, ptr, value_size);
>>> - rcu_read_unlock();
>>> + if (map->map_type == BPF_MAP_TYPE_QUEUE ||
>>> + map->map_type == BPF_MAP_TYPE_STACK) {
>>> + err = map->ops->map_pop_elem(map, value);
>> please clean up the paches, so that patch 4 doesn't immediately
>> deletes the lines that were introduced in patch 3.
>> Otherwise what was the point of them in patch 3?
>
> Actually there are not deleted but moved, anyway, I will clean it up a
> little bit to move to a closer place.
>>
>>> + } else {
>>> + if (!map->ops->map_lookup_and_delete_elem) {
>>> + err = -ENOTSUPP;
>>> + goto free_value;
>>> + }
>>> + rcu_read_lock();
>>> + ptr = map->ops->map_lookup_and_delete_elem(map, key);
>>> + if (ptr)
>>> + memcpy(value, ptr, value_size);
>>> + rcu_read_unlock();
>>> err = ptr ? 0 : -ENOENT;
>>> + }
>>> +
>>> __this_cpu_dec(bpf_prog_active);
>>> preempt_enable();
>>> diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
>>> index 73c81bef6ae8..489667f93061 100644
>>> --- a/kernel/bpf/verifier.c
>>> +++ b/kernel/bpf/verifier.c
>>> @@ -2121,7 +2121,8 @@ static int check_func_arg(struct
>>> bpf_verifier_env *env, u32 regno,
>>> }
>>> if (arg_type == ARG_PTR_TO_MAP_KEY ||
>>> - arg_type == ARG_PTR_TO_MAP_VALUE) {
>>> + arg_type == ARG_PTR_TO_MAP_VALUE ||
>>> + arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) {
>>> expected_type = PTR_TO_STACK;
>>> if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE &&
>>> type != expected_type)
>>> @@ -2191,7 +2192,8 @@ static int check_func_arg(struct
>>> bpf_verifier_env *env, u32 regno,
>>> err = check_helper_mem_access(env, regno,
>>> meta->map_ptr->key_size, false,
>>> NULL);
>>> - } else if (arg_type == ARG_PTR_TO_MAP_VALUE) {
>>> + } else if (arg_type == ARG_PTR_TO_MAP_VALUE ||
>>> + arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) {
>>> /* bpf_map_xxx(..., map_ptr, ..., value) call:
>>> * check [value, value + map->value_size) validity
>>> */
>>> @@ -2200,9 +2202,10 @@ static int check_func_arg(struct
>>> bpf_verifier_env *env, u32 regno,
>>> verbose(env, "invalid map_ptr to access map->value\n");
>>> return -EACCES;
>>> }
>>> + meta->raw_mode = (arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE);
>>> err = check_helper_mem_access(env, regno,
>>> meta->map_ptr->value_size, false,
>>> - NULL);
>>> + meta);
>>> } else if (arg_type_is_mem_size(arg_type)) {
>>> bool zero_size_allowed = (arg_type ==
>>> ARG_CONST_SIZE_OR_ZERO);
>>> @@ -2676,7 +2679,10 @@ record_func_map(struct bpf_verifier_env
>>> *env, struct bpf_call_arg_meta *meta,
>>> if (func_id != BPF_FUNC_tail_call &&
>>> func_id != BPF_FUNC_map_lookup_elem &&
>>> func_id != BPF_FUNC_map_update_elem &&
>>> - func_id != BPF_FUNC_map_delete_elem)
>>> + func_id != BPF_FUNC_map_delete_elem &&
>>> + func_id != BPF_FUNC_map_push_elem &&
>>> + func_id != BPF_FUNC_map_pop_elem &&
>>> + func_id != BPF_FUNC_map_peek_elem)
>>> return 0;
>>> if (meta->map_ptr == NULL) {
>>> diff --git a/net/core/filter.c b/net/core/filter.c
>>> index 591c698bc517..40736e0d9cff 100644
>>> --- a/net/core/filter.c
>>> +++ b/net/core/filter.c
>>> @@ -4993,6 +4993,12 @@ bpf_base_func_proto(enum bpf_func_id func_id)
>>> return &bpf_map_update_elem_proto;
>>> case BPF_FUNC_map_delete_elem:
>>> return &bpf_map_delete_elem_proto;
>>> + case BPF_FUNC_map_push_elem:
>>> + return &bpf_map_push_elem_proto;
>>> + case BPF_FUNC_map_pop_elem:
>>> + return &bpf_map_pop_elem_proto;
>>> + case BPF_FUNC_map_peek_elem:
>>> + return &bpf_map_peek_elem_proto;
>>> case BPF_FUNC_get_prandom_u32:
>>> return &bpf_get_prandom_u32_proto;
>>> case BPF_FUNC_get_smp_processor_id:
>>>
>
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox