* [PATCH net-next 4/6] net: Fill in extack for mpls lwt encap
From: David Ahern @ 2017-05-25 3:54 UTC (permalink / raw)
To: netdev; +Cc: roopa, David Ahern
In-Reply-To: <20170525035442.51407-1-dsahern@gmail.com>
Fill in extack for errors in build_state for mpls lwt encap including
passing extack to nla_get_labels and adding error messages for failures
in it.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
net/mpls/af_mpls.c | 49 ++++++++++++++++++++++++++++++++++++++----------
net/mpls/internal.h | 2 +-
net/mpls/mpls_iptunnel.c | 12 +++++++-----
3 files changed, 47 insertions(+), 16 deletions(-)
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 257ec66009da..f3830951fb1c 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -728,8 +728,8 @@ static int mpls_nh_build(struct net *net, struct mpls_route *rt,
goto errout;
if (newdst) {
- err = nla_get_labels(newdst, max_labels,
- &nh->nh_labels, nh->nh_label);
+ err = nla_get_labels(newdst, max_labels, &nh->nh_labels,
+ nh->nh_label, NULL);
if (err)
goto errout;
}
@@ -782,7 +782,8 @@ static u8 mpls_count_nexthops(struct rtnexthop *rtnh, int len,
nla = nla_find(attrs, attrlen, RTA_NEWDST);
if (nla &&
- nla_get_labels(nla, MAX_NEW_LABELS, &n_labels, NULL) != 0)
+ nla_get_labels(nla, MAX_NEW_LABELS, &n_labels,
+ NULL, NULL) != 0)
return 0;
*max_labels = max_t(u8, *max_labels, n_labels);
@@ -1541,8 +1542,8 @@ int nla_put_labels(struct sk_buff *skb, int attrtype,
}
EXPORT_SYMBOL_GPL(nla_put_labels);
-int nla_get_labels(const struct nlattr *nla,
- u8 max_labels, u8 *labels, u32 label[])
+int nla_get_labels(const struct nlattr *nla, u8 max_labels, u8 *labels,
+ u32 label[], struct netlink_ext_ack *extack)
{
unsigned len = nla_len(nla);
struct mpls_shim_hdr *nla_label;
@@ -1553,13 +1554,18 @@ int nla_get_labels(const struct nlattr *nla,
/* len needs to be an even multiple of 4 (the label size). Number
* of labels is a u8 so check for overflow.
*/
- if (len & 3 || len / 4 > 255)
+ if (len & 3 || len / 4 > 255) {
+ NL_SET_ERR_MSG_ATTR(extack, nla,
+ "Invalid length for labels attribute");
return -EINVAL;
+ }
/* Limit the number of new labels allowed */
nla_labels = len/4;
- if (nla_labels > max_labels)
+ if (nla_labels > max_labels) {
+ NL_SET_ERR_MSG(extack, "Too many labels");
return -EINVAL;
+ }
/* when label == NULL, caller wants number of labels */
if (!label)
@@ -1574,8 +1580,29 @@ int nla_get_labels(const struct nlattr *nla,
/* Ensure the bottom of stack flag is properly set
* and ttl and tc are both clear.
*/
- if ((dec.bos != bos) || dec.ttl || dec.tc)
+ if (dec.ttl) {
+ NL_SET_ERR_MSG_ATTR(extack, nla,
+ "TTL in label must be 0");
+ return -EINVAL;
+ }
+
+ if (dec.tc) {
+ NL_SET_ERR_MSG_ATTR(extack, nla,
+ "Traffic class in label must be 0");
return -EINVAL;
+ }
+
+ if (dec.bos != bos) {
+ NL_SET_BAD_ATTR(extack, nla);
+ if (bos) {
+ NL_SET_ERR_MSG(extack,
+ "BOS bit must be set in first label");
+ } else {
+ NL_SET_ERR_MSG(extack,
+ "BOS bit can only be set in first label");
+ }
+ return -EINVAL;
+ }
switch (dec.label) {
case MPLS_LABEL_IMPLNULL:
@@ -1583,6 +1610,8 @@ int nla_get_labels(const struct nlattr *nla,
* assign and distribute, but which never
* actually appears in the encapsulation.
*/
+ NL_SET_ERR_MSG_ATTR(extack, nla,
+ "Implicit NULL Label (3) can not be used in encapsulation");
return -EINVAL;
}
@@ -1696,14 +1725,14 @@ static int rtm_to_route_config(struct sk_buff *skb, struct nlmsghdr *nlh,
case RTA_NEWDST:
if (nla_get_labels(nla, MAX_NEW_LABELS,
&cfg->rc_output_labels,
- cfg->rc_output_label))
+ cfg->rc_output_label, NULL))
goto errout;
break;
case RTA_DST:
{
u8 label_count;
if (nla_get_labels(nla, 1, &label_count,
- &cfg->rc_label))
+ &cfg->rc_label, NULL))
goto errout;
/* Reserved labels may not be set */
diff --git a/net/mpls/internal.h b/net/mpls/internal.h
index 4db6a5971322..e59f299ceb3f 100644
--- a/net/mpls/internal.h
+++ b/net/mpls/internal.h
@@ -203,7 +203,7 @@ static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev)
int nla_put_labels(struct sk_buff *skb, int attrtype, u8 labels,
const u32 label[]);
int nla_get_labels(const struct nlattr *nla, u8 max_labels, u8 *labels,
- u32 label[]);
+ u32 label[], struct netlink_ext_ack *extack);
int nla_get_via(const struct nlattr *nla, u8 *via_alen, u8 *via_table,
u8 via[]);
bool mpls_output_possible(const struct net_device *dev);
diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c
index 15e1aa708e50..6e558a419f60 100644
--- a/net/mpls/mpls_iptunnel.c
+++ b/net/mpls/mpls_iptunnel.c
@@ -173,13 +173,14 @@ static int mpls_build_state(struct nlattr *nla,
if (ret < 0)
return ret;
- if (!tb[MPLS_IPTUNNEL_DST])
+ if (!tb[MPLS_IPTUNNEL_DST]) {
+ NL_SET_ERR_MSG(extack, "MPLS_IPTUNNEL_DST attribute is missing");
return -EINVAL;
-
+ }
/* determine number of labels */
- if (nla_get_labels(tb[MPLS_IPTUNNEL_DST],
- MAX_NEW_LABELS, &n_labels, NULL))
+ if (nla_get_labels(tb[MPLS_IPTUNNEL_DST], MAX_NEW_LABELS,
+ &n_labels, NULL, extack))
return -EINVAL;
newts = lwtunnel_state_alloc(sizeof(*tun_encap_info) +
@@ -189,7 +190,8 @@ static int mpls_build_state(struct nlattr *nla,
tun_encap_info = mpls_lwtunnel_encap(newts);
ret = nla_get_labels(tb[MPLS_IPTUNNEL_DST], n_labels,
- &tun_encap_info->labels, tun_encap_info->label);
+ &tun_encap_info->labels, tun_encap_info->label,
+ extack);
if (ret)
goto errout;
--
2.11.0 (Apple Git-81)
^ permalink raw reply related
* [PATCH net-next 3/6] net: plumb extack arg down to lwtunnel build state
From: David Ahern @ 2017-05-25 3:54 UTC (permalink / raw)
To: netdev; +Cc: roopa, David Ahern
In-Reply-To: <20170525035442.51407-1-dsahern@gmail.com>
Pass extack arg down to lwtunnel_build_state and the build_state callbacks.
Add messages for failures in lwtunnel_build_state, and add the extarg to
nla_parse where possible in the build_state callbacks.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/linux/netlink.h | 10 ++++++++++
include/net/lwtunnel.h | 9 ++++++---
net/core/lwt_bpf.c | 5 +++--
net/core/lwtunnel.c | 20 +++++++++++++++++---
net/ipv4/fib_lookup.h | 3 ++-
net/ipv4/fib_semantics.c | 20 +++++++++++---------
net/ipv4/fib_trie.c | 2 +-
net/ipv4/ip_tunnel_core.c | 11 +++++++----
net/ipv6/ila/ila_lwt.c | 5 +++--
net/ipv6/route.c | 2 +-
net/ipv6/seg6_iptunnel.c | 5 +++--
net/mpls/mpls_iptunnel.c | 5 +++--
12 files changed, 67 insertions(+), 30 deletions(-)
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index a68aad484c69..8664fd26eb5d 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -102,6 +102,16 @@ struct netlink_ext_ack {
(extack)->bad_attr = (attr); \
} while (0)
+#define NL_SET_ERR_MSG_ATTR(extack, attr, msg) do { \
+ static const char __msg[] = (msg); \
+ struct netlink_ext_ack *__extack = (extack); \
+ \
+ if (__extack) { \
+ __extack->_msg = __msg; \
+ __extack->bad_attr = (attr); \
+ } \
+} while (0)
+
extern void netlink_kernel_release(struct sock *sk);
extern int __netlink_change_ngroups(struct sock *sk, unsigned int groups);
extern int netlink_change_ngroups(struct sock *sk, unsigned int groups);
diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index ca6f002774ef..7c26863b8cf4 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -35,7 +35,8 @@ struct lwtunnel_state {
struct lwtunnel_encap_ops {
int (*build_state)(struct nlattr *encap,
unsigned int family, const void *cfg,
- struct lwtunnel_state **ts);
+ struct lwtunnel_state **ts,
+ struct netlink_ext_ack *extack);
void (*destroy_state)(struct lwtunnel_state *lws);
int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb);
int (*input)(struct sk_buff *skb);
@@ -114,7 +115,8 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len,
int lwtunnel_build_state(u16 encap_type,
struct nlattr *encap,
unsigned int family, const void *cfg,
- struct lwtunnel_state **lws);
+ struct lwtunnel_state **lws,
+ struct netlink_ext_ack *extack);
int lwtunnel_fill_encap(struct sk_buff *skb,
struct lwtunnel_state *lwtstate);
int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate);
@@ -192,7 +194,8 @@ static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len,
static inline int lwtunnel_build_state(u16 encap_type,
struct nlattr *encap,
unsigned int family, const void *cfg,
- struct lwtunnel_state **lws)
+ struct lwtunnel_state **lws,
+ struct netlink_ext_ack *extack)
{
return -EOPNOTSUPP;
}
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index b3bc0a31af9f..1307731ddfe4 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -240,7 +240,8 @@ static const struct nla_policy bpf_nl_policy[LWT_BPF_MAX + 1] = {
static int bpf_build_state(struct nlattr *nla,
unsigned int family, const void *cfg,
- struct lwtunnel_state **ts)
+ struct lwtunnel_state **ts,
+ struct netlink_ext_ack *extack)
{
struct nlattr *tb[LWT_BPF_MAX + 1];
struct lwtunnel_state *newts;
@@ -250,7 +251,7 @@ static int bpf_build_state(struct nlattr *nla,
if (family != AF_INET && family != AF_INET6)
return -EAFNOSUPPORT;
- ret = nla_parse_nested(tb, LWT_BPF_MAX, nla, bpf_nl_policy, NULL);
+ ret = nla_parse_nested(tb, LWT_BPF_MAX, nla, bpf_nl_policy, extack);
if (ret < 0)
return ret;
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index ab840386a74d..a0feca1df7b5 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -103,25 +103,39 @@ EXPORT_SYMBOL(lwtunnel_encap_del_ops);
int lwtunnel_build_state(u16 encap_type,
struct nlattr *encap, unsigned int family,
- const void *cfg, struct lwtunnel_state **lws)
+ const void *cfg, struct lwtunnel_state **lws,
+ struct netlink_ext_ack *extack)
{
const struct lwtunnel_encap_ops *ops;
+ bool found = false;
int ret = -EINVAL;
if (encap_type == LWTUNNEL_ENCAP_NONE ||
- encap_type > LWTUNNEL_ENCAP_MAX)
+ encap_type > LWTUNNEL_ENCAP_MAX) {
+ NL_SET_BAD_ATTR(extack, encap);
+ NL_SET_ERR_MSG(extack, "Unknown LWT encapsulation type");
return ret;
+ }
ret = -EOPNOTSUPP;
rcu_read_lock();
ops = rcu_dereference(lwtun_encaps[encap_type]);
if (likely(ops && ops->build_state && try_module_get(ops->owner))) {
- ret = ops->build_state(encap, family, cfg, lws);
+ found = true;
+ ret = ops->build_state(encap, family, cfg, lws, extack);
if (ret)
module_put(ops->owner);
}
rcu_read_unlock();
+ /* don't rely on -EOPNOTSUPP to detect match as build_state
+ * handlers could return it
+ */
+ if (!found) {
+ NL_SET_BAD_ATTR(extack, encap);
+ NL_SET_ERR_MSG(extack, "LWT encapsulation type not supported");
+ }
+
return ret;
}
EXPORT_SYMBOL(lwtunnel_build_state);
diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index 2704e08545da..769ab87ebc4b 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -30,7 +30,8 @@ static inline void fib_alias_accessed(struct fib_alias *fa)
void fib_release_info(struct fib_info *);
struct fib_info *fib_create_info(struct fib_config *cfg,
struct netlink_ext_ack *extack);
-int fib_nh_match(struct fib_config *cfg, struct fib_info *fi);
+int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
+ struct netlink_ext_ack *extack);
int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, u32 tb_id,
u8 type, __be32 dst, int dst_len, u8 tos, struct fib_info *fi,
unsigned int);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 4852e183afe0..89e8fcc8449b 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -530,7 +530,7 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
ret = lwtunnel_build_state(nla_get_u16(
nla_entype),
nla, AF_INET, cfg,
- &lwtstate);
+ &lwtstate, extack);
if (ret)
goto errout;
nexthop_nh->nh_lwtstate =
@@ -612,7 +612,8 @@ static inline void fib_add_weight(struct fib_info *fi,
static int fib_encap_match(u16 encap_type,
struct nlattr *encap,
const struct fib_nh *nh,
- const struct fib_config *cfg)
+ const struct fib_config *cfg,
+ struct netlink_ext_ack *extack)
{
struct lwtunnel_state *lwtstate;
int ret, result = 0;
@@ -620,8 +621,8 @@ static int fib_encap_match(u16 encap_type,
if (encap_type == LWTUNNEL_ENCAP_NONE)
return 0;
- ret = lwtunnel_build_state(encap_type, encap,
- AF_INET, cfg, &lwtstate);
+ ret = lwtunnel_build_state(encap_type, encap, AF_INET,
+ cfg, &lwtstate, extack);
if (!ret) {
result = lwtunnel_cmp_encap(lwtstate, nh->nh_lwtstate);
lwtstate_free(lwtstate);
@@ -630,7 +631,8 @@ static int fib_encap_match(u16 encap_type,
return result;
}
-int fib_nh_match(struct fib_config *cfg, struct fib_info *fi)
+int fib_nh_match(struct fib_config *cfg, struct fib_info *fi,
+ struct netlink_ext_ack *extack)
{
#ifdef CONFIG_IP_ROUTE_MULTIPATH
struct rtnexthop *rtnh;
@@ -642,9 +644,9 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi)
if (cfg->fc_oif || cfg->fc_gw) {
if (cfg->fc_encap) {
- if (fib_encap_match(cfg->fc_encap_type,
- cfg->fc_encap, fi->fib_nh, cfg))
- return 1;
+ if (fib_encap_match(cfg->fc_encap_type, cfg->fc_encap,
+ fi->fib_nh, cfg, extack))
+ return 1;
}
if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) &&
(!cfg->fc_gw || cfg->fc_gw == fi->fib_nh->nh_gw))
@@ -1145,7 +1147,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
}
err = lwtunnel_build_state(cfg->fc_encap_type,
cfg->fc_encap, AF_INET, cfg,
- &lwtstate);
+ &lwtstate, extack);
if (err)
goto failure;
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 015ff759b0fd..03800e39e924 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1561,7 +1561,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb,
fi->fib_prefsrc == cfg->fc_prefsrc) &&
(!cfg->fc_protocol ||
fi->fib_protocol == cfg->fc_protocol) &&
- fib_nh_match(cfg, fi) == 0) {
+ fib_nh_match(cfg, fi, extack) == 0) {
fa_to_delete = fa;
break;
}
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index baf196eaf1d8..90e11479c725 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -228,14 +228,16 @@ static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = {
static int ip_tun_build_state(struct nlattr *attr,
unsigned int family, const void *cfg,
- struct lwtunnel_state **ts)
+ struct lwtunnel_state **ts,
+ struct netlink_ext_ack *extack)
{
struct ip_tunnel_info *tun_info;
struct lwtunnel_state *new_state;
struct nlattr *tb[LWTUNNEL_IP_MAX + 1];
int err;
- err = nla_parse_nested(tb, LWTUNNEL_IP_MAX, attr, ip_tun_policy, NULL);
+ err = nla_parse_nested(tb, LWTUNNEL_IP_MAX, attr, ip_tun_policy,
+ extack);
if (err < 0)
return err;
@@ -325,7 +327,8 @@ static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = {
static int ip6_tun_build_state(struct nlattr *attr,
unsigned int family, const void *cfg,
- struct lwtunnel_state **ts)
+ struct lwtunnel_state **ts,
+ struct netlink_ext_ack *extack)
{
struct ip_tunnel_info *tun_info;
struct lwtunnel_state *new_state;
@@ -333,7 +336,7 @@ static int ip6_tun_build_state(struct nlattr *attr,
int err;
err = nla_parse_nested(tb, LWTUNNEL_IP6_MAX, attr, ip6_tun_policy,
- NULL);
+ extack);
if (err < 0)
return err;
diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c
index f4a413aba423..0c02a09bc351 100644
--- a/net/ipv6/ila/ila_lwt.c
+++ b/net/ipv6/ila/ila_lwt.c
@@ -117,7 +117,8 @@ static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = {
static int ila_build_state(struct nlattr *nla,
unsigned int family, const void *cfg,
- struct lwtunnel_state **ts)
+ struct lwtunnel_state **ts,
+ struct netlink_ext_ack *extack)
{
struct ila_lwt *ilwt;
struct ila_params *p;
@@ -146,7 +147,7 @@ static int ila_build_state(struct nlattr *nla,
return -EINVAL;
}
- ret = nla_parse_nested(tb, ILA_ATTR_MAX, nla, ila_nl_policy, NULL);
+ ret = nla_parse_nested(tb, ILA_ATTR_MAX, nla, ila_nl_policy, extack);
if (ret < 0)
return ret;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index afc76b24ee6b..0146116f8539 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1939,7 +1939,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
err = lwtunnel_build_state(cfg->fc_encap_type,
cfg->fc_encap, AF_INET6, cfg,
- &lwtstate);
+ &lwtstate, extack);
if (err)
goto out;
rt->dst.lwtstate = lwtstate_get(lwtstate);
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 6a495490d43e..264d772d3c7d 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -326,7 +326,8 @@ static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
static int seg6_build_state(struct nlattr *nla,
unsigned int family, const void *cfg,
- struct lwtunnel_state **ts)
+ struct lwtunnel_state **ts,
+ struct netlink_ext_ack *extack)
{
struct nlattr *tb[SEG6_IPTUNNEL_MAX + 1];
struct seg6_iptunnel_encap *tuninfo;
@@ -336,7 +337,7 @@ static int seg6_build_state(struct nlattr *nla,
int err;
err = nla_parse_nested(tb, SEG6_IPTUNNEL_MAX, nla,
- seg6_iptunnel_policy, NULL);
+ seg6_iptunnel_policy, extack);
if (err < 0)
return err;
diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c
index 369c7a23c86c..15e1aa708e50 100644
--- a/net/mpls/mpls_iptunnel.c
+++ b/net/mpls/mpls_iptunnel.c
@@ -159,7 +159,8 @@ static int mpls_xmit(struct sk_buff *skb)
static int mpls_build_state(struct nlattr *nla,
unsigned int family, const void *cfg,
- struct lwtunnel_state **ts)
+ struct lwtunnel_state **ts,
+ struct netlink_ext_ack *extack)
{
struct mpls_iptunnel_encap *tun_encap_info;
struct nlattr *tb[MPLS_IPTUNNEL_MAX + 1];
@@ -168,7 +169,7 @@ static int mpls_build_state(struct nlattr *nla,
int ret;
ret = nla_parse_nested(tb, MPLS_IPTUNNEL_MAX, nla,
- mpls_iptunnel_policy, NULL);
+ mpls_iptunnel_policy, extack);
if (ret < 0)
return ret;
--
2.11.0 (Apple Git-81)
^ permalink raw reply related
* [PATCH net-next 2/6] net: lwtunnel: Add extack to encap attr validation
From: David Ahern @ 2017-05-25 3:54 UTC (permalink / raw)
To: netdev; +Cc: roopa, David Ahern
In-Reply-To: <20170525035442.51407-1-dsahern@gmail.com>
Pass extack down to lwtunnel_valid_encap_type and
lwtunnel_valid_encap_type_attr. Add messages for unknown
or unsupported encap types.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/lwtunnel.h | 13 +++++++++----
net/core/lwtunnel.c | 18 +++++++++++++-----
net/ipv4/fib_frontend.c | 6 ++++--
net/ipv6/route.c | 4 ++--
4 files changed, 28 insertions(+), 13 deletions(-)
diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index ebfe237aad7e..ca6f002774ef 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -107,8 +107,10 @@ int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op,
unsigned int num);
int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op,
unsigned int num);
-int lwtunnel_valid_encap_type(u16 encap_type);
-int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len);
+int lwtunnel_valid_encap_type(u16 encap_type,
+ struct netlink_ext_ack *extack);
+int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len,
+ struct netlink_ext_ack *extack);
int lwtunnel_build_state(u16 encap_type,
struct nlattr *encap,
unsigned int family, const void *cfg,
@@ -172,11 +174,14 @@ static inline int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op,
return -EOPNOTSUPP;
}
-static inline int lwtunnel_valid_encap_type(u16 encap_type)
+static inline int lwtunnel_valid_encap_type(u16 encap_type,
+ struct netlink_ext_ack *extack)
{
+ NL_SET_ERR_MSG(extack, "CONFIG_LWTUNNEL is not enabled in this kernel");
return -EOPNOTSUPP;
}
-static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len)
+static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len,
+ struct netlink_ext_ack *extack)
{
/* return 0 since we are not walking attr looking for
* RTA_ENCAP_TYPE attribute on nexthops.
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index cfae3d5fe11f..ab840386a74d 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -126,14 +126,16 @@ int lwtunnel_build_state(u16 encap_type,
}
EXPORT_SYMBOL(lwtunnel_build_state);
-int lwtunnel_valid_encap_type(u16 encap_type)
+int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack)
{
const struct lwtunnel_encap_ops *ops;
int ret = -EINVAL;
if (encap_type == LWTUNNEL_ENCAP_NONE ||
- encap_type > LWTUNNEL_ENCAP_MAX)
+ encap_type > LWTUNNEL_ENCAP_MAX) {
+ NL_SET_ERR_MSG(extack, "Unknown lwt encapsulation type");
return ret;
+ }
rcu_read_lock();
ops = rcu_dereference(lwtun_encaps[encap_type]);
@@ -153,11 +155,16 @@ int lwtunnel_valid_encap_type(u16 encap_type)
}
}
#endif
- return ops ? 0 : -EOPNOTSUPP;
+ ret = ops ? 0 : -EOPNOTSUPP;
+ if (ret < 0)
+ NL_SET_ERR_MSG(extack, "lwt encapsulation type not supported");
+
+ return ret;
}
EXPORT_SYMBOL(lwtunnel_valid_encap_type);
-int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining)
+int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining,
+ struct netlink_ext_ack *extack)
{
struct rtnexthop *rtnh = (struct rtnexthop *)attr;
struct nlattr *nla_entype;
@@ -174,7 +181,8 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining)
if (nla_entype) {
encap_type = nla_get_u16(nla_entype);
- if (lwtunnel_valid_encap_type(encap_type) != 0)
+ if (lwtunnel_valid_encap_type(encap_type,
+ extack) != 0)
return -EOPNOTSUPP;
}
}
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 2d55882d566e..f03fe8521f6e 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -684,7 +684,8 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
break;
case RTA_MULTIPATH:
err = lwtunnel_valid_encap_type_attr(nla_data(attr),
- nla_len(attr));
+ nla_len(attr),
+ extack);
if (err < 0)
goto errout;
cfg->fc_mp = nla_data(attr);
@@ -701,7 +702,8 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
break;
case RTA_ENCAP_TYPE:
cfg->fc_encap_type = nla_get_u16(attr);
- err = lwtunnel_valid_encap_type(cfg->fc_encap_type);
+ err = lwtunnel_valid_encap_type(cfg->fc_encap_type,
+ extack);
if (err < 0)
goto errout;
break;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 80bda31ffbbe..afc76b24ee6b 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3016,7 +3016,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]);
err = lwtunnel_valid_encap_type_attr(cfg->fc_mp,
- cfg->fc_mp_len);
+ cfg->fc_mp_len, extack);
if (err < 0)
goto errout;
}
@@ -3035,7 +3035,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
if (tb[RTA_ENCAP_TYPE]) {
cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]);
- err = lwtunnel_valid_encap_type(cfg->fc_encap_type);
+ err = lwtunnel_valid_encap_type(cfg->fc_encap_type, extack);
if (err < 0)
goto errout;
}
--
2.11.0 (Apple Git-81)
^ permalink raw reply related
* [PATCH net-next 1/6] net: ipv4: Add extack message for invalid prefix or length
From: David Ahern @ 2017-05-25 3:54 UTC (permalink / raw)
To: netdev; +Cc: roopa, David Ahern
In-Reply-To: <20170525035442.51407-1-dsahern@gmail.com>
Add extack error message for invalid prefix length and invalid prefix.
Example of the latter is a route spec containing 172.16.100.1/24, where
the /24 mask means the lower 8-bits should be 0. Amazing how easy that
one is to overlook when an EINVAL is returned.
Signed-off-by: David Ahern <dsahern@gmail.com>
---
include/net/ip_fib.h | 3 ++-
net/ipv4/fib_frontend.c | 6 +++---
net/ipv4/fib_trie.c | 20 +++++++++++++++-----
3 files changed, 20 insertions(+), 9 deletions(-)
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 42e8b8f55f7c..d490a0f8dc4c 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -265,7 +265,8 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
struct fib_result *res, int fib_flags);
int fib_table_insert(struct net *, struct fib_table *, struct fib_config *,
struct netlink_ext_ack *extack);
-int fib_table_delete(struct net *, struct fib_table *, struct fib_config *);
+int fib_table_delete(struct net *, struct fib_table *, struct fib_config *,
+ struct netlink_ext_ack *extack);
int fib_table_dump(struct fib_table *table, struct sk_buff *skb,
struct netlink_callback *cb);
int fib_table_flush(struct net *net, struct fib_table *table);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 14d2f7bd7c76..2d55882d566e 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -588,7 +588,7 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg)
if (cmd == SIOCDELRT) {
tb = fib_get_table(net, cfg.fc_table);
if (tb)
- err = fib_table_delete(net, tb, &cfg);
+ err = fib_table_delete(net, tb, &cfg, NULL);
else
err = -ESRCH;
} else {
@@ -732,7 +732,7 @@ static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
goto errout;
}
- err = fib_table_delete(net, tb, &cfg);
+ err = fib_table_delete(net, tb, &cfg, extack);
errout:
return err;
}
@@ -851,7 +851,7 @@ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifad
if (cmd == RTM_NEWROUTE)
fib_table_insert(net, tb, &cfg, NULL);
else
- fib_table_delete(net, tb, &cfg);
+ fib_table_delete(net, tb, &cfg, NULL);
}
void fib_add_ifaddr(struct in_ifaddr *ifa)
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 6d0f6c79d9aa..015ff759b0fd 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1115,15 +1115,20 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
u32 key;
int err;
- if (plen > KEYLENGTH)
+ if (plen > KEYLENGTH) {
+ NL_SET_ERR_MSG(extack, "Invalid prefix length");
return -EINVAL;
+ }
key = ntohl(cfg->fc_dst);
pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen);
- if ((plen < KEYLENGTH) && (key << plen))
+ if ((plen < KEYLENGTH) && (key << plen)) {
+ NL_SET_ERR_MSG(extack,
+ "Invalid prefix for given prefix length");
return -EINVAL;
+ }
fi = fib_create_info(cfg, extack);
if (IS_ERR(fi)) {
@@ -1507,7 +1512,7 @@ static void fib_remove_alias(struct trie *t, struct key_vector *tp,
/* Caller must hold RTNL. */
int fib_table_delete(struct net *net, struct fib_table *tb,
- struct fib_config *cfg)
+ struct fib_config *cfg, struct netlink_ext_ack *extack)
{
struct trie *t = (struct trie *) tb->tb_data;
struct fib_alias *fa, *fa_to_delete;
@@ -1517,13 +1522,18 @@ int fib_table_delete(struct net *net, struct fib_table *tb,
u8 tos = cfg->fc_tos;
u32 key;
- if (plen > KEYLENGTH)
+ if (plen > KEYLENGTH) {
+ NL_SET_ERR_MSG(extack, "Invalid prefix length");
return -EINVAL;
+ }
key = ntohl(cfg->fc_dst);
- if ((plen < KEYLENGTH) && (key << plen))
+ if ((plen < KEYLENGTH) && (key << plen)) {
+ NL_SET_ERR_MSG(extack,
+ "Invalid prefix for given prefix length");
return -EINVAL;
+ }
l = fib_find_node(t, &tp, key);
if (!l)
--
2.11.0 (Apple Git-81)
^ permalink raw reply related
* [PATCH net-next 0/6] net: another round of extack handling for routing
From: David Ahern @ 2017-05-25 3:54 UTC (permalink / raw)
To: netdev; +Cc: roopa, David Ahern
This set focuses on passing extack through lwtunnel and MPLS with
additional catches for IPv4 route add and minor cleanups in MPLS
encountered passing the extack arg around.
David Ahern (6):
net: ipv4: Add extack message for invalid prefix or length
net: lwtunnel: Add extack to encap attr validation
net: plumb extack arg down to lwtunnel build state
net: Fill in extack for mpls lwt encap
net: mpls: Add extack messages for route add and delete failures
net: mpls: minor cleanups
include/linux/netlink.h | 10 +++
include/net/ip_fib.h | 3 +-
include/net/lwtunnel.h | 22 ++++--
net/core/lwt_bpf.c | 5 +-
net/core/lwtunnel.c | 38 ++++++++--
net/ipv4/fib_frontend.c | 12 +--
net/ipv4/fib_lookup.h | 3 +-
net/ipv4/fib_semantics.c | 20 ++---
net/ipv4/fib_trie.c | 22 ++++--
net/ipv4/ip_tunnel_core.c | 11 ++-
net/ipv6/ila/ila_lwt.c | 5 +-
net/ipv6/route.c | 6 +-
net/ipv6/seg6_iptunnel.c | 5 +-
net/mpls/af_mpls.c | 184 ++++++++++++++++++++++++++++++++++------------
net/mpls/internal.h | 4 +-
net/mpls/mpls_iptunnel.c | 17 +++--
16 files changed, 259 insertions(+), 108 deletions(-)
--
2.11.0 (Apple Git-81)
^ permalink raw reply
* Re: [PATCH net-next 1/8] net: ipv4: refactor __ip_route_output_key_hash
From: Roopa Prabhu @ 2017-05-25 3:05 UTC (permalink / raw)
To: David Ahern
Cc: Rosen, Rami, davem@davemloft.net, netdev@vger.kernel.org,
nikolay@cumulusnetworks.com
In-Reply-To: <692be183-cb75-fe33-605b-e458b10ef240@gmail.com>
On Wed, May 24, 2017 at 6:10 PM, David Ahern <dsahern@gmail.com> wrote:
> On 5/24/17 1:33 PM, Rosen, Rami wrote:
>> Hi, Rupa /David Ahern,
>>
>> First, thanks for this patch set!
>>
>> Second, it seems to me that something might be incorrect here.
>>
>> You have these additions in this patch (1/8):
>> ...
>> +struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *flp,
>> + const struct sk_buff *skb,
>> + struct fib_result *res);
>> ...
>> +struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
>> + const struct sk_buff *skb)
>> +{
>> + struct fib_result res;
>> + struct rtable *rth;
>> +
>> + res.tclassid = 0;
>> + res.fi = NULL;
>> + res.table = NULL;
>> +
>> + rcu_read_lock();
>> + rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
>> rcu_read_unlock();
>> +
>> return rth;
>> }
>> -EXPORT_SYMBOL_GPL(__ip_route_output_key_hash);
>> +EXPORT_SYMBOL_GPL(ip_route_output_key_hash);
>>
>>
>> So the third parameter to ip_route_output_key_hash_rcu() should be skb*, and the fourth parameter should be fib_result *. However, you do not pass the skb parameter
>> when calling ip_route_output_key_hash_rcu() in
>> ip_route_output_key_hash() (in fact you don't use it at all), and you pass mp_hash as the fourth parameter.
>
> Yep, it's a problem with the forward port of the first round of patches.
yep,
>
> Roopa: in include/net/route.h, __ip_route_output_key_hash should be
> removed as well.
ack, thanks Rami and david.
will fix it in v2.
^ permalink raw reply
* [PATCH] bonding: Don't update slave->link until ready to commit
From: Nithin Nayak Sujir @ 2017-05-25 2:45 UTC (permalink / raw)
To: davem; +Cc: netdev, Nithin Nayak Sujir, Mahesh Bandewar, Jay Vosburgh
In the loadbalance arp monitoring scheme, when a slave link change is
detected, the slave->link is immediately updated and slave_state_changed
is set. Later down the function, the rtnl_lock is acquired and the
changes are committed, updating the bond link state.
However, the acquisition of the rtnl_lock can fail. The next time the
monitor runs, since slave->link is already updated, it determines that
link is unchanged. This results in the bond link state permanently out
of sync with the slave link.
This patch modifies bond_loadbalance_arp_mon() to handle link changes
identical to bond_ab_arp_{inspect/commit}(). The new link state is
maintained in slave->new_link until we're ready to commit at which point
it's copied into slave->link.
NOTE: miimon_{inspect/commit}() has a more complex state machine
requiring the use of the bond_{propose,commit}_link_state() functions
which maintains the intermediate state in slave->link_new_state. The arp
monitors don't require that.
Testing: This bug is very easy to reproduce with the following steps.
1. In a loop, toggle a slave link of a bond slave interface.
2. In a separate loop, do ifconfig up/down of an unrelated interface to
create contention for rtnl_lock.
Within a few iterations, the bond link goes out of sync with the slave
link.
Signed-off-by: Nithin Nayak Sujir <nsujir@tintri.com>
Cc: Mahesh Bandewar <maheshb@google.com>
Cc: Jay Vosburgh <jay.vosburgh@canonical.com>
---
drivers/net/bonding/bond_main.c | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 7331331..2359478b 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2612,11 +2612,13 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
bond_for_each_slave_rcu(bond, slave, iter) {
unsigned long trans_start = dev_trans_start(slave->dev);
+ slave->new_link = BOND_LINK_NOCHANGE;
+
if (slave->link != BOND_LINK_UP) {
if (bond_time_in_interval(bond, trans_start, 1) &&
bond_time_in_interval(bond, slave->last_rx, 1)) {
- slave->link = BOND_LINK_UP;
+ slave->new_link = BOND_LINK_UP;
slave_state_changed = 1;
/* primary_slave has no meaning in round-robin
@@ -2643,7 +2645,7 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
if (!bond_time_in_interval(bond, trans_start, 2) ||
!bond_time_in_interval(bond, slave->last_rx, 2)) {
- slave->link = BOND_LINK_DOWN;
+ slave->new_link = BOND_LINK_DOWN;
slave_state_changed = 1;
if (slave->link_failure_count < UINT_MAX)
@@ -2674,6 +2676,11 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
if (!rtnl_trylock())
goto re_arm;
+ bond_for_each_slave(bond, slave, iter) {
+ if (slave->new_link != BOND_LINK_NOCHANGE)
+ slave->link = slave->new_link;
+ }
+
if (slave_state_changed) {
bond_slave_state_change(bond);
if (BOND_MODE(bond) == BOND_MODE_XOR)
--
2.8.2
^ permalink raw reply related
* Re: [PATCH net-next 1/8] net: ipv4: refactor __ip_route_output_key_hash
From: kbuild test robot @ 2017-05-25 2:38 UTC (permalink / raw)
To: Roopa Prabhu; +Cc: kbuild-all, davem, netdev, dsahern, nikolay
In-Reply-To: <1495649951-30417-2-git-send-email-roopa@cumulusnetworks.com>
[-- Attachment #1: Type: text/plain, Size: 6359 bytes --]
Hi David,
[auto build test ERROR on net-next/master]
url: https://github.com/0day-ci/linux/commits/Roopa-Prabhu/net-extend-RTM_GETROUTE-to-return-fib-result/20170525-053253
config: openrisc-or1ksim_defconfig (attached as .config)
compiler: or1k-linux-gcc (GCC) 5.4.0
reproduce:
wget https://raw.githubusercontent.com/01org/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
make.cross ARCH=openrisc
Note: the linux-review/Roopa-Prabhu/net-extend-RTM_GETROUTE-to-return-fib-result/20170525-053253 HEAD 083c4ee9e124d0acf29d159ced8a22cb41665a7a builds fine.
It only hurts bisectibility.
All errors (new ones prefixed by >>):
In file included from include/net/route.h:31:0,
from include/net/lwtunnel.h:8,
from include/net/ip_tunnels.h:17,
from include/net/dst_metadata.h:5,
from net/ipv4/route.c:94:
net/ipv4/route.c: In function 'ip_route_output_key_hash_rcu':
>> include/net/ip_fib.h:167:32: error: request for member 'fi' in something not a structure or union
#define FIB_RES_NH(res) ((res).fi->fib_nh[0])
^
include/net/ip_fib.h:196:28: note: in expansion of macro 'FIB_RES_NH'
#define FIB_RES_DEV(res) (FIB_RES_NH(res).nh_dev)
^
net/ipv4/route.c:2399:35: note: in expansion of macro 'FIB_RES_DEV'
dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(res)) ? :
^
net/ipv4/route.c: In function 'ip_route_output_key_hash':
net/ipv4/route.c:2430:53: error: 'mp_hash' undeclared (first use in this function)
rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
^
net/ipv4/route.c:2430:53: note: each undeclared identifier is reported only once for each function it appears in
net/ipv4/route.c:2430:47: error: passing argument 3 of 'ip_route_output_key_hash_rcu' from incompatible pointer type [-Werror=incompatible-pointer-types]
rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
^
net/ipv4/route.c:2249:16: note: expected 'const struct sk_buff *' but argument is of type 'struct fib_result *'
struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
^
cc1: some warnings being treated as errors
--
In file included from include/net/route.h:31:0,
from include/net/lwtunnel.h:8,
from include/net/ip_tunnels.h:17,
from include/net/dst_metadata.h:5,
from net//ipv4/route.c:94:
net//ipv4/route.c: In function 'ip_route_output_key_hash_rcu':
>> include/net/ip_fib.h:167:32: error: request for member 'fi' in something not a structure or union
#define FIB_RES_NH(res) ((res).fi->fib_nh[0])
^
include/net/ip_fib.h:196:28: note: in expansion of macro 'FIB_RES_NH'
#define FIB_RES_DEV(res) (FIB_RES_NH(res).nh_dev)
^
net//ipv4/route.c:2399:35: note: in expansion of macro 'FIB_RES_DEV'
dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(res)) ? :
^
net//ipv4/route.c: In function 'ip_route_output_key_hash':
net//ipv4/route.c:2430:53: error: 'mp_hash' undeclared (first use in this function)
rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
^
net//ipv4/route.c:2430:53: note: each undeclared identifier is reported only once for each function it appears in
net//ipv4/route.c:2430:47: error: passing argument 3 of 'ip_route_output_key_hash_rcu' from incompatible pointer type [-Werror=incompatible-pointer-types]
rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
^
net//ipv4/route.c:2249:16: note: expected 'const struct sk_buff *' but argument is of type 'struct fib_result *'
struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
^
cc1: some warnings being treated as errors
vim +/fi +167 include/net/ip_fib.h
5f300893f Thomas Graf 2006-11-09 151 u32 fl_mark;
246955fe4 Robert Olsson 2005-06-20 152 unsigned char fl_tos;
246955fe4 Robert Olsson 2005-06-20 153 unsigned char fl_scope;
246955fe4 Robert Olsson 2005-06-20 154 unsigned char tb_id_in;
246955fe4 Robert Olsson 2005-06-20 155
246955fe4 Robert Olsson 2005-06-20 156 unsigned char tb_id; /* Results */
246955fe4 Robert Olsson 2005-06-20 157 unsigned char prefixlen;
246955fe4 Robert Olsson 2005-06-20 158 unsigned char nh_sel;
246955fe4 Robert Olsson 2005-06-20 159 unsigned char type;
246955fe4 Robert Olsson 2005-06-20 160 unsigned char scope;
246955fe4 Robert Olsson 2005-06-20 161 int err;
246955fe4 Robert Olsson 2005-06-20 162 };
^1da177e4 Linus Torvalds 2005-04-16 163
^1da177e4 Linus Torvalds 2005-04-16 164 #ifdef CONFIG_IP_ROUTE_MULTIPATH
^1da177e4 Linus Torvalds 2005-04-16 165 #define FIB_RES_NH(res) ((res).fi->fib_nh[(res).nh_sel])
^1da177e4 Linus Torvalds 2005-04-16 166 #else /* CONFIG_IP_ROUTE_MULTIPATH */
^1da177e4 Linus Torvalds 2005-04-16 @167 #define FIB_RES_NH(res) ((res).fi->fib_nh[0])
5b9e12dbf Denis V. Lunev 2013-03-13 168 #endif /* CONFIG_IP_ROUTE_MULTIPATH */
^1da177e4 Linus Torvalds 2005-04-16 169
5b9e12dbf Denis V. Lunev 2013-03-13 170 #ifdef CONFIG_IP_MULTIPLE_TABLES
93456b6d7 Denis V. Lunev 2008-01-10 171 #define FIB_TABLE_HASHSZ 256
5b9e12dbf Denis V. Lunev 2013-03-13 172 #else
5b9e12dbf Denis V. Lunev 2013-03-13 173 #define FIB_TABLE_HASHSZ 2
5b9e12dbf Denis V. Lunev 2013-03-13 174 #endif
^1da177e4 Linus Torvalds 2005-04-16 175
:::::: The code at line 167 was first introduced by commit
:::::: 1da177e4c3f41524e886b7f1b8a0c1fc7321cac2 Linux-2.6.12-rc2
:::::: TO: Linus Torvalds <torvalds@ppc970.osdl.org>
:::::: CC: Linus Torvalds <torvalds@ppc970.osdl.org>
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 7551 bytes --]
^ permalink raw reply
* Re: [PATCH net-next 8/8] net: ipv6: RTM_GETROUTE: return matched fib result when requested
From: David Ahern @ 2017-05-25 2:35 UTC (permalink / raw)
To: Roopa Prabhu, davem; +Cc: netdev, nikolay
In-Reply-To: <1495649951-30417-9-git-send-email-roopa@cumulusnetworks.com>
Since you have to do a v2 ...
On 5/24/17 12:19 PM, Roopa Prabhu wrote:
> @@ -3622,6 +3623,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
> memset(&fl6, 0, sizeof(fl6));
> rtm = nlmsg_data(nlh);
> fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, 0);
> + fibmatch = (rtm->rtm_flags & RTM_F_FIB_MATCH) ? true : false;
this is typically done as !!(rtm->rtm_flags & RTM_F_FIB_MATCH)
>
> if (tb[RTA_SRC]) {
> if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr))
> @@ -3667,12 +3669,27 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
> if (!ipv6_addr_any(&fl6.saddr))
> flags |= RT6_LOOKUP_F_HAS_SADDR;
>
> - rt = (struct rt6_info *)ip6_route_input_lookup(net, dev, &fl6,
> - flags);
> + if (!fibmatch)
> + rt = (struct rt6_info *)ip6_route_input_lookup(net, dev,
> + &fl6,
> + flags);
> } else {
> fl6.flowi6_oif = oif;
>
> - rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl6);
> + if (!fibmatch)
> + rt = (struct rt6_info *)ip6_route_output_flags(net,
> + NULL,
> + &fl6, 0);
> + }
> +
> + if (fibmatch) {
> + rt = (struct rt6_info *)ip6_route_lookup(net, &fl6, 0);
> + if (rt->dst.error) {
> + err = rt->dst.error;
> + ip6_rt_put(rt);
> + goto errout;
> + }
> +
I'd prefer to see the typecasts go away and use container_of to go from
dst_entry to rt6_info. I realize some of this is movement of existing
code, but better to clean up as we go.
^ permalink raw reply
* [PATCH net-next 1/2] be2net: Fix UE detection logic for BE3
From: Suresh Reddy @ 2017-05-25 2:24 UTC (permalink / raw)
To: netdev; +Cc: Suresh Reddy
In-Reply-To: <1495679079-12025-1-git-send-email-suresh.reddy@broadcom.com>
On certain platforms BE3 chips may indicate spurious UEs (unrecoverable
error). Because of the UE detection logic was disabled in the driver
for BE3 chips. Because of this, even in cases of a real UE,
a failover will not occur. This patch re-enables UE detection on BE3
and if a UE is detected, reads the POST register. If the POST register,
reports either a FAT_LOG_STATE or a ARMFW_UE, then it means that a valid
UE occurred in the chip.
Signed-off-by: Suresh Reddy <suresh.reddy@broadcom.com>
---
drivers/net/ethernet/emulex/benet/be_hw.h | 3 +++
drivers/net/ethernet/emulex/benet/be_main.c | 27 +++++++++++++++++++--------
2 files changed, 22 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/emulex/benet/be_hw.h b/drivers/net/ethernet/emulex/benet/be_hw.h
index 36e4232..c967f45 100644
--- a/drivers/net/ethernet/emulex/benet/be_hw.h
+++ b/drivers/net/ethernet/emulex/benet/be_hw.h
@@ -49,6 +49,9 @@
#define POST_STAGE_BE_RESET 0x3 /* Host wants to reset chip */
#define POST_STAGE_ARMFW_RDY 0xc000 /* FW is done with POST */
#define POST_STAGE_RECOVERABLE_ERR 0xE000 /* Recoverable err detected */
+/* FW has detected a UE and is dumping FAT log data */
+#define POST_STAGE_FAT_LOG_START 0x0D00
+#define POST_STAGE_ARMFW_UE 0xF000 /*FW has asserted an UE*/
/* Lancer SLIPORT registers */
#define SLIPORT_STATUS_OFFSET 0x404
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index f3a09ab..8000551 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -3241,8 +3241,9 @@ void be_detect_error(struct be_adapter *adapter)
{
u32 ue_lo = 0, ue_hi = 0, ue_lo_mask = 0, ue_hi_mask = 0;
u32 sliport_status = 0, sliport_err1 = 0, sliport_err2 = 0;
- u32 i;
struct device *dev = &adapter->pdev->dev;
+ u16 val;
+ u32 i;
if (be_check_error(adapter, BE_ERROR_HW))
return;
@@ -3280,15 +3281,25 @@ void be_detect_error(struct be_adapter *adapter)
ue_lo = (ue_lo & ~ue_lo_mask);
ue_hi = (ue_hi & ~ue_hi_mask);
- /* On certain platforms BE hardware can indicate spurious UEs.
- * Allow HW to stop working completely in case of a real UE.
- * Hence not setting the hw_error for UE detection.
- */
-
if (ue_lo || ue_hi) {
+ /* On certain platforms BE3 hardware can indicate
+ * spurious UEs. In case of a UE in the chip,
+ * the POST register correctly reports either a
+ * FAT_LOG_START state (FW is currently dumping
+ * FAT log data) or a ARMFW_UE state. Check for the
+ * above states to ascertain if the UE is valid or not.
+ */
+ if (BE3_chip(adapter)) {
+ val = be_POST_stage_get(adapter);
+ if ((val & POST_STAGE_FAT_LOG_START)
+ != POST_STAGE_FAT_LOG_START &&
+ (val & POST_STAGE_ARMFW_UE)
+ != POST_STAGE_ARMFW_UE)
+ return;
+ }
+
dev_err(dev, "Error detected in the adapter");
- if (skyhawk_chip(adapter))
- be_set_error(adapter, BE_ERROR_UE);
+ be_set_error(adapter, BE_ERROR_UE);
for (i = 0; ue_lo; ue_lo >>= 1, i++) {
if (ue_lo & 1)
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 0/2] be2net: patch-set
From: Suresh Reddy @ 2017-05-25 2:24 UTC (permalink / raw)
To: netdev; +Cc: Suresh Reddy
In-Reply-To: <Suresh.Reddy@broadcom.com>
Hi Dave, Please consider applying these two patches to net-next
Suresh Reddy (2):
be2net: Fix UE detection logic for BE3
be2net: Update the driver version to 11.4.0.0
drivers/net/ethernet/emulex/benet/be.h | 2 +-
drivers/net/ethernet/emulex/benet/be_hw.h | 3 +++
drivers/net/ethernet/emulex/benet/be_main.c | 27 +++++++++++++++++++--------
3 files changed, 23 insertions(+), 9 deletions(-)
--
1.8.3.1
^ permalink raw reply
* [PATCH net-next 2/2] be2net: Update the driver version to 11.4.0.0
From: Suresh Reddy @ 2017-05-25 2:24 UTC (permalink / raw)
To: netdev; +Cc: Suresh Reddy
In-Reply-To: <1495679079-12025-1-git-send-email-suresh.reddy@broadcom.com>
Signed-off-by: Suresh Reddy <suresh.reddy@broadcom.com>
---
drivers/net/ethernet/emulex/benet/be.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 5056624..674cf9d 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -37,7 +37,7 @@
#include "be_hw.h"
#include "be_roce.h"
-#define DRV_VER "11.1.0.0"
+#define DRV_VER "11.4.0.0"
#define DRV_NAME "be2net"
#define BE_NAME "Emulex BladeEngine2"
#define BE3_NAME "Emulex BladeEngine3"
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next] ibmvnic: Enable TSO support
From: Thomas Falcon @ 2017-05-25 2:29 UTC (permalink / raw)
To: netdev; +Cc: Thomas Falcon, Nathan Fontenot, John Allen
Enable TSO in the ibmvnic driver. Scatter-gather is also enabled,
though there currently is no support for scatter-gather in
vNIC-compatible hardware, resulting in forced linearization
of all fragmented SKB's. Though not ideal, given the throughput
improvement gained by enabling TSO, it has been decided
that this is an acceptable tradeoff.
The feature is also enabled by a module parameter.
This parameter is necessary because TSO can not easily be
enabled or disabled in firmware without reinitializing the driver.
CC: Nathan Fontenot <nfont@linux.vnet.ibm.com>
CC: John Allen <jallen@linux.vnet.ibm.com>
Signed-off-by: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
---
drivers/net/ethernet/ibm/ibmvnic.c | 39 +++++++++++++++++++++++++++++++++++---
1 file changed, 36 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index abe2b6e..64e8d50 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -81,6 +81,11 @@
static const char ibmvnic_driver_name[] = "ibmvnic";
static const char ibmvnic_driver_string[] = "IBM System i/p Virtual NIC Driver";
+static int large_send_offload;
+module_param(large_send_offload, bool, 0644);
+MODULE_PARM_DESC(large_send_offload,
+ "Determines whether large send offload is enabled");
+
MODULE_AUTHOR("Santiago Leon <santi_leon@yahoo.com>");
MODULE_DESCRIPTION("IBM System i/p Virtual NIC Driver");
MODULE_LICENSE("GPL");
@@ -1025,6 +1030,17 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
goto out;
}
+ /* All scatter-gather SKB's will be linearized for the time being, but
+ * scatter-gather is only enabled if the user wishes to use TSO.
+ */
+ if (skb_shinfo(skb)->nr_frags && __skb_linearize(skb)) {
+ dev_kfree_skb_any(skb);
+ tx_send_failed++;
+ tx_dropped++;
+ ret = NETDEV_TX_OK;
+ goto out;
+ }
+
tx_pool = &adapter->tx_pool[queue_num];
tx_scrq = adapter->tx_scrq[queue_num];
txq = netdev_get_tx_queue(netdev, skb_get_queue_mapping(skb));
@@ -1082,6 +1098,11 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
tx_crq.v1.flags1 |= IBMVNIC_TX_CHKSUM_OFFLOAD;
hdrs += 2;
}
+ if (skb_is_gso(skb)) {
+ tx_crq.v1.flags1 |= IBMVNIC_TX_LSO;
+ tx_crq.v1.mss = cpu_to_be16(skb_shinfo(skb)->gso_size);
+ hdrs += 2;
+ }
/* determine if l2/3/4 headers are sent to firmware */
if ((*hdrs >> 7) & 1 &&
(skb->protocol == htons(ETH_P_IP) ||
@@ -2629,10 +2650,10 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter)
adapter->ip_offload_ctrl.udp_ipv4_chksum = buf->udp_ipv4_chksum;
adapter->ip_offload_ctrl.tcp_ipv6_chksum = buf->tcp_ipv6_chksum;
adapter->ip_offload_ctrl.udp_ipv6_chksum = buf->udp_ipv6_chksum;
+ adapter->ip_offload_ctrl.large_tx_ipv4 = buf->large_tx_ipv4;
+ adapter->ip_offload_ctrl.large_tx_ipv6 = buf->large_tx_ipv6;
- /* large_tx/rx disabled for now, additional features needed */
- adapter->ip_offload_ctrl.large_tx_ipv4 = 0;
- adapter->ip_offload_ctrl.large_tx_ipv6 = 0;
+ /* large_rx disabled for now, additional features needed */
adapter->ip_offload_ctrl.large_rx_ipv4 = 0;
adapter->ip_offload_ctrl.large_rx_ipv6 = 0;
@@ -2648,6 +2669,18 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter)
(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)))
adapter->netdev->features |= NETIF_F_RXCSUM;
+ if (large_send_offload) {
+ /* Scatter-gather is not currently supported by firmware.
+ * It will only be enabled to support TSO operations.
+ */
+ adapter->netdev->features = NETIF_F_SG;
+
+ if (buf->large_tx_ipv4)
+ adapter->netdev->features |= NETIF_F_TSO;
+ if (buf->large_tx_ipv6)
+ adapter->netdev->features |= NETIF_F_TSO6;
+ }
+
memset(&crq, 0, sizeof(crq));
crq.control_ip_offload.first = IBMVNIC_CRQ_CMD;
crq.control_ip_offload.cmd = CONTROL_IP_OFFLOAD;
--
1.8.3.1
^ permalink raw reply related
* Re: [PATCH net-next 7/8] net: ipv4: RTM_GETROUTE: return matched fib result when requested
From: David Ahern @ 2017-05-25 2:16 UTC (permalink / raw)
To: Roopa Prabhu, davem; +Cc: netdev, nikolay
In-Reply-To: <1495649951-30417-8-git-send-email-roopa@cumulusnetworks.com>
On 5/24/17 12:19 PM, Roopa Prabhu wrote:
> @@ -2746,8 +2748,15 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
> if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE)
> table_id = rt->rt_table_id;
>
> - err = rt_fill_info(net, dst, src, table_id, &fl4, skb,
> - NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, rt);
> + if (rtm->rtm_flags & RTM_F_FIB_MATCH)
> + err = fib_dump_info(skb, NETLINK_CB(in_skb).portid,
> + nlh->nlmsg_seq, RTM_NEWROUTE, table_id,
> + rt->rt_type, res.prefix, res.prefixlen,
> + fl4.flowi4_tos, res.fi, 0);
I like this part -- much simpler than duplicating the attributes which
is where I was headed.
^ permalink raw reply
* Re: [PATCH net-next 1/8] net: ipv4: refactor __ip_route_output_key_hash
From: kbuild test robot @ 2017-05-25 1:30 UTC (permalink / raw)
To: Roopa Prabhu; +Cc: kbuild-all, davem, netdev, dsahern, nikolay
In-Reply-To: <1495649951-30417-2-git-send-email-roopa@cumulusnetworks.com>
[-- Attachment #1: Type: text/plain, Size: 5778 bytes --]
Hi David,
[auto build test ERROR on net-next/master]
url: https://github.com/0day-ci/linux/commits/Roopa-Prabhu/net-extend-RTM_GETROUTE-to-return-fib-result/20170525-053253
config: cris-etrax-100lx_v2_defconfig (attached as .config)
compiler: cris-linux-gcc (GCC) 6.2.0
reproduce:
wget https://raw.githubusercontent.com/01org/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
make.cross ARCH=cris
Note: the linux-review/Roopa-Prabhu/net-extend-RTM_GETROUTE-to-return-fib-result/20170525-053253 HEAD 083c4ee9e124d0acf29d159ced8a22cb41665a7a builds fine.
It only hurts bisectibility.
All error/warnings (new ones prefixed by >>):
In file included from include/net/route.h:31:0,
from include/net/lwtunnel.h:8,
from include/net/ip_tunnels.h:17,
from include/net/dst_metadata.h:5,
from net/ipv4/route.c:94:
net/ipv4/route.c: In function 'ip_route_output_key_hash_rcu':
>> include/net/ip_fib.h:167:32: error: 'res' is a pointer; did you mean to use '->'?
#define FIB_RES_NH(res) ((res).fi->fib_nh[0])
^
->
>> include/net/ip_fib.h:196:28: note: in expansion of macro 'FIB_RES_NH'
#define FIB_RES_DEV(res) (FIB_RES_NH(res).nh_dev)
^~~~~~~~~~
>> net/ipv4/route.c:2399:35: note: in expansion of macro 'FIB_RES_DEV'
dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(res)) ? :
^~~~~~~~~~~
net/ipv4/route.c: In function 'ip_route_output_key_hash':
>> net/ipv4/route.c:2430:53: error: 'mp_hash' undeclared (first use in this function)
rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
^~~~~~~
net/ipv4/route.c:2430:53: note: each undeclared identifier is reported only once for each function it appears in
>> net/ipv4/route.c:2430:47: error: passing argument 3 of 'ip_route_output_key_hash_rcu' from incompatible pointer type [-Werror=incompatible-pointer-types]
rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
^
net/ipv4/route.c:2249:16: note: expected 'const struct sk_buff *' but argument is of type 'struct fib_result *'
struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
^~~~~~~~~~~~~~~~~~~~~~~~~~~~
cc1: some warnings being treated as errors
--
In file included from include/net/route.h:31:0,
from include/net/lwtunnel.h:8,
from include/net/ip_tunnels.h:17,
from include/net/dst_metadata.h:5,
from net//ipv4/route.c:94:
net//ipv4/route.c: In function 'ip_route_output_key_hash_rcu':
>> include/net/ip_fib.h:167:32: error: 'res' is a pointer; did you mean to use '->'?
#define FIB_RES_NH(res) ((res).fi->fib_nh[0])
^
->
>> include/net/ip_fib.h:196:28: note: in expansion of macro 'FIB_RES_NH'
#define FIB_RES_DEV(res) (FIB_RES_NH(res).nh_dev)
^~~~~~~~~~
net//ipv4/route.c:2399:35: note: in expansion of macro 'FIB_RES_DEV'
dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(res)) ? :
^~~~~~~~~~~
net//ipv4/route.c: In function 'ip_route_output_key_hash':
net//ipv4/route.c:2430:53: error: 'mp_hash' undeclared (first use in this function)
rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
^~~~~~~
net//ipv4/route.c:2430:53: note: each undeclared identifier is reported only once for each function it appears in
net//ipv4/route.c:2430:47: error: passing argument 3 of 'ip_route_output_key_hash_rcu' from incompatible pointer type [-Werror=incompatible-pointer-types]
rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
^
net//ipv4/route.c:2249:16: note: expected 'const struct sk_buff *' but argument is of type 'struct fib_result *'
struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
^~~~~~~~~~~~~~~~~~~~~~~~~~~~
cc1: some warnings being treated as errors
vim +/mp_hash +2430 net/ipv4/route.c
2393 fl4->saddr = res->fi->fib_prefsrc;
2394 else
2395 fl4->saddr = fl4->daddr;
2396 }
2397
2398 /* L3 master device is the loopback for that domain */
> 2399 dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(res)) ? :
2400 net->loopback_dev;
2401 fl4->flowi4_oif = dev_out->ifindex;
2402 flags |= RTCF_LOCAL;
2403 goto make_route;
2404 }
2405
2406 fib_select_path(net, res, fl4, skb);
2407
2408 dev_out = FIB_RES_DEV(*res);
2409 fl4->flowi4_oif = dev_out->ifindex;
2410
2411
2412 make_route:
2413 rth = __mkroute_output(res, fl4, orig_oif, dev_out, flags);
2414
2415 out:
2416 return rth;
2417 }
2418
2419 struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
2420 const struct sk_buff *skb)
2421 {
2422 struct fib_result res;
2423 struct rtable *rth;
2424
2425 res.tclassid = 0;
2426 res.fi = NULL;
2427 res.table = NULL;
2428
2429 rcu_read_lock();
> 2430 rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
2431 rcu_read_unlock();
2432
2433 return rth;
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 8682 bytes --]
^ permalink raw reply
* Re: Deleting a dynamic mac entry..
From: Toshiaki Makita @ 2017-05-25 1:11 UTC (permalink / raw)
To: Manohar Kumar; +Cc: netdev, bridge
In-Reply-To: <CA+N+6-xtSgQ4eDN7SBMg43WXEc=6quPNE4L1-3xjLuTMte0DSA@mail.gmail.com>
On 2017/05/25 3:05, Manohar Kumar wrote:
> Thanks, Toshiaki.
>
> What is the right way to set the default_pvid using the bridge command
> ? I tried this, which fails..
>
> root@net-3:~# ip link set dev vxlan0 name untagged type vlan id 0
> RTNETLINK answers: Operation not supported
> root@net-3:~#
>
> All the interfaces in the bridge are untagged.
# ip link set br0 down
# echo 0 > /sys/class/net/br0/bridge/default_pvid
Toshiaki Makita
^ permalink raw reply
* Re: [PATCH net-next 1/8] net: ipv4: refactor __ip_route_output_key_hash
From: David Ahern @ 2017-05-25 1:10 UTC (permalink / raw)
To: Rosen, Rami, Roopa Prabhu, davem@davemloft.net
Cc: netdev@vger.kernel.org, nikolay@cumulusnetworks.com
In-Reply-To: <9B0331B6EBBD0E4684FBFAEDA55776F93D54F8DF@HASMSX110.ger.corp.intel.com>
On 5/24/17 1:33 PM, Rosen, Rami wrote:
> Hi, Rupa /David Ahern,
>
> First, thanks for this patch set!
>
> Second, it seems to me that something might be incorrect here.
>
> You have these additions in this patch (1/8):
> ...
> +struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *flp,
> + const struct sk_buff *skb,
> + struct fib_result *res);
> ...
> +struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
> + const struct sk_buff *skb)
> +{
> + struct fib_result res;
> + struct rtable *rth;
> +
> + res.tclassid = 0;
> + res.fi = NULL;
> + res.table = NULL;
> +
> + rcu_read_lock();
> + rth = ip_route_output_key_hash_rcu(net, fl4, &res, mp_hash);
> rcu_read_unlock();
> +
> return rth;
> }
> -EXPORT_SYMBOL_GPL(__ip_route_output_key_hash);
> +EXPORT_SYMBOL_GPL(ip_route_output_key_hash);
>
>
> So the third parameter to ip_route_output_key_hash_rcu() should be skb*, and the fourth parameter should be fib_result *. However, you do not pass the skb parameter
> when calling ip_route_output_key_hash_rcu() in
> ip_route_output_key_hash() (in fact you don't use it at all), and you pass mp_hash as the fourth parameter.
Yep, it's a problem with the forward port of the first round of patches.
Roopa: in include/net/route.h, __ip_route_output_key_hash should be
removed as well.
^ permalink raw reply
* Re: [PATCH net-next 3/3] net: sysfs: Document PHY device sysfs attributes
From: Florian Fainelli @ 2017-05-25 0:03 UTC (permalink / raw)
To: Andrew Lunn; +Cc: netdev, davem
In-Reply-To: <00fd6fec-29a2-9a54-085b-95f775610d3b@gmail.com>
On 05/24/2017 04:07 PM, Florian Fainelli wrote:
> Hi Andrew,
>
> On 05/24/2017 01:10 PM, Andrew Lunn wrote:
>>> +What: /sys/class/mdio_bus/<bus>/<device>/phy_interface
>>> +Date: February 2014
>>> +KernelVersion: 3.15
>>> +Contact: netdev@vger.kernel.org
>>> +Description:
>>> + String value indicating the PHY interface, possible
>>> + values are in include/linux/phy.h function phy_modes.
>>
>> Hi Florian
>>
>> Does this suggest that these strings should be moved to
>> include/uapi/linux/phy.h?
>
> Humm, I suppose we could do that, although I am not sure ally sure what
> we would be putting in there (at least for now).
I actually prefer to put the possible values in the sysfs documentation
files instead of in a UAPI header. Will submit a v2.
--
Florian
^ permalink raw reply
* Re: [PATCH 0/2] Replace driver's usage of hard-coded device IDs to #defines
From: David Miller @ 2017-05-25 0:02 UTC (permalink / raw)
To: myron.stowe; +Cc: linux-pci, netdev, bhelgaas, saeedm, noaos, tariqt
In-Reply-To: <20170524224734.24221.33787.stgit@amt.stowe>
From: Myron Stowe <myron.stowe@redhat.com>
Date: Wed, 24 May 2017 16:47:34 -0600
> Noa Osherovich introduced a series of new Mellanox device ID definitions to
> help differentiate specific controllers that needed INTx masking quirks [1].
>
> Bjorn Helgaas followed on, using the device ID definitions Noa provided to
> replace hard-coded values within the mxl4 ID table [2].
>
> This patch continues along similar lines, adding a few additional Mellanox
> device ID definitions and converting the net/mlx5e driver's mlx5 ID table to
> use the defines so tools like 'grep' and 'cscope' can be used to help
> identify relationships with other aspects (such as INTx masking).
If you're adding pci_ids.h defines, it's only valid to do so if you
actually use the defines in more than one location.
This patch series is not doing that.
^ permalink raw reply
* Re: [PATCH] test_bpf: Add a couple of tests for BPF_JSGE.
From: Daniel Borkmann @ 2017-05-24 23:52 UTC (permalink / raw)
To: David Daney, Alexei Starovoitov, netdev, linux-kernel
In-Reply-To: <20170524233549.18388-1-david.daney@cavium.com>
On 05/25/2017 01:35 AM, David Daney wrote:
> Some JITs can optimize comparisons with zero. Add a couple of
> BPF_JSGE tests against immediate zero.
>
> Signed-off-by: David Daney <david.daney@cavium.com>
Thanks for the tests!
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
^ permalink raw reply
* [PATCH] test_bpf: Add a couple of tests for BPF_JSGE.
From: David Daney @ 2017-05-24 23:35 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, netdev, linux-kernel; +Cc: David Daney
Some JITs can optimize comparisons with zero. Add a couple of
BPF_JSGE tests against immediate zero.
Signed-off-by: David Daney <david.daney@cavium.com>
---
lib/test_bpf.c | 38 ++++++++++++++++++++++++++++++++++++++
1 file changed, 38 insertions(+)
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 889bc31..be88cba 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -4504,6 +4504,44 @@ static struct bpf_test tests[] = {
{ },
{ { 0, 1 } },
},
+ {
+ "JMP_JSGE_K: Signed jump: value walk 1",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_LD_IMM64(R1, -3),
+ BPF_JMP_IMM(BPF_JSGE, R1, 0, 6),
+ BPF_ALU64_IMM(BPF_ADD, R1, 1),
+ BPF_JMP_IMM(BPF_JSGE, R1, 0, 4),
+ BPF_ALU64_IMM(BPF_ADD, R1, 1),
+ BPF_JMP_IMM(BPF_JSGE, R1, 0, 2),
+ BPF_ALU64_IMM(BPF_ADD, R1, 1),
+ BPF_JMP_IMM(BPF_JSGE, R1, 0, 1),
+ BPF_EXIT_INSN(), /* bad exit */
+ BPF_ALU32_IMM(BPF_MOV, R0, 1), /* good exit */
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
+ {
+ "JMP_JSGE_K: Signed jump: value walk 2",
+ .u.insns_int = {
+ BPF_ALU32_IMM(BPF_MOV, R0, 0),
+ BPF_LD_IMM64(R1, -3),
+ BPF_JMP_IMM(BPF_JSGE, R1, 0, 4),
+ BPF_ALU64_IMM(BPF_ADD, R1, 2),
+ BPF_JMP_IMM(BPF_JSGE, R1, 0, 2),
+ BPF_ALU64_IMM(BPF_ADD, R1, 2),
+ BPF_JMP_IMM(BPF_JSGE, R1, 0, 1),
+ BPF_EXIT_INSN(), /* bad exit */
+ BPF_ALU32_IMM(BPF_MOV, R0, 1), /* good exit */
+ BPF_EXIT_INSN(),
+ },
+ INTERNAL,
+ { },
+ { { 0, 1 } },
+ },
/* BPF_JMP | BPF_JGT | BPF_K */
{
"JMP_JGT_K: if (3 > 2) return 1",
--
2.9.4
^ permalink raw reply related
* linux-next: manual merge of the net-next tree with the net tree
From: Stephen Rothwell @ 2017-05-24 23:34 UTC (permalink / raw)
To: David Miller, Networking
Cc: Linux-Next Mailing List, Linux Kernel Mailing List, Andrew Lunn
Hi all,
Today's linux-next merge of the net-next tree got a conflict in:
drivers/net/phy/marvell.c
between commit:
f2899788353c ("net: phy: marvell: Limit errata to 88m1101")
from the net tree and commit:
0c3439bc7773 ("net: phy: Marvell: checkpatch - Comments")
from the net-next tree.
I fixed it up (I just used the former version) and can carry the fix as
necessary. This is now fixed as far as linux-next is concerned, but any
non trivial conflicts should be mentioned to your upstream maintainer
when your tree is submitted for merging. You may also want to consider
cooperating with the maintainer of the conflicting tree to minimise any
particularly complex conflicts.
--
Cheers,
Stephen Rothwell
^ permalink raw reply
* Re: [PATCH net-next 3/3] net: sysfs: Document PHY device sysfs attributes
From: Florian Fainelli @ 2017-05-24 23:07 UTC (permalink / raw)
To: Andrew Lunn; +Cc: netdev, davem
In-Reply-To: <20170524201018.GH1788@lunn.ch>
Hi Andrew,
On 05/24/2017 01:10 PM, Andrew Lunn wrote:
>> +What: /sys/class/mdio_bus/<bus>/<device>/phy_interface
>> +Date: February 2014
>> +KernelVersion: 3.15
>> +Contact: netdev@vger.kernel.org
>> +Description:
>> + String value indicating the PHY interface, possible
>> + values are in include/linux/phy.h function phy_modes.
>
> Hi Florian
>
> Does this suggest that these strings should be moved to
> include/uapi/linux/phy.h?
Humm, I suppose we could do that, although I am not sure ally sure what
we would be putting in there (at least for now).
--
Florian
^ permalink raw reply
* [PATCH net v2 5/5] bpf: add various verifier test cases
From: Daniel Borkmann @ 2017-05-24 23:05 UTC (permalink / raw)
To: davem; +Cc: alexei.starovoitov, netdev, Daniel Borkmann
In-Reply-To: <cover.1495665905.git.daniel@iogearbox.net>
This patch adds various verifier test cases:
1) A test case for the pruning issue when tracking alignment
is used.
2) Various PTR_TO_MAP_VALUE_OR_NULL tests to make sure pointer
arithmetic turns such register into UNKNOWN_VALUE type.
3) Test cases for the special treatment of LD_ABS/LD_IND to
make sure verifier doesn't break calling convention here.
Latter is needed, since f.e. arm64 JIT uses r1 - r5 for
storing temporary data, so they really must be marked as
NOT_INIT.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
include/linux/filter.h | 10 ++
tools/include/linux/filter.h | 10 ++
tools/testing/selftests/bpf/test_verifier.c | 239 +++++++++++++++++++++++++++-
3 files changed, 255 insertions(+), 4 deletions(-)
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 56197f8..62d948f 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -272,6 +272,16 @@
.off = OFF, \
.imm = IMM })
+/* Unconditional jumps, goto pc + off16 */
+
+#define BPF_JMP_A(OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_JMP | BPF_JA, \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = OFF, \
+ .imm = 0 })
+
/* Function call */
#define BPF_EMIT_CALL(FUNC) \
diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h
index 390d7c9..4ce25d4 100644
--- a/tools/include/linux/filter.h
+++ b/tools/include/linux/filter.h
@@ -208,6 +208,16 @@
.off = OFF, \
.imm = IMM })
+/* Unconditional jumps, goto pc + off16 */
+
+#define BPF_JMP_A(OFF) \
+ ((struct bpf_insn) { \
+ .code = BPF_JMP | BPF_JA, \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = OFF, \
+ .imm = 0 })
+
/* Function call */
#define BPF_EMIT_CALL(FUNC) \
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 3773562..cabb19b 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -49,6 +49,7 @@
#define MAX_NR_MAPS 4
#define F_NEEDS_EFFICIENT_UNALIGNED_ACCESS (1 << 0)
+#define F_LOAD_WITH_STRICT_ALIGNMENT (1 << 1)
struct bpf_test {
const char *descr;
@@ -2615,6 +2616,30 @@ struct test_val {
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
},
{
+ "direct packet access: test17 (pruning, alignment)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct __sk_buff, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct __sk_buff, data_end)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+ offsetof(struct __sk_buff, mark)),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 14),
+ BPF_JMP_IMM(BPF_JGT, BPF_REG_7, 1, 4),
+ BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+ BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, -4),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 1),
+ BPF_JMP_A(-6),
+ },
+ .errstr = "misaligned packet access off 2+15+-4 size 4",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .flags = F_LOAD_WITH_STRICT_ALIGNMENT,
+ },
+ {
"helper access to packet: test1, valid packet_ptr range",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
@@ -3341,6 +3366,70 @@ struct test_val {
.prog_type = BPF_PROG_TYPE_SCHED_CLS
},
{
+ "alu ops on ptr_to_map_value_or_null, 1",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_1, 10),
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 2),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map1 = { 4 },
+ .errstr = "R4 invalid mem access",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS
+ },
+ {
+ "alu ops on ptr_to_map_value_or_null, 2",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_1, 10),
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_4, -1),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map1 = { 4 },
+ .errstr = "R4 invalid mem access",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS
+ },
+ {
+ "alu ops on ptr_to_map_value_or_null, 3",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_1, 10),
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_4, 1),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_ST_MEM(BPF_DW, BPF_REG_4, 0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map1 = { 4 },
+ .errstr = "R4 invalid mem access",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS
+ },
+ {
"invalid memory access with multiple map_lookup_elem calls",
.insns = {
BPF_MOV64_IMM(BPF_REG_1, 10),
@@ -4937,7 +5026,149 @@ struct test_val {
.fixup_map_in_map = { 3 },
.errstr = "R1 type=map_value_or_null expected=map_ptr",
.result = REJECT,
- }
+ },
+ {
+ "ld_abs: check calling conv, r1",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_1, 0),
+ BPF_LD_ABS(BPF_W, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R1 !read_ok",
+ .result = REJECT,
+ },
+ {
+ "ld_abs: check calling conv, r2",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_2, 0),
+ BPF_LD_ABS(BPF_W, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R2 !read_ok",
+ .result = REJECT,
+ },
+ {
+ "ld_abs: check calling conv, r3",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+ BPF_LD_ABS(BPF_W, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_3),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R3 !read_ok",
+ .result = REJECT,
+ },
+ {
+ "ld_abs: check calling conv, r4",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_4, 0),
+ BPF_LD_ABS(BPF_W, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_4),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R4 !read_ok",
+ .result = REJECT,
+ },
+ {
+ "ld_abs: check calling conv, r5",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_5, 0),
+ BPF_LD_ABS(BPF_W, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_5),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R5 !read_ok",
+ .result = REJECT,
+ },
+ {
+ "ld_abs: check calling conv, r7",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_7, 0),
+ BPF_LD_ABS(BPF_W, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ },
+ {
+ "ld_ind: check calling conv, r1",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_1, 1),
+ BPF_LD_IND(BPF_W, BPF_REG_1, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R1 !read_ok",
+ .result = REJECT,
+ },
+ {
+ "ld_ind: check calling conv, r2",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_2, 1),
+ BPF_LD_IND(BPF_W, BPF_REG_2, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R2 !read_ok",
+ .result = REJECT,
+ },
+ {
+ "ld_ind: check calling conv, r3",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_3, 1),
+ BPF_LD_IND(BPF_W, BPF_REG_3, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_3),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R3 !read_ok",
+ .result = REJECT,
+ },
+ {
+ "ld_ind: check calling conv, r4",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_4, 1),
+ BPF_LD_IND(BPF_W, BPF_REG_4, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_4),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R4 !read_ok",
+ .result = REJECT,
+ },
+ {
+ "ld_ind: check calling conv, r5",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_5, 1),
+ BPF_LD_IND(BPF_W, BPF_REG_5, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_5),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R5 !read_ok",
+ .result = REJECT,
+ },
+ {
+ "ld_ind: check calling conv, r7",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_7, 1),
+ BPF_LD_IND(BPF_W, BPF_REG_7, -0x200000),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ },
};
static int probe_filter_length(const struct bpf_insn *fp)
@@ -5059,9 +5290,9 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
do_test_fixup(test, prog, map_fds);
- fd_prog = bpf_load_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
- prog, prog_len, "GPL", 0, bpf_vlog,
- sizeof(bpf_vlog));
+ fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
+ prog, prog_len, test->flags & F_LOAD_WITH_STRICT_ALIGNMENT,
+ "GPL", 0, bpf_vlog, sizeof(bpf_vlog));
expected_ret = unpriv && test->result_unpriv != UNDEF ?
test->result_unpriv : test->result;
--
1.9.3
^ permalink raw reply related
* [PATCH net v2 4/5] bpf: fix wrong exposure of map_flags into fdinfo for lpm
From: Daniel Borkmann @ 2017-05-24 23:05 UTC (permalink / raw)
To: davem; +Cc: alexei.starovoitov, netdev, Daniel Borkmann
In-Reply-To: <cover.1495665905.git.daniel@iogearbox.net>
trie_alloc() always needs to have BPF_F_NO_PREALLOC passed in via
attr->map_flags, since it does not support preallocation yet. We
check the flag, but we never copy the flag into trie->map.map_flags,
which is later on exposed into fdinfo and used by loaders such as
iproute2. Latter uses this in bpf_map_selfcheck_pinned() to test
whether a pinned map has the same spec as the one from the BPF obj
file and if not, bails out, which is currently the case for lpm
since it exposes always 0 as flags.
Also copy over flags in array_map_alloc() and stack_map_alloc().
They always have to be 0 right now, but we should make sure to not
miss to copy them over at a later point in time when we add actual
flags for them to use.
Fixes: b95a5c4db09b ("bpf: add a longest prefix match trie map implementation")
Reported-by: Jarno Rajahalme <jarno@covalent.io>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
kernel/bpf/arraymap.c | 1 +
kernel/bpf/lpm_trie.c | 1 +
kernel/bpf/stackmap.c | 1 +
3 files changed, 3 insertions(+)
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 5e00b23..172dc8e 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -86,6 +86,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
array->map.key_size = attr->key_size;
array->map.value_size = attr->value_size;
array->map.max_entries = attr->max_entries;
+ array->map.map_flags = attr->map_flags;
array->elem_size = elem_size;
if (!percpu)
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 39cfafd..b09185f 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -432,6 +432,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr)
trie->map.key_size = attr->key_size;
trie->map.value_size = attr->value_size;
trie->map.max_entries = attr->max_entries;
+ trie->map.map_flags = attr->map_flags;
trie->data_size = attr->key_size -
offsetof(struct bpf_lpm_trie_key, data);
trie->max_prefixlen = trie->data_size * 8;
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index 4dfd6f2..31147d7 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -88,6 +88,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
smap->map.key_size = attr->key_size;
smap->map.value_size = value_size;
smap->map.max_entries = attr->max_entries;
+ smap->map.map_flags = attr->map_flags;
smap->n_buckets = n_buckets;
smap->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
--
1.9.3
^ permalink raw reply related
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