summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
Diffstat (limited to 'net')
-rw-r--r--net/core/dev.c40
-rw-r--r--net/core/filter.c42
-rw-r--r--net/core/net_namespace.c1
-rw-r--r--net/core/rtnetlink.c107
-rw-r--r--net/dsa/dsa2.c313
-rw-r--r--net/dsa/slave.c2
-rw-r--r--net/ipv4/tcp.c1
-rw-r--r--net/ipv4/tcp_input.c7
-rw-r--r--net/ipv4/tcp_minisocks.c4
-rw-r--r--net/ipv4/tcp_output.c1
-rw-r--r--net/ipv4/tcp_recovery.c48
-rw-r--r--net/ipv4/tcp_timer.c31
-rw-r--r--net/openvswitch/datapath.c47
-rw-r--r--net/openvswitch/datapath.h4
-rw-r--r--net/openvswitch/dp_notify.c4
-rw-r--r--net/sched/cls_bpf.c10
16 files changed, 404 insertions, 258 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index 1423cf4d695c..30b5fe32c525 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4545,7 +4545,7 @@ static int __netif_receive_skb(struct sk_buff *skb)
return ret;
}
-static int generic_xdp_install(struct net_device *dev, struct netdev_xdp *xdp)
+static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
{
struct bpf_prog *old = rtnl_dereference(dev->xdp_prog);
struct bpf_prog *new = xdp->prog;
@@ -7090,26 +7090,26 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down)
}
EXPORT_SYMBOL(dev_change_proto_down);
-u8 __dev_xdp_attached(struct net_device *dev, xdp_op_t xdp_op, u32 *prog_id)
+u8 __dev_xdp_attached(struct net_device *dev, bpf_op_t bpf_op, u32 *prog_id)
{
- struct netdev_xdp xdp;
+ struct netdev_bpf xdp;
memset(&xdp, 0, sizeof(xdp));
xdp.command = XDP_QUERY_PROG;
/* Query must always succeed. */
- WARN_ON(xdp_op(dev, &xdp) < 0);
+ WARN_ON(bpf_op(dev, &xdp) < 0);
if (prog_id)
*prog_id = xdp.prog_id;
return xdp.prog_attached;
}
-static int dev_xdp_install(struct net_device *dev, xdp_op_t xdp_op,
+static int dev_xdp_install(struct net_device *dev, bpf_op_t bpf_op,
struct netlink_ext_ack *extack, u32 flags,
struct bpf_prog *prog)
{
- struct netdev_xdp xdp;
+ struct netdev_bpf xdp;
memset(&xdp, 0, sizeof(xdp));
if (flags & XDP_FLAGS_HW_MODE)
@@ -7120,7 +7120,7 @@ static int dev_xdp_install(struct net_device *dev, xdp_op_t xdp_op,
xdp.flags = flags;
xdp.prog = prog;
- return xdp_op(dev, &xdp);
+ return bpf_op(dev, &xdp);
}
/**
@@ -7137,32 +7137,36 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
{
const struct net_device_ops *ops = dev->netdev_ops;
struct bpf_prog *prog = NULL;
- xdp_op_t xdp_op, xdp_chk;
+ bpf_op_t bpf_op, bpf_chk;
int err;
ASSERT_RTNL();
- xdp_op = xdp_chk = ops->ndo_xdp;
- if (!xdp_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE)))
+ bpf_op = bpf_chk = ops->ndo_bpf;
+ if (!bpf_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE)))
return -EOPNOTSUPP;
- if (!xdp_op || (flags & XDP_FLAGS_SKB_MODE))
- xdp_op = generic_xdp_install;
- if (xdp_op == xdp_chk)
- xdp_chk = generic_xdp_install;
+ if (!bpf_op || (flags & XDP_FLAGS_SKB_MODE))
+ bpf_op = generic_xdp_install;
+ if (bpf_op == bpf_chk)
+ bpf_chk = generic_xdp_install;
if (fd >= 0) {
- if (xdp_chk && __dev_xdp_attached(dev, xdp_chk, NULL))
+ if (bpf_chk && __dev_xdp_attached(dev, bpf_chk, NULL))
return -EEXIST;
if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) &&
- __dev_xdp_attached(dev, xdp_op, NULL))
+ __dev_xdp_attached(dev, bpf_op, NULL))
return -EBUSY;
- prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP);
+ if (bpf_op == ops->ndo_bpf)
+ prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP,
+ dev);
+ else
+ prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_XDP);
if (IS_ERR(prog))
return PTR_ERR(prog);
}
- err = dev_xdp_install(dev, xdp_op, extack, flags, prog);
+ err = dev_xdp_install(dev, bpf_op, extack, flags, prog);
if (err < 0 && prog)
bpf_prog_put(prog);
diff --git a/net/core/filter.c b/net/core/filter.c
index a0112168d6f9..1afa17935954 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3777,25 +3777,6 @@ static bool tc_cls_act_is_valid_access(int off, int size,
return bpf_skb_is_valid_access(off, size, type, info);
}
-static bool
-tc_cls_act_is_valid_access_analyzer(int off, int size,
- enum bpf_access_type type,
- struct bpf_insn_access_aux *info)
-{
- switch (off) {
- case offsetof(struct sk_buff, len):
- return true;
- case offsetof(struct sk_buff, data):
- info->reg_type = PTR_TO_PACKET;
- return true;
- case offsetof(struct sk_buff, cb) +
- offsetof(struct bpf_skb_data_end, data_end):
- info->reg_type = PTR_TO_PACKET_END;
- return true;
- }
- return false;
-}
-
static bool __is_valid_xdp_access(int off, int size)
{
if (off < 0 || off >= sizeof(struct xdp_md))
@@ -3830,21 +3811,6 @@ static bool xdp_is_valid_access(int off, int size,
return __is_valid_xdp_access(off, size);
}
-static bool xdp_is_valid_access_analyzer(int off, int size,
- enum bpf_access_type type,
- struct bpf_insn_access_aux *info)
-{
- switch (off) {
- case offsetof(struct xdp_buff, data):
- info->reg_type = PTR_TO_PACKET;
- return true;
- case offsetof(struct xdp_buff, data_end):
- info->reg_type = PTR_TO_PACKET_END;
- return true;
- }
- return false;
-}
-
void bpf_warn_invalid_xdp_action(u32 act)
{
const u32 act_max = XDP_REDIRECT;
@@ -4516,10 +4482,6 @@ const struct bpf_verifier_ops tc_cls_act_verifier_ops = {
.gen_prologue = tc_cls_act_prologue,
};
-const struct bpf_verifier_ops tc_cls_act_analyzer_ops = {
- .is_valid_access = tc_cls_act_is_valid_access_analyzer,
-};
-
const struct bpf_prog_ops tc_cls_act_prog_ops = {
.test_run = bpf_prog_test_run_skb,
};
@@ -4530,10 +4492,6 @@ const struct bpf_verifier_ops xdp_verifier_ops = {
.convert_ctx_access = xdp_convert_ctx_access,
};
-const struct bpf_verifier_ops xdp_analyzer_ops = {
- .is_valid_access = xdp_is_valid_access_analyzer,
-};
-
const struct bpf_prog_ops xdp_prog_ops = {
.test_run = bpf_prog_test_run_xdp,
};
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 6cfdc7c84c48..b797832565d3 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -234,6 +234,7 @@ int peernet2id_alloc(struct net *net, struct net *peer)
rtnl_net_notifyid(net, RTM_NEWNSID, id);
return id;
}
+EXPORT_SYMBOL_GPL(peernet2id_alloc);
/* This function returns, if assigned, the id of a peer netns. */
int peernet2id(struct net *net, struct net *peer)
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index de24d394c69e..dc5ad84ac096 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -921,7 +921,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
+ nla_total_size(4) /* IFLA_EVENT */
+ nla_total_size(4) /* IFLA_NEW_NETNSID */
+ nla_total_size(1); /* IFLA_PROTO_DOWN */
-
+ + nla_total_size(4) /* IFLA_IF_NETNSID */
+ + 0;
}
static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
@@ -1269,10 +1270,10 @@ static u8 rtnl_xdp_attached_mode(struct net_device *dev, u32 *prog_id)
*prog_id = generic_xdp_prog->aux->id;
return XDP_ATTACHED_SKB;
}
- if (!ops->ndo_xdp)
+ if (!ops->ndo_bpf)
return XDP_ATTACHED_NONE;
- return __dev_xdp_attached(dev, ops->ndo_xdp, prog_id);
+ return __dev_xdp_attached(dev, ops->ndo_bpf, prog_id);
}
static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
@@ -1370,13 +1371,14 @@ static noinline_for_stack int nla_put_ifalias(struct sk_buff *skb,
}
static int rtnl_fill_link_netnsid(struct sk_buff *skb,
- const struct net_device *dev)
+ const struct net_device *dev,
+ struct net *src_net)
{
if (dev->rtnl_link_ops && dev->rtnl_link_ops->get_link_net) {
struct net *link_net = dev->rtnl_link_ops->get_link_net(dev);
if (!net_eq(dev_net(dev), link_net)) {
- int id = peernet2id_alloc(dev_net(dev), link_net);
+ int id = peernet2id_alloc(src_net, link_net);
if (nla_put_s32(skb, IFLA_LINK_NETNSID, id))
return -EMSGSIZE;
@@ -1427,10 +1429,11 @@ static int rtnl_fill_link_af(struct sk_buff *skb,
return 0;
}
-static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
+static int rtnl_fill_ifinfo(struct sk_buff *skb,
+ struct net_device *dev, struct net *src_net,
int type, u32 pid, u32 seq, u32 change,
unsigned int flags, u32 ext_filter_mask,
- u32 event, int *new_nsid)
+ u32 event, int *new_nsid, int tgt_netnsid)
{
struct ifinfomsg *ifm;
struct nlmsghdr *nlh;
@@ -1448,6 +1451,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
ifm->ifi_flags = dev_get_flags(dev);
ifm->ifi_change = change;
+ if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_IF_NETNSID, tgt_netnsid))
+ goto nla_put_failure;
+
if (nla_put_string(skb, IFLA_IFNAME, dev->name) ||
nla_put_u32(skb, IFLA_TXQLEN, dev->tx_queue_len) ||
nla_put_u8(skb, IFLA_OPERSTATE,
@@ -1513,7 +1519,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
goto nla_put_failure;
}
- if (rtnl_fill_link_netnsid(skb, dev))
+ if (rtnl_fill_link_netnsid(skb, dev, src_net))
goto nla_put_failure;
if (new_nsid &&
@@ -1571,6 +1577,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_XDP] = { .type = NLA_NESTED },
[IFLA_EVENT] = { .type = NLA_U32 },
[IFLA_GROUP] = { .type = NLA_U32 },
+ [IFLA_IF_NETNSID] = { .type = NLA_S32 },
};
static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -1674,9 +1681,28 @@ static bool link_dump_filtered(struct net_device *dev,
return false;
}
+static struct net *get_target_net(struct sk_buff *skb, int netnsid)
+{
+ struct net *net;
+
+ net = get_net_ns_by_id(sock_net(skb->sk), netnsid);
+ if (!net)
+ return ERR_PTR(-EINVAL);
+
+ /* For now, the caller is required to have CAP_NET_ADMIN in
+ * the user namespace owning the target net ns.
+ */
+ if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) {
+ put_net(net);
+ return ERR_PTR(-EACCES);
+ }
+ return net;
+}
+
static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
+ struct net *tgt_net = net;
int h, s_h;
int idx = 0, s_idx;
struct net_device *dev;
@@ -1686,6 +1712,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
const struct rtnl_link_ops *kind_ops = NULL;
unsigned int flags = NLM_F_MULTI;
int master_idx = 0;
+ int netnsid = -1;
int err;
int hdrlen;
@@ -1704,6 +1731,15 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX,
ifla_policy, NULL) >= 0) {
+ if (tb[IFLA_IF_NETNSID]) {
+ netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]);
+ tgt_net = get_target_net(skb, netnsid);
+ if (IS_ERR(tgt_net)) {
+ tgt_net = net;
+ netnsid = -1;
+ }
+ }
+
if (tb[IFLA_EXT_MASK])
ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
@@ -1719,17 +1755,19 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
idx = 0;
- head = &net->dev_index_head[h];
+ head = &tgt_net->dev_index_head[h];
hlist_for_each_entry(dev, head, index_hlist) {
if (link_dump_filtered(dev, master_idx, kind_ops))
goto cont;
if (idx < s_idx)
goto cont;
- err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK,
+ err = rtnl_fill_ifinfo(skb, dev, net,
+ RTM_NEWLINK,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, 0,
flags,
- ext_filter_mask, 0, NULL);
+ ext_filter_mask, 0, NULL,
+ netnsid);
if (err < 0) {
if (likely(skb->len))
@@ -1748,6 +1786,8 @@ out_err:
cb->args[0] = h;
cb->seq = net->dev_base_seq;
nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+ if (netnsid >= 0)
+ put_net(tgt_net);
return err;
}
@@ -2360,6 +2400,9 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
if (err < 0)
goto errout;
+ if (tb[IFLA_IF_NETNSID])
+ return -EOPNOTSUPP;
+
if (tb[IFLA_IFNAME])
nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
else
@@ -2454,6 +2497,9 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
if (err < 0)
return err;
+ if (tb[IFLA_IF_NETNSID])
+ return -EOPNOTSUPP;
+
if (tb[IFLA_IFNAME])
nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
@@ -2585,6 +2631,9 @@ replay:
if (err < 0)
return err;
+ if (tb[IFLA_IF_NETNSID])
+ return -EOPNOTSUPP;
+
if (tb[IFLA_IFNAME])
nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
else
@@ -2818,11 +2867,13 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
+ struct net *tgt_net = net;
struct ifinfomsg *ifm;
char ifname[IFNAMSIZ];
struct nlattr *tb[IFLA_MAX+1];
struct net_device *dev = NULL;
struct sk_buff *nskb;
+ int netnsid = -1;
int err;
u32 ext_filter_mask = 0;
@@ -2830,35 +2881,50 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
if (err < 0)
return err;
+ if (tb[IFLA_IF_NETNSID]) {
+ netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]);
+ tgt_net = get_target_net(skb, netnsid);
+ if (IS_ERR(tgt_net))
+ return PTR_ERR(tgt_net);
+ }
+
if (tb[IFLA_IFNAME])
nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
if (tb[IFLA_EXT_MASK])
ext_filter_mask = nla_get_u32(tb[IFLA_EXT_MASK]);
+ err = -EINVAL;
ifm = nlmsg_data(nlh);
if (ifm->ifi_index > 0)
- dev = __dev_get_by_index(net, ifm->ifi_index);
+ dev = __dev_get_by_index(tgt_net, ifm->ifi_index);
else if (tb[IFLA_IFNAME])
- dev = __dev_get_by_name(net, ifname);
+ dev = __dev_get_by_name(tgt_net, ifname);
else
- return -EINVAL;
+ goto out;
+ err = -ENODEV;
if (dev == NULL)
- return -ENODEV;
+ goto out;
+ err = -ENOBUFS;
nskb = nlmsg_new(if_nlmsg_size(dev, ext_filter_mask), GFP_KERNEL);
if (nskb == NULL)
- return -ENOBUFS;
+ goto out;
- err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).portid,
- nlh->nlmsg_seq, 0, 0, ext_filter_mask, 0, NULL);
+ err = rtnl_fill_ifinfo(nskb, dev, net,
+ RTM_NEWLINK, NETLINK_CB(skb).portid,
+ nlh->nlmsg_seq, 0, 0, ext_filter_mask,
+ 0, NULL, netnsid);
if (err < 0) {
/* -EMSGSIZE implies BUG in if_nlmsg_size */
WARN_ON(err == -EMSGSIZE);
kfree_skb(nskb);
} else
err = rtnl_unicast(nskb, net, NETLINK_CB(skb).portid);
+out:
+ if (netnsid >= 0)
+ put_net(tgt_net);
return err;
}
@@ -2948,8 +3014,9 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
if (skb == NULL)
goto errout;
- err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0, 0, event,
- new_nsid);
+ err = rtnl_fill_ifinfo(skb, dev, dev_net(dev),
+ type, 0, 0, change, 0, 0, event,
+ new_nsid, -1);
if (err < 0) {
/* -EMSGSIZE implies BUG in if_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index 797d1156b4e6..283104e5ca6a 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -21,65 +21,77 @@
#include "dsa_priv.h"
-static LIST_HEAD(dsa_switch_trees);
+static LIST_HEAD(dsa_tree_list);
static DEFINE_MUTEX(dsa2_mutex);
static const struct devlink_ops dsa_devlink_ops = {
};
-static struct dsa_switch_tree *dsa_get_dst(u32 tree)
+static struct dsa_switch_tree *dsa_tree_find(int index)
{
struct dsa_switch_tree *dst;
- list_for_each_entry(dst, &dsa_switch_trees, list)
- if (dst->tree == tree) {
- kref_get(&dst->refcount);
+ list_for_each_entry(dst, &dsa_tree_list, list)
+ if (dst->index == index)
return dst;
- }
+
return NULL;
}
-static void dsa_free_dst(struct kref *ref)
+static struct dsa_switch_tree *dsa_tree_alloc(int index)
{
- struct dsa_switch_tree *dst = container_of(ref, struct dsa_switch_tree,
- refcount);
+ struct dsa_switch_tree *dst;
- list_del(&dst->list);
- kfree(dst);
+ dst = kzalloc(sizeof(*dst), GFP_KERNEL);
+ if (!dst)
+ return NULL;
+
+ dst->index = index;
+
+ INIT_LIST_HEAD(&dst->list);
+ list_add_tail(&dsa_tree_list, &dst->list);
+
+ /* Initialize the reference counter to the number of switches, not 1 */
+ kref_init(&dst->refcount);
+ refcount_set(&dst->refcount.refcount, 0);
+
+ return dst;
}
-static void dsa_put_dst(struct dsa_switch_tree *dst)
+static void dsa_tree_free(struct dsa_switch_tree *dst)
{
- kref_put(&dst->refcount, dsa_free_dst);
+ list_del(&dst->list);
+ kfree(dst);
}
-static struct dsa_switch_tree *dsa_add_dst(u32 tree)
+static struct dsa_switch_tree *dsa_tree_touch(int index)
{
struct dsa_switch_tree *dst;
- dst = kzalloc(sizeof(*dst), GFP_KERNEL);
+ dst = dsa_tree_find(index);
if (!dst)
- return NULL;
- dst->tree = tree;
- INIT_LIST_HEAD(&dst->list);
- list_add_tail(&dsa_switch_trees, &dst->list);
- kref_init(&dst->refcount);
+ dst = dsa_tree_alloc(index);
return dst;
}
-static void dsa_dst_add_ds(struct dsa_switch_tree *dst,
- struct dsa_switch *ds, u32 index)
+static void dsa_tree_get(struct dsa_switch_tree *dst)
{
kref_get(&dst->refcount);
- dst->ds[index] = ds;
}
-static void dsa_dst_del_ds(struct dsa_switch_tree *dst,
- struct dsa_switch *ds, u32 index)
+static void dsa_tree_release(struct kref *ref)
{
- dst->ds[index] = NULL;
- kref_put(&dst->refcount, dsa_free_dst);
+ struct dsa_switch_tree *dst;
+
+ dst = container_of(ref, struct dsa_switch_tree, refcount);
+
+ dsa_tree_free(dst);
+}
+
+static void dsa_tree_put(struct dsa_switch_tree *dst)
+{
+ kref_put(&dst->refcount, dsa_tree_release);
}
/* For platform data configurations, we need to have a valid name argument to
@@ -454,20 +466,56 @@ static void dsa_dst_unapply(struct dsa_switch_tree *dst)
dst->cpu_dp = NULL;
- pr_info("DSA: tree %d unapplied\n", dst->tree);
+ pr_info("DSA: tree %d unapplied\n", dst->index);
dst->applied = false;
}
-static int dsa_cpu_parse(struct dsa_port *port, u32 index,
- struct dsa_switch_tree *dst,
- struct dsa_switch *ds)
+static void dsa_tree_remove_switch(struct dsa_switch_tree *dst,
+ unsigned int index)
{
+ dst->ds[index] = NULL;
+ dsa_tree_put(dst);
+}
+
+static int dsa_tree_add_switch(struct dsa_switch_tree *dst,
+ struct dsa_switch *ds)
+{
+ unsigned int index = ds->index;
+
+ if (dst->ds[index])
+ return -EBUSY;
+
+ dsa_tree_get(dst);
+ dst->ds[index] = ds;
+
+ return 0;
+}
+
+static int dsa_port_parse_user(struct dsa_port *dp, const char *name)
+{
+ if (!name)
+ name = "eth%d";
+
+ dp->type = DSA_PORT_TYPE_USER;
+ dp->name = name;
+
+ return 0;
+}
+
+static int dsa_port_parse_dsa(struct dsa_port *dp)
+{
+ dp->type = DSA_PORT_TYPE_DSA;
+
+ return 0;
+}
+
+static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master)
+{
+ struct dsa_switch *ds = dp->ds;
+ struct dsa_switch_tree *dst = ds->dst;
const struct dsa_device_ops *tag_ops;
enum dsa_tag_protocol tag_protocol;
- if (!dst->cpu_dp)
- dst->cpu_dp = port;
-
tag_protocol = ds->ops->get_tag_protocol(ds);
tag_ops = dsa_resolve_tag_protocol(tag_protocol);
if (IS_ERR(tag_ops)) {
@@ -475,11 +523,21 @@ static int dsa_cpu_parse(struct dsa_port *port, u32 index,
return PTR_ERR(tag_ops);
}
- dst->cpu_dp->tag_ops = tag_ops;
+ dp->type = DSA_PORT_TYPE_CPU;
+ dp->rcv = tag_ops->rcv;
+ dp->tag_ops = tag_ops;
+ dp->master = master;
+ dp->dst = dst;
+
+ return 0;
+}
- /* Make a few copies for faster access in master receive hot path */
- dst->cpu_dp->rcv = dst->cpu_dp->tag_ops->rcv;
- dst->cpu_dp->dst = dst;
+static int dsa_cpu_parse(struct dsa_port *port, u32 index,
+ struct dsa_switch_tree *dst,
+ struct dsa_switch *ds)
+{
+ if (!dst->cpu_dp)
+ dst->cpu_dp = port;
return 0;
}
@@ -504,7 +562,7 @@ static int dsa_ds_parse(struct dsa_switch_tree *dst, struct dsa_switch *ds)
}
- pr_info("DSA: switch %d %d parsed\n", dst->tree, ds->index);
+ pr_info("DSA: switch %d %d parsed\n", dst->index, ds->index);
return 0;
}
@@ -549,7 +607,7 @@ static int dsa_dst_parse(struct dsa_switch_tree *dst)
}
}
- pr_info("DSA: tree %d parsed\n", dst->tree);
+ pr_info("DSA: tree %d parsed\n", dst->index);
return 0;
}
@@ -557,8 +615,10 @@ static int dsa_dst_parse(struct dsa_switch_tree *dst)
static int dsa_port_parse_of(struct dsa_port *dp, struct device_node *dn)
{
struct device_node *ethernet = of_parse_phandle(dn, "ethernet", 0);
- struct device_node *link = of_parse_phandle(dn, "link", 0);
const char *name = of_get_property(dn, "label", NULL);
+ bool link = of_property_read_bool(dn, "link");
+
+ dp->dn = dn;
if (ethernet) {
struct net_device *master;
@@ -567,24 +627,17 @@ static int dsa_port_parse_of(struct dsa_port *dp, struct device_node *dn)
if (!master)
return -EPROBE_DEFER;
- dp->type = DSA_PORT_TYPE_CPU;
- dp->master = master;
- } else if (link) {
- dp->type = DSA_PORT_TYPE_DSA;
- } else {
- if (!name)
- name = "eth%d";
-
- dp->type = DSA_PORT_TYPE_USER;
- dp->name = name;
+ return dsa_port_parse_cpu(dp, master);
}
- dp->dn = dn;
+ if (link)
+ return dsa_port_parse_dsa(dp);
- return 0;
+ return dsa_port_parse_user(dp, name);
}
-static int dsa_parse_ports_of(struct device_node *dn, struct dsa_switch *ds)
+static int dsa_switch_parse_ports_of(struct dsa_switch *ds,
+ struct device_node *dn)
{
struct device_node *ports, *port;
struct dsa_port *dp;
@@ -615,6 +668,39 @@ static int dsa_parse_ports_of(struct device_node *dn, struct dsa_switch *ds)
return 0;
}
+static int dsa_switch_parse_member_of(struct dsa_switch *ds,
+ struct device_node *dn)
+{
+ u32 m[2] = { 0, 0 };
+ int sz;
+
+ /* Don't error out if this optional property isn't found */
+ sz = of_property_read_variable_u32_array(dn, "dsa,member", m, 2, 2);
+ if (sz < 0 && sz != -EINVAL)
+ return sz;
+
+ ds->index = m[1];
+ if (ds->index >= DSA_MAX_SWITCHES)
+ return -EINVAL;
+
+ ds->dst = dsa_tree_touch(m[0]);
+ if (!ds->dst)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static int dsa_switch_parse_of(struct dsa_switch *ds, struct device_node *dn)
+{
+ int err;
+
+ err = dsa_switch_parse_member_of(ds, dn);
+ if (err)
+ return err;
+
+ return dsa_switch_parse_ports_of(ds, dn);
+}
+
static int dsa_port_parse(struct dsa_port *dp, const char *name,
struct device *dev)
{
@@ -627,20 +713,17 @@ static int dsa_port_parse(struct dsa_port *dp, const char *name,
dev_put(master);
- dp->type = DSA_PORT_TYPE_CPU;
- dp->master = master;
- } else if (!strcmp(name, "dsa")) {
- dp->type = DSA_PORT_TYPE_DSA;
- } else {
- dp->type = DSA_PORT_TYPE_USER;
+ return dsa_port_parse_cpu(dp, master);
}
- dp->name = name;
+ if (!strcmp(name, "dsa"))
+ return dsa_port_parse_dsa(dp);
- return 0;
+ return dsa_port_parse_user(dp, name);
}
-static int dsa_parse_ports(struct dsa_chip_data *cd, struct dsa_switch *ds)
+static int dsa_switch_parse_ports(struct dsa_switch *ds,
+ struct dsa_chip_data *cd)
{
bool valid_name_found = false;
struct dsa_port *dp;
@@ -670,40 +753,19 @@ static int dsa_parse_ports(struct dsa_chip_data *cd, struct dsa_switch *ds)
return 0;
}
-static int dsa_parse_member_dn(struct device_node *np, u32 *tree, u32 *index)
+static int dsa_switch_parse(struct dsa_switch *ds, struct dsa_chip_data *cd)
{
- int err;
-
- *tree = *index = 0;
-
- err = of_property_read_u32_index(np, "dsa,member", 0, tree);
- if (err) {
- /* Does not exist, but it is optional */
- if (err == -EINVAL)
- return 0;
- return err;
- }
+ ds->cd = cd;
- err = of_property_read_u32_index(np, "dsa,member", 1, index);
- if (err)
- return err;
-
- if (*index >= DSA_MAX_SWITCHES)
- return -EINVAL;
-
- return 0;
-}
-
-static int dsa_parse_member(struct dsa_chip_data *pd, u32 *tree, u32 *index)
-{
- if (!pd)
- return -ENODEV;
-
- /* We do not support complex trees with dsa_chip_data */
- *tree = 0;
- *index = 0;
+ /* We don't support interconnected switches nor multiple trees via
+ * platform data, so this is the unique switch of the tree.
+ */
+ ds->index = 0;
+ ds->dst = dsa_tree_touch(0);
+ if (!ds->dst)
+ return -ENOMEM;
- return 0;
+ return dsa_switch_parse_ports(ds, cd);
}
static int _dsa_register_switch(struct dsa_switch *ds)
@@ -711,58 +773,37 @@ static int _dsa_register_switch(struct dsa_switch *ds)
struct dsa_chip_data *pdata = ds->dev->platform_data;
struct device_node *np = ds->dev->of_node;
struct dsa_switch_tree *dst;
- u32 tree, index;
+ unsigned int index;
int i, err;
- if (np) {
- err = dsa_parse_member_dn(np, &tree, &index);
- if (err)
- return err;
+ if (np)
+ err = dsa_switch_parse_of(ds, np);
+ else if (pdata)
+ err = dsa_switch_parse(ds, pdata);
+ else
+ err = -ENODEV;
- err = dsa_parse_ports_of(np, ds);
- if (err)
- return err;
- } else {
- err = dsa_parse_member(pdata, &tree, &index);
- if (err)
- return err;
-
- err = dsa_parse_ports(pdata, ds);
- if (err)
- return err;
- }
-
- dst = dsa_get_dst(tree);
- if (!dst) {
- dst = dsa_add_dst(tree);
- if (!dst)
- return -ENOMEM;
- }
-
- if (dst->ds[index]) {
- err = -EBUSY;
- goto out;
- }
+ if (err)
+ return err;
- ds->dst = dst;
- ds->index = index;
- ds->cd = pdata;
+ index = ds->index;
+ dst = ds->dst;
/* Initialize the routing table */
for (i = 0; i < DSA_MAX_SWITCHES; ++i)
ds->rtable[i] = DSA_RTABLE_NONE;
- dsa_dst_add_ds(dst, ds, index);
+ err = dsa_tree_add_switch(dst, ds);
+ if (err)
+ return err;
err = dsa_dst_complete(dst);
if (err < 0)
goto out_del_dst;
- if (err == 1) {
- /* Not all switches registered yet */
- err = 0;
- goto out;
- }
+ /* Not all switches registered yet */
+ if (err == 1)
+ return 0;
if (dst->applied) {
pr_info("DSA: Disjoint trees?\n");
@@ -779,13 +820,10 @@ static int _dsa_register_switch(struct dsa_switch *ds)
goto out_del_dst;
}
- dsa_put_dst(dst);
return 0;
out_del_dst:
- dsa_dst_del_ds(dst, ds, ds->index);
-out:
- dsa_put_dst(dst);
+ dsa_tree_remove_switch(dst, index);
return err;
}
@@ -827,10 +865,11 @@ EXPORT_SYMBOL_GPL(dsa_register_switch);
static void _dsa_unregister_switch(struct dsa_switch *ds)
{
struct dsa_switch_tree *dst = ds->dst;
+ unsigned int index = ds->index;
dsa_dst_unapply(dst);
- dsa_dst_del_ds(dst, ds, ds->index);
+ dsa_tree_remove_switch(dst, index);
}
void dsa_unregister_switch(struct dsa_switch *ds)
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 9b75d0ac4092..814ced75a0cc 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -55,7 +55,7 @@ void dsa_slave_mii_bus_init(struct dsa_switch *ds)
ds->slave_mii_bus->read = dsa_slave_phy_read;
ds->slave_mii_bus->write = dsa_slave_phy_write;
snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d.%d",
- ds->dst->tree, ds->index);
+ ds->dst->index, ds->index);
ds->slave_mii_bus->parent = ds->dev;
ds->slave_mii_bus->phy_mask = ~ds->phys_mii_mask;
}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a7a0f316eb86..c4cb19ed4628 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -447,6 +447,7 @@ void tcp_init_sock(struct sock *sk)
tcp_assign_congestion_control(sk);
tp->tsoffset = 0;
+ tp->rack.reo_wnd_steps = 1;
sk->sk_state = TCP_CLOSE;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8393b405ea98..0ada8bfc2ebd 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -856,6 +856,7 @@ void tcp_disable_fack(struct tcp_sock *tp)
static void tcp_dsack_seen(struct tcp_sock *tp)
{
tp->rx_opt.sack_ok |= TCP_DSACK_SEEN;
+ tp->rack.dsack_seen = 1;
}
static void tcp_update_reordering(struct sock *sk, const int metric,
@@ -2408,6 +2409,8 @@ static bool tcp_try_undo_recovery(struct sock *sk)
mib_idx = LINUX_MIB_TCPFULLUNDO;
NET_INC_STATS(sock_net(sk), mib_idx);
+ } else if (tp->rack.reo_wnd_persist) {
+ tp->rack.reo_wnd_persist--;
}
if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) {
/* Hold old state until something *above* high_seq
@@ -2427,6 +2430,8 @@ static bool tcp_try_undo_dsack(struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
if (tp->undo_marker && !tp->undo_retrans) {
+ tp->rack.reo_wnd_persist = min(TCP_RACK_RECOVERY_THRESH,
+ tp->rack.reo_wnd_persist + 1);
DBGUNDO(sk, "D-SACK");
tcp_undo_cwnd_reduction(sk, false);
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDSACKUNDO);
@@ -3644,6 +3649,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, &acked,
&sack_state);
+ tcp_rack_update_reo_wnd(sk, &rs);
+
if (tp->tlp_high_seq)
tcp_process_tlp_ack(sk, ack, flag);
/* If needed, reset TLP/RTO timer; RACK may later override this. */
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 3c65c1a3f944..4bb86580decd 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -551,6 +551,10 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
newtp->syn_data_acked = 0;
newtp->rack.mstamp = 0;
newtp->rack.advanced = 0;
+ newtp->rack.reo_wnd_steps = 1;
+ newtp->rack.last_delivered = 0;
+ newtp->rack.reo_wnd_persist = 0;
+ newtp->rack.dsack_seen = 0;
__TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS);
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b98b2f7f07e7..a9d917e4dad5 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -381,7 +381,6 @@ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb,
static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags)
{
skb->ip_summed = CHECKSUM_PARTIAL;
- skb->csum = 0;
TCP_SKB_CB(skb)->tcp_flags = flags;
TCP_SKB_CB(skb)->sacked = 0;
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index ac3e9c6d3a3d..d3ea89020c69 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -44,6 +44,7 @@ static bool tcp_rack_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2)
static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
{
struct tcp_sock *tp = tcp_sk(sk);
+ u32 min_rtt = tcp_min_rtt(tp);
struct sk_buff *skb, *n;
u32 reo_wnd;
@@ -54,8 +55,10 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
* to queuing or delayed ACKs.
*/
reo_wnd = 1000;
- if ((tp->rack.reord || !tp->lost_out) && tcp_min_rtt(tp) != ~0U)
- reo_wnd = max(tcp_min_rtt(tp) >> 2, reo_wnd);
+ if ((tp->rack.reord || !tp->lost_out) && min_rtt != ~0U) {
+ reo_wnd = max((min_rtt >> 2) * tp->rack.reo_wnd_steps, reo_wnd);
+ reo_wnd = min(reo_wnd, tp->srtt_us >> 3);
+ }
list_for_each_entry_safe(skb, n, &tp->tsorted_sent_queue,
tcp_tsorted_anchor) {
@@ -160,3 +163,44 @@ void tcp_rack_reo_timeout(struct sock *sk)
if (inet_csk(sk)->icsk_pending != ICSK_TIME_RETRANS)
tcp_rearm_rto(sk);
}
+
+/* Updates the RACK's reo_wnd based on DSACK and no. of recoveries.
+ *
+ * If DSACK is received, increment reo_wnd by min_rtt/4 (upper bounded
+ * by srtt), since there is possibility that spurious retransmission was
+ * due to reordering delay longer than reo_wnd.
+ *
+ * Persist the current reo_wnd value for TCP_RACK_RECOVERY_THRESH (16)
+ * no. of successful recoveries (accounts for full DSACK-based loss
+ * recovery undo). After that, reset it to default (min_rtt/4).
+ *
+ * At max, reo_wnd is incremented only once per rtt. So that the new
+ * DSACK on which we are reacting, is due to the spurious retx (approx)
+ * after the reo_wnd has been updated last time.
+ *
+ * reo_wnd is tracked in terms of steps (of min_rtt/4), rather than
+ * absolute value to account for change in rtt.
+ */
+void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_STATIC_REO_WND ||
+ !rs->prior_delivered)
+ return;
+
+ /* Disregard DSACK if a rtt has not passed since we adjusted reo_wnd */
+ if (before(rs->prior_delivered, tp->rack.last_delivered))
+ tp->rack.dsack_seen = 0;
+
+ /* Adjust the reo_wnd if update is pending */
+ if (tp->rack.dsack_seen) {
+ tp->rack.reo_wnd_steps = min_t(u32, 0xFF,
+ tp->rack.reo_wnd_steps + 1);
+ tp->rack.dsack_seen = 0;
+ tp->rack.last_delivered = tp->delivered;
+ tp->rack.reo_wnd_persist = TCP_RACK_RECOVERY_THRESH;
+ } else if (!tp->rack.reo_wnd_persist) {
+ tp->rack.reo_wnd_steps = 1;
+ }
+}
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 035a1ef1f2d8..16df6dd44b98 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -107,26 +107,23 @@ static int tcp_orphan_retries(struct sock *sk, bool alive)
static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
{
- struct net *net = sock_net(sk);
+ const struct net *net = sock_net(sk);
+ int mss;
/* Black hole detection */
- if (net->ipv4.sysctl_tcp_mtu_probing) {
- if (!icsk->icsk_mtup.enabled) {
- icsk->icsk_mtup.enabled = 1;
- icsk->icsk_mtup.probe_timestamp = tcp_jiffies32;
- tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
- } else {
- struct net *net = sock_net(sk);
- struct tcp_sock *tp = tcp_sk(sk);
- int mss;
-
- mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1;
- mss = min(net->ipv4.sysctl_tcp_base_mss, mss);
- mss = max(mss, 68 - tp->tcp_header_len);
- icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss);
- tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
- }
+ if (!net->ipv4.sysctl_tcp_mtu_probing)
+ return;
+
+ if (!icsk->icsk_mtup.enabled) {
+ icsk->icsk_mtup.enabled = 1;
+ icsk->icsk_mtup.probe_timestamp = tcp_jiffies32;
+ } else {
+ mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1;
+ mss = min(net->ipv4.sysctl_tcp_base_mss, mss);
+ mss = max(mss, 68 - tcp_sk(sk)->tcp_header_len);
+ icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss);
}
+ tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
}
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index c3aec6227c91..4d38ac044cee 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1848,7 +1848,8 @@ static struct genl_family dp_datapath_genl_family __ro_after_init = {
/* Called with ovs_mutex or RCU read lock. */
static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb,
- u32 portid, u32 seq, u32 flags, u8 cmd)
+ struct net *net, u32 portid, u32 seq,
+ u32 flags, u8 cmd)
{
struct ovs_header *ovs_header;
struct ovs_vport_stats vport_stats;
@@ -1864,9 +1865,17 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb,
if (nla_put_u32(skb, OVS_VPORT_ATTR_PORT_NO, vport->port_no) ||
nla_put_u32(skb, OVS_VPORT_ATTR_TYPE, vport->ops->type) ||
nla_put_string(skb, OVS_VPORT_ATTR_NAME,
- ovs_vport_name(vport)))
+ ovs_vport_name(vport)) ||
+ nla_put_u32(skb, OVS_VPORT_ATTR_IFINDEX, vport->dev->ifindex))
goto nla_put_failure;
+ if (!net_eq(net, dev_net(vport->dev))) {
+ int id = peernet2id_alloc(net, dev_net(vport->dev));
+
+ if (nla_put_s32(skb, OVS_VPORT_ATTR_NETNSID, id))
+ goto nla_put_failure;
+ }
+
ovs_vport_get_stats(vport, &vport_stats);
if (nla_put_64bit(skb, OVS_VPORT_ATTR_STATS,
sizeof(struct ovs_vport_stats), &vport_stats,
@@ -1896,8 +1905,8 @@ static struct sk_buff *ovs_vport_cmd_alloc_info(void)
}
/* Called with ovs_mutex, only via ovs_dp_notify_wq(). */
-struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid,
- u32 seq, u8 cmd)
+struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, struct net *net,
+ u32 portid, u32 seq, u8 cmd)
{
struct sk_buff *skb;
int retval;
@@ -1906,7 +1915,7 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid,
if (!skb)
return ERR_PTR(-ENOMEM);
- retval = ovs_vport_cmd_fill_info(vport, skb, portid, seq, 0, cmd);
+ retval = ovs_vport_cmd_fill_info(vport, skb, net, portid, seq, 0, cmd);
BUG_ON(retval < 0);
return skb;
@@ -1920,6 +1929,8 @@ static struct vport *lookup_vport(struct net *net,
struct datapath *dp;
struct vport *vport;
+ if (a[OVS_VPORT_ATTR_IFINDEX])
+ return ERR_PTR(-EOPNOTSUPP);
if (a[OVS_VPORT_ATTR_NAME]) {
vport = ovs_vport_locate(net, nla_data(a[OVS_VPORT_ATTR_NAME]));
if (!vport)
@@ -1944,6 +1955,7 @@ static struct vport *lookup_vport(struct net *net,
return vport;
} else
return ERR_PTR(-EINVAL);
+
}
/* Called with ovs_mutex */
@@ -1983,6 +1995,8 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
if (!a[OVS_VPORT_ATTR_NAME] || !a[OVS_VPORT_ATTR_TYPE] ||
!a[OVS_VPORT_ATTR_UPCALL_PID])
return -EINVAL;
+ if (a[OVS_VPORT_ATTR_IFINDEX])
+ return -EOPNOTSUPP;
port_no = a[OVS_VPORT_ATTR_PORT_NO]
? nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]) : 0;
@@ -2032,8 +2046,9 @@ restart:
goto exit_unlock_free;
}
- err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
- info->snd_seq, 0, OVS_VPORT_CMD_NEW);
+ err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
+ info->snd_portid, info->snd_seq, 0,
+ OVS_VPORT_CMD_NEW);
if (netdev_get_fwd_headroom(vport->dev) > dp->max_headroom)
update_headroom(dp);
@@ -2090,8 +2105,9 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info)
goto exit_unlock_free;
}
- err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
- info->snd_seq, 0, OVS_VPORT_CMD_NEW);
+ err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
+ info->snd_portid, info->snd_seq, 0,
+ OVS_VPORT_CMD_NEW);
BUG_ON(err < 0);
ovs_unlock();
@@ -2128,8 +2144,9 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info)
goto exit_unlock_free;
}
- err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
- info->snd_seq, 0, OVS_VPORT_CMD_DEL);
+ err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
+ info->snd_portid, info->snd_seq, 0,
+ OVS_VPORT_CMD_DEL);
BUG_ON(err < 0);
/* the vport deletion may trigger dp headroom update */
@@ -2169,8 +2186,9 @@ static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info)
err = PTR_ERR(vport);
if (IS_ERR(vport))
goto exit_unlock_free;
- err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid,
- info->snd_seq, 0, OVS_VPORT_CMD_NEW);
+ err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
+ info->snd_portid, info->snd_seq, 0,
+ OVS_VPORT_CMD_NEW);
BUG_ON(err < 0);
rcu_read_unlock();
@@ -2202,6 +2220,7 @@ static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) {
if (j >= skip &&
ovs_vport_cmd_fill_info(vport, skb,
+ sock_net(skb->sk),
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
NLM_F_MULTI,
@@ -2228,6 +2247,8 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = {
[OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 },
[OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 },
[OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED },
+ [OVS_VPORT_ATTR_IFINDEX] = { .type = NLA_U32 },
+ [OVS_VPORT_ATTR_NETNSID] = { .type = NLA_S32 },
};
static const struct genl_ops dp_vport_genl_ops[] = {
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 480600649d0b..4a104ef9e12c 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -200,8 +200,8 @@ int ovs_dp_upcall(struct datapath *, struct sk_buff *,
uint32_t cutlen);
const char *ovs_dp_name(const struct datapath *dp);
-struct sk_buff *ovs_vport_cmd_build_info(struct vport *, u32 pid, u32 seq,
- u8 cmd);
+struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, struct net *net,
+ u32 portid, u32 seq, u8 cmd);
int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
const struct sw_flow_actions *, struct sw_flow_key *);
diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c
index 653d073bae45..f3ee2f2825c0 100644
--- a/net/openvswitch/dp_notify.c
+++ b/net/openvswitch/dp_notify.c
@@ -30,8 +30,8 @@ static void dp_detach_port_notify(struct vport *vport)
struct datapath *dp;
dp = vport->dp;
- notify = ovs_vport_cmd_build_info(vport, 0, 0,
- OVS_VPORT_CMD_DEL);
+ notify = ovs_vport_cmd_build_info(vport, ovs_dp_get_net(dp),
+ 0, 0, OVS_VPORT_CMD_DEL);
ovs_dp_detach_port(vport);
if (IS_ERR(notify)) {
genl_set_err(&dp_vport_genl_family, ovs_dp_get_net(dp), 0,
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index bc3edde1b9d7..dc9bd9a0070b 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -374,7 +374,7 @@ static int cls_bpf_prog_from_ops(struct nlattr **tb, struct cls_bpf_prog *prog)
}
static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog,
- const struct tcf_proto *tp)
+ u32 gen_flags, const struct tcf_proto *tp)
{
struct bpf_prog *fp;
char *name = NULL;
@@ -382,7 +382,11 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog,
bpf_fd = nla_get_u32(tb[TCA_BPF_FD]);
- fp = bpf_prog_get_type(bpf_fd, BPF_PROG_TYPE_SCHED_CLS);
+ if (gen_flags & TCA_CLS_FLAGS_SKIP_SW)
+ fp = bpf_prog_get_type_dev(bpf_fd, BPF_PROG_TYPE_SCHED_CLS,
+ qdisc_dev(tp->q));
+ else
+ fp = bpf_prog_get_type(bpf_fd, BPF_PROG_TYPE_SCHED_CLS);
if (IS_ERR(fp))
return PTR_ERR(fp);
@@ -440,7 +444,7 @@ static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp,
prog->gen_flags = gen_flags;
ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) :
- cls_bpf_prog_from_efd(tb, prog, tp);
+ cls_bpf_prog_from_efd(tb, prog, gen_flags, tp);
if (ret < 0)
return ret;
OpenPOWER on IntegriCloud