* [PATCH iproute2 0/2] malloc correct buff at run time
From: Hangbin Liu @ 2017-09-08 10:14 UTC (permalink / raw)
To: netdev; +Cc: Stephen Hemminger, Michal Kubecek, Phil Sutter, Hangbin Liu
With commit 72b365e8e0fd ("libnetlink: Double the dump buffer size") and
460c03f3f3cc ("iplink: double the buffer size also in iplink_get()"), we
extend the buffer size to avoid truncated message with large numbers of
VFs. But just as Michal said, this is not future-proof since the NIC
number is increasing. We have customer even has 220+ VFs now.
This is not make sense to hard code the buffer and increase it all the time.
So let's just malloc the correct buff size at run time.
I'm not sure what init size would be suitable, so I keep use the original
size. I have tried with a small size like 1024, and it also works.
I tested with most ip cmds and all looks good.
Hangbin Liu (2):
lib/libnetlink: re malloc buff if size is not enough
lib/libnetlink: update rtnl_talk to support malloc buff at run time
bridge/fdb.c | 2 +-
bridge/link.c | 2 +-
bridge/mdb.c | 2 +-
bridge/vlan.c | 2 +-
genl/ctrl.c | 14 +++---
include/libnetlink.h | 6 +--
ip/ipaddress.c | 5 ++-
ip/ipaddrlabel.c | 4 +-
ip/ipfou.c | 4 +-
ip/ipila.c | 4 +-
ip/ipl2tp.c | 8 ++--
ip/iplink.c | 28 +++++-------
ip/iplink_vrf.c | 24 ++++-------
ip/ipmacsec.c | 2 +-
ip/ipneigh.c | 2 +-
ip/ipnetns.c | 13 +++---
ip/ipntable.c | 2 +-
ip/iproute.c | 20 +++++----
ip/iprule.c | 7 +--
ip/ipseg6.c | 7 +--
ip/iptoken.c | 2 +-
ip/link_gre.c | 7 +--
ip/link_gre6.c | 7 +--
ip/link_ip6tnl.c | 7 +--
ip/link_iptnl.c | 7 +--
ip/link_vti.c | 7 +--
ip/link_vti6.c | 7 +--
ip/tcp_metrics.c | 7 +--
ip/xfrm_policy.c | 22 +++++-----
ip/xfrm_state.c | 25 ++++++-----
lib/libgenl.c | 5 ++-
lib/libnetlink.c | 118 ++++++++++++++++++++++++++++++++-------------------
misc/ss.c | 2 +-
tc/m_action.c | 9 ++--
tc/tc_class.c | 2 +-
tc/tc_filter.c | 7 +--
tc/tc_qdisc.c | 2 +-
37 files changed, 217 insertions(+), 184 deletions(-)
--
2.5.5
^ permalink raw reply
* [PATCH iproute2 1/2] lib/libnetlink: re malloc buff if size is not enough
From: Hangbin Liu @ 2017-09-08 10:14 UTC (permalink / raw)
To: netdev; +Cc: Stephen Hemminger, Michal Kubecek, Phil Sutter, Hangbin Liu
In-Reply-To: <1504865697-27274-1-git-send-email-liuhangbin@gmail.com>
With commit 72b365e8e0fd ("libnetlink: Double the dump buffer size")
we doubled the buffer size to support more VFs. But the VFs number is
increasing all the time. Some customers even use more than 200 VFs now.
We could not double it everytime when the buffer is not enough. Let's just
not hard code the buffer size and malloc the correct number when running.
Introduce a new function rtnl_recvmsg() to get correct buffer.
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
---
lib/libnetlink.c | 98 ++++++++++++++++++++++++++++++++++++++------------------
1 file changed, 66 insertions(+), 32 deletions(-)
diff --git a/lib/libnetlink.c b/lib/libnetlink.c
index be7ac86..37cfb5a 100644
--- a/lib/libnetlink.c
+++ b/lib/libnetlink.c
@@ -402,6 +402,59 @@ static void rtnl_dump_error(const struct rtnl_handle *rth,
}
}
+static int rtnl_recvmsg(int fd, struct msghdr *msg, char **buf)
+{
+ struct iovec *iov;
+ int len = -1, buf_len = 32768;
+ char *buffer = *buf;
+
+ int flag = MSG_PEEK | MSG_TRUNC;
+
+ if (buffer == NULL)
+re_malloc:
+ buffer = malloc(buf_len);
+
+ if (buffer == NULL) {
+ fprintf(stderr, "malloc error: no enough buffer\n");
+ return -1;
+ }
+
+ iov = msg->msg_iov;
+ iov->iov_base = buffer;
+ iov->iov_len = buf_len;
+
+re_recv:
+ len = recvmsg(fd, msg, flag);
+
+ if (len < 0) {
+ if (errno == EINTR || errno == EAGAIN)
+ return 0;
+ fprintf(stderr, "netlink receive error %s (%d)\n",
+ strerror(errno), errno);
+ return len;
+ }
+
+ if (len == 0) {
+ fprintf(stderr, "EOF on netlink\n");
+ return -1;
+ }
+
+ if (len > buf_len) {
+ free(buffer);
+ buf_len = len;
+ flag = 0;
+ goto re_malloc;
+ }
+
+ if (flag != 0) {
+ flag = 0;
+ goto re_recv;
+ }
+
+ *buf = buffer;
+ return len;
+}
+
int rtnl_dump_filter_l(struct rtnl_handle *rth,
const struct rtnl_dump_filter_arg *arg)
{
@@ -413,31 +466,20 @@ int rtnl_dump_filter_l(struct rtnl_handle *rth,
.msg_iov = &iov,
.msg_iovlen = 1,
};
- char buf[32768];
+ static char *buf = NULL;
int dump_intr = 0;
- iov.iov_base = buf;
while (1) {
int status;
const struct rtnl_dump_filter_arg *a;
int found_done = 0;
int msglen = 0;
- iov.iov_len = sizeof(buf);
- status = recvmsg(rth->fd, &msg, 0);
-
- if (status < 0) {
- if (errno == EINTR || errno == EAGAIN)
- continue;
- fprintf(stderr, "netlink receive error %s (%d)\n",
- strerror(errno), errno);
- return -1;
- }
-
- if (status == 0) {
- fprintf(stderr, "EOF on netlink\n");
- return -1;
- }
+ status = rtnl_recvmsg(rth->fd, &msg, &buf);
+ if (status < 0)
+ return status;
+ else if (status == 0)
+ continue;
if (rth->dump_fp)
fwrite(buf, 1, NLMSG_ALIGN(status), rth->dump_fp);
@@ -543,7 +585,7 @@ static int __rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n,
.msg_iov = &iov,
.msg_iovlen = 1,
};
- char buf[32768] = {};
+ static char *buf = NULL;
n->nlmsg_seq = seq = ++rtnl->seq;
@@ -556,22 +598,14 @@ static int __rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n,
return -1;
}
- iov.iov_base = buf;
while (1) {
- iov.iov_len = sizeof(buf);
- status = recvmsg(rtnl->fd, &msg, 0);
+ status = rtnl_recvmsg(rtnl->fd, &msg, &buf);
+
+ if (status < 0)
+ return status;
+ else if (status == 0)
+ continue;
- if (status < 0) {
- if (errno == EINTR || errno == EAGAIN)
- continue;
- fprintf(stderr, "netlink receive error %s (%d)\n",
- strerror(errno), errno);
- return -1;
- }
- if (status == 0) {
- fprintf(stderr, "EOF on netlink\n");
- return -1;
- }
if (msg.msg_namelen != sizeof(nladdr)) {
fprintf(stderr,
"sender address length == %d\n",
--
2.5.5
^ permalink raw reply related
* [PATCH iproute2 2/2] lib/libnetlink: update rtnl_talk to support malloc buff at run time
From: Hangbin Liu @ 2017-09-08 10:14 UTC (permalink / raw)
To: netdev; +Cc: Stephen Hemminger, Michal Kubecek, Phil Sutter, Hangbin Liu
In-Reply-To: <1504865697-27274-1-git-send-email-liuhangbin@gmail.com>
This is an update for 460c03f3f3cc ("iplink: double the buffer size also in
iplink_get()"). After update, we will not need to double the buffer size
every time when VFs number increased.
With call like rtnl_talk(&rth, &req.n, NULL, 0), we can simply remove the
length parameter.
With call like rtnl_talk(&rth, nlh, nlh, sizeof(req), I add a new variable
answer to avoid overwrite data in nlh, because it may has more info after
nlh. also this will avoid nlh buffer not enough issue.
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
---
bridge/fdb.c | 2 +-
bridge/link.c | 2 +-
bridge/mdb.c | 2 +-
bridge/vlan.c | 2 +-
genl/ctrl.c | 14 ++++++++------
include/libnetlink.h | 6 +++---
ip/ipaddress.c | 5 +++--
ip/ipaddrlabel.c | 4 ++--
ip/ipfou.c | 4 ++--
ip/ipila.c | 4 ++--
ip/ipl2tp.c | 8 ++++----
ip/iplink.c | 28 +++++++++++-----------------
ip/iplink_vrf.c | 24 ++++++++----------------
ip/ipmacsec.c | 2 +-
ip/ipneigh.c | 2 +-
ip/ipnetns.c | 13 +++++++------
ip/ipntable.c | 2 +-
ip/iproute.c | 20 +++++++++++---------
ip/iprule.c | 7 ++++---
ip/ipseg6.c | 7 ++++---
ip/iptoken.c | 2 +-
ip/link_gre.c | 7 ++++---
ip/link_gre6.c | 7 ++++---
ip/link_ip6tnl.c | 7 ++++---
ip/link_iptnl.c | 7 ++++---
ip/link_vti.c | 7 ++++---
ip/link_vti6.c | 7 ++++---
ip/tcp_metrics.c | 7 ++++---
ip/xfrm_policy.c | 22 +++++++++++-----------
ip/xfrm_state.c | 25 ++++++++++++-------------
lib/libgenl.c | 5 +++--
lib/libnetlink.c | 20 +++++++++-----------
misc/ss.c | 2 +-
tc/m_action.c | 9 ++++-----
tc/tc_class.c | 2 +-
tc/tc_filter.c | 7 ++++---
tc/tc_qdisc.c | 2 +-
37 files changed, 151 insertions(+), 152 deletions(-)
diff --git a/bridge/fdb.c b/bridge/fdb.c
index e5cebf9..807914f 100644
--- a/bridge/fdb.c
+++ b/bridge/fdb.c
@@ -535,7 +535,7 @@ static int fdb_modify(int cmd, int flags, int argc, char **argv)
return -1;
}
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&rth, &req.n, NULL) < 0)
return -1;
return 0;
diff --git a/bridge/link.c b/bridge/link.c
index 93472ad..cc29a2a 100644
--- a/bridge/link.c
+++ b/bridge/link.c
@@ -426,7 +426,7 @@ static int brlink_modify(int argc, char **argv)
addattr_nest_end(&req.n, nest);
}
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&rth, &req.n, NULL) < 0)
return -1;
return 0;
diff --git a/bridge/mdb.c b/bridge/mdb.c
index e60ff3e..fbd8184 100644
--- a/bridge/mdb.c
+++ b/bridge/mdb.c
@@ -298,7 +298,7 @@ static int mdb_modify(int cmd, int flags, int argc, char **argv)
entry.vid = vid;
addattr_l(&req.n, sizeof(req), MDBA_SET_ENTRY, &entry, sizeof(entry));
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&rth, &req.n, NULL) < 0)
return -1;
return 0;
diff --git a/bridge/vlan.c b/bridge/vlan.c
index ebcdace..5d68359 100644
--- a/bridge/vlan.c
+++ b/bridge/vlan.c
@@ -133,7 +133,7 @@ static int vlan_modify(int cmd, int argc, char **argv)
addattr_nest_end(&req.n, afspec);
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&rth, &req.n, NULL) < 0)
return -1;
return 0;
diff --git a/genl/ctrl.c b/genl/ctrl.c
index 448988e..699657b 100644
--- a/genl/ctrl.c
+++ b/genl/ctrl.c
@@ -55,6 +55,7 @@ int genl_ctrl_resolve_family(const char *family)
};
struct nlmsghdr *nlh = &req.n;
struct genlmsghdr *ghdr = &req.g;
+ struct nlmsghdr *answer = NULL;
if (rtnl_open_byproto(&rth, 0, NETLINK_GENERIC) < 0) {
fprintf(stderr, "Cannot open generic netlink socket\n");
@@ -63,19 +64,19 @@ int genl_ctrl_resolve_family(const char *family)
addattr_l(nlh, 128, CTRL_ATTR_FAMILY_NAME, family, strlen(family) + 1);
- if (rtnl_talk(&rth, nlh, nlh, sizeof(req)) < 0) {
+ if (rtnl_talk(&rth, nlh, &answer) < 0) {
fprintf(stderr, "Error talking to the kernel\n");
goto errout;
}
{
struct rtattr *tb[CTRL_ATTR_MAX + 1];
- int len = nlh->nlmsg_len;
+ int len = answer->nlmsg_len;
struct rtattr *attrs;
- if (nlh->nlmsg_type != GENL_ID_CTRL) {
+ if (answer->nlmsg_type != GENL_ID_CTRL) {
fprintf(stderr, "Not a controller message, nlmsg_len=%d "
- "nlmsg_type=0x%x\n", nlh->nlmsg_len, nlh->nlmsg_type);
+ "nlmsg_type=0x%x\n", answer->nlmsg_len, answer->nlmsg_type);
goto errout;
}
@@ -299,6 +300,7 @@ static int ctrl_list(int cmd, int argc, char **argv)
.g.cmd = CTRL_CMD_GETFAMILY,
};
struct nlmsghdr *nlh = &req.n;
+ struct nlmsghdr *answer = NULL;
if (rtnl_open_byproto(&rth, 0, NETLINK_GENERIC) < 0) {
fprintf(stderr, "Cannot open generic netlink socket\n");
@@ -331,12 +333,12 @@ static int ctrl_list(int cmd, int argc, char **argv)
goto ctrl_done;
}
- if (rtnl_talk(&rth, nlh, nlh, sizeof(req)) < 0) {
+ if (rtnl_talk(&rth, nlh, &answer) < 0) {
fprintf(stderr, "Error talking to the kernel\n");
goto ctrl_done;
}
- if (print_ctrl2(NULL, nlh, (void *) stdout) < 0) {
+ if (print_ctrl2(NULL, answer, (void *) stdout) < 0) {
fprintf(stderr, "Dump terminated\n");
goto ctrl_done;
}
diff --git a/include/libnetlink.h b/include/libnetlink.h
index 69257f0..77b6260 100644
--- a/include/libnetlink.h
+++ b/include/libnetlink.h
@@ -93,13 +93,13 @@ int rtnl_dump_filter_nc(struct rtnl_handle *rth,
#define rtnl_dump_filter(rth, filter, arg) \
rtnl_dump_filter_nc(rth, filter, arg, 0)
int rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n,
- struct nlmsghdr *answer, size_t len)
+ struct nlmsghdr **answer)
__attribute__((warn_unused_result));
int rtnl_talk_extack(struct rtnl_handle *rtnl, struct nlmsghdr *n,
- struct nlmsghdr *answer, size_t len, nl_ext_ack_fn_t errfn)
+ struct nlmsghdr **answer, nl_ext_ack_fn_t errfn)
__attribute__((warn_unused_result));
int rtnl_talk_suppress_rtnl_errmsg(struct rtnl_handle *rtnl, struct nlmsghdr *n,
- struct nlmsghdr *answer, size_t len)
+ struct nlmsghdr **answer)
__attribute__((warn_unused_result));
int rtnl_send(struct rtnl_handle *rth, const void *buf, int)
__attribute__((warn_unused_result));
diff --git a/ip/ipaddress.c b/ip/ipaddress.c
index c9312f0..f84e591 100644
--- a/ip/ipaddress.c
+++ b/ip/ipaddress.c
@@ -1385,12 +1385,13 @@ static int restore_handler(const struct sockaddr_nl *nl,
struct nlmsghdr *n, void *arg)
{
int ret;
+ struct nlmsghdr *answer = NULL;
n->nlmsg_flags |= NLM_F_REQUEST | NLM_F_CREATE | NLM_F_ACK;
ll_init_map(&rth);
- ret = rtnl_talk(&rth, n, n, sizeof(*n));
+ ret = rtnl_talk(&rth, n, &answer);
if ((ret < 0) && (errno == EEXIST))
ret = 0;
@@ -2076,7 +2077,7 @@ static int ipaddr_modify(int cmd, int flags, int argc, char **argv)
return -1;
}
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&rth, &req.n, NULL) < 0)
return -2;
return 0;
diff --git a/ip/ipaddrlabel.c b/ip/ipaddrlabel.c
index 1d324da..6ea9bff 100644
--- a/ip/ipaddrlabel.c
+++ b/ip/ipaddrlabel.c
@@ -176,7 +176,7 @@ static int ipaddrlabel_modify(int cmd, int argc, char **argv)
if (req.ifal.ifal_family == AF_UNSPEC)
req.ifal.ifal_family = AF_INET6;
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&rth, &req.n, NULL) < 0)
return -2;
return 0;
@@ -203,7 +203,7 @@ static int flush_addrlabel(const struct sockaddr_nl *who, struct nlmsghdr *n, vo
if (rtnl_open(&rth2, 0) < 0)
return -1;
- if (rtnl_talk(&rth2, n, NULL, 0) < 0)
+ if (rtnl_talk(&rth2, n, NULL) < 0)
return -2;
rtnl_close(&rth2);
diff --git a/ip/ipfou.c b/ip/ipfou.c
index 00dbe15..23000dc 100644
--- a/ip/ipfou.c
+++ b/ip/ipfou.c
@@ -116,7 +116,7 @@ static int do_add(int argc, char **argv)
fou_parse_opt(argc, argv, &req.n, true);
- if (rtnl_talk(&genl_rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&genl_rth, &req.n, NULL) < 0)
return -2;
return 0;
@@ -128,7 +128,7 @@ static int do_del(int argc, char **argv)
fou_parse_opt(argc, argv, &req.n, false);
- if (rtnl_talk(&genl_rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&genl_rth, &req.n, NULL) < 0)
return -2;
return 0;
diff --git a/ip/ipila.c b/ip/ipila.c
index 843cc16..0403fc4 100644
--- a/ip/ipila.c
+++ b/ip/ipila.c
@@ -220,7 +220,7 @@ static int do_add(int argc, char **argv)
ila_parse_opt(argc, argv, &req.n, true);
- if (rtnl_talk(&genl_rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&genl_rth, &req.n, NULL) < 0)
return -2;
return 0;
@@ -232,7 +232,7 @@ static int do_del(int argc, char **argv)
ila_parse_opt(argc, argv, &req.n, false);
- if (rtnl_talk(&genl_rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&genl_rth, &req.n, NULL) < 0)
return -2;
return 0;
diff --git a/ip/ipl2tp.c b/ip/ipl2tp.c
index 88664c9..742adbe 100644
--- a/ip/ipl2tp.c
+++ b/ip/ipl2tp.c
@@ -129,7 +129,7 @@ static int create_tunnel(struct l2tp_parm *p)
addattr(&req.n, 1024, L2TP_ATTR_UDP_ZERO_CSUM6_RX);
}
- if (rtnl_talk(&genl_rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&genl_rth, &req.n, NULL) < 0)
return -2;
return 0;
@@ -142,7 +142,7 @@ static int delete_tunnel(struct l2tp_parm *p)
addattr32(&req.n, 128, L2TP_ATTR_CONN_ID, p->tunnel_id);
- if (rtnl_talk(&genl_rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&genl_rth, &req.n, NULL) < 0)
return -2;
return 0;
@@ -185,7 +185,7 @@ static int create_session(struct l2tp_parm *p)
if (p->ifname && p->ifname[0])
addattrstrz(&req.n, 1024, L2TP_ATTR_IFNAME, p->ifname);
- if (rtnl_talk(&genl_rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&genl_rth, &req.n, NULL) < 0)
return -2;
return 0;
@@ -198,7 +198,7 @@ static int delete_session(struct l2tp_parm *p)
addattr32(&req.n, 1024, L2TP_ATTR_CONN_ID, p->tunnel_id);
addattr32(&req.n, 1024, L2TP_ATTR_SESSION_ID, p->session_id);
- if (rtnl_talk(&genl_rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&genl_rth, &req.n, NULL) < 0)
return -2;
return 0;
diff --git a/ip/iplink.c b/ip/iplink.c
index 72c3479..e078d2a 100644
--- a/ip/iplink.c
+++ b/ip/iplink.c
@@ -248,16 +248,18 @@ static int nl_get_ll_addr_len(unsigned int dev_index)
.ifi_index = dev_index,
}
};
+ struct nlmsghdr *answer = NULL;
struct rtattr *tb[IFLA_MAX+1];
- if (rtnl_talk(&rth, &req.n, &req.n, sizeof(req)) < 0)
+ if (rtnl_talk(&rth, &req.n, &answer) < 0)
return -1;
- len = req.n.nlmsg_len - NLMSG_LENGTH(sizeof(req.i));
+ len = answer->nlmsg_len - NLMSG_LENGTH(sizeof(struct ifinfomsg));
if (len < 0)
return -1;
- parse_rtattr_flags(tb, IFLA_MAX, IFLA_RTA(&req.i), len, NLA_F_NESTED);
+ parse_rtattr_flags(tb, IFLA_MAX, IFLA_RTA(NLMSG_DATA(answer)),
+ len, NLA_F_NESTED);
if (!tb[IFLA_ADDRESS])
return -1;
@@ -912,7 +914,7 @@ static int iplink_modify(int cmd, unsigned int flags, int argc, char **argv)
req.i.ifi_index = 0;
addattr32(&req.n, sizeof(req), IFLA_GROUP, group);
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&rth, &req.n, NULL) < 0)
return -2;
return 0;
}
@@ -1007,7 +1009,7 @@ static int iplink_modify(int cmd, unsigned int flags, int argc, char **argv)
return -1;
}
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&rth, &req.n, NULL) < 0)
return -2;
return 0;
@@ -1022,10 +1024,7 @@ int iplink_get(unsigned int flags, char *name, __u32 filt_mask)
.n.nlmsg_type = RTM_GETLINK,
.i.ifi_family = preferred_family,
};
- struct {
- struct nlmsghdr n;
- char buf[32768];
- } answer;
+ struct nlmsghdr *answer = NULL;
if (name) {
len = strlen(name) + 1;
@@ -1038,18 +1037,13 @@ int iplink_get(unsigned int flags, char *name, __u32 filt_mask)
}
addattr32(&req.n, sizeof(req), IFLA_EXT_MASK, filt_mask);
- if (rtnl_talk(&rth, &req.n, &answer.n, sizeof(answer)) < 0)
- return -2;
- if (answer.n.nlmsg_len > sizeof(answer.buf)) {
- fprintf(stderr, "Message truncated from %u to %lu\n",
- answer.n.nlmsg_len, sizeof(answer.buf));
+ if (rtnl_talk(&rth, &req.n, &answer) < 0)
return -2;
- }
if (brief)
- print_linkinfo_brief(NULL, &answer.n, stdout, NULL);
+ print_linkinfo_brief(NULL, answer, stdout, NULL);
else
- print_linkinfo(NULL, &answer.n, stdout);
+ print_linkinfo(NULL, answer, stdout);
return 0;
}
diff --git a/ip/iplink_vrf.c b/ip/iplink_vrf.c
index 2b85a3a..6dbc8b4 100644
--- a/ip/iplink_vrf.c
+++ b/ip/iplink_vrf.c
@@ -114,10 +114,7 @@ __u32 ipvrf_get_table(const char *name)
.ifi_family = preferred_family,
},
};
- struct {
- struct nlmsghdr n;
- char buf[8192];
- } answer;
+ struct nlmsghdr *answer = NULL;
struct rtattr *tb[IFLA_MAX+1];
struct rtattr *li[IFLA_INFO_MAX+1];
struct rtattr *vrf_attr[IFLA_VRF_MAX + 1];
@@ -127,8 +124,7 @@ __u32 ipvrf_get_table(const char *name)
addattr_l(&req.n, sizeof(req), IFLA_IFNAME, name, strlen(name) + 1);
- if (rtnl_talk_suppress_rtnl_errmsg(&rth, &req.n,
- &answer.n, sizeof(answer)) < 0) {
+ if (rtnl_talk_suppress_rtnl_errmsg(&rth, &req.n, &answer) < 0) {
/* special case "default" vrf to be the main table */
if (errno == ENODEV && !strcmp(name, "default"))
if (rtnl_rttable_a2n(&tb_id, "main"))
@@ -138,8 +134,8 @@ __u32 ipvrf_get_table(const char *name)
return tb_id;
}
- ifi = NLMSG_DATA(&answer.n);
- len = answer.n.nlmsg_len - NLMSG_LENGTH(sizeof(*ifi));
+ ifi = NLMSG_DATA(answer);
+ len = answer->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi));
if (len < 0) {
fprintf(stderr, "BUG: Invalid response to link query.\n");
return 0;
@@ -184,10 +180,7 @@ int name_is_vrf(const char *name)
.ifi_family = preferred_family,
},
};
- struct {
- struct nlmsghdr n;
- char buf[8192];
- } answer;
+ struct nlmsghdr *answer = NULL;
struct rtattr *tb[IFLA_MAX+1];
struct rtattr *li[IFLA_INFO_MAX+1];
struct ifinfomsg *ifi;
@@ -195,12 +188,11 @@ int name_is_vrf(const char *name)
addattr_l(&req.n, sizeof(req), IFLA_IFNAME, name, strlen(name) + 1);
- if (rtnl_talk_suppress_rtnl_errmsg(&rth, &req.n,
- &answer.n, sizeof(answer)) < 0)
+ if (rtnl_talk_suppress_rtnl_errmsg(&rth, &req.n, &answer) < 0)
return 0;
- ifi = NLMSG_DATA(&answer.n);
- len = answer.n.nlmsg_len - NLMSG_LENGTH(sizeof(*ifi));
+ ifi = NLMSG_DATA(answer);
+ len = answer->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi));
if (len < 0) {
fprintf(stderr, "BUG: Invalid response to link query.\n");
return 0;
diff --git a/ip/ipmacsec.c b/ip/ipmacsec.c
index aa89a00..9a2d0eb 100644
--- a/ip/ipmacsec.c
+++ b/ip/ipmacsec.c
@@ -421,7 +421,7 @@ static int do_modify_nl(enum cmd c, enum macsec_nl_commands cmd, int ifindex,
addattr_nest_end(&req.n, attr_sa);
talk:
- if (rtnl_talk(&genl_rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&genl_rth, &req.n, NULL) < 0)
return -2;
return 0;
diff --git a/ip/ipneigh.c b/ip/ipneigh.c
index 9c38a60..32f2d55 100644
--- a/ip/ipneigh.c
+++ b/ip/ipneigh.c
@@ -184,7 +184,7 @@ static int ipneigh_modify(int cmd, int flags, int argc, char **argv)
return -1;
}
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&rth, &req.n, NULL) < 0)
exit(2);
return 0;
diff --git a/ip/ipnetns.c b/ip/ipnetns.c
index afb4978..628dfb1 100644
--- a/ip/ipnetns.c
+++ b/ip/ipnetns.c
@@ -95,12 +95,13 @@ static int get_netnsid_from_name(const char *name)
struct nlmsghdr n;
struct rtgenmsg g;
char buf[1024];
- } answer, req = {
+ } req = {
.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct rtgenmsg)),
.n.nlmsg_flags = NLM_F_REQUEST,
.n.nlmsg_type = RTM_GETNSID,
.g.rtgen_family = AF_UNSPEC,
};
+ struct nlmsghdr *answer = NULL;
struct rtattr *tb[NETNSA_MAX + 1];
struct rtgenmsg *rthdr;
int len, fd;
@@ -110,18 +111,18 @@ static int get_netnsid_from_name(const char *name)
return fd;
addattr32(&req.n, 1024, NETNSA_FD, fd);
- if (rtnl_talk(&rtnsh, &req.n, &answer.n, sizeof(answer)) < 0) {
+ if (rtnl_talk(&rtnsh, &req.n, &answer) < 0) {
close(fd);
return -2;
}
close(fd);
/* Validate message and parse attributes */
- if (answer.n.nlmsg_type == NLMSG_ERROR)
+ if (answer->nlmsg_type == NLMSG_ERROR)
return -1;
- rthdr = NLMSG_DATA(&answer.n);
- len = answer.n.nlmsg_len - NLMSG_SPACE(sizeof(*rthdr));
+ rthdr = NLMSG_DATA(answer);
+ len = answer->nlmsg_len - NLMSG_SPACE(sizeof(*rthdr));
if (len < 0)
return -1;
@@ -689,7 +690,7 @@ static int set_netnsid_from_name(const char *name, int nsid)
addattr32(&req.n, 1024, NETNSA_FD, fd);
addattr32(&req.n, 1024, NETNSA_NSID, nsid);
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&rth, &req.n, NULL) < 0)
err = -2;
close(fd);
diff --git a/ip/ipntable.c b/ip/ipntable.c
index 88236ce..2f72c98 100644
--- a/ip/ipntable.c
+++ b/ip/ipntable.c
@@ -304,7 +304,7 @@ static int ipntable_modify(int cmd, int flags, int argc, char **argv)
RTA_PAYLOAD(parms_rta));
}
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&rth, &req.n, NULL) < 0)
exit(2);
return 0;
diff --git a/ip/iproute.c b/ip/iproute.c
index 83fd70c..aa929d9 100644
--- a/ip/iproute.c
+++ b/ip/iproute.c
@@ -1298,7 +1298,7 @@ static int iproute_modify(int cmd, unsigned int flags, int argc, char **argv)
if (!type_ok && req.r.rtm_family == AF_MPLS)
req.r.rtm_type = RTN_UNICAST;
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&rth, &req.n, NULL) < 0)
return -2;
return 0;
@@ -1678,6 +1678,7 @@ static int iproute_get(int argc, char **argv)
};
char *idev = NULL;
char *odev = NULL;
+ struct nlmsghdr *answer = NULL;
int connected = 0;
int fib_match = 0;
int from_ok = 0;
@@ -1798,20 +1799,20 @@ static int iproute_get(int argc, char **argv)
if (fib_match)
req.r.rtm_flags |= RTM_F_FIB_MATCH;
- if (rtnl_talk(&rth, &req.n, &req.n, sizeof(req)) < 0)
+ if (rtnl_talk(&rth, &req.n, &answer) < 0)
return -2;
if (connected && !from_ok) {
- struct rtmsg *r = NLMSG_DATA(&req.n);
- int len = req.n.nlmsg_len;
+ struct rtmsg *r = NLMSG_DATA(answer);
+ int len = answer->nlmsg_len;
struct rtattr *tb[RTA_MAX+1];
- if (print_route(NULL, &req.n, (void *)stdout) < 0) {
+ if (print_route(NULL, answer, (void *)stdout) < 0) {
fprintf(stderr, "An error :-)\n");
return -1;
}
- if (req.n.nlmsg_type != RTM_NEWROUTE) {
+ if (answer->nlmsg_type != RTM_NEWROUTE) {
fprintf(stderr, "Not a route?\n");
return -1;
}
@@ -1841,11 +1842,11 @@ static int iproute_get(int argc, char **argv)
req.n.nlmsg_flags = NLM_F_REQUEST;
req.n.nlmsg_type = RTM_GETROUTE;
- if (rtnl_talk(&rth, &req.n, &req.n, sizeof(req)) < 0)
+ if (rtnl_talk(&rth, &req.n, &answer) < 0)
return -2;
}
- if (print_route(NULL, &req.n, (void *)stdout) < 0) {
+ if (print_route(NULL, answer, (void *)stdout) < 0) {
fprintf(stderr, "An error :-)\n");
return -1;
}
@@ -1869,6 +1870,7 @@ static int restore_handler(const struct sockaddr_nl *nl,
struct rtattr *tb[RTA_MAX+1];
int len = n->nlmsg_len - NLMSG_LENGTH(sizeof(*r));
int ret, prio = *(int *)arg;
+ struct nlmsghdr *answer = NULL;
parse_rtattr(tb, RTA_MAX, RTM_RTA(r), len);
@@ -1893,7 +1895,7 @@ restore:
ll_init_map(&rth);
- ret = rtnl_talk(&rth, n, n, sizeof(*n));
+ ret = rtnl_talk(&rth, n, &answer);
if ((ret < 0) && (errno == EEXIST))
ret = 0;
diff --git a/ip/iprule.c b/ip/iprule.c
index 8313138..872cfd2 100644
--- a/ip/iprule.c
+++ b/ip/iprule.c
@@ -393,7 +393,7 @@ static int flush_rule(const struct sockaddr_nl *who, struct nlmsghdr *n,
if (rtnl_open(&rth2, 0) < 0)
return -1;
- if (rtnl_talk(&rth2, n, NULL, 0) < 0)
+ if (rtnl_talk(&rth2, n, NULL) < 0)
return -2;
rtnl_close(&rth2);
@@ -548,12 +548,13 @@ static int restore_handler(const struct sockaddr_nl *nl,
struct nlmsghdr *n, void *arg)
{
int ret;
+ struct nlmsghdr *answer = NULL;
n->nlmsg_flags |= NLM_F_REQUEST | NLM_F_CREATE | NLM_F_ACK;
ll_init_map(&rth);
- ret = rtnl_talk(&rth, n, n, sizeof(*n));
+ ret = rtnl_talk(&rth, n, &answer);
if ((ret < 0) && (errno == EEXIST))
ret = 0;
@@ -760,7 +761,7 @@ static int iprule_modify(int cmd, int argc, char **argv)
if (!table_ok && cmd == RTM_NEWRULE)
req.r.rtm_table = RT_TABLE_MAIN;
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&rth, &req.n, NULL) < 0)
return -2;
return 0;
diff --git a/ip/ipseg6.c b/ip/ipseg6.c
index a8f5c69..6d7b1d0 100644
--- a/ip/ipseg6.c
+++ b/ip/ipseg6.c
@@ -125,6 +125,7 @@ static int process_msg(const struct sockaddr_nl *who, struct nlmsghdr *n,
static int seg6_do_cmd(void)
{
SEG6_REQUEST(req, 1024, opts.cmd, NLM_F_REQUEST);
+ struct nlmsghdr *answer = NULL;
int repl = 0, dump = 0;
if (genl_family < 0) {
@@ -163,12 +164,12 @@ static int seg6_do_cmd(void)
}
if (!repl && !dump) {
- if (rtnl_talk(&grth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&grth, &req.n, NULL) < 0)
return -1;
} else if (repl) {
- if (rtnl_talk(&grth, &req.n, &req.n, sizeof(req)) < 0)
+ if (rtnl_talk(&grth, &req.n, &answer) < 0)
return -2;
- if (process_msg(NULL, &req.n, stdout) < 0) {
+ if (process_msg(NULL, answer, stdout) < 0) {
fprintf(stderr, "Error parsing reply\n");
exit(1);
}
diff --git a/ip/iptoken.c b/ip/iptoken.c
index 1869f76..0528bad 100644
--- a/ip/iptoken.c
+++ b/ip/iptoken.c
@@ -166,7 +166,7 @@ static int iptoken_set(int argc, char **argv, bool delete)
addattr_nest_end(&req.n, afs6);
addattr_nest_end(&req.n, afs);
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&rth, &req.n, NULL) < 0)
return -2;
return 0;
diff --git a/ip/link_gre.c b/ip/link_gre.c
index c2ec5f2..21131ab 100644
--- a/ip/link_gre.c
+++ b/ip/link_gre.c
@@ -75,6 +75,7 @@ static int gre_parse_opt(struct link_util *lu, int argc, char **argv,
.i.ifi_family = preferred_family,
.i.ifi_index = ifi->ifi_index,
};
+ struct nlmsghdr *answer = NULL;
struct rtattr *tb[IFLA_MAX + 1];
struct rtattr *linkinfo[IFLA_INFO_MAX+1];
struct rtattr *greinfo[IFLA_GRE_MAX + 1];
@@ -98,19 +99,19 @@ static int gre_parse_opt(struct link_util *lu, int argc, char **argv,
__u32 fwmark = 0;
if (!(n->nlmsg_flags & NLM_F_CREATE)) {
- if (rtnl_talk(&rth, &req.n, &req.n, sizeof(req)) < 0) {
+ if (rtnl_talk(&rth, &req.n, &answer) < 0) {
get_failed:
fprintf(stderr,
"Failed to get existing tunnel info.\n");
return -1;
}
- len = req.n.nlmsg_len;
+ len = answer->nlmsg_len;
len -= NLMSG_LENGTH(sizeof(*ifi));
if (len < 0)
goto get_failed;
- parse_rtattr(tb, IFLA_MAX, IFLA_RTA(&req.i), len);
+ parse_rtattr(tb, IFLA_MAX, IFLA_RTA(answer + sizeof(struct nlmsghdr)), len);
if (!tb[IFLA_LINKINFO])
goto get_failed;
diff --git a/ip/link_gre6.c b/ip/link_gre6.c
index 78b5215..98e689e 100644
--- a/ip/link_gre6.c
+++ b/ip/link_gre6.c
@@ -86,6 +86,7 @@ static int gre_parse_opt(struct link_util *lu, int argc, char **argv,
.i.ifi_family = preferred_family,
.i.ifi_index = ifi->ifi_index,
};
+ struct nlmsghdr *answer = NULL;
struct rtattr *tb[IFLA_MAX + 1];
struct rtattr *linkinfo[IFLA_INFO_MAX+1];
struct rtattr *greinfo[IFLA_GRE_MAX + 1];
@@ -108,19 +109,19 @@ static int gre_parse_opt(struct link_util *lu, int argc, char **argv,
__u32 fwmark = 0;
if (!(n->nlmsg_flags & NLM_F_CREATE)) {
- if (rtnl_talk(&rth, &req.n, &req.n, sizeof(req)) < 0) {
+ if (rtnl_talk(&rth, &req.n, &answer) < 0) {
get_failed:
fprintf(stderr,
"Failed to get existing tunnel info.\n");
return -1;
}
- len = req.n.nlmsg_len;
+ len = answer->nlmsg_len;
len -= NLMSG_LENGTH(sizeof(*ifi));
if (len < 0)
goto get_failed;
- parse_rtattr(tb, IFLA_MAX, IFLA_RTA(&req.i), len);
+ parse_rtattr(tb, IFLA_MAX, IFLA_RTA(NLMSG_DATA(answer)), len);
if (!tb[IFLA_LINKINFO])
goto get_failed;
diff --git a/ip/link_ip6tnl.c b/ip/link_ip6tnl.c
index 505fb47..19e0ca6 100644
--- a/ip/link_ip6tnl.c
+++ b/ip/link_ip6tnl.c
@@ -83,6 +83,7 @@ static int ip6tunnel_parse_opt(struct link_util *lu, int argc, char **argv,
.i.ifi_family = preferred_family,
.i.ifi_index = ifi->ifi_index,
};
+ struct nlmsghdr *answer = NULL;
struct rtattr *tb[IFLA_MAX + 1];
struct rtattr *linkinfo[IFLA_INFO_MAX+1];
struct rtattr *iptuninfo[IFLA_IPTUN_MAX + 1];
@@ -103,19 +104,19 @@ static int ip6tunnel_parse_opt(struct link_util *lu, int argc, char **argv,
__u32 fwmark = 0;
if (!(n->nlmsg_flags & NLM_F_CREATE)) {
- if (rtnl_talk(&rth, &req.n, &req.n, sizeof(req)) < 0) {
+ if (rtnl_talk(&rth, &req.n, &answer) < 0) {
get_failed:
fprintf(stderr,
"Failed to get existing tunnel info.\n");
return -1;
}
- len = req.n.nlmsg_len;
+ len = answer->nlmsg_len;
len -= NLMSG_LENGTH(sizeof(*ifi));
if (len < 0)
goto get_failed;
- parse_rtattr(tb, IFLA_MAX, IFLA_RTA(&req.i), len);
+ parse_rtattr(tb, IFLA_MAX, IFLA_RTA(NLMSG_DATA(answer)), len);
if (!tb[IFLA_LINKINFO])
goto get_failed;
diff --git a/ip/link_iptnl.c b/ip/link_iptnl.c
index d24e737..0ea957b 100644
--- a/ip/link_iptnl.c
+++ b/ip/link_iptnl.c
@@ -84,6 +84,7 @@ static int iptunnel_parse_opt(struct link_util *lu, int argc, char **argv,
.i.ifi_family = preferred_family,
.i.ifi_index = ifi->ifi_index,
};
+ struct nlmsghdr *answer = NULL;
struct rtattr *tb[IFLA_MAX + 1];
struct rtattr *linkinfo[IFLA_INFO_MAX+1];
struct rtattr *iptuninfo[IFLA_IPTUN_MAX + 1];
@@ -108,19 +109,19 @@ static int iptunnel_parse_opt(struct link_util *lu, int argc, char **argv,
__u32 fwmark = 0;
if (!(n->nlmsg_flags & NLM_F_CREATE)) {
- if (rtnl_talk(&rth, &req.n, &req.n, sizeof(req)) < 0) {
+ if (rtnl_talk(&rth, &req.n, &answer) < 0) {
get_failed:
fprintf(stderr,
"Failed to get existing tunnel info.\n");
return -1;
}
- len = req.n.nlmsg_len;
+ len = answer->nlmsg_len;
len -= NLMSG_LENGTH(sizeof(*ifi));
if (len < 0)
goto get_failed;
- parse_rtattr(tb, IFLA_MAX, IFLA_RTA(&req.i), len);
+ parse_rtattr(tb, IFLA_MAX, IFLA_RTA(NLMSG_DATA(answer)), len);
if (!tb[IFLA_LINKINFO])
goto get_failed;
diff --git a/ip/link_vti.c b/ip/link_vti.c
index 3ffecfa..de15b4a 100644
--- a/ip/link_vti.c
+++ b/ip/link_vti.c
@@ -61,6 +61,7 @@ static int vti_parse_opt(struct link_util *lu, int argc, char **argv,
.i.ifi_family = preferred_family,
.i.ifi_index = ifi->ifi_index,
};
+ struct nlmsghdr *answer = NULL;
struct rtattr *tb[IFLA_MAX + 1];
struct rtattr *linkinfo[IFLA_INFO_MAX+1];
struct rtattr *vtiinfo[IFLA_VTI_MAX + 1];
@@ -73,19 +74,19 @@ static int vti_parse_opt(struct link_util *lu, int argc, char **argv,
int len;
if (!(n->nlmsg_flags & NLM_F_CREATE)) {
- if (rtnl_talk(&rth, &req.n, &req.n, sizeof(req)) < 0) {
+ if (rtnl_talk(&rth, &req.n, &answer) < 0) {
get_failed:
fprintf(stderr,
"Failed to get existing tunnel info.\n");
return -1;
}
- len = req.n.nlmsg_len;
+ len = answer->nlmsg_len;
len -= NLMSG_LENGTH(sizeof(*ifi));
if (len < 0)
goto get_failed;
- parse_rtattr(tb, IFLA_MAX, IFLA_RTA(&req.i), len);
+ parse_rtattr(tb, IFLA_MAX, IFLA_RTA(NLMSG_DATA(answer)), len);
if (!tb[IFLA_LINKINFO])
goto get_failed;
diff --git a/ip/link_vti6.c b/ip/link_vti6.c
index 6ea1fc2..663ee03 100644
--- a/ip/link_vti6.c
+++ b/ip/link_vti6.c
@@ -56,6 +56,7 @@ static int vti6_parse_opt(struct link_util *lu, int argc, char **argv,
.i.ifi_family = preferred_family,
.i.ifi_index = ifi->ifi_index,
};
+ struct nlmsghdr *answer = NULL;
struct rtattr *tb[IFLA_MAX + 1];
struct rtattr *linkinfo[IFLA_INFO_MAX+1];
struct rtattr *vtiinfo[IFLA_VTI_MAX + 1];
@@ -68,19 +69,19 @@ static int vti6_parse_opt(struct link_util *lu, int argc, char **argv,
int len;
if (!(n->nlmsg_flags & NLM_F_CREATE)) {
- if (rtnl_talk(&rth, &req.n, &req.n, sizeof(req)) < 0) {
+ if (rtnl_talk(&rth, &req.n, &answer) < 0) {
get_failed:
fprintf(stderr,
"Failed to get existing tunnel info.\n");
return -1;
}
- len = req.n.nlmsg_len;
+ len = answer->nlmsg_len;
len -= NLMSG_LENGTH(sizeof(*ifi));
if (len < 0)
goto get_failed;
- parse_rtattr(tb, IFLA_MAX, IFLA_RTA(&req.i), len);
+ parse_rtattr(tb, IFLA_MAX, IFLA_RTA(NLMSG_DATA(answer)), len);
if (!tb[IFLA_LINKINFO])
goto get_failed;
diff --git a/ip/tcp_metrics.c b/ip/tcp_metrics.c
index 8972acd..547d791 100644
--- a/ip/tcp_metrics.c
+++ b/ip/tcp_metrics.c
@@ -306,6 +306,7 @@ static int process_msg(const struct sockaddr_nl *who, struct nlmsghdr *n,
static int tcpm_do_cmd(int cmd, int argc, char **argv)
{
TCPM_REQUEST(req, 1024, TCP_METRICS_CMD_GET, NLM_F_REQUEST);
+ struct nlmsghdr *answer = NULL;
int atype = -1, stype = -1;
int ack;
@@ -457,12 +458,12 @@ static int tcpm_do_cmd(int cmd, int argc, char **argv)
}
if (ack) {
- if (rtnl_talk(&grth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&grth, &req.n, NULL) < 0)
return -2;
} else if (atype >= 0) {
- if (rtnl_talk(&grth, &req.n, &req.n, sizeof(req)) < 0)
+ if (rtnl_talk(&grth, &req.n, &answer) < 0)
return -2;
- if (process_msg(NULL, &req.n, stdout) < 0) {
+ if (process_msg(NULL, answer, stdout) < 0) {
fprintf(stderr, "Dump terminated\n");
exit(1);
}
diff --git a/ip/xfrm_policy.c b/ip/xfrm_policy.c
index de689c4..c794779 100644
--- a/ip/xfrm_policy.c
+++ b/ip/xfrm_policy.c
@@ -386,7 +386,7 @@ static int xfrm_policy_modify(int cmd, unsigned int flags, int argc, char **argv
if (req.xpinfo.sel.family == AF_UNSPEC)
req.xpinfo.sel.family = AF_INET;
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&rth, &req.n, NULL) < 0)
exit(2);
rtnl_close(&rth);
@@ -548,7 +548,7 @@ int xfrm_policy_print(const struct sockaddr_nl *who, struct nlmsghdr *n,
}
static int xfrm_policy_get_or_delete(int argc, char **argv, int delete,
- void *res_nlbuf, size_t res_size)
+ struct nlmsghdr **answer)
{
struct rtnl_handle rth;
struct {
@@ -659,7 +659,7 @@ static int xfrm_policy_get_or_delete(int argc, char **argv, int delete,
(void *)&ctx, ctx.sctx.len);
}
- if (rtnl_talk(&rth, &req.n, res_nlbuf, res_size) < 0)
+ if (rtnl_talk(&rth, &req.n, answer) < 0)
exit(2);
rtnl_close(&rth);
@@ -669,15 +669,14 @@ static int xfrm_policy_get_or_delete(int argc, char **argv, int delete,
static int xfrm_policy_delete(int argc, char **argv)
{
- return xfrm_policy_get_or_delete(argc, argv, 1, NULL, 0);
+ return xfrm_policy_get_or_delete(argc, argv, 1, NULL);
}
static int xfrm_policy_get(int argc, char **argv)
{
- char buf[NLMSG_BUF_SIZE] = {};
- struct nlmsghdr *n = (struct nlmsghdr *)buf;
+ struct nlmsghdr *n = NULL;
- xfrm_policy_get_or_delete(argc, argv, 0, n, sizeof(buf));
+ xfrm_policy_get_or_delete(argc, argv, 0, &n);
if (xfrm_policy_print(NULL, n, (void *)stdout) < 0) {
fprintf(stderr, "An error :-)\n");
@@ -1049,7 +1048,7 @@ static int xfrm_spd_setinfo(int argc, char **argv)
if (rtnl_open_byproto(&rth, 0, NETLINK_XFRM) < 0)
exit(1);
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&rth, &req.n, NULL) < 0)
exit(2);
rtnl_close(&rth);
@@ -1070,14 +1069,15 @@ static int xfrm_spd_getinfo(int argc, char **argv)
.n.nlmsg_type = XFRM_MSG_GETSPDINFO,
.flags = 0XFFFFFFFF,
};
+ struct nlmsghdr *answer = NULL;
if (rtnl_open_byproto(&rth, 0, NETLINK_XFRM) < 0)
exit(1);
- if (rtnl_talk(&rth, &req.n, &req.n, sizeof(req)) < 0)
+ if (rtnl_talk(&rth, &req.n, &answer) < 0)
exit(2);
- print_spdinfo(&req.n, (void *)stdout);
+ print_spdinfo(answer, (void *)stdout);
rtnl_close(&rth);
@@ -1123,7 +1123,7 @@ static int xfrm_policy_flush(int argc, char **argv)
if (show_stats > 1)
fprintf(stderr, "Flush policy\n");
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&rth, &req.n, NULL) < 0)
exit(2);
rtnl_close(&rth);
diff --git a/ip/xfrm_state.c b/ip/xfrm_state.c
index 4483fb8..02d3efa 100644
--- a/ip/xfrm_state.c
+++ b/ip/xfrm_state.c
@@ -726,7 +726,7 @@ static int xfrm_state_modify(int cmd, unsigned int flags, int argc, char **argv)
if (req.xsinfo.family == AF_UNSPEC)
req.xsinfo.family = AF_INET;
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&rth, &req.n, NULL) < 0)
exit(2);
rtnl_close(&rth);
@@ -757,8 +757,7 @@ static int xfrm_state_allocspi(int argc, char **argv)
char *minp = NULL;
char *maxp = NULL;
struct xfrm_mark mark = {0, 0};
- char res_buf[NLMSG_BUF_SIZE] = {};
- struct nlmsghdr *res_n = (struct nlmsghdr *)res_buf;
+ struct nlmsghdr *answer = NULL;
while (argc > 0) {
if (strcmp(*argv, "mode") == 0) {
@@ -858,10 +857,10 @@ static int xfrm_state_allocspi(int argc, char **argv)
req.xspi.info.family = AF_INET;
- if (rtnl_talk(&rth, &req.n, res_n, sizeof(res_buf)) < 0)
+ if (rtnl_talk(&rth, &req.n, &answer) < 0)
exit(2);
- if (xfrm_state_print(NULL, res_n, (void *)stdout) < 0) {
+ if (xfrm_state_print(NULL, answer, (void *)stdout) < 0) {
fprintf(stderr, "An error :-)\n");
exit(1);
}
@@ -1046,16 +1045,15 @@ static int xfrm_state_get_or_delete(int argc, char **argv, int delete)
req.xsid.family = AF_INET;
if (delete) {
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&rth, &req.n, NULL) < 0)
exit(2);
} else {
- char buf[NLMSG_BUF_SIZE] = {};
- struct nlmsghdr *res_n = (struct nlmsghdr *)buf;
+ struct nlmsghdr *answer = NULL;
- if (rtnl_talk(&rth, &req.n, res_n, sizeof(req)) < 0)
+ if (rtnl_talk(&rth, &req.n, &answer) < 0)
exit(2);
- if (xfrm_state_print(NULL, res_n, (void *)stdout) < 0) {
+ if (xfrm_state_print(NULL, answer, (void *)stdout) < 0) {
fprintf(stderr, "An error :-)\n");
exit(1);
}
@@ -1321,14 +1319,15 @@ static int xfrm_sad_getinfo(int argc, char **argv)
.n.nlmsg_type = XFRM_MSG_GETSADINFO,
.flags = 0XFFFFFFFF,
};
+ struct nlmsghdr *answer = NULL;
if (rtnl_open_byproto(&rth, 0, NETLINK_XFRM) < 0)
exit(1);
- if (rtnl_talk(&rth, &req.n, &req.n, sizeof(req)) < 0)
+ if (rtnl_talk(&rth, &req.n, &answer) < 0)
exit(2);
- print_sadinfo(&req.n, (void *)stdout);
+ print_sadinfo(answer, (void *)stdout);
rtnl_close(&rth);
@@ -1376,7 +1375,7 @@ static int xfrm_state_flush(int argc, char **argv)
fprintf(stderr, "Flush state with XFRM-PROTO value \"%s\"\n",
strxf_xfrmproto(req.xsf.proto));
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&rth, &req.n, NULL) < 0)
exit(2);
rtnl_close(&rth);
diff --git a/lib/libgenl.c b/lib/libgenl.c
index 50d2d92..9994469 100644
--- a/lib/libgenl.c
+++ b/lib/libgenl.c
@@ -49,16 +49,17 @@ int genl_resolve_family(struct rtnl_handle *grth, const char *family)
{
GENL_REQUEST(req, 1024, GENL_ID_CTRL, 0, 0, CTRL_CMD_GETFAMILY,
NLM_F_REQUEST);
+ struct nlmsghdr *answer = NULL;
addattr_l(&req.n, sizeof(req), CTRL_ATTR_FAMILY_NAME,
family, strlen(family) + 1);
- if (rtnl_talk(grth, &req.n, &req.n, sizeof(req)) < 0) {
+ if (rtnl_talk(grth, &req.n, &answer) < 0) {
fprintf(stderr, "Error talking to the kernel\n");
return -2;
}
- return genl_parse_getfamily(&req.n);
+ return genl_parse_getfamily(answer);
}
int genl_init_handle(struct rtnl_handle *grth, const char *family,
diff --git a/lib/libnetlink.c b/lib/libnetlink.c
index 37cfb5a..ff986d4 100644
--- a/lib/libnetlink.c
+++ b/lib/libnetlink.c
@@ -568,7 +568,7 @@ static void rtnl_talk_error(struct nlmsghdr *h, struct nlmsgerr *err,
}
static int __rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n,
- struct nlmsghdr *answer, size_t maxlen,
+ struct nlmsghdr **answer,
bool show_rtnl_err, nl_ext_ack_fn_t errfn)
{
int status;
@@ -643,8 +643,7 @@ static int __rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n,
fprintf(stderr, "ERROR truncated\n");
} else if (!err->error) {
if (answer)
- memcpy(answer, h,
- MIN(maxlen, h->nlmsg_len));
+ *answer= h;
return 0;
}
@@ -657,8 +656,7 @@ static int __rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n,
}
if (answer) {
- memcpy(answer, h,
- MIN(maxlen, h->nlmsg_len));
+ *answer= h;
return 0;
}
@@ -681,22 +679,22 @@ static int __rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n,
}
int rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n,
- struct nlmsghdr *answer, size_t maxlen)
+ struct nlmsghdr **answer)
{
- return __rtnl_talk(rtnl, n, answer, maxlen, true, NULL);
+ return __rtnl_talk(rtnl, n, answer, true, NULL);
}
int rtnl_talk_extack(struct rtnl_handle *rtnl, struct nlmsghdr *n,
- struct nlmsghdr *answer, size_t maxlen,
+ struct nlmsghdr **answer,
nl_ext_ack_fn_t errfn)
{
- return __rtnl_talk(rtnl, n, answer, maxlen, true, errfn);
+ return __rtnl_talk(rtnl, n, answer, true, errfn);
}
int rtnl_talk_suppress_rtnl_errmsg(struct rtnl_handle *rtnl, struct nlmsghdr *n,
- struct nlmsghdr *answer, size_t maxlen)
+ struct nlmsghdr **answer)
{
- return __rtnl_talk(rtnl, n, answer, maxlen, false, NULL);
+ return __rtnl_talk(rtnl, n, answer, false, NULL);
}
int rtnl_listen_all_nsid(struct rtnl_handle *rth)
diff --git a/misc/ss.c b/misc/ss.c
index dd8dfaa..bf21d80 100644
--- a/misc/ss.c
+++ b/misc/ss.c
@@ -2597,7 +2597,7 @@ static int kill_inet_sock(struct nlmsghdr *h, void *arg, struct sockstat *s)
raw->sdiag_raw_protocol = s->raw_prot;
}
- return rtnl_talk(rth, &req.nlh, NULL, 0);
+ return rtnl_talk(rth, &req.nlh, NULL);
}
static int show_one_inet_sock(const struct sockaddr_nl *addr,
diff --git a/tc/m_action.c b/tc/m_action.c
index 6ebe85e..12e033b 100644
--- a/tc/m_action.c
+++ b/tc/m_action.c
@@ -507,14 +507,13 @@ static int tc_action_gd(int cmd, unsigned int flags, int *argc_p, char ***argv_p
req.n.nlmsg_seq = rth.dump = ++rth.seq;
if (cmd == RTM_GETACTION)
- ans = &req.n;
- if (rtnl_talk(&rth, &req.n, ans, MAX_MSG) < 0) {
+ if (rtnl_talk(&rth, &req.n, &ans) < 0) {
fprintf(stderr, "We have an error talking to the kernel\n");
return 1;
}
- if (ans && print_action(NULL, &req.n, (void *)stdout) < 0) {
+ if (ans && print_action(NULL, ans, (void *)stdout) < 0) {
fprintf(stderr, "Dump terminated\n");
return 1;
}
@@ -550,7 +549,7 @@ static int tc_action_modify(int cmd, unsigned int flags, int *argc_p, char ***ar
}
tail->rta_len = (void *) NLMSG_TAIL(&req.n) - (void *) tail;
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0) {
+ if (rtnl_talk(&rth, &req.n, NULL) < 0) {
fprintf(stderr, "We have an error talking to the kernel\n");
ret = -1;
}
@@ -617,7 +616,7 @@ static int tc_act_list_or_flush(int argc, char **argv, int event)
req.n.nlmsg_type = RTM_DELACTION;
req.n.nlmsg_flags |= NLM_F_ROOT;
req.n.nlmsg_flags |= NLM_F_REQUEST;
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0) {
+ if (rtnl_talk(&rth, &req.n, NULL) < 0) {
fprintf(stderr, "We have an error flushing\n");
return 1;
}
diff --git a/tc/tc_class.c b/tc/tc_class.c
index 1a1f1fa..0214775 100644
--- a/tc/tc_class.c
+++ b/tc/tc_class.c
@@ -149,7 +149,7 @@ static int tc_class_modify(int cmd, unsigned int flags, int argc, char **argv)
}
}
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&rth, &req.n, NULL) < 0)
return 2;
return 0;
diff --git a/tc/tc_filter.c b/tc/tc_filter.c
index cf290ae..c43d1b2 100644
--- a/tc/tc_filter.c
+++ b/tc/tc_filter.c
@@ -194,7 +194,7 @@ static int tc_filter_modify(int cmd, unsigned int flags, int argc, char **argv)
}
}
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0) {
+ if (rtnl_talk(&rth, &req.n, NULL) < 0) {
fprintf(stderr, "We have an error talking to the kernel\n");
return 2;
}
@@ -331,6 +331,7 @@ static int tc_filter_get(int cmd, unsigned int flags, int argc, char **argv)
.t.tcm_parent = TC_H_UNSPEC,
.t.tcm_family = AF_UNSPEC,
};
+ struct nlmsghdr *answer = NULL;
struct filter_util *q = NULL;
__u32 prio = 0;
__u32 protocol = 0;
@@ -484,12 +485,12 @@ static int tc_filter_get(int cmd, unsigned int flags, int argc, char **argv)
return -1;
}
- if (rtnl_talk(&rth, &req.n, &req.n, MAX_MSG) < 0) {
+ if (rtnl_talk(&rth, &req.n, &answer) < 0) {
fprintf(stderr, "We have an error talking to the kernel\n");
return 2;
}
- print_filter(NULL, &req.n, (void *)stdout);
+ print_filter(NULL, answer, (void *)stdout);
return 0;
}
diff --git a/tc/tc_qdisc.c b/tc/tc_qdisc.c
index 1e9d909..c52114a 100644
--- a/tc/tc_qdisc.c
+++ b/tc/tc_qdisc.c
@@ -190,7 +190,7 @@ static int tc_qdisc_modify(int cmd, unsigned int flags, int argc, char **argv)
req.t.tcm_ifindex = idx;
}
- if (rtnl_talk(&rth, &req.n, NULL, 0) < 0)
+ if (rtnl_talk(&rth, &req.n, NULL) < 0)
return 2;
return 0;
--
2.5.5
^ permalink raw reply related
* [PATCH net] net: qualcomm: rmnet: Fix a double free
From: Dan Carpenter @ 2017-09-08 10:23 UTC (permalink / raw)
To: Subash Abhinov Kasiviswanathan; +Cc: David S. Miller, netdev, kernel-janitors
This is called from rmnet_map_ingress_handler(). When the
rmnet_map_deaggregate() returns NULL then the caller calls
consume_skb(skb) which frees the skb. The kfree_skb() on this error
path leads to a double free.
Fixes: ceed73a2cf4a ("drivers: net: ethernet: qualcomm: rmnet: Initial implementation")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
---
This is from static analysis and not tested.
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c
index 557c9bf1a469..0335fce54201 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_data.c
@@ -95,10 +95,8 @@ struct sk_buff *rmnet_map_deaggregate(struct sk_buff *skb)
skb_pull(skb, packet_len);
/* Some hardware can send us empty frames. Catch them */
- if (ntohs(maph->pkt_len) == 0) {
- kfree_skb(skb);
+ if (ntohs(maph->pkt_len) == 0)
return NULL;
- }
return skbn;
}
^ permalink raw reply related
* [PATCH v2] rtl8xxxu: Don't printk raw binary if serial number is not burned in.
From: Adam Borowski @ 2017-09-08 10:30 UTC (permalink / raw)
To: Jes Sorensen, Kalle Valo, linux-wireless-u79uwXL29TY76Z2rM5mHXA,
netdev-u79uwXL29TY76Z2rM5mHXA, Stefano Brivio
Cc: Adam Borowski
In-Reply-To: <20170908032706.1fa59da9@elisabeth>
I assume that a blank efuse comes with all ones, thus I did not bother
recognizing other possible junk values. This matches 100% of dongles
I've seen (a single Gembird 8192eu).
Signed-off-by: Adam Borowski <kilobyte-b9QjgO8OEXPVItvQsEIGlw@public.gmane.org>
---
v2: strncmp("goofy string") -> memchr_inv()
Stefano Brivio wrote:
> You might want to use memchr_inv():
>
> if (memchr_inv(efuse->serial, 0xff, 11))
> dev_info(&priv->udev->dev, "Serial: %.11s\n", efuse->serial);
> ...
>
> Mostly cosmetic though.
This looks much better, thanks!
drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c
index 80fee699f58a..38b2ba1ac6f8 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/rtl8xxxu_8192e.c
@@ -614,7 +614,10 @@ static int rtl8192eu_parse_efuse(struct rtl8xxxu_priv *priv)
dev_info(&priv->udev->dev, "Vendor: %.7s\n", efuse->vendor_name);
dev_info(&priv->udev->dev, "Product: %.11s\n", efuse->device_name);
- dev_info(&priv->udev->dev, "Serial: %.11s\n", efuse->serial);
+ if (memchr_inv(efuse->serial, 0xff, 11))
+ dev_info(&priv->udev->dev, "Serial: %.11s\n", efuse->serial);
+ else
+ dev_info(&priv->udev->dev, "Serial not available.\n");
if (rtl8xxxu_debug & RTL8XXXU_DEBUG_EFUSE) {
unsigned char *raw = priv->efuse_wifi.raw;
--
2.14.1
^ permalink raw reply related
* [PATCH net] phy: mvebu-cp110: checking for NULL instead of IS_ERR()
From: Dan Carpenter @ 2017-09-08 10:31 UTC (permalink / raw)
To: Kishon Vijay Abraham I, Antoine Tenart
Cc: netdev, kernel-janitors, linux-kernel, David S. Miller
devm_ioremap_resource() never returns NULL, it only returns error
pointers so this test needs to be changed.
Fixes: d0438bd6aa09 ("phy: add the mvebu cp110 comphy driver")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
---
This driver apparently is going through the net tree, but netdev isn't
listed as handling it in MAINTAINERS. Kishon, do you know what's up
with that?
diff --git a/drivers/phy/marvell/phy-mvebu-cp110-comphy.c b/drivers/phy/marvell/phy-mvebu-cp110-comphy.c
index 73ebad6634a7..24578bd68ddc 100644
--- a/drivers/phy/marvell/phy-mvebu-cp110-comphy.c
+++ b/drivers/phy/marvell/phy-mvebu-cp110-comphy.c
@@ -576,8 +576,8 @@ static int mvebu_comphy_probe(struct platform_device *pdev)
return PTR_ERR(priv->regmap);
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
priv->base = devm_ioremap_resource(&pdev->dev, res);
- if (!priv->base)
- return -ENOMEM;
+ if (IS_ERR(priv->base))
+ return PTR_ERR(priv->base);
for_each_available_child_of_node(pdev->dev.of_node, child) {
struct mvebu_comphy_lane *lane;
^ permalink raw reply related
* Re: [PATCH net] bpf: don't select potentially stale ri->map from buggy xdp progs
From: Daniel Borkmann @ 2017-09-08 10:34 UTC (permalink / raw)
To: Jesper Dangaard Brouer; +Cc: davem, ast, john.fastabend, andy, netdev
In-Reply-To: <20170908070610.4b8e1df1@redhat.com>
On 09/08/2017 07:06 AM, Jesper Dangaard Brouer wrote:
> On Fri, 8 Sep 2017 00:14:51 +0200
> Daniel Borkmann <daniel@iogearbox.net> wrote:
>
>> + /* This is really only caused by a deliberately crappy
>> + * BPF program, normally we would never hit that case,
>> + * so no need to inform someone via tracepoints either,
>> + * just bail out.
>> + */
>> + if (unlikely(map_owner != xdp_prog))
>> + return -EINVAL;
>
> IMHO we do need to call the tracepoint here. It is not just crappy
> BPF-progs that cause this situation, it is also drivers not implementing
> XDP_REDIRECT yet (which is all but ixgbe). Due to the level XDP
> operates at, tracepoints are the only way users can runtime troubleshoot
> their XDP programs.
Drivers not implementing XDP_REDIRECT don't even get there in
the first place. What they will do is to hit the 'default' case
when they check for the action code from the BPF program. Then
call into bpf_warn_invalid_xdp_action(act), and fall-through
to hit the tracepoint at trace_xdp_exception() which is also
triggered by XDP_ABORTED usually. So when that happens we do
complain loudly and call a tracepoint already. We should probably
tweak the bpf_warn_invalid_xdp_action() message a little to make
it clear that the action could also just be unsupported by the
driver instead of being illegal.
^ permalink raw reply
* Re: [V2 PATCH net-next 1/2] xdp: implement xdp_redirect_map for generic XDP
From: Daniel Borkmann @ 2017-09-08 10:41 UTC (permalink / raw)
To: Jesper Dangaard Brouer
Cc: netdev, David S. Miller, Daniel Borkmann, John Fastabend,
Andy Gospodarek, alexei.starovoitov
In-Reply-To: <20170908103601.21cdecb2@redhat.com>
On 09/08/2017 10:36 AM, Jesper Dangaard Brouer wrote:
> On Thu, 07 Sep 2017 16:09:56 +0200
> Daniel Borkmann <daniel@iogearbox.net> wrote:
>> On 09/07/2017 02:33 PM, Jesper Dangaard Brouer wrote:
>>> Using bpf_redirect_map is allowed for generic XDP programs, but the
>>> appropriate map lookup was never performed in xdp_do_generic_redirect().
>>>
>>> Instead the map-index is directly used as the ifindex. For the
>>> xdp_redirect_map sample in SKB-mode '-S', this resulted in trying
>>> sending on ifindex 0 which isn't valid, resulting in getting SKB
>>> packets dropped. Thus, the reported performance numbers are wrong in
>>> commit 24251c264798 ("samples/bpf: add option for native and skb mode
>>> for redirect apps") for the 'xdp_redirect_map -S' case.
>>>
>>> It might seem innocent this was lacking, but it can actually crash the
>>> kernel. The potential crash is caused by not consuming redirect_info->map.
>>> The bpf_redirect_map helper will set this_cpu_ptr(&redirect_info)->map
>>> pointer, which will survive even after unloading the xdp bpf_prog and
>>> deallocating the devmap data-structure. This leaves a dead map
>>> pointer around. The kernel will crash when loading the xdp_redirect
>>> sample (in native XDP mode) as it doesn't reset map (via bpf_redirect)
>>> and returns XDP_REDIRECT, which will cause it to dereference the map
>>> pointer.
>>>
>>> Fixes: 6103aa96ec07 ("net: implement XDP_REDIRECT for xdp generic")
>>> Fixes: 24251c264798 ("samples/bpf: add option for native and skb mode for redirect apps")
>>> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
>>> ---
>>> include/trace/events/xdp.h | 4 ++--
>>> net/core/filter.c | 14 +++++++++++---
>>> 2 files changed, 13 insertions(+), 5 deletions(-)
>>>
>>> diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h
>>> index 862575ac8da9..4e16c43fba10 100644
>>> --- a/include/trace/events/xdp.h
>>> +++ b/include/trace/events/xdp.h
>>> @@ -138,11 +138,11 @@ DEFINE_EVENT_PRINT(xdp_redirect_template, xdp_redirect_map_err,
>>>
>>> #define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx) \
>>> trace_xdp_redirect_map(dev, xdp, fwd ? fwd->ifindex : 0, \
>>> - 0, map, idx);
>>> + 0, map, idx)
>>>
>>> #define _trace_xdp_redirect_map_err(dev, xdp, fwd, map, idx, err) \
>>> trace_xdp_redirect_map_err(dev, xdp, fwd ? fwd->ifindex : 0, \
>>> - err, map, idx);
>>> + err, map, idx)
>>>
>>> #endif /* _TRACE_XDP_H */
>>>
>>> diff --git a/net/core/filter.c b/net/core/filter.c
>>> index 5912c738a7b2..3767470cab6c 100644
>>> --- a/net/core/filter.c
>>> +++ b/net/core/filter.c
>>> @@ -2566,13 +2566,19 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
>>> struct bpf_prog *xdp_prog)
>>> {
>>> struct redirect_info *ri = this_cpu_ptr(&redirect_info);
>>> + struct bpf_map *map = ri->map;
>>> u32 index = ri->ifindex;
>>> struct net_device *fwd;
>>> unsigned int len;
>>> int err = 0;
>>>
>>> - fwd = dev_get_by_index_rcu(dev_net(dev), index);
>>> ri->ifindex = 0;
>>> + ri->map = NULL;
>>> +
>>> + if (map)
>>> + fwd = __dev_map_lookup_elem(map, index);
>>> + else
>>> + fwd = dev_get_by_index_rcu(dev_net(dev), index);
>>> if (unlikely(!fwd)) {
>>> err = -EINVAL;
>>> goto err;
>>> @@ -2590,10 +2596,12 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
>>> }
>>>
>>> skb->dev = fwd;
>>
>> Looks much better above, thanks!
>>
>>> - _trace_xdp_redirect(dev, xdp_prog, index);
>>> + map ? _trace_xdp_redirect_map(dev, xdp_prog, fwd, map, index)
>>> + : _trace_xdp_redirect(dev, xdp_prog, index);
>>
>> Could we rather make this in a way such that when the two
>> tracepoints are disabled and thus patched out, that we can
>> also omit the extra conditional which has no purpose then?
>
> First of all I don't think it make much of a difference, I measured the
> impact of the full patch to "cost" 1.62 nanosec (which is arguably
> below the accuracy level of the system under test)
>
> Secondly, I plan to optimize the map case for generic XDP later, where
> I would naturally split this into two functions (as V1, and as
> native-XDP), thus this extra conditional would go away. As I've shown
> offlist (to you, John and Andy) I demonstrated a 24% speedup via a
> xmit_more hack for generic XDP.
Okay, that would be nice indeed to have xmit_more support for
generic XDP as well. If this is going to be split off anyway
later on as in xdp_do_redirect() case, then:
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
^ permalink raw reply
* Re: [PATCH iproute2 1/2] lib/libnetlink: re malloc buff if size is not enough
From: Phil Sutter @ 2017-09-08 11:02 UTC (permalink / raw)
To: Hangbin Liu; +Cc: netdev, Stephen Hemminger, Michal Kubecek
In-Reply-To: <1504865697-27274-2-git-send-email-liuhangbin@gmail.com>
Hi Hangbin,
On Fri, Sep 08, 2017 at 06:14:56PM +0800, Hangbin Liu wrote:
[...]
> diff --git a/lib/libnetlink.c b/lib/libnetlink.c
> index be7ac86..37cfb5a 100644
> --- a/lib/libnetlink.c
> +++ b/lib/libnetlink.c
> @@ -402,6 +402,59 @@ static void rtnl_dump_error(const struct rtnl_handle *rth,
> }
> }
>
> +static int rtnl_recvmsg(int fd, struct msghdr *msg, char **buf)
> +{
> + struct iovec *iov;
> + int len = -1, buf_len = 32768;
> + char *buffer = *buf;
Isn't it possible to make 'buffer' static instead of the two 'buf'
variables in rtnl_dump_filter_l() and __rtnl_talk()? Then we would have
only a single buffer which is shared between both functions instead of
two which are independently allocated.
> +
> + int flag = MSG_PEEK | MSG_TRUNC;
> +
> + if (buffer == NULL)
> +re_malloc:
> + buffer = malloc(buf_len);
I think using realloc() here is more appropriate since there is no need
to free the buffer in beforehand and calling realloc(NULL, len) is
equivalent to calling malloc(len). I think 'realloc' is also a better
name for the goto label.
> + if (buffer == NULL) {
> + fprintf(stderr, "malloc error: no enough buffer\n");
Minor typo here: s/no/not/
> + return -1;
Return -ENOMEM?
> + }
> +
> + iov = msg->msg_iov;
> + iov->iov_base = buffer;
> + iov->iov_len = buf_len;
> +
> +re_recv:
Just call this 'recv'? (Not really important though.)
> + len = recvmsg(fd, msg, flag);
> +
> + if (len < 0) {
> + if (errno == EINTR || errno == EAGAIN)
> + return 0;
Instead of returning 0 (which makes callers retry), goto re_recv?
> + fprintf(stderr, "netlink receive error %s (%d)\n",
> + strerror(errno), errno);
> + return len;
> + }
> +
> + if (len == 0) {
> + fprintf(stderr, "EOF on netlink\n");
> + return -1;
Return -ENODATA here? (Initially I though about -EOF, but EOF is -1 so
that would be incorrect).
> + }
> +
> + if (len > buf_len) {
> + free(buffer);
If you use realloc() above, this can be dropped.
> + buf_len = len;
For this to work you have to make buf_len static too, otherwise you will
unnecessarily reallocate the buffer. Oh, and that also requires the
single buffer (as pointed out above) because you will otherwise use a
common buf_len for both static buffers passed to this function.
> + flag = 0;
> + goto re_malloc;
> + }
> +
> + if (flag != 0) {
> + flag = 0;
> + goto re_recv;
> + }
> +
> + *buf = buffer;
> + return len;
> +}
> +
> int rtnl_dump_filter_l(struct rtnl_handle *rth,
> const struct rtnl_dump_filter_arg *arg)
> {
> @@ -413,31 +466,20 @@ int rtnl_dump_filter_l(struct rtnl_handle *rth,
> .msg_iov = &iov,
> .msg_iovlen = 1,
> };
> - char buf[32768];
> + static char *buf = NULL;
If you keep the static buffer in rtnl_recvmsg(), there is no need to
assign NULL here.
> int dump_intr = 0;
>
> - iov.iov_base = buf;
> while (1) {
> int status;
> const struct rtnl_dump_filter_arg *a;
> int found_done = 0;
> int msglen = 0;
>
> - iov.iov_len = sizeof(buf);
> - status = recvmsg(rth->fd, &msg, 0);
> -
> - if (status < 0) {
> - if (errno == EINTR || errno == EAGAIN)
> - continue;
> - fprintf(stderr, "netlink receive error %s (%d)\n",
> - strerror(errno), errno);
> - return -1;
> - }
> -
> - if (status == 0) {
> - fprintf(stderr, "EOF on netlink\n");
> - return -1;
> - }
> + status = rtnl_recvmsg(rth->fd, &msg, &buf);
> + if (status < 0)
> + return status;
> + else if (status == 0)
> + continue;
When retrying inside rtnl_recvmsg(), it won't return 0 anymore. I
believe the whole 'while (1)' loop could go away then.
Everything noted for rtnl_dump_filter_l() applies to __rtnl_talk() as
well.
Thanks, Phil
^ permalink raw reply
* Re: [PATCH iproute2 2/2] lib/libnetlink: update rtnl_talk to support malloc buff at run time
From: Phil Sutter @ 2017-09-08 11:06 UTC (permalink / raw)
To: Hangbin Liu; +Cc: netdev, Stephen Hemminger, Michal Kubecek
In-Reply-To: <1504865697-27274-3-git-send-email-liuhangbin@gmail.com>
Hi Hangbin,
On Fri, Sep 08, 2017 at 06:14:57PM +0800, Hangbin Liu wrote:
[...]
> diff --git a/genl/ctrl.c b/genl/ctrl.c
> index 448988e..699657b 100644
> --- a/genl/ctrl.c
> +++ b/genl/ctrl.c
> @@ -55,6 +55,7 @@ int genl_ctrl_resolve_family(const char *family)
> };
> struct nlmsghdr *nlh = &req.n;
> struct genlmsghdr *ghdr = &req.g;
> + struct nlmsghdr *answer = NULL;
I don't think it's necessary to assign NULL here or in any of the other
cases.
> if (rtnl_open_byproto(&rth, 0, NETLINK_GENERIC) < 0) {
> fprintf(stderr, "Cannot open generic netlink socket\n");
> @@ -63,19 +64,19 @@ int genl_ctrl_resolve_family(const char *family)
>
> addattr_l(nlh, 128, CTRL_ATTR_FAMILY_NAME, family, strlen(family) + 1);
>
> - if (rtnl_talk(&rth, nlh, nlh, sizeof(req)) < 0) {
> + if (rtnl_talk(&rth, nlh, &answer) < 0) {
I didn't check, but it's likely that at least in some cases 'nlh'
contains some buffer space to hold the answer (if it will be larger than
the input). If so, this could be dropped since the buffer is no longer
reused.
Apart from that, looks good to me!
Thanks, Phil
^ permalink raw reply
* Re: [PATCH net 0/2] netfilter: ipvs: some fixes in sctp_conn_schedule
From: Pablo Neira Ayuso @ 2017-09-08 11:40 UTC (permalink / raw)
To: Simon Horman
Cc: Xin Long, netfilter-devel, Alex Gartrell, lvs-devel, netdev, ja,
wensong
In-Reply-To: <20170831115904.GA16979@verge.net.au>
On Thu, Aug 31, 2017 at 01:59:08PM +0200, Simon Horman wrote:
> On Mon, Aug 28, 2017 at 06:17:32PM +0200, Pablo Neira Ayuso wrote:
> > On Sun, Aug 20, 2017 at 01:38:06PM +0800, Xin Long wrote:
> > > Patch 1/2 fixes the regression introduced by commit 5e26b1b3abce.
> > > Patch 2/2 makes ipvs not create conn for sctp ABORT packet.
> >
> > Will wait for Julian and Simon to tell me what I should do with this.
>
> Hi Pablo,
>
> could you take these directly with Julian's Ack and the following?
>
> Signed-off-by: Simon Horman <horms@verge.net.au>
Series applied, thanks!
^ permalink raw reply
* Re: [PATCH] netfilter: nat: constify rhashtable_params
From: Pablo Neira Ayuso @ 2017-09-08 11:46 UTC (permalink / raw)
To: Arvind Yadav
Cc: davem, fw, kadlec, linux-kernel, netdev, coreteam,
netfilter-devel
In-Reply-To: <d978194ca83e9aa41a330a42442eecd8be9e9a60.1504093452.git.arvind.yadav.cs@gmail.com>
On Wed, Aug 30, 2017 at 05:18:04PM +0530, Arvind Yadav wrote:
> rhashtable_params are not supposed to change at runtime. All
> Functions rhashtable_* working with const rhashtable_params
> provided by <linux/rhashtable.h>. So mark the non-const structs
> as const.
Applied to nf, thanks.
^ permalink raw reply
* Re: [PATCH net] bpf: don't select potentially stale ri->map from buggy xdp progs
From: Jesper Dangaard Brouer @ 2017-09-08 11:52 UTC (permalink / raw)
To: Daniel Borkmann, andy; +Cc: davem, ast, john.fastabend, netdev, brouer
In-Reply-To: <59B27234.4050703@iogearbox.net>
On Fri, 08 Sep 2017 12:34:28 +0200 Daniel Borkmann <daniel@iogearbox.net> wrote:
> On 09/08/2017 07:06 AM, Jesper Dangaard Brouer wrote:
> > On Fri, 8 Sep 2017 00:14:51 +0200
> > Daniel Borkmann <daniel@iogearbox.net> wrote:
> >
> >> + /* This is really only caused by a deliberately crappy
> >> + * BPF program, normally we would never hit that case,
> >> + * so no need to inform someone via tracepoints either,
> >> + * just bail out.
> >> + */
> >> + if (unlikely(map_owner != xdp_prog))
> >> + return -EINVAL;
> >
> > IMHO we do need to call the tracepoint here. It is not just crappy
> > BPF-progs that cause this situation, it is also drivers not implementing
> > XDP_REDIRECT yet (which is all but ixgbe). Due to the level XDP
> > operates at, tracepoints are the only way users can runtime troubleshoot
> > their XDP programs.
>
> Drivers not implementing XDP_REDIRECT don't even get there in
> the first place. What they will do is to hit the 'default' case
> when they check for the action code from the BPF program. Then
> call into bpf_warn_invalid_xdp_action(act), and fall-through
> to hit the tracepoint at trace_xdp_exception() which is also
> triggered by XDP_ABORTED usually. So when that happens we do
> complain loudly and call a tracepoint already. We should probably
> tweak the bpf_warn_invalid_xdp_action() message a little to make
> it clear that the action could also just be unsupported by the
> driver instead of being illegal.
Yes. drivers not implementing XDP_REDIRECT will cause a tracepoint
trace_xdp_exception() to be called for its _own_ packets.
But it will still setup and leave map and map_owner pointer dangling.
Another NIC can load an xdp_prog that return XDP_REDIRECT, which will hit
above if-statement, and its packets will disappear, without getting
recorded by a tracepoint (thus hard to debug!).
The fundamental point is that tracepoints is the way we choose to
handle debugging XDP programs. Thus, we must trigger a tracepoint when
a packet gets dropped. Even in this unlikely case.
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
LinkedIn: http://www.linkedin.com/in/brouer
^ permalink raw reply
* Re: [PATCH] net:netfilter alloc xt_byteslimit_htable with wrong size
From: Pablo Neira Ayuso @ 2017-09-08 11:58 UTC (permalink / raw)
To: zhizhou.tian
Cc: kadlec, fw, davem, netfilter-devel, coreteam, netdev,
linux-kernel
In-Reply-To: <1504839616-14519-1-git-send-email-zhizhou.tian@gmail.com>
On Fri, Sep 08, 2017 at 11:00:16AM +0800, zhizhou.tian@gmail.com wrote:
> From: Zhizhou Tian <zhizhou.tian@gmail.com>
>
> struct xt_byteslimit_htable used hlist_head,
> but alloc memory with sizeof(struct list_head)
Applied, thanks.
For the record, I have mangled the patch titled to:
netfilter: xt_hashlimit: alloc hashtable with right size
^ permalink raw reply
* Re: [PATCH iproute2 0/2] malloc correct buff at run time
From: Michal Kubecek @ 2017-09-08 12:03 UTC (permalink / raw)
To: Hangbin Liu; +Cc: netdev, Stephen Hemminger, Phil Sutter
In-Reply-To: <1504865697-27274-1-git-send-email-liuhangbin@gmail.com>
On Fri, Sep 08, 2017 at 06:14:55PM +0800, Hangbin Liu wrote:
> With commit 72b365e8e0fd ("libnetlink: Double the dump buffer size") and
> 460c03f3f3cc ("iplink: double the buffer size also in iplink_get()"), we
> extend the buffer size to avoid truncated message with large numbers of
> VFs. But just as Michal said, this is not future-proof since the NIC
> number is increasing. We have customer even has 220+ VFs now.
This sounds like the moment we hit the bigger problem with
IFLA_VFINFO_LIST is closer than I thought. The info block for one VF is
already 236 bytes long (or was in 4.4) so that 278 VFs would be over the
natural limit for IFLA_VFINFO_LIST attribute given by 16-bit nla_len
field.
> This is not make sense to hard code the buffer and increase it all the time.
> So let's just malloc the correct buff size at run time.
>
> I'm not sure what init size would be suitable, so I keep use the original
> size. I have tried with a small size like 1024, and it also works.
I don't think it's that important as the command usually runs only for
short time so allocating a 32KB buffer even if we could do with less is
not a big issue. (I didn't really like the idea of a 32KB buffer on
stack but with malloc() it's OK, I would say.)
Michal Kubecek
^ permalink raw reply
* [PATCH 1/1] forcedeth: remove tx_stop variable
From: Zhu Yanjun @ 2017-09-08 12:28 UTC (permalink / raw)
To: davem, netdev
The variable tx_stop is used to indicate the tx queue state: started
or stopped. In fact, the inline function netif_queue_stopped can do
the same work. So replace the variable tx_stop with the
function netif_queue_stopped.
Signed-off-by: Zhu Yanjun <yanjun.zhu@oracle.com>
---
drivers/net/ethernet/nvidia/forcedeth.c | 13 ++++---------
1 file changed, 4 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c
index 994a83a..e6e0de4 100644
--- a/drivers/net/ethernet/nvidia/forcedeth.c
+++ b/drivers/net/ethernet/nvidia/forcedeth.c
@@ -834,7 +834,6 @@ struct fe_priv {
u32 tx_pkts_in_progress;
struct nv_skb_map *tx_change_owner;
struct nv_skb_map *tx_end_flip;
- int tx_stop;
/* TX software stats */
struct u64_stats_sync swstats_tx_syncp;
@@ -1939,7 +1938,6 @@ static void nv_init_tx(struct net_device *dev)
np->tx_pkts_in_progress = 0;
np->tx_change_owner = NULL;
np->tx_end_flip = NULL;
- np->tx_stop = 0;
for (i = 0; i < np->tx_ring_size; i++) {
if (!nv_optimized(np)) {
@@ -2211,7 +2209,6 @@ static netdev_tx_t nv_start_xmit(struct sk_buff *skb, struct net_device *dev)
empty_slots = nv_get_empty_tx_slots(np);
if (unlikely(empty_slots <= entries)) {
netif_stop_queue(dev);
- np->tx_stop = 1;
spin_unlock_irqrestore(&np->lock, flags);
return NETDEV_TX_BUSY;
}
@@ -2359,7 +2356,6 @@ static netdev_tx_t nv_start_xmit_optimized(struct sk_buff *skb,
empty_slots = nv_get_empty_tx_slots(np);
if (unlikely(empty_slots <= entries)) {
netif_stop_queue(dev);
- np->tx_stop = 1;
spin_unlock_irqrestore(&np->lock, flags);
return NETDEV_TX_BUSY;
}
@@ -2583,8 +2579,8 @@ static int nv_tx_done(struct net_device *dev, int limit)
netdev_completed_queue(np->dev, tx_work, bytes_compl);
- if (unlikely((np->tx_stop == 1) && (np->get_tx.orig != orig_get_tx))) {
- np->tx_stop = 0;
+ if (unlikely(netif_queue_stopped(dev) &&
+ (np->get_tx.orig != orig_get_tx))) {
netif_wake_queue(dev);
}
return tx_work;
@@ -2637,8 +2633,8 @@ static int nv_tx_done_optimized(struct net_device *dev, int limit)
netdev_completed_queue(np->dev, tx_work, bytes_cleaned);
- if (unlikely((np->tx_stop == 1) && (np->get_tx.ex != orig_get_tx))) {
- np->tx_stop = 0;
+ if (unlikely(netif_queue_stopped(dev) &&
+ (np->get_tx.ex != orig_get_tx))) {
netif_wake_queue(dev);
}
return tx_work;
@@ -2724,7 +2720,6 @@ static void nv_tx_timeout(struct net_device *dev)
/* 2) complete any outstanding tx and do not give HW any limited tx pkts */
saved_tx_limit = np->tx_limit;
np->tx_limit = 0; /* prevent giving HW any limited pkts */
- np->tx_stop = 0; /* prevent waking tx queue */
if (!nv_optimized(np))
nv_tx_done(dev, np->tx_ring_size);
else
--
2.7.4
^ permalink raw reply related
* Re: [PATCH iproute2 1/2] lib/libnetlink: re malloc buff if size is not enough
From: Michal Kubecek @ 2017-09-08 12:32 UTC (permalink / raw)
To: Phil Sutter, Hangbin Liu, netdev, Stephen Hemminger
In-Reply-To: <20170908110247.GS2399@orbyte.nwl.cc>
On Fri, Sep 08, 2017 at 01:02:47PM +0200, Phil Sutter wrote:
> Hi Hangbin,
>
> On Fri, Sep 08, 2017 at 06:14:56PM +0800, Hangbin Liu wrote:
> [...]
> > diff --git a/lib/libnetlink.c b/lib/libnetlink.c
> > index be7ac86..37cfb5a 100644
> > --- a/lib/libnetlink.c
> > +++ b/lib/libnetlink.c
> > @@ -402,6 +402,59 @@ static void rtnl_dump_error(const struct rtnl_handle *rth,
> > }
> > }
> >
> > +static int rtnl_recvmsg(int fd, struct msghdr *msg, char **buf)
> > +{
> > + struct iovec *iov;
> > + int len = -1, buf_len = 32768;
> > + char *buffer = *buf;
>
> Isn't it possible to make 'buffer' static instead of the two 'buf'
> variables in rtnl_dump_filter_l() and __rtnl_talk()? Then we would have
> only a single buffer which is shared between both functions instead of
> two which are independently allocated.
Do we have to worry about reentrancy? Only arpd is multithreaded in
iproute2 but there might be also other users of libnetlink.
> > +
> > + int flag = MSG_PEEK | MSG_TRUNC;
> > +
> > + if (buffer == NULL)
> > +re_malloc:
> > + buffer = malloc(buf_len);
>
> I think using realloc() here is more appropriate since there is no need
> to free the buffer in beforehand and calling realloc(NULL, len) is
> equivalent to calling malloc(len). I think 'realloc' is also a better
> name for the goto label.
>
> > + if (buffer == NULL) {
> > + fprintf(stderr, "malloc error: no enough buffer\n");
>
> Minor typo here: s/no/not/
>
> > + return -1;
>
> Return -ENOMEM?
Hm... the only caller of rtnl_dump_filter_l only checks if the return
value is negative. Even worse, at least some of the functions calling
__rtnl_talk() check errno (or use perror()) instead, even if it's not
always preserved. That's something for a wider cleanup, I would say.
>
> > + }
> > +
> > + iov = msg->msg_iov;
> > + iov->iov_base = buffer;
> > + iov->iov_len = buf_len;
> > +
> > +re_recv:
>
> Just call this 'recv'? (Not really important though.)
>
> > + len = recvmsg(fd, msg, flag);
> > +
> > + if (len < 0) {
> > + if (errno == EINTR || errno == EAGAIN)
> > + return 0;
>
> Instead of returning 0 (which makes callers retry), goto re_recv?
>
> > + fprintf(stderr, "netlink receive error %s (%d)\n",
> > + strerror(errno), errno);
> > + return len;
> > + }
> > +
> > + if (len == 0) {
> > + fprintf(stderr, "EOF on netlink\n");
> > + return -1;
>
> Return -ENODATA here? (Initially I though about -EOF, but EOF is -1 so
> that would be incorrect).
>
> > + }
> > +
> > + if (len > buf_len) {
> > + free(buffer);
>
> If you use realloc() above, this can be dropped.
>
> > + buf_len = len;
>
> For this to work you have to make buf_len static too, otherwise you will
> unnecessarily reallocate the buffer. Oh, and that also requires the
> single buffer (as pointed out above) because you will otherwise use a
> common buf_len for both static buffers passed to this function.
>
> > + flag = 0;
> > + goto re_malloc;
> > + }
> > +
> > + if (flag != 0) {
> > + flag = 0;
> > + goto re_recv;
> > + }
> > +
> > + *buf = buffer;
> > + return len;
> > +}
> > +
> > int rtnl_dump_filter_l(struct rtnl_handle *rth,
> > const struct rtnl_dump_filter_arg *arg)
> > {
> > @@ -413,31 +466,20 @@ int rtnl_dump_filter_l(struct rtnl_handle *rth,
> > .msg_iov = &iov,
> > .msg_iovlen = 1,
> > };
> > - char buf[32768];
> > + static char *buf = NULL;
>
> If you keep the static buffer in rtnl_recvmsg(), there is no need to
> assign NULL here.
>
> > int dump_intr = 0;
> >
> > - iov.iov_base = buf;
> > while (1) {
> > int status;
> > const struct rtnl_dump_filter_arg *a;
> > int found_done = 0;
> > int msglen = 0;
> >
> > - iov.iov_len = sizeof(buf);
> > - status = recvmsg(rth->fd, &msg, 0);
> > -
> > - if (status < 0) {
> > - if (errno == EINTR || errno == EAGAIN)
> > - continue;
> > - fprintf(stderr, "netlink receive error %s (%d)\n",
> > - strerror(errno), errno);
> > - return -1;
> > - }
> > -
> > - if (status == 0) {
> > - fprintf(stderr, "EOF on netlink\n");
> > - return -1;
> > - }
> > + status = rtnl_recvmsg(rth->fd, &msg, &buf);
> > + if (status < 0)
> > + return status;
> > + else if (status == 0)
> > + continue;
>
> When retrying inside rtnl_recvmsg(), it won't return 0 anymore. I
> believe the whole 'while (1)' loop could go away then.
Doesn't this loop also handle the response divided into multiple
packets?
Michal Kubecek
^ permalink raw reply
* Re: [PATCH net] bpf: don't select potentially stale ri->map from buggy xdp progs
From: Daniel Borkmann @ 2017-09-08 12:34 UTC (permalink / raw)
To: Jesper Dangaard Brouer, andy; +Cc: davem, ast, john.fastabend, netdev
In-Reply-To: <20170908135242.55f99177@redhat.com>
On 09/08/2017 01:52 PM, Jesper Dangaard Brouer wrote:
> On Fri, 08 Sep 2017 12:34:28 +0200 Daniel Borkmann <daniel@iogearbox.net> wrote:
>> On 09/08/2017 07:06 AM, Jesper Dangaard Brouer wrote:
>>> On Fri, 8 Sep 2017 00:14:51 +0200
>>> Daniel Borkmann <daniel@iogearbox.net> wrote:
>>>
>>>> + /* This is really only caused by a deliberately crappy
>>>> + * BPF program, normally we would never hit that case,
>>>> + * so no need to inform someone via tracepoints either,
>>>> + * just bail out.
>>>> + */
>>>> + if (unlikely(map_owner != xdp_prog))
>>>> + return -EINVAL;
>>>
>>> IMHO we do need to call the tracepoint here. It is not just crappy
>>> BPF-progs that cause this situation, it is also drivers not implementing
>>> XDP_REDIRECT yet (which is all but ixgbe). Due to the level XDP
>>> operates at, tracepoints are the only way users can runtime troubleshoot
>>> their XDP programs.
>>
>> Drivers not implementing XDP_REDIRECT don't even get there in
>> the first place. What they will do is to hit the 'default' case
>> when they check for the action code from the BPF program. Then
>> call into bpf_warn_invalid_xdp_action(act), and fall-through
>> to hit the tracepoint at trace_xdp_exception() which is also
>> triggered by XDP_ABORTED usually. So when that happens we do
>> complain loudly and call a tracepoint already. We should probably
>> tweak the bpf_warn_invalid_xdp_action() message a little to make
>> it clear that the action could also just be unsupported by the
>> driver instead of being illegal.
>
> Yes. drivers not implementing XDP_REDIRECT will cause a tracepoint
> trace_xdp_exception() to be called for its _own_ packets.
Yep, plus a big one time warning for the case a user doesn't
look at tracepoints initially.
> But it will still setup and leave map and map_owner pointer dangling.
> Another NIC can load an xdp_prog that return XDP_REDIRECT, which will hit
> above if-statement, and its packets will disappear, without getting
> recorded by a tracepoint (thus hard to debug!).
If a user wants to reproduce this exact error, he would need
to go and reload the program on the driver not supporting the
XDP_REDIRECT in the first place, and then reload his buggy program
on the other driver supporting XDP_REDIRECT but w/o having called
bpf_xdp_redirect_map(), so exactly once on the switch from one
driver to another with this misuse, any subsequent packets will
trigger _trace_xdp_redirect_err(), same way as if the buggy
program was loaded to the 2nd driver from the beginning since
the map and ifindex etc will be zero, hence my comment on this.
^ permalink raw reply
* Re: [PATCH v2] netfilter: xt_hashlimit: fix build error caused by 64bit division
From: Pablo Neira Ayuso @ 2017-09-08 12:56 UTC (permalink / raw)
To: Vishwanath Pai
Cc: netfilter-devel, torvalds, davem, kadlec, johunt, fw, netdev,
pai.vishwain, mingo, ilubashe, bp, luto, x86, linux-kernel,
brgerst, andrew.cooper3, jgross, boris.ostrovsky, keescook, akpm,
arnd
In-Reply-To: <1504849138-17427-1-git-send-email-vpai@akamai.com>
On Fri, Sep 08, 2017 at 01:38:58AM -0400, Vishwanath Pai wrote:
> 64bit division causes build/link errors on 32bit architectures. It
> prints out error messages like:
>
> ERROR: "__aeabi_uldivmod" [net/netfilter/xt_hashlimit.ko] undefined!
>
> The value of avg passed through by userspace in BYTE mode cannot exceed
> U32_MAX. Which means 64bit division in user2rate_bytes is unnecessary.
> To fix this I have changed the type of param 'user' to u32.
>
> Since anything greater than U32_MAX is an invalid input we error out in
> hashlimit_mt_check_common() when this is the case.
>
> Changes in v2:
> Making return type as u32 would cause an overflow for small
> values of 'user' (for example 2, 3 etc). To avoid this I bumped up
> 'r' to u64 again as well as the return type. This is OK since the
> variable that stores the result is u64. We still avoid 64bit
> division here since 'user' is u32.
Applied, thanks.
^ permalink raw reply
* [PATCH net-next 0/3] add UniPhier AVE ethernet support
From: Kunihiko Hayashi @ 2017-09-08 13:02 UTC (permalink / raw)
To: netdev, David S. Miller, Andrew Lunn, Florian Fainelli
Cc: Rob Herring, Mark Rutland, linux-arm-kernel, linux-kernel,
devicetree, Masahiro Yamada, Masami Hiramatsu, Jassi Brar,
Kunihiko Hayashi
This series adds support for Socionext AVE ethernet controller implemented
on UniPhier SoCs. This driver supports RGMII/RMII modes.
Furthermore, this series includes support for realtek RTL8201F PHY to be
implemented on some supported boards.
Jassi Brar (1):
net: phy: realtek: add RTL8201F phy-id and functions
Kunihiko Hayashi (2):
dt-bindings: net: add DT bindings for Socionext UniPhier AVE
net: ethernet: socionext: add AVE ethernet driver
.../bindings/net/socionext,uniphier-ave4.txt | 44 +
drivers/net/ethernet/Kconfig | 1 +
drivers/net/ethernet/Makefile | 1 +
drivers/net/ethernet/socionext/Kconfig | 22 +
drivers/net/ethernet/socionext/Makefile | 4 +
drivers/net/ethernet/socionext/sni_ave.c | 1618 ++++++++++++++++++++
drivers/net/phy/realtek.c | 45 +
7 files changed, 1735 insertions(+)
create mode 100644 Documentation/devicetree/bindings/net/socionext,uniphier-ave4.txt
create mode 100644 drivers/net/ethernet/socionext/Kconfig
create mode 100644 drivers/net/ethernet/socionext/Makefile
create mode 100644 drivers/net/ethernet/socionext/sni_ave.c
--
2.7.4
^ permalink raw reply
* [PATCH net-next 1/3] dt-bindings: net: add DT bindings for Socionext UniPhier AVE
From: Kunihiko Hayashi @ 2017-09-08 13:02 UTC (permalink / raw)
To: netdev, David S. Miller, Andrew Lunn, Florian Fainelli
Cc: Rob Herring, Mark Rutland, linux-arm-kernel, linux-kernel,
devicetree, Masahiro Yamada, Masami Hiramatsu, Jassi Brar,
Kunihiko Hayashi
In-Reply-To: <1504875731-3680-1-git-send-email-hayashi.kunihiko@socionext.com>
DT bindings for the AVE ethernet controller found on Socionext's
UniPhier platforms.
Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
.../bindings/net/socionext,uniphier-ave4.txt | 44 ++++++++++++++++++++++
1 file changed, 44 insertions(+)
create mode 100644 Documentation/devicetree/bindings/net/socionext,uniphier-ave4.txt
diff --git a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.txt b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.txt
new file mode 100644
index 0000000..57ae96d
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.txt
@@ -0,0 +1,44 @@
+* Socionext AVE ethernet controller
+
+This describes the devicetree bindings for AVE ethernet controller
+implemented on Socionext UniPhier SoCs.
+
+Required properties:
+ - compatible: Should be "socionext,uniphier-ave4"
+ - reg: Address where registers are mapped and size of region.
+ - interrupts: IRQ common for mac and phy interrupts.
+ - phy-mode: See ethernet.txt in the same directory.
+ - #address-cells: Must be <1>.
+ - #size-cells: Must be <0>.
+ - Node, with 'reg' property, for each PHY on the MDIO bus.
+
+Optional properties:
+ - socionext,desc-bits: 32/64 descriptor size. Default 32.
+ - local-mac-address: See ethernet.txt in the same directory.
+ - pinctrl-names: List of assigned state names, see pinctrl
+ binding documentation.
+ - pinctrl-0: List of phandles to configure the GPIO pin used
+ as interrupt line, see also generic and your platform
+ specific pinctrl binding documentation.
+ - socionext,internal-phy-interrupt: Boolean to denote if the
+ PHY interrupt is internally handled by the MAC.
+
+
+Example:
+
+ eth: ethernet@65000000 {
+ compatible = "socionext,uniphier-ave4";
+ reg = <0x65000000 0x8500>;
+ interrupts = <0 66 4>;
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_ether_rgmii>;
+ phy-mode = "rgmii";
+ socionext,desc-bits = <64>;
+ local-mac-address = [00 00 00 00 00 00];
+
+ #address-cells = <1>;
+ #size-cells = <0>;
+ ethphy: ethphy@1 {
+ reg = <1>;
+ };
+ };
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 3/3] net: phy: realtek: add RTL8201F phy-id and functions
From: Kunihiko Hayashi @ 2017-09-08 13:02 UTC (permalink / raw)
To: netdev, David S. Miller, Andrew Lunn, Florian Fainelli
Cc: Rob Herring, Mark Rutland, linux-arm-kernel, linux-kernel,
devicetree, Masahiro Yamada, Masami Hiramatsu, Jassi Brar,
Jongsung Kim, Kunihiko Hayashi
In-Reply-To: <1504875731-3680-1-git-send-email-hayashi.kunihiko@socionext.com>
From: Jassi Brar <jaswinder.singh@linaro.org>
Add RTL8201F phy-id and the related functions to the driver.
The original patch is as follows:
https://patchwork.kernel.org/patch/2538341/
Signed-off-by: Jongsung Kim <neidhard.kim@lge.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
---
drivers/net/phy/realtek.c | 45 +++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 45 insertions(+)
diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 9cbe645..d9974ce 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -29,10 +29,23 @@
#define RTL8211F_PAGE_SELECT 0x1f
#define RTL8211F_TX_DELAY 0x100
+#define RTL8201F_ISR 0x1e
+#define RTL8201F_PAGE_SELECT 0x1f
+#define RTL8201F_IER 0x13
+
MODULE_DESCRIPTION("Realtek PHY driver");
MODULE_AUTHOR("Johnson Leung");
MODULE_LICENSE("GPL");
+static int rtl8201_ack_interrupt(struct phy_device *phydev)
+{
+ int err;
+
+ err = phy_read(phydev, RTL8201F_ISR);
+
+ return (err < 0) ? err : 0;
+}
+
static int rtl821x_ack_interrupt(struct phy_device *phydev)
{
int err;
@@ -54,6 +67,25 @@ static int rtl8211f_ack_interrupt(struct phy_device *phydev)
return (err < 0) ? err : 0;
}
+static int rtl8201_config_intr(struct phy_device *phydev)
+{
+ int err;
+
+ /* switch to page 7 */
+ phy_write(phydev, RTL8201F_PAGE_SELECT, 0x7);
+
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED)
+ err = phy_write(phydev, RTL8201F_IER,
+ BIT(13) | BIT(12) | BIT(11));
+ else
+ err = phy_write(phydev, RTL8201F_IER, 0);
+
+ /* restore to default page 0 */
+ phy_write(phydev, RTL8201F_PAGE_SELECT, 0x0);
+
+ return err;
+}
+
static int rtl8211b_config_intr(struct phy_device *phydev)
{
int err;
@@ -129,6 +161,18 @@ static struct phy_driver realtek_drvs[] = {
.config_aneg = &genphy_config_aneg,
.read_status = &genphy_read_status,
}, {
+ .phy_id = 0x001cc816,
+ .name = "RTL8201F 10/100Mbps Ethernet",
+ .phy_id_mask = 0x001fffff,
+ .features = PHY_BASIC_FEATURES,
+ .flags = PHY_HAS_INTERRUPT,
+ .config_aneg = &genphy_config_aneg,
+ .read_status = &genphy_read_status,
+ .ack_interrupt = &rtl8201_ack_interrupt,
+ .config_intr = &rtl8201_config_intr,
+ .suspend = genphy_suspend,
+ .resume = genphy_resume,
+ }, {
.phy_id = 0x001cc912,
.name = "RTL8211B Gigabit Ethernet",
.phy_id_mask = 0x001fffff,
@@ -181,6 +225,7 @@ static struct phy_driver realtek_drvs[] = {
module_phy_driver(realtek_drvs);
static struct mdio_device_id __maybe_unused realtek_tbl[] = {
+ { 0x001cc816, 0x001fffff },
{ 0x001cc912, 0x001fffff },
{ 0x001cc914, 0x001fffff },
{ 0x001cc915, 0x001fffff },
--
2.7.4
^ permalink raw reply related
* [PATCH net-next 2/3] net: ethernet: socionext: add AVE ethernet driver
From: Kunihiko Hayashi @ 2017-09-08 13:02 UTC (permalink / raw)
To: netdev, David S. Miller, Andrew Lunn, Florian Fainelli
Cc: Rob Herring, Mark Rutland, linux-arm-kernel, linux-kernel,
devicetree, Masahiro Yamada, Masami Hiramatsu, Jassi Brar,
Kunihiko Hayashi
In-Reply-To: <1504875731-3680-1-git-send-email-hayashi.kunihiko@socionext.com>
The UniPhier platform from Socionext provides the AVE ethernet
controller that includes MAC and MDIO bus supporting RGMII/RMII
modes. The controller is named AVE.
Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
drivers/net/ethernet/Kconfig | 1 +
drivers/net/ethernet/Makefile | 1 +
drivers/net/ethernet/socionext/Kconfig | 22 +
drivers/net/ethernet/socionext/Makefile | 4 +
drivers/net/ethernet/socionext/sni_ave.c | 1618 ++++++++++++++++++++++++++++++
5 files changed, 1646 insertions(+)
create mode 100644 drivers/net/ethernet/socionext/Kconfig
create mode 100644 drivers/net/ethernet/socionext/Makefile
create mode 100644 drivers/net/ethernet/socionext/sni_ave.c
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index c604213..d50519e 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -170,6 +170,7 @@ source "drivers/net/ethernet/sis/Kconfig"
source "drivers/net/ethernet/sfc/Kconfig"
source "drivers/net/ethernet/sgi/Kconfig"
source "drivers/net/ethernet/smsc/Kconfig"
+source "drivers/net/ethernet/socionext/Kconfig"
source "drivers/net/ethernet/stmicro/Kconfig"
source "drivers/net/ethernet/sun/Kconfig"
source "drivers/net/ethernet/tehuti/Kconfig"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index a0a03d4..9f55b36 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -81,6 +81,7 @@ obj-$(CONFIG_SFC) += sfc/
obj-$(CONFIG_SFC_FALCON) += sfc/falcon/
obj-$(CONFIG_NET_VENDOR_SGI) += sgi/
obj-$(CONFIG_NET_VENDOR_SMSC) += smsc/
+obj-$(CONFIG_NET_VENDOR_SOCIONEXT) += socionext/
obj-$(CONFIG_NET_VENDOR_STMICRO) += stmicro/
obj-$(CONFIG_NET_VENDOR_SUN) += sun/
obj-$(CONFIG_NET_VENDOR_TEHUTI) += tehuti/
diff --git a/drivers/net/ethernet/socionext/Kconfig b/drivers/net/ethernet/socionext/Kconfig
new file mode 100644
index 0000000..788f26f
--- /dev/null
+++ b/drivers/net/ethernet/socionext/Kconfig
@@ -0,0 +1,22 @@
+config NET_VENDOR_SOCIONEXT
+ bool "Socionext ethernet drivers"
+ default y
+ ---help---
+ Option to select ethernet drivers for Socionext platforms.
+
+ Note that the answer to this question doesn't directly affect the
+ kernel: saying N will just cause the configurator to skip all
+ the questions about Agere devices. If you say Y, you will be asked
+ for your specific card in the following questions.
+
+if NET_VENDOR_SOCIONEXT
+
+config SNI_AVE
+ tristate "Socionext AVE ethernet support"
+ depends on (ARCH_UNIPHIER || COMPILE_TEST) && OF
+ select PHYLIB
+ ---help---
+ Driver for gigabit ethernet MACs, called AVE, in the
+ Socionext UniPhier family.
+
+endif #NET_VENDOR_SOCIONEXT
diff --git a/drivers/net/ethernet/socionext/Makefile b/drivers/net/ethernet/socionext/Makefile
new file mode 100644
index 0000000..0356341
--- /dev/null
+++ b/drivers/net/ethernet/socionext/Makefile
@@ -0,0 +1,4 @@
+#
+# Makefile for all ethernet ip drivers on Socionext platforms
+#
+obj-$(CONFIG_SNI_AVE) += sni_ave.o
diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c
new file mode 100644
index 0000000..c870777
--- /dev/null
+++ b/drivers/net/ethernet/socionext/sni_ave.c
@@ -0,0 +1,1618 @@
+/**
+ * sni_ave.c - Socionext UniPhier AVE ethernet driver
+ *
+ * Copyright 2014 Panasonic Corporation
+ * Copyright 2015-2017 Socionext Inc.
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 of
+ * the License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/etherdevice.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/mii.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/of_net.h>
+#include <linux/of_mdio.h>
+#include <linux/of_platform.h>
+#include <linux/phy.h>
+#include <linux/reset.h>
+#include <linux/types.h>
+
+/* General Register Group */
+#define AVE_IDR 0x0 /* ID */
+#define AVE_VR 0x4 /* Version */
+#define AVE_GRR 0x8 /* Global Reset */
+#define AVE_CFGR 0xc /* Configuration */
+
+/* Interrupt Register Group */
+#define AVE_GIMR 0x100 /* Global Interrupt Mask */
+#define AVE_GISR 0x104 /* Global Interrupt Status */
+
+/* MAC Register Group */
+#define AVE_TXCR 0x200 /* TX Setup */
+#define AVE_RXCR 0x204 /* RX Setup */
+#define AVE_RXMAC1R 0x208 /* MAC address (lower) */
+#define AVE_RXMAC2R 0x20c /* MAC address (upper) */
+#define AVE_MDIOCTR 0x214 /* MDIO Control */
+#define AVE_MDIOAR 0x218 /* MDIO Address */
+#define AVE_MDIOWDR 0x21c /* MDIO Data */
+#define AVE_MDIOSR 0x220 /* MDIO Status */
+#define AVE_MDIORDR 0x224 /* MDIO Rd Data */
+
+/* Descriptor Control Register Group */
+#define AVE_DESCC 0x300 /* Descriptor Control */
+#define AVE_TXDC 0x304 /* TX Descriptor Configuration */
+#define AVE_RXDC0 0x308 /* RX Descriptor Ring0 Configuration */
+#define AVE_IIRQC 0x34c /* Interval IRQ Control */
+
+/* Frame Counter Register Group */
+#define AVE_BFCR 0x400 /* Bad Frame Counter */
+#define AVE_RX0OVFFC 0x414 /* OVF Frame Counter (Ring0) */
+#define AVE_SN5FC 0x438 /* Frame Counter No5 */
+#define AVE_SN6FC 0x43c /* Frame Counter No6 */
+#define AVE_SN7FC 0x440 /* Frame Counter No7 */
+
+/* Packet Filter Register Group */
+#define AVE_PKTF_BASE 0x800 /* PF Base Address */
+#define AVE_PFMBYTE_BASE 0xd00 /* PF Mask Byte Base Address */
+#define AVE_PFMBIT_BASE 0xe00 /* PF Mask Bit Base Address */
+#define AVE_PFSEL_BASE 0xf00 /* PF Selector Base Address */
+#define AVE_PFEN 0xffc /* Packet Filter Enable */
+#define AVE_PKTF(ent) (AVE_PKTF_BASE + (ent) * 0x40)
+#define AVE_PFMBYTE(ent) (AVE_PFMBYTE_BASE + (ent) * 8)
+#define AVE_PFMBIT(ent) (AVE_PFMBIT_BASE + (ent) * 4)
+#define AVE_PFSEL(ent) (AVE_PFSEL_BASE + (ent) * 4)
+
+/* 64bit descriptor memory */
+#define AVE_DESC_SIZE_64 12 /* Descriptor Size */
+
+#define AVE_TXDM_64 0x1000 /* Tx Descriptor Memory */
+#define AVE_RXDM_64 0x1c00 /* Rx Descriptor Memory */
+
+#define AVE_TXDM_SIZE_64 0x0ba0 /* Tx Descriptor Memory Size 3KB */
+#define AVE_RXDM_SIZE_64 0x6000 /* Rx Descriptor Memory Size 24KB */
+
+/* 32bit descriptor memory */
+#define AVE_DESC_SIZE_32 8 /* Descriptor Size */
+
+#define AVE_TXDM_32 0x1000 /* Tx Descriptor Memory */
+#define AVE_RXDM_32 0x1800 /* Rx Descriptor Memory */
+
+#define AVE_TXDM_SIZE_32 0x07c0 /* Tx Descriptor Memory Size 2KB */
+#define AVE_RXDM_SIZE_32 0x4000 /* Rx Descriptor Memory Size 16KB */
+
+/* RMII Bridge Register Group */
+#define AVE_RSTCTRL 0x8028 /* Reset control */
+#define AVE_RSTCTRL_RMIIRST BIT(16)
+#define AVE_LINKSEL 0x8034 /* Link speed setting */
+#define AVE_LINKSEL_100M BIT(0)
+
+/* AVE_GRR */
+#define AVE_GRR_RXFFR BIT(5) /* Reset RxFIFO */
+#define AVE_GRR_PHYRST BIT(4) /* Reset external PHY */
+#define AVE_GRR_GRST BIT(0) /* Reset all MAC */
+
+/* AVE_GISR (common with GIMR) */
+#define AVE_GI_PHY BIT(24) /* PHY interrupt */
+#define AVE_GI_TX BIT(16) /* Tx complete */
+#define AVE_GI_RXERR BIT(8) /* Receive frame more than max size */
+#define AVE_GI_RXOVF BIT(7) /* Overflow at the RxFIFO */
+#define AVE_GI_RXDROP BIT(6) /* Drop packet */
+#define AVE_GI_RXIINT BIT(5) /* Interval interrupt */
+
+/* AVE_TXCR */
+#define AVE_TXCR_FLOCTR BIT(18) /* Flow control */
+#define AVE_TXCR_TXSPD_1G BIT(17)
+#define AVE_TXCR_TXSPD_100 BIT(16)
+
+/* AVE_RXCR */
+#define AVE_RXCR_RXEN BIT(30) /* Rx enable */
+#define AVE_RXCR_FDUPEN BIT(22) /* Interface mode */
+#define AVE_RXCR_FLOCTR BIT(21) /* Flow control */
+#define AVE_RXCR_AFEN BIT(19) /* MAC address filter */
+#define AVE_RXCR_DRPEN BIT(18) /* Drop pause frame */
+#define AVE_RXCR_MPSIZ_MASK GENMASK(10, 0)
+
+/* AVE_MDIOCTR */
+#define AVE_MDIOCTR_RREQ BIT(3) /* Read request */
+#define AVE_MDIOCTR_WREQ BIT(2) /* Write request */
+
+/* AVE_MDIOSR */
+#define AVE_MDIOSR_STS BIT(0) /* access status */
+
+/* AVE_DESCC */
+#define AVE_DESCC_TD BIT(0) /* Enable Tx descriptor */
+#define AVE_DESCC_RDSTP BIT(4) /* Pause Rx descriptor */
+#define AVE_DESCC_RD0 BIT(8) /* Enable Rx descriptor Ring0 */
+
+#define AVE_DESCC_CTRL_MASK GENMASK(15, 0)
+
+/* AVE_TXDC */
+#define AVE_TXDC_SIZE GENMASK(27, 16) /* Size of Tx descriptor */
+#define AVE_TXDC_ADDR GENMASK(11, 0) /* Start address */
+#define AVE_TXDC_ADDR_START 0
+
+/* AVE_RXDC0 */
+#define AVE_RXDC0_SIZE GENMASK(30, 16) /* Size of Rx descriptor */
+#define AVE_RXDC0_ADDR GENMASK(14, 0) /* Start address */
+#define AVE_RXDC0_ADDR_START 0
+
+/* AVE_IIRQC */
+#define AVE_IIRQC_EN0 BIT(27) /* Enable interval interrupt Ring0 */
+#define AVE_IIRQC_BSCK GENMASK(15, 0) /* Interval count unit */
+
+/* Command status for Descriptor */
+#define AVE_STS_OWN BIT(31) /* Descriptor ownership */
+#define AVE_STS_INTR BIT(29) /* Request for interrupt */
+#define AVE_STS_OK BIT(27) /* Normal transmit */
+/* TX */
+#define AVE_STS_NOCSUM BIT(28) /* No use HW checksum */
+#define AVE_STS_1ST BIT(26) /* Head of buffer chain */
+#define AVE_STS_LAST BIT(25) /* Tail of buffer chain */
+#define AVE_STS_OWC BIT(21) /* Out of window,Late Collision */
+#define AVE_STS_EC BIT(20) /* Excess collision occurred */
+#define AVE_STS_PKTLEN_TX GENMASK(15, 0)
+/* RX */
+#define AVE_STS_CSSV BIT(21) /* Checksum check performed */
+#define AVE_STS_CSER BIT(20) /* Checksum error detected */
+#define AVE_STS_PKTLEN_RX GENMASK(10, 0)
+
+/* AVE_CFGR */
+#define AVE_CFGR_FLE BIT(31) /* Filter Function */
+#define AVE_CFGR_CHE BIT(30) /* Checksum Function */
+#define AVE_CFGR_MII BIT(27) /* Func mode (1:MII/RMII, 0:RGMII) */
+#define AVE_CFGR_IPFCEN BIT(24) /* IP fragment sum Enable */
+
+#define AVE_MAX_ETHFRAME 1518
+
+/* Packet filter size */
+#define AVE_PF_SIZE 17 /* Number of all packet filter */
+#define AVE_PF_MULTICAST_SIZE 7 /* Number of multicast filter */
+
+/* Packet filter definition */
+#define AVE_PFNUM_FILTER 0 /* No.0 */
+#define AVE_PFNUM_UNICAST 1 /* No.1 */
+#define AVE_PFNUM_BROADCAST 2 /* No.2 */
+#define AVE_PFNUM_MULTICAST 11 /* No.11-17 */
+
+/* NETIF Message control */
+#define AVE_DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | \
+ NETIF_MSG_PROBE | \
+ NETIF_MSG_LINK | \
+ NETIF_MSG_TIMER | \
+ NETIF_MSG_IFDOWN | \
+ NETIF_MSG_IFUP | \
+ NETIF_MSG_RX_ERR | \
+ NETIF_MSG_TX_ERR)
+
+/* Parameter for descriptor */
+#define AVE_NR_TXDESC 32 /* Tx descriptor */
+#define AVE_NR_RXDESC 64 /* Rx descriptor */
+
+/* Parameter for interrupt */
+#define AVE_INTM_COUNT 20
+#define AVE_FORCE_TXINTCNT 1
+
+#define IS_DESC_64BIT(p) ((p)->desc_size == AVE_DESC_SIZE_64)
+
+enum desc_id {
+ AVE_DESCID_TX = 0,
+ AVE_DESCID_RX,
+};
+
+enum desc_state {
+ AVE_DESC_STOP = 0,
+ AVE_DESC_START,
+ AVE_DESC_RX_SUSPEND,
+ AVE_DESC_RX_PERMIT,
+};
+
+struct ave_desc {
+ struct sk_buff *skbs;
+ dma_addr_t skbs_dma;
+ size_t skbs_dmalen;
+};
+
+struct ave_desc_info {
+ u32 ndesc; /* number of descriptor */
+ u32 daddr; /* start address of descriptor */
+ u32 proc_idx; /* index of processing packet */
+ u32 done_idx; /* index of processed packet */
+ struct ave_desc *desc; /* skb info related descriptor */
+};
+
+struct ave_private {
+ int phy_id;
+ unsigned int desc_size;
+ u32 msg_enable;
+ struct clk *clk;
+ phy_interface_t phy_mode;
+ struct phy_device *phydev;
+ struct mii_bus *mdio;
+ struct net_device_stats stats;
+ bool internal_phy_interrupt;
+
+ /* NAPI support */
+ struct net_device *ndev;
+ struct napi_struct napi_rx;
+ struct napi_struct napi_tx;
+
+ /* descriptor */
+ struct ave_desc_info rx;
+ struct ave_desc_info tx;
+};
+
+static inline u32 ave_r32(struct net_device *ndev, u32 offset)
+{
+ void __iomem *addr = (void __iomem *)ndev->base_addr;
+
+ return readl_relaxed(addr + offset);
+}
+
+static inline void ave_w32(struct net_device *ndev, u32 offset, u32 value)
+{
+ void __iomem *addr = (void __iomem *)ndev->base_addr;
+
+ writel_relaxed(value, addr + offset);
+}
+
+static inline u32 ave_rdesc(struct net_device *ndev, enum desc_id id,
+ int entry, int offset)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ u32 addr = (id == AVE_DESCID_TX) ? priv->tx.daddr : priv->rx.daddr;
+
+ addr += entry * priv->desc_size + offset;
+
+ return ave_r32(ndev, addr);
+}
+
+static inline void ave_wdesc(struct net_device *ndev, enum desc_id id,
+ int entry, int offset, u32 val)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ u32 addr = (id == AVE_DESCID_TX) ? priv->tx.daddr : priv->rx.daddr;
+
+ addr += entry * priv->desc_size + offset;
+
+ ave_w32(ndev, addr, val);
+}
+
+static void ave_wdesc_addr(struct net_device *ndev, enum desc_id id,
+ int entry, int offset, dma_addr_t paddr)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+
+ ave_wdesc(ndev, id, entry, offset, (u32)((u64)paddr & 0xFFFFFFFFULL));
+ if (IS_DESC_64BIT(priv))
+ ave_wdesc(ndev, id,
+ entry, offset + 4, (u32)((u64)paddr >> 32));
+ else if ((u64)paddr > (u64)U32_MAX)
+ netdev_warn(ndev, "DMA address exceeds the address space\n");
+}
+
+static void ave_get_fwversion(struct net_device *ndev, char *buf, int len)
+{
+ u32 major, minor;
+
+ major = (ave_r32(ndev, AVE_VR) & GENMASK(15, 8)) >> 8;
+ minor = (ave_r32(ndev, AVE_VR) & GENMASK(7, 0));
+ snprintf(buf, len, "v%u.%u", major, minor);
+}
+
+static void ave_get_drvinfo(struct net_device *ndev,
+ struct ethtool_drvinfo *info)
+{
+ struct device *dev = ndev->dev.parent;
+
+ strlcpy(info->driver, dev->driver->name, sizeof(info->driver));
+ strlcpy(info->bus_info, dev_name(dev), sizeof(info->bus_info));
+ ave_get_fwversion(ndev, info->fw_version, sizeof(info->fw_version));
+}
+
+static int ave_nway_reset(struct net_device *ndev)
+{
+ return genphy_restart_aneg(ndev->phydev);
+}
+
+static u32 ave_get_link(struct net_device *ndev)
+{
+ int err;
+
+ err = genphy_update_link(ndev->phydev);
+ if (err)
+ return ethtool_op_get_link(ndev);
+
+ return ndev->phydev->link;
+}
+
+static u32 ave_get_msglevel(struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+
+ return priv->msg_enable;
+}
+
+static void ave_set_msglevel(struct net_device *ndev, u32 val)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+
+ priv->msg_enable = val;
+}
+
+static void ave_get_wol(struct net_device *ndev,
+ struct ethtool_wolinfo *wol)
+{
+ wol->supported = 0;
+ wol->wolopts = 0;
+ phy_ethtool_get_wol(ndev->phydev, wol);
+}
+
+static int ave_set_wol(struct net_device *ndev,
+ struct ethtool_wolinfo *wol)
+{
+ if (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE))
+ return -EOPNOTSUPP;
+
+ return phy_ethtool_set_wol(ndev->phydev, wol);
+}
+
+static const struct ethtool_ops ave_ethtool_ops = {
+ .get_link_ksettings = phy_ethtool_get_link_ksettings,
+ .set_link_ksettings = phy_ethtool_set_link_ksettings,
+ .get_drvinfo = ave_get_drvinfo,
+ .nway_reset = ave_nway_reset,
+ .get_link = ave_get_link,
+ .get_msglevel = ave_get_msglevel,
+ .set_msglevel = ave_set_msglevel,
+ .get_wol = ave_get_wol,
+ .set_wol = ave_set_wol,
+};
+
+static int ave_pfsel_start(struct net_device *ndev, unsigned int entry)
+{
+ u32 val;
+
+ if (WARN_ON(entry > AVE_PF_SIZE))
+ return -EINVAL;
+
+ val = ave_r32(ndev, AVE_PFEN);
+ ave_w32(ndev, AVE_PFEN, val | BIT(entry));
+
+ return 0;
+}
+
+static int ave_pfsel_stop(struct net_device *ndev, unsigned int entry)
+{
+ u32 val;
+
+ if (WARN_ON(entry > AVE_PF_SIZE))
+ return -EINVAL;
+
+ val = ave_r32(ndev, AVE_PFEN);
+ ave_w32(ndev, AVE_PFEN, val & ~BIT(entry));
+
+ return 0;
+}
+
+static int ave_pfsel_macaddr_set(struct net_device *ndev,
+ unsigned int entry, unsigned char *mac_addr,
+ unsigned int set_size)
+{
+ u32 val;
+
+ if (WARN_ON(entry > AVE_PF_SIZE))
+ return -EINVAL;
+ if (WARN_ON(set_size > 6))
+ return -EINVAL;
+
+ ave_pfsel_stop(ndev, entry);
+
+ /* set MAC address for the filter */
+ val = le32_to_cpu(((u32 *)mac_addr)[0]);
+ ave_w32(ndev, AVE_PKTF(entry), val);
+ val = (u32)le16_to_cpu(((u16 *)mac_addr)[2]);
+ ave_w32(ndev, AVE_PKTF(entry) + 4, val);
+
+ /* set byte mask */
+ ave_w32(ndev, AVE_PFMBYTE(entry), GENMASK(31, set_size) & ~0xc0);
+ ave_w32(ndev, AVE_PFMBYTE(entry) + 4, 0xFFFFFFFF);
+
+ /* set bit mask filter */
+ ave_w32(ndev, AVE_PFMBIT(entry), 0x0000FFFF);
+
+ /* set selector to ring 0 */
+ ave_w32(ndev, AVE_PFSEL(entry), 0);
+
+ /* restart filter */
+ ave_pfsel_start(ndev, entry);
+
+ return 0;
+}
+
+static int ave_mdio_busywait(struct net_device *ndev)
+{
+ int ret = 1, loop = 100;
+ u32 mdiosr;
+
+ /* wait until completion */
+ while (1) {
+ mdiosr = ave_r32(ndev, AVE_MDIOSR);
+ if (!(mdiosr & AVE_MDIOSR_STS))
+ break;
+
+ usleep_range(10, 20);
+ if (!loop--) {
+ netdev_err(ndev,
+ "failed to read from MDIO (status:0x%08x)\n",
+ mdiosr);
+ ret = 0;
+ break;
+ }
+ }
+
+ return ret;
+}
+
+static int ave_mdiobus_read(struct mii_bus *bus, int phyid, int regnum)
+{
+ struct net_device *ndev = bus->priv;
+ u32 mdioctl;
+
+ /* write address */
+ ave_w32(ndev, AVE_MDIOAR, (phyid << 8) | regnum);
+
+ /* read request */
+ mdioctl = ave_r32(ndev, AVE_MDIOCTR);
+ ave_w32(ndev, AVE_MDIOCTR, mdioctl | AVE_MDIOCTR_RREQ);
+
+ if (!ave_mdio_busywait(ndev)) {
+ netdev_err(ndev, "phy-%d reg-%x read failed\n",
+ phyid, regnum);
+ return 0xffff;
+ }
+
+ return ave_r32(ndev, AVE_MDIORDR) & GENMASK(15, 0);
+}
+
+static int ave_mdiobus_write(struct mii_bus *bus,
+ int phyid, int regnum, u16 val)
+{
+ struct net_device *ndev = bus->priv;
+ u32 mdioctl;
+
+ /* write address */
+ ave_w32(ndev, AVE_MDIOAR, (phyid << 8) | regnum);
+
+ /* write data */
+ ave_w32(ndev, AVE_MDIOWDR, val);
+
+ /* write request */
+ mdioctl = ave_r32(ndev, AVE_MDIOCTR);
+ ave_w32(ndev, AVE_MDIOCTR, mdioctl | AVE_MDIOCTR_WREQ);
+
+ if (!ave_mdio_busywait(ndev)) {
+ netdev_err(ndev, "phy-%d reg-%x write failed\n",
+ phyid, regnum);
+ return -1;
+ }
+
+ return 0;
+}
+
+static dma_addr_t ave_dma_map(struct net_device *ndev, struct ave_desc *desc,
+ void *ptr, size_t len,
+ enum dma_data_direction dir)
+{
+ dma_addr_t paddr;
+
+ paddr = dma_map_single(ndev->dev.parent, ptr, len, dir);
+ if (dma_mapping_error(ndev->dev.parent, paddr)) {
+ desc->skbs_dma = 0;
+ paddr = (dma_addr_t)virt_to_phys(ptr);
+ } else {
+ desc->skbs_dma = paddr;
+ desc->skbs_dmalen = len;
+ }
+
+ return paddr;
+}
+
+static void ave_dma_unmap(struct net_device *ndev, struct ave_desc *desc,
+ enum dma_data_direction dir)
+{
+ if (!desc->skbs_dma)
+ return;
+
+ dma_unmap_single(ndev->dev.parent,
+ desc->skbs_dma, desc->skbs_dmalen, dir);
+ desc->skbs_dma = 0;
+}
+
+/* Set Rx descriptor and memory */
+static int ave_set_rxdesc(struct net_device *ndev, int entry)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ struct sk_buff *skb;
+ unsigned long align;
+ dma_addr_t paddr;
+ void *buffptr;
+ int ret = 0;
+
+ skb = priv->rx.desc[entry].skbs;
+ if (!skb) {
+ skb = netdev_alloc_skb_ip_align(ndev,
+ AVE_MAX_ETHFRAME + NET_SKB_PAD);
+ if (!skb) {
+ netdev_err(ndev, "can't allocate skb for Rx\n");
+ return -ENOMEM;
+ }
+ }
+
+ /* set disable to cmdsts */
+ ave_wdesc(ndev, AVE_DESCID_RX, entry, 0, AVE_STS_INTR | AVE_STS_OWN);
+
+ /* align skb data for cache size */
+ align = (unsigned long)skb_tail_pointer(skb) & (NET_SKB_PAD - 1);
+ align = NET_SKB_PAD - align;
+ skb_reserve(skb, align);
+ buffptr = (void *)skb_tail_pointer(skb);
+
+ paddr = ave_dma_map(ndev, &priv->rx.desc[entry], buffptr,
+ AVE_MAX_ETHFRAME + NET_IP_ALIGN, DMA_FROM_DEVICE);
+ priv->rx.desc[entry].skbs = skb;
+
+ /* set buffer pointer */
+ ave_wdesc_addr(ndev, AVE_DESCID_RX, entry, 4, paddr);
+
+ /* set enable to cmdsts */
+ ave_wdesc(ndev, AVE_DESCID_RX,
+ entry, 0, AVE_STS_INTR | AVE_MAX_ETHFRAME);
+
+ return ret;
+}
+
+/* Switch state of descriptor */
+static int ave_desc_switch(struct net_device *ndev, enum desc_state state)
+{
+ int counter;
+ u32 val;
+
+ switch (state) {
+ case AVE_DESC_START:
+ ave_w32(ndev, AVE_DESCC, AVE_DESCC_TD | AVE_DESCC_RD0);
+ break;
+
+ case AVE_DESC_STOP:
+ ave_w32(ndev, AVE_DESCC, 0);
+ counter = 0;
+ while (1) {
+ usleep_range(100, 150);
+ if (!ave_r32(ndev, AVE_DESCC))
+ break;
+
+ counter++;
+ if (counter > 100) {
+ netdev_err(ndev, "can't stop descriptor\n");
+ return -EBUSY;
+ }
+ }
+ break;
+
+ case AVE_DESC_RX_SUSPEND:
+ val = ave_r32(ndev, AVE_DESCC);
+ val |= AVE_DESCC_RDSTP;
+ val &= AVE_DESCC_CTRL_MASK;
+ ave_w32(ndev, AVE_DESCC, val);
+
+ counter = 0;
+ while (1) {
+ usleep_range(100, 150);
+ val = ave_r32(ndev, AVE_DESCC);
+ if (val & (AVE_DESCC_RDSTP << 16))
+ break;
+
+ counter++;
+ if (counter > 1000) {
+ netdev_err(ndev, "can't suspend descriptor\n");
+ return -EBUSY;
+ }
+ }
+ break;
+
+ case AVE_DESC_RX_PERMIT:
+ val = ave_r32(ndev, AVE_DESCC);
+ val &= ~AVE_DESCC_RDSTP;
+ val &= AVE_DESCC_CTRL_MASK;
+ ave_w32(ndev, AVE_DESCC, val);
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int ave_tx_completion(struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ u32 proc_idx, done_idx, ndesc, val;
+ int freebuf_flag = 0;
+
+ proc_idx = priv->tx.proc_idx;
+ done_idx = priv->tx.done_idx;
+ ndesc = priv->tx.ndesc;
+
+ /* free pre stored skb from done to proc */
+ while (proc_idx != done_idx) {
+ /* get cmdsts */
+ val = ave_rdesc(ndev, AVE_DESCID_TX, done_idx, 0);
+
+ /* do nothing if owner is HW */
+ if (val & AVE_STS_OWN)
+ break;
+
+ /* check Tx status and updates statistics */
+ if (val & AVE_STS_OK) {
+ priv->stats.tx_bytes += val & AVE_STS_PKTLEN_TX;
+
+ /* success */
+ if (val & AVE_STS_LAST)
+ priv->stats.tx_packets++;
+ } else {
+ /* error */
+ if (val & AVE_STS_LAST) {
+ priv->stats.tx_errors++;
+ if (val & (AVE_STS_OWC | AVE_STS_EC))
+ priv->stats.collisions++;
+ }
+ }
+
+ /* release skb */
+ if (priv->tx.desc[done_idx].skbs) {
+ ave_dma_unmap(ndev, &priv->tx.desc[done_idx],
+ DMA_TO_DEVICE);
+ dev_consume_skb_any(priv->tx.desc[done_idx].skbs);
+ priv->tx.desc[done_idx].skbs = NULL;
+ freebuf_flag++;
+ }
+ done_idx = (done_idx + 1) % ndesc;
+ }
+
+ priv->tx.done_idx = done_idx;
+
+ /* wake queue for freeing buffer */
+ if (netif_queue_stopped(ndev))
+ if (netif_running(ndev))
+ if (freebuf_flag)
+ netif_wake_queue(ndev);
+
+ return freebuf_flag;
+}
+
+static int ave_rx(struct net_device *ndev, int num)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ struct sk_buff *skb;
+ u32 proc_idx, done_idx, ndesc, cmdsts;
+ int restpkt, npkts;
+ unsigned int pktlen;
+
+ proc_idx = priv->rx.proc_idx;
+ done_idx = priv->rx.done_idx;
+ ndesc = priv->rx.ndesc;
+ restpkt = ((proc_idx + ndesc - 1) - done_idx) % ndesc;
+
+ for (npkts = 0; npkts < num; npkts++) {
+ /* we can't receive more packet, so fill desc quickly */
+ if (--restpkt < 0)
+ break;
+
+ cmdsts = ave_rdesc(ndev, AVE_DESCID_RX, proc_idx, 0);
+
+ /* owner is hardware */
+ if ((cmdsts & AVE_STS_OWN) != AVE_STS_OWN)
+ break;
+
+ if ((cmdsts & AVE_STS_OK) != AVE_STS_OK) {
+ priv->stats.rx_errors++;
+ proc_idx = (proc_idx + 1) % ndesc;
+ continue;
+ }
+
+ pktlen = cmdsts & AVE_STS_PKTLEN_RX;
+
+ /* get skbuff for rx */
+ skb = priv->rx.desc[proc_idx].skbs;
+ priv->rx.desc[proc_idx].skbs = NULL;
+
+ ave_dma_unmap(ndev, &priv->rx.desc[proc_idx], DMA_FROM_DEVICE);
+
+ skb->dev = ndev;
+ skb_reserve(skb, NET_IP_ALIGN);
+ skb_put(skb, pktlen);
+
+ skb->protocol = eth_type_trans(skb, ndev);
+
+ if ((cmdsts & AVE_STS_CSSV) && (!(cmdsts & AVE_STS_CSER)))
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+ /* update stats */
+ priv->stats.rx_packets++;
+ priv->stats.rx_bytes += pktlen;
+
+ netif_receive_skb(skb);
+
+ proc_idx = (proc_idx + 1) % ndesc;
+ }
+
+ priv->rx.proc_idx = proc_idx;
+
+ /* refill the Rx buffers */
+ while (proc_idx != done_idx) {
+ if (ave_set_rxdesc(ndev, done_idx))
+ break;
+ done_idx = (done_idx + 1) % ndesc;
+ }
+
+ priv->rx.done_idx = done_idx;
+
+ return npkts;
+}
+
+static inline u32 ave_irq_disable_all(struct net_device *ndev)
+{
+ u32 ret;
+
+ ret = ave_r32(ndev, AVE_GIMR);
+ ave_w32(ndev, AVE_GIMR, 0);
+
+ return ret;
+}
+
+static inline void ave_irq_restore(struct net_device *ndev, u32 val)
+{
+ ave_w32(ndev, AVE_GIMR, val);
+}
+
+static inline void ave_irq_enable(struct net_device *ndev, u32 bitflag)
+{
+ ave_w32(ndev, AVE_GIMR, ave_r32(ndev, AVE_GIMR) | bitflag);
+ ave_w32(ndev, AVE_GISR, bitflag);
+}
+
+static inline void ave_irq_disable(struct net_device *ndev, u32 bitflag)
+{
+ ave_w32(ndev, AVE_GIMR, ave_r32(ndev, AVE_GIMR) & ~bitflag);
+}
+
+static void ave_global_reset(struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ u32 grr, descc;
+ u32 val;
+
+ grr = ave_r32(ndev, AVE_GRR);
+ if ((grr & AVE_GRR_GRST) != AVE_GRR_GRST) {
+ descc = ave_r32(ndev, AVE_DESCC);
+ if ((descc & AVE_DESCC_RD0) == AVE_DESCC_RD0)
+ /* suspend Rx descriptor */
+ ave_desc_switch(ndev, AVE_DESC_RX_SUSPEND);
+ }
+
+ /* set config register */
+ val = AVE_CFGR_FLE | AVE_CFGR_IPFCEN | AVE_CFGR_CHE;
+ if (priv->phy_mode != PHY_INTERFACE_MODE_RGMII)
+ val |= AVE_CFGR_MII;
+ ave_w32(ndev, AVE_CFGR, val);
+
+ /* reset RMII register */
+ val = ave_r32(ndev, AVE_RSTCTRL);
+ val &= ~AVE_RSTCTRL_RMIIRST;
+ ave_w32(ndev, AVE_RSTCTRL, val);
+
+ /* assert reset */
+ ave_w32(ndev, AVE_GRR, AVE_GRR_GRST | AVE_GRR_PHYRST);
+ msleep(20);
+
+ /* 1st, negate PHY reset only */
+ ave_w32(ndev, AVE_GRR, AVE_GRR_GRST);
+ msleep(40);
+
+ /* negate reset */
+ ave_w32(ndev, AVE_GRR, 0);
+ msleep(40);
+
+ /* negate RMII register */
+ val = ave_r32(ndev, AVE_RSTCTRL);
+ val |= AVE_RSTCTRL_RMIIRST;
+ ave_w32(ndev, AVE_RSTCTRL, val);
+
+ /* disable all interrupt */
+ ave_irq_disable_all(ndev);
+}
+
+static void ave_rxf_reset(struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ u32 rxcr_org;
+
+ /* save and disable MAC receive op */
+ rxcr_org = ave_r32(ndev, AVE_RXCR);
+ ave_w32(ndev, AVE_RXCR, rxcr_org & (~AVE_RXCR_RXEN));
+
+ /* suspend Rx descriptor */
+ ave_desc_switch(ndev, AVE_DESC_RX_SUSPEND);
+
+ /* receive all packets before descriptor starts */
+ ave_rx(ndev, priv->rx.ndesc);
+
+ /* assert reset */
+ ave_w32(ndev, AVE_GRR, AVE_GRR_RXFFR);
+ usleep_range(40, 50);
+
+ /* negate reset */
+ ave_w32(ndev, AVE_GRR, 0);
+ usleep_range(10, 20);
+
+ /* negate interrupt status */
+ ave_w32(ndev, AVE_GISR, AVE_GI_RXOVF);
+
+ /* permit descriptor */
+ ave_desc_switch(ndev, AVE_DESC_RX_PERMIT);
+
+ /* restore MAC reccieve op */
+ ave_w32(ndev, AVE_RXCR, rxcr_org);
+}
+
+static irqreturn_t ave_interrupt(int irq, void *netdev)
+{
+ struct net_device *ndev = (struct net_device *)netdev;
+ struct ave_private *priv = netdev_priv(ndev);
+ u32 gimr_val, gisr_val;
+
+ gimr_val = ave_irq_disable_all(ndev);
+
+ /* get interrupt status */
+ gisr_val = ave_r32(ndev, AVE_GISR);
+
+ /* PHY */
+ if (gisr_val & AVE_GI_PHY) {
+ ave_w32(ndev, AVE_GISR, AVE_GI_PHY);
+ if (priv->internal_phy_interrupt)
+ phy_mac_interrupt(ndev->phydev, ndev->phydev->link);
+ }
+
+ /* check exceeding packet */
+ if (gisr_val & AVE_GI_RXERR) {
+ ave_w32(ndev, AVE_GISR, AVE_GI_RXERR);
+ netdev_err(ndev, "receive a packet exceeding frame buffer\n");
+ }
+
+ gisr_val &= gimr_val;
+ if (!gisr_val)
+ goto exit_isr;
+
+ /* RxFIFO overflow */
+ if (gisr_val & AVE_GI_RXOVF) {
+ priv->stats.rx_fifo_errors++;
+ ave_rxf_reset(ndev);
+ goto exit_isr;
+ }
+
+ /* Rx drop */
+ if (gisr_val & AVE_GI_RXDROP) {
+ priv->stats.rx_dropped++;
+ ave_w32(ndev, AVE_GISR, AVE_GI_RXDROP);
+ }
+
+ /* Rx interval */
+ if (gisr_val & AVE_GI_RXIINT) {
+ napi_schedule(&priv->napi_rx);
+ /* still force to disable Rx interrupt until NAPI finishes */
+ gimr_val &= ~AVE_GI_RXIINT;
+ }
+
+ /* Tx completed */
+ if (gisr_val & AVE_GI_TX) {
+ napi_schedule(&priv->napi_tx);
+ /* still force to disable Tx interrupt until NAPI finishes */
+ gimr_val &= ~AVE_GI_TX;
+ }
+
+exit_isr:
+ ave_irq_restore(ndev, gimr_val);
+
+ return IRQ_HANDLED;
+}
+
+static int ave_poll_rx(struct napi_struct *napi, int budget)
+{
+ struct ave_private *priv;
+ struct net_device *ndev;
+ int num;
+
+ priv = container_of(napi, struct ave_private, napi_rx);
+ ndev = priv->ndev;
+
+ num = ave_rx(ndev, budget);
+ if (num < budget) {
+ napi_complete_done(napi, num);
+
+ /* enable Rx interrupt when NAPI finishes */
+ ave_irq_enable(ndev, AVE_GI_RXIINT);
+ }
+
+ return num;
+}
+
+static int ave_poll_tx(struct napi_struct *napi, int budget)
+{
+ struct ave_private *priv;
+ struct net_device *ndev;
+ int num;
+
+ priv = container_of(napi, struct ave_private, napi_tx);
+ ndev = priv->ndev;
+
+ num = ave_tx_completion(ndev);
+ if (num < budget) {
+ napi_complete(napi);
+
+ /* enable Tx interrupt when NAPI finishes */
+ ave_irq_enable(ndev, AVE_GI_TX);
+ }
+
+ return num;
+}
+
+static void ave_pfsel_promisc_set(struct net_device *ndev,
+ unsigned int entry, u32 rxring)
+{
+ if (WARN_ON(entry > AVE_PF_SIZE))
+ return;
+
+ ave_pfsel_stop(ndev, entry);
+
+ /* set byte mask */
+ ave_w32(ndev, AVE_PFMBYTE(entry), 0xFFFFFFFF);
+ ave_w32(ndev, AVE_PFMBYTE(entry) + 4, 0xFFFFFFFF);
+
+ /* set bit mask filter */
+ ave_w32(ndev, AVE_PFMBIT(entry), 0x0000FFFF);
+
+ /* set selector to rxring */
+ ave_w32(ndev, AVE_PFSEL(entry), rxring);
+
+ ave_pfsel_start(ndev, entry);
+}
+
+static void ave_pfsel_init(struct net_device *ndev)
+{
+ int i;
+ unsigned char bcast_mac[ETH_ALEN];
+
+ eth_broadcast_addr(bcast_mac);
+
+ /* Stop all filter */
+ for (i = 0; i < AVE_PF_SIZE; i++)
+ ave_pfsel_stop(ndev, i);
+
+ /* promiscious entry, select ring 0 */
+ ave_pfsel_promisc_set(ndev, AVE_PFNUM_FILTER, 0);
+
+ /* unicast entry */
+ ave_pfsel_macaddr_set(ndev, AVE_PFNUM_UNICAST, ndev->dev_addr, 6);
+
+ /* broadcast entry */
+ ave_pfsel_macaddr_set(ndev, AVE_PFNUM_BROADCAST, bcast_mac, 6);
+}
+
+static void ave_adjust_link(struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ struct phy_device *phydev = ndev->phydev;
+ u32 val, txcr, rxcr, rxcr_org;
+
+ /* set RGMII speed */
+ val = ave_r32(ndev, AVE_TXCR);
+ val &= ~(AVE_TXCR_TXSPD_100 | AVE_TXCR_TXSPD_1G);
+
+ if (priv->phy_mode == PHY_INTERFACE_MODE_RGMII &&
+ phydev->speed == SPEED_1000)
+ val |= AVE_TXCR_TXSPD_1G;
+ else if (phydev->speed == SPEED_100)
+ val |= AVE_TXCR_TXSPD_100;
+
+ ave_w32(ndev, AVE_TXCR, val);
+
+ /* set RMII speed (100M/10M only) */
+ if (priv->phy_mode != PHY_INTERFACE_MODE_RGMII) {
+ val = ave_r32(ndev, AVE_LINKSEL);
+ if (phydev->speed == SPEED_10)
+ val &= ~AVE_LINKSEL_100M;
+ else
+ val |= AVE_LINKSEL_100M;
+ ave_w32(ndev, AVE_LINKSEL, val);
+ }
+
+ /* check current RXCR/TXCR */
+ rxcr = ave_r32(ndev, AVE_RXCR);
+ txcr = ave_r32(ndev, AVE_TXCR);
+ rxcr_org = rxcr;
+
+ if (phydev->duplex)
+ rxcr |= AVE_RXCR_FDUPEN;
+ else
+ rxcr &= ~AVE_RXCR_FDUPEN;
+
+ if (phydev->pause) {
+ rxcr |= AVE_RXCR_FLOCTR;
+ txcr |= AVE_TXCR_FLOCTR;
+ } else {
+ rxcr &= ~AVE_RXCR_FLOCTR;
+ txcr &= ~AVE_TXCR_FLOCTR;
+ }
+
+ if (rxcr_org != rxcr) {
+ /* disable Rx mac */
+ ave_w32(ndev, AVE_RXCR, rxcr & ~AVE_RXCR_RXEN);
+ /* change and enable TX/Rx mac */
+ ave_w32(ndev, AVE_TXCR, txcr);
+ ave_w32(ndev, AVE_RXCR, rxcr);
+ }
+
+ if (phydev->link)
+ netif_carrier_on(ndev);
+ else
+ netif_carrier_off(ndev);
+
+ phy_print_status(phydev);
+}
+
+static int ave_init(struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ struct device *dev = ndev->dev.parent;
+ struct device_node *phy_node, *np = dev->of_node;
+ struct phy_device *phydev;
+ const void *mac_addr;
+ u32 supported;
+
+ /* get mac address */
+ mac_addr = of_get_mac_address(np);
+ if (mac_addr)
+ ether_addr_copy(ndev->dev_addr, mac_addr);
+
+ /* if the mac address is invalid, use random mac address */
+ if (!is_valid_ether_addr(ndev->dev_addr)) {
+ eth_hw_addr_random(ndev);
+ dev_warn(dev, "Using random MAC address: %pM\n",
+ ndev->dev_addr);
+ }
+
+ /* attach PHY with MAC */
+ phy_node = of_get_next_available_child(np, NULL);
+ phydev = of_phy_connect(ndev, phy_node,
+ ave_adjust_link, 0, priv->phy_mode);
+ if (!phydev) {
+ dev_err(dev, "could not attach to PHY\n");
+ return -ENODEV;
+ }
+ of_node_put(phy_node);
+
+ priv->phydev = phydev;
+ phydev->autoneg = AUTONEG_ENABLE;
+ phydev->speed = 0;
+ phydev->duplex = 0;
+
+ dev_info(dev, "connected to %s phy with id 0x%x\n",
+ phydev->drv->name, phydev->phy_id);
+
+ if (priv->phy_mode != PHY_INTERFACE_MODE_RGMII) {
+ supported = phydev->supported;
+ phydev->supported &= ~PHY_GBIT_FEATURES;
+ phydev->supported |= supported & PHY_BASIC_FEATURES;
+ }
+
+ /* PHY interrupt stop instruction is needed because the interrupt
+ * continues to assert.
+ */
+ phy_stop_interrupts(phydev);
+
+ /* When PHY driver can't handle its interrupt directly,
+ * interrupt request always fails and polling method is used
+ * alternatively. In this case, the libphy says
+ * "libphy: uniphier-mdio: Can't get IRQ -1 (PHY)".
+ */
+ phy_start_interrupts(phydev);
+
+ phy_start_aneg(phydev);
+
+ return 0;
+}
+
+static void ave_uninit(struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+
+ phy_stop_interrupts(priv->phydev);
+ phy_disconnect(priv->phydev);
+}
+
+static int ave_open(struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ int entry;
+ u32 val;
+
+ /* initialize Tx work */
+ priv->tx.proc_idx = 0;
+ priv->tx.done_idx = 0;
+ memset(priv->tx.desc, 0, sizeof(struct ave_desc) * priv->tx.ndesc);
+
+ /* initialize Tx descriptor */
+ for (entry = 0; entry < priv->tx.ndesc; entry++) {
+ ave_wdesc(ndev, AVE_DESCID_TX, entry, 0, 0);
+ ave_wdesc_addr(ndev, AVE_DESCID_TX, entry, 4, 0);
+ }
+ ave_w32(ndev, AVE_TXDC, AVE_TXDC_ADDR_START
+ | (((priv->tx.ndesc * priv->desc_size) << 16) & AVE_TXDC_SIZE));
+
+ /* initialize Rx work */
+ priv->rx.proc_idx = 0;
+ priv->rx.done_idx = 0;
+ memset(priv->rx.desc, 0, sizeof(struct ave_desc) * priv->rx.ndesc);
+
+ /* initialize Rx descriptor and buffer */
+ for (entry = 0; entry < priv->rx.ndesc; entry++) {
+ if (ave_set_rxdesc(ndev, entry))
+ break;
+ }
+ ave_w32(ndev, AVE_RXDC0, AVE_RXDC0_ADDR_START
+ | (((priv->rx.ndesc * priv->desc_size) << 16) & AVE_RXDC0_SIZE));
+
+ /* enable descriptor */
+ ave_desc_switch(ndev, AVE_DESC_START);
+
+ /* initialize filter */
+ ave_pfsel_init(ndev);
+
+ /* set macaddr */
+ val = le32_to_cpu(((u32 *)ndev->dev_addr)[0]);
+ ave_w32(ndev, AVE_RXMAC1R, val);
+ val = (u32)le16_to_cpu(((u16 *)ndev->dev_addr)[2]);
+ ave_w32(ndev, AVE_RXMAC2R, val);
+
+ /* set Rx configuration */
+ /* full duplex, enable pause drop, enalbe flow control */
+ val = AVE_RXCR_RXEN | AVE_RXCR_FDUPEN | AVE_RXCR_DRPEN |
+ AVE_RXCR_FLOCTR | (AVE_MAX_ETHFRAME & AVE_RXCR_MPSIZ_MASK);
+ ave_w32(ndev, AVE_RXCR, val);
+
+ /* set Tx configuration */
+ /* enable flow control, disable loopback */
+ ave_w32(ndev, AVE_TXCR, AVE_TXCR_FLOCTR);
+
+ /* enable timer, clear EN,INTM, and mask interval unit(BSCK) */
+ val = ave_r32(ndev, AVE_IIRQC) & AVE_IIRQC_BSCK;
+ val |= AVE_IIRQC_EN0 | (AVE_INTM_COUNT << 16);
+ ave_w32(ndev, AVE_IIRQC, val);
+
+ /* set interrupt mask */
+ val = AVE_GI_RXIINT | AVE_GI_RXOVF | AVE_GI_TX;
+ val |= (priv->internal_phy_interrupt) ? AVE_GI_PHY : 0;
+ ave_irq_restore(ndev, val);
+
+ napi_enable(&priv->napi_rx);
+ napi_enable(&priv->napi_tx);
+
+ phy_start(ndev->phydev);
+ netif_start_queue(ndev);
+
+ return 0;
+}
+
+static int ave_stop(struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ int entry;
+
+ /* disable all interrupt */
+ ave_irq_disable_all(ndev);
+ disable_irq(ndev->irq);
+
+ netif_tx_disable(ndev);
+ phy_stop(ndev->phydev);
+ napi_disable(&priv->napi_tx);
+ napi_disable(&priv->napi_rx);
+
+ /* free Tx buffer */
+ for (entry = 0; entry < priv->tx.ndesc; entry++) {
+ if (!priv->tx.desc[entry].skbs)
+ continue;
+
+ ave_dma_unmap(ndev, &priv->tx.desc[entry], DMA_TO_DEVICE);
+ dev_kfree_skb_any(priv->tx.desc[entry].skbs);
+ priv->tx.desc[entry].skbs = NULL;
+ }
+ priv->tx.proc_idx = 0;
+ priv->tx.done_idx = 0;
+
+ /* free Rx buffer */
+ for (entry = 0; entry < priv->rx.ndesc; entry++) {
+ if (!priv->rx.desc[entry].skbs)
+ continue;
+
+ ave_dma_unmap(ndev, &priv->rx.desc[entry], DMA_FROM_DEVICE);
+ dev_kfree_skb_any(priv->rx.desc[entry].skbs);
+ priv->rx.desc[entry].skbs = NULL;
+ }
+ priv->rx.proc_idx = 0;
+ priv->rx.done_idx = 0;
+
+ return 0;
+}
+
+static int ave_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ u32 proc_idx, done_idx, ndesc, cmdsts;
+ int freepkt;
+ unsigned char *buffptr = NULL; /* buffptr for descriptor */
+ unsigned int len;
+ dma_addr_t paddr;
+
+ proc_idx = priv->tx.proc_idx;
+ done_idx = priv->tx.done_idx;
+ ndesc = priv->tx.ndesc;
+ freepkt = ((done_idx + ndesc - 1) - proc_idx) % ndesc;
+
+ /* not enough entry, then we stop queue */
+ if (unlikely(freepkt < 2)) {
+ netif_stop_queue(ndev);
+ if (unlikely(freepkt < 1))
+ return NETDEV_TX_BUSY;
+ }
+
+ priv->tx.desc[proc_idx].skbs = skb;
+
+ /* add padding for short packet */
+ if (skb_padto(skb, ETH_ZLEN)) {
+ dev_kfree_skb_any(skb);
+ return NETDEV_TX_OK;
+ }
+
+ buffptr = skb->data - NET_IP_ALIGN;
+ len = max_t(unsigned int, ETH_ZLEN, skb->len);
+
+ paddr = ave_dma_map(ndev, &priv->tx.desc[proc_idx], buffptr,
+ len + NET_IP_ALIGN, DMA_TO_DEVICE);
+ paddr += NET_IP_ALIGN;
+
+ /* set buffer address to descriptor */
+ ave_wdesc_addr(ndev, AVE_DESCID_TX, proc_idx, 4, paddr);
+
+ /* set flag and length to send */
+ cmdsts = AVE_STS_OWN | AVE_STS_1ST | AVE_STS_LAST
+ | (len & AVE_STS_PKTLEN_TX);
+
+ /* set interrupt per AVE_FORCE_TXINTCNT or when queue is stopped */
+ if (!(proc_idx % AVE_FORCE_TXINTCNT) || netif_queue_stopped(ndev))
+ cmdsts |= AVE_STS_INTR;
+
+ /* disable checksum calculation when skb doesn't calurate checksum */
+ if (skb->ip_summed == CHECKSUM_NONE ||
+ skb->ip_summed == CHECKSUM_UNNECESSARY)
+ cmdsts |= AVE_STS_NOCSUM;
+
+ /* set cmdsts */
+ ave_wdesc(ndev, AVE_DESCID_TX, proc_idx, 0, cmdsts);
+
+ priv->tx.proc_idx = (proc_idx + 1) % ndesc;
+
+ return NETDEV_TX_OK;
+}
+
+static int ave_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd)
+{
+ return phy_mii_ioctl(ndev->phydev, ifr, cmd);
+}
+
+static void ave_set_rx_mode(struct net_device *ndev)
+{
+ int count, mc_cnt = netdev_mc_count(ndev);
+ struct netdev_hw_addr *hw_adr;
+ u32 val;
+ u8 v4multi_macadr[6] = { 0x01, 0x00, 0x00, 0x00, 0x00, 0x00 };
+ u8 v6multi_macadr[6] = { 0x33, 0x00, 0x00, 0x00, 0x00, 0x00 };
+
+ /* MAC addr filter enable for promiscious mode */
+ val = ave_r32(ndev, AVE_RXCR);
+ if (ndev->flags & IFF_PROMISC || !mc_cnt)
+ val &= ~AVE_RXCR_AFEN;
+ else
+ val |= AVE_RXCR_AFEN;
+ ave_w32(ndev, AVE_RXCR, val);
+
+ /* set all multicast address */
+ if ((ndev->flags & IFF_ALLMULTI) || (mc_cnt > AVE_PF_MULTICAST_SIZE)) {
+ ave_pfsel_macaddr_set(ndev, AVE_PFNUM_MULTICAST,
+ v4multi_macadr, 1);
+ ave_pfsel_macaddr_set(ndev, AVE_PFNUM_MULTICAST + 1,
+ v6multi_macadr, 1);
+ } else {
+ /* stop all multicast filter */
+ for (count = 0; count < AVE_PF_MULTICAST_SIZE; count++)
+ ave_pfsel_stop(ndev, AVE_PFNUM_MULTICAST + count);
+
+ /* set multicast addresses */
+ count = 0;
+ netdev_for_each_mc_addr(hw_adr, ndev) {
+ if (count == mc_cnt)
+ break;
+ ave_pfsel_macaddr_set(ndev, AVE_PFNUM_MULTICAST + count,
+ hw_adr->addr, 6);
+ count++;
+ }
+ }
+}
+
+static struct net_device_stats *ave_stats(struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ u32 drop_num = 0;
+
+ priv->stats.rx_errors = ave_r32(ndev, AVE_BFCR);
+
+ drop_num += ave_r32(ndev, AVE_RX0OVFFC);
+ drop_num += ave_r32(ndev, AVE_SN5FC);
+ drop_num += ave_r32(ndev, AVE_SN6FC);
+ drop_num += ave_r32(ndev, AVE_SN7FC);
+ priv->stats.rx_dropped = drop_num;
+
+ return &priv->stats;
+}
+
+static int ave_set_mac_address(struct net_device *ndev, void *p)
+{
+ int ret = eth_mac_addr(ndev, p);
+ u32 val;
+
+ if (ret)
+ return ret;
+
+ /* set macaddr */
+ val = le32_to_cpu(((u32 *)ndev->dev_addr)[0]);
+ ave_w32(ndev, AVE_RXMAC1R, val);
+ val = (u32)le16_to_cpu(((u16 *)ndev->dev_addr)[2]);
+ ave_w32(ndev, AVE_RXMAC2R, val);
+
+ /* pfsel unicast entry */
+ ave_pfsel_macaddr_set(ndev, AVE_PFNUM_UNICAST, ndev->dev_addr, 6);
+
+ return 0;
+}
+
+static const struct net_device_ops ave_netdev_ops = {
+ .ndo_init = ave_init,
+ .ndo_uninit = ave_uninit,
+ .ndo_open = ave_open,
+ .ndo_stop = ave_stop,
+ .ndo_start_xmit = ave_start_xmit,
+ .ndo_do_ioctl = ave_ioctl,
+ .ndo_set_rx_mode = ave_set_rx_mode,
+ .ndo_get_stats = ave_stats,
+ .ndo_set_mac_address = ave_set_mac_address,
+};
+
+static int ave_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct device_node *np = dev->of_node;
+ u32 desc_bits, ave_id;
+ struct reset_control *rst;
+ struct ave_private *priv;
+ phy_interface_t phy_mode;
+ struct net_device *ndev;
+ struct resource *res;
+ void __iomem *base;
+ int irq, ret = 0;
+ char buf[ETHTOOL_FWVERS_LEN];
+
+ /* get phy mode */
+ phy_mode = of_get_phy_mode(np);
+ if (phy_mode < 0) {
+ dev_err(dev, "phy-mode not found\n");
+ return -EINVAL;
+ }
+
+ irq = platform_get_irq(pdev, 0);
+ if (irq < 0) {
+ dev_err(dev, "IRQ not found\n");
+ return irq;
+ }
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ base = devm_ioremap_resource(dev, res);
+ if (IS_ERR(base))
+ return PTR_ERR(base);
+
+ /* alloc netdevice */
+ ndev = alloc_etherdev(sizeof(struct ave_private));
+ if (!ndev) {
+ dev_err(dev, "can't allocate ethernet device\n");
+ return -ENOMEM;
+ }
+
+ ndev->base_addr = (unsigned long)base;
+ ndev->irq = irq;
+ ndev->netdev_ops = &ave_netdev_ops;
+ ndev->ethtool_ops = &ave_ethtool_ops;
+ SET_NETDEV_DEV(ndev, dev);
+
+ /* support hardware checksum */
+ ndev->features |= (NETIF_F_IP_CSUM | NETIF_F_RXCSUM);
+ ndev->hw_features |= (NETIF_F_IP_CSUM | NETIF_F_RXCSUM);
+
+ ndev->max_mtu = AVE_MAX_ETHFRAME - (ETH_HLEN + ETH_FCS_LEN);
+
+ priv = netdev_priv(ndev);
+ priv->ndev = ndev;
+ priv->msg_enable = netif_msg_init(-1, AVE_DEFAULT_MSG_ENABLE);
+ priv->phy_mode = phy_mode;
+
+ /* get bits of descriptor from devicetree */
+ of_property_read_u32(np, "socionext,desc-bits", &desc_bits);
+ priv->desc_size = AVE_DESC_SIZE_32;
+ if (desc_bits == 64)
+ priv->desc_size = AVE_DESC_SIZE_64;
+ else if (desc_bits != 32)
+ dev_warn(dev, "Defaulting to 32bit descriptor\n");
+
+ /* use internal phy interrupt */
+ priv->internal_phy_interrupt =
+ of_property_read_bool(np, "socionext,internal-phy-interrupt");
+
+ /* setting private data for descriptor */
+ priv->tx.daddr = IS_DESC_64BIT(priv) ? AVE_TXDM_64 : AVE_TXDM_32;
+ priv->tx.ndesc = AVE_NR_TXDESC;
+ priv->tx.desc = devm_kzalloc(dev,
+ sizeof(struct ave_desc) * priv->tx.ndesc,
+ GFP_KERNEL);
+ if (!priv->tx.desc)
+ return -ENOMEM;
+
+ priv->rx.daddr = IS_DESC_64BIT(priv) ? AVE_RXDM_64 : AVE_RXDM_32;
+ priv->rx.ndesc = AVE_NR_RXDESC;
+ priv->rx.desc = devm_kzalloc(dev,
+ sizeof(struct ave_desc) * priv->rx.ndesc,
+ GFP_KERNEL);
+ if (!priv->rx.desc)
+ return -ENOMEM;
+
+ /* enable clock */
+ priv->clk = devm_clk_get(dev, NULL);
+ if (IS_ERR(priv->clk))
+ priv->clk = NULL;
+ clk_prepare_enable(priv->clk);
+
+ /* reset block */
+ rst = devm_reset_control_get(dev, NULL);
+ if (!IS_ERR_OR_NULL(rst)) {
+ reset_control_deassert(rst);
+ reset_control_put(rst);
+ }
+
+ /* reset mac and phy */
+ ave_global_reset(ndev);
+
+ /* request interrupt */
+ ret = devm_request_irq(dev, irq, ave_interrupt,
+ IRQF_SHARED, ndev->name, ndev);
+ if (ret)
+ goto err_req_irq;
+
+ /* create MDIO bus */
+ priv->mdio = devm_mdiobus_alloc(dev);
+ if (!priv->mdio) {
+ ret = -ENOMEM;
+ goto err_mdiobus_alloc;
+ }
+
+ priv->mdio->priv = ndev;
+ priv->mdio->parent = dev;
+ priv->mdio->read = ave_mdiobus_read;
+ priv->mdio->write = ave_mdiobus_write;
+ priv->mdio->name = "uniphier-mdio";
+ snprintf(priv->mdio->id, MII_BUS_ID_SIZE, "%s-%x",
+ pdev->name, pdev->id);
+
+ ret = of_mdiobus_register(priv->mdio, np);
+ if (ret) {
+ dev_err(dev, "of_mdiobus_register(%s) failed\n", np->full_name);
+ ret = -ENOMEM;
+ goto err_mdiobus_register;
+ }
+
+ /* Register as a NAPI supported driver */
+ netif_napi_add(ndev, &priv->napi_rx, ave_poll_rx, priv->rx.ndesc);
+ netif_tx_napi_add(ndev, &priv->napi_tx, ave_poll_tx, priv->tx.ndesc);
+
+ ret = register_netdev(ndev);
+ if (ret) {
+ dev_err(dev, "failed to register netdevice\n");
+ goto err_netdev_register;
+ }
+
+ platform_set_drvdata(pdev, ndev);
+
+ /* get ID and version */
+ ave_id = ave_r32(ndev, AVE_IDR);
+ ave_get_fwversion(ndev, buf, sizeof(buf));
+
+ dev_info(dev, "Socionext %c%c%c%c Ethernet IP %s (irq=%d, phy=%s)\n",
+ (ave_id >> 24) & 0xff, (ave_id >> 16) & 0xff,
+ (ave_id >> 8) & 0xff, (ave_id >> 0) & 0xff,
+ buf, ndev->irq, phy_modes(phy_mode));
+
+ return 0;
+
+err_netdev_register:
+ netif_napi_del(&priv->napi_rx);
+ netif_napi_del(&priv->napi_tx);
+ mdiobus_unregister(priv->mdio);
+err_mdiobus_register:
+err_mdiobus_alloc:
+err_req_irq:
+ free_netdev(ndev);
+ clk_disable_unprepare(priv->clk);
+
+ return ret;
+}
+
+static int ave_remove(struct platform_device *pdev)
+{
+ struct net_device *ndev = platform_get_drvdata(pdev);
+ struct ave_private *priv = netdev_priv(ndev);
+
+ unregister_netdev(ndev);
+ netif_napi_del(&priv->napi_rx);
+ netif_napi_del(&priv->napi_tx);
+ mdiobus_unregister(priv->mdio);
+ free_netdev(ndev);
+ clk_disable_unprepare(priv->clk);
+
+ return 0;
+}
+
+static const struct of_device_id of_ave_match[] = {
+ { .compatible = "socionext,uniphier-ave4" },
+ { /* Sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, of_ave_match);
+
+static struct platform_driver ave_driver = {
+ .probe = ave_probe,
+ .remove = ave_remove,
+ .driver = {
+ .name = "ave",
+ .of_match_table = of_ave_match,
+ },
+};
+module_platform_driver(ave_driver);
+
+MODULE_DESCRIPTION("Socionext UniPhier AVE ethernet driver");
+MODULE_LICENSE("GPL v2");
--
2.7.4
^ permalink raw reply related
* Re: [PATCH v5 10/10] net: stmmac: dwmac-sun8i: Handle integrated/external MDIOs
From: Andrew Lunn @ 2017-09-08 13:05 UTC (permalink / raw)
To: Corentin Labbe
Cc: robh+dt, mark.rutland, maxime.ripard, wens, linux,
catalin.marinas, will.deacon, peppe.cavallaro, alexandre.torgue,
f.fainelli, netdev, devicetree, linux-arm-kernel, linux-kernel
In-Reply-To: <20170908071156.5115-11-clabbe.montjoie@gmail.com>
> +#define DWMAC_sUN8I_MDIO_MUX_INTERNAL_ID 0
> +#define DWMAC_sUN8I_MDIO_MUX_EXTERNAL_ID 1
>
> /* H3/A64 specific bits */
> #define SYSCON_RMII_EN BIT(13) /* 1: enable RMII (overrides EPIT) */
> @@ -634,6 +639,76 @@ static int sun8i_dwmac_reset(struct stmmac_priv *priv)
> return 0;
> }
>
> +/* MDIO multiplexing switch function
> + * This function is called by the mdio-mux layer when it thinks the mdio bus
> + * multiplexer needs to switch.
> + * 'current_child' is the current value of the mux register
> + * 'desired_child' is the value of the 'reg' property of the target child MDIO
> + * node.
> + * The first time this function is called, current_child == -1.
> + * If current_child == desired_child, then the mux is already set to the
> + * correct bus.
> + *
> + * Note that we do not use reg/mask like mdio-mux-mmioreg because we need to
> + * know easily which bus is used (reset must be done only for desired bus).
> + */
> +static int mdio_mux_syscon_switch_fn(int current_child, int desired_child,
> + void *data)
> +{
> + struct stmmac_priv *priv = data;
> + struct sunxi_priv_data *gmac = priv->plat->bsp_priv;
> + u32 reg, val;
> + int ret = 0;
> + bool need_reset = false;
> +
> + if (current_child ^ desired_child) {
> + regmap_read(gmac->regmap, SYSCON_EMAC_REG, ®);
> + switch (desired_child) {
> + case DWMAC_sUN8I_MDIO_MUX_INTERNAL_ID:
> + dev_info(priv->device, "Switch mux to internal PHY");
> + val = (reg & ~H3_EPHY_MUX_MASK) | H3_EPHY_SELECT;
> + if (gmac->use_internal_phy)
> + need_reset = true;
> + break;
This i don't get. Why do you need use_internal_phy? Isn't that
implicit from DWMAC_sUN8I_MDIO_MUX_INTERNAL_ID? Is it even possible to
use an external PHY on the internal MDIO bus?
> + case DWMAC_sUN8I_MDIO_MUX_EXTERNAL_ID:
> + dev_info(priv->device, "Switch mux to external PHY");
> + val = (reg & ~H3_EPHY_MUX_MASK) | H3_EPHY_SHUTDOWN;
> + if (!gmac->use_internal_phy)
> + need_reset = true;
> + break;
And is it possible to use the internal PHY on the external bus?
Andrew
^ permalink raw reply
* Re: [PATCH net] bpf: don't select potentially stale ri->map from buggy xdp progs
From: Jesper Dangaard Brouer @ 2017-09-08 13:07 UTC (permalink / raw)
To: Daniel Borkmann; +Cc: andy, davem, ast, john.fastabend, netdev, brouer
In-Reply-To: <59B28E45.40700@iogearbox.net>
On Fri, 08 Sep 2017 14:34:13 +0200
Daniel Borkmann <daniel@iogearbox.net> wrote:
> On 09/08/2017 01:52 PM, Jesper Dangaard Brouer wrote:
> > On Fri, 08 Sep 2017 12:34:28 +0200 Daniel Borkmann <daniel@iogearbox.net> wrote:
> >> On 09/08/2017 07:06 AM, Jesper Dangaard Brouer wrote:
> >>> On Fri, 8 Sep 2017 00:14:51 +0200
> >>> Daniel Borkmann <daniel@iogearbox.net> wrote:
> >>>
> >>>> + /* This is really only caused by a deliberately crappy
> >>>> + * BPF program, normally we would never hit that case,
> >>>> + * so no need to inform someone via tracepoints either,
> >>>> + * just bail out.
> >>>> + */
> >>>> + if (unlikely(map_owner != xdp_prog))
> >>>> + return -EINVAL;
> >>>
> >>> IMHO we do need to call the tracepoint here. It is not just crappy
> >>> BPF-progs that cause this situation, it is also drivers not implementing
> >>> XDP_REDIRECT yet (which is all but ixgbe). Due to the level XDP
> >>> operates at, tracepoints are the only way users can runtime troubleshoot
> >>> their XDP programs.
> >>
> >> Drivers not implementing XDP_REDIRECT don't even get there in
> >> the first place. What they will do is to hit the 'default' case
> >> when they check for the action code from the BPF program. Then
> >> call into bpf_warn_invalid_xdp_action(act), and fall-through
> >> to hit the tracepoint at trace_xdp_exception() which is also
> >> triggered by XDP_ABORTED usually. So when that happens we do
> >> complain loudly and call a tracepoint already. We should probably
> >> tweak the bpf_warn_invalid_xdp_action() message a little to make
> >> it clear that the action could also just be unsupported by the
> >> driver instead of being illegal.
> >
> > Yes. drivers not implementing XDP_REDIRECT will cause a tracepoint
> > trace_xdp_exception() to be called for its _own_ packets.
>
> Yep, plus a big one time warning for the case a user doesn't
> look at tracepoints initially.
>
> > But it will still setup and leave map and map_owner pointer dangling.
> > Another NIC can load an xdp_prog that return XDP_REDIRECT, which will hit
> > above if-statement, and its packets will disappear, without getting
> > recorded by a tracepoint (thus hard to debug!).
>
> If a user wants to reproduce this exact error, he would need
> to go and reload the program on the driver not supporting the
> XDP_REDIRECT in the first place, and then reload his buggy program
> on the other driver supporting XDP_REDIRECT but w/o having called
> bpf_xdp_redirect_map(), so exactly once on the switch from one
> driver to another with this misuse, any subsequent packets will
> trigger _trace_xdp_redirect_err(), same way as if the buggy
> program was loaded to the 2nd driver from the beginning since
> the map and ifindex etc will be zero, hence my comment on this.
We can agree that the second program that experience the side-effect is
also buggy, as just returning XDP_REDIRECT without calling
bpf_xdp_redirect_map() or bpf_xdp_redirect(), is a bug in the bpf
program. Thus, the comment about a "deliberately crappy BPF program"
is not wrong.
You don't have to load and unload xdp programs. My test is simply
having two XDP programs running. 1. xdp_redirect_map on mlx5 which
doesn't implement XDP_REDIRECT, and 2. a "deliberately crappy BPF
program" on ixgbe that just returns XDP_REDIRECT.
In below output I've used -EFAULT == -14 to capture this situation
happening:
ksoftirqd/3 28 [003] 3437.829882: xdp:xdp_redirect_err: prog_id=3 action=REDIRECT ifindex=2 to_ifindex=0 err=-22
swapper 0 [005] 3437.829882: xdp:xdp_redirect_err: prog_id=3 action=REDIRECT ifindex=2 to_ifindex=0 err=-22
ksoftirqd/0 7 [000] 3437.829882: xdp:xdp_exception: prog_id=5 action=REDIRECT ifindex=7
ksoftirqd/4 34 [004] 3437.829882: xdp:xdp_redirect_err: prog_id=3 action=REDIRECT ifindex=2 to_ifindex=0 err=-22
ksoftirqd/2 22 [002] 3437.829882: xdp:xdp_redirect_err: prog_id=3 action=REDIRECT ifindex=2 to_ifindex=0 err=-22
ksoftirqd/3 28 [003] 3437.829882: xdp:xdp_redirect_err: prog_id=3 action=REDIRECT ifindex=2 to_ifindex=0 err=-22
swapper 0 [005] 3437.829882: xdp:xdp_redirect_err: prog_id=3 action=REDIRECT ifindex=2 to_ifindex=0 err=-22
swapper 0 [005] 3437.829882: xdp:xdp_redirect_err: prog_id=3 action=REDIRECT ifindex=2 to_ifindex=0 err=-22
ksoftirqd/3 28 [003] 3437.829882: xdp:xdp_redirect_err: prog_id=3 action=REDIRECT ifindex=2 to_ifindex=0 err=-22
ksoftirqd/2 22 [002] 3437.829882: xdp:xdp_redirect_err: prog_id=3 action=REDIRECT ifindex=2 to_ifindex=0 err=-22
ksoftirqd/4 34 [004] 3437.829882: xdp:xdp_redirect_err: prog_id=3 action=REDIRECT ifindex=2 to_ifindex=0 err=-22
ksoftirqd/3 28 [003] 3437.829882: xdp:xdp_redirect_err: prog_id=3 action=REDIRECT ifindex=2 to_ifindex=0 err=-22
ksoftirqd/2 22 [002] 3437.829882: xdp:xdp_redirect_err: prog_id=3 action=REDIRECT ifindex=2 to_ifindex=0 err=-22
ksoftirqd/0 7 [000] 3437.829882: xdp:xdp_redirect_map_err: prog_id=3 action=REDIRECT ifindex=2 to_ifindex=0 err=-14 map_id=5 map_index=0
swapper 0 [005] 3437.829883: xdp:xdp_redirect_err: prog_id=3 action=REDIRECT ifindex=2 to_ifindex=0 err=-22
ksoftirqd/3 28 [003] 3437.829883: xdp:xdp_redirect_err: prog_id=3 action=REDIRECT ifindex=2 to_ifindex=0 err=-22
And I can see I made a mistake and dereference the map_id ;-)
BTW, just to make it clear, I love the rest of the patch. And I love
how you solved this. Cool trick. You also closed a hole where someone
could set the map in one bpf_prog and cause the next bpf program to
forward using this map (this could be a policy violation).
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
LinkedIn: http://www.linkedin.com/in/brouer
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox