* [PATCH net-next v2 2/2] reuseport, bpf: add test case for bpf_get_numa_node_id
From: Daniel Borkmann @ 2016-10-21 10:46 UTC (permalink / raw)
To: davem; +Cc: alexei.starovoitov, edumazet, netdev, Daniel Borkmann
In-Reply-To: <cover.1477043972.git.daniel@iogearbox.net>
The test case is very similar to reuseport_bpf_cpu, only that here
we select socket members based on current numa node id.
# numactl -H
available: 2 nodes (0-1)
node 0 cpus: 0 1 2 3 4 5 12 13 14 15 16 17
node 0 size: 128867 MB
node 0 free: 120080 MB
node 1 cpus: 6 7 8 9 10 11 18 19 20 21 22 23
node 1 size: 96765 MB
node 1 free: 87504 MB
node distances:
node 0 1
0: 10 20
1: 20 10
# ./reuseport_bpf_numa
---- IPv4 UDP ----
send node 0, receive socket 0
send node 1, receive socket 1
send node 1, receive socket 1
send node 0, receive socket 0
---- IPv6 UDP ----
send node 0, receive socket 0
send node 1, receive socket 1
send node 1, receive socket 1
send node 0, receive socket 0
---- IPv4 TCP ----
send node 0, receive socket 0
send node 1, receive socket 1
send node 1, receive socket 1
send node 0, receive socket 0
---- IPv6 TCP ----
send node 0, receive socket 0
send node 1, receive socket 1
send node 1, receive socket 1
send node 0, receive socket 0
SUCCESS
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
tools/testing/selftests/net/.gitignore | 1 +
tools/testing/selftests/net/Makefile | 11 +-
tools/testing/selftests/net/reuseport_bpf_numa.c | 255 +++++++++++++++++++++++
3 files changed, 263 insertions(+), 4 deletions(-)
create mode 100644 tools/testing/selftests/net/reuseport_bpf_numa.c
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 0840684..afe109e 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -3,4 +3,5 @@ psock_fanout
psock_tpacket
reuseport_bpf
reuseport_bpf_cpu
+reuseport_bpf_numa
reuseport_dualstack
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 0e53407..e24e4c8 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -1,14 +1,17 @@
# Makefile for net selftests
-CFLAGS = -Wall -O2 -g
-
+CFLAGS = -Wall -Wl,--no-as-needed -O2 -g
CFLAGS += -I../../../../usr/include/
-NET_PROGS = socket psock_fanout psock_tpacket reuseport_bpf reuseport_bpf_cpu reuseport_dualstack
+NET_PROGS = socket
+NET_PROGS += psock_fanout psock_tpacket
+NET_PROGS += reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
+NET_PROGS += reuseport_dualstack
all: $(NET_PROGS)
+reuseport_bpf_numa: LDFLAGS += -lnuma
%: %.c
- $(CC) $(CFLAGS) -o $@ $^
+ $(CC) $(CFLAGS) $(LDFLAGS) -o $@ $^
TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh
TEST_FILES := $(NET_PROGS)
diff --git a/tools/testing/selftests/net/reuseport_bpf_numa.c b/tools/testing/selftests/net/reuseport_bpf_numa.c
new file mode 100644
index 0000000..6f20bc9
--- /dev/null
+++ b/tools/testing/selftests/net/reuseport_bpf_numa.c
@@ -0,0 +1,255 @@
+/*
+ * Test functionality of BPF filters with SO_REUSEPORT. Same test as
+ * in reuseport_bpf_cpu, only as one socket per NUMA node.
+ */
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <linux/filter.h>
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/unistd.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/epoll.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <unistd.h>
+#include <numa.h>
+
+static const int PORT = 8888;
+
+static void build_rcv_group(int *rcv_fd, size_t len, int family, int proto)
+{
+ struct sockaddr_storage addr;
+ struct sockaddr_in *addr4;
+ struct sockaddr_in6 *addr6;
+ size_t i;
+ int opt;
+
+ switch (family) {
+ case AF_INET:
+ addr4 = (struct sockaddr_in *)&addr;
+ addr4->sin_family = AF_INET;
+ addr4->sin_addr.s_addr = htonl(INADDR_ANY);
+ addr4->sin_port = htons(PORT);
+ break;
+ case AF_INET6:
+ addr6 = (struct sockaddr_in6 *)&addr;
+ addr6->sin6_family = AF_INET6;
+ addr6->sin6_addr = in6addr_any;
+ addr6->sin6_port = htons(PORT);
+ break;
+ default:
+ error(1, 0, "Unsupported family %d", family);
+ }
+
+ for (i = 0; i < len; ++i) {
+ rcv_fd[i] = socket(family, proto, 0);
+ if (rcv_fd[i] < 0)
+ error(1, errno, "failed to create receive socket");
+
+ opt = 1;
+ if (setsockopt(rcv_fd[i], SOL_SOCKET, SO_REUSEPORT, &opt,
+ sizeof(opt)))
+ error(1, errno, "failed to set SO_REUSEPORT");
+
+ if (bind(rcv_fd[i], (struct sockaddr *)&addr, sizeof(addr)))
+ error(1, errno, "failed to bind receive socket");
+
+ if (proto == SOCK_STREAM && listen(rcv_fd[i], len * 10))
+ error(1, errno, "failed to listen on receive port");
+ }
+}
+
+static void attach_bpf(int fd)
+{
+ static char bpf_log_buf[65536];
+ static const char bpf_license[] = "";
+
+ int bpf_fd;
+ const struct bpf_insn prog[] = {
+ /* R0 = bpf_get_numa_node_id() */
+ { BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_numa_node_id },
+ /* return R0 */
+ { BPF_JMP | BPF_EXIT, 0, 0, 0, 0 }
+ };
+ union bpf_attr attr;
+
+ memset(&attr, 0, sizeof(attr));
+ attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
+ attr.insn_cnt = sizeof(prog) / sizeof(prog[0]);
+ attr.insns = (unsigned long) &prog;
+ attr.license = (unsigned long) &bpf_license;
+ attr.log_buf = (unsigned long) &bpf_log_buf;
+ attr.log_size = sizeof(bpf_log_buf);
+ attr.log_level = 1;
+
+ bpf_fd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr));
+ if (bpf_fd < 0)
+ error(1, errno, "ebpf error. log:\n%s\n", bpf_log_buf);
+
+ if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_REUSEPORT_EBPF, &bpf_fd,
+ sizeof(bpf_fd)))
+ error(1, errno, "failed to set SO_ATTACH_REUSEPORT_EBPF");
+
+ close(bpf_fd);
+}
+
+static void send_from_node(int node_id, int family, int proto)
+{
+ struct sockaddr_storage saddr, daddr;
+ struct sockaddr_in *saddr4, *daddr4;
+ struct sockaddr_in6 *saddr6, *daddr6;
+ int fd;
+
+ switch (family) {
+ case AF_INET:
+ saddr4 = (struct sockaddr_in *)&saddr;
+ saddr4->sin_family = AF_INET;
+ saddr4->sin_addr.s_addr = htonl(INADDR_ANY);
+ saddr4->sin_port = 0;
+
+ daddr4 = (struct sockaddr_in *)&daddr;
+ daddr4->sin_family = AF_INET;
+ daddr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+ daddr4->sin_port = htons(PORT);
+ break;
+ case AF_INET6:
+ saddr6 = (struct sockaddr_in6 *)&saddr;
+ saddr6->sin6_family = AF_INET6;
+ saddr6->sin6_addr = in6addr_any;
+ saddr6->sin6_port = 0;
+
+ daddr6 = (struct sockaddr_in6 *)&daddr;
+ daddr6->sin6_family = AF_INET6;
+ daddr6->sin6_addr = in6addr_loopback;
+ daddr6->sin6_port = htons(PORT);
+ break;
+ default:
+ error(1, 0, "Unsupported family %d", family);
+ }
+
+ if (numa_run_on_node(node_id) < 0)
+ error(1, errno, "failed to pin to node");
+
+ fd = socket(family, proto, 0);
+ if (fd < 0)
+ error(1, errno, "failed to create send socket");
+
+ if (bind(fd, (struct sockaddr *)&saddr, sizeof(saddr)))
+ error(1, errno, "failed to bind send socket");
+
+ if (connect(fd, (struct sockaddr *)&daddr, sizeof(daddr)))
+ error(1, errno, "failed to connect send socket");
+
+ if (send(fd, "a", 1, 0) < 0)
+ error(1, errno, "failed to send message");
+
+ close(fd);
+}
+
+static
+void receive_on_node(int *rcv_fd, int len, int epfd, int node_id, int proto)
+{
+ struct epoll_event ev;
+ int i, fd;
+ char buf[8];
+
+ i = epoll_wait(epfd, &ev, 1, -1);
+ if (i < 0)
+ error(1, errno, "epoll_wait failed");
+
+ if (proto == SOCK_STREAM) {
+ fd = accept(ev.data.fd, NULL, NULL);
+ if (fd < 0)
+ error(1, errno, "failed to accept");
+ i = recv(fd, buf, sizeof(buf), 0);
+ close(fd);
+ } else {
+ i = recv(ev.data.fd, buf, sizeof(buf), 0);
+ }
+
+ if (i < 0)
+ error(1, errno, "failed to recv");
+
+ for (i = 0; i < len; ++i)
+ if (ev.data.fd == rcv_fd[i])
+ break;
+ if (i == len)
+ error(1, 0, "failed to find socket");
+ fprintf(stderr, "send node %d, receive socket %d\n", node_id, i);
+ if (node_id != i)
+ error(1, 0, "node id/receive socket mismatch");
+}
+
+static void test(int *rcv_fd, int len, int family, int proto)
+{
+ struct epoll_event ev;
+ int epfd, node;
+
+ build_rcv_group(rcv_fd, len, family, proto);
+ attach_bpf(rcv_fd[0]);
+
+ epfd = epoll_create(1);
+ if (epfd < 0)
+ error(1, errno, "failed to create epoll");
+ for (node = 0; node < len; ++node) {
+ ev.events = EPOLLIN;
+ ev.data.fd = rcv_fd[node];
+ if (epoll_ctl(epfd, EPOLL_CTL_ADD, rcv_fd[node], &ev))
+ error(1, errno, "failed to register sock epoll");
+ }
+
+ /* Forward iterate */
+ for (node = 0; node < len; ++node) {
+ send_from_node(node, family, proto);
+ receive_on_node(rcv_fd, len, epfd, node, proto);
+ }
+
+ /* Reverse iterate */
+ for (node = len - 1; node >= 0; --node) {
+ send_from_node(node, family, proto);
+ receive_on_node(rcv_fd, len, epfd, node, proto);
+ }
+
+ close(epfd);
+ for (node = 0; node < len; ++node)
+ close(rcv_fd[node]);
+}
+
+int main(void)
+{
+ int *rcv_fd, nodes;
+
+ if (numa_available() < 0)
+ error(1, errno, "no numa api support");
+
+ nodes = numa_max_node() + 1;
+
+ rcv_fd = calloc(nodes, sizeof(int));
+ if (!rcv_fd)
+ error(1, 0, "failed to allocate array");
+
+ fprintf(stderr, "---- IPv4 UDP ----\n");
+ test(rcv_fd, nodes, AF_INET, SOCK_DGRAM);
+
+ fprintf(stderr, "---- IPv6 UDP ----\n");
+ test(rcv_fd, nodes, AF_INET6, SOCK_DGRAM);
+
+ fprintf(stderr, "---- IPv4 TCP ----\n");
+ test(rcv_fd, nodes, AF_INET, SOCK_STREAM);
+
+ fprintf(stderr, "---- IPv6 TCP ----\n");
+ test(rcv_fd, nodes, AF_INET6, SOCK_STREAM);
+
+ free(rcv_fd);
+
+ fprintf(stderr, "SUCCESS\n");
+ return 0;
+}
--
1.9.3
^ permalink raw reply related
* [PATCH net-next v2 0/2] Add BPF numa id helper
From: Daniel Borkmann @ 2016-10-21 10:46 UTC (permalink / raw)
To: davem; +Cc: alexei.starovoitov, edumazet, netdev, Daniel Borkmann
This patch set adds a helper for retrieving current numa node
id and a test case for SO_REUSEPORT.
Thanks!
v1 -> v2:
- Missed __weak definition when bpf syscall is not enabled, sorry.
- Rest as is.
Daniel Borkmann (2):
bpf: add helper for retrieving current numa node id
reuseport, bpf: add test case for bpf_get_numa_node_id
include/linux/bpf.h | 1 +
include/uapi/linux/bpf.h | 6 +
kernel/bpf/core.c | 1 +
kernel/bpf/helpers.c | 12 ++
kernel/trace/bpf_trace.c | 2 +
net/core/filter.c | 2 +
tools/testing/selftests/net/.gitignore | 1 +
tools/testing/selftests/net/Makefile | 11 +-
tools/testing/selftests/net/reuseport_bpf_numa.c | 255 +++++++++++++++++++++++
9 files changed, 287 insertions(+), 4 deletions(-)
create mode 100644 tools/testing/selftests/net/reuseport_bpf_numa.c
--
1.9.3
^ permalink raw reply
* [PATCH net-next v2 1/2] bpf: add helper for retrieving current numa node id
From: Daniel Borkmann @ 2016-10-21 10:46 UTC (permalink / raw)
To: davem; +Cc: alexei.starovoitov, edumazet, netdev, Daniel Borkmann
In-Reply-To: <cover.1477043972.git.daniel@iogearbox.net>
Use case is mainly for soreuseport to select sockets for the local
numa node, but since generic, lets also add this for other networking
and tracing program types.
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
include/linux/bpf.h | 1 +
include/uapi/linux/bpf.h | 6 ++++++
kernel/bpf/core.c | 1 +
kernel/bpf/helpers.c | 12 ++++++++++++
kernel/trace/bpf_trace.c | 2 ++
net/core/filter.c | 2 ++
6 files changed, 24 insertions(+)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c201017..edcd96d 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -319,6 +319,7 @@ static inline struct bpf_prog *bpf_prog_inc(struct bpf_prog *prog)
extern const struct bpf_func_proto bpf_get_prandom_u32_proto;
extern const struct bpf_func_proto bpf_get_smp_processor_id_proto;
+extern const struct bpf_func_proto bpf_get_numa_node_id_proto;
extern const struct bpf_func_proto bpf_tail_call_proto;
extern const struct bpf_func_proto bpf_ktime_get_ns_proto;
extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index f09c70b..374ef58 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -426,6 +426,12 @@ enum bpf_func_id {
*/
BPF_FUNC_set_hash_invalid,
+ /**
+ * bpf_get_numa_node_id()
+ * Returns the id of the current NUMA node.
+ */
+ BPF_FUNC_get_numa_node_id,
+
__BPF_FUNC_MAX_ID,
};
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index aa6d981..82a0414 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1043,6 +1043,7 @@ void bpf_user_rnd_init_once(void)
const struct bpf_func_proto bpf_get_prandom_u32_proto __weak;
const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;
+const struct bpf_func_proto bpf_get_numa_node_id_proto __weak;
const struct bpf_func_proto bpf_ktime_get_ns_proto __weak;
const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak;
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 3991840..045cbe6 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -13,6 +13,7 @@
#include <linux/rcupdate.h>
#include <linux/random.h>
#include <linux/smp.h>
+#include <linux/topology.h>
#include <linux/ktime.h>
#include <linux/sched.h>
#include <linux/uidgid.h>
@@ -92,6 +93,17 @@
.ret_type = RET_INTEGER,
};
+BPF_CALL_0(bpf_get_numa_node_id)
+{
+ return numa_node_id();
+}
+
+const struct bpf_func_proto bpf_get_numa_node_id_proto = {
+ .func = bpf_get_numa_node_id,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+};
+
BPF_CALL_0(bpf_ktime_get_ns)
{
/* NMI safe access to clock monotonic */
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 5dcb992..fa77311 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -422,6 +422,8 @@ static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id)
return bpf_get_trace_printk_proto();
case BPF_FUNC_get_smp_processor_id:
return &bpf_get_smp_processor_id_proto;
+ case BPF_FUNC_get_numa_node_id:
+ return &bpf_get_numa_node_id_proto;
case BPF_FUNC_perf_event_read:
return &bpf_perf_event_read_proto;
case BPF_FUNC_probe_write_user:
diff --git a/net/core/filter.c b/net/core/filter.c
index 00351cd..cd9e2ba 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2492,6 +2492,8 @@ static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff,
return &bpf_get_prandom_u32_proto;
case BPF_FUNC_get_smp_processor_id:
return &bpf_get_raw_smp_processor_id_proto;
+ case BPF_FUNC_get_numa_node_id:
+ return &bpf_get_numa_node_id_proto;
case BPF_FUNC_tail_call:
return &bpf_tail_call_proto;
case BPF_FUNC_ktime_get_ns:
--
1.9.3
^ permalink raw reply related
* Re: [PATCH net-next] nfnetlink_log: Use GFP_NOWARN for skb allocation
From: Pablo Neira Ayuso @ 2016-10-21 10:38 UTC (permalink / raw)
To: Calvin Owens
Cc: Patrick McHardy, Jozsef Kadlecsik, David S. Miller,
netfilter-devel, coreteam, netdev, linux-kernel, kernel-team
In-Reply-To: <1b50152e3ea7c3e18995349126d4352e4fc73933.1475873569.git.calvinowens@fb.com>
On Fri, Oct 07, 2016 at 02:02:16PM -0700, Calvin Owens wrote:
> Since the code explicilty falls back to a smaller allocation when the
> large one fails, we shouldn't complain when that happens.
Applied, thanks.
^ permalink raw reply
* Re: [PATCH] net: stmmac: Add OXNAS Glue Driver
From: Joachim Eastwood @ 2016-10-21 10:20 UTC (permalink / raw)
To: Neil Armstrong
Cc: peppe.cavallaro, alexandre.torgue-qxv4g6HH51o, netdev,
linux-oxnas-Xt5XgHjqiBU06sgRBLv0+0B+6BGkLq7r,
linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, devicetree
In-Reply-To: <20161021084445.24989-1-narmstrong-rdvid1DuHRBWk0Htik3J/w@public.gmane.org>
Hi Neil,
On 21 October 2016 at 10:44, Neil Armstrong <narmstrong-rdvid1DuHRBWk0Htik3J/w@public.gmane.org> wrote:
> Add Synopsys Designware MAC Glue layer for the Oxford Semiconductor OX820.
>
> Signed-off-by: Neil Armstrong <narmstrong-rdvid1DuHRBWk0Htik3J/w@public.gmane.org>
> ---
> .../devicetree/bindings/net/oxnas-dwmac.txt | 44 +++++
> drivers/net/ethernet/stmicro/stmmac/Kconfig | 11 ++
> drivers/net/ethernet/stmicro/stmmac/Makefile | 1 +
> drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c | 219 +++++++++++++++++++++
> 4 files changed, 275 insertions(+)
> create mode 100644 Documentation/devicetree/bindings/net/oxnas-dwmac.txt
> create mode 100644 drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c
>
> Changes since RFC at https://patchwork.kernel.org/patch/9387257 :
> - Drop init/exit callbacks
> - Implement proper remove and PM callback
> - Call init from probe
> - Disable/Unprepare clock if stmmac probe fails
<snip>
> +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-oxnas.c
> @@ -0,0 +1,219 @@
> +/*
> + * Oxford Semiconductor OXNAS DWMAC glue layer
> + *
> + * Copyright (C) 2016 Neil Armstrong <narmstrong-rdvid1DuHRBWk0Htik3J/w@public.gmane.org>
> + * Copyright (C) 2014 Daniel Golle <daniel-g5gK2j5usbvCyp4qypjU+w@public.gmane.org>
> + * Copyright (C) 2013 Ma Haijun <mahaijuns-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
> + * Copyright (C) 2012 John Crispin <blogic-p3rKhJxN3npAfugRpC6u6w@public.gmane.org>
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License version 2 as
> + * published by the Free Software Foundation.
> + *
> + * You should have received a copy of the GNU General Public License
> + * along with this program. If not, see <http://www.gnu.org/licenses/>.
> + */
> +
> +#include <linux/device.h>
> +#include <linux/io.h>
> +#include <linux/module.h>
> +#include <linux/of.h>
> +#include <linux/platform_device.h>
> +#include <linux/regmap.h>
> +#include <linux/mfd/syscon.h>
> +#include <linux/stmmac.h>
> +
> +#include "stmmac_platform.h"
> +
> +/* System Control regmap offsets */
> +#define OXNAS_DWMAC_CTRL_REGOFFSET 0x78
> +#define OXNAS_DWMAC_DELAY_REGOFFSET 0x100
> +
> +/* Control Register */
> +#define DWMAC_CKEN_RX_IN 14
> +#define DWMAC_CKEN_RXN_OUT 13
> +#define DWMAC_CKEN_RX_OUT 12
> +#define DWMAC_CKEN_TX_IN 10
> +#define DWMAC_CKEN_TXN_OUT 9
> +#define DWMAC_CKEN_TX_OUT 8
> +#define DWMAC_RX_SOURCE 7
> +#define DWMAC_TX_SOURCE 6
> +#define DWMAC_LOW_TX_SOURCE 4
> +#define DWMAC_AUTO_TX_SOURCE 3
> +#define DWMAC_RGMII 2
> +#define DWMAC_SIMPLE_MUX 1
> +#define DWMAC_CKEN_GTX 0
> +
> +/* Delay register */
> +#define DWMAC_TX_VARDELAY_SHIFT 0
> +#define DWMAC_TXN_VARDELAY_SHIFT 8
> +#define DWMAC_RX_VARDELAY_SHIFT 16
> +#define DWMAC_RXN_VARDELAY_SHIFT 24
> +#define DWMAC_TX_VARDELAY(d) ((d) << DWMAC_TX_VARDELAY_SHIFT)
> +#define DWMAC_TXN_VARDELAY(d) ((d) << DWMAC_TXN_VARDELAY_SHIFT)
> +#define DWMAC_RX_VARDELAY(d) ((d) << DWMAC_RX_VARDELAY_SHIFT)
> +#define DWMAC_RXN_VARDELAY(d) ((d) << DWMAC_RXN_VARDELAY_SHIFT)
> +
> +struct oxnas_dwmac {
> + struct device *dev;
> + struct clk *clk;
> + struct regmap *regmap;
> +};
> +
> +static int oxnas_dwmac_init(struct oxnas_dwmac *dwmac)
> +{
> + unsigned int value;
> + int ret;
> +
> + /* Reset HW here before changing the glue configuration */
> + ret = device_reset(dwmac->dev);
> + if (ret)
> + return ret;
> +
> + clk_prepare_enable(dwmac->clk);
You might want to check the return value from clk_prepare_enable() as well.
> +
> + ret = regmap_read(dwmac->regmap, OXNAS_DWMAC_CTRL_REGOFFSET, &value);
> + if (ret < 0)
> + return ret;
> +
> + /* Enable GMII_GTXCLK to follow GMII_REFCLK, required for gigabit PHY */
> + value |= BIT(DWMAC_CKEN_GTX);
> + /* Use simple mux for 25/125 Mhz clock switching */
> + value |= BIT(DWMAC_SIMPLE_MUX);
> + /* set auto switch tx clock source */
> + value |= BIT(DWMAC_AUTO_TX_SOURCE);
> + /* enable tx & rx vardelay */
> + value |= BIT(DWMAC_CKEN_TX_OUT);
> + value |= BIT(DWMAC_CKEN_TXN_OUT);
> + value |= BIT(DWMAC_CKEN_TX_IN);
> + value |= BIT(DWMAC_CKEN_RX_OUT);
> + value |= BIT(DWMAC_CKEN_RXN_OUT);
> + value |= BIT(DWMAC_CKEN_RX_IN);
> + regmap_write(dwmac->regmap, OXNAS_DWMAC_CTRL_REGOFFSET, value);
> +
> + /* set tx & rx vardelay */
> + value = DWMAC_TX_VARDELAY(4);
> + value |= DWMAC_TXN_VARDELAY(2);
> + value |= DWMAC_RX_VARDELAY(10);
> + value |= DWMAC_RXN_VARDELAY(8);
> + regmap_write(dwmac->regmap, OXNAS_DWMAC_DELAY_REGOFFSET, value);
> +
> + return 0;
> +}
> +
> +static int oxnas_dwmac_probe(struct platform_device *pdev)
> +{
> + struct plat_stmmacenet_data *plat_dat;
> + struct stmmac_resources stmmac_res;
> + struct device_node *sysctrl;
> + struct oxnas_dwmac *dwmac;
> + int ret;
> +
> + sysctrl = of_parse_phandle(pdev->dev.of_node, "oxsemi,sys-ctrl", 0);
> + if (!sysctrl) {
> + dev_err(&pdev->dev, "failed to get sys-ctrl node\n");
> + return -EINVAL;
> + }
> +
> + ret = stmmac_get_platform_resources(pdev, &stmmac_res);
> + if (ret)
> + return ret;
> +
> + plat_dat = stmmac_probe_config_dt(pdev, &stmmac_res.mac);
> + if (IS_ERR(plat_dat))
> + return PTR_ERR(plat_dat);
> +
> + dwmac = devm_kzalloc(&pdev->dev, sizeof(*dwmac), GFP_KERNEL);
> + if (!dwmac)
> + return -ENOMEM;
> +
> + dwmac->dev = &pdev->dev;
> + plat_dat->bsp_priv = dwmac;
> +
> + dwmac->regmap = syscon_node_to_regmap(sysctrl);
> + if (IS_ERR(dwmac->regmap)) {
> + dev_err(&pdev->dev, "failed to have sysctrl regmap\n");
> + return PTR_ERR(dwmac->regmap);
> + }
> +
> + dwmac->clk = devm_clk_get(&pdev->dev, "gmac");
> + if (IS_ERR(dwmac->clk))
> + return PTR_ERR(dwmac->clk);
> +
> + ret = oxnas_dwmac_init(dwmac);
> + if (ret)
> + return ret;
> +
> + ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
> + if (ret)
> + clk_disable_unprepare(dwmac->clk);
> +
> + return ret;
> +}
> +
> +static int oxnas_dwmac_remove(struct platform_device *pdev)
> +{
> + struct net_device *ndev = platform_get_drvdata(pdev);
> + struct stmmac_priv *priv = netdev_priv(ndev);
> + struct oxnas_dwmac *dwmac = priv->plat->bsp_priv;
Instead of this long dance of variables use the get_stmmac_bsp_priv()-helper.
You can take a look at dwmac-meson8b.c for reference.
> + int ret = stmmac_dvr_remove(&pdev->dev);
> +
> + clk_disable_unprepare(dwmac->clk);
> +
> + return ret;
> +}
> +
> +#ifdef CONFIG_PM_SLEEP
> +static int oxnas_dwmac_suspend(struct device *dev)
> +{
> + struct net_device *ndev = dev_get_drvdata(dev);
> + struct stmmac_priv *priv = netdev_priv(ndev);
> + struct oxnas_dwmac *dwmac = priv->plat->bsp_priv;
get_stmmac_bsp_priv()
> + int ret;
> +
> + ret = stmmac_suspend(dev);
> + clk_disable_unprepare(dwmac->clk);
> +
> + return ret;
> +}
> +
> +static int oxnas_dwmac_resume(struct device *dev)
> +{
> + struct net_device *ndev = dev_get_drvdata(dev);
> + struct stmmac_priv *priv = netdev_priv(ndev);
> + struct oxnas_dwmac *dwmac = priv->plat->bsp_priv;
get_stmmac_bsp_priv()
> + int ret;
> +
> + ret = oxnas_dwmac_init(dwmac);
> + if (ret)
> + return ret;
> +
> + ret = stmmac_resume(dev);
> +
> + return ret;
> +}
> +#endif /* CONFIG_PM_SLEEP */
With these changes:
Acked-by: Joachim Eastwood <manabian-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
best regards,
Joachim Eastwood
--
To unsubscribe from this list: send the line "unsubscribe devicetree" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH 02/13] netfilter: nft_dynset: fix element timeout for HZ != 1000
From: Pablo Neira Ayuso @ 2016-10-21 10:12 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1477044743-18948-1-git-send-email-pablo@netfilter.org>
From: "Anders K. Pedersen" <akp@cohaesio.com>
With HZ=100 element timeout in dynamic sets (i.e. flow tables) is 10 times
higher than configured.
Add proper conversion to/from jiffies, when interacting with userspace.
I tested this on Linux 4.8.1, and it applies cleanly to current nf and
nf-next trees.
Fixes: 22fe54d5fefc ("netfilter: nf_tables: add support for dynamic set updates")
Signed-off-by: Anders K. Pedersen <akp@cohaesio.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nft_dynset.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index e3b83c31da2e..517f08767a3c 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -158,7 +158,8 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
if (tb[NFTA_DYNSET_TIMEOUT] != NULL) {
if (!(set->flags & NFT_SET_TIMEOUT))
return -EINVAL;
- timeout = be64_to_cpu(nla_get_be64(tb[NFTA_DYNSET_TIMEOUT]));
+ timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64(
+ tb[NFTA_DYNSET_TIMEOUT])));
}
priv->sreg_key = nft_parse_register(tb[NFTA_DYNSET_SREG_KEY]);
@@ -246,7 +247,8 @@ static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr)
goto nla_put_failure;
if (nla_put_string(skb, NFTA_DYNSET_SET_NAME, priv->set->name))
goto nla_put_failure;
- if (nla_put_be64(skb, NFTA_DYNSET_TIMEOUT, cpu_to_be64(priv->timeout),
+ if (nla_put_be64(skb, NFTA_DYNSET_TIMEOUT,
+ cpu_to_be64(jiffies_to_msecs(priv->timeout)),
NFTA_DYNSET_PAD))
goto nla_put_failure;
if (priv->expr && nft_expr_dump(skb, NFTA_DYNSET_EXPR, priv->expr))
--
2.1.4
^ permalink raw reply related
* [PATCH 05/13] netfilter: xt_ipcomp: add "ip[6]t_ipcomp" module alias name
From: Pablo Neira Ayuso @ 2016-10-21 10:12 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1477044743-18948-1-git-send-email-pablo@netfilter.org>
From: Liping Zhang <liping.zhang@spreadtrum.com>
Otherwise, user cannot add related rules if xt_ipcomp.ko is not loaded:
# iptables -A OUTPUT -p 108 -m ipcomp --ipcompspi 1
iptables: No chain/target/match by that name.
Signed-off-by: Liping Zhang <liping.zhang@spreadtrum.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/xt_ipcomp.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/net/netfilter/xt_ipcomp.c b/net/netfilter/xt_ipcomp.c
index 89d53104c6b3..000e70377f85 100644
--- a/net/netfilter/xt_ipcomp.c
+++ b/net/netfilter/xt_ipcomp.c
@@ -26,6 +26,8 @@
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Fan Du <fan.du@windriver.com>");
MODULE_DESCRIPTION("Xtables: IPv4/6 IPsec-IPComp SPI match");
+MODULE_ALIAS("ipt_ipcomp");
+MODULE_ALIAS("ip6t_ipcomp");
/* Returns 1 if the spi is matched by the range, 0 otherwise */
static inline bool
--
2.1.4
^ permalink raw reply related
* [PATCH 04/13] netfilter: xt_NFLOG: fix unexpected truncated packet
From: Pablo Neira Ayuso @ 2016-10-21 10:12 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1477044743-18948-1-git-send-email-pablo@netfilter.org>
From: Liping Zhang <liping.zhang@spreadtrum.com>
Justin and Chris spotted that iptables NFLOG target was broken when they
upgraded the kernel to 4.8: "ulogd-2.0.5- IPs are no longer logged" or
"results in segfaults in ulogd-2.0.5".
Because "struct nf_loginfo li;" is a local variable, and flags will be
filled with garbage value, not inited to zero. So if it contains 0x1,
packets will not be logged to the userspace anymore.
Fixes: 7643507fe8b5 ("netfilter: xt_NFLOG: nflog-range does not truncate packets")
Reported-by: Justin Piszcz <jpiszcz@lucidpixels.com>
Reported-by: Chris Caputo <ccaputo@alt.net>
Tested-by: Chris Caputo <ccaputo@alt.net>
Signed-off-by: Liping Zhang <liping.zhang@spreadtrum.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/xt_NFLOG.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/netfilter/xt_NFLOG.c b/net/netfilter/xt_NFLOG.c
index 018eed7e1ff1..8668a5c18dc3 100644
--- a/net/netfilter/xt_NFLOG.c
+++ b/net/netfilter/xt_NFLOG.c
@@ -32,6 +32,7 @@ nflog_tg(struct sk_buff *skb, const struct xt_action_param *par)
li.u.ulog.copy_len = info->len;
li.u.ulog.group = info->group;
li.u.ulog.qthreshold = info->threshold;
+ li.u.ulog.flags = 0;
if (info->flags & XT_NFLOG_F_COPY_LEN)
li.u.ulog.flags |= NF_LOG_F_COPY_LEN;
--
2.1.4
^ permalink raw reply related
* [PATCH 11/13] netfilter: x_tables: suppress kmemcheck warning
From: Pablo Neira Ayuso @ 2016-10-21 10:12 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1477044743-18948-1-git-send-email-pablo@netfilter.org>
From: Florian Westphal <fw@strlen.de>
Markus Trippelsdorf reports:
WARNING: kmemcheck: Caught 64-bit read from uninitialized memory (ffff88001e605480)
4055601e0088ffff000000000000000090686d81ffffffff0000000000000000
u u u u u u u u u u u u u u u u i i i i i i i i u u u u u u u u
^
|RIP: 0010:[<ffffffff8166e561>] [<ffffffff8166e561>] nf_register_net_hook+0x51/0x160
[..]
[<ffffffff8166e561>] nf_register_net_hook+0x51/0x160
[<ffffffff8166eaaf>] nf_register_net_hooks+0x3f/0xa0
[<ffffffff816d6715>] ipt_register_table+0xe5/0x110
[..]
This warning is harmless; we copy 'uninitialized' data from the hook ops
but it will not be used.
Long term the structures keeping run-time data should be disentangled
from those only containing config-time data (such as where in the list
to insert a hook), but thats -next material.
Reported-by: Markus Trippelsdorf <markus@trippelsdorf.de>
Suggested-by: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Aaron Conole <aconole@bytheb.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/x_tables.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index e0aa7c1d0224..fc4977456c30 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1513,7 +1513,7 @@ xt_hook_ops_alloc(const struct xt_table *table, nf_hookfn *fn)
if (!num_hooks)
return ERR_PTR(-EINVAL);
- ops = kmalloc(sizeof(*ops) * num_hooks, GFP_KERNEL);
+ ops = kcalloc(num_hooks, sizeof(*ops), GFP_KERNEL);
if (ops == NULL)
return ERR_PTR(-ENOMEM);
--
2.1.4
^ permalink raw reply related
* [PATCH 12/13] netfilter: conntrack: restart gc immediately if GC_MAX_EVICTS is reached
From: Pablo Neira Ayuso @ 2016-10-21 10:12 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1477044743-18948-1-git-send-email-pablo@netfilter.org>
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
When the maximum evictions number is reached, do not wait 5 seconds before
the next run.
CC: Florian Westphal <fw@strlen.de>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_conntrack_core.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index ba6a1d421222..df2f5a3901df 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -983,7 +983,7 @@ static void gc_worker(struct work_struct *work)
return;
ratio = scanned ? expired_count * 100 / scanned : 0;
- if (ratio >= 90)
+ if (ratio >= 90 || expired_count == GC_MAX_EVICTS)
next_run = 0;
gc_work->last_bucket = i;
--
2.1.4
^ permalink raw reply related
* [PATCH 08/13] netfilter: nft_exthdr: fix error handling in nft_exthdr_init()
From: Pablo Neira Ayuso @ 2016-10-21 10:12 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1477044743-18948-1-git-send-email-pablo@netfilter.org>
From: Dan Carpenter <dan.carpenter@oracle.com>
"err" needs to be signed for the error handling to work.
Fixes: 36b701fae12a ('netfilter: nf_tables: validate maximum value of u32 netlink attributes')
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nft_exthdr.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index a84cf3d66056..47beb3abcc9d 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -59,7 +59,8 @@ static int nft_exthdr_init(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
{
struct nft_exthdr *priv = nft_expr_priv(expr);
- u32 offset, len, err;
+ u32 offset, len;
+ int err;
if (tb[NFTA_EXTHDR_DREG] == NULL ||
tb[NFTA_EXTHDR_TYPE] == NULL ||
--
2.1.4
^ permalink raw reply related
* [PATCH 07/13] netfilter: nf_tables: underflow in nft_parse_u32_check()
From: Pablo Neira Ayuso @ 2016-10-21 10:12 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1477044743-18948-1-git-send-email-pablo@netfilter.org>
From: Dan Carpenter <dan.carpenter@oracle.com>
We don't want to allow negatives here.
Fixes: 36b701fae12a ('netfilter: nf_tables: validate maximum value of u32 netlink attributes')
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nf_tables_api.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index b70d3ea1430e..24db22257586 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -4423,7 +4423,7 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
*/
unsigned int nft_parse_u32_check(const struct nlattr *attr, int max, u32 *dest)
{
- int val;
+ u32 val;
val = ntohl(nla_get_be32(attr));
if (val > max)
--
2.1.4
^ permalink raw reply related
* [PATCH 01/13] netfilter: xt_hashlimit: Add missing ULL suffixes for 64-bit constants
From: Pablo Neira Ayuso @ 2016-10-21 10:12 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1477044743-18948-1-git-send-email-pablo@netfilter.org>
From: Geert Uytterhoeven <geert@linux-m68k.org>
On 32-bit (e.g. with m68k-linux-gnu-gcc-4.1):
net/netfilter/xt_hashlimit.c: In function ‘user2credits’:
net/netfilter/xt_hashlimit.c:476: warning: integer constant is too large for ‘long’ type
...
net/netfilter/xt_hashlimit.c:478: warning: integer constant is too large for ‘long’ type
...
net/netfilter/xt_hashlimit.c:480: warning: integer constant is too large for ‘long’ type
...
net/netfilter/xt_hashlimit.c: In function ‘rateinfo_recalc’:
net/netfilter/xt_hashlimit.c:513: warning: integer constant is too large for ‘long’ type
Fixes: 11d5f15723c9f39d ("netfilter: xt_hashlimit: Create revision 2 to support higher pps rates")
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Vishwanath Pai <vpai@akamai.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/xt_hashlimit.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index 2fab0c65aa94..b89b688e9d01 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -431,7 +431,7 @@ static void htable_put(struct xt_hashlimit_htable *hinfo)
CREDITS_PER_JIFFY*HZ*60*60*24 < 2^32 ie.
*/
#define MAX_CPJ_v1 (0xFFFFFFFF / (HZ*60*60*24))
-#define MAX_CPJ (0xFFFFFFFFFFFFFFFF / (HZ*60*60*24))
+#define MAX_CPJ (0xFFFFFFFFFFFFFFFFULL / (HZ*60*60*24))
/* Repeated shift and or gives us all 1s, final shift and add 1 gives
* us the power of 2 below the theoretical max, so GCC simply does a
@@ -473,7 +473,7 @@ static u64 user2credits(u64 user, int revision)
return div64_u64(user * HZ * CREDITS_PER_JIFFY_v1,
XT_HASHLIMIT_SCALE);
} else {
- if (user > 0xFFFFFFFFFFFFFFFF / (HZ*CREDITS_PER_JIFFY))
+ if (user > 0xFFFFFFFFFFFFFFFFULL / (HZ*CREDITS_PER_JIFFY))
return div64_u64(user, XT_HASHLIMIT_SCALE_v2)
* HZ * CREDITS_PER_JIFFY;
--
2.1.4
^ permalink raw reply related
* [PATCH 13/13] netfilter: fix nf_queue handling
From: Pablo Neira Ayuso @ 2016-10-21 10:12 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1477044743-18948-1-git-send-email-pablo@netfilter.org>
nf_queue handling is broken since e3b37f11e6e4 ("netfilter: replace
list_head with single linked list") for two reasons:
1) If the bypass flag is set on, there are no userspace listeners and
we still have more hook entries to iterate over, then jump to the
next hook. Otherwise accept the packet. On nf_reinject() path, the
okfn() needs to be invoked.
2) We should not re-enter the same hook on packet reinjection. If the
packet is accepted, we have to skip the current hook from where the
packet was enqueued, otherwise the packets gets enqueued over and
over again.
This restores the previous list_for_each_entry_continue() behaviour
happening from nf_iterate() that was dealing with these two cases.
This patch introduces a new nf_queue() wrapper function so this fix
becomes simpler.
Fixes: e3b37f11e6e4 ("netfilter: replace list_head with single linked list")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/core.c | 13 +++---------
net/netfilter/nf_internals.h | 2 +-
net/netfilter/nf_queue.c | 48 +++++++++++++++++++++++++++++---------------
3 files changed, 36 insertions(+), 27 deletions(-)
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index fcb5d1df11e9..004af030ef1a 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -361,16 +361,9 @@ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state)
if (ret == 0)
ret = -EPERM;
} else if ((verdict & NF_VERDICT_MASK) == NF_QUEUE) {
- int err;
-
- RCU_INIT_POINTER(state->hook_entries, entry);
- err = nf_queue(skb, state, verdict >> NF_VERDICT_QBITS);
- if (err < 0) {
- if (err == -ESRCH &&
- (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS))
- goto next_hook;
- kfree_skb(skb);
- }
+ ret = nf_queue(skb, state, &entry, verdict);
+ if (ret == 1 && entry)
+ goto next_hook;
}
return ret;
}
diff --git a/net/netfilter/nf_internals.h b/net/netfilter/nf_internals.h
index e0adb5959342..9fdb655f85bc 100644
--- a/net/netfilter/nf_internals.h
+++ b/net/netfilter/nf_internals.h
@@ -18,7 +18,7 @@ unsigned int nf_iterate(struct sk_buff *skb, struct nf_hook_state *state,
/* nf_queue.c */
int nf_queue(struct sk_buff *skb, struct nf_hook_state *state,
- unsigned int queuenum);
+ struct nf_hook_entry **entryp, unsigned int verdict);
void nf_queue_nf_hook_drop(struct net *net, const struct nf_hook_entry *entry);
int __init netfilter_queue_init(void);
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index 96964a0070e1..8f08d759844a 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -107,13 +107,8 @@ void nf_queue_nf_hook_drop(struct net *net, const struct nf_hook_entry *entry)
rcu_read_unlock();
}
-/*
- * Any packet that leaves via this function must come back
- * through nf_reinject().
- */
-int nf_queue(struct sk_buff *skb,
- struct nf_hook_state *state,
- unsigned int queuenum)
+static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state,
+ unsigned int queuenum)
{
int status = -ENOENT;
struct nf_queue_entry *entry = NULL;
@@ -161,6 +156,27 @@ int nf_queue(struct sk_buff *skb,
return status;
}
+/* Packets leaving via this function must come back through nf_reinject(). */
+int nf_queue(struct sk_buff *skb, struct nf_hook_state *state,
+ struct nf_hook_entry **entryp, unsigned int verdict)
+{
+ struct nf_hook_entry *entry = *entryp;
+ int ret;
+
+ RCU_INIT_POINTER(state->hook_entries, entry);
+ ret = __nf_queue(skb, state, verdict >> NF_VERDICT_QBITS);
+ if (ret < 0) {
+ if (ret == -ESRCH &&
+ (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS)) {
+ *entryp = rcu_dereference(entry->next);
+ return 1;
+ }
+ kfree_skb(skb);
+ }
+
+ return 0;
+}
+
void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
{
struct nf_hook_entry *hook_entry;
@@ -187,26 +203,26 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
entry->state.thresh = INT_MIN;
if (verdict == NF_ACCEPT) {
- next_hook:
- verdict = nf_iterate(skb, &entry->state, &hook_entry);
+ hook_entry = rcu_dereference(hook_entry->next);
+ if (hook_entry)
+next_hook:
+ verdict = nf_iterate(skb, &entry->state, &hook_entry);
}
switch (verdict & NF_VERDICT_MASK) {
case NF_ACCEPT:
case NF_STOP:
+okfn:
local_bh_disable();
entry->state.okfn(entry->state.net, entry->state.sk, skb);
local_bh_enable();
break;
case NF_QUEUE:
- RCU_INIT_POINTER(entry->state.hook_entries, hook_entry);
- err = nf_queue(skb, &entry->state,
- verdict >> NF_VERDICT_QBITS);
- if (err < 0) {
- if (err == -ESRCH &&
- (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS))
+ err = nf_queue(skb, &entry->state, &hook_entry, verdict);
+ if (err == 1) {
+ if (hook_entry)
goto next_hook;
- kfree_skb(skb);
+ goto okfn;
}
break;
case NF_STOLEN:
--
2.1.4
^ permalink raw reply related
* [PATCH 10/13] netfilter: nf_tables: avoid uninitialized variable warning
From: Pablo Neira Ayuso @ 2016-10-21 10:12 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1477044743-18948-1-git-send-email-pablo@netfilter.org>
From: Arnd Bergmann <arnd@arndb.de>
The newly added nft_range_eval() function handles the two possible
nft range operations, but as the compiler warning points out,
any unexpected value would lead to the 'mismatch' variable being
used without being initialized:
net/netfilter/nft_range.c: In function 'nft_range_eval':
net/netfilter/nft_range.c:45:5: error: 'mismatch' may be used uninitialized in this function [-Werror=maybe-uninitialized]
This removes the variable in question and instead moves the
condition into the switch itself, which is potentially more
efficient than adding a bogus 'default' clause as in my
first approach, and is nicer than using the 'uninitialized_var'
macro.
Fixes: 0f3cd9b36977 ("netfilter: nf_tables: add range expression")
Link: http://patchwork.ozlabs.org/patch/677114/
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nft_range.c | 10 ++++------
1 file changed, 4 insertions(+), 6 deletions(-)
diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c
index 9bc4586c3006..fbc88009ca2e 100644
--- a/net/netfilter/nft_range.c
+++ b/net/netfilter/nft_range.c
@@ -28,22 +28,20 @@ static void nft_range_eval(const struct nft_expr *expr,
const struct nft_pktinfo *pkt)
{
const struct nft_range_expr *priv = nft_expr_priv(expr);
- bool mismatch;
int d1, d2;
d1 = memcmp(®s->data[priv->sreg], &priv->data_from, priv->len);
d2 = memcmp(®s->data[priv->sreg], &priv->data_to, priv->len);
switch (priv->op) {
case NFT_RANGE_EQ:
- mismatch = (d1 < 0 || d2 > 0);
+ if (d1 < 0 || d2 > 0)
+ regs->verdict.code = NFT_BREAK;
break;
case NFT_RANGE_NEQ:
- mismatch = (d1 >= 0 && d2 <= 0);
+ if (d1 >= 0 && d2 <= 0)
+ regs->verdict.code = NFT_BREAK;
break;
}
-
- if (mismatch)
- regs->verdict.code = NFT_BREAK;
}
static const struct nla_policy nft_range_policy[NFTA_RANGE_MAX + 1] = {
--
2.1.4
^ permalink raw reply related
* [PATCH 09/13] netfilter: nft_range: validate operation netlink attribute
From: Pablo Neira Ayuso @ 2016-10-21 10:12 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1477044743-18948-1-git-send-email-pablo@netfilter.org>
Use nft_parse_u32_check() to make sure we don't get a value over the
unsigned 8-bit integer. Moreover, make sure this value doesn't go over
the two supported range comparison modes.
Fixes: 9286c2eb1fda ("netfilter: nft_range: validate operation netlink attribute")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nft_range.c | 16 +++++++++++++++-
1 file changed, 15 insertions(+), 1 deletion(-)
diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c
index c6d5358482d1..9bc4586c3006 100644
--- a/net/netfilter/nft_range.c
+++ b/net/netfilter/nft_range.c
@@ -59,6 +59,7 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr
struct nft_range_expr *priv = nft_expr_priv(expr);
struct nft_data_desc desc_from, desc_to;
int err;
+ u32 op;
err = nft_data_init(NULL, &priv->data_from, sizeof(priv->data_from),
&desc_from, tb[NFTA_RANGE_FROM_DATA]);
@@ -80,7 +81,20 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr
if (err < 0)
goto err2;
- priv->op = ntohl(nla_get_be32(tb[NFTA_RANGE_OP]));
+ err = nft_parse_u32_check(tb[NFTA_RANGE_OP], U8_MAX, &op);
+ if (err < 0)
+ goto err2;
+
+ switch (op) {
+ case NFT_RANGE_EQ:
+ case NFT_RANGE_NEQ:
+ break;
+ default:
+ err = -EINVAL;
+ goto err2;
+ }
+
+ priv->op = op;
priv->len = desc_from.len;
return 0;
err2:
--
2.1.4
^ permalink raw reply related
* [PATCH 06/13] netfilter: nft_hash: add missing NFTA_HASH_OFFSET's nla_policy
From: Pablo Neira Ayuso @ 2016-10-21 10:12 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1477044743-18948-1-git-send-email-pablo@netfilter.org>
From: Liping Zhang <liping.zhang@spreadtrum.com>
Missing the nla_policy description will also miss the validation check
in kernel.
Fixes: 70ca767ea1b2 ("netfilter: nft_hash: Add hash offset value")
Signed-off-by: Liping Zhang <liping.zhang@spreadtrum.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
net/netfilter/nft_hash.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c
index 09473b415b95..baf694de3935 100644
--- a/net/netfilter/nft_hash.c
+++ b/net/netfilter/nft_hash.c
@@ -44,6 +44,7 @@ static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = {
[NFTA_HASH_LEN] = { .type = NLA_U32 },
[NFTA_HASH_MODULUS] = { .type = NLA_U32 },
[NFTA_HASH_SEED] = { .type = NLA_U32 },
+ [NFTA_HASH_OFFSET] = { .type = NLA_U32 },
};
static int nft_hash_init(const struct nft_ctx *ctx,
--
2.1.4
^ permalink raw reply related
* [PATCH 03/13] netfilter: conntrack: remove obsolete sysctl (nf_conntrack_events_retry_timeout)
From: Pablo Neira Ayuso @ 2016-10-21 10:12 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
In-Reply-To: <1477044743-18948-1-git-send-email-pablo@netfilter.org>
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
This entry has been removed in commit 9500507c6138.
Fixes: 9500507c6138 ("netfilter: conntrack: remove timer from ecache extension")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
Documentation/networking/nf_conntrack-sysctl.txt | 18 ------------------
1 file changed, 18 deletions(-)
diff --git a/Documentation/networking/nf_conntrack-sysctl.txt b/Documentation/networking/nf_conntrack-sysctl.txt
index 4fb51d32fccc..399e4e866a9c 100644
--- a/Documentation/networking/nf_conntrack-sysctl.txt
+++ b/Documentation/networking/nf_conntrack-sysctl.txt
@@ -33,24 +33,6 @@ nf_conntrack_events - BOOLEAN
If this option is enabled, the connection tracking code will
provide userspace with connection tracking events via ctnetlink.
-nf_conntrack_events_retry_timeout - INTEGER (seconds)
- default 15
-
- This option is only relevant when "reliable connection tracking
- events" are used. Normally, ctnetlink is "lossy", that is,
- events are normally dropped when userspace listeners can't keep up.
-
- Userspace can request "reliable event mode". When this mode is
- active, the conntrack will only be destroyed after the event was
- delivered. If event delivery fails, the kernel periodically
- re-tries to send the event to userspace.
-
- This is the maximum interval the kernel should use when re-trying
- to deliver the destroy event.
-
- A higher number means there will be fewer delivery retries and it
- will take longer for a backlog to be processed.
-
nf_conntrack_expect_max - INTEGER
Maximum size of expectation table. Default value is
nf_conntrack_buckets / 256. Minimum is 1.
--
2.1.4
^ permalink raw reply related
* [PATCH 00/13] Netfilter fixes for net
From: Pablo Neira Ayuso @ 2016-10-21 10:12 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
Hi David,
The following patchset contains Netfilter fixes for your net tree,
they are:
1) Fix compilation warning in xt_hashlimit on m68k 32-bits, from
Geert Uytterhoeven.
2) Fix wrong timeout in set elements added from packet path via
nft_dynset, from Anders K. Pedersen.
3) Remove obsolete nf_conntrack_events_retry_timeout sysctl
documentation, from Nicolas Dichtel.
4) Ensure proper initialization of log flags via xt_LOG, from
Liping Zhang.
5) Missing alias to autoload ipcomp, also from Liping Zhang.
6) Missing NFTA_HASH_OFFSET attribute validation, again from Liping.
7) Wrong integer type in the new nft_parse_u32_check() function,
from Dan Carpenter.
8) Another wrong integer type declaration in nft_exthdr_init, also
from Dan Carpenter.
9) Fix insufficient mode validation in nft_range.
10) Fix compilation warning in nft_range due to possible uninitialized
value, from Arnd Bergmann.
11) Zero nf_hook_ops allocated via xt_hook_alloc() in x_tables to
calm down kmemcheck, from Florian Westphal.
12) Schedule gc_worker() to run again if GC_MAX_EVICTS quota is reached,
from Nicolas Dichtel.
13) Fix nf_queue() after conversion to single-linked hook list, related
to incorrect bypass flag handling and incorrect hook point of
reinjection.
You can pull these changes from:
git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf.git
Thanks!
----------------------------------------------------------------
The following changes since commit 6d3a4c404648e415e7d96e285d723936d4df7ed0:
strparser: Propagate correct error code in strp_recv() (2016-10-12 01:51:49 -0400)
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf.git HEAD
for you to fetch changes up to 7034b566a4e7d550621c2dfafd380b77b3787cd9:
netfilter: fix nf_queue handling (2016-10-20 19:59:59 +0200)
----------------------------------------------------------------
Anders K. Pedersen (1):
netfilter: nft_dynset: fix element timeout for HZ != 1000
Arnd Bergmann (1):
netfilter: nf_tables: avoid uninitialized variable warning
Dan Carpenter (2):
netfilter: nf_tables: underflow in nft_parse_u32_check()
netfilter: nft_exthdr: fix error handling in nft_exthdr_init()
Florian Westphal (1):
netfilter: x_tables: suppress kmemcheck warning
Geert Uytterhoeven (1):
netfilter: xt_hashlimit: Add missing ULL suffixes for 64-bit constants
Liping Zhang (3):
netfilter: xt_NFLOG: fix unexpected truncated packet
netfilter: xt_ipcomp: add "ip[6]t_ipcomp" module alias name
netfilter: nft_hash: add missing NFTA_HASH_OFFSET's nla_policy
Nicolas Dichtel (2):
netfilter: conntrack: remove obsolete sysctl (nf_conntrack_events_retry_timeout)
netfilter: conntrack: restart gc immediately if GC_MAX_EVICTS is reached
Pablo Neira Ayuso (2):
netfilter: nft_range: validate operation netlink attribute
netfilter: fix nf_queue handling
Documentation/networking/nf_conntrack-sysctl.txt | 18 ---------
net/netfilter/core.c | 13 ++-----
net/netfilter/nf_conntrack_core.c | 2 +-
net/netfilter/nf_internals.h | 2 +-
net/netfilter/nf_queue.c | 48 ++++++++++++++++--------
net/netfilter/nf_tables_api.c | 2 +-
net/netfilter/nft_dynset.c | 6 ++-
net/netfilter/nft_exthdr.c | 3 +-
net/netfilter/nft_hash.c | 1 +
net/netfilter/nft_range.c | 26 +++++++++----
net/netfilter/x_tables.c | 2 +-
net/netfilter/xt_NFLOG.c | 1 +
net/netfilter/xt_hashlimit.c | 4 +-
net/netfilter/xt_ipcomp.c | 2 +
14 files changed, 70 insertions(+), 60 deletions(-)
^ permalink raw reply
* Re: [PATCH net-next v2 6/9] net: use core MTU range checking in virt drivers
From: Wei Liu @ 2016-10-21 10:09 UTC (permalink / raw)
To: Jarod Wilson
Cc: linux-kernel, netdev, virtualization, K. Y. Srinivasan,
Haiyang Zhang, Michael S. Tsirkin, Shrikrishna Khare,
VMware, Inc., Wei Liu, Paul Durrant, David Kershner
In-Reply-To: <20161020175524.6184-7-jarod@redhat.com>
On Thu, Oct 20, 2016 at 01:55:21PM -0400, Jarod Wilson wrote:
> hyperv_net:
> - set min/max_mtu, per Haiyang, after rndis_filter_device_add
>
> virtio_net:
> - set min/max_mtu
> - remove virtnet_change_mtu
>
> vmxnet3:
> - set min/max_mtu
>
> xen-netback:
> - min_mtu = 0, max_mtu = 65517
>
> xen-netfront:
> - min_mtu = 0, max_mtu = 65535
>
> unisys/visor:
> - clean up defines a little to not clash with network core or add
> redundat definitions
>
> CC: netdev@vger.kernel.org
> CC: virtualization@lists.linux-foundation.org
> CC: "K. Y. Srinivasan" <kys@microsoft.com>
> CC: Haiyang Zhang <haiyangz@microsoft.com>
> CC: "Michael S. Tsirkin" <mst@redhat.com>
> CC: Shrikrishna Khare <skhare@vmware.com>
> CC: "VMware, Inc." <pv-drivers@vmware.com>
> CC: Wei Liu <wei.liu2@citrix.com>
> CC: Paul Durrant <paul.durrant@citrix.com>
> CC: David Kershner <david.kershner@unisys.com>
> Signed-off-by: Jarod Wilson <jarod@redhat.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
^ permalink raw reply
* [PATCH v7] net: ip, diag -- Add diag interface for raw sockets
From: Cyrill Gorcunov @ 2016-10-21 10:03 UTC (permalink / raw)
To: netdev
Cc: David Ahern, David Miller, eric.dumazet, jhs, linux-kernel,
kuznet, jmorris, yoshfuji, kaber, avagin, stephen
In criu we are actively using diag interface to collect sockets
present in the system when dumping applications. And while for
unix, tcp, udp[lite], packet, netlink it works as expected,
the raw sockets do not have. Thus add it.
v2:
- add missing sock_put calls in raw_diag_dump_one (by eric.dumazet@)
- implement @destroy for diag requests (by dsa@)
v3:
- add export of raw_abort for IPv6 (by dsa@)
- pass net-admin flag into inet_sk_diag_fill due to
changes in net-next branch (by dsa@)
v4:
- use @pad in struct inet_diag_req_v2 for raw socket
protocol specification: raw module carries sockets
which may have custom protocol passed from socket()
syscall and sole @sdiag_protocol is not enough to
match underlied ones
- start reporting protocol specifed in socket() call
when sockets are raw ones for the same reason: user
space tools like ss may parse this attribute and use
it for socket matching
v5 (by eric.dumazet@):
- use sock_hold in raw_sock_get instead of atomic_inc,
we're holding (raw_v4_hashinfo|raw_v6_hashinfo)->lock
when looking up so counter won't be zero here.
v6:
- use sdiag_raw_protocol() helper which will access @pad
structure used for raw sockets protocol specification:
we can't simply rename this member without breaking uapi
v7:
- sine sdiag_raw_protocol() helper is not suitable for
uapi lets rather make an alias structure with proper
names. __check_inet_diag_req_raw helper will catch
if any of structure unintentionally changed.
CC: David S. Miller <davem@davemloft.net>
CC: Eric Dumazet <eric.dumazet@gmail.com>
CC: David Ahern <dsa@cumulusnetworks.com>
CC: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
CC: James Morris <jmorris@namei.org>
CC: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
CC: Patrick McHardy <kaber@trash.net>
CC: Andrey Vagin <avagin@openvz.org>
CC: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
---
include/net/raw.h | 6
include/net/rawv6.h | 7 +
include/uapi/linux/inet_diag.h | 17 ++
net/ipv4/Kconfig | 8 +
net/ipv4/Makefile | 1
net/ipv4/inet_diag.c | 9 +
net/ipv4/raw.c | 21 ++-
net/ipv4/raw_diag.c | 261 +++++++++++++++++++++++++++++++++++++++++
net/ipv6/raw.c | 7 -
9 files changed, 333 insertions(+), 4 deletions(-)
Index: linux-ml.git/include/net/raw.h
===================================================================
--- linux-ml.git.orig/include/net/raw.h
+++ linux-ml.git/include/net/raw.h
@@ -23,6 +23,12 @@
extern struct proto raw_prot;
+extern struct raw_hashinfo raw_v4_hashinfo;
+struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
+ unsigned short num, __be32 raddr,
+ __be32 laddr, int dif);
+
+int raw_abort(struct sock *sk, int err);
void raw_icmp_error(struct sk_buff *, int, u32);
int raw_local_deliver(struct sk_buff *, int);
Index: linux-ml.git/include/net/rawv6.h
===================================================================
--- linux-ml.git.orig/include/net/rawv6.h
+++ linux-ml.git/include/net/rawv6.h
@@ -3,6 +3,13 @@
#include <net/protocol.h>
+extern struct raw_hashinfo raw_v6_hashinfo;
+struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
+ unsigned short num, const struct in6_addr *loc_addr,
+ const struct in6_addr *rmt_addr, int dif);
+
+int raw_abort(struct sock *sk, int err);
+
void raw6_icmp_error(struct sk_buff *, int nexthdr,
u8 type, u8 code, int inner_offset, __be32);
bool raw6_local_deliver(struct sk_buff *, int);
Index: linux-ml.git/include/uapi/linux/inet_diag.h
===================================================================
--- linux-ml.git.orig/include/uapi/linux/inet_diag.h
+++ linux-ml.git/include/uapi/linux/inet_diag.h
@@ -43,6 +43,23 @@ struct inet_diag_req_v2 {
struct inet_diag_sockid id;
};
+/*
+ * SOCK_RAW sockets require the underlied protocol to be
+ * additionally specified so we can use @pad member for
+ * this, but we can't rename it because userspace programs
+ * still may depend on this name. Instead lets use another
+ * structure definition as an alias for struct
+ * @inet_diag_req_v2.
+ */
+struct inet_diag_req_raw {
+ __u8 sdiag_family;
+ __u8 sdiag_protocol;
+ __u8 idiag_ext;
+ __u8 sdiag_raw_protocol;
+ __u32 idiag_states;
+ struct inet_diag_sockid id;
+};
+
enum {
INET_DIAG_REQ_NONE,
INET_DIAG_REQ_BYTECODE,
Index: linux-ml.git/net/ipv4/Kconfig
===================================================================
--- linux-ml.git.orig/net/ipv4/Kconfig
+++ linux-ml.git/net/ipv4/Kconfig
@@ -430,6 +430,14 @@ config INET_UDP_DIAG
Support for UDP socket monitoring interface used by the ss tool.
If unsure, say Y.
+config INET_RAW_DIAG
+ tristate "RAW: socket monitoring interface"
+ depends on INET_DIAG && (IPV6 || IPV6=n)
+ default n
+ ---help---
+ Support for RAW socket monitoring interface used by the ss tool.
+ If unsure, say Y.
+
config INET_DIAG_DESTROY
bool "INET: allow privileged process to administratively close sockets"
depends on INET_DIAG
Index: linux-ml.git/net/ipv4/Makefile
===================================================================
--- linux-ml.git.orig/net/ipv4/Makefile
+++ linux-ml.git/net/ipv4/Makefile
@@ -40,6 +40,7 @@ obj-$(CONFIG_NETFILTER) += netfilter.o n
obj-$(CONFIG_INET_DIAG) += inet_diag.o
obj-$(CONFIG_INET_TCP_DIAG) += tcp_diag.o
obj-$(CONFIG_INET_UDP_DIAG) += udp_diag.o
+obj-$(CONFIG_INET_RAW_DIAG) += raw_diag.o
obj-$(CONFIG_NET_TCPPROBE) += tcp_probe.o
obj-$(CONFIG_TCP_CONG_BIC) += tcp_bic.o
obj-$(CONFIG_TCP_CONG_CDG) += tcp_cdg.o
Index: linux-ml.git/net/ipv4/inet_diag.c
===================================================================
--- linux-ml.git.orig/net/ipv4/inet_diag.c
+++ linux-ml.git/net/ipv4/inet_diag.c
@@ -200,6 +200,15 @@ int inet_sk_diag_fill(struct sock *sk, s
if (sock_diag_put_meminfo(sk, skb, INET_DIAG_SKMEMINFO))
goto errout;
+ /*
+ * RAW sockets might have user-defined protocols assigned,
+ * so report the one supplied on socket creation.
+ */
+ if (sk->sk_type == SOCK_RAW) {
+ if (nla_put_u8(skb, INET_DIAG_PROTOCOL, sk->sk_protocol))
+ goto errout;
+ }
+
if (!icsk) {
handler->idiag_get_info(sk, r, NULL);
goto out;
Index: linux-ml.git/net/ipv4/raw.c
===================================================================
--- linux-ml.git.orig/net/ipv4/raw.c
+++ linux-ml.git/net/ipv4/raw.c
@@ -89,9 +89,10 @@ struct raw_frag_vec {
int hlen;
};
-static struct raw_hashinfo raw_v4_hashinfo = {
+struct raw_hashinfo raw_v4_hashinfo = {
.lock = __RW_LOCK_UNLOCKED(raw_v4_hashinfo.lock),
};
+EXPORT_SYMBOL_GPL(raw_v4_hashinfo);
int raw_hash_sk(struct sock *sk)
{
@@ -120,7 +121,7 @@ void raw_unhash_sk(struct sock *sk)
}
EXPORT_SYMBOL_GPL(raw_unhash_sk);
-static struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
+struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
unsigned short num, __be32 raddr, __be32 laddr, int dif)
{
sk_for_each_from(sk) {
@@ -136,6 +137,7 @@ static struct sock *__raw_v4_lookup(stru
found:
return sk;
}
+EXPORT_SYMBOL_GPL(__raw_v4_lookup);
/*
* 0 - deliver
@@ -918,6 +920,20 @@ static int compat_raw_ioctl(struct sock
}
#endif
+int raw_abort(struct sock *sk, int err)
+{
+ lock_sock(sk);
+
+ sk->sk_err = err;
+ sk->sk_error_report(sk);
+ udp_disconnect(sk, 0);
+
+ release_sock(sk);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(raw_abort);
+
struct proto raw_prot = {
.name = "RAW",
.owner = THIS_MODULE,
@@ -943,6 +959,7 @@ struct proto raw_prot = {
.compat_getsockopt = compat_raw_getsockopt,
.compat_ioctl = compat_raw_ioctl,
#endif
+ .diag_destroy = raw_abort,
};
#ifdef CONFIG_PROC_FS
Index: linux-ml.git/net/ipv4/raw_diag.c
===================================================================
--- /dev/null
+++ linux-ml.git/net/ipv4/raw_diag.c
@@ -0,0 +1,261 @@
+#include <linux/module.h>
+
+#include <linux/inet_diag.h>
+#include <linux/sock_diag.h>
+
+#include <net/raw.h>
+#include <net/rawv6.h>
+
+#ifdef pr_fmt
+# undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+static struct raw_hashinfo *
+raw_get_hashinfo(const struct inet_diag_req_v2 *r)
+{
+ if (r->sdiag_family == AF_INET) {
+ return &raw_v4_hashinfo;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (r->sdiag_family == AF_INET6) {
+ return &raw_v6_hashinfo;
+#endif
+ } else {
+ pr_warn_once("Unexpected inet family %d\n",
+ r->sdiag_family);
+ WARN_ON_ONCE(1);
+ return ERR_PTR(-EINVAL);
+ }
+}
+
+/*
+ * Due to requirement of not breaking user API we can't simply
+ * rename @pad field in inet_diag_req_v2 structure, instead
+ * use helper to figure it out.
+ */
+
+static struct sock *raw_lookup(struct net *net, struct sock *from,
+ const struct inet_diag_req_v2 *req)
+{
+ struct inet_diag_req_raw *r = (void *)req;
+ struct sock *sk = NULL;
+
+ if (r->sdiag_family == AF_INET)
+ sk = __raw_v4_lookup(net, from, r->sdiag_raw_protocol,
+ r->id.idiag_dst[0],
+ r->id.idiag_src[0],
+ r->id.idiag_if);
+#if IS_ENABLED(CONFIG_IPV6)
+ else
+ sk = __raw_v6_lookup(net, from, r->sdiag_raw_protocol,
+ (const struct in6_addr *)r->id.idiag_src,
+ (const struct in6_addr *)r->id.idiag_dst,
+ r->id.idiag_if);
+#endif
+ return sk;
+}
+
+static struct sock *raw_sock_get(struct net *net, const struct inet_diag_req_v2 *r)
+{
+ struct raw_hashinfo *hashinfo = raw_get_hashinfo(r);
+ struct sock *sk = NULL, *s;
+ int slot;
+
+ if (IS_ERR(hashinfo))
+ return ERR_CAST(hashinfo);
+
+ read_lock(&hashinfo->lock);
+ for (slot = 0; slot < RAW_HTABLE_SIZE; slot++) {
+ sk_for_each(s, &hashinfo->ht[slot]) {
+ sk = raw_lookup(net, s, r);
+ if (sk) {
+ /*
+ * Grab it and keep until we fill
+ * diag meaage to be reported, so
+ * caller should call sock_put then.
+ * We can do that because we're keeping
+ * hashinfo->lock here.
+ */
+ sock_hold(sk);
+ break;
+ }
+ }
+ }
+ read_unlock(&hashinfo->lock);
+
+ return sk ? sk : ERR_PTR(-ENOENT);
+}
+
+static int raw_diag_dump_one(struct sk_buff *in_skb,
+ const struct nlmsghdr *nlh,
+ const struct inet_diag_req_v2 *r)
+{
+ struct net *net = sock_net(in_skb->sk);
+ struct sk_buff *rep;
+ struct sock *sk;
+ int err;
+
+ sk = raw_sock_get(net, r);
+ if (IS_ERR(sk))
+ return PTR_ERR(sk);
+
+ rep = nlmsg_new(sizeof(struct inet_diag_msg) +
+ sizeof(struct inet_diag_meminfo) + 64,
+ GFP_KERNEL);
+ if (!rep) {
+ sock_put(sk);
+ return -ENOMEM;
+ }
+
+ err = inet_sk_diag_fill(sk, NULL, rep, r,
+ sk_user_ns(NETLINK_CB(in_skb).sk),
+ NETLINK_CB(in_skb).portid,
+ nlh->nlmsg_seq, 0, nlh,
+ netlink_net_capable(in_skb, CAP_NET_ADMIN));
+ sock_put(sk);
+
+ if (err < 0) {
+ kfree_skb(rep);
+ return err;
+ }
+
+ err = netlink_unicast(net->diag_nlsk, rep,
+ NETLINK_CB(in_skb).portid,
+ MSG_DONTWAIT);
+ if (err > 0)
+ err = 0;
+ return err;
+}
+
+static int sk_diag_dump(struct sock *sk, struct sk_buff *skb,
+ struct netlink_callback *cb,
+ const struct inet_diag_req_v2 *r,
+ struct nlattr *bc, bool net_admin)
+{
+ if (!inet_diag_bc_sk(bc, sk))
+ return 0;
+
+ return inet_sk_diag_fill(sk, NULL, skb, r,
+ sk_user_ns(NETLINK_CB(cb->skb).sk),
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, NLM_F_MULTI,
+ cb->nlh, net_admin);
+}
+
+static void raw_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
+ const struct inet_diag_req_v2 *r, struct nlattr *bc)
+{
+ bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN);
+ struct raw_hashinfo *hashinfo = raw_get_hashinfo(r);
+ struct net *net = sock_net(skb->sk);
+ int num, s_num, slot, s_slot;
+ struct sock *sk = NULL;
+
+ if (IS_ERR(hashinfo))
+ return;
+
+ s_slot = cb->args[0];
+ num = s_num = cb->args[1];
+
+ read_lock(&hashinfo->lock);
+ for (slot = s_slot; slot < RAW_HTABLE_SIZE; s_num = 0, slot++) {
+ num = 0;
+
+ sk_for_each(sk, &hashinfo->ht[slot]) {
+ struct inet_sock *inet = inet_sk(sk);
+
+ if (!net_eq(sock_net(sk), net))
+ continue;
+ if (num < s_num)
+ goto next;
+ if (sk->sk_family != r->sdiag_family)
+ goto next;
+ if (r->id.idiag_sport != inet->inet_sport &&
+ r->id.idiag_sport)
+ goto next;
+ if (r->id.idiag_dport != inet->inet_dport &&
+ r->id.idiag_dport)
+ goto next;
+ if (sk_diag_dump(sk, skb, cb, r, bc, net_admin) < 0)
+ goto out_unlock;
+next:
+ num++;
+ }
+ }
+
+out_unlock:
+ read_unlock(&hashinfo->lock);
+
+ cb->args[0] = slot;
+ cb->args[1] = num;
+}
+
+static void raw_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
+ void *info)
+{
+ r->idiag_rqueue = sk_rmem_alloc_get(sk);
+ r->idiag_wqueue = sk_wmem_alloc_get(sk);
+}
+
+#ifdef CONFIG_INET_DIAG_DESTROY
+static int raw_diag_destroy(struct sk_buff *in_skb,
+ const struct inet_diag_req_v2 *r)
+{
+ struct net *net = sock_net(in_skb->sk);
+ struct sock *sk;
+
+ sk = raw_sock_get(net, r);
+ if (IS_ERR(sk))
+ return PTR_ERR(sk);
+ return sock_diag_destroy(sk, ECONNABORTED);
+}
+#endif
+
+static const struct inet_diag_handler raw_diag_handler = {
+ .dump = raw_diag_dump,
+ .dump_one = raw_diag_dump_one,
+ .idiag_get_info = raw_diag_get_info,
+ .idiag_type = IPPROTO_RAW,
+ .idiag_info_size = 0,
+#ifdef CONFIG_INET_DIAG_DESTROY
+ .destroy = raw_diag_destroy,
+#endif
+};
+
+static void __always_unused __check_inet_diag_req_raw(void)
+{
+ /*
+ * Make sure the two structures are identical,
+ * except the @pad field.
+ */
+#define __offset_mismatch(m1, m2) \
+ (offsetof(struct inet_diag_req_v2, m1) != \
+ offsetof(struct inet_diag_req_raw, m2))
+
+ BUILD_BUG_ON(sizeof(struct inet_diag_req_v2) !=
+ sizeof(struct inet_diag_req_raw));
+ BUILD_BUG_ON(__offset_mismatch(sdiag_family, sdiag_family));
+ BUILD_BUG_ON(__offset_mismatch(sdiag_protocol, sdiag_protocol));
+ BUILD_BUG_ON(__offset_mismatch(idiag_ext, idiag_ext));
+ BUILD_BUG_ON(__offset_mismatch(pad, sdiag_raw_protocol));
+ BUILD_BUG_ON(__offset_mismatch(idiag_states, idiag_states));
+ BUILD_BUG_ON(__offset_mismatch(id, id));
+#undef __offset_mismatch
+}
+
+static int __init raw_diag_init(void)
+{
+ return inet_diag_register(&raw_diag_handler);
+}
+
+static void __exit raw_diag_exit(void)
+{
+ inet_diag_unregister(&raw_diag_handler);
+}
+
+module_init(raw_diag_init);
+module_exit(raw_diag_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-255 /* AF_INET - IPPROTO_RAW */);
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 10-255 /* AF_INET6 - IPPROTO_RAW */);
Index: linux-ml.git/net/ipv6/raw.c
===================================================================
--- linux-ml.git.orig/net/ipv6/raw.c
+++ linux-ml.git/net/ipv6/raw.c
@@ -65,11 +65,12 @@
#define ICMPV6_HDRLEN 4 /* ICMPv6 header, RFC 4443 Section 2.1 */
-static struct raw_hashinfo raw_v6_hashinfo = {
+struct raw_hashinfo raw_v6_hashinfo = {
.lock = __RW_LOCK_UNLOCKED(raw_v6_hashinfo.lock),
};
+EXPORT_SYMBOL_GPL(raw_v6_hashinfo);
-static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
+struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
unsigned short num, const struct in6_addr *loc_addr,
const struct in6_addr *rmt_addr, int dif)
{
@@ -102,6 +103,7 @@ static struct sock *__raw_v6_lookup(stru
found:
return sk;
}
+EXPORT_SYMBOL_GPL(__raw_v6_lookup);
/*
* 0 - deliver
@@ -1252,6 +1254,7 @@ struct proto rawv6_prot = {
.compat_getsockopt = compat_rawv6_getsockopt,
.compat_ioctl = compat_rawv6_ioctl,
#endif
+ .diag_destroy = raw_abort,
};
#ifdef CONFIG_PROC_FS
^ permalink raw reply
* Re: [PATCH] net: cpsw: fix obtaining mac address for am3517
From: Tony Lindgren @ 2016-10-21 9:51 UTC (permalink / raw)
To: Jeroen Hofstee
Cc: netdev, Mugunthan V N, Grygorii Strashko, linux-omap,
linux-kernel
In-Reply-To: <6dbeca0a-65ad-3a1c-2fe5-60023d83dabd@victronenergy.com>
* Jeroen Hofstee <jhofstee@victronenergy.com> [161021 02:31]:
> Aaah, lets wait a sec. I just saw there is another user of this function,
> so above is simply not true....
>
> if (of_machine_is_compatible("ti,dra7"))
> return davinci_emac_3517_get_macid(dev, 0x514, slave, mac_addr);
Oh OK, then this will produce duplicate macs.
> So let me check if I don't break that one..... or better, let me send a v2,
> which
> changes the caller to pass slave as 0 here?
>
> if (of_device_is_compatible(dev->of_node, "ti,am3517-emac"))
> return davinci_emac_3517_get_macid(dev, 0x110, slave, mac_addr);
>
Yeah that sounds good to me.
Regards,
Tony
^ permalink raw reply
* Re: [PATCH] net: cpsw: fix obtaining mac address for am3517
From: Jeroen Hofstee @ 2016-10-21 9:30 UTC (permalink / raw)
To: Tony Lindgren
Cc: netdev, Mugunthan V N, Grygorii Strashko, linux-omap,
linux-kernel
In-Reply-To: <20161021075317.767cu7qkmcn4k4e4@atomide.com>
Hello Tony,
On 21-10-16 09:53, Tony Lindgren wrote:
> * Jeroen Hofstee <jhofstee@victronenergy.com> [161021 00:37]:
>> Hello Tony,
>>
>> On 21-10-16 08:38, Tony Lindgren wrote:
>>> * Jeroen Hofstee <jhofstee@victronenergy.com> [161020 12:57]:
>>>> Commit b6745f6e4e63 ("drivers: net: cpsw: davinci_emac: move reading mac
>>>> id to common file") did not only move the code for an am3517, it also
>>>> added the slave parameter, resulting in a invalid (all zero) mac address
>>>> being returned. So change it back to always read from slave zero, so it
>>>> works again.
>>> Hmm doesn't this now break it for cpsw with two instances?
>>>
>> Yes, well, they get the same mac address at least. But does it matter?
>> This changes davinci_emac_3517_get_macid, the only way to get there
>> is:
>>
>> if (of_device_is_compatible(dev->of_node, "ti,am3517-emac"))
>> return davinci_emac_3517_get_macid(dev, 0x110, slave, mac_addr)
>>
>> and the only user of ti,am3517-emac is arch/arm/boot/dts/am3517.dtsi,
>> which only has one emac. So the change is already am3517 specific.
>>
>>> We may need am3517 specific quirk flag instead?
>> Given above, it is already am3517 specific. Let me know if you prefer this
>> route then I will have a look at it.
> Oh OK thanks for explaining it :) As it's already am3517 specific:
>
> Acked-by: Tony Lindgren <tony@atomide.com>
Aaah, lets wait a sec. I just saw there is another user of this function,
so above is simply not true....
if (of_machine_is_compatible("ti,dra7"))
return davinci_emac_3517_get_macid(dev, 0x514, slave, mac_addr);
So let me check if I don't break that one..... or better, let me send a
v2, which
changes the caller to pass slave as 0 here?
if (of_device_is_compatible(dev->of_node, "ti,am3517-emac"))
return davinci_emac_3517_get_macid(dev, 0x110, slave, mac_addr);
Regards,
Jeroen
^ permalink raw reply
* [PATCH net 3/7] qede: Loopback implementation should ignore the normal traffic
From: sudarsana.kalluru @ 2016-10-21 8:43 UTC (permalink / raw)
To: davem
Cc: netdev, Ariel.Elior, Yuval.Mintz, manish.chopra,
Sudarsana Reddy Kalluru
In-Reply-To: <1477039425-31341-1-git-send-email-sudarsana.kalluru@cavium.com>
From: Sudarsana Reddy Kalluru <sudarsana.kalluru@cavium.com>
During the execution of loopback test, driver may receive the packets which
are not originated by this test, loopback implementation need to skip those
packets.
Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Yuval Mintz <Yuval.Mintz@cavium.com>
---
drivers/net/ethernet/qlogic/qede/qede.h | 1 +
drivers/net/ethernet/qlogic/qede/qede_ethtool.c | 80 +++++++++++++++----------
drivers/net/ethernet/qlogic/qede/qede_main.c | 3 +-
3 files changed, 49 insertions(+), 35 deletions(-)
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index 28c0e9f..d6a4a9a5 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -348,6 +348,7 @@ void qede_reload(struct qede_dev *edev,
int qede_txq_has_work(struct qede_tx_queue *txq);
void qede_recycle_rx_bd_ring(struct qede_rx_queue *rxq, struct qede_dev *edev,
u8 count);
+void qede_update_rx_prod(struct qede_dev *edev, struct qede_rx_queue *rxq);
#define RX_RING_SIZE_POW 13
#define RX_RING_SIZE ((u16)BIT(RX_RING_SIZE_POW))
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index bf04fb9..7da184c 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -1207,8 +1207,8 @@ static int qede_selftest_receive_traffic(struct qede_dev *edev)
struct qede_rx_queue *rxq = NULL;
struct sw_rx_data *sw_rx_data;
union eth_rx_cqe *cqe;
+ int i, rc = 0;
u8 *data_ptr;
- int i;
for_each_queue(i) {
if (edev->fp_array[i].type & QEDE_FASTPATH_RX) {
@@ -1227,46 +1227,60 @@ static int qede_selftest_receive_traffic(struct qede_dev *edev)
* queue and that the loopback traffic is not IP.
*/
for (i = 0; i < QEDE_SELFTEST_POLL_COUNT; i++) {
- if (qede_has_rx_work(rxq))
+ if (!qede_has_rx_work(rxq)) {
+ usleep_range(100, 200);
+ continue;
+ }
+
+ hw_comp_cons = le16_to_cpu(*rxq->hw_cons_ptr);
+ sw_comp_cons = qed_chain_get_cons_idx(&rxq->rx_comp_ring);
+
+ /* Memory barrier to prevent the CPU from doing speculative
+ * reads of CQE/BD before reading hw_comp_cons. If the CQE is
+ * read before it is written by FW, then FW writes CQE and SB,
+ * and then the CPU reads the hw_comp_cons, it will use an old
+ * CQE.
+ */
+ rmb();
+
+ /* Get the CQE from the completion ring */
+ cqe = (union eth_rx_cqe *)qed_chain_consume(&rxq->rx_comp_ring);
+
+ /* Get the data from the SW ring */
+ sw_rx_index = rxq->sw_rx_cons & NUM_RX_BDS_MAX;
+ sw_rx_data = &rxq->sw_rx_ring[sw_rx_index];
+ fp_cqe = &cqe->fast_path_regular;
+ len = le16_to_cpu(fp_cqe->len_on_first_bd);
+ data_ptr = (u8 *)(page_address(sw_rx_data->data) +
+ fp_cqe->placement_offset +
+ sw_rx_data->page_offset);
+ if (ether_addr_equal(data_ptr, edev->ndev->dev_addr) &&
+ ether_addr_equal(data_ptr + ETH_ALEN,
+ edev->ndev->dev_addr)) {
+ for (i = ETH_HLEN; i < len; i++)
+ if (data_ptr[i] != (unsigned char)(i & 0xff)) {
+ rc = -1;
+ break;
+ }
+
+ qede_recycle_rx_bd_ring(rxq, edev, 1);
+ qed_chain_recycle_consumed(&rxq->rx_comp_ring);
break;
- usleep_range(100, 200);
+ }
+
+ DP_INFO(edev, "Not the transmitted packet\n");
+ qede_recycle_rx_bd_ring(rxq, edev, 1);
+ qed_chain_recycle_consumed(&rxq->rx_comp_ring);
}
- if (!qede_has_rx_work(rxq)) {
+ if (i == QEDE_SELFTEST_POLL_COUNT) {
DP_NOTICE(edev, "Failed to receive the traffic\n");
return -1;
}
- hw_comp_cons = le16_to_cpu(*rxq->hw_cons_ptr);
- sw_comp_cons = qed_chain_get_cons_idx(&rxq->rx_comp_ring);
-
- /* Memory barrier to prevent the CPU from doing speculative reads of CQE
- * / BD before reading hw_comp_cons. If the CQE is read before it is
- * written by FW, then FW writes CQE and SB, and then the CPU reads the
- * hw_comp_cons, it will use an old CQE.
- */
- rmb();
-
- /* Get the CQE from the completion ring */
- cqe = (union eth_rx_cqe *)qed_chain_consume(&rxq->rx_comp_ring);
-
- /* Get the data from the SW ring */
- sw_rx_index = rxq->sw_rx_cons & NUM_RX_BDS_MAX;
- sw_rx_data = &rxq->sw_rx_ring[sw_rx_index];
- fp_cqe = &cqe->fast_path_regular;
- len = le16_to_cpu(fp_cqe->len_on_first_bd);
- data_ptr = (u8 *)(page_address(sw_rx_data->data) +
- fp_cqe->placement_offset + sw_rx_data->page_offset);
- for (i = ETH_HLEN; i < len; i++)
- if (data_ptr[i] != (unsigned char)(i & 0xff)) {
- DP_NOTICE(edev, "Loopback test failed\n");
- qede_recycle_rx_bd_ring(rxq, edev, 1);
- return -1;
- }
-
- qede_recycle_rx_bd_ring(rxq, edev, 1);
+ qede_update_rx_prod(edev, rxq);
- return 0;
+ return rc;
}
static int qede_selftest_run_loopback(struct qede_dev *edev, u32 loopback_mode)
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 343038c..da8ef69 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -943,8 +943,7 @@ static inline int qede_realloc_rx_buffer(struct qede_dev *edev,
return 0;
}
-static inline void qede_update_rx_prod(struct qede_dev *edev,
- struct qede_rx_queue *rxq)
+void qede_update_rx_prod(struct qede_dev *edev, struct qede_rx_queue *rxq)
{
u16 bd_prod = qed_chain_get_prod_idx(&rxq->rx_bd_ring);
u16 cqe_prod = qed_chain_get_prod_idx(&rxq->rx_comp_ring);
--
1.8.3.1
^ permalink raw reply related
* [PATCH net 2/7] qede: Do not allow RSS config for 100G devices
From: sudarsana.kalluru @ 2016-10-21 8:43 UTC (permalink / raw)
To: davem
Cc: netdev, Ariel.Elior, Yuval.Mintz, manish.chopra,
Sudarsana Reddy Kalluru
In-Reply-To: <1477039425-31341-1-git-send-email-sudarsana.kalluru@cavium.com>
From: Sudarsana Reddy Kalluru <sudarsana.kalluru@cavium.com>
RSS configuration is not supported for 100G adapters.
Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Yuval Mintz <Yuval.Mintz@cavium.com>
---
drivers/net/ethernet/qlogic/qede/qede_ethtool.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index 16a1a47..bf04fb9 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -1055,6 +1055,12 @@ static int qede_set_rxfh(struct net_device *dev, const u32 *indir,
struct qede_dev *edev = netdev_priv(dev);
int i;
+ if (edev->dev_info.common.num_hwfns > 1) {
+ DP_INFO(edev,
+ "RSS configuration is not supported for 100G devices\n");
+ return -EOPNOTSUPP;
+ }
+
if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
return -EOPNOTSUPP;
--
1.8.3.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox