* The SO_BINDTODEVICE was set to the desired interface, but packets are received from all interfaces.
From: Damir Mansurov @ 2018-05-07 10:19 UTC (permalink / raw)
To: netdev; +Cc: Konstantin Ushakov, Alexandra N. Kossovsky, Andrey Dmitrov
[-- Attachment #1: Type: text/plain, Size: 1871 bytes --]
Greetings,
After successful call of the setsockopt(SO_BINDTODEVICE) function to set
data reception from only one interface, the data is still received from
all interfaces. Function setsockopt() returns 0 but then recv() receives
data from all available network interfaces.
The problem is reproducible on linux kernels 4.14 - 4.16, but it does
not on linux kernels 4.4, 4.13.
I have written C-code to reproduce this issue (see attached files
b2d_send.c and b2d_recv.c). See below explanation of tested configuration.
PC-1 PC-2
------------------- -------------------
| b2d_send | | b2d_recv |
| | | |
| ------| |------ |
| | eth0 |---------------| eth0 | |
| ------| |------ |
| | | |
| ------| |------ |
| | eth1 |---------------| eth1 | |
| ------| |------ |
| | | |
------------------- -------------------
Steps:
1. Copy b2d_recv.c to PC-2, compile it ("gcc -o b2d_recv b2d_recv.c")
and run "./b2d_recv eth0 23777" to get derived data only from eth0
interface. Port number in this example is 23777 only for sample.
2. Copy b2d_send.c to PC-1, compile it ("gcc -o b2d_send b2d_send.c")
and run "./b2d_send ip1 ip2 23777" where ip1 and ip2 are ip addresses of
interfaces eth0 and eth1 of PC-2.
3. Result:
- b2d_recv prints out data from eth0 and eth1 on linux kernels from 4.14
up to 4.16.
- b2d_recv prints out data from only eth0 on linux kernels below 4.14.
******************
Thanks,
Damir Mansurov
dnman@oktetlabs.ru
[-- Attachment #2: b2d_recv.c --]
[-- Type: text/x-csrc, Size: 3108 bytes --]
/*
* Receive udp packets from desired interface
*
* This tool is used to check that option SO_BINDTODEVICE works correctly
* setsockop(SO_BINDTODEVICE)
* Use together with b2d_send.c
*
* 1. Start b2d_recv on receiver PC
* 2. Start b2d_send on sender PC
* 3. Check that packets are received only from the selected interface
*
* usage: ./b2d_recv interface port
* example: ./b2d_recv eth0 23777
*/
#include <sys/types.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <arpa/inet.h>
#include <unistd.h>
#include <errno.h>
#define RX_BUFF_SIZE 1024
/* create recv socket, if error occured exit(EXIT_FAILURE) */
int create_recv_sock(const char * str_interface, const char * str_port,
struct sockaddr_in * sock_addr);
int
main(int argc, char *argv[])
{
struct sockaddr_in sa_recv;
if (argc != 3)
{
printf("usage: %s interface port\n", argv[0]);
exit(EXIT_FAILURE);
}
int sfd_recv = create_recv_sock(argv[1], argv[2], &sa_recv);
char rx_buff[RX_BUFF_SIZE] = {0};
struct sockaddr_in src_addr;
socklen_t addr_len;
memset(&src_addr, 0, sizeof(struct sockaddr_in));
while (1)
{
ssize_t res = recvfrom(sfd_recv, rx_buff, RX_BUFF_SIZE - 1, 0,
(struct sockaddr *)&src_addr, &addr_len);
if (res < 0)
{
perror("recvfrom");
exit(EXIT_FAILURE);
}
char buf[256];
const char * x = inet_ntop(src_addr.sin_family, &src_addr.sin_addr,
buf, addr_len);
if (x == NULL)
{
perror("inet_ntop");
exit(EXIT_FAILURE);
}
printf("recv %ld bytes from %s:%u: \"%s\"\n",
res, buf, ntohs(src_addr.sin_port), rx_buff);
}
exit(EXIT_SUCCESS);
}
int
create_recv_sock(const char * str_interface, const char * str_port,
struct sockaddr_in * sock_addr)
{
int sockfd = socket(AF_INET, SOCK_DGRAM, 0);
if (sockfd < 0)
{
perror("socket");
exit(EXIT_FAILURE);
}
memset(sock_addr, 0, sizeof(struct sockaddr_in));
sock_addr->sin_family = AF_INET;
sock_addr->sin_addr.s_addr = htonl(INADDR_ANY);
sock_addr->sin_port = htons((uint16_t)atoi(str_port));
int res = bind(sockfd, (struct sockaddr*)sock_addr,
sizeof(struct sockaddr_in));
if (res < 0)
{
perror("bind");
exit(EXIT_FAILURE);
}
if (strlen(str_interface) == 0)
{
puts("Data will be received from all interfaces");
}
else
{
res = setsockopt(sockfd, SOL_SOCKET, SO_BINDTODEVICE,
str_interface, strlen(str_interface) + 1);
if (res < 0)
{
perror("setsockopt");
exit(EXIT_FAILURE);
}
else
{
printf("success bind to device \"%s\"\n", str_interface);
}
}
printf("recv port %s\n", str_port);
return sockfd;
}/* create_recv_socket() */
[-- Attachment #3: b2d_send.c --]
[-- Type: text/x-csrc, Size: 2501 bytes --]
/*
* Send udp packets from two various interfaces,
*
* This tool used to check correctly work option
* setsockopt(SO_BINDTODEVICE)
* Use together with b2d_recv.c
* Detailed description in file b2d_recv.c
*
* usage ./b2d_send ip1 ip2 port
* example: ./b2d_send 192.168.44.2 192.168.45.2 23777
*/
#include <sys/types.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <arpa/inet.h>
#include <unistd.h>
#include <errno.h>
#define RX_BUFF_SIZE 1024
/* create sender socket, if error occured exit(EXIT_FAILURE) */
int create_sender_sock(const char * str_ip, const char * str_port,
struct sockaddr_in * sock_addr);
int
main(int argc, char *argv[])
{
struct sockaddr_in sa_sender1, sa_sender2;
if (argc != 4)
{
printf("usage: %s ip1 ip2 port\n", argv[0]);
exit(EXIT_FAILURE);
}
int sfd_sender1 = create_sender_sock(argv[1], argv[3], &sa_sender1);
int sfd_sender2 = create_sender_sock(argv[2], argv[3], &sa_sender2);
char tx_buff1[] = "Data from first socket";
char tx_buff2[] = "Data from second socket";
ssize_t res = send(sfd_sender1, tx_buff1, strlen(tx_buff1) + 1, 0);
if (res < 0)
{
perror("sender1");
exit(EXIT_FAILURE);
}
printf("success send %ld bytes to %s:%s \"%s\"\n",
res, argv[1], argv[3], tx_buff1);
res = send(sfd_sender2, tx_buff2, strlen(tx_buff2) + 1, 0);
if (res < 0)
{
perror("sender2");
exit(EXIT_FAILURE);
}
printf("success send %ld bytes to %s:%s \"%s\"\n",
res, argv[2], argv[3], tx_buff2);
exit(EXIT_SUCCESS);
}/* main() */
int
create_sender_sock(const char * str_ip, const char * str_port,
struct sockaddr_in * sock_addr)
{
int res;
int sockfd = socket(AF_INET, SOCK_DGRAM, 0);
if (sockfd < 0)
{
perror("socket");
exit(EXIT_FAILURE);
}
memset(sock_addr, 0, sizeof(struct sockaddr_in));
sock_addr->sin_family = AF_INET;
if (inet_pton(AF_INET, str_ip, &(sock_addr->sin_addr)) != 1)
{
perror("Bad ip_add");
exit(EXIT_FAILURE);
}
sock_addr->sin_port = htons((uint16_t)atoi(str_port));
res = connect(sockfd, (struct sockaddr*)sock_addr,
sizeof(struct sockaddr_in));
if (res < 0)
{
perror("connect");
exit(EXIT_FAILURE);
}
return sockfd;
}/* create_sender_socket() */
^ permalink raw reply
* Re: [RFC bpf-next 00/10] initial control flow support for eBPF verifier
From: Jiong Wang @ 2018-05-07 10:33 UTC (permalink / raw)
To: alexei.starovoitov, daniel; +Cc: john.fastabend, netdev, oss-drivers
In-Reply-To: <1525688567-19618-1-git-send-email-jiong.wang@netronome.com>
On 07/05/2018 11:22, Jiong Wang wrote:
> execution time
> ===
> test_l4lb_noinline:
> existing check_subprog/check_cfg: ~55000 ns
> new infrastructure: ~135000 ns
>
> test_xdp_noinline:
> existing check_subprog/check_cfg: ~52000 ns
> new infrastructure: ~120000 ns
Intel(R) Xeon(R) CPU E5-2630 v4 @ 2.20GHz
Regards,
Jiong
^ permalink raw reply
* [PATCH net] MAINTAINERS: Update the 3c59x network driver entry
From: Steffen Klassert @ 2018-05-07 10:39 UTC (permalink / raw)
To: David Miller; +Cc: netdev
Replace my old E-Mail address with a working one.
While at it, change the maintainance status to
'Odd Fixes'. I'm still around with some knowledge,
but don't actively maintain it anymore.
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
MAINTAINERS | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index b1ccabd0dbc3..b3cbf1c3ed07 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -137,9 +137,9 @@ Maintainers List (try to look for most precise areas first)
-----------------------------------
3C59X NETWORK DRIVER
-M: Steffen Klassert <klassert@mathematik.tu-chemnitz.de>
+M: Steffen Klassert <klassert@kernel.org>
L: netdev@vger.kernel.org
-S: Maintained
+S: Odd Fixes
F: Documentation/networking/vortex.txt
F: drivers/net/ethernet/3com/3c59x.c
--
2.14.1
^ permalink raw reply related
* [iproute2-next 1/1] tipc: Add support to set and get MTU for UDP bearer
From: GhantaKrishnamurthy MohanKrishna @ 2018-05-07 11:14 UTC (permalink / raw)
To: tipc-discussion, jon.maloy, maloy, ying.xue,
mohan.krishna.ghanta.krishnamurthy, netdev, davem, dsahern
In this commit we introduce the ability to set and get
MTU for UDP media and bearer.
For set and get properties such as tolerance, window and priority,
we already do:
$ tipc media set PPROPERTY media MEDIA
$ tipc media get PPROPERTY media MEDIA
$ tipc bearer set OPTION media MEDIA ARGS
$ tipc bearer get [OPTION] media MEDIA ARGS
The same has been extended for MTU, with an exception to support
only media type UDP.
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: GhantaKrishnamurthy MohanKrishna <mohan.krishna.ghanta.krishnamurthy@ericsson.com>
---
tipc/bearer.c | 55 ++++++++++++++++++++++++++++++++++++++++++++++---------
tipc/media.c | 24 ++++++++++++++++++++++--
2 files changed, 68 insertions(+), 11 deletions(-)
diff --git a/tipc/bearer.c b/tipc/bearer.c
index 0d8457015062..27e8d77f5635 100644
--- a/tipc/bearer.c
+++ b/tipc/bearer.c
@@ -42,7 +42,8 @@ static void _print_bearer_opts(void)
"OPTIONS\n"
" priority - Bearer link priority\n"
" tolerance - Bearer link tolerance\n"
- " window - Bearer link window\n");
+ " window - Bearer link window\n"
+ " mtu - Bearer link mtu\n");
}
void print_bearer_media(void)
@@ -194,6 +195,21 @@ static int nl_add_udp_enable_opts(struct nlmsghdr *nlh, struct opt *opts,
return 0;
}
+static char *cmd_get_media_type(const struct cmd *cmd, struct cmdl *cmdl,
+ struct opt *opts)
+{
+ struct opt *opt;
+
+ if (!(opt = get_opt(opts, "media"))) {
+ if (help_flag)
+ (cmd->help)(cmdl);
+ else
+ fprintf(stderr, "error, missing bearer media\n");
+ return NULL;
+ }
+ return opt->val;
+}
+
static int nl_add_bearer_name(struct nlmsghdr *nlh, const struct cmd *cmd,
struct cmdl *cmdl, struct opt *opts,
const struct tipc_sup_media *sup_media)
@@ -217,15 +233,8 @@ int cmd_get_unique_bearer_name(const struct cmd *cmd, struct cmdl *cmdl,
struct opt *opt;
const struct tipc_sup_media *entry;
-
- if (!(opt = get_opt(opts, "media"))) {
- if (help_flag)
- (cmd->help)(cmdl);
- else
- fprintf(stderr, "error, missing bearer media\n");
+ if (!(media = cmd_get_media_type(cmd, cmdl, opts)))
return -EINVAL;
- }
- media = opt->val;
for (entry = sup_media; entry->media; entry++) {
if (strcmp(entry->media, media))
@@ -559,6 +568,8 @@ static int cmd_bearer_set_prop(struct nlmsghdr *nlh, const struct cmd *cmd,
prop = TIPC_NLA_PROP_TOL;
else if ((strcmp(cmd->cmd, "window") == 0))
prop = TIPC_NLA_PROP_WIN;
+ else if ((strcmp(cmd->cmd, "mtu") == 0))
+ prop = TIPC_NLA_PROP_MTU;
else
return -EINVAL;
@@ -571,6 +582,17 @@ static int cmd_bearer_set_prop(struct nlmsghdr *nlh, const struct cmd *cmd,
if (parse_opts(opts, cmdl) < 0)
return -EINVAL;
+ if (prop == TIPC_NLA_PROP_MTU) {
+ char *media;
+
+ if (!(media = cmd_get_media_type(cmd, cmdl, opts)))
+ return -EINVAL;
+ else if (strcmp(media, "udp")) {
+ fprintf(stderr, "error, not supported for media\n");
+ return -EINVAL;
+ }
+ }
+
if (!(nlh = msg_init(buf, TIPC_NL_BEARER_SET))) {
fprintf(stderr, "error, message initialisation failed\n");
return -1;
@@ -597,6 +619,7 @@ static int cmd_bearer_set(struct nlmsghdr *nlh, const struct cmd *cmd,
{ "priority", cmd_bearer_set_prop, cmd_bearer_set_help },
{ "tolerance", cmd_bearer_set_prop, cmd_bearer_set_help },
{ "window", cmd_bearer_set_prop, cmd_bearer_set_help },
+ { "mtu", cmd_bearer_set_prop, cmd_bearer_set_help },
{ NULL }
};
@@ -877,12 +900,25 @@ static int cmd_bearer_get_prop(struct nlmsghdr *nlh, const struct cmd *cmd,
prop = TIPC_NLA_PROP_TOL;
else if ((strcmp(cmd->cmd, "window") == 0))
prop = TIPC_NLA_PROP_WIN;
+ else if ((strcmp(cmd->cmd, "mtu") == 0))
+ prop = TIPC_NLA_PROP_MTU;
else
return -EINVAL;
if (parse_opts(opts, cmdl) < 0)
return -EINVAL;
+ if (prop == TIPC_NLA_PROP_MTU) {
+ char *media;
+
+ if (!(media = cmd_get_media_type(cmd, cmdl, opts)))
+ return -EINVAL;
+ else if (strcmp(media, "udp")) {
+ fprintf(stderr, "error, not supported for media\n");
+ return -EINVAL;
+ }
+ }
+
if (!(nlh = msg_init(buf, TIPC_NL_BEARER_GET))) {
fprintf(stderr, "error, message initialisation failed\n");
return -1;
@@ -904,6 +940,7 @@ static int cmd_bearer_get(struct nlmsghdr *nlh, const struct cmd *cmd,
{ "priority", cmd_bearer_get_prop, cmd_bearer_get_help },
{ "tolerance", cmd_bearer_get_prop, cmd_bearer_get_help },
{ "window", cmd_bearer_get_prop, cmd_bearer_get_help },
+ { "mtu", cmd_bearer_get_prop, cmd_bearer_get_help },
{ "media", cmd_bearer_get_media, cmd_bearer_get_help },
{ NULL }
};
diff --git a/tipc/media.c b/tipc/media.c
index 6e10c7e5d8e6..969ef6578b3b 100644
--- a/tipc/media.c
+++ b/tipc/media.c
@@ -103,6 +103,8 @@ static int cmd_media_get_prop(struct nlmsghdr *nlh, const struct cmd *cmd,
prop = TIPC_NLA_PROP_TOL;
else if ((strcmp(cmd->cmd, "window") == 0))
prop = TIPC_NLA_PROP_WIN;
+ else if ((strcmp(cmd->cmd, "mtu") == 0))
+ prop = TIPC_NLA_PROP_MTU;
else
return -EINVAL;
@@ -123,6 +125,12 @@ static int cmd_media_get_prop(struct nlmsghdr *nlh, const struct cmd *cmd,
fprintf(stderr, "error, missing media\n");
return -EINVAL;
}
+
+ if ((prop == TIPC_NLA_PROP_MTU) &&
+ (strcmp(opt->val, "udp"))) {
+ fprintf(stderr, "error, not supported for media\n");
+ return -EINVAL;
+ }
nest = mnl_attr_nest_start(nlh, TIPC_NLA_MEDIA);
mnl_attr_put_strz(nlh, TIPC_NLA_MEDIA_NAME, opt->val);
mnl_attr_nest_end(nlh, nest);
@@ -136,7 +144,8 @@ static void cmd_media_get_help(struct cmdl *cmdl)
"PROPERTIES\n"
" tolerance - Get media tolerance\n"
" priority - Get media priority\n"
- " window - Get media window\n",
+ " window - Get media window\n"
+ " mtu - Get media mtu\n",
cmdl->argv[0]);
}
@@ -147,6 +156,7 @@ static int cmd_media_get(struct nlmsghdr *nlh, const struct cmd *cmd,
{ "priority", cmd_media_get_prop, cmd_media_get_help },
{ "tolerance", cmd_media_get_prop, cmd_media_get_help },
{ "window", cmd_media_get_prop, cmd_media_get_help },
+ { "mtu", cmd_media_get_prop, cmd_media_get_help },
{ NULL }
};
@@ -159,7 +169,8 @@ static void cmd_media_set_help(struct cmdl *cmdl)
"PROPERTIES\n"
" tolerance TOLERANCE - Set media tolerance\n"
" priority PRIORITY - Set media priority\n"
- " window WINDOW - Set media window\n",
+ " window WINDOW - Set media window\n"
+ " mtu MTU - Set media mtu\n",
cmdl->argv[0]);
}
@@ -183,6 +194,8 @@ static int cmd_media_set_prop(struct nlmsghdr *nlh, const struct cmd *cmd,
prop = TIPC_NLA_PROP_TOL;
else if ((strcmp(cmd->cmd, "window") == 0))
prop = TIPC_NLA_PROP_WIN;
+ else if ((strcmp(cmd->cmd, "mtu") == 0))
+ prop = TIPC_NLA_PROP_MTU;
else
return -EINVAL;
@@ -210,6 +223,12 @@ static int cmd_media_set_prop(struct nlmsghdr *nlh, const struct cmd *cmd,
fprintf(stderr, "error, missing media\n");
return -EINVAL;
}
+
+ if ((prop == TIPC_NLA_PROP_MTU) &&
+ (strcmp(opt->val, "udp"))) {
+ fprintf(stderr, "error, not supported for media\n");
+ return -EINVAL;
+ }
mnl_attr_put_strz(nlh, TIPC_NLA_MEDIA_NAME, opt->val);
props = mnl_attr_nest_start(nlh, TIPC_NLA_MEDIA_PROP);
@@ -228,6 +247,7 @@ static int cmd_media_set(struct nlmsghdr *nlh, const struct cmd *cmd,
{ "priority", cmd_media_set_prop, cmd_media_set_help },
{ "tolerance", cmd_media_set_prop, cmd_media_set_help },
{ "window", cmd_media_set_prop, cmd_media_set_help },
+ { "mtu", cmd_media_set_prop, cmd_media_set_help },
{ NULL }
};
--
2.1.4
^ permalink raw reply related
* Re: [PATCHv2 net] sctp: delay the authentication for the duplicated cookie-echo chunk
From: Neil Horman @ 2018-05-07 11:38 UTC (permalink / raw)
To: Xin Long; +Cc: network dev, linux-sctp, davem, Marcelo Ricardo Leitner
In-Reply-To: <2a815adb308826967c84cd8dc371c3c9b054c8da.1525503587.git.lucien.xin@gmail.com>
On Sat, May 05, 2018 at 02:59:47PM +0800, Xin Long wrote:
> Now sctp only delays the authentication for the normal cookie-echo
> chunk by setting chunk->auth_chunk in sctp_endpoint_bh_rcv(). But
> for the duplicated one with auth, in sctp_assoc_bh_rcv(), it does
> authentication first based on the old asoc, which will definitely
> fail due to the different auth info in the old asoc.
>
> The duplicated cookie-echo chunk will create a new asoc with the
> auth info from this chunk, and the authentication should also be
> done with the new asoc's auth info for all of the collision 'A',
> 'B' and 'D'. Otherwise, the duplicated cookie-echo chunk with auth
> will never pass the authentication and create the new connection.
>
> This issue exists since very beginning, and this fix is to make
> sctp_assoc_bh_rcv() follow the way sctp_endpoint_bh_rcv() does
> for the normal cookie-echo chunk to delay the authentication.
>
> While at it, remove the unused params from sctp_sf_authenticate()
> and define sctp_auth_chunk_verify() used for all the places that
> do the delayed authentication.
>
> v1->v2:
> fix the typo in changelog as Marcelo noticed.
>
> Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
> Signed-off-by: Xin Long <lucien.xin@gmail.com>
> ---
> net/sctp/associola.c | 30 ++++++++++++++++-
> net/sctp/sm_statefuns.c | 86 ++++++++++++++++++++++++++-----------------------
> 2 files changed, 75 insertions(+), 41 deletions(-)
>
> diff --git a/net/sctp/associola.c b/net/sctp/associola.c
> index 837806d..a47179d 100644
> --- a/net/sctp/associola.c
> +++ b/net/sctp/associola.c
> @@ -1024,8 +1024,9 @@ static void sctp_assoc_bh_rcv(struct work_struct *work)
> struct sctp_endpoint *ep;
> struct sctp_chunk *chunk;
> struct sctp_inq *inqueue;
> - int state;
> + int first_time = 1; /* is this the first time through the loop */
> int error = 0;
> + int state;
>
> /* The association should be held so we should be safe. */
> ep = asoc->ep;
> @@ -1036,6 +1037,30 @@ static void sctp_assoc_bh_rcv(struct work_struct *work)
> state = asoc->state;
> subtype = SCTP_ST_CHUNK(chunk->chunk_hdr->type);
>
> + /* If the first chunk in the packet is AUTH, do special
> + * processing specified in Section 6.3 of SCTP-AUTH spec
> + */
> + if (first_time && subtype.chunk == SCTP_CID_AUTH) {
> + struct sctp_chunkhdr *next_hdr;
> +
> + next_hdr = sctp_inq_peek(inqueue);
> + if (!next_hdr)
> + goto normal;
> +
> + /* If the next chunk is COOKIE-ECHO, skip the AUTH
> + * chunk while saving a pointer to it so we can do
> + * Authentication later (during cookie-echo
> + * processing).
> + */
> + if (next_hdr->type == SCTP_CID_COOKIE_ECHO) {
> + chunk->auth_chunk = skb_clone(chunk->skb,
> + GFP_ATOMIC);
> + chunk->auth = 1;
> + continue;
> + }
> + }
> +
> +normal:
> /* SCTP-AUTH, Section 6.3:
> * The receiver has a list of chunk types which it expects
> * to be received only after an AUTH-chunk. This list has
> @@ -1074,6 +1099,9 @@ static void sctp_assoc_bh_rcv(struct work_struct *work)
> /* If there is an error on chunk, discard this packet. */
> if (error && chunk)
> chunk->pdiscard = 1;
> +
> + if (first_time)
> + first_time = 0;
> }
> sctp_association_put(asoc);
> }
> diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
> index 28c070e..c9ae340 100644
> --- a/net/sctp/sm_statefuns.c
> +++ b/net/sctp/sm_statefuns.c
> @@ -153,10 +153,7 @@ static enum sctp_disposition sctp_sf_violation_chunk(
> struct sctp_cmd_seq *commands);
>
> static enum sctp_ierror sctp_sf_authenticate(
> - struct net *net,
> - const struct sctp_endpoint *ep,
> const struct sctp_association *asoc,
> - const union sctp_subtype type,
> struct sctp_chunk *chunk);
>
> static enum sctp_disposition __sctp_sf_do_9_1_abort(
> @@ -626,6 +623,38 @@ enum sctp_disposition sctp_sf_do_5_1C_ack(struct net *net,
> return SCTP_DISPOSITION_CONSUME;
> }
>
> +static bool sctp_auth_chunk_verify(struct net *net, struct sctp_chunk *chunk,
> + const struct sctp_association *asoc)
> +{
> + struct sctp_chunk auth;
> +
> + if (!chunk->auth_chunk)
> + return true;
> +
> + /* SCTP-AUTH: auth_chunk pointer is only set when the cookie-echo
> + * is supposed to be authenticated and we have to do delayed
> + * authentication. We've just recreated the association using
> + * the information in the cookie and now it's much easier to
> + * do the authentication.
> + */
> +
> + /* Make sure that we and the peer are AUTH capable */
> + if (!net->sctp.auth_enable || !asoc->peer.auth_capable)
> + return false;
> +
> + /* set-up our fake chunk so that we can process it */
> + auth.skb = chunk->auth_chunk;
> + auth.asoc = chunk->asoc;
> + auth.sctp_hdr = chunk->sctp_hdr;
> + auth.chunk_hdr = (struct sctp_chunkhdr *)
> + skb_push(chunk->auth_chunk,
> + sizeof(struct sctp_chunkhdr));
> + skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr));
> + auth.transport = chunk->transport;
> +
> + return sctp_sf_authenticate(asoc, &auth) == SCTP_IERROR_NO_ERROR;
> +}
> +
> /*
> * Respond to a normal COOKIE ECHO chunk.
> * We are the side that is being asked for an association.
> @@ -763,37 +792,9 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net,
> if (error)
> goto nomem_init;
>
> - /* SCTP-AUTH: auth_chunk pointer is only set when the cookie-echo
> - * is supposed to be authenticated and we have to do delayed
> - * authentication. We've just recreated the association using
> - * the information in the cookie and now it's much easier to
> - * do the authentication.
> - */
> - if (chunk->auth_chunk) {
> - struct sctp_chunk auth;
> - enum sctp_ierror ret;
> -
> - /* Make sure that we and the peer are AUTH capable */
> - if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) {
> - sctp_association_free(new_asoc);
> - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
> - }
> -
> - /* set-up our fake chunk so that we can process it */
> - auth.skb = chunk->auth_chunk;
> - auth.asoc = chunk->asoc;
> - auth.sctp_hdr = chunk->sctp_hdr;
> - auth.chunk_hdr = (struct sctp_chunkhdr *)
> - skb_push(chunk->auth_chunk,
> - sizeof(struct sctp_chunkhdr));
> - skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr));
> - auth.transport = chunk->transport;
> -
> - ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth);
> - if (ret != SCTP_IERROR_NO_ERROR) {
> - sctp_association_free(new_asoc);
> - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
> - }
> + if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) {
> + sctp_association_free(new_asoc);
> + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
> }
>
> repl = sctp_make_cookie_ack(new_asoc, chunk);
> @@ -1797,13 +1798,15 @@ static enum sctp_disposition sctp_sf_do_dupcook_a(
> if (sctp_auth_asoc_init_active_key(new_asoc, GFP_ATOMIC))
> goto nomem;
>
> + if (!sctp_auth_chunk_verify(net, chunk, new_asoc))
> + return SCTP_DISPOSITION_DISCARD;
> +
> /* Make sure no new addresses are being added during the
> * restart. Though this is a pretty complicated attack
> * since you'd have to get inside the cookie.
> */
> - if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands)) {
> + if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands))
> return SCTP_DISPOSITION_CONSUME;
> - }
>
> /* If the endpoint is in the SHUTDOWN-ACK-SENT state and recognizes
> * the peer has restarted (Action A), it MUST NOT setup a new
> @@ -1912,6 +1915,9 @@ static enum sctp_disposition sctp_sf_do_dupcook_b(
> if (sctp_auth_asoc_init_active_key(new_asoc, GFP_ATOMIC))
> goto nomem;
>
> + if (!sctp_auth_chunk_verify(net, chunk, new_asoc))
> + return SCTP_DISPOSITION_DISCARD;
> +
> /* Update the content of current association. */
> sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc));
> sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE,
> @@ -2009,6 +2015,9 @@ static enum sctp_disposition sctp_sf_do_dupcook_d(
> * a COOKIE ACK.
> */
>
> + if (!sctp_auth_chunk_verify(net, chunk, asoc))
> + return SCTP_DISPOSITION_DISCARD;
> +
> /* Don't accidentally move back into established state. */
> if (asoc->state < SCTP_STATE_ESTABLISHED) {
> sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
> @@ -4171,10 +4180,7 @@ enum sctp_disposition sctp_sf_eat_fwd_tsn_fast(
> * The return value is the disposition of the chunk.
> */
> static enum sctp_ierror sctp_sf_authenticate(
> - struct net *net,
> - const struct sctp_endpoint *ep,
> const struct sctp_association *asoc,
> - const union sctp_subtype type,
> struct sctp_chunk *chunk)
> {
> struct sctp_shared_key *sh_key = NULL;
> @@ -4275,7 +4281,7 @@ enum sctp_disposition sctp_sf_eat_auth(struct net *net,
> commands);
>
> auth_hdr = (struct sctp_authhdr *)chunk->skb->data;
> - error = sctp_sf_authenticate(net, ep, asoc, type, chunk);
> + error = sctp_sf_authenticate(asoc, chunk);
> switch (error) {
> case SCTP_IERROR_AUTH_BAD_HMAC:
> /* Generate the ERROR chunk and discard the rest
> --
> 2.1.0
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-sctp" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
^ permalink raw reply
* [PATCH] trivial: fix inconsistent help texts
From: Georg Hofmann @ 2018-05-07 12:03 UTC (permalink / raw)
Cc: Georg Hofmann, David S. Miller, Alexey Kuznetsov,
Hideaki YOSHIFUJI, Jiri Kosina, netdev, linux-kernel
This patch removes "experimental" from the help text where depends on
CONFIG_EXPERIMENTAL was already removed.
Signed-off-by: Georg Hofmann <georg@hofmannsweb.com>
---
net/ipv6/Kconfig | 9 ++++-----
1 file changed, 4 insertions(+), 5 deletions(-)
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index 6794ddf..11e4e80 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -34,16 +34,15 @@ config IPV6_ROUTE_INFO
bool "IPv6: Route Information (RFC 4191) support"
depends on IPV6_ROUTER_PREF
---help---
- This is experimental support of Route Information.
+ Support of Route Information.
If unsure, say N.
config IPV6_OPTIMISTIC_DAD
bool "IPv6: Enable RFC 4429 Optimistic DAD"
---help---
- This is experimental support for optimistic Duplicate
- Address Detection. It allows for autoconfigured addresses
- to be used more quickly.
+ Support for optimistic Duplicate Address Detection. It allows for
+ autoconfigured addresses to be used more quickly.
If unsure, say N.
@@ -280,7 +279,7 @@ config IPV6_MROUTE
depends on IPV6
select IP_MROUTE_COMMON
---help---
- Experimental support for IPv6 multicast forwarding.
+ Support for IPv6 multicast forwarding.
If unsure, say N.
config IPV6_MROUTE_MULTIPLE_TABLES
--
2.7.4
^ permalink raw reply related
* [PATCH net-next] dt-bindings: dsa: Remove unnecessary #address/#size-cells
From: Fabio Estevam @ 2018-05-07 12:17 UTC (permalink / raw)
To: davem; +Cc: f.fainelli, andrew, robh+dt, netdev, devicetree, Fabio Estevam
From: Fabio Estevam <fabio.estevam@nxp.com>
If the example binding is used on a real dts file, the following DTC
warning is seen with W=1:
arch/arm/boot/dts/imx6q-b450v3.dtb: Warning (avoid_unnecessary_addr_size): /mdio-gpio/switch@0: unnecessary #address-cells/#size-cells without "ranges" or child "reg" property
Remove unnecessary #address-cells/#size-cells to improve the binding
document examples.
Signed-off-by: Fabio Estevam <fabio.estevam@nxp.com>
---
Documentation/devicetree/bindings/net/dsa/dsa.txt | 6 ------
1 file changed, 6 deletions(-)
diff --git a/Documentation/devicetree/bindings/net/dsa/dsa.txt b/Documentation/devicetree/bindings/net/dsa/dsa.txt
index cfe8f64..3ceeb8d 100644
--- a/Documentation/devicetree/bindings/net/dsa/dsa.txt
+++ b/Documentation/devicetree/bindings/net/dsa/dsa.txt
@@ -82,8 +82,6 @@ linked into one DSA cluster.
switch0: switch0@0 {
compatible = "marvell,mv88e6085";
- #address-cells = <1>;
- #size-cells = <0>;
reg = <0>;
dsa,member = <0 0>;
@@ -135,8 +133,6 @@ linked into one DSA cluster.
switch1: switch1@0 {
compatible = "marvell,mv88e6085";
- #address-cells = <1>;
- #size-cells = <0>;
reg = <0>;
dsa,member = <0 1>;
@@ -204,8 +200,6 @@ linked into one DSA cluster.
switch2: switch2@0 {
compatible = "marvell,mv88e6085";
- #address-cells = <1>;
- #size-cells = <0>;
reg = <0>;
dsa,member = <0 2>;
--
2.7.4
^ permalink raw reply related
* Re: [PATCH 09/18] net: mac80211.h: fix a bad comment line
From: Kalle Valo @ 2018-05-07 12:37 UTC (permalink / raw)
To: Mauro Carvalho Chehab
Cc: Linux Doc Mailing List, Mauro Carvalho Chehab, linux-kernel,
Jonathan Corbet, Johannes Berg, David S. Miller, linux-wireless,
netdev
In-Reply-To: <1b14ef4f63547c86c544e112b74acfff2b41f4af.1525684985.git.mchehab+samsung@kernel.org>
Mauro Carvalho Chehab <mchehab+samsung@kernel.org> writes:
> Sphinx produces a lot of errors like this:
> ./include/net/mac80211.h:2083: warning: bad line: >
>
> Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Randy already submitted a similar patch:
https://patchwork.kernel.org/patch/10367275/
But it seems Johannes has not applied that yet.
--
Kalle Valo
^ permalink raw reply
* Re: [PATCH 09/18] net: mac80211.h: fix a bad comment line
From: Johannes Berg @ 2018-05-07 12:38 UTC (permalink / raw)
To: Kalle Valo, Mauro Carvalho Chehab
Cc: Linux Doc Mailing List, Mauro Carvalho Chehab, linux-kernel,
Jonathan Corbet, David S. Miller, linux-wireless, netdev
In-Reply-To: <87fu334p5v.fsf@purkki.adurom.net>
On Mon, 2018-05-07 at 15:37 +0300, Kalle Valo wrote:
> Mauro Carvalho Chehab <mchehab+samsung@kernel.org> writes:
>
> > Sphinx produces a lot of errors like this:
> > ./include/net/mac80211.h:2083: warning: bad line: >
> >
> > Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
>
> Randy already submitted a similar patch:
>
> https://patchwork.kernel.org/patch/10367275/
>
> But it seems Johannes has not applied that yet.
Yeah, I've been super busy preparing for the plugfest.
I'll make a pass over all the patches as soon as I can, hopefully today
or tomorrow.
johannes
^ permalink raw reply
* Re: The SO_BINDTODEVICE was set to the desired interface, but packets are received from all interfaces.
From: Paolo Abeni @ 2018-05-07 12:41 UTC (permalink / raw)
To: Damir Mansurov, netdev, David Ahern
Cc: Konstantin Ushakov, Alexandra N. Kossovsky, Andrey Dmitrov
In-Reply-To: <5a61e34b-75c2-0452-d6e2-6e4ea77d5ac2@oktetlabs.ru>
Hi,
On Mon, 2018-05-07 at 13:19 +0300, Damir Mansurov wrote:
> After successful call of the setsockopt(SO_BINDTODEVICE) function to set
> data reception from only one interface, the data is still received from
> all interfaces. Function setsockopt() returns 0 but then recv() receives
> data from all available network interfaces.
>
> The problem is reproducible on linux kernels 4.14 - 4.16, but it does
> not on linux kernels 4.4, 4.13.
I think that the cause is commit:
commit fb74c27735f0a34e76dbf1972084e984ad2ea145
Author: David Ahern <dsahern@gmail.com>
Date: Mon Aug 7 08:44:16 2017 -0700
net: ipv4: add second dif to udp socket lookups
Something like the following should fix, but I'm unsure it preserves
the intended semathics for 'sdif'. David, can you please have a look?
Thanks!
Paolo
---
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index dd3102a37ef9..0d593d5c33cf 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -401,9 +401,9 @@ static int compute_score(struct sock *sk, struct net *net,
bool dev_match = (sk->sk_bound_dev_if == dif ||
sk->sk_bound_dev_if == sdif);
- if (exact_dif && !dev_match)
+ if (!dev_match)
return -1;
- if (sk->sk_bound_dev_if && dev_match)
+ if (sk->sk_bound_dev_if)
score += 4;
}
^ permalink raw reply related
* Re: [PATCH net] vhost: Use kzalloc() to allocate vhost_msg_node
From: Michael S. Tsirkin @ 2018-05-07 13:03 UTC (permalink / raw)
To: Kevin Easton
Cc: Jason Wang, kvm, virtualization, netdev, linux-kernel,
syzkaller-bugs
In-Reply-To: <20180427154502.GA22544@la.guarana.org>
On Fri, Apr 27, 2018 at 11:45:02AM -0400, Kevin Easton wrote:
> The struct vhost_msg within struct vhost_msg_node is copied to userspace,
> so it should be allocated with kzalloc() to ensure all structure padding
> is zeroed.
>
> Signed-off-by: Kevin Easton <kevin@guarana.org>
> Reported-by: syzbot+87cfa083e727a224754b@syzkaller.appspotmail.com
> ---
> drivers/vhost/vhost.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
> index f3bd8e9..1b84dcff 100644
> --- a/drivers/vhost/vhost.c
> +++ b/drivers/vhost/vhost.c
> @@ -2339,7 +2339,7 @@ EXPORT_SYMBOL_GPL(vhost_disable_notify);
> /* Create a new message. */
> struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type)
> {
> - struct vhost_msg_node *node = kmalloc(sizeof *node, GFP_KERNEL);
> + struct vhost_msg_node *node = kzalloc(sizeof *node, GFP_KERNEL);
> if (!node)
> return NULL;
> node->vq = vq;
Let's just init the msg though.
OK it seems this is the best we can do for now,
we need a new feature bit to fix it for 32 bit
userspace on 64 bit kernels.
Does the following help?
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index f3bd8e9..58d9aec 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -2342,6 +2342,9 @@ struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type)
struct vhost_msg_node *node = kmalloc(sizeof *node, GFP_KERNEL);
if (!node)
return NULL;
+
+ /* Make sure all padding within the structure is initialized. */
+ memset(&node->msg, 0, sizeof node->msg);
node->vq = vq;
node->msg.type = type;
return node;
^ permalink raw reply related
* Re: [PATCH bpf-next v3 00/15] Introducing AF_XDP support
From: Jesper Dangaard Brouer @ 2018-05-07 13:09 UTC (permalink / raw)
To: Magnus Karlsson
Cc: Alexei Starovoitov, Daniel Borkmann, Björn Töpel,
Karlsson, Magnus, Alexander Duyck, Alexander Duyck,
John Fastabend, Alexei Starovoitov, Willem de Bruijn,
Michael S. Tsirkin, Network Development, Björn Töpel,
michael.lundkvist, Brandeburg, Jesse, Singhai, Anjali,
Zhang, Qi Z, brouer
In-Reply-To: <CAJ8uoz2L+3dw5OOHJJ0CyV-y5w1ooNAjKHzHAcAiKhTjAq-vzQ@mail.gmail.com>
On Mon, 7 May 2018 11:13:58 +0200
Magnus Karlsson <magnus.karlsson@gmail.com> wrote:
> On Sat, May 5, 2018 at 2:34 AM, Alexei Starovoitov
> <alexei.starovoitov@gmail.com> wrote:
> > On Fri, May 04, 2018 at 01:22:17PM +0200, Magnus Karlsson wrote:
> >> On Fri, May 4, 2018 at 1:38 AM, Alexei Starovoitov
> >> <alexei.starovoitov@gmail.com> wrote:
> >> > On Fri, May 04, 2018 at 12:49:09AM +0200, Daniel Borkmann wrote:
> >> >> On 05/02/2018 01:01 PM, Björn Töpel wrote:
> >> >> > From: Björn Töpel <bjorn.topel@intel.com>
> >> >> >
> >> >> > This patch set introduces a new address family called AF_XDP that is
> >> >> > optimized for high performance packet processing and, in upcoming
> >> >> > patch sets, zero-copy semantics. In this patch set, we have removed
> >> >> > all zero-copy related code in order to make it smaller, simpler and
> >> >> > hopefully more review friendly. This patch set only supports copy-mode
> >> >> > for the generic XDP path (XDP_SKB) for both RX and TX and copy-mode
> >> >> > for RX using the XDP_DRV path. Zero-copy support requires XDP and
> >> >> > driver changes that Jesper Dangaard Brouer is working on. Some of his
> >> >> > work has already been accepted. We will publish our zero-copy support
> >> >> > for RX and TX on top of his patch sets at a later point in time.
> >> >>
> >> >> +1, would be great to see it land this cycle. Saw few minor nits here
> >> >> and there but nothing to hold it up, for the series:
> >> >>
> >> >> Acked-by: Daniel Borkmann <daniel@iogearbox.net>
> >> >>
> >> >> Thanks everyone!
> >> >
> >> > Great stuff!
> >> >
> >> > Applied to bpf-next, with one condition.
> >> > Upcoming zero-copy patches for both RX and TX need to be posted
> >> > and reviewed within this release window.
> >> > If netdev community as a whole won't be able to agree on the zero-copy
> >> > bits we'd need to revert this feature before the next merge window.
> >>
> >> Thanks everyone for reviewing this. Highly appreciated.
> >>
> >> Just so we understand the purpose correctly:
> >>
> >> 1: Do you want to see the ZC patches in order to verify that the user
> >> space API holds? If so, we can produce an additional RFC patch set
> >> using a big chunk of code that we had in RFC V1. We are not proud of
> >> this code since it is clunky, but it hopefully proves the point with
> >> the uapi being the same.
> >>
> >> 2: And/Or are you worried about us all (the netdev community) not
> >> agreeing on a way to implement ZC internally in the drivers and the
> >> XDP infrastructure? This is not going to be possible to finish during
> >> this cycle since we do not like the implementation we had in RFC V1.
> >> Too intrusive and now we also have nicer abstractions from Jesper that
> >> we can use and extend to provide a (hopefully) much cleaner and less
> >> intrusive solution.
> >
> > short answer: both.
> >
> > Cleanliness and performance of the ZC code is not as important as
> > getting API right. The main concern that during ZC review process
> > we will find out that existing API has issues, so we have to
> > do this exercise before the merge window.
> > And RFC won't fly. Send the patches for real. They have to go
> > through the proper code review. The hackers of netdev community
> > can accept a partial, or a bit unclean, or slightly inefficient
> > implementation, since it can be and will be improved later,
> > but API we cannot change once it goes into official release.
> >
> > Here is the example of API concern:
> > this patch set added shared umem concept. It sounds good in theory,
> > but will it perform well with ZC ? Earlier RFCs didn't have that
> > feature. If it won't perform well than it shouldn't be in the tree.
> > The key reason to let AF_XDP into the tree is its performance promise.
> > If it doesn't perform we should rip it out and redesign.
>
> That is a fair point. We will try to produce patch sets for zero-copy
> RX and TX using the latest interfaces within this merge window. Just
> note that we will focus on this for the next week(s) instead of the
> review items that you and Daniel Borkmann submitted. If we get those
> patch sets out in time and we agree that they are a possible way
> forward, then we produce patches with your fixes. It was mainly small
> items, so should be quick.
I would like to see that you create a new xdp_mem_type for this new
zero-copy type. This will allow other XDP redirect methods/types (e.g.
devmap and cpumap) to react appropriately when receiving a zero-copy
frame.
For devmap, I'm hoping we can allow/support using the ndo_xdp_xmit call
without (first) copying (into a newly allocated page). By arguing that
if an xsk-userspace app modify a frame it's not allowed to, then it is
simply a bug in the program. (Note, this would also allow using
ndo_xdp_xmit call for TX from xsk-userspace).
For cpumap, it is hard to avoid a copy, but I'm hoping we could delay
the copy (and alloc of mem dest area) until on the remote CPU. This is
already the principle of cpumap; of moving the allocation of the SKB to
the remote CPU.
For ZC to interact with XDP redirect-core and return API, the zero-copy
memory type/allocator, need to provide an area for the xdp_frame data
to be stored in (as we cannot allow using top-of-frame like
non-zero-copy variants), and extend xdp_frame with an ZC umem-id.
I imagine we can avoid any dynamic allocations, as we upfront (at bind
and XDP_UMEM_REG time) know the number of frames. (e.g. pre-alloc in
xdp_umem_reg() call, and have xdp_umem_get_xdp_frame lookup func).
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
LinkedIn: http://www.linkedin.com/in/brouer
^ permalink raw reply
* [PATCH net 0/2] Aquantia various patches 2018-05
From: Igor Russkikh @ 2018-05-07 13:10 UTC (permalink / raw)
To: David S . Miller; +Cc: netdev, David Arcari, Pavel Belous, Igor Russkikh
These are two patches covering issues found during test cycles:
First is that driver should declare valid vlan_features
Second fix is about correct allocation of MSI interrupts on some systems.
Igor Russkikh (2):
net: aquantia: driver should correctly declare vlan_features bits
net: aquantia: Limit number of vectors to actually allocated irqs
drivers/net/ethernet/aquantia/atlantic/aq_nic.c | 3 +++
drivers/net/ethernet/aquantia/atlantic/aq_nic.h | 1 +
drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c | 20 ++++++++++----------
3 files changed, 14 insertions(+), 10 deletions(-)
--
2.7.4
^ permalink raw reply
* [PATCH net 1/2] net: aquantia: driver should correctly declare vlan_features bits
From: Igor Russkikh @ 2018-05-07 13:10 UTC (permalink / raw)
To: David S . Miller; +Cc: netdev, David Arcari, Pavel Belous, Igor Russkikh
In-Reply-To: <cover.1525360773.git.igor.russkikh@aquantia.com>
In particular, not reporting SG forced skbs to be linear for vlan
interfaces over atlantic NIC.
With this fix it is possible to enable SG feature on device and
therefore optimize performance.
Reported-by: Ma Yuying <yuma@redhat.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
---
drivers/net/ethernet/aquantia/atlantic/aq_nic.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 32f6d2e..720760d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -246,6 +246,8 @@ void aq_nic_ndev_init(struct aq_nic_s *self)
self->ndev->hw_features |= aq_hw_caps->hw_features;
self->ndev->features = aq_hw_caps->hw_features;
+ self->ndev->vlan_features |= NETIF_F_HW_CSUM | NETIF_F_RXCSUM |
+ NETIF_F_RXHASH | NETIF_F_SG | NETIF_F_LRO;
self->ndev->priv_flags = aq_hw_caps->hw_priv_flags;
self->ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
--
2.7.4
^ permalink raw reply related
* [PATCH net 2/2] net: aquantia: Limit number of vectors to actually allocated irqs
From: Igor Russkikh @ 2018-05-07 13:10 UTC (permalink / raw)
To: David S . Miller; +Cc: netdev, David Arcari, Pavel Belous, Igor Russkikh
In-Reply-To: <cover.1525360773.git.igor.russkikh@aquantia.com>
Driver should use pci_alloc_irq_vectors return value to correct number
of allocated vectors and napi instances. Otherwise it'll panic later
in pci_irq_vector.
Driver also should allow more than one MSI vectors to be allocated.
Error return path from pci_alloc_irq_vectors is also fixed to revert
resources in a correct sequence when error happens.
Reported-by: Long, Nicholas <nicholas.a.long@baesystems.com>
Fixes: 23ee07a ("net: aquantia: Cleanup pci functions module")
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
---
drivers/net/ethernet/aquantia/atlantic/aq_nic.c | 1 +
drivers/net/ethernet/aquantia/atlantic/aq_nic.h | 1 +
drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c | 20 ++++++++++----------
3 files changed, 12 insertions(+), 10 deletions(-)
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 720760d..1a1a638 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -95,6 +95,7 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
/*rss rings */
cfg->vecs = min(cfg->aq_hw_caps->vecs, AQ_CFG_VECS_DEF);
cfg->vecs = min(cfg->vecs, num_online_cpus());
+ cfg->vecs = min(cfg->vecs, self->irqvecs);
/* cfg->vecs should be power of 2 for RSS */
if (cfg->vecs >= 8U)
cfg->vecs = 8U;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index 219b550..faa533a 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -80,6 +80,7 @@ struct aq_nic_s {
struct pci_dev *pdev;
unsigned int msix_entry_mask;
+ u32 irqvecs;
};
static inline struct device *aq_nic_get_dev(struct aq_nic_s *self)
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
index ecc6306..a50e08b 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
@@ -267,16 +267,16 @@ static int aq_pci_probe(struct pci_dev *pdev,
numvecs = min(numvecs, num_online_cpus());
/*enable interrupts */
#if !AQ_CFG_FORCE_LEGACY_INT
- err = pci_alloc_irq_vectors(self->pdev, numvecs, numvecs,
- PCI_IRQ_MSIX);
-
- if (err < 0) {
- err = pci_alloc_irq_vectors(self->pdev, 1, 1,
- PCI_IRQ_MSI | PCI_IRQ_LEGACY);
- if (err < 0)
- goto err_hwinit;
+ numvecs = pci_alloc_irq_vectors(self->pdev, 1, numvecs,
+ PCI_IRQ_MSIX | PCI_IRQ_MSI |
+ PCI_IRQ_LEGACY);
+
+ if (numvecs < 0) {
+ err = numvecs;
+ goto err_hwinit;
}
#endif
+ self->irqvecs = numvecs;
/* net device init */
aq_nic_cfg_start(self);
@@ -298,9 +298,9 @@ static int aq_pci_probe(struct pci_dev *pdev,
kfree(self->aq_hw);
err_ioremap:
free_netdev(ndev);
-err_pci_func:
- pci_release_regions(pdev);
err_ndev:
+ pci_release_regions(pdev);
+err_pci_func:
pci_disable_device(pdev);
return err;
}
--
2.7.4
^ permalink raw reply related
* Re: [PATCH net] vhost: Use kzalloc() to allocate vhost_msg_node
From: Dmitry Vyukov @ 2018-05-07 13:12 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: Kevin Easton, Jason Wang, KVM list, virtualization, netdev, LKML,
syzkaller-bugs
In-Reply-To: <20180507155534-mutt-send-email-mst@kernel.org>
On Mon, May 7, 2018 at 3:03 PM, Michael S. Tsirkin <mst@redhat.com> wrote:
> On Fri, Apr 27, 2018 at 11:45:02AM -0400, Kevin Easton wrote:
>> The struct vhost_msg within struct vhost_msg_node is copied to userspace,
>> so it should be allocated with kzalloc() to ensure all structure padding
>> is zeroed.
>>
>> Signed-off-by: Kevin Easton <kevin@guarana.org>
>> Reported-by: syzbot+87cfa083e727a224754b@syzkaller.appspotmail.com
>> ---
>> drivers/vhost/vhost.c | 2 +-
>> 1 file changed, 1 insertion(+), 1 deletion(-)
>>
>> diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
>> index f3bd8e9..1b84dcff 100644
>> --- a/drivers/vhost/vhost.c
>> +++ b/drivers/vhost/vhost.c
>> @@ -2339,7 +2339,7 @@ EXPORT_SYMBOL_GPL(vhost_disable_notify);
>> /* Create a new message. */
>> struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type)
>> {
>> - struct vhost_msg_node *node = kmalloc(sizeof *node, GFP_KERNEL);
>> + struct vhost_msg_node *node = kzalloc(sizeof *node, GFP_KERNEL);
>> if (!node)
>> return NULL;
>> node->vq = vq;
>
>
> Let's just init the msg though.
>
> OK it seems this is the best we can do for now,
> we need a new feature bit to fix it for 32 bit
> userspace on 64 bit kernels.
>
> Does the following help?
Hi Michael,
You can ask reporter (syzbot) to test:
https://github.com/google/syzkaller/blob/master/docs/syzbot.md#testing-patches
https://github.com/google/syzkaller/blob/master/docs/syzbot.md#kmsan-bugs
> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
>
> diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
> index f3bd8e9..58d9aec 100644
> --- a/drivers/vhost/vhost.c
> +++ b/drivers/vhost/vhost.c
> @@ -2342,6 +2342,9 @@ struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type)
> struct vhost_msg_node *node = kmalloc(sizeof *node, GFP_KERNEL);
> if (!node)
> return NULL;
> +
> + /* Make sure all padding within the structure is initialized. */
> + memset(&node->msg, 0, sizeof node->msg);
> node->vq = vq;
> node->msg.type = type;
> return node;
>
> --
> You received this message because you are subscribed to the Google Groups "syzkaller-bugs" group.
> To unsubscribe from this group and stop receiving emails from it, send an email to syzkaller-bugs+unsubscribe@googlegroups.com.
> To view this discussion on the web visit https://groups.google.com/d/msgid/syzkaller-bugs/20180507155534-mutt-send-email-mst%40kernel.org.
> For more options, visit https://groups.google.com/d/optout.
^ permalink raw reply
* [PATCH net-next] net-next/hinic: add pci device ids for 25ge and 100ge card
From: Zhao Chen @ 2018-05-07 13:21 UTC (permalink / raw)
To: davem
Cc: linux-kernel, netdev, aviad.krawczyk, zhaochen6, tony.qu,
yin.yinshi, luoshaokai
This patch adds PCI device IDs to support 25GE and 100GE card:
1. Add device id 0x0201 for HINIC 100GE dual port card.
2. Add device id 0x0200 for HINIC 25GE dual port card.
3. Macro of device id 0x1822 is modified for HINIC 25GE quad port card.
Signed-off-by: Zhao Chen <zhaochen6@huawei.com>
---
drivers/net/ethernet/huawei/hinic/hinic_main.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index eb53bd93065e..5b122728dcb4 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -51,7 +51,9 @@ static unsigned int rx_weight = 64;
module_param(rx_weight, uint, 0644);
MODULE_PARM_DESC(rx_weight, "Number Rx packets for NAPI budget (default=64)");
-#define PCI_DEVICE_ID_HI1822_PF 0x1822
+#define HINIC_DEV_ID_QUAD_PORT_25GE 0x1822
+#define HINIC_DEV_ID_DUAL_PORT_25GE 0x0200
+#define HINIC_DEV_ID_DUAL_PORT_100GE 0x0201
#define HINIC_WQ_NAME "hinic_dev"
@@ -1097,7 +1099,9 @@ static void hinic_remove(struct pci_dev *pdev)
}
static const struct pci_device_id hinic_pci_table[] = {
- { PCI_VDEVICE(HUAWEI, PCI_DEVICE_ID_HI1822_PF), 0},
+ { PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_QUAD_PORT_25GE), 0},
+ { PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_DUAL_PORT_25GE), 0},
+ { PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_DUAL_PORT_100GE), 0},
{ 0, 0}
};
MODULE_DEVICE_TABLE(pci, hinic_pci_table);
--
2.17.0
^ permalink raw reply related
* Re: [bpf-next v2 8/9] bpf: Provide helper to do forwarding lookups in kernel FIB table
From: Jesper Dangaard Brouer @ 2018-05-07 13:35 UTC (permalink / raw)
To: David Ahern
Cc: netdev, borkmann, ast, davem, shm, roopa, toke, john.fastabend,
brouer
In-Reply-To: <20180504025432.23451-9-dsahern@gmail.com>
On Thu, 3 May 2018 19:54:31 -0700 David Ahern <dsahern@gmail.com> wrote:
> diff --git a/net/core/filter.c b/net/core/filter.c
> index 6877426c23a6..cf0d27acf1d1 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
[...]
> +static const struct bpf_func_proto bpf_xdp_fib_lookup_proto = {
> + .func = bpf_xdp_fib_lookup,
> + .gpl_only = true,
Is it a deliberate choice to require BPF-progs using this helper to be
GPL licensed?
Asking as this seems to be the first network related helper with this
requirement, while this is typical for tracing related helpers.
> + .ret_type = RET_INTEGER,
> + .arg1_type = ARG_PTR_TO_CTX,
> + .arg2_type = ARG_PTR_TO_MEM,
> + .arg3_type = ARG_CONST_SIZE,
> + .arg4_type = ARG_ANYTHING,
> +};
--
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-next] flow_dissector: do not rely on implicit casts
From: Jon Maloy @ 2018-05-07 13:54 UTC (permalink / raw)
To: Paolo Abeni, netdev@vger.kernel.org; +Cc: David S. Miller
In-Reply-To: <163b504b851217e600d9b48aa7cba76b376a675a.1525687522.git.pabeni@redhat.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
> -----Original Message-----
> From: netdev-owner@vger.kernel.org [mailto:netdev-
> owner@vger.kernel.org] On Behalf Of Paolo Abeni
> Sent: Monday, May 07, 2018 06:06
> To: netdev@vger.kernel.org
> Cc: David S. Miller <davem@davemloft.net>
> Subject: [PATCH net-next] flow_dissector: do not rely on implicit casts
>
> This change fixes a couple of type mismatch reported by the sparse tool,
> explicitly using the requested type for the offending arguments.
>
> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
> ---
> include/net/tipc.h | 4 ++--
> net/core/flow_dissector.c | 2 +-
> 2 files changed, 3 insertions(+), 3 deletions(-)
>
> diff --git a/include/net/tipc.h b/include/net/tipc.h index
> 07670ec022a7..f0e7e6bc1bef 100644
> --- a/include/net/tipc.h
> +++ b/include/net/tipc.h
> @@ -44,11 +44,11 @@ struct tipc_basic_hdr {
> __be32 w[4];
> };
>
> -static inline u32 tipc_hdr_rps_key(struct tipc_basic_hdr *hdr)
> +static inline __be32 tipc_hdr_rps_key(struct tipc_basic_hdr *hdr)
> {
> u32 w0 = ntohl(hdr->w[0]);
> bool keepalive_msg = (w0 & KEEPALIVE_MSG_MASK) ==
> KEEPALIVE_MSG_MASK;
> - int key;
> + __be32 key;
>
> /* Return source node identity as key */
> if (likely(!keepalive_msg))
> diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index
> 030d4ca177fb..4fc1e84d77ec 100644
> --- a/net/core/flow_dissector.c
> +++ b/net/core/flow_dissector.c
> @@ -1316,7 +1316,7 @@ u32 skb_get_poff(const struct sk_buff *skb) {
> struct flow_keys_basic keys;
>
> - if (!skb_flow_dissect_flow_keys_basic(skb, &keys, 0, 0, 0, 0, 0))
> + if (!skb_flow_dissect_flow_keys_basic(skb, &keys, NULL, 0, 0, 0, 0))
> return 0;
>
> return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb));
> --
> 2.14.3
^ permalink raw reply
* [PATCH] net: 8390: Fix possible data races in __ei_get_stats
From: Jia-Ju Bai @ 2018-05-07 14:08 UTC (permalink / raw)
To: davem, fthain, joe; +Cc: netdev, linux-kernel, Jia-Ju Bai
The write operations to "dev->stats" are protected by
the spinlock on line 862-864, but the read operations to
this data on line 858 and 867 are not protected by the spinlock.
Thus, there may exist data races for "dev->stats".
To fix the data races, the read operations to "dev->stats" are
protected by the spinlock, and a local variable is used for return.
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
---
drivers/net/ethernet/8390/lib8390.c | 14 ++++++++++----
1 file changed, 10 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/8390/lib8390.c b/drivers/net/ethernet/8390/lib8390.c
index c9c55c9eab9f..198952247d30 100644
--- a/drivers/net/ethernet/8390/lib8390.c
+++ b/drivers/net/ethernet/8390/lib8390.c
@@ -852,19 +852,25 @@ static struct net_device_stats *__ei_get_stats(struct net_device *dev)
unsigned long ioaddr = dev->base_addr;
struct ei_device *ei_local = netdev_priv(dev);
unsigned long flags;
+ struct net_device_stats *stats;
+
+ spin_lock_irqsave(&ei_local->page_lock, flags);
/* If the card is stopped, just return the present stats. */
- if (!netif_running(dev))
- return &dev->stats;
+ if (!netif_running(dev)) {
+ stats = &dev->stats;
+ spin_unlock_irqrestore(&ei_local->page_lock, flags);
+ return stats;
+ }
- spin_lock_irqsave(&ei_local->page_lock, flags);
/* Read the counter registers, assuming we are in page 0. */
dev->stats.rx_frame_errors += ei_inb_p(ioaddr + EN0_COUNTER0);
dev->stats.rx_crc_errors += ei_inb_p(ioaddr + EN0_COUNTER1);
dev->stats.rx_missed_errors += ei_inb_p(ioaddr + EN0_COUNTER2);
+ stats = &dev->stats;
spin_unlock_irqrestore(&ei_local->page_lock, flags);
- return &dev->stats;
+ return stats;
}
/*
--
2.17.0
^ permalink raw reply related
* Re: [bpf-next v2 8/9] bpf: Provide helper to do forwarding lookups in kernel FIB table
From: Daniel Borkmann @ 2018-05-07 14:10 UTC (permalink / raw)
To: Jesper Dangaard Brouer, David Ahern
Cc: netdev, borkmann, ast, davem, shm, roopa, toke, john.fastabend
In-Reply-To: <20180507153552.5063a4b2@redhat.com>
On 05/07/2018 03:35 PM, Jesper Dangaard Brouer wrote:
> On Thu, 3 May 2018 19:54:31 -0700 David Ahern <dsahern@gmail.com> wrote:
>
>> diff --git a/net/core/filter.c b/net/core/filter.c
>> index 6877426c23a6..cf0d27acf1d1 100644
>> --- a/net/core/filter.c
>> +++ b/net/core/filter.c
> [...]
>> +static const struct bpf_func_proto bpf_xdp_fib_lookup_proto = {
>> + .func = bpf_xdp_fib_lookup,
>> + .gpl_only = true,
>
> Is it a deliberate choice to require BPF-progs using this helper to be
> GPL licensed?
>
> Asking as this seems to be the first network related helper with this
> requirement, while this is typical for tracing related helpers.
Good point, we should remove that. In networking it's only the perf event
output helpers tying into tracing bits. After all, if you do a route lookup
via netlink from user space there's no such restriction at all.
^ permalink raw reply
* Re: [PATCH] net: 8390: Fix possible data races in __ei_get_stats
From: Eric Dumazet @ 2018-05-07 14:15 UTC (permalink / raw)
To: Jia-Ju Bai, davem, fthain, joe; +Cc: netdev, linux-kernel
In-Reply-To: <20180507140809.28847-1-baijiaju1990@gmail.com>
On 05/07/2018 07:08 AM, Jia-Ju Bai wrote:
> The write operations to "dev->stats" are protected by
> the spinlock on line 862-864, but the read operations to
> this data on line 858 and 867 are not protected by the spinlock.
> Thus, there may exist data races for "dev->stats".
>
> To fix the data races, the read operations to "dev->stats" are
> protected by the spinlock, and a local variable is used for return.
>
> Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
> ---
> drivers/net/ethernet/8390/lib8390.c | 14 ++++++++++----
> 1 file changed, 10 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/net/ethernet/8390/lib8390.c b/drivers/net/ethernet/8390/lib8390.c
> index c9c55c9eab9f..198952247d30 100644
> --- a/drivers/net/ethernet/8390/lib8390.c
> +++ b/drivers/net/ethernet/8390/lib8390.c
> @@ -852,19 +852,25 @@ static struct net_device_stats *__ei_get_stats(struct net_device *dev)
> unsigned long ioaddr = dev->base_addr;
> struct ei_device *ei_local = netdev_priv(dev);
> unsigned long flags;
> + struct net_device_stats *stats;
> +
> + spin_lock_irqsave(&ei_local->page_lock, flags);
>
> /* If the card is stopped, just return the present stats. */
> - if (!netif_running(dev))
> - return &dev->stats;
> + if (!netif_running(dev)) {
> + stats = &dev->stats;
> + spin_unlock_irqrestore(&ei_local->page_lock, flags);
> + return stats;
> + }
>
> - spin_lock_irqsave(&ei_local->page_lock, flags);
> /* Read the counter registers, assuming we are in page 0. */
> dev->stats.rx_frame_errors += ei_inb_p(ioaddr + EN0_COUNTER0);
> dev->stats.rx_crc_errors += ei_inb_p(ioaddr + EN0_COUNTER1);
> dev->stats.rx_missed_errors += ei_inb_p(ioaddr + EN0_COUNTER2);
> + stats = &dev->stats;
> spin_unlock_irqrestore(&ei_local->page_lock, flags);
>
> - return &dev->stats;
> + return stats;
> }
>
> /*
>
dev->stats is not a pointer, it is an array embedded in the
struct net_device
So this patch is not needed, since dev->stats can not change.
^ permalink raw reply
* Re: [bpf-next v2 8/9] bpf: Provide helper to do forwarding lookups in kernel FIB table
From: David Ahern @ 2018-05-07 14:26 UTC (permalink / raw)
To: Daniel Borkmann, Jesper Dangaard Brouer
Cc: netdev, borkmann, ast, davem, shm, roopa, toke, john.fastabend
In-Reply-To: <247aa1c4-e860-db72-fbb4-9da6c3a3f84c@iogearbox.net>
On 5/7/18 8:10 AM, Daniel Borkmann wrote:
> On 05/07/2018 03:35 PM, Jesper Dangaard Brouer wrote:
>> On Thu, 3 May 2018 19:54:31 -0700 David Ahern <dsahern@gmail.com> wrote:
>>
>>> diff --git a/net/core/filter.c b/net/core/filter.c
>>> index 6877426c23a6..cf0d27acf1d1 100644
>>> --- a/net/core/filter.c
>>> +++ b/net/core/filter.c
>> [...]
>>> +static const struct bpf_func_proto bpf_xdp_fib_lookup_proto = {
>>> + .func = bpf_xdp_fib_lookup,
>>> + .gpl_only = true,
>>
>> Is it a deliberate choice to require BPF-progs using this helper to be
>> GPL licensed?
>>
>> Asking as this seems to be the first network related helper with this
>> requirement, while this is typical for tracing related helpers.
>
> Good point, we should remove that. In networking it's only the perf event
> output helpers tying into tracing bits. After all, if you do a route lookup
> via netlink from user space there's no such restriction at all.
>
Networking symbols are typically exported GPL for modules. The person
writing the code and exporting GPL is specifying a desire that only GPL
licensed modules can link to the symbol.
Given the common analogy of modules and bpf programs, why can't a writer
of a bpf helper specify a preference that only GPL licensed programs
leverage a BPF helper?
^ permalink raw reply
* Re: [PATCH net-next v2 1/3] ipv4: support sport and dport in RTM_GETROUTE
From: Roopa Prabhu @ 2018-05-07 14:42 UTC (permalink / raw)
To: David Ahern; +Cc: David Miller, netdev, Nikolay Aleksandrov, Ido Schimmel
In-Reply-To: <a6027834-d056-5ff9-82e7-52d4ba2e90fb@cumulusnetworks.com>
On Sun, May 6, 2018 at 6:46 PM, David Ahern <dsa@cumulusnetworks.com> wrote:
> On 5/6/18 6:59 PM, Roopa Prabhu wrote:
>> From: Roopa Prabhu <roopa@cumulusnetworks.com>
>>
>> This is a followup to fib rules sport, dport match support.
>> Having them supported in getroute makes it easier to test
>> fib rule lookups. Used by fib rule self tests. Before this patch
>> getroute used same skb to pass through the route lookup and
>> for the netlink getroute reply msg. This patch allocates separate
>> skb's to keep flow dissector happy.
>>
>> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
>> ---
>> include/uapi/linux/rtnetlink.h | 2 +
>> net/ipv4/route.c | 151 ++++++++++++++++++++++++++++++-----------
>> 2 files changed, 115 insertions(+), 38 deletions(-)
>>
>> diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
>> index 9b15005..630ecf4 100644
>> --- a/include/uapi/linux/rtnetlink.h
>> +++ b/include/uapi/linux/rtnetlink.h
>> @@ -327,6 +327,8 @@ enum rtattr_type_t {
>> RTA_PAD,
>> RTA_UID,
>> RTA_TTL_PROPAGATE,
>> + RTA_SPORT,
>> + RTA_DPORT,
>
> If you are going to add sport and dport because of the potential for FIB
> rules, you need to add ip-proto as well. I realize existing code assumed
> UDP, but the FIB rules cover any IP proto. Yes, I know this makes the
> change much larger to generate tcp, udp as well as iphdr options; the
> joys of new features. ;-)
:) sure..like i mentioned in the cover letter..., i was thinking of
submitting follow up patches for more ip_proto.
since i will be spinning v3, let me see if i can include that too.
>
> I also suggest a comment that these new RTA attributes are used for
> GETROUTE only.
sure
>
> And you need to add the new entries to rtm_ipv4_policy.
>
>
>> __RTA_MAX
>> };
ack,
>>
>> diff --git a/net/ipv4/route.c b/net/ipv4/route.c
>> index 1412a7b..e91ed62 100644
>> --- a/net/ipv4/route.c
>> +++ b/net/ipv4/route.c
>> @@ -2568,11 +2568,10 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
>> EXPORT_SYMBOL_GPL(ip_route_output_flow);
>>
>> /* called with rcu_read_lock held */
>> -static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id,
>> - struct flowi4 *fl4, struct sk_buff *skb, u32 portid,
>> - u32 seq)
>> +static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
>> + struct rtable *rt, u32 table_id, struct flowi4 *fl4,
>> + struct sk_buff *skb, u32 portid, u32 seq)
>> {
>> - struct rtable *rt = skb_rtable(skb);
>> struct rtmsg *r;
>> struct nlmsghdr *nlh;
>> unsigned long expires = 0;
>> @@ -2651,6 +2650,14 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id,
>> from_kuid_munged(current_user_ns(), fl4->flowi4_uid)))
>> goto nla_put_failure;
>>
>> + if (fl4->fl4_sport &&
>> + nla_put_be16(skb, RTA_SPORT, fl4->fl4_sport))
>> + goto nla_put_failure;
>> +
>> + if (fl4->fl4_dport &&
>> + nla_put_be16(skb, RTA_DPORT, fl4->fl4_dport))
>> + goto nla_put_failure;
>
> Why return the attributes to the user? I can't see any value in that.
> UID option is not returned either so there is precedence.
hmm..i do see UID returned just 2 lines above. :)
In the least i think it will confirm that the kernel did see your attributes :).
>
>
>> +
>> error = rt->dst.error;
>>
>> if (rt_is_input_route(rt)) {
>> @@ -2668,7 +2675,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id,
>> }
>> } else
>> #endif
>> - if (nla_put_u32(skb, RTA_IIF, skb->dev->ifindex))
>> + if (nla_put_u32(skb, RTA_IIF, fl4->flowi4_iif))
>> goto nla_put_failure;
>> }
>>
>> @@ -2683,35 +2690,86 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id,
>> return -EMSGSIZE;
>> }
>>
>> +static int nla_get_port(struct nlattr *attr, __be16 *port)
>> +{
>> + int p = nla_get_be16(attr);
>
> __be16 p;
>
>> +
>> + if (p <= 0 || p >= 0xffff)
>> + return -EINVAL;
>
> This check is not needed by definition of be16.
ack, will fix the kbuild sparse warning also for both v4 and v6.
>
>> +
>> + *port = p;
>> + return 0;
>> +}
>> +
>> +static int inet_rtm_getroute_reply(struct sk_buff *in_skb, struct nlmsghdr *nlh,
>> + __be32 dst, __be32 src, struct flowi4 *fl4,
>> + struct rtable *rt, struct fib_result *res)
>> +{
>> + struct net *net = sock_net(in_skb->sk);
>> + struct rtmsg *rtm = nlmsg_data(nlh);
>> + u32 table_id = RT_TABLE_MAIN;
>> + struct sk_buff *skb;
>> + int err = 0;
>> +
>> + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
>> + if (!skb) {
>> + err = -ENOMEM;
>> + return err;
>> + }
>
> just 'return -ENOMEM' and without the {}.
yep
>
>
>> +
>> + if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE)
>> + table_id = res->table ? res->table->tb_id : 0;
>> +
>> + if (rtm->rtm_flags & RTM_F_FIB_MATCH)
>> + err = fib_dump_info(skb, NETLINK_CB(in_skb).portid,
>> + nlh->nlmsg_seq, RTM_NEWROUTE, table_id,
>> + rt->rt_type, res->prefix, res->prefixlen,
>> + fl4->flowi4_tos, res->fi, 0);
>> + else
>> + err = rt_fill_info(net, dst, src, rt, table_id,
>> + fl4, skb, NETLINK_CB(in_skb).portid,
>> + nlh->nlmsg_seq);
>> + if (err < 0)
>> + goto errout;
>> +
>> + return rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
>> +
>> +errout:
>> + kfree_skb(skb);
>> + return err;
>> +}
>> +
>> static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
>> struct netlink_ext_ack *extack)
>> {
>> struct net *net = sock_net(in_skb->sk);
>> - struct rtmsg *rtm;
>> struct nlattr *tb[RTA_MAX+1];
>> + __be16 sport = 0, dport = 0;
>> struct fib_result res = {};
>> struct rtable *rt = NULL;
>> + struct sk_buff *skb;
>> + struct rtmsg *rtm;
>> struct flowi4 fl4;
>> + struct iphdr *iph;
>> + struct udphdr *udph;
>> __be32 dst = 0;
>> __be32 src = 0;
>> + kuid_t uid;
>> u32 iif;
>> int err;
>> int mark;
>> - struct sk_buff *skb;
>> - u32 table_id = RT_TABLE_MAIN;
>> - kuid_t uid;
>>
>> err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy,
>> extack);
>> if (err < 0)
>> - goto errout;
>> + return err;
>>
>> rtm = nlmsg_data(nlh);
>>
>> skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
>> if (!skb) {
>> err = -ENOBUFS;
>> - goto errout;
>> + return err;
>
> just return -ENOBUFS
>
yes
>
>> }
>>
>> /* Reserve room for dummy headers, this skb can pass
>
^ permalink raw reply
* [net-next 0/6][pull request] 100GbE Intel Wired LAN Driver Updates 2018-05-07
From: Jeff Kirsher @ 2018-05-07 14:45 UTC (permalink / raw)
To: davem; +Cc: Jeff Kirsher, netdev, nhorman, sassmann, jogreene
This series contains updates to fm10k only.
Jake provides all the changes in the series, starting with adding
support for accelerated MACVLAN devices. Reduced code duplication by
implementing a macro to be used when setting up the type specific
macros. Avoided potential bugs with stats by using a macro to calculate
the array size when passing to ensure that the size is correct.
The following are changes since commit 90278871d4b0da39c84fc9aa4929b0809dc7cf3c:
Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-next
and are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue 100GbE
Jacob Keller (6):
fm10k: setup VLANs for l2 accelerated macvlan interfaces
fm10k: reduce duplicate fm10k_stat macro code
fm10k: use variadic arguments to fm10k_add_stat_strings
fm10k: use macro to avoid passing the array and size separately
fm10k: warn if the stat size is unknown
fm10k: don't protect fm10k_queue_mac_request by fm10k_host_mbx_ready
drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c | 115 +++++++++++------------
drivers/net/ethernet/intel/fm10k/fm10k_netdev.c | 62 ++++++++++--
2 files changed, 110 insertions(+), 67 deletions(-)
--
2.14.3
^ 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