* [iproute2 net-next 8/8] Introduce ip vrf command
From: David Ahern @ 2016-12-10 20:32 UTC (permalink / raw)
To: netdev, stephen; +Cc: David Ahern
In-Reply-To: <1481401934-4026-1-git-send-email-dsa@cumulusnetworks.com>
'ip vrf' follows the user semnatics established by 'ip netns'.
The 'ip vrf' subcommand supports 3 usages:
1. Run a command against a given vrf:
ip vrf exec NAME CMD
Uses the recently committed cgroup/sock BPF option. vrf directory
is added to cgroup2 mount. Individual vrfs are created under it. BPF
filter attached to vrf/NAME cgroup2 to set sk_bound_dev_if to the VRF
device index. From there the current process (ip's pid) is addded to
the cgroups.proc file and the given command is exected. In doing so
all AF_INET/AF_INET6 (ipv4/ipv6) sockets are automatically bound to
the VRF domain.
The association is inherited parent to child allowing the command to
be a shell from which other commands are run relative to the VRF.
2. Show the VRF a process is bound to:
ip vrf id
This command essentially looks at /proc/pid/cgroup for a "::/vrf/"
entry with the VRF name following.
3. Show process ids bound to a VRF
ip vrf pids NAME
This command dumps the file MNT/vrf/NAME/cgroup.procs since that file
shows the process ids in the particular vrf cgroup.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
ip/Makefile | 3 +-
ip/ip.c | 4 +-
ip/ip_common.h | 2 +
ip/ipvrf.c | 289 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
man/man8/ip-vrf.8 | 88 +++++++++++++++++
5 files changed, 384 insertions(+), 2 deletions(-)
create mode 100644 ip/ipvrf.c
create mode 100644 man/man8/ip-vrf.8
diff --git a/ip/Makefile b/ip/Makefile
index c8e6c6172741..1928489e7f90 100644
--- a/ip/Makefile
+++ b/ip/Makefile
@@ -7,7 +7,8 @@ IPOBJ=ip.o ipaddress.o ipaddrlabel.o iproute.o iprule.o ipnetns.o \
iplink_vxlan.o tcp_metrics.o iplink_ipoib.o ipnetconf.o link_ip6tnl.o \
link_iptnl.o link_gre6.o iplink_bond.o iplink_bond_slave.o iplink_hsr.o \
iplink_bridge.o iplink_bridge_slave.o ipfou.o iplink_ipvlan.o \
- iplink_geneve.o iplink_vrf.o iproute_lwtunnel.o ipmacsec.o ipila.o
+ iplink_geneve.o iplink_vrf.o iproute_lwtunnel.o ipmacsec.o ipila.o \
+ ipvrf.o
RTMONOBJ=rtmon.o
diff --git a/ip/ip.c b/ip/ip.c
index cb3adcb3f57d..07050b07592a 100644
--- a/ip/ip.c
+++ b/ip/ip.c
@@ -51,7 +51,8 @@ static void usage(void)
" ip [ -force ] -batch filename\n"
"where OBJECT := { link | address | addrlabel | route | rule | neigh | ntable |\n"
" tunnel | tuntap | maddress | mroute | mrule | monitor | xfrm |\n"
-" netns | l2tp | fou | macsec | tcp_metrics | token | netconf | ila }\n"
+" netns | l2tp | fou | macsec | tcp_metrics | token | netconf | ila |\n"
+" vrf }\n"
" OPTIONS := { -V[ersion] | -s[tatistics] | -d[etails] | -r[esolve] |\n"
" -h[uman-readable] | -iec |\n"
" -f[amily] { inet | inet6 | ipx | dnet | mpls | bridge | link } |\n"
@@ -99,6 +100,7 @@ static const struct cmd {
{ "mrule", do_multirule },
{ "netns", do_netns },
{ "netconf", do_ipnetconf },
+ { "vrf", do_ipvrf},
{ "help", do_help },
{ 0 }
};
diff --git a/ip/ip_common.h b/ip/ip_common.h
index 3162f1ca5b2c..28763e81e4a4 100644
--- a/ip/ip_common.h
+++ b/ip/ip_common.h
@@ -57,6 +57,8 @@ extern int do_ipila(int argc, char **argv);
int do_tcp_metrics(int argc, char **argv);
int do_ipnetconf(int argc, char **argv);
int do_iptoken(int argc, char **argv);
+int do_ipvrf(int argc, char **argv);
+
int iplink_get(unsigned int flags, char *name, __u32 filt_mask);
static inline int rtm_get_table(struct rtmsg *r, struct rtattr **tb)
diff --git a/ip/ipvrf.c b/ip/ipvrf.c
new file mode 100644
index 000000000000..c4f0e53532e2
--- /dev/null
+++ b/ip/ipvrf.c
@@ -0,0 +1,289 @@
+/*
+ * ipvrf.c "ip vrf"
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: David Ahern <dsa@cumulusnetworks.com>
+ *
+ */
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/socket.h>
+#include <sys/mount.h>
+#include <linux/bpf.h>
+#include <linux/if.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <errno.h>
+#include <limits.h>
+
+#include "rt_names.h"
+#include "utils.h"
+#include "ip_common.h"
+#include "libbpf.h"
+#include "bpf_util.h"
+
+#define CGRP_PROC_FILE "/cgroup.procs"
+
+static void usage(void)
+{
+ fprintf(stderr, "Usage: ip vrf exec [NAME] cmd ...\n");
+ fprintf(stderr, " ip vrf identify [PID]\n");
+ fprintf(stderr, " ip vrf pids [NAME]\n");
+
+ exit(-1);
+}
+
+static int ipvrf_identify(int argc, char **argv)
+{
+ char path[PATH_MAX];
+ char buf[4096];
+ char *vrf, *end;
+ int fd, rc = -1;
+ unsigned int pid;
+ ssize_t n;
+
+ if (argc < 1)
+ pid = getpid();
+ else if (argc > 1)
+ invarg("Extra arguments specified\n", argv[1]);
+ else if (get_unsigned(&pid, argv[0], 10))
+ invarg("Invalid pid\n", argv[0]);
+
+ snprintf(path, sizeof(path), "/proc/%d/cgroup", pid);
+ fd = open(path, O_RDONLY);
+ if (fd < 0) {
+ fprintf(stderr,
+ "Failed to open cgroups file: %s\n", strerror(errno));
+ return -1;
+ }
+
+ n = read(fd, buf, sizeof(buf) - 1);
+ if (n < 0) {
+ fprintf(stderr,
+ "Failed to read cgroups file: %s\n", strerror(errno));
+ goto out;
+ }
+ buf[n] = '\0';
+ vrf = strstr(buf, "::/vrf/");
+ if (vrf) {
+ vrf += 7; /* skip past "::/vrf/" */
+ end = strchr(vrf, '\n');
+ if (end)
+ *end = '\0';
+
+ printf("%s\n", vrf);
+ }
+
+ rc = 0;
+out:
+ close(fd);
+
+ return rc;
+}
+
+static int ipvrf_pids(int argc, char **argv)
+{
+ char path[PATH_MAX];
+ char buf[4096];
+ char *mnt, *vrf;
+ int fd, rc = -1;
+ ssize_t n;
+
+ if (argc != 1) {
+ fprintf(stderr, "Invalid arguments\n");
+ return -1;
+ }
+
+ vrf = argv[0];
+
+ mnt = find_cgroup2_mount();
+ if (!mnt)
+ return -1;
+
+ snprintf(path, sizeof(path), "%s/vrf/%s%s", mnt, vrf, CGRP_PROC_FILE);
+ free(mnt);
+ fd = open(path, O_RDONLY);
+ if (fd < 0)
+ return 0; /* no cgroup file, nothing to show */
+
+ while (1) {
+ n = read(fd, buf, sizeof(buf) - 1);
+ if (n < 0) {
+ fprintf(stderr,
+ "Failed to read cgroups file: %s\n", strerror(errno));
+ break;
+ } else if (n == 0) {
+ rc = 0;
+ break;
+ }
+ printf("%s", buf);
+ }
+
+ close(fd);
+
+ return rc;
+}
+
+/* load BPF program to set sk_bound_dev_if for sockets */
+static char bpf_log_buf[256*1024];
+
+static int prog_load(int idx)
+{
+ struct bpf_insn prog[] = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_MOV64_IMM(BPF_REG_3, idx),
+ BPF_MOV64_IMM(BPF_REG_2, offsetof(struct bpf_sock, bound_dev_if)),
+ BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3, offsetof(struct bpf_sock, bound_dev_if)),
+ BPF_MOV64_IMM(BPF_REG_0, 1), /* r0 = verdict */
+ BPF_EXIT_INSN(),
+ };
+
+ return bpf_prog_load(BPF_PROG_TYPE_CGROUP_SOCK, prog, sizeof(prog),
+ "GPL", bpf_log_buf, sizeof(bpf_log_buf));
+}
+
+static int vrf_configure_cgroup(const char *path, int ifindex)
+{
+ int rc = -1, cg_fd, prog_fd = -1;
+
+ cg_fd = open(path, O_DIRECTORY | O_RDONLY);
+ if (cg_fd < 0) {
+ fprintf(stderr, "Failed to open cgroup path: '%s'\n", strerror(errno));
+ goto out;
+ }
+
+ /*
+ * Load bpf program into kernel and attach to cgroup to affect
+ * socket creates
+ */
+ prog_fd = prog_load(ifindex);
+ if (prog_fd < 0) {
+ printf("Failed to load BPF prog: '%s'\n", strerror(errno));
+ goto out;
+ }
+
+ if (bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_INET_SOCK_CREATE)) {
+ fprintf(stderr, "Failed to attach prog to cgroup: '%s'\n",
+ strerror(errno));
+ fprintf(stderr, "Kernel compiled with CGROUP_BPF enabled?\n");
+ goto out;
+ }
+
+ rc = 0;
+out:
+ close(cg_fd);
+ close(prog_fd);
+
+ return rc;
+}
+
+static int vrf_switch(const char *name)
+{
+ char path[PATH_MAX], *mnt, pid[16];
+ int ifindex = name_is_vrf(name);
+ bool default_vrf = false;
+ int rc = -1, len, fd = -1;
+
+ if (!ifindex) {
+ if (strcmp(name, "default")) {
+ fprintf(stderr, "Invalid VRF name\n");
+ return -1;
+ }
+ default_vrf = true;
+ }
+
+ mnt = find_cgroup2_mount();
+ if (!mnt)
+ return -1;
+
+ /* path to cgroup; make sure buffer has room to cat "/cgroup.procs"
+ * to the end of the path
+ */
+ len = snprintf(path, sizeof(path) - sizeof(CGRP_PROC_FILE), "%s%s/%s",
+ mnt, default_vrf ? "" : "/vrf", name);
+ if (len > sizeof(path) - sizeof(CGRP_PROC_FILE)) {
+ fprintf(stderr, "Invalid path to cgroup2 mount\n");
+ goto out;
+ }
+
+ if (make_path(path, 0755)) {
+ fprintf(stderr, "Failed to setup vrf cgroup2 directory\n");
+ goto out;
+ }
+
+ if (!default_vrf && vrf_configure_cgroup(path, ifindex))
+ goto out;
+
+ /*
+ * write pid to cgroup.procs making process part of cgroup
+ */
+ strcat(path, CGRP_PROC_FILE);
+ fd = open(path, O_RDWR | O_APPEND);
+ if (fd < 0) {
+ fprintf(stderr, "cgroups.procs file does not exist.\n");
+ goto out;
+ }
+
+ snprintf(pid, sizeof(pid), "%d", getpid());
+ if (write(fd, pid, strlen(pid)) < 0) {
+ fprintf(stderr, "Failed to join cgroup\n");
+ goto out;
+ }
+
+ rc = 0;
+out:
+ free(mnt);
+ close(fd);
+
+ return rc;
+}
+
+static int ipvrf_exec(int argc, char **argv)
+{
+ if (argc < 1) {
+ fprintf(stderr, "No VRF name specified\n");
+ return -1;
+ }
+ if (argc < 2) {
+ fprintf(stderr, "No command specified\n");
+ return -1;
+ }
+
+ if (vrf_switch(argv[0]))
+ return -1;
+
+ return -cmd_exec(argv[1], argv + 1, !!batch_mode);
+}
+
+int do_ipvrf(int argc, char **argv)
+{
+ if (argc == 0) {
+ fprintf(stderr, "No command given. Try \"ip vrf help\".\n");
+ exit(-1);
+ }
+
+ if (matches(*argv, "identify") == 0)
+ return ipvrf_identify(argc-1, argv+1);
+
+ if (matches(*argv, "pids") == 0)
+ return ipvrf_pids(argc-1, argv+1);
+
+ if (matches(*argv, "exec") == 0)
+ return ipvrf_exec(argc-1, argv+1);
+
+ if (matches(*argv, "help") == 0)
+ usage();
+
+ fprintf(stderr, "Command \"%s\" is unknown, try \"ip vrf help\".\n",
+ *argv);
+
+ exit(-1);
+}
diff --git a/man/man8/ip-vrf.8 b/man/man8/ip-vrf.8
new file mode 100644
index 000000000000..57a7c7692ce8
--- /dev/null
+++ b/man/man8/ip-vrf.8
@@ -0,0 +1,88 @@
+.TH IP\-VRF 8 "7 Dec 2016" "iproute2" "Linux"
+.SH NAME
+ip-vrf \- run a command against a vrf
+.SH SYNOPSIS
+.sp
+.ad l
+.in +8
+.ti -8
+.B ip
+.B vrf
+.RI " { " COMMAND " | "
+.BR help " }"
+.sp
+
+.ti -8
+.BR "ip vrf identify"
+.RI "[ " PID " ]"
+
+.ti -8
+.BR "ip vrf pids"
+.I NAME
+
+.ti -8
+.BR "ip vrf exec "
+.RI "[ " NAME " ] " command ...
+
+.SH DESCRIPTION
+A VRF provides traffic isolation at layer 3 for routing, similar to how a
+VLAN is used to isolate traffic at layer 2. Fundamentally, a VRF is a separate
+routing table. Network devices are associated with a VRF by enslaving the
+device to the VRF. At that point network addresses assigned to the device are
+local to the VRF with host and connected routes moved to the table associated
+with the VRF.
+
+A process can specify a VRF using several APIs -- binding the socket to the
+VRF device using SO_BINDTODEVICE, setting the VRF association using
+IP_UNICAST_IF or IPV6_UNICAST_IF, or specifying the VRF for a specific message
+using IP_PKTINFO or IPV6_PKTINFO.
+
+By default a process is not bound to any VRF. An association can be set
+explicitly by making the program use one of the APIs mentioned above or
+implicitly using a helper to set SO_BINDTODEVICE for all IPv4 and IPv6
+sockets (AF_INET and AF_INET6) when the socket is created. This ip-vrf command
+is a helper to run a command against a specific VRF with the VRF association
+inherited parent to child.
+
+.TP
+.B ip vrf exec [ NAME ] cmd ... - Run cmd against the named VRF
+.sp
+This command allows applications that are VRF unaware to be run against
+a VRF other than the default VRF (main table). A command can be run against
+the default VRF by passing the "default" as the VRF name. This is useful if
+the current shell is associated with another VRF (e.g, Management VRF).
+
+.TP
+.B ip vrf identify [PID] - Report VRF association for process
+.sp
+This command shows the VRF association of the specified process. If PID is
+not specified then the id of the current process is used.
+
+.TP
+.B ip vrf pids NAME - Report processes associated with the named VRF
+.sp
+This command shows all process ids that are associated with the given
+VRF.
+
+.SH CAVEATS
+This command requires a kernel compiled with CGROUPS and CGROUP_BPF enabled.
+
+The VRF helper *only* affects network layer sockets.
+
+.SH EXAMPLES
+.PP
+ip vrf exec red ssh 10.100.1.254
+.RS
+Executes ssh to 10.100.1.254 against the VRF red table.
+.RE
+
+.SH SEE ALSO
+.br
+.BR ip (8),
+.BR ip-link (8),
+.BR ip-address (8),
+.BR ip-route (8),
+.BR ip-neighbor (8)
+
+.SH AUTHOR
+Original Manpage by David Ahern
--
2.1.4
^ permalink raw reply related
* Re: Misalignment, MIPS, and ip_hdr(skb)->version
From: Måns Rullgård @ 2016-12-10 20:32 UTC (permalink / raw)
To: Felix Fietkau
Cc: linux-mips, Netdev, LKML, David Miller, WireGuard mailing list
In-Reply-To: <7f8ba817-73ef-e1e1-4fdf-b9178e922008@nbd.name>
Felix Fietkau <nbd@nbd.name> writes:
> On 2016-12-10 14:25, Måns Rullgård wrote:
>> Felix Fietkau <nbd@nbd.name> writes:
>>
>>> On 2016-12-07 19:54, Jason A. Donenfeld wrote:
>>>> On Wed, Dec 7, 2016 at 7:51 PM, David Miller <davem@davemloft.net> wrote:
>>>>> It's so much better to analyze properly where the misalignment comes from
>>>>> and address it at the source, as we have for various cases that trip up
>>>>> Sparc too.
>>>>
>>>> That's sort of my attitude too, hence starting this thread. Any
>>>> pointers you have about this would be most welcome, so as not to
>>>> perpetuate what already seems like an issue in other parts of the
>>>> stack.
>>> Hi Jason,
>>>
>>> I'm the author of that hackish LEDE/OpenWrt patch that works around the
>>> misalignment issues. Here's some context regarding that patch:
>>>
>>> I intentionally put it in the target specific patches for only one of
>>> our MIPS targets. There are a few ar71xx devices where the misalignment
>>> cannot be fixed, because the Ethernet MAC has a 4-byte DMA alignment
>>> requirement, and does not support inserting 2 bytes of padding to
>>> correct the IP header misalignment.
>>>
>>> With these limitations the choice was between this ugly network stack
>>> patch or inserting a very expensive memmove in the data path (which is
>>> better than taking the mis-alignment traps, but still hurts routing
>>> performance significantly).
>>
>> I solved this problem in an Ethernet driver by copying the initial part
>> of the packet to an aligned skb and appending the remainder using
>> skb_add_rx_frag(). The kernel network stack only cares about the
>> headers, so the alignment of the packet payload doesn't matter.
>
> I considered that as well, but it's bad for routing performance if the
> ethernet MAC does not support scatter/gather for xmit.
> Unfortunately that limitation is quite common on embedded hardware.
Yes, I can see that being an issue. However, if you're doing zero-copy
routing, the header part of the original buffer should still be there,
unused, so you could presumably copy the header of the outgoing packet
there and then do dma as usual. Maybe there's something in the network
stack that makes this impossible though.
--
Måns Rullgård
^ permalink raw reply
* Re: Misalignment, MIPS, and ip_hdr(skb)->version
From: Felix Fietkau @ 2016-12-10 20:36 UTC (permalink / raw)
To: Måns Rullgård
Cc: linux-mips, Netdev, LKML, David Miller, WireGuard mailing list
In-Reply-To: <yw1xy3znwmmr.fsf@unicorn.mansr.com>
On 2016-12-10 21:32, Måns Rullgård wrote:
> Felix Fietkau <nbd@nbd.name> writes:
>
>> On 2016-12-10 14:25, Måns Rullgård wrote:
>>> Felix Fietkau <nbd@nbd.name> writes:
>>>
>>>> On 2016-12-07 19:54, Jason A. Donenfeld wrote:
>>>>> On Wed, Dec 7, 2016 at 7:51 PM, David Miller <davem@davemloft.net> wrote:
>>>>>> It's so much better to analyze properly where the misalignment comes from
>>>>>> and address it at the source, as we have for various cases that trip up
>>>>>> Sparc too.
>>>>>
>>>>> That's sort of my attitude too, hence starting this thread. Any
>>>>> pointers you have about this would be most welcome, so as not to
>>>>> perpetuate what already seems like an issue in other parts of the
>>>>> stack.
>>>> Hi Jason,
>>>>
>>>> I'm the author of that hackish LEDE/OpenWrt patch that works around the
>>>> misalignment issues. Here's some context regarding that patch:
>>>>
>>>> I intentionally put it in the target specific patches for only one of
>>>> our MIPS targets. There are a few ar71xx devices where the misalignment
>>>> cannot be fixed, because the Ethernet MAC has a 4-byte DMA alignment
>>>> requirement, and does not support inserting 2 bytes of padding to
>>>> correct the IP header misalignment.
>>>>
>>>> With these limitations the choice was between this ugly network stack
>>>> patch or inserting a very expensive memmove in the data path (which is
>>>> better than taking the mis-alignment traps, but still hurts routing
>>>> performance significantly).
>>>
>>> I solved this problem in an Ethernet driver by copying the initial part
>>> of the packet to an aligned skb and appending the remainder using
>>> skb_add_rx_frag(). The kernel network stack only cares about the
>>> headers, so the alignment of the packet payload doesn't matter.
>>
>> I considered that as well, but it's bad for routing performance if the
>> ethernet MAC does not support scatter/gather for xmit.
>> Unfortunately that limitation is quite common on embedded hardware.
>
> Yes, I can see that being an issue. However, if you're doing zero-copy
> routing, the header part of the original buffer should still be there,
> unused, so you could presumably copy the header of the outgoing packet
> there and then do dma as usual. Maybe there's something in the network
> stack that makes this impossible though.
That still puts more pressure on the ridiculously small dcache sizes
that are typical for embedded MIPS routers.
- Felix
_______________________________________________
WireGuard mailing list
WireGuard@lists.zx2c4.com
https://lists.zx2c4.com/mailman/listinfo/wireguard
^ permalink raw reply
* Re: [PATCH net v3] ibmveth: set correct gso_size and gso_type
From: David Miller @ 2016-12-10 20:56 UTC (permalink / raw)
To: tlfalcon
Cc: netdev, brking, marcelo.leitner, pradeeps, jmaxwell37, zdai,
eric.dumazet
In-Reply-To: <1481395188-9137-1-git-send-email-tlfalcon@linux.vnet.ibm.com>
From: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
Date: Sat, 10 Dec 2016 12:39:48 -0600
> v3: include a check for non-zero mss when calculating gso_segs
>
> v2: calculate gso_segs after Eric Dumazet's comments on the earlier patch
> and make sure everyone is included on CC
I already applied v1 which made it all the way even to Linus's
tree. So you'll have to send me relative fixups if there are
things to fix or change since v1.
You must always generate patches against the current 'net' tree.
^ permalink raw reply
* Re: [iproute2 net-next 1/8] lib bpf: Add support for BPF_PROG_ATTACH and BPF_PROG_DETACH
From: Daniel Borkmann @ 2016-12-10 21:16 UTC (permalink / raw)
To: David Ahern, netdev, stephen
In-Reply-To: <1481401934-4026-2-git-send-email-dsa@cumulusnetworks.com>
On 12/10/2016 09:32 PM, David Ahern wrote:
> For consistency with other bpf commands, the functions are named
> bpf_prog_attach and bpf_prog_detach. The existing bpf_prog_attach is
> renamed to bpf_prog_load_and_report since it calls bpf_prog_load and
> bpf_prog_report.
>
> Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
> ---
> include/bpf_util.h | 3 +++
> lib/bpf.c | 31 ++++++++++++++++++++++++++-----
> 2 files changed, 29 insertions(+), 5 deletions(-)
>
> diff --git a/include/bpf_util.h b/include/bpf_util.h
> index 05baeecda57f..49b96bbc208f 100644
> --- a/include/bpf_util.h
> +++ b/include/bpf_util.h
> @@ -75,6 +75,9 @@ int bpf_trace_pipe(void);
>
> void bpf_print_ops(FILE *f, struct rtattr *bpf_ops, __u16 len);
>
> +int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type);
> +int bpf_prog_detach(int target_fd, enum bpf_attach_type type);
> +
> #ifdef HAVE_ELF
> int bpf_send_map_fds(const char *path, const char *obj);
> int bpf_recv_map_fds(const char *path, int *fds, struct bpf_map_aux *aux,
> diff --git a/lib/bpf.c b/lib/bpf.c
> index 2a8cd51d4dae..103fc1ef0593 100644
> --- a/lib/bpf.c
> +++ b/lib/bpf.c
> @@ -850,6 +850,27 @@ int bpf_graft_map(const char *map_path, uint32_t *key, int argc, char **argv)
> return ret;
> }
>
> +int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type)
> +{
> + union bpf_attr attr = {
> + .target_fd = target_fd,
> + .attach_bpf_fd = prog_fd,
> + .attach_type = type,
> + };
Please make this consistent with the other bpf(2) cmds we
have in the current lib code. There were some gcc issues in
the past, see:
https://git.kernel.org/cgit/linux/kernel/git/shemminger/iproute2.git/commit/?id=67584e3ab289a22eb9a2e51f90d23e2ced2e76b0
F.e. bpf_map_create() currently looks like:
union bpf_attr attr = {};
attr.map_type = type;
attr.key_size = size_key;
attr.value_size = size_value;
attr.max_entries = max_elem;
attr.map_flags = flags;
> + return bpf(BPF_PROG_ATTACH, &attr, sizeof(attr));
> +}
> +
> +int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
> +{
> + union bpf_attr attr = {
> + .target_fd = target_fd,
> + .attach_type = type,
> + };
Ditto.
> + return bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
> +}
> +
> #ifdef HAVE_ELF
> struct bpf_elf_prog {
> enum bpf_prog_type type;
> @@ -1262,9 +1283,9 @@ static void bpf_prog_report(int fd, const char *section,
> bpf_dump_error(ctx, "Verifier analysis:\n\n");
> }
>
> -static int bpf_prog_attach(const char *section,
> - const struct bpf_elf_prog *prog,
> - struct bpf_elf_ctx *ctx)
> +static int bpf_prog_load_and_report(const char *section,
> + const struct bpf_elf_prog *prog,
> + struct bpf_elf_ctx *ctx)
> {
Please name it bpf_prog_create() then, it would be consistent to
bpf_map_create() and shorter as well.
> int tries = 0, fd;
> retry:
> @@ -1656,7 +1677,7 @@ static int bpf_fetch_prog(struct bpf_elf_ctx *ctx, const char *section,
> prog.size = data.sec_data->d_size;
> prog.license = ctx->license;
>
> - fd = bpf_prog_attach(section, &prog, ctx);
> + fd = bpf_prog_load_and_report(section, &prog, ctx);
> if (fd < 0)
> return fd;
>
> @@ -1755,7 +1776,7 @@ static int bpf_fetch_prog_relo(struct bpf_elf_ctx *ctx, const char *section,
> prog.size = data_insn.sec_data->d_size;
> prog.license = ctx->license;
>
> - fd = bpf_prog_attach(section, &prog, ctx);
> + fd = bpf_prog_load_and_report(section, &prog, ctx);
> if (fd < 0) {
> *lderr = true;
> return fd;
>
^ permalink raw reply
* Re: [iproute2 net-next 1/8] lib bpf: Add support for BPF_PROG_ATTACH and BPF_PROG_DETACH
From: Daniel Borkmann @ 2016-12-10 21:21 UTC (permalink / raw)
To: David Ahern, netdev, stephen
In-Reply-To: <584C70C0.8040506@iogearbox.net>
On 12/10/2016 10:16 PM, Daniel Borkmann wrote:
> On 12/10/2016 09:32 PM, David Ahern wrote:
>> For consistency with other bpf commands, the functions are named
>> bpf_prog_attach and bpf_prog_detach. The existing bpf_prog_attach is
>> renamed to bpf_prog_load_and_report since it calls bpf_prog_load and
>> bpf_prog_report.
>>
>> Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
>> ---
>> include/bpf_util.h | 3 +++
>> lib/bpf.c | 31 ++++++++++++++++++++++++++-----
>> 2 files changed, 29 insertions(+), 5 deletions(-)
>>
>> diff --git a/include/bpf_util.h b/include/bpf_util.h
>> index 05baeecda57f..49b96bbc208f 100644
>> --- a/include/bpf_util.h
>> +++ b/include/bpf_util.h
>> @@ -75,6 +75,9 @@ int bpf_trace_pipe(void);
>>
>> void bpf_print_ops(FILE *f, struct rtattr *bpf_ops, __u16 len);
>>
>> +int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type);
>> +int bpf_prog_detach(int target_fd, enum bpf_attach_type type);
>> +
>> #ifdef HAVE_ELF
>> int bpf_send_map_fds(const char *path, const char *obj);
>> int bpf_recv_map_fds(const char *path, int *fds, struct bpf_map_aux *aux,
>> diff --git a/lib/bpf.c b/lib/bpf.c
>> index 2a8cd51d4dae..103fc1ef0593 100644
>> --- a/lib/bpf.c
>> +++ b/lib/bpf.c
>> @@ -850,6 +850,27 @@ int bpf_graft_map(const char *map_path, uint32_t *key, int argc, char **argv)
>> return ret;
>> }
>>
>> +int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type)
>> +{
>> + union bpf_attr attr = {
>> + .target_fd = target_fd,
>> + .attach_bpf_fd = prog_fd,
>> + .attach_type = type,
>> + };
>
> Please make this consistent with the other bpf(2) cmds we
> have in the current lib code. There were some gcc issues in
> the past, see:
>
> https://git.kernel.org/cgit/linux/kernel/git/shemminger/iproute2.git/commit/?id=67584e3ab289a22eb9a2e51f90d23e2ced2e76b0
>
> F.e. bpf_map_create() currently looks like:
>
> union bpf_attr attr = {};
>
> attr.map_type = type;
> attr.key_size = size_key;
> attr.value_size = size_value;
> attr.max_entries = max_elem;
> attr.map_flags = flags;
>
>> + return bpf(BPF_PROG_ATTACH, &attr, sizeof(attr));
>> +}
>> +
>> +int bpf_prog_detach(int target_fd, enum bpf_attach_type type)
>> +{
>> + union bpf_attr attr = {
>> + .target_fd = target_fd,
>> + .attach_type = type,
>> + };
>
> Ditto.
>
>> + return bpf(BPF_PROG_DETACH, &attr, sizeof(attr));
>> +}
>> +
>> #ifdef HAVE_ELF
>> struct bpf_elf_prog {
>> enum bpf_prog_type type;
>> @@ -1262,9 +1283,9 @@ static void bpf_prog_report(int fd, const char *section,
>> bpf_dump_error(ctx, "Verifier analysis:\n\n");
>> }
>>
>> -static int bpf_prog_attach(const char *section,
>> - const struct bpf_elf_prog *prog,
>> - struct bpf_elf_ctx *ctx)
>> +static int bpf_prog_load_and_report(const char *section,
>> + const struct bpf_elf_prog *prog,
>> + struct bpf_elf_ctx *ctx)
>> {
>
> Please name it bpf_prog_create() then, it would be consistent to
> bpf_map_create() and shorter as well.
Sorry, lack of coffee, scratch that.
Can't the current bpf_prog_attach() stay as is, and you name the above new
functions bpf_prog_attach_fd() and bpf_prog_detach_fd()? I think that would
be better.
>> int tries = 0, fd;
>> retry:
>> @@ -1656,7 +1677,7 @@ static int bpf_fetch_prog(struct bpf_elf_ctx *ctx, const char *section,
>> prog.size = data.sec_data->d_size;
>> prog.license = ctx->license;
>>
>> - fd = bpf_prog_attach(section, &prog, ctx);
>> + fd = bpf_prog_load_and_report(section, &prog, ctx);
>> if (fd < 0)
>> return fd;
>>
>> @@ -1755,7 +1776,7 @@ static int bpf_fetch_prog_relo(struct bpf_elf_ctx *ctx, const char *section,
>> prog.size = data_insn.sec_data->d_size;
>> prog.license = ctx->license;
>>
>> - fd = bpf_prog_attach(section, &prog, ctx);
>> + fd = bpf_prog_load_and_report(section, &prog, ctx);
>> if (fd < 0) {
>> *lderr = true;
>> return fd;
>>
>
^ permalink raw reply
* Re: [iproute2 net-next 2/8] bpf: export bpf_prog_load
From: Daniel Borkmann @ 2016-12-10 21:24 UTC (permalink / raw)
To: David Ahern, netdev, stephen
In-Reply-To: <1481401934-4026-3-git-send-email-dsa@cumulusnetworks.com>
On 12/10/2016 09:32 PM, David Ahern wrote:
> Code move only; no functional change intended.
>
> Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
> ---
> include/bpf_util.h | 3 +++
> lib/bpf.c | 40 ++++++++++++++++++++--------------------
> 2 files changed, 23 insertions(+), 20 deletions(-)
>
> diff --git a/include/bpf_util.h b/include/bpf_util.h
> index 49b96bbc208f..dcbdca6978d6 100644
> --- a/include/bpf_util.h
> +++ b/include/bpf_util.h
> @@ -75,6 +75,9 @@ int bpf_trace_pipe(void);
>
> void bpf_print_ops(FILE *f, struct rtattr *bpf_ops, __u16 len);
>
> +int bpf_prog_load(enum bpf_prog_type type, const struct bpf_insn *insns,
> + size_t size_insns, const char *license, char *log,
> + size_t size_log);
Just a really minor nit: please add a newline here.
> int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type);
> int bpf_prog_detach(int target_fd, enum bpf_attach_type type);
>
^ permalink raw reply
* Re: [PATCH] sh_eth: add wake-on-lan support via magic packet
From: Sergei Shtylyov @ 2016-12-10 21:25 UTC (permalink / raw)
To: Niklas Söderlund; +Cc: Simon Horman, netdev, linux-renesas-soc
In-Reply-To: <20161208145635.GH21834@bigcity.dyn.berto.se>
Hello!
On 12/08/2016 05:56 PM, Niklas Söderlund wrote:
>> You only enable the WOL support fo the R-Car gen2 chips but never say that
>> explicitly, neither in the subject nor here.
>>
>>> Signed-off-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
>>> ---
>>> drivers/net/ethernet/renesas/sh_eth.c | 120 +++++++++++++++++++++++++++++++---
>>> drivers/net/ethernet/renesas/sh_eth.h | 4 ++
>>> 2 files changed, 116 insertions(+), 8 deletions(-)
>>
>>> diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
>>> index 05b0dc5..3974046 100644
>>> --- a/drivers/net/ethernet/renesas/sh_eth.c
>>> +++ b/drivers/net/ethernet/renesas/sh_eth.c
[...]
>>> @@ -1657,6 +1658,10 @@ static irqreturn_t sh_eth_interrupt(int irq, void *netdev)
>>> goto out;
>>>
>>> if (!likely(mdp->irq_enabled)) {
>>
>> Oops, I guess unlikely(!mdp->irq_enabled) was meant here...
>
> I can correct this in a separate patch if you wish.
I'll look into this myself, I think.
>> + /* Handle MagicPacket interrupt */
>> + if (sh_eth_read(ndev, ECSR) & ECSR_MPD)
What if it wasn't enabled ATM?
[...]
>>> @@ -3111,6 +3150,10 @@ static int sh_eth_drv_probe(struct platform_device *pdev)
>>> if (ret)
>>> goto out_napi_del;
>>>
>>> + mdp->wol_enabled = false;
>>
>> No need, the '*mdp' was kzalloc'ed.
>
> OK, i prefer to explicitly set for easier reading of the code. But if
> you wish I will remove this in v2.
Yes, remove it please.
>>> @@ -3150,15 +3193,71 @@ static int sh_eth_drv_remove(struct platform_device *pdev)
>>>
>>> #ifdef CONFIG_PM
>>> #ifdef CONFIG_PM_SLEEP
>>> +static int sh_eth_wol_setup(struct net_device *ndev)
>>> +{
>>> + struct sh_eth_private *mdp = netdev_priv(ndev);
>>> +
>>> + /* Only allow ECI interrupts */
>>> + mdp->irq_enabled = false;
>>
>> Why 'false' if you enable IRQs below?
>
> I mask all interrupts except MagicPacket (ECSIPR_MPDIP) interrupts form
> the ECI (DMAC_M_ECI) and by setting irq_enabled to false the interrupt
> handler will only ack any residue interrupt.
I don't see where it ack's anything, it just clears EESIPR and returns in
this case.
> This is how it's done in
> other parts of the driver when disabling interrupts.
Not in all parts of the driver that disable EESIPR interrupts... I must
confess that I never liked that 'mdp->irq_enabled' flag and still suspect we
can get things done without it... I need to look at this code again, sigh...
> This is also why I only check for MagicPacket interrupts if irq_enabled
> is false.
I would have preferred that this was done with the other EMAC interrupts,
in sh_eth_error().
>>> + synchronize_irq(ndev->irq);
>>> + napi_disable(&mdp->napi);
>>> + sh_eth_write(ndev, DMAC_M_ECI, EESIPR);
>>> +
>>> + /* Enable ECI MagicPacket interrupt */
>>> + sh_eth_write(ndev, ECSIPR_MPDIP, ECSIPR);
I'd prefer if it was always enabled via 'ecsipr_value'.
>>> +
>>> + /* Enable MagicPacket */
>>> + sh_eth_modify(ndev, ECMR, 0, ECMR_PMDE);
>>> +
>>> + /* Increased clock usage so device won't be suspended */
>>> + clk_enable(mdp->clk);
>>
>> Hum, intermixiggn runtime PM with clock API doesn't look good...
>
> I agree it looks weird but I need a way to increment the usage count for
> the clock otherwise the PM code will disable the module clock and WoL
> will not work.
How will it do it if you don't call sh_eth_close() in this case?
> Note that this call will not enable the clock just
> increase the usage count so it won't be disabled when the PM code
> decrease it after the sh_eth suspend function is run.
You mean that the PM code calls RPM or clk API on its own? That's strange...
> If you know of a different way of ensuring that the clock is not turned
> off I be happy to look at it. I did some investigation into this and
> calling clk_enable() directly is for example what happens in the
> enable_irq_wake() call path to ensure the clock for the irq_chip is not
> turned off if it is a wakeup source, se for example
> gpio_rcar_irq_set_wake() in drivers/gpio/gpio-rcar.c.
Thanks, will look into it...
[...]
MBR, Sergei
^ permalink raw reply
* Re: [iproute2 net-next 3/8] Add libbpf.h header with BPF_ macros
From: Daniel Borkmann @ 2016-12-10 21:27 UTC (permalink / raw)
To: David Ahern, netdev, stephen
In-Reply-To: <1481401934-4026-4-git-send-email-dsa@cumulusnetworks.com>
On 12/10/2016 09:32 PM, David Ahern wrote:
> Based on version in kernel repo, samples/bpf/libbpf.h
>
> Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
> ---
> include/libbpf.h | 184 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 184 insertions(+)
> create mode 100644 include/libbpf.h
>
> diff --git a/include/libbpf.h b/include/libbpf.h
> new file mode 100644
> index 000000000000..37951f509a10
> --- /dev/null
> +++ b/include/libbpf.h
> @@ -0,0 +1,184 @@
> +/* eBPF mini library */
> +#ifndef __LIBBPF_H
> +#define __LIBBPF_H
Creating include/libbpf.h is a bit confusing, since all the function
declarations of the current bpf lib code are located in include/bpf_util.h.
Please add all this there as well instead of creating a new file.
^ permalink raw reply
* Re: [iproute2 net-next 1/8] lib bpf: Add support for BPF_PROG_ATTACH and BPF_PROG_DETACH
From: David Ahern @ 2016-12-10 22:15 UTC (permalink / raw)
To: Daniel Borkmann, netdev, stephen
In-Reply-To: <584C71F0.3000203@iogearbox.net>
On 12/10/16 2:21 PM, Daniel Borkmann wrote:
>>
>> Please name it bpf_prog_create() then, it would be consistent to
>> bpf_map_create() and shorter as well.
>
> Sorry, lack of coffee, scratch that.
>
> Can't the current bpf_prog_attach() stay as is, and you name the above new
> functions bpf_prog_attach_fd() and bpf_prog_detach_fd()? I think that would
> be better.
ok. no concerns about consistency with libbpf in the kernel repo?
Seems like making iproute2 and the kernel version the same will allow samples and code to move between them much easier.
^ permalink raw reply
* Re: Misalignment, MIPS, and ip_hdr(skb)->version
From: Dan Lüdtke @ 2016-12-10 22:18 UTC (permalink / raw)
To: Daniel Kahn Gillmor
Cc: linux-mips, Netdev, LKML, Hannes Frederic Sowa,
WireGuard mailing list
In-Reply-To: <87vauvhwdu.fsf@alice.fifthhorseman.net>
> On 8 Dec 2016, at 05:34, Daniel Kahn Gillmor <dkg@fifthhorseman.net> wrote:
>
> On Wed 2016-12-07 19:30:34 -0500, Hannes Frederic Sowa wrote:
>> Your custom protocol should be designed in a way you get an aligned ip
>> header. Most protocols of the IETF follow this mantra and it is always
>> possible to e.g. pad options so you end up on aligned boundaries for the
>> next header.
>
> fwiw, i'm not convinced that "most protocols of the IETF follow this
> mantra". we've had multiple discussions in different protocol groups
> about shaving or bloating by a few bytes here or there in different
> protocols, and i don't think anyone has brought up memory alignment as
> an argument in any of the discussions i've followed.
>
If the trade-off is between 1 padding byte and 2 byte alignment versus 3 padding bytes and 4 byte alignment I would definitely opt for 3 padding bytes. I know how that waste feels like to a protocol designer, but I think it is worth it. Maybe the padding/reserved will be useful some day for an additional feature.
I remember alignment being discussed and taken very seriously in 6man a couple of times. Often, though, protocol designers did align without much discussion. Implementing unaligned protocols is a pain I've experienced first hand.
^ permalink raw reply
* [Patch net] e1000: use disable_hardirq() for e1000_netpoll()
From: Cong Wang @ 2016-12-10 22:22 UTC (permalink / raw)
To: netdev; +Cc: sd, davej, Cong Wang, Peter Zijlstra (Intel), Jeff Kirsher
In commit 02cea3958664 ("genirq: Provide disable_hardirq()")
Peter introduced disable_hardirq() for netpoll, but it is forgotten
to use it for e1000.
This patch changes disable_irq() to disable_hardirq() for e1000.
Reported-by: Dave Jones <davej@codemonkey.org.uk>
Suggested-by: Sabrina Dubroca <sd@queasysnail.net>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
---
drivers/net/ethernet/intel/e1000/e1000_main.c | 4 ++--
drivers/net/ethernet/intel/e1000e/netdev.c | 8 ++++----
2 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index f42129d..164c3bb 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -5257,8 +5257,8 @@ static void e1000_netpoll(struct net_device *netdev)
{
struct e1000_adapter *adapter = netdev_priv(netdev);
- disable_irq(adapter->pdev->irq);
- e1000_intr(adapter->pdev->irq, netdev);
+ if (disable_hardirq(adapter->pdev->irq))
+ e1000_intr(adapter->pdev->irq, netdev);
enable_irq(adapter->pdev->irq);
}
#endif
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 7017281..9a0be77 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -6762,13 +6762,13 @@ static void e1000_netpoll(struct net_device *netdev)
e1000_intr_msix(adapter->pdev->irq, netdev);
break;
case E1000E_INT_MODE_MSI:
- disable_irq(adapter->pdev->irq);
- e1000_intr_msi(adapter->pdev->irq, netdev);
+ if (disable_hardirq(adapter->pdev->irq))
+ e1000_intr_msi(adapter->pdev->irq, netdev);
enable_irq(adapter->pdev->irq);
break;
default: /* E1000E_INT_MODE_LEGACY */
- disable_irq(adapter->pdev->irq);
- e1000_intr(adapter->pdev->irq, netdev);
+ if (disable_hardirq(adapter->pdev->irq))
+ e1000_intr(adapter->pdev->irq, netdev);
enable_irq(adapter->pdev->irq);
break;
}
--
2.5.5
^ permalink raw reply related
* Re: [Patch net-next] netlink: use blocking notifier
From: David Miller @ 2016-12-10 22:26 UTC (permalink / raw)
To: xiyou.wangcong; +Cc: netdev
In-Reply-To: <1481346661-25380-1-git-send-email-xiyou.wangcong@gmail.com>
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Fri, 9 Dec 2016 21:10:59 -0800
> netlink_chain is called in ->release(), which is apparently
> a process context, so we don't have to use an atomic notifier
> here.
>
> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Applied.
^ permalink raw reply
* Re: [PATCH] net: socket: removed an unnecessary newline
From: David Miller @ 2016-12-10 22:27 UTC (permalink / raw)
To: kushwaha.a; +Cc: sergei.shtylyov, netdev, akkushwaha9896
In-Reply-To: <1481348687-23904-1-git-send-email-kushwaha.a@samsung.com>
From: kushwaha.a@samsung.com
Date: Sat, 10 Dec 2016 11:14:47 +0530
> From: Amit Kushwaha <kushwaha.a@samsung.com>
>
> This patch removes a newline which was added
> in socket.c file in net-next
>
> Signed-off-by: Amit Kushwaha <kushwaha.a@samsung.com>
Applied.
^ permalink raw reply
* Re: [PATCH net-next] net: mvneta: select GENERIC_ALLOCATOR
From: David Miller @ 2016-12-10 22:28 UTC (permalink / raw)
To: arnd; +Cc: gregory.clement, mw, f.fainelli, netdev, linux-kernel
In-Reply-To: <20161210103844.1465583-1-arnd@arndb.de>
From: Arnd Bergmann <arnd@arndb.de>
Date: Sat, 10 Dec 2016 11:38:32 +0100
> We previously relied on GENERIC_ALLOCATOR to be selected by CONFIG_ARM,
> but now we can compile-test the driver on other architectures that
> don't select it:
>
> drivers/net/built-in.o: In function `mvneta_bm_remove':
> mvneta_bm.c:(.text+0x4ee35): undefined reference to `gen_pool_free'
>
> This adds an explicit select for the part of the driver that has
> the dependency.
>
> Fixes: a0627f776a45 ("net: marvell: Allow drivers to be built with COMPILE_TEST")
> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Applied.
^ permalink raw reply
* Re: [PATCH 1/5] net: ethernet: ti: cpsw: improve re-split policy
From: David Miller @ 2016-12-10 22:30 UTC (permalink / raw)
To: ivan.khoronzhuk
Cc: mugunthanvnm, grygorii.strashko, linux-omap, netdev, linux-kernel
In-Reply-To: <1481372630-14914-1-git-send-email-ivan.khoronzhuk@linaro.org>
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Sat, 10 Dec 2016 14:23:45 +0200
> This patches add several simplifications and improvements to set
> maximum rate for channels taking in account switch and dual emac mode.
>
> Don't re-split res in the following cases:
> - speed of phys is not changed
> - speed of phys is changed and no rate limited channels
> - speed of phys is changed and all channels are rate limited
> - phy is unlinked while dev is open
> - phy is linked back but speed is not changed
>
> The maximum speed is sum of "linked" phys, thus res are split taken
> into account two interfaces, both for dual emac mode and for
> switch mode.
>
> Tested on am572x
>
> Based on net-next/master
Applied.
^ permalink raw reply
* Re: [PATCH 2/5] net: ethernet: ti: cpsw: don't start queue twice
From: David Miller @ 2016-12-10 22:30 UTC (permalink / raw)
To: ivan.khoronzhuk
Cc: mugunthanvnm, grygorii.strashko, linux-omap, netdev, linux-kernel
In-Reply-To: <1481372630-14914-3-git-send-email-ivan.khoronzhuk@linaro.org>
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Sat, 10 Dec 2016 14:23:47 +0200
> No need to start queues after cpsw is started as it will be done
> while cpsw_adjust_link(), after phy connection.
>
> Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Applied.
^ permalink raw reply
* Re: [PATCH 3/5] net: ethernet: ti: cpsw: combine budget and weight split and check
From: David Miller @ 2016-12-10 22:30 UTC (permalink / raw)
To: ivan.khoronzhuk
Cc: mugunthanvnm, grygorii.strashko, linux-omap, netdev, linux-kernel
In-Reply-To: <1481372630-14914-4-git-send-email-ivan.khoronzhuk@linaro.org>
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Sat, 10 Dec 2016 14:23:48 +0200
> Re-split weight along with budget. It simplify code a little
> and update state after every rate change. Also it's necessarily
> to move arguments checks to this combined function. Replace
> maximum rate check for an interface on maximum possible rate.
>
> Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Applied.
^ permalink raw reply
* Re: [PATCH 4/5] net: ethernet: ti: cpsw: re-split res only when speed is changed
From: David Miller @ 2016-12-10 22:30 UTC (permalink / raw)
To: ivan.khoronzhuk
Cc: mugunthanvnm, grygorii.strashko, linux-omap, netdev, linux-kernel
In-Reply-To: <1481372630-14914-5-git-send-email-ivan.khoronzhuk@linaro.org>
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Sat, 10 Dec 2016 14:23:49 +0200
> Don't re-split res in the following cases:
> - speed of phys is not changed
> - speed of phys is changed and no rate limited channels
> - speed of phys is changed and all channels are rate limited
> - phy is unlinked while dev is open
> - phy is linked back but speed is not changed
>
> The maximum speed is sum of "linked" phys, thus res are split taken
> in account two interfaces, both for dual emac mode and for
> switch mode.
>
> Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Applied.
^ permalink raw reply
* Re: [PATCH 5/5] net: ethernet: ti: cpsw: sync rates for channels in dual emac mode
From: David Miller @ 2016-12-10 22:30 UTC (permalink / raw)
To: ivan.khoronzhuk
Cc: mugunthanvnm, grygorii.strashko, linux-omap, netdev, linux-kernel
In-Reply-To: <1481372630-14914-6-git-send-email-ivan.khoronzhuk@linaro.org>
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Sat, 10 Dec 2016 14:23:50 +0200
> The channels are common for both ndevs in dual emac mode. Hence, keep
> in sync their rates.
>
> Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Applied.
^ permalink raw reply
* Re: [PATCH] net: nicvf: use new api ethtool_{get|set}_link_ksettings
From: David Miller @ 2016-12-10 22:32 UTC (permalink / raw)
To: tremyfr; +Cc: sgoutham, rric, netdev, linux-kernel
In-Reply-To: <1481378448-22278-1-git-send-email-tremyfr@gmail.com>
From: Philippe Reynes <tremyfr@gmail.com>
Date: Sat, 10 Dec 2016 15:00:48 +0100
> The ethtool api {get|set}_settings is deprecated.
> We move this driver to new api {get|set}_link_ksettings.
>
> Signed-off-by: Philippe Reynes <tremyfr@gmail.com>
Applied.
^ permalink raw reply
* Re: [iproute2 net-next 1/8] lib bpf: Add support for BPF_PROG_ATTACH and BPF_PROG_DETACH
From: Daniel Borkmann @ 2016-12-10 23:18 UTC (permalink / raw)
To: David Ahern, netdev, stephen
In-Reply-To: <93dbc1b0-a76e-4375-0a52-6aa5b4a78c7e@cumulusnetworks.com>
On 12/10/2016 11:15 PM, David Ahern wrote:
> On 12/10/16 2:21 PM, Daniel Borkmann wrote:
>>>
>>> Please name it bpf_prog_create() then, it would be consistent to
>>> bpf_map_create() and shorter as well.
>>
>> Sorry, lack of coffee, scratch that.
>>
>> Can't the current bpf_prog_attach() stay as is, and you name the above new
>> functions bpf_prog_attach_fd() and bpf_prog_detach_fd()? I think that would
>> be better.
>
> ok. no concerns about consistency with libbpf in the kernel repo?
>
> Seems like making iproute2 and the kernel version the same will allow samples and code to move between them much easier.
I think the lib/bpf.c code is quite different anyway, so I don't think it's
much of a concern or even requirement to look exactly the same as the samples
code (it was also never designed with such requirement). But besides that,
it's also trivial enough from reading the code due to the BPF_PROG_ATTACH
and BPF_PROG_DETACH anyway.
^ permalink raw reply
* [PATCH net-next 1/3] net: l2tp: export debug flags to UAPI
From: Asbjoern Sloth Toennesen @ 2016-12-11 0:18 UTC (permalink / raw)
To: David S . Miller; +Cc: James Chapman, netdev, linux-kernel
Move the L2TP_MSG_* definitions to UAPI, as it is part of
the netlink API.
Signed-off-by: Asbjoern Sloth Toennesen <asbjorn@asbjorn.st>
---
include/uapi/linux/l2tp.h | 17 ++++++++++++++++-
net/l2tp/l2tp_core.h | 10 ----------
2 files changed, 16 insertions(+), 11 deletions(-)
diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h
index 5daa48e..85ddb74 100644
--- a/include/uapi/linux/l2tp.h
+++ b/include/uapi/linux/l2tp.h
@@ -108,7 +108,7 @@ enum {
L2TP_ATTR_VLAN_ID, /* u16 */
L2TP_ATTR_COOKIE, /* 0, 4 or 8 bytes */
L2TP_ATTR_PEER_COOKIE, /* 0, 4 or 8 bytes */
- L2TP_ATTR_DEBUG, /* u32 */
+ L2TP_ATTR_DEBUG, /* u32, enum l2tp_debug_flags */
L2TP_ATTR_RECV_SEQ, /* u8 */
L2TP_ATTR_SEND_SEQ, /* u8 */
L2TP_ATTR_LNS_MODE, /* u8 */
@@ -175,6 +175,21 @@ enum l2tp_seqmode {
L2TP_SEQ_ALL = 2,
};
+/**
+ * enum l2tp_debug_flags - debug message categories for L2TP tunnels/sessions
+ *
+ * @L2TP_MSG_DEBUG: verbose debug (if compiled in)
+ * @L2TP_MSG_CONTROL: userspace - kernel interface
+ * @L2TP_MSG_SEQ: sequence numbers
+ * @L2TP_MSG_DATA: data packets
+ */
+enum l2tp_debug_flags {
+ L2TP_MSG_DEBUG = (1 << 0),
+ L2TP_MSG_CONTROL = (1 << 1),
+ L2TP_MSG_SEQ = (1 << 2),
+ L2TP_MSG_DATA = (1 << 3),
+};
+
/*
* NETLINK_GENERIC related info
*/
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 2599af6..8f560f7 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -23,16 +23,6 @@
#define L2TP_HASH_BITS_2 8
#define L2TP_HASH_SIZE_2 (1 << L2TP_HASH_BITS_2)
-/* Debug message categories for the DEBUG socket option */
-enum {
- L2TP_MSG_DEBUG = (1 << 0), /* verbose debug (if
- * compiled in) */
- L2TP_MSG_CONTROL = (1 << 1), /* userspace - kernel
- * interface */
- L2TP_MSG_SEQ = (1 << 2), /* sequence numbers */
- L2TP_MSG_DATA = (1 << 3), /* data packets */
-};
-
struct sk_buff;
struct l2tp_stats {
--
2.10.2
^ permalink raw reply related
* [PATCH net-next 2/3] net: l2tp: deprecate PPPOL2TP_MSG_* in favour of L2TP_MSG_*
From: Asbjoern Sloth Toennesen @ 2016-12-11 0:18 UTC (permalink / raw)
To: David S . Miller; +Cc: James Chapman, netdev, linux-kernel
In-Reply-To: <20161211001859.10333-1-asbjorn@asbjorn.st>
PPPOL2TP_MSG_* and L2TP_MSG_* are duplicates, and are being used
interchangeably in the kernel, so let's standardize on L2TP_MSG_*
internally, and keep PPPOL2TP_MSG_* defined in UAPI for compatibility.
Signed-off-by: Asbjoern Sloth Toennesen <asbjorn@asbjorn.st>
---
Documentation/networking/l2tp.txt | 8 ++++----
include/uapi/linux/if_pppol2tp.h | 13 ++++++-------
2 files changed, 10 insertions(+), 11 deletions(-)
diff --git a/Documentation/networking/l2tp.txt b/Documentation/networking/l2tp.txt
index 4650a00..9bc271c 100644
--- a/Documentation/networking/l2tp.txt
+++ b/Documentation/networking/l2tp.txt
@@ -177,10 +177,10 @@ setsockopt on the PPPoX socket to set a debug mask.
The following debug mask bits are available:
-PPPOL2TP_MSG_DEBUG verbose debug (if compiled in)
-PPPOL2TP_MSG_CONTROL userspace - kernel interface
-PPPOL2TP_MSG_SEQ sequence numbers handling
-PPPOL2TP_MSG_DATA data packets
+L2TP_MSG_DEBUG verbose debug (if compiled in)
+L2TP_MSG_CONTROL userspace - kernel interface
+L2TP_MSG_SEQ sequence numbers handling
+L2TP_MSG_DATA data packets
If enabled, files under a l2tp debugfs directory can be used to dump
kernel state about L2TP tunnels and sessions. To access it, the
diff --git a/include/uapi/linux/if_pppol2tp.h b/include/uapi/linux/if_pppol2tp.h
index 4bd1f55..6418c4d 100644
--- a/include/uapi/linux/if_pppol2tp.h
+++ b/include/uapi/linux/if_pppol2tp.h
@@ -18,6 +18,7 @@
#include <linux/types.h>
#include <linux/in.h>
#include <linux/in6.h>
+#include <linux/l2tp.h>
/* Structure used to connect() the socket to a particular tunnel UDP
* socket over IPv4.
@@ -90,14 +91,12 @@ enum {
PPPOL2TP_SO_REORDERTO = 5,
};
-/* Debug message categories for the DEBUG socket option */
+/* Debug message categories for the DEBUG socket option (deprecated) */
enum {
- PPPOL2TP_MSG_DEBUG = (1 << 0), /* verbose debug (if
- * compiled in) */
- PPPOL2TP_MSG_CONTROL = (1 << 1), /* userspace - kernel
- * interface */
- PPPOL2TP_MSG_SEQ = (1 << 2), /* sequence numbers */
- PPPOL2TP_MSG_DATA = (1 << 3), /* data packets */
+ PPPOL2TP_MSG_DEBUG = L2TP_MSG_DEBUG,
+ PPPOL2TP_MSG_CONTROL = L2TP_MSG_CONTROL,
+ PPPOL2TP_MSG_SEQ = L2TP_MSG_SEQ,
+ PPPOL2TP_MSG_DATA = L2TP_MSG_DATA,
};
--
2.10.2
^ permalink raw reply related
* [PATCH net-next 3/3] net: l2tp: ppp: change PPPOL2TP_MSG_* => L2TP_MSG_*
From: Asbjoern Sloth Toennesen @ 2016-12-11 0:18 UTC (permalink / raw)
To: David S . Miller; +Cc: James Chapman, netdev, linux-kernel
In-Reply-To: <20161211001859.10333-1-asbjorn@asbjorn.st>
Signed-off-by: Asbjoern Sloth Toennesen <asbjorn@asbjorn.st>
---
net/l2tp/l2tp_ppp.c | 54 ++++++++++++++++++++++++++---------------------------
1 file changed, 27 insertions(+), 27 deletions(-)
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 2ddfec1..36cc56f 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -231,14 +231,14 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int
if (sk->sk_state & PPPOX_BOUND) {
struct pppox_sock *po;
- l2tp_dbg(session, PPPOL2TP_MSG_DATA,
+ l2tp_dbg(session, L2TP_MSG_DATA,
"%s: recv %d byte data frame, passing to ppp\n",
session->name, data_len);
po = pppox_sk(sk);
ppp_input(&po->chan, skb);
} else {
- l2tp_dbg(session, PPPOL2TP_MSG_DATA,
+ l2tp_dbg(session, L2TP_MSG_DATA,
"%s: recv %d byte data frame, passing to L2TP socket\n",
session->name, data_len);
@@ -251,7 +251,7 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int
return;
no_sock:
- l2tp_info(session, PPPOL2TP_MSG_DATA, "%s: no socket\n", session->name);
+ l2tp_info(session, L2TP_MSG_DATA, "%s: no socket\n", session->name);
kfree_skb(skb);
}
@@ -773,7 +773,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
/* This is how we get the session context from the socket. */
sk->sk_user_data = session;
sk->sk_state = PPPOX_CONNECTED;
- l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: created\n",
+ l2tp_info(session, L2TP_MSG_CONTROL, "%s: created\n",
session->name);
end:
@@ -827,7 +827,7 @@ static int pppol2tp_session_create(struct net *net, u32 tunnel_id, u32 session_i
ps = l2tp_session_priv(session);
ps->tunnel_sock = tunnel->sock;
- l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: created\n",
+ l2tp_info(session, L2TP_MSG_CONTROL, "%s: created\n",
session->name);
error = 0;
@@ -989,7 +989,7 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session,
struct l2tp_tunnel *tunnel = session->tunnel;
struct pppol2tp_ioc_stats stats;
- l2tp_dbg(session, PPPOL2TP_MSG_CONTROL,
+ l2tp_dbg(session, L2TP_MSG_CONTROL,
"%s: pppol2tp_session_ioctl(cmd=%#x, arg=%#lx)\n",
session->name, cmd, arg);
@@ -1009,7 +1009,7 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session,
if (copy_to_user((void __user *) arg, &ifr, sizeof(struct ifreq)))
break;
- l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: get mtu=%d\n",
+ l2tp_info(session, L2TP_MSG_CONTROL, "%s: get mtu=%d\n",
session->name, session->mtu);
err = 0;
break;
@@ -1025,7 +1025,7 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session,
session->mtu = ifr.ifr_mtu;
- l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: set mtu=%d\n",
+ l2tp_info(session, L2TP_MSG_CONTROL, "%s: set mtu=%d\n",
session->name, session->mtu);
err = 0;
break;
@@ -1039,7 +1039,7 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session,
if (put_user(session->mru, (int __user *) arg))
break;
- l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: get mru=%d\n",
+ l2tp_info(session, L2TP_MSG_CONTROL, "%s: get mru=%d\n",
session->name, session->mru);
err = 0;
break;
@@ -1054,7 +1054,7 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session,
break;
session->mru = val;
- l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: set mru=%d\n",
+ l2tp_info(session, L2TP_MSG_CONTROL, "%s: set mru=%d\n",
session->name, session->mru);
err = 0;
break;
@@ -1064,7 +1064,7 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session,
if (put_user(ps->flags, (int __user *) arg))
break;
- l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: get flags=%d\n",
+ l2tp_info(session, L2TP_MSG_CONTROL, "%s: get flags=%d\n",
session->name, ps->flags);
err = 0;
break;
@@ -1074,7 +1074,7 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session,
if (get_user(val, (int __user *) arg))
break;
ps->flags = val;
- l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: set flags=%d\n",
+ l2tp_info(session, L2TP_MSG_CONTROL, "%s: set flags=%d\n",
session->name, ps->flags);
err = 0;
break;
@@ -1091,7 +1091,7 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session,
if (copy_to_user((void __user *) arg, &stats,
sizeof(stats)))
break;
- l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: get L2TP stats\n",
+ l2tp_info(session, L2TP_MSG_CONTROL, "%s: get L2TP stats\n",
session->name);
err = 0;
break;
@@ -1119,7 +1119,7 @@ static int pppol2tp_tunnel_ioctl(struct l2tp_tunnel *tunnel,
struct sock *sk;
struct pppol2tp_ioc_stats stats;
- l2tp_dbg(tunnel, PPPOL2TP_MSG_CONTROL,
+ l2tp_dbg(tunnel, L2TP_MSG_CONTROL,
"%s: pppol2tp_tunnel_ioctl(cmd=%#x, arg=%#lx)\n",
tunnel->name, cmd, arg);
@@ -1155,7 +1155,7 @@ static int pppol2tp_tunnel_ioctl(struct l2tp_tunnel *tunnel,
err = -EFAULT;
break;
}
- l2tp_info(tunnel, PPPOL2TP_MSG_CONTROL, "%s: get L2TP stats\n",
+ l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: get L2TP stats\n",
tunnel->name);
err = 0;
break;
@@ -1245,7 +1245,7 @@ static int pppol2tp_tunnel_setsockopt(struct sock *sk,
switch (optname) {
case PPPOL2TP_SO_DEBUG:
tunnel->debug = val;
- l2tp_info(tunnel, PPPOL2TP_MSG_CONTROL, "%s: set debug=%x\n",
+ l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: set debug=%x\n",
tunnel->name, tunnel->debug);
break;
@@ -1273,7 +1273,7 @@ static int pppol2tp_session_setsockopt(struct sock *sk,
break;
}
session->recv_seq = !!val;
- l2tp_info(session, PPPOL2TP_MSG_CONTROL,
+ l2tp_info(session, L2TP_MSG_CONTROL,
"%s: set recv_seq=%d\n",
session->name, session->recv_seq);
break;
@@ -1291,7 +1291,7 @@ static int pppol2tp_session_setsockopt(struct sock *sk,
PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
}
l2tp_session_set_header_len(session, session->tunnel->version);
- l2tp_info(session, PPPOL2TP_MSG_CONTROL,
+ l2tp_info(session, L2TP_MSG_CONTROL,
"%s: set send_seq=%d\n",
session->name, session->send_seq);
break;
@@ -1302,20 +1302,20 @@ static int pppol2tp_session_setsockopt(struct sock *sk,
break;
}
session->lns_mode = !!val;
- l2tp_info(session, PPPOL2TP_MSG_CONTROL,
+ l2tp_info(session, L2TP_MSG_CONTROL,
"%s: set lns_mode=%d\n",
session->name, session->lns_mode);
break;
case PPPOL2TP_SO_DEBUG:
session->debug = val;
- l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: set debug=%x\n",
+ l2tp_info(session, L2TP_MSG_CONTROL, "%s: set debug=%x\n",
session->name, session->debug);
break;
case PPPOL2TP_SO_REORDERTO:
session->reorder_timeout = msecs_to_jiffies(val);
- l2tp_info(session, PPPOL2TP_MSG_CONTROL,
+ l2tp_info(session, L2TP_MSG_CONTROL,
"%s: set reorder_timeout=%d\n",
session->name, session->reorder_timeout);
break;
@@ -1396,7 +1396,7 @@ static int pppol2tp_tunnel_getsockopt(struct sock *sk,
switch (optname) {
case PPPOL2TP_SO_DEBUG:
*val = tunnel->debug;
- l2tp_info(tunnel, PPPOL2TP_MSG_CONTROL, "%s: get debug=%x\n",
+ l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: get debug=%x\n",
tunnel->name, tunnel->debug);
break;
@@ -1419,31 +1419,31 @@ static int pppol2tp_session_getsockopt(struct sock *sk,
switch (optname) {
case PPPOL2TP_SO_RECVSEQ:
*val = session->recv_seq;
- l2tp_info(session, PPPOL2TP_MSG_CONTROL,
+ l2tp_info(session, L2TP_MSG_CONTROL,
"%s: get recv_seq=%d\n", session->name, *val);
break;
case PPPOL2TP_SO_SENDSEQ:
*val = session->send_seq;
- l2tp_info(session, PPPOL2TP_MSG_CONTROL,
+ l2tp_info(session, L2TP_MSG_CONTROL,
"%s: get send_seq=%d\n", session->name, *val);
break;
case PPPOL2TP_SO_LNSMODE:
*val = session->lns_mode;
- l2tp_info(session, PPPOL2TP_MSG_CONTROL,
+ l2tp_info(session, L2TP_MSG_CONTROL,
"%s: get lns_mode=%d\n", session->name, *val);
break;
case PPPOL2TP_SO_DEBUG:
*val = session->debug;
- l2tp_info(session, PPPOL2TP_MSG_CONTROL, "%s: get debug=%d\n",
+ l2tp_info(session, L2TP_MSG_CONTROL, "%s: get debug=%d\n",
session->name, *val);
break;
case PPPOL2TP_SO_REORDERTO:
*val = (int) jiffies_to_msecs(session->reorder_timeout);
- l2tp_info(session, PPPOL2TP_MSG_CONTROL,
+ l2tp_info(session, L2TP_MSG_CONTROL,
"%s: get reorder_timeout=%d\n", session->name, *val);
break;
--
2.10.2
^ 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