* Re: Repeating "unregister_netdevice: waiting for lo to become free" caused by upstream 76da0704507bb ("ipv6: only call ip6_route_dev_notify() once for NETDEV_UNREGISTER")
From: Rafał Miłecki @ 2018-04-25 14:16 UTC (permalink / raw)
To: WANG Cong, David S. Miller, Alexey Kuznetsov, Hideaki YOSHIFUJI,
Network Development, jeffy, David Ahern, Khlebnikov
Cc: Greg Kroah-Hartman, Stable, Dan Streetman, Dan Streetman
In-Reply-To: <CACna6rwXW1LZdjpd2yc2_Gt=8M1n3aTF7_ZPGi01KVfwqxpWCQ@mail.gmail.com>
On 23.04.2018 15:08, Rafał Miłecki wrote:
> I've just updated my kernel 4.4.x and noticed a regression. Bisecting
> pointed me to the commit 2417da3f4d6bc ("ipv6: only call
> ip6_route_dev_notify() once for NETDEV_UNREGISTER") [0] which is
> backport of upstream 76da0704507bb. That backported commit has
> appeared in a 4.4.103.
>
> I use OpenWrt/LEDE [1] distribution and LXC [2] 1.1.5. After stopping
> a container I start getting these messages:
> [ 229.419188] unregister_netdevice: waiting for lo to become free. Usage count = 1
> [ 239.660408] unregister_netdevice: waiting for lo to become free. Usage count = 1
> [ 249.839189] unregister_netdevice: waiting for lo to become free. Usage count = 1
> (...)
>
> Trying to start LXC nevertheless results in lxc-start command hang
> around network configuration. Trying to query LXC state afterwards
> results in a lxc-info command hang too.
>
> I tried Googling for this issue and found similar reports:
> https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1729637
> https://github.com/fnproject/fn/issues/686
> https://lime-technology.com/forums/topic/66863-kernelunregister_netdevice-waiting-for-lo-to-become-free-usage-count-1/
> all of them related to the Docker, which is probably a similar use
> case to the LXC.
>
> I couldn't find any reference to commit 76da0704507bb that could
> suggest fixing the problem I'm seeing.
>
> Does anyone have an idea what is the issue I'm seeing about? Or even
> better, how to fix it? Can I provide any additional info that would
> help?
>
>
> [0] https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable.git/commit/?h=linux-4.4.y&id=2417da3f4d6bc4fc6c77f613f0e2264090892aa5
> [1] https://openwrt.org/
> [2] https://linuxcontainers.org/
Today I tried 4.14.34 to see if that helps. Unfortunately it doesn't. I
still experience the same problem.
From reading various reports regarding that "unregister_netdevice:
waiting for lo to become free" message it appears the problem is caused
by a leaking dst refcnt somewhere in the kernel code.
I found links to few commit fixing leaks at various places:
4a31a6b19f9dd ("sctp: fix dst refcnt leak in sctp_v4_get_dst")
957d761cf91cd ("sctp: fix dst refcnt leak in sctp_v6_get_dst()")
4ee806d51176b ("net: tcp: close sock if net namespace is exiting")
d747a7a51b009 ("tcp: reset sk_rx_dst in tcp_disconnect()")
751eb6b6042a5 ("ipv6: addrconf: fix dev refcont leak when DAD failed")
All above patches are present in the linux-v4.4.y and are part of kernel
4.4.124 I use. So it seems I'm facing yet another dst refcnt leak.
Could commit 2417da3f4d6bc ("ipv6: only call ip6_route_dev_notify() once
for NETDEV_UNREGISTER") introduce a new dst refcnt leak? Or does it only
expost existing one?
^ permalink raw reply
* [PATCH bpf-next] bpf: fix xdp_generic for bpf_adjust_tail usecase
From: Nikita V. Shirokov @ 2018-04-25 14:15 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann, David S . Miller
Cc: netdev, Nikita V. Shirokov
when bpf_adjust_tail was introduced for generic xdp, it changed skb's tail
pointer, so it was pointing to the new "end of the packet". however skb's
len field wasn't properly modified, so on the wire ethernet frame had
original (or even bigger, if adjust_head was used) size. this diff is fixing
this.
Fixes: 198d83bb3 (" bpf: make generic xdp compatible w/
bpf_xdp_adjust_tail")
Signed-off-by: Nikita V. Shirokov <tehnerd@tehnerd.com>
---
Notes:
original tests missed this because it looks like tap interface
ignores incorrect ethernet FCS (all tests were done in VM)
and even w/ missaligned l3 and l2 lengths, kernel still were
accepting this ICMP packet
output was generated w/ bpf_adjust_tail prog from samples
before this fix (see lengths field of the ethernet layer):
tehnerd@maindev:~$ sudo tcpdump -ni tap0 icmp -vvv -eee
tcpdump: listening on tap0, link-type EN10MB (Ethernet), capture size 262144 bytes
06:38:15.546782 52:54:00:12:34:57 > 12:0e:a3:cc:78:b8, ethertype IPv4 (0x0800), length 1454: (tos 0x0, ttl 64, id 0, offset 0, flags [none], proto ICMP (1), length 112)
172.16.0.2 > 172.16.0.1: ICMP 172.16.0.2 unreachable - need to frag (mtu 586), length 92
(tos 0x0, ttl 64, id 48021, offset 0, flags [DF], proto TCP (6), length 1412)
172.16.0.1.50916 > 172.16.0.2.22: Flags [P.], seq 427401155:427402515, ack 3567613893, win 229, options [nop,nop,TS val 1287434011 ecr 2176566223], length 1360
after:
tehnerd@maindev:~$ sudo tcpdump -ni tap0 icmp -vvv -eee
tcpdump: listening on tap0, link-type EN10MB (Ethernet), capture size 262144 bytes
06:47:37.226843 52:54:00:12:34:57 > 32:45:9f:69:35:ba, ethertype IPv4 (0x0800), length 126: (tos 0x0, ttl 64, id 0, offset 0, flags [none], proto ICMP (1), length 112)
172.16.0.2 > 172.16.0.1: ICMP 172.16.0.2 unreachable - need to frag (mtu 586), length 92
(tos 0x0, ttl 64, id 29964, offset 0, flags [DF], proto TCP (6), length 1412)
172.16.0.1.50918 > 172.16.0.2.22: Flags [P.], seq 14171614:14172974, ack 1433043471, win 229, options [nop,nop,TS val 1287995744 ecr 3312743811], length 1360
net/core/dev.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/net/core/dev.c b/net/core/dev.c
index c624a04dad1f..8f8931b93140 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4057,8 +4057,10 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
* pckt.
*/
off = orig_data_end - xdp.data_end;
- if (off != 0)
+ if (off != 0) {
skb_set_tail_pointer(skb, xdp.data_end - xdp.data);
+ skb->len -= off;
+ }
switch (act) {
case XDP_REDIRECT:
--
2.15.1
^ permalink raw reply related
* Re: [PATCH bpf-next] bpf: Allow bpf_jit_enable = 2 with BPF_JIT_ALWAYS_ON config
From: Alexei Starovoitov @ 2018-04-25 14:14 UTC (permalink / raw)
To: Leo Yan
Cc: Daniel Borkmann, David S. Miller, Alexei Starovoitov,
Kirill Tkhai, netdev, linux-kernel
In-Reply-To: <20180425092547.GA24401@leoy-ThinkPad-X240s>
On Wed, Apr 25, 2018 at 05:25:47PM +0800, Leo Yan wrote:
>
> If we have concern for security issue, should we remove support for
> 'bpf_jit_enable = 2' and modify the doc to reflect this change?
I suggest to fix the doc.
^ permalink raw reply
* Re: [RFC bpf] bpf, x64: fix JIT emission for dead code
From: Alexei Starovoitov @ 2018-04-25 14:12 UTC (permalink / raw)
To: Gianluca Borello; +Cc: netdev, daniel, ast
In-Reply-To: <20180425054216.48961-1-g.borello@gmail.com>
On Wed, Apr 25, 2018 at 05:42:16AM +0000, Gianluca Borello wrote:
> Commit 2a5418a13fcf ("bpf: improve dead code sanitizing") replaced dead
> code with a series of ja-1 instructions, for safety. That made JIT
> compilation much more complex for some BPF programs. One instance of such
> programs is, for example:
>
> bool flag = false
> ...
> /* A bunch of other code */
> ...
> if (flag)
> do_something()
>
> In some cases llvm is not able to remove at compile time the code for
> do_something(), so the generated BPF program ends up with a large amount
> of dead instructions. In one specific real life example, there are two
> series of ~500 and ~1000 dead instructions in the program. When the
> verifier replaces them with a series of ja-1 instructions, it causes an
> interesting behavior at JIT time.
>
> During the first pass, since all the instructions are estimated at 64
> bytes, the ja-1 instructions end up being translated as 5 bytes JMP
> instructions (0xE9), since the jump offsets become increasingly large (>
> 127) as each instruction gets discovered to be 5 bytes instead of the
> estimated 64.
>
> Starting from the second pass, the first N instructions of the ja-1
> sequence get translated into 2 bytes JMPs (0xEB) because the jump offsets
> become <= 127 this time. In particular, N is defined as roughly 127 / (5
> - 2) ~= 42. So, each further pass will make the subsequent N JMP
> instructions shrink from 5 to 2 bytes, making the image shrink every time.
> This means that in order to have the entire program converge, there need
> to be, in the real example above, at least ~1000 / 42 ~= 24 passes just
> for translating the dead code. If we add this number to the passes needed
> to translate the other non dead code, it brings such program to 40+
> passes, and JIT doesn't complete. Ultimately the userspace loader fails
> because such BPF program was supposed to be part of a prog array owner
> being JITed.
>
> While it is certainly possible to try to refactor such programs to help
> the compiler remove dead code, the behavior is not really intuitive and it
> puts further burden on the BPF developer who is not expecting such
> behavior. To make things worse, such programs are working just fine in all
> the kernel releases prior to the ja-1 fix.
>
> A possible approach to mitigate this behavior consists into noticing that
> for ja-1 instructions we don't really need to rely on the estimated size
> of the previous and current instructions, we know that a -1 BPF jump
> offset can be safely translated into a 0xEB instruction with a jump offset
> of -2.
>
> Such fix brings the BPF program in the previous example to complete again
> in ~9 passes.
>
> Fixes: 2a5418a13fcf ("bpf: improve dead code sanitizing")
> Signed-off-by: Gianluca Borello <g.borello@gmail.com>
> ---
> Hi
>
> Posting this as RFC since I just wanted to report this potential bug and
> propose a possible fix, although I'm not sure if:
>
> 1) There might be a better fix on the JIT side
> 2) We might want to replace the ja-1 instructions with something else
> 3) We might want to ignore this issue
>
> If we choose option 3, I'd just like to point out that this caused a real
> regression on a couple BPF programs that are part of a larger collection
> of programs that used to work fine on 4.15 and I recently found broken
> in 4.16, so there would be some value in somehow addressing this.
>
> Thanks
>
> arch/x86/net/bpf_jit_comp.c | 12 +++++++++++-
> 1 file changed, 11 insertions(+), 1 deletion(-)
>
> diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
> index b725154182cc..abce27ceb411 100644
> --- a/arch/x86/net/bpf_jit_comp.c
> +++ b/arch/x86/net/bpf_jit_comp.c
> @@ -1027,7 +1027,17 @@ xadd: if (is_imm8(insn->off))
> break;
>
> case BPF_JMP | BPF_JA:
> - jmp_offset = addrs[i + insn->off] - addrs[i];
> + if (insn->off == -1)
> + /* -1 jmp instructions will always jump
> + * backwards two bytes. Explicitly handling
> + * this case avoids wasting too many passes
> + * when there are long sequences of replaced
> + * dead code.
> + */
> + jmp_offset = -2;
> + else
> + jmp_offset = addrs[i + insn->off] - addrs[i];
> +
Impressive analysis and fix. Thank you Gianluca.
Acked-by: Alexei Starovoitov <ast@kernel.org>
^ permalink raw reply
* Re: [PATCH] rds: ib: Fix missing call to rds_ib_dev_put in rds_ib_setup_qp
From: Håkon Bugge @ 2018-04-25 13:48 UTC (permalink / raw)
To: Dag Moxnes
Cc: Santosh Shilimkar, David S. Miller, netdev, OFED mailing list,
rds-devel, linux-kernel
In-Reply-To: <1524655321-8379-1-git-send-email-dag.moxnes@oracle.com>
> On 25 Apr 2018, at 13:22, Dag Moxnes <dag.moxnes@oracle.com> wrote:
>
> The function rds_ib_setup_qp is calling rds_ib_get_client_data and
> should correspondingly call rds_ib_dev_put. This call was lost in
> the non-error path with the introduction of error handling done in
> commit 3b12f73a5c29 ("rds: ib: add error handle")
>
> Signed-off-by: Dag Moxnes <dag.moxnes@oracle.com>
Reviewed-by: Håkon Bugge <haakon.bugge@oracle.com>
Thxs, Håkon
> ---
> net/rds/ib_cm.c | 3 ++-
> 1 files changed, 2 insertions(+), 1 deletions(-)
>
> diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
> index eea1d86..13b38ad 100644
> --- a/net/rds/ib_cm.c
> +++ b/net/rds/ib_cm.c
> @@ -547,7 +547,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
> rdsdebug("conn %p pd %p cq %p %p\n", conn, ic->i_pd,
> ic->i_send_cq, ic->i_recv_cq);
>
> - return ret;
> + goto out;
>
> sends_out:
> vfree(ic->i_sends);
> @@ -572,6 +572,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
> ic->i_send_cq = NULL;
> rds_ibdev_out:
> rds_ib_remove_conn(rds_ibdev, conn);
> +out:
> rds_ib_dev_put(rds_ibdev);
>
> return ret;
> --
> 1.7.1
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH ipruote2-next v4] Add support for cake qdisc
From: Toke Høiland-Jørgensen @ 2018-04-25 13:42 UTC (permalink / raw)
To: netdev; +Cc: cake, Toke Høiland-Jørgensen, Dave Taht
In-Reply-To: <20180425134249.21300-1-toke@toke.dk>
sch_cake is intended to squeeze the most bandwidth and latency out of even
the slowest ISP links and routers, while presenting an API simple enough
that even an ISP can configure it.
Example of use on a cable ISP uplink:
tc qdisc add dev eth0 cake bandwidth 20Mbit nat docsis ack-filter
To shape a cable download link (ifb and tc-mirred setup elided)
tc qdisc add dev ifb0 cake bandwidth 200mbit nat docsis ingress wash besteffort
Cake is filled with:
* A hybrid Codel/Blue AQM algorithm, "Cobalt", tied to an FQ_Codel
derived Flow Queuing system, which autoconfigures based on the bandwidth.
* A novel "triple-isolate" mode (the default) which balances per-host
and per-flow FQ even through NAT.
* An deficit based shaper, that can also be used in an unlimited mode.
* 8 way set associative hashing to reduce flow collisions to a minimum.
* A reasonable interpretation of various diffserv latency/loss tradeoffs.
* Support for zeroing diffserv markings for entering and exiting traffic.
* Support for interacting well with Docsis 3.0 shaper framing.
* Support for DSL framing types and shapers.
* Support for ack filtering.
* Extensive statistics for measuring, loss, ecn markings, latency variation.
Various versions baking have been available as an out of tree build for
kernel versions going back to 3.10, as the embedded router world has been
running a few years behind mainline Linux. A stable version has been
generally available on lede-17.01 and later.
sch_cake replaces a combination of iptables, tc filter, htb and fq_codel
in the sqm-scripts, with sane defaults and vastly simpler configuration.
Cake's principal author is Jonathan Morton, with contributions from
Kevin Darbyshire-Bryant, Toke Høiland-Jørgensen, Sebastian Moeller,
Ryan Mounce, Guido Sarducci, Dean Scarff, Nils Andreas Svee, Dave Täht,
and Loganaden Velvindron.
Testing from Pete Heist, Georgios Amanakis, and the many other members of
the cake@lists.bufferbloat.net mailing list.
Signed-off-by: Dave Taht <dave.taht@gmail.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
---
Changelog:
v4:
- Switch stats parsing to use nested netlink attributes
- Tweaks to JSON stats output keys
v3:
- Remove accidentally included test flag
v2:
- Updated netlink config ABI
- Remove diffserv-llt mode
- Various tweaks and clean-ups of stats output
man/man8/tc-cake.8 | 632 +++++++++++++++++++++++++++++++++++++
man/man8/tc.8 | 1 +
tc/Makefile | 1 +
tc/q_cake.c | 761 +++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 1395 insertions(+)
create mode 100644 man/man8/tc-cake.8
create mode 100644 tc/q_cake.c
diff --git a/man/man8/tc-cake.8 b/man/man8/tc-cake.8
new file mode 100644
index 00000000..30e41bc9
--- /dev/null
+++ b/man/man8/tc-cake.8
@@ -0,0 +1,632 @@
+.TH CAKE 8 "23 November 2017" "iproute2" "Linux"
+.SH NAME
+CAKE \- Common Applications Kept Enhanced (CAKE)
+.SH SYNOPSIS
+.B tc qdisc ... cake
+.br
+[
+.BR bandwidth
+RATE |
+.BR unlimited*
+|
+.BR autorate_ingress
+]
+.br
+[
+.BR rtt
+TIME |
+.BR datacentre
+|
+.BR lan
+|
+.BR metro
+|
+.BR regional
+|
+.BR internet*
+|
+.BR oceanic
+|
+.BR satellite
+|
+.BR interplanetary
+]
+.br
+[
+.BR besteffort
+|
+.BR diffserv8
+|
+.BR diffserv4
+|
+.BR diffserv3*
+]
+.br
+[
+.BR flowblind
+|
+.BR srchost
+|
+.BR dsthost
+|
+.BR hosts
+|
+.BR flows
+|
+.BR dual-srchost
+|
+.BR dual-dsthost
+|
+.BR triple-isolate*
+]
+.br
+[
+.BR nat
+|
+.BR nonat*
+]
+.br
+[
+.BR wash
+|
+.BR nowash*
+]
+.br
+[
+.BR ack-filter
+|
+.BR ack-filter-aggressive
+|
+.BR no-ack-filter*
+]
+.br
+[
+.BR memlimit
+LIMIT ]
+.br
+[
+.BR ptm
+|
+.BR atm
+|
+.BR noatm*
+]
+.br
+[
+.BR overhead
+N |
+.BR conservative
+|
+.BR raw*
+]
+.br
+[
+.BR mpu
+N ]
+.br
+[
+.BR ingress
+|
+.BR egress*
+]
+.br
+(* marks defaults)
+
+
+.SH DESCRIPTION
+CAKE (Common Applications Kept Enhanced) is a shaping-capable queue discipline
+which uses both AQM and FQ. It combines COBALT, which is an AQM algorithm
+combining Codel and BLUE, a shaper which operates in deficit mode, and a variant
+of DRR++ for flow isolation. 8-way set-associative hashing is used to virtually
+eliminate hash collisions. Priority queuing is available through a simplified
+diffserv implementation. Overhead compensation for various encapsulation
+schemes is tightly integrated.
+
+All settings are optional; the default settings are chosen to be sensible in
+most common deployments. Most people will only need to set the
+.B bandwidth
+parameter to get useful results, but reading the
+.B Overhead Compensation
+and
+.B Round Trip Time
+sections is strongly encouraged.
+
+.SH SHAPER PARAMETERS
+CAKE uses a deficit-mode shaper, which does not exhibit the initial burst
+typical of token-bucket shapers. It will automatically burst precisely as much
+as required to maintain the configured throughput. As such, it is very
+straightforward to configure.
+.PP
+.B unlimited
+(default)
+.br
+ No limit on the bandwidth.
+.PP
+.B bandwidth
+RATE
+.br
+ Set the shaper bandwidth. See
+.BR tc(8)
+or examples below for details of the RATE value.
+.PP
+.B autorate_ingress
+.br
+ Automatic capacity estimation based on traffic arriving at this qdisc.
+This is most likely to be useful with cellular links, which tend to change
+quality randomly. A
+.B bandwidth
+parameter can be used in conjunction to specify an initial estimate. The shaper
+will periodically be set to a bandwidth slightly below the estimated rate. This
+estimator cannot estimate the bandwidth of links downstream of itself.
+
+.SH OVERHEAD COMPENSATION PARAMETERS
+The size of each packet on the wire may differ from that seen by Linux. The
+following parameters allow CAKE to compensate for this difference by internally
+considering each packet to be bigger than Linux informs it. To assist users who
+are not expert network engineers, keywords have been provided to represent a
+number of common link technologies.
+
+.SS Manual Overhead Specification
+.B overhead
+BYTES
+.br
+ Adds BYTES to the size of each packet. BYTES may be negative; values
+between -64 and 256 (inclusive) are accepted.
+.PP
+.B mpu
+BYTES
+.br
+ Rounds each packet (including overhead) up to a minimum length
+BYTES. BYTES may not be negative; values between 0 and 256 (inclusive)
+are accepted.
+.PP
+.B atm
+.br
+ Compensates for ATM cell framing, which is normally found on ADSL links.
+This is performed after the
+.B overhead
+parameter above. ATM uses fixed 53-byte cells, each of which can carry 48 bytes
+payload.
+.PP
+.B ptm
+.br
+ Compensates for PTM encoding, which is normally found on VDSL2 links and
+uses a 64b/65b encoding scheme. It is even more efficient to simply
+derate the specified shaper bandwidth by a factor of 64/65 or 0.984. See
+ITU G.992.3 Annex N and IEEE 802.3 Section 61.3 for details.
+.PP
+.B noatm
+.br
+ Disables ATM and PTM compensation.
+
+.SS Failsafe Overhead Keywords
+These two keywords are provided for quick-and-dirty setup. Use them if you
+can't be bothered to read the rest of this section.
+.PP
+.B raw
+(default)
+.br
+ Turns off all overhead compensation in CAKE. The packet size reported
+by Linux will be used directly.
+.PP
+ Other overhead keywords may be added after "raw". The effect of this is
+to make the overhead compensation operate relative to the reported packet size,
+not the underlying IP packet size.
+.PP
+.B conservative
+.br
+ Compensates for more overhead than is likely to occur on any
+widely-deployed link technology.
+.br
+ Equivalent to
+.B overhead 48 atm.
+
+.SS ADSL Overhead Keywords
+Most ADSL modems have a way to check which framing scheme is in use. Often this
+is also specified in the settings document provided by the ISP. The keywords in
+this section are intended to correspond with these sources of information. All
+of them implicitly set the
+.B atm
+flag.
+.PP
+.B pppoa-vcmux
+.br
+ Equivalent to
+.B overhead 10 atm
+.PP
+.B pppoa-llc
+.br
+ Equivalent to
+.B overhead 14 atm
+.PP
+.B pppoe-vcmux
+.br
+ Equivalent to
+.B overhead 32 atm
+.PP
+.B pppoe-llcsnap
+.br
+ Equivalent to
+.B overhead 40 atm
+.PP
+.B bridged-vcmux
+.br
+ Equivalent to
+.B overhead 24 atm
+.PP
+.B bridged-llcsnap
+.br
+ Equivalent to
+.B overhead 32 atm
+.PP
+.B ipoa-vcmux
+.br
+ Equivalent to
+.B overhead 8 atm
+.PP
+.B ipoa-llcsnap
+.br
+ Equivalent to
+.B overhead 16 atm
+.PP
+See also the Ethernet Correction Factors section below.
+
+.SS VDSL2 Overhead Keywords
+ATM was dropped from VDSL2 in favour of PTM, which is a much more
+straightforward framing scheme. Some ISPs retained PPPoE for compatibility with
+their existing back-end systems.
+.PP
+.B pppoe-ptm
+.br
+ Equivalent to
+.B overhead 30 ptm
+
+.br
+ PPPoE: 2B PPP + 6B PPPoE +
+.br
+ ETHERNET: 6B dest MAC + 6B src MAC + 2B ethertype + 4B Frame Check Sequence +
+.br
+ PTM: 1B Start of Frame (S) + 1B End of Frame (Ck) + 2B TC-CRC (PTM-FCS)
+.br
+.PP
+.B bridged-ptm
+.br
+ Equivalent to
+.B overhead 22 ptm
+.br
+ ETHERNET: 6B dest MAC + 6B src MAC + 2B ethertype + 4B Frame Check Sequence +
+.br
+ PTM: 1B Start of Frame (S) + 1B End of Frame (Ck) + 2B TC-CRC (PTM-FCS)
+.br
+.PP
+See also the Ethernet Correction Factors section below.
+
+.SS DOCSIS Cable Overhead Keyword
+DOCSIS is the universal standard for providing Internet service over cable-TV
+infrastructure.
+
+In this case, the actual on-wire overhead is less important than the packet size
+the head-end equipment uses for shaping and metering. This is specified to be
+an Ethernet frame including the CRC (aka FCS).
+.PP
+.B docsis
+.br
+ Equivalent to
+.B overhead 18 mpu 64 noatm
+
+.SS Ethernet Overhead Keywords
+.PP
+.B ethernet
+.br
+ Accounts for Ethernet's preamble, inter-frame gap, and Frame Check
+Sequence. Use this keyword when the bottleneck being shaped for is an
+actual Ethernet cable.
+.br
+ Equivalent to
+.B overhead 38 mpu 84 noatm
+.PP
+.B ether-vlan
+.br
+ Adds 4 bytes to the overhead compensation, accounting for an IEEE 802.1Q
+VLAN header appended to the Ethernet frame header. NB: Some ISPs use one or
+even two of these within PPPoE; this keyword may be repeated as necessary to
+express this.
+
+.SH ROUND TRIP TIME PARAMETERS
+Active Queue Management (AQM) consists of embedding congestion signals in the
+packet flow, which receivers use to instruct senders to slow down when the queue
+is persistently occupied. CAKE uses ECN signalling when available, and packet
+drops otherwise, according to a combination of the Codel and BLUE AQM algorithms
+called COBALT.
+
+Very short latencies require a very rapid AQM response to adequately control
+latency. However, such a rapid response tends to impair throughput when the
+actual RTT is relatively long. CAKE allows specifying the RTT it assumes for
+tuning various parameters. Actual RTTs within an order of magnitude of this
+will generally work well for both throughput and latency management.
+
+At the 'lan' setting and below, the time constants are similar in magnitude to
+the jitter in the Linux kernel itself, so congestion might be signalled
+prematurely. The flows will then become sparse and total throughput reduced,
+leaving little or no back-pressure for the fairness logic to work against. Use
+the "metro" setting for local lans unless you have a custom kernel.
+.PP
+.B rtt
+TIME
+.br
+ Manually specify an RTT.
+.PP
+.B datacentre
+.br
+ For extremely high-performance 10GigE+ networks only. Equivalent to
+.B rtt 100us.
+.PP
+.B lan
+.br
+ For pure Ethernet (not Wi-Fi) networks, at home or in the office. Don't
+use this when shaping for an Internet access link. Equivalent to
+.B rtt 1ms.
+.PP
+.B metro
+.br
+ For traffic mostly within a single city. Equivalent to
+.B rtt 10ms.
+.PP
+.B regional
+.br
+ For traffic mostly within a European-sized country. Equivalent to
+.B rtt 30ms.
+.PP
+.B internet
+(default)
+.br
+ This is suitable for most Internet traffic. Equivalent to
+.B rtt 100ms.
+.PP
+.B oceanic
+.br
+ For Internet traffic with generally above-average latency, such as that
+suffered by Australasian residents. Equivalent to
+.B rtt 300ms.
+.PP
+.B satellite
+.br
+ For traffic via geostationary satellites. Equivalent to
+.B rtt 1000ms.
+.PP
+.B interplanetary
+.br
+ So named because Jupiter is about 1 light-hour from Earth. Use this to
+(almost) completely disable AQM actions. Equivalent to
+.B rtt 3600s.
+
+.SH FLOW ISOLATION PARAMETERS
+With flow isolation enabled, CAKE places packets from different flows into
+different queues, each of which carries its own AQM state. Packets from each
+queue are then delivered fairly, according to a DRR++ algorithm which minimises
+latency for "sparse" flows. CAKE uses a set-associative hashing algorithm to
+minimise flow collisions.
+
+These keywords specify whether fairness based on source address, destination
+address, individual flows, or any combination of those is desired.
+.PP
+.B flowblind
+.br
+ Disables flow isolation; all traffic passes through a single queue for
+each tin.
+.PP
+.B srchost
+.br
+ Flows are defined only by source address. Could be useful on the egress
+path of an ISP backhaul.
+.PP
+.B dsthost
+.br
+ Flows are defined only by destination address. Could be useful on the
+ingress path of an ISP backhaul.
+.PP
+.B hosts
+.br
+ Flows are defined by source-destination host pairs. This is host
+isolation, rather than flow isolation.
+.PP
+.B flows
+.br
+ Flows are defined by the entire 5-tuple of source address, destination
+address, transport protocol, source port and destination port. This is the type
+of flow isolation performed by SFQ and fq_codel.
+.PP
+.B dual-srchost
+.br
+ Flows are defined by the 5-tuple, and fairness is applied first over
+source addresses, then over individual flows. Good for use on egress traffic
+from a LAN to the internet, where it'll prevent any one LAN host from
+monopolising the uplink, regardless of the number of flows they use.
+.PP
+.B dual-dsthost
+.br
+ Flows are defined by the 5-tuple, and fairness is applied first over
+destination addresses, then over individual flows. Good for use on ingress
+traffic to a LAN from the internet, where it'll prevent any one LAN host from
+monopolising the downlink, regardless of the number of flows they use.
+.PP
+.B triple-isolate
+(default)
+.br
+ Flows are defined by the 5-tuple, and fairness is applied over source
+*and* destination addresses intelligently (ie. not merely by host-pairs), and
+also over individual flows. Use this if you're not certain whether to use
+dual-srchost or dual-dsthost; it'll do both jobs at once, preventing any one
+host on *either* side of the link from monopolising it with a large number of
+flows.
+.PP
+.B nat
+.br
+ Instructs Cake to perform a NAT lookup before applying flow-isolation
+rules, to determine the true addresses and port numbers of the packet, to
+improve fairness between hosts "inside" the NAT. This has no practical effect
+in "flowblind" or "flows" modes, or if NAT is performed on a different host.
+.PP
+.B nonat
+(default)
+.br
+ Cake will not perform a NAT lookup. Flow isolation will be performed
+using the addresses and port numbers directly visible to the interface Cake is
+attached to.
+
+.SH PRIORITY QUEUE PARAMETERS
+CAKE can divide traffic into "tins" based on the Diffserv field. Each tin has
+its own independent set of flow-isolation queues, and is serviced based on a WRR
+algorithm. To avoid perverse Diffserv marking incentives, tin weights have a
+"priority sharing" value when bandwidth used by that tin is below a threshold,
+and a lower "bandwidth sharing" value when above. Bandwidth is compared against
+the threshold using the same algorithm as the deficit-mode shaper.
+
+Detailed customisation of tin parameters is not provided. The following presets
+perform all necessary tuning, relative to the current shaper bandwidth and RTT
+settings.
+.PP
+.B besteffort
+.br
+ Disables priority queuing by placing all traffic in one tin.
+.PP
+.B precedence
+.br
+ Enables legacy interpretation of TOS "Precedence" field. Use of this
+preset on the modern Internet is firmly discouraged.
+.PP
+.B diffserv4
+.br
+ Provides a general-purpose Diffserv implementation with four tins:
+.br
+ Bulk (CS1), 6.25% threshold, generally low priority.
+.br
+ Best Effort (general), 100% threshold.
+.br
+ Video (AF4x, AF3x, CS3, AF2x, CS2, TOS4, TOS1), 50% threshold.
+.br
+ Voice (CS7, CS6, EF, VA, CS5, CS4), 25% threshold.
+.PP
+.B diffserv3
+(default)
+.br
+ Provides a simple, general-purpose Diffserv implementation with three tins:
+.br
+ Bulk (CS1), 6.25% threshold, generally low priority.
+.br
+ Best Effort (general), 100% threshold.
+.br
+ Voice (CS7, CS6, EF, VA, TOS4), 25% threshold, reduced Codel interval.
+
+.SH OTHER PARAMETERS
+.B memlimit
+LIMIT
+.br
+ Limit the memory consumed by Cake to LIMIT bytes. Note that this does
+not translate directly to queue size (so do not size this based on bandwidth
+delay product considerations, but rather on worst case acceptable memory
+consumption), as there is some overhead in the data structures containing the
+packets, especially for small packets.
+
+ By default, the limit is calculated based on the bandwidth and RTT
+settings.
+
+.PP
+.B wash
+
+.br
+ Traffic entering your diffserv domain is frequently mis-marked in
+transit from the perspective of your network, and traffic exiting yours may be
+mis-marked from the perspective of the transiting provider.
+
+Apply the wash option to clear all extra diffserv (but not ECN bits), after
+priority queuing has taken place.
+
+If you are shaping inbound, and cannot trust the diffserv markings (as is the
+case for Comcast Cable, among others), it is best to use a single queue
+"besteffort" mode with wash.
+
+.SH EXAMPLES
+# tc qdisc delete root dev eth0
+.br
+# tc qdisc add root dev eth0 cake bandwidth 100Mbit ethernet
+.br
+# tc -s qdisc show dev eth0
+.br
+qdisc cake 1: root refcnt 2 bandwidth 100Mbit diffserv3 triple-isolate rtt 100.0ms noatm overhead 38 mpu 84
+ Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
+ backlog 0b 0p requeues 0
+ memory used: 0b of 5000000b
+ capacity estimate: 100Mbit
+ min/max network layer size: 65535 / 0
+ min/max overhead-adjusted size: 65535 / 0
+ average network hdr offset: 0
+
+ Bulk Best Effort Voice
+ thresh 6250Kbit 100Mbit 25Mbit
+ target 5.0ms 5.0ms 5.0ms
+ interval 100.0ms 100.0ms 100.0ms
+ pk_delay 0us 0us 0us
+ av_delay 0us 0us 0us
+ sp_delay 0us 0us 0us
+ pkts 0 0 0
+ bytes 0 0 0
+ way_inds 0 0 0
+ way_miss 0 0 0
+ way_cols 0 0 0
+ drops 0 0 0
+ marks 0 0 0
+ ack_drop 0 0 0
+ sp_flows 0 0 0
+ bk_flows 0 0 0
+ un_flows 0 0 0
+ max_len 0 0 0
+ quantum 300 1514 762
+
+After some use:
+.br
+# tc -s qdisc show dev eth0
+
+qdisc cake 1: root refcnt 2 bandwidth 100Mbit diffserv3 triple-isolate rtt 100.0ms noatm overhead 38 mpu 84
+ Sent 44709231 bytes 31931 pkt (dropped 45, overlimits 93782 requeues 0)
+ backlog 33308b 22p requeues 0
+ memory used: 292352b of 5000000b
+ capacity estimate: 100Mbit
+ min/max network layer size: 28 / 1500
+ min/max overhead-adjusted size: 84 / 1538
+ average network hdr offset: 14
+
+ Bulk Best Effort Voice
+ thresh 6250Kbit 100Mbit 25Mbit
+ target 5.0ms 5.0ms 5.0ms
+ interval 100.0ms 100.0ms 100.0ms
+ pk_delay 8.7ms 6.9ms 5.0ms
+ av_delay 4.9ms 5.3ms 3.8ms
+ sp_delay 727us 1.4ms 511us
+ pkts 2590 21271 8137
+ bytes 3081804 30302659 11426206
+ way_inds 0 46 0
+ way_miss 3 17 4
+ way_cols 0 0 0
+ drops 20 15 10
+ marks 0 0 0
+ ack_drop 0 0 0
+ sp_flows 2 4 1
+ bk_flows 1 2 1
+ un_flows 0 0 0
+ max_len 1514 1514 1514
+ quantum 300 1514 762
+
+.SH SEE ALSO
+.BR tc (8),
+.BR tc-codel (8),
+.BR tc-fq_codel (8),
+.BR tc-red (8)
+
+.SH AUTHORS
+Cake's principal author is Jonathan Morton, with contributions from
+Tony Ambardar, Kevin Darbyshire-Bryant, Toke Høiland-Jørgensen,
+Sebastian Moeller, Ryan Mounce, Dean Scarff, Nils Andreas Svee, and Dave Täht.
+
+This manual page was written by Loganaden Velvindron. Please report corrections
+to the Linux Networking mailing list <netdev@vger.kernel.org>.
diff --git a/man/man8/tc.8 b/man/man8/tc.8
index 840880fb..716dfec5 100644
--- a/man/man8/tc.8
+++ b/man/man8/tc.8
@@ -795,6 +795,7 @@ was written by Alexey N. Kuznetsov and added in Linux 2.2.
.BR tc-basic (8),
.BR tc-bfifo (8),
.BR tc-bpf (8),
+.BR tc-cake (8),
.BR tc-cbq (8),
.BR tc-cgroup (8),
.BR tc-choke (8),
diff --git a/tc/Makefile b/tc/Makefile
index dfd00267..d9a43568 100644
--- a/tc/Makefile
+++ b/tc/Makefile
@@ -66,6 +66,7 @@ TCMODULES += q_codel.o
TCMODULES += q_fq_codel.o
TCMODULES += q_fq.o
TCMODULES += q_pie.o
+TCMODULES += q_cake.o
TCMODULES += q_hhf.o
TCMODULES += q_clsact.o
TCMODULES += e_bpf.o
diff --git a/tc/q_cake.c b/tc/q_cake.c
new file mode 100644
index 00000000..eab97950
--- /dev/null
+++ b/tc/q_cake.c
@@ -0,0 +1,761 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */
+/*
+ * Common Applications Kept Enhanced -- CAKE
+ *
+ * Copyright (C) 2014-2018 Jonathan Morton <chromatix99@gmail.com>
+ * Copyright (C) 2017-2018 Toke Høiland-Jørgensen <toke@toke.dk>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ * notice, this list of conditions, and the following disclaimer,
+ * without modification.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ * notice, this list of conditions and the following disclaimer in the
+ * documentation and/or other materials provided with the distribution.
+ * 3. The names of the authors may not be used to endorse or promote products
+ * derived from this software without specific prior written permission.
+ *
+ * Alternatively, provided that this notice is retained in full, this
+ * software may be distributed under the terms of the GNU General
+ * Public License ("GPL") version 2, in which case the provisions of the
+ * GPL apply INSTEAD OF those given above.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+ * DAMAGE.
+ *
+ */
+
+#include <stddef.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <syslog.h>
+#include <fcntl.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <string.h>
+#include <inttypes.h>
+
+#include "utils.h"
+#include "tc_util.h"
+
+static void explain(void)
+{
+ fprintf(stderr,
+"Usage: ... cake [ bandwidth RATE | unlimited* | autorate_ingress ]\n"
+" [ rtt TIME | datacentre | lan | metro | regional |\n"
+" internet* | oceanic | satellite | interplanetary ]\n"
+" [ besteffort | diffserv8 | diffserv4 | diffserv3* ]\n"
+" [ flowblind | srchost | dsthost | hosts | flows |\n"
+" dual-srchost | dual-dsthost | triple-isolate* ]\n"
+" [ nat | nonat* ]\n"
+" [ wash | nowash* ]\n"
+" [ ack-filter | ack-filter-aggressive | no-ack-filter* ]\n"
+" [ memlimit LIMIT ]\n"
+" [ ptm | atm | noatm* ] [ overhead N | conservative | raw* ]\n"
+" [ mpu N ] [ ingress | egress* ]\n"
+" (* marks defaults)\n");
+}
+
+static int cake_parse_opt(struct qdisc_util *qu, int argc, char **argv,
+ struct nlmsghdr *n, const char *dev)
+{
+ int unlimited = 0;
+ unsigned bandwidth = 0;
+ unsigned interval = 0;
+ unsigned target = 0;
+ unsigned diffserv = 0;
+ unsigned memlimit = 0;
+ int overhead = 0;
+ bool overhead_set = false;
+ bool overhead_override = false;
+ int mpu = 0;
+ int flowmode = -1;
+ int nat = -1;
+ int atm = -1;
+ int autorate = -1;
+ int wash = -1;
+ int ingress = -1;
+ int ack_filter = -1;
+ struct rtattr *tail;
+
+ while (argc > 0) {
+ if (strcmp(*argv, "bandwidth") == 0) {
+ NEXT_ARG();
+ if (get_rate(&bandwidth, *argv)) {
+ fprintf(stderr, "Illegal \"bandwidth\"\n");
+ return -1;
+ }
+ unlimited = 0;
+ autorate = 0;
+ } else if (strcmp(*argv, "unlimited") == 0) {
+ bandwidth = 0;
+ unlimited = 1;
+ autorate = 0;
+ } else if (strcmp(*argv, "autorate_ingress") == 0) {
+ autorate = 1;
+
+ } else if (strcmp(*argv, "rtt") == 0) {
+ NEXT_ARG();
+ if (get_time(&interval, *argv)) {
+ fprintf(stderr, "Illegal \"rtt\"\n");
+ return -1;
+ }
+ target = interval / 20;
+ if(!target)
+ target = 1;
+ } else if (strcmp(*argv, "datacentre") == 0) {
+ interval = 100;
+ target = 5;
+ } else if (strcmp(*argv, "lan") == 0) {
+ interval = 1000;
+ target = 50;
+ } else if (strcmp(*argv, "metro") == 0) {
+ interval = 10000;
+ target = 500;
+ } else if (strcmp(*argv, "regional") == 0) {
+ interval = 30000;
+ target = 1500;
+ } else if (strcmp(*argv, "internet") == 0) {
+ interval = 100000;
+ target = 5000;
+ } else if (strcmp(*argv, "oceanic") == 0) {
+ interval = 300000;
+ target = 15000;
+ } else if (strcmp(*argv, "satellite") == 0) {
+ interval = 1000000;
+ target = 50000;
+ } else if (strcmp(*argv, "interplanetary") == 0) {
+ interval = 1000000000;
+ target = 50000000;
+
+ } else if (strcmp(*argv, "besteffort") == 0) {
+ diffserv = CAKE_DIFFSERV_BESTEFFORT;
+ } else if (strcmp(*argv, "precedence") == 0) {
+ diffserv = CAKE_DIFFSERV_PRECEDENCE;
+ } else if (strcmp(*argv, "diffserv8") == 0) {
+ diffserv = CAKE_DIFFSERV_DIFFSERV8;
+ } else if (strcmp(*argv, "diffserv4") == 0) {
+ diffserv = CAKE_DIFFSERV_DIFFSERV4;
+ } else if (strcmp(*argv, "diffserv") == 0) {
+ diffserv = CAKE_DIFFSERV_DIFFSERV4;
+ } else if (strcmp(*argv, "diffserv3") == 0) {
+ diffserv = CAKE_DIFFSERV_DIFFSERV3;
+
+ } else if (strcmp(*argv, "nowash") == 0) {
+ wash = 0;
+ } else if (strcmp(*argv, "wash") == 0) {
+ wash = 1;
+
+ } else if (strcmp(*argv, "flowblind") == 0) {
+ flowmode = CAKE_FLOW_NONE;
+ } else if (strcmp(*argv, "srchost") == 0) {
+ flowmode = CAKE_FLOW_SRC_IP;
+ } else if (strcmp(*argv, "dsthost") == 0) {
+ flowmode = CAKE_FLOW_DST_IP;
+ } else if (strcmp(*argv, "hosts") == 0) {
+ flowmode = CAKE_FLOW_HOSTS;
+ } else if (strcmp(*argv, "flows") == 0) {
+ flowmode = CAKE_FLOW_FLOWS;
+ } else if (strcmp(*argv, "dual-srchost") == 0) {
+ flowmode = CAKE_FLOW_DUAL_SRC;
+ } else if (strcmp(*argv, "dual-dsthost") == 0) {
+ flowmode = CAKE_FLOW_DUAL_DST;
+ } else if (strcmp(*argv, "triple-isolate") == 0) {
+ flowmode = CAKE_FLOW_TRIPLE;
+
+ } else if (strcmp(*argv, "nat") == 0) {
+ nat = 1;
+ } else if (strcmp(*argv, "nonat") == 0) {
+ nat = 0;
+
+ } else if (strcmp(*argv, "ptm") == 0) {
+ atm = CAKE_ATM_PTM;
+ } else if (strcmp(*argv, "atm") == 0) {
+ atm = CAKE_ATM_ATM;
+ } else if (strcmp(*argv, "noatm") == 0) {
+ atm = CAKE_ATM_NONE;
+
+ } else if (strcmp(*argv, "raw") == 0) {
+ atm = CAKE_ATM_NONE;
+ overhead = 0;
+ overhead_set = true;
+ overhead_override = true;
+ } else if (strcmp(*argv, "conservative") == 0) {
+ /*
+ * Deliberately over-estimate overhead:
+ * one whole ATM cell plus ATM framing.
+ * A safe choice if the actual overhead is unknown.
+ */
+ atm = CAKE_ATM_ATM;
+ overhead = 48;
+ overhead_set = true;
+
+ /* Various ADSL framing schemes, all over ATM cells */
+ } else if (strcmp(*argv, "ipoa-vcmux") == 0) {
+ atm = CAKE_ATM_ATM;
+ overhead += 8;
+ overhead_set = true;
+ } else if (strcmp(*argv, "ipoa-llcsnap") == 0) {
+ atm = CAKE_ATM_ATM;
+ overhead += 16;
+ overhead_set = true;
+ } else if (strcmp(*argv, "bridged-vcmux") == 0) {
+ atm = CAKE_ATM_ATM;
+ overhead += 24;
+ overhead_set = true;
+ } else if (strcmp(*argv, "bridged-llcsnap") == 0) {
+ atm = CAKE_ATM_ATM;
+ overhead += 32;
+ overhead_set = true;
+ } else if (strcmp(*argv, "pppoa-vcmux") == 0) {
+ atm = CAKE_ATM_ATM;
+ overhead += 10;
+ overhead_set = true;
+ } else if (strcmp(*argv, "pppoa-llc") == 0) {
+ atm = CAKE_ATM_ATM;
+ overhead += 14;
+ overhead_set = true;
+ } else if (strcmp(*argv, "pppoe-vcmux") == 0) {
+ atm = CAKE_ATM_ATM;
+ overhead += 32;
+ overhead_set = true;
+ } else if (strcmp(*argv, "pppoe-llcsnap") == 0) {
+ atm = CAKE_ATM_ATM;
+ overhead += 40;
+ overhead_set = true;
+
+ /* Typical VDSL2 framing schemes, both over PTM */
+ /* PTM has 64b/65b coding which absorbs some bandwidth */
+ } else if (strcmp(*argv, "pppoe-ptm") == 0) {
+ /* 2B PPP + 6B PPPoE + 6B dest MAC + 6B src MAC
+ * + 2B ethertype + 4B Frame Check Sequence
+ * + 1B Start of Frame (S) + 1B End of Frame (Ck)
+ * + 2B TC-CRC (PTM-FCS) = 30B
+ */
+ atm = CAKE_ATM_PTM;
+ overhead += 30;
+ overhead_set = true;
+ } else if (strcmp(*argv, "bridged-ptm") == 0) {
+ /* 6B dest MAC + 6B src MAC + 2B ethertype
+ * + 4B Frame Check Sequence
+ * + 1B Start of Frame (S) + 1B End of Frame (Ck)
+ * + 2B TC-CRC (PTM-FCS) = 22B
+ */
+ atm = CAKE_ATM_PTM;
+ overhead += 22;
+ overhead_set = true;
+
+ } else if (strcmp(*argv, "via-ethernet") == 0) {
+ /*
+ * We used to use this flag to manually compensate for
+ * Linux including the Ethernet header on Ethernet-type
+ * interfaces, but not on IP-type interfaces.
+ *
+ * It is no longer needed, because Cake now adjusts for
+ * that automatically, and is thus ignored.
+ *
+ * It would be deleted entirely, but it appears in the
+ * stats output when the automatic compensation is
+ * active.
+ */
+
+ } else if (strcmp(*argv, "ethernet") == 0) {
+ /* ethernet pre-amble & interframe gap & FCS
+ * you may need to add vlan tag */
+ overhead += 38;
+ overhead_set = true;
+ mpu = 84;
+
+ /* Additional Ethernet-related overhead used by some ISPs */
+ } else if (strcmp(*argv, "ether-vlan") == 0) {
+ /* 802.1q VLAN tag - may be repeated */
+ overhead += 4;
+ overhead_set = true;
+
+ /*
+ * DOCSIS cable shapers account for Ethernet frame with FCS,
+ * but not interframe gap or preamble.
+ */
+ } else if (strcmp(*argv, "docsis") == 0) {
+ atm = CAKE_ATM_NONE;
+ overhead += 18;
+ overhead_set = true;
+ mpu = 64;
+
+ } else if (strcmp(*argv, "overhead") == 0) {
+ char* p = NULL;
+ NEXT_ARG();
+ overhead = strtol(*argv, &p, 10);
+ if(!p || *p || !*argv || overhead < -64 || overhead > 256) {
+ fprintf(stderr, "Illegal \"overhead\", valid range is -64 to 256\\n");
+ return -1;
+ }
+ overhead_set = true;
+
+ } else if (strcmp(*argv, "mpu") == 0) {
+ char* p = NULL;
+ NEXT_ARG();
+ mpu = strtol(*argv, &p, 10);
+ if(!p || *p || !*argv || mpu < 0 || mpu > 256) {
+ fprintf(stderr, "Illegal \"mpu\", valid range is 0 to 256\\n");
+ return -1;
+ }
+
+ } else if (strcmp(*argv, "ingress") == 0) {
+ ingress = 1;
+ } else if (strcmp(*argv, "egress") == 0) {
+ ingress = 0;
+
+ } else if (strcmp(*argv, "no-ack-filter") == 0) {
+ ack_filter = CAKE_ACK_NONE;
+ } else if (strcmp(*argv, "ack-filter") == 0) {
+ ack_filter = CAKE_ACK_FILTER;
+ } else if (strcmp(*argv, "ack-filter-aggressive") == 0) {
+ ack_filter = CAKE_ACK_AGGRESSIVE;
+
+ } else if (strcmp(*argv, "memlimit") == 0) {
+ NEXT_ARG();
+ if(get_size(&memlimit, *argv)) {
+ fprintf(stderr, "Illegal value for \"memlimit\": \"%s\"\n", *argv);
+ return -1;
+ }
+
+ } else if (strcmp(*argv, "help") == 0) {
+ explain();
+ return -1;
+ } else {
+ fprintf(stderr, "What is \"%s\"?\n", *argv);
+ explain();
+ return -1;
+ }
+ argc--; argv++;
+ }
+
+ tail = NLMSG_TAIL(n);
+ addattr_l(n, 1024, TCA_OPTIONS, NULL, 0);
+ if (bandwidth || unlimited)
+ addattr_l(n, 1024, TCA_CAKE_BASE_RATE, &bandwidth, sizeof(bandwidth));
+ if (diffserv)
+ addattr_l(n, 1024, TCA_CAKE_DIFFSERV_MODE, &diffserv, sizeof(diffserv));
+ if (atm != -1)
+ addattr_l(n, 1024, TCA_CAKE_ATM, &atm, sizeof(atm));
+ if (flowmode != -1)
+ addattr_l(n, 1024, TCA_CAKE_FLOW_MODE, &flowmode, sizeof(flowmode));
+ if (overhead_set)
+ addattr_l(n, 1024, TCA_CAKE_OVERHEAD, &overhead, sizeof(overhead));
+ if (overhead_override) {
+ unsigned zero = 0;
+ addattr_l(n, 1024, TCA_CAKE_RAW, &zero, sizeof(zero));
+ }
+ if (mpu > 0)
+ addattr_l(n, 1024, TCA_CAKE_MPU, &mpu, sizeof(mpu));
+ if (interval)
+ addattr_l(n, 1024, TCA_CAKE_RTT, &interval, sizeof(interval));
+ if (target)
+ addattr_l(n, 1024, TCA_CAKE_TARGET, &target, sizeof(target));
+ if (autorate != -1)
+ addattr_l(n, 1024, TCA_CAKE_AUTORATE, &autorate, sizeof(autorate));
+ if (memlimit)
+ addattr_l(n, 1024, TCA_CAKE_MEMORY, &memlimit, sizeof(memlimit));
+ if (nat != -1)
+ addattr_l(n, 1024, TCA_CAKE_NAT, &nat, sizeof(nat));
+ if (wash != -1)
+ addattr_l(n, 1024, TCA_CAKE_WASH, &wash, sizeof(wash));
+ if (ingress != -1)
+ addattr_l(n, 1024, TCA_CAKE_INGRESS, &ingress, sizeof(ingress));
+ if (ack_filter != -1)
+ addattr_l(n, 1024, TCA_CAKE_ACK_FILTER, &ack_filter, sizeof(ack_filter));
+
+ tail->rta_len = (void *) NLMSG_TAIL(n) - (void *) tail;
+ return 0;
+}
+
+
+static int cake_print_opt(struct qdisc_util *qu, FILE *f, struct rtattr *opt)
+{
+ struct rtattr *tb[TCA_CAKE_MAX + 1];
+ unsigned bandwidth = 0;
+ unsigned diffserv = 0;
+ unsigned flowmode = 0;
+ unsigned interval = 0;
+ unsigned memlimit = 0;
+ int overhead = 0;
+ int raw = 0;
+ int mpu = 0;
+ int atm = 0;
+ int nat = 0;
+ int autorate = 0;
+ int wash = 0;
+ int ingress = 0;
+ int ack_filter = 0;
+ SPRINT_BUF(b1);
+ SPRINT_BUF(b2);
+
+ if (opt == NULL)
+ return 0;
+
+ parse_rtattr_nested(tb, TCA_CAKE_MAX, opt);
+
+ if (tb[TCA_CAKE_BASE_RATE] &&
+ RTA_PAYLOAD(tb[TCA_CAKE_BASE_RATE]) >= sizeof(__u32)) {
+ bandwidth = rta_getattr_u32(tb[TCA_CAKE_BASE_RATE]);
+ if(bandwidth) {
+ print_uint(PRINT_JSON, "bandwidth", NULL, bandwidth);
+ print_string(PRINT_FP, NULL, "bandwidth %s ", sprint_rate(bandwidth, b1));
+ } else
+ print_string(PRINT_ANY, "bandwidth", "bandwidth %s ", "unlimited");
+ }
+ if (tb[TCA_CAKE_AUTORATE] &&
+ RTA_PAYLOAD(tb[TCA_CAKE_AUTORATE]) >= sizeof(__u32)) {
+ autorate = rta_getattr_u32(tb[TCA_CAKE_AUTORATE]);
+ if(autorate == 1)
+ print_string(PRINT_ANY, "autorate", "autorate_%s ", "ingress");
+ else if(autorate)
+ print_string(PRINT_ANY, "autorate", "(?autorate?) ", "unknown");
+ }
+ if (tb[TCA_CAKE_DIFFSERV_MODE] &&
+ RTA_PAYLOAD(tb[TCA_CAKE_DIFFSERV_MODE]) >= sizeof(__u32)) {
+ diffserv = rta_getattr_u32(tb[TCA_CAKE_DIFFSERV_MODE]);
+ switch(diffserv) {
+ case CAKE_DIFFSERV_DIFFSERV3:
+ print_string(PRINT_ANY, "diffserv", "%s ", "diffserv3");
+ break;
+ case CAKE_DIFFSERV_DIFFSERV4:
+ print_string(PRINT_ANY, "diffserv", "%s ", "diffserv4");
+ break;
+ case CAKE_DIFFSERV_DIFFSERV8:
+ print_string(PRINT_ANY, "diffserv", "%s ", "diffserv8");
+ break;
+ case CAKE_DIFFSERV_BESTEFFORT:
+ print_string(PRINT_ANY, "diffserv", "%s ", "besteffort");
+ break;
+ case CAKE_DIFFSERV_PRECEDENCE:
+ print_string(PRINT_ANY, "diffserv", "%s ", "precedence");
+ break;
+ default:
+ print_string(PRINT_ANY, "diffserv", "(?diffserv?) ", "unknown");
+ break;
+ };
+ }
+ if (tb[TCA_CAKE_FLOW_MODE] &&
+ RTA_PAYLOAD(tb[TCA_CAKE_FLOW_MODE]) >= sizeof(__u32)) {
+ flowmode = rta_getattr_u32(tb[TCA_CAKE_FLOW_MODE]);
+ switch(flowmode) {
+ case CAKE_FLOW_NONE:
+ print_string(PRINT_ANY, "flowmode", "%s ", "flowblind");
+ break;
+ case CAKE_FLOW_SRC_IP:
+ print_string(PRINT_ANY, "flowmode", "%s ", "srchost");
+ break;
+ case CAKE_FLOW_DST_IP:
+ print_string(PRINT_ANY, "flowmode", "%s ", "dsthost");
+ break;
+ case CAKE_FLOW_HOSTS:
+ print_string(PRINT_ANY, "flowmode", "%s ", "hosts");
+ break;
+ case CAKE_FLOW_FLOWS:
+ print_string(PRINT_ANY, "flowmode", "%s ", "flows");
+ break;
+ case CAKE_FLOW_DUAL_SRC:
+ print_string(PRINT_ANY, "flowmode", "%s ", "dual-srchost");
+ break;
+ case CAKE_FLOW_DUAL_DST:
+ print_string(PRINT_ANY, "flowmode", "%s ", "dual-dsthost");
+ break;
+ case CAKE_FLOW_TRIPLE:
+ print_string(PRINT_ANY, "flowmode", "%s ", "triple-isolate");
+ break;
+ default:
+ print_string(PRINT_ANY, "flowmode", "(?flowmode?) ", "unknown");
+ break;
+ };
+
+ }
+
+ if (tb[TCA_CAKE_NAT] &&
+ RTA_PAYLOAD(tb[TCA_CAKE_NAT]) >= sizeof(__u32)) {
+ nat = rta_getattr_u32(tb[TCA_CAKE_NAT]);
+ }
+
+ if(nat)
+ print_string(PRINT_FP, NULL, "nat ", NULL);
+ print_bool(PRINT_JSON, "nat", NULL, nat);
+
+ if (tb[TCA_CAKE_WASH] &&
+ RTA_PAYLOAD(tb[TCA_CAKE_WASH]) >= sizeof(__u32)) {
+ wash = rta_getattr_u32(tb[TCA_CAKE_WASH]);
+ }
+ if (tb[TCA_CAKE_ATM] &&
+ RTA_PAYLOAD(tb[TCA_CAKE_ATM]) >= sizeof(__u32)) {
+ atm = rta_getattr_u32(tb[TCA_CAKE_ATM]);
+ }
+ if (tb[TCA_CAKE_OVERHEAD] &&
+ RTA_PAYLOAD(tb[TCA_CAKE_OVERHEAD]) >= sizeof(__s32)) {
+ overhead = *(__s32 *) RTA_DATA(tb[TCA_CAKE_OVERHEAD]);
+ }
+ if (tb[TCA_CAKE_MPU] &&
+ RTA_PAYLOAD(tb[TCA_CAKE_MPU]) >= sizeof(__u32)) {
+ mpu = rta_getattr_u32(tb[TCA_CAKE_MPU]);
+ }
+ if (tb[TCA_CAKE_INGRESS] &&
+ RTA_PAYLOAD(tb[TCA_CAKE_INGRESS]) >= sizeof(__u32)) {
+ ingress = rta_getattr_u32(tb[TCA_CAKE_INGRESS]);
+ }
+ if (tb[TCA_CAKE_ACK_FILTER] &&
+ RTA_PAYLOAD(tb[TCA_CAKE_ACK_FILTER]) >= sizeof(__u32)) {
+ ack_filter = rta_getattr_u32(tb[TCA_CAKE_ACK_FILTER]);
+ }
+ if (tb[TCA_CAKE_RAW]) {
+ raw = 1;
+ }
+ if (tb[TCA_CAKE_RTT] &&
+ RTA_PAYLOAD(tb[TCA_CAKE_RTT]) >= sizeof(__u32)) {
+ interval = rta_getattr_u32(tb[TCA_CAKE_RTT]);
+ }
+
+ if (wash)
+ print_string(PRINT_FP, NULL, "wash ", NULL);
+ print_bool(PRINT_JSON, "wash", NULL, wash);
+
+ if (ingress)
+ print_string(PRINT_FP, NULL, "ingress ", NULL);
+ print_bool(PRINT_JSON, "ingress", NULL, ingress);
+
+ if (ack_filter == CAKE_ACK_AGGRESSIVE)
+ print_string(PRINT_ANY, "ack-filter", "ack-filter-%s ", "aggressive");
+ else if (ack_filter == CAKE_ACK_FILTER)
+ print_string(PRINT_ANY, "ack-filter", "ack-filter ", "enabled");
+ else
+ print_string(PRINT_JSON, "ack-filter", NULL, "disabled");
+
+ if (interval)
+ print_string(PRINT_FP, NULL, "rtt %s ", sprint_time(interval, b2));
+ print_uint(PRINT_JSON, "rtt", NULL, interval);
+
+ if (raw)
+ print_string(PRINT_FP, NULL, "raw ", NULL);
+ print_bool(PRINT_JSON, "raw", NULL, raw);
+
+ if (atm == CAKE_ATM_ATM)
+ print_string(PRINT_ANY, "atm", "%s ", "atm");
+ else if (atm == CAKE_ATM_PTM)
+ print_string(PRINT_ANY, "atm", "%s ", "ptm");
+ else if (!raw)
+ print_string(PRINT_ANY, "atm", "%s ", "noatm");
+
+ print_int(PRINT_ANY, "overhead", "overhead %d ", overhead);
+
+ if (mpu)
+ print_uint(PRINT_ANY, "mpu", "mpu %" PRIu64 " ", mpu);
+
+ if (memlimit) {
+ print_uint(PRINT_JSON, "memlimit", NULL, memlimit);
+ print_string(PRINT_FP, NULL, "memlimit %s", sprint_size(memlimit, b1));
+ }
+
+ return 0;
+}
+
+static void cake_print_json_tin(struct rtattr **tstat)
+{
+#define PRINT_TSTAT_JSON(type, name, attr) if (tstat[TCA_CAKE_TIN_STATS_ ## attr]) \
+ print_uint(PRINT_JSON, name, NULL, \
+ rta_getattr_ ## type((struct rtattr *)tstat[TCA_CAKE_TIN_STATS_ ## attr]))
+
+ open_json_object(NULL);
+ PRINT_TSTAT_JSON(u32, "threshold_rate", THRESHOLD_RATE);
+ PRINT_TSTAT_JSON(u32, "target_us", TARGET_US);
+ PRINT_TSTAT_JSON(u32, "interval_us", INTERVAL_US);
+ PRINT_TSTAT_JSON(u32, "peak_delay_us", PEAK_DELAY_US);
+ PRINT_TSTAT_JSON(u32, "avg_delay_us", AVG_DELAY_US);
+ PRINT_TSTAT_JSON(u32, "base_delay_us", BASE_DELAY_US);
+ PRINT_TSTAT_JSON(u32, "sent_packets", SENT_PACKETS);
+ PRINT_TSTAT_JSON(u64, "sent_bytes", SENT_BYTES64);
+ PRINT_TSTAT_JSON(u32, "way_indirect_hits", WAY_INDIRECT_HITS);
+ PRINT_TSTAT_JSON(u32, "way_misses", WAY_MISSES);
+ PRINT_TSTAT_JSON(u32, "way_collisions", WAY_COLLISIONS);
+ PRINT_TSTAT_JSON(u32, "drops", DROPPED_PACKETS);
+ PRINT_TSTAT_JSON(u32, "ecn_mark", ECN_MARKED_PACKETS);
+ PRINT_TSTAT_JSON(u32, "ack_drops", ACKS_DROPPED_PACKETS);
+ PRINT_TSTAT_JSON(u32, "sparse_flows", SPARSE_FLOWS);
+ PRINT_TSTAT_JSON(u32, "bulk_flows", BULK_FLOWS);
+ PRINT_TSTAT_JSON(u32, "unresponsive_flows", UNRESPONSIVE_FLOWS);
+ PRINT_TSTAT_JSON(u32, "max_pkt_len", MAX_SKBLEN);
+ PRINT_TSTAT_JSON(u32, "flow_quantum", FLOW_QUANTUM);
+ close_json_object();
+
+#undef PRINT_TSTAT_JSON
+}
+
+static int cake_print_xstats(struct qdisc_util *qu, FILE *f,
+ struct rtattr *xstats)
+{
+ SPRINT_BUF(b1);
+ struct rtattr *st[TCA_CAKE_STATS_MAX + 1];
+ int i;
+
+ if (xstats == NULL)
+ return 0;
+
+#define GET_STAT_U32(attr) rta_getattr_u32(st[TCA_CAKE_STATS_ ## attr])
+
+ parse_rtattr_nested(st, TCA_CAKE_STATS_MAX, xstats);
+
+ if (st[TCA_CAKE_STATS_MEMORY_USED] &&
+ st[TCA_CAKE_STATS_MEMORY_LIMIT]) {
+ print_string(PRINT_FP, NULL, " memory used: %s",
+ sprint_size(GET_STAT_U32(MEMORY_USED), b1));
+
+ print_string(PRINT_FP, NULL, " of %s\n",
+ sprint_size(GET_STAT_U32(MEMORY_LIMIT), b1));
+
+ print_uint(PRINT_JSON, "memory_used", NULL,
+ GET_STAT_U32(MEMORY_USED));
+ print_uint(PRINT_JSON, "memory_limit", NULL,
+ GET_STAT_U32(MEMORY_LIMIT));
+ }
+
+ if (st[TCA_CAKE_STATS_CAPACITY_ESTIMATE]) {
+ print_string(PRINT_FP, NULL, " capacity estimate: %s\n",
+ sprint_rate(GET_STAT_U32(CAPACITY_ESTIMATE), b1));
+ print_uint(PRINT_JSON, "capacity_estimate", NULL,
+ GET_STAT_U32(CAPACITY_ESTIMATE));
+ }
+
+ if (st[TCA_CAKE_STATS_MIN_NETLEN] &&
+ st[TCA_CAKE_STATS_MAX_NETLEN]) {
+ print_uint(PRINT_ANY, "min_network_size",
+ " min/max network layer size: %12u",
+ GET_STAT_U32(MIN_NETLEN));
+ print_uint(PRINT_ANY, "max_network_size",
+ " /%8u\n", GET_STAT_U32(MAX_NETLEN));
+ }
+
+ if (st[TCA_CAKE_STATS_MIN_ADJLEN] &&
+ st[TCA_CAKE_STATS_MAX_ADJLEN]) {
+ print_uint(PRINT_ANY, "min_adj_size",
+ " min/max overhead-adjusted size: %8u",
+ GET_STAT_U32(MIN_ADJLEN));
+ print_uint(PRINT_ANY, "max_adj_size",
+ " /%8u\n", GET_STAT_U32(MAX_ADJLEN));
+ }
+
+ if (st[TCA_CAKE_STATS_AVG_NETOFF])
+ print_uint(PRINT_ANY, "avg_hdr_offset",
+ " average network hdr offset: %12u\n\n",
+ GET_STAT_U32(AVG_NETOFF));
+
+#undef GET_STAT_U32
+
+ if (st[TCA_CAKE_STATS_TIN_STATS]) {
+ struct rtattr *tins[TC_CAKE_MAX_TINS + 1];
+ struct rtattr *tstat[TC_CAKE_MAX_TINS][TCA_CAKE_TIN_STATS_MAX + 1];
+ int num_tins = 0;
+
+ parse_rtattr_nested(tins, TC_CAKE_MAX_TINS, st[TCA_CAKE_STATS_TIN_STATS]);
+
+ for (i = 1; i <= TC_CAKE_MAX_TINS && tins[i]; i++) {
+ parse_rtattr_nested(tstat[i-1], TCA_CAKE_TIN_STATS_MAX, tins[i]);
+ num_tins++;
+ }
+
+ if (!num_tins)
+ return 0;
+
+ if (is_json_context()) {
+ open_json_array(PRINT_JSON, "tins");
+ for (i = 0; i < num_tins; i++)
+ cake_print_json_tin(tstat[i]);
+ close_json_array(PRINT_JSON, NULL);
+
+ return 0;
+ }
+
+
+ switch(num_tins) {
+ case 3:
+ fprintf(f, " Bulk Best Effort Voice\n");
+ break;
+
+ case 4:
+ fprintf(f, " Bulk Best Effort Video Voice\n");
+ break;
+
+ default:
+ fprintf(f, " ");
+ for(i=0; i < num_tins; i++)
+ fprintf(f, " Tin %u", i);
+ fprintf(f, "\n");
+ };
+
+#define GET_TSTAT(i, attr) (tstat[i][TCA_CAKE_TIN_STATS_ ## attr])
+#define PRINT_TSTAT(name, attr, fmts, val) do { \
+ if (GET_TSTAT(0, attr)) { \
+ fprintf(f, name); \
+ for (i = 0; i < num_tins; i++) \
+ fprintf(f, " %12" fmts, val); \
+ fprintf(f, "\n"); \
+ } \
+ } while (0)
+
+#define SPRINT_TSTAT(pfunc, name, attr) PRINT_TSTAT( \
+ name, attr, "s", sprint_ ## pfunc( \
+ rta_getattr_u32(GET_TSTAT(i, attr)), b1))
+
+#define PRINT_TSTAT_U32(name, attr) PRINT_TSTAT( \
+ name, attr, "u", rta_getattr_u32(GET_TSTAT(i, attr)))
+
+#define PRINT_TSTAT_U64(name, attr) PRINT_TSTAT( \
+ name, attr, "llu", rta_getattr_u64(GET_TSTAT(i, attr)))
+
+ SPRINT_TSTAT(rate, " thresh ", THRESHOLD_RATE);
+ SPRINT_TSTAT(time, " target ", TARGET_US);
+ SPRINT_TSTAT(time, " interval", INTERVAL_US);
+ SPRINT_TSTAT(time, " pk_delay", PEAK_DELAY_US);
+ SPRINT_TSTAT(time, " av_delay", AVG_DELAY_US);
+ SPRINT_TSTAT(time, " sp_delay", BASE_DELAY_US);
+
+ PRINT_TSTAT_U32(" pkts ", SENT_PACKETS);
+ PRINT_TSTAT_U64(" bytes ", SENT_BYTES64);
+
+ PRINT_TSTAT_U32(" way_inds", WAY_INDIRECT_HITS);
+ PRINT_TSTAT_U32(" way_miss", WAY_MISSES);
+ PRINT_TSTAT_U32(" way_cols", WAY_COLLISIONS);
+ PRINT_TSTAT_U32(" drops ", DROPPED_PACKETS);
+ PRINT_TSTAT_U32(" marks ", ECN_MARKED_PACKETS);
+ PRINT_TSTAT_U32(" ack_drop", ACKS_DROPPED_PACKETS);
+ PRINT_TSTAT_U32(" sp_flows", SPARSE_FLOWS);
+ PRINT_TSTAT_U32(" bk_flows", BULK_FLOWS);
+ PRINT_TSTAT_U32(" un_flows", UNRESPONSIVE_FLOWS);
+ PRINT_TSTAT_U32(" max_len ", MAX_SKBLEN);
+ PRINT_TSTAT_U32(" quantum ", FLOW_QUANTUM);
+
+#undef GET_STAT
+#undef PRINT_TSTAT
+#undef SPRINT_TSTAT
+#undef PRINT_TSTAT_U32
+#undef PRINT_TSTAT_U64
+ }
+ return 0;
+}
+
+struct qdisc_util cake_qdisc_util = {
+ .id = "cake",
+ .parse_qopt = cake_parse_opt,
+ .print_qopt = cake_print_opt,
+ .print_xstats = cake_print_xstats,
+};
--
2.17.0
^ permalink raw reply related
* [PATCH net-next v3] Add Common Applications Kept Enhanced (cake) qdisc
From: Toke Høiland-Jørgensen @ 2018-04-25 13:42 UTC (permalink / raw)
To: netdev; +Cc: cake, Toke Høiland-Jørgensen, Dave Taht
sch_cake targets the home router use case and is intended to squeeze the
most bandwidth and latency out of even the slowest ISP links and routers,
while presenting an API simple enough that even an ISP can configure it.
Example of use on a cable ISP uplink:
tc qdisc add dev eth0 cake bandwidth 20Mbit nat docsis ack-filter
To shape a cable download link (ifb and tc-mirred setup elided)
tc qdisc add dev ifb0 cake bandwidth 200mbit nat docsis ingress wash
CAKE is filled with:
* A hybrid Codel/Blue AQM algorithm, "Cobalt", tied to an FQ_Codel
derived Flow Queuing system, which autoconfigures based on the bandwidth.
* A novel "triple-isolate" mode (the default) which balances per-host
and per-flow FQ even through NAT.
* An deficit based shaper, that can also be used in an unlimited mode.
* 8 way set associative hashing to reduce flow collisions to a minimum.
* A reasonable interpretation of various diffserv latency/loss tradeoffs.
* Support for zeroing diffserv markings for entering and exiting traffic.
* Support for interacting well with Docsis 3.0 shaper framing.
* Extensive support for DSL framing types.
* Support for ack filtering.
* Extensive statistics for measuring, loss, ecn markings, latency
variation.
A paper describing the design of CAKE is available at
https://arxiv.org/abs/1804.07617
Various versions baking have been available as an out of tree build for
kernel versions going back to 3.10, as the embedded router world has been
running a few years behind mainline Linux. A stable version has been
generally available on lede-17.01 and later.
sch_cake replaces a combination of iptables, tc filter, htb and fq_codel
in the sqm-scripts, with sane defaults and vastly simpler configuration.
CAKE's principal author is Jonathan Morton, with contributions from
Kevin Darbyshire-Bryant, Toke Høiland-Jørgensen, Sebastian Moeller,
Ryan Mounce, Guido Sarducci, Dean Scarff, Nils Andreas Svee, Dave Täht,
and Loganaden Velvindron.
Testing from Pete Heist, Georgios Amanakis, and the many other members of
the cake@lists.bufferbloat.net mailing list.
tc -s qdisc show dev eth2
qdisc cake 1: root refcnt 2 bandwidth 100Mbit diffserv3 triple-isolate rtt 100.0ms raw overhead 0
Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
memory used: 0b of 5000000b
capacity estimate: 100Mbit
min/max network layer size: 65535 / 0
min/max overhead-adjusted size: 65535 / 0
average network hdr offset: 0
Bulk Best Effort Voice
thresh 6250Kbit 100Mbit 25Mbit
target 5.0ms 5.0ms 5.0ms
interval 100.0ms 100.0ms 100.0ms
pk_delay 0us 0us 0us
av_delay 0us 0us 0us
sp_delay 0us 0us 0us
pkts 0 0 0
bytes 0 0 0
way_inds 0 0 0
way_miss 0 0 0
way_cols 0 0 0
drops 0 0 0
marks 0 0 0
ack_drop 0 0 0
sp_flows 0 0 0
bk_flows 0 0 0
un_flows 0 0 0
max_len 0 0 0
quantum 300 1514 762
Tested-by: Pete Heist <peteheist@gmail.com>
Tested-by: Georgios Amanakis <gamanakis@gmail.com>
Signed-off-by: Dave Taht <dave.taht@gmail.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
---
Changelog:
v3:
- Use IS_REACHABLE() macro to fix compilation when sch_cake is
built-in and conntrack is a module.
- Switch the stats output to use nested netlink attributes instead
of a versioned struct.
- Remove GPL boilerplate.
- Fix array initialisation style.
v2:
- Fix kbuild test bot complaint
- Clean up the netlink ABI
- Fix checkpatch complaints
- A few tweaks to the behaviour of cake based on testing carried out
while writing the paper.
include/uapi/linux/pkt_sched.h | 104 ++
net/sched/Kconfig | 11 +
net/sched/Makefile | 1 +
net/sched/sch_cake.c | 2616 ++++++++++++++++++++++++++++++++
4 files changed, 2732 insertions(+)
create mode 100644 net/sched/sch_cake.c
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 37b5096ae97b..a54474ac8259 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -934,4 +934,108 @@ enum {
#define TCA_CBS_MAX (__TCA_CBS_MAX - 1)
+/* CAKE */
+enum {
+ TCA_CAKE_UNSPEC,
+ TCA_CAKE_BASE_RATE,
+ TCA_CAKE_DIFFSERV_MODE,
+ TCA_CAKE_ATM,
+ TCA_CAKE_FLOW_MODE,
+ TCA_CAKE_OVERHEAD,
+ TCA_CAKE_RTT,
+ TCA_CAKE_TARGET,
+ TCA_CAKE_AUTORATE,
+ TCA_CAKE_MEMORY,
+ TCA_CAKE_NAT,
+ TCA_CAKE_RAW, // was _ETHERNET
+ TCA_CAKE_WASH,
+ TCA_CAKE_MPU,
+ TCA_CAKE_INGRESS,
+ TCA_CAKE_ACK_FILTER,
+ __TCA_CAKE_MAX
+};
+#define TCA_CAKE_MAX (__TCA_CAKE_MAX - 1)
+
+enum {
+ __TCA_CAKE_STATS_INVALID,
+ TCA_CAKE_STATS_CAPACITY_ESTIMATE,
+ TCA_CAKE_STATS_MEMORY_LIMIT,
+ TCA_CAKE_STATS_MEMORY_USED,
+ TCA_CAKE_STATS_AVG_NETOFF,
+ TCA_CAKE_STATS_MIN_NETLEN,
+ TCA_CAKE_STATS_MAX_NETLEN,
+ TCA_CAKE_STATS_MIN_ADJLEN,
+ TCA_CAKE_STATS_MAX_ADJLEN,
+ TCA_CAKE_STATS_TIN_STATS,
+ __TCA_CAKE_STATS_MAX
+};
+#define TCA_CAKE_STATS_MAX (__TCA_CAKE_STATS_MAX - 1)
+
+enum {
+ __TCA_CAKE_TIN_STATS_INVALID,
+ TCA_CAKE_TIN_STATS_PAD,
+ TCA_CAKE_TIN_STATS_SENT_PACKETS,
+ TCA_CAKE_TIN_STATS_SENT_BYTES64,
+ TCA_CAKE_TIN_STATS_DROPPED_PACKETS,
+ TCA_CAKE_TIN_STATS_DROPPED_BYTES64,
+ TCA_CAKE_TIN_STATS_ACKS_DROPPED_PACKETS,
+ TCA_CAKE_TIN_STATS_ACKS_DROPPED_BYTES64,
+ TCA_CAKE_TIN_STATS_ECN_MARKED_PACKETS,
+ TCA_CAKE_TIN_STATS_ECN_MARKED_BYTES64,
+ TCA_CAKE_TIN_STATS_BACKLOG_PACKETS,
+ TCA_CAKE_TIN_STATS_BACKLOG_BYTES64,
+ TCA_CAKE_TIN_STATS_THRESHOLD_RATE,
+ TCA_CAKE_TIN_STATS_TARGET_US,
+ TCA_CAKE_TIN_STATS_INTERVAL_US,
+ TCA_CAKE_TIN_STATS_WAY_INDIRECT_HITS,
+ TCA_CAKE_TIN_STATS_WAY_MISSES,
+ TCA_CAKE_TIN_STATS_WAY_COLLISIONS,
+ TCA_CAKE_TIN_STATS_PEAK_DELAY_US,
+ TCA_CAKE_TIN_STATS_AVG_DELAY_US,
+ TCA_CAKE_TIN_STATS_BASE_DELAY_US,
+ TCA_CAKE_TIN_STATS_SPARSE_FLOWS,
+ TCA_CAKE_TIN_STATS_BULK_FLOWS,
+ TCA_CAKE_TIN_STATS_UNRESPONSIVE_FLOWS,
+ TCA_CAKE_TIN_STATS_MAX_SKBLEN,
+ TCA_CAKE_TIN_STATS_FLOW_QUANTUM,
+ __TCA_CAKE_TIN_STATS_MAX
+};
+#define TCA_CAKE_TIN_STATS_MAX (__TCA_CAKE_TIN_STATS_MAX - 1)
+#define TC_CAKE_MAX_TINS (8)
+
+enum {
+ CAKE_FLOW_NONE = 0,
+ CAKE_FLOW_SRC_IP,
+ CAKE_FLOW_DST_IP,
+ CAKE_FLOW_HOSTS, /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_DST_IP */
+ CAKE_FLOW_FLOWS,
+ CAKE_FLOW_DUAL_SRC, /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_FLOWS */
+ CAKE_FLOW_DUAL_DST, /* = CAKE_FLOW_DST_IP | CAKE_FLOW_FLOWS */
+ CAKE_FLOW_TRIPLE, /* = CAKE_FLOW_HOSTS | CAKE_FLOW_FLOWS */
+ CAKE_FLOW_MAX,
+};
+
+enum {
+ CAKE_DIFFSERV_DIFFSERV3 = 0,
+ CAKE_DIFFSERV_DIFFSERV4,
+ CAKE_DIFFSERV_DIFFSERV8,
+ CAKE_DIFFSERV_BESTEFFORT,
+ CAKE_DIFFSERV_PRECEDENCE,
+ CAKE_DIFFSERV_MAX
+};
+
+enum {
+ CAKE_ACK_NONE = 0,
+ CAKE_ACK_FILTER,
+ CAKE_ACK_AGGRESSIVE,
+ CAKE_ACK_MAX
+};
+
+enum {
+ CAKE_ATM_NONE = 0,
+ CAKE_ATM_ATM,
+ CAKE_ATM_PTM,
+ CAKE_ATM_MAX
+};
+
#endif
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index a01169fb5325..6e7d614b5757 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -284,6 +284,17 @@ config NET_SCH_FQ_CODEL
If unsure, say N.
+config NET_SCH_CAKE
+ tristate "Common Applications Kept Enhanced (CAKE)"
+ help
+ Say Y here if you want to use the Common Applications Kept Enhanced
+ (CAKE) queue management algorithm.
+
+ To compile this driver as a module, choose M here: the module
+ will be called sch_cake.
+
+ If unsure, say N.
+
config NET_SCH_FQ
tristate "Fair Queue"
help
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 8811d3804878..435054cee32c 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -50,6 +50,7 @@ obj-$(CONFIG_NET_SCH_CHOKE) += sch_choke.o
obj-$(CONFIG_NET_SCH_QFQ) += sch_qfq.o
obj-$(CONFIG_NET_SCH_CODEL) += sch_codel.o
obj-$(CONFIG_NET_SCH_FQ_CODEL) += sch_fq_codel.o
+obj-$(CONFIG_NET_SCH_CAKE) += sch_cake.o
obj-$(CONFIG_NET_SCH_FQ) += sch_fq.o
obj-$(CONFIG_NET_SCH_HHF) += sch_hhf.o
obj-$(CONFIG_NET_SCH_PIE) += sch_pie.o
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
new file mode 100644
index 000000000000..3575ecff4476
--- /dev/null
+++ b/net/sched/sch_cake.c
@@ -0,0 +1,2616 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+
+/* COMMON Applications Kept Enhanced (CAKE) discipline
+ *
+ * Copyright (C) 2014-2018 Jonathan Morton <chromatix99@gmail.com>
+ * Copyright (C) 2015-2018 Toke Høiland-Jørgensen <toke@toke.dk>
+ * Copyright (C) 2014-2018 Dave Täht <dave.taht@gmail.com>
+ * Copyright (C) 2015-2018 Sebastian Moeller <moeller0@gmx.de>
+ * (C) 2015-2018 Kevin Darbyshire-Bryant <kevin@darbyshire-bryant.me.uk>
+ * Copyright (C) 2017 Ryan Mounce <ryan@mounce.com.au>
+ *
+ * The CAKE Principles:
+ * (or, how to have your cake and eat it too)
+ *
+ * This is a combination of several shaping, AQM and FQ techniques into one
+ * easy-to-use package:
+ *
+ * - An overall bandwidth shaper, to move the bottleneck away from dumb CPE
+ * equipment and bloated MACs. This operates in deficit mode (as in sch_fq),
+ * eliminating the need for any sort of burst parameter (eg. token bucket
+ * depth). Burst support is limited to that necessary to overcome scheduling
+ * latency.
+ *
+ * - A Diffserv-aware priority queue, giving more priority to certain classes,
+ * up to a specified fraction of bandwidth. Above that bandwidth threshold,
+ * the priority is reduced to avoid starving other tins.
+ *
+ * - Each priority tin has a separate Flow Queue system, to isolate traffic
+ * flows from each other. This prevents a burst on one flow from increasing
+ * the delay to another. Flows are distributed to queues using a
+ * set-associative hash function.
+ *
+ * - Each queue is actively managed by Cobalt, which is a combination of the
+ * Codel and Blue AQM algorithms. This serves flows fairly, and signals
+ * congestion early via ECN (if available) and/or packet drops, to keep
+ * latency low. The codel parameters are auto-tuned based on the bandwidth
+ * setting, as is necessary at low bandwidths.
+ *
+ * The configuration parameters are kept deliberately simple for ease of use.
+ * Everything has sane defaults. Complete generality of configuration is *not*
+ * a goal.
+ *
+ * The priority queue operates according to a weighted DRR scheme, combined with
+ * a bandwidth tracker which reuses the shaper logic to detect which side of the
+ * bandwidth sharing threshold the tin is operating. This determines whether a
+ * priority-based weight (high) or a bandwidth-based weight (low) is used for
+ * that tin in the current pass.
+ *
+ * This qdisc was inspired by Eric Dumazet's fq_codel code, which he kindly
+ * granted us permission to leverage.
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/jiffies.h>
+#include <linux/string.h>
+#include <linux/in.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/skbuff.h>
+#include <linux/jhash.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/reciprocal_div.h>
+#include <net/netlink.h>
+#include <linux/version.h>
+#include "pkt_sched.h"
+#include <linux/if_vlan.h>
+#include <net/pkt_sched.h>
+#include <net/tcp.h>
+#include <net/flow_dissector.h>
+
+#if IS_REACHABLE(CONFIG_NF_CONNTRACK)
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_zones.h>
+#include <net/netfilter/nf_conntrack.h>
+#endif
+
+#define CAKE_SET_WAYS (8)
+#define CAKE_MAX_TINS (8)
+#define CAKE_QUEUES (1024)
+#define US2TIME(a) (a * (u64)NSEC_PER_USEC)
+
+typedef u64 cobalt_time_t;
+typedef s64 cobalt_tdiff_t;
+
+/**
+ * struct cobalt_params - contains codel and blue parameters
+ * @interval: codel initial drop rate
+ * @target: maximum persistent sojourn time & blue update rate
+ * @mtu_time: serialisation delay of maximum-size packet
+ * @p_inc: increment of blue drop probability (0.32 fxp)
+ * @p_dec: decrement of blue drop probability (0.32 fxp)
+ */
+struct cobalt_params {
+ cobalt_time_t interval;
+ cobalt_time_t target;
+ cobalt_time_t mtu_time;
+ u32 p_inc;
+ u32 p_dec;
+};
+
+/* struct cobalt_vars - contains codel and blue variables
+ * @count: codel dropping frequency
+ * @rec_inv_sqrt: reciprocal value of sqrt(count) >> 1
+ * @drop_next: time to drop next packet, or when we dropped last
+ * @blue_timer: Blue time to next drop
+ * @p_drop: BLUE drop probability (0.32 fxp)
+ * @dropping: set if in dropping state
+ * @ecn_marked: set if marked
+ */
+struct cobalt_vars {
+ u32 count;
+ u32 rec_inv_sqrt;
+ cobalt_time_t drop_next;
+ cobalt_time_t blue_timer;
+ u32 p_drop;
+ bool dropping;
+ bool ecn_marked;
+};
+
+enum {
+ CAKE_SET_NONE = 0,
+ CAKE_SET_SPARSE,
+ CAKE_SET_SPARSE_WAIT, /* counted in SPARSE, actually in BULK */
+ CAKE_SET_BULK,
+ CAKE_SET_DECAYING
+};
+
+struct cake_flow {
+ /* this stuff is all needed per-flow at dequeue time */
+ struct sk_buff *head;
+ struct sk_buff *tail;
+ struct sk_buff *ackcheck;
+ struct list_head flowchain;
+ s32 deficit;
+ struct cobalt_vars cvars;
+ u16 srchost; /* index into cake_host table */
+ u16 dsthost;
+ u8 set;
+}; /* please try to keep this structure <= 64 bytes */
+
+struct cake_host {
+ u32 srchost_tag;
+ u32 dsthost_tag;
+ u16 srchost_refcnt;
+ u16 dsthost_refcnt;
+};
+
+struct cake_heap_entry {
+ u16 t:3, b:10;
+};
+
+struct cake_tin_data {
+ struct cake_flow flows[CAKE_QUEUES];
+ u32 backlogs[CAKE_QUEUES];
+ u32 tags[CAKE_QUEUES]; /* for set association */
+ u16 overflow_idx[CAKE_QUEUES];
+ struct cake_host hosts[CAKE_QUEUES]; /* for triple isolation */
+ u32 perturb;
+ u16 flow_quantum;
+
+ struct cobalt_params cparams;
+ u32 drop_overlimit;
+ u16 bulk_flow_count;
+ u16 sparse_flow_count;
+ u16 decaying_flow_count;
+ u16 unresponsive_flow_count;
+
+ u32 max_skblen;
+
+ struct list_head new_flows;
+ struct list_head old_flows;
+ struct list_head decaying_flows;
+
+ /* time_next = time_this + ((len * rate_ns) >> rate_shft) */
+ u64 tin_time_next_packet;
+ u32 tin_rate_ns;
+ u32 tin_rate_bps;
+ u16 tin_rate_shft;
+
+ u16 tin_quantum_prio;
+ u16 tin_quantum_band;
+ s32 tin_deficit;
+ u32 tin_backlog;
+ u32 tin_dropped;
+ u32 tin_ecn_mark;
+
+ u32 packets;
+ u64 bytes;
+
+ u32 ack_drops;
+
+ /* moving averages */
+ cobalt_time_t avge_delay;
+ cobalt_time_t peak_delay;
+ cobalt_time_t base_delay;
+
+ /* hash function stats */
+ u32 way_directs;
+ u32 way_hits;
+ u32 way_misses;
+ u32 way_collisions;
+}; /* number of tins is small, so size of this struct doesn't matter much */
+
+struct cake_sched_data {
+ struct cake_tin_data *tins;
+
+ struct cake_heap_entry overflow_heap[CAKE_QUEUES * CAKE_MAX_TINS];
+ u16 overflow_timeout;
+
+ u16 tin_cnt;
+ u8 tin_mode;
+#define CAKE_FLOW_NAT_FLAG 64
+ u8 flow_mode;
+ u8 ack_filter;
+ u8 atm_mode;
+
+ /* time_next = time_this + ((len * rate_ns) >> rate_shft) */
+ u16 rate_shft;
+ u64 time_next_packet;
+ u64 failsafe_next_packet;
+ u32 rate_ns;
+ u32 rate_bps;
+ u16 rate_flags;
+ s16 rate_overhead;
+ u16 rate_mpu;
+ u32 interval;
+ u32 target;
+
+ /* resource tracking */
+ u32 buffer_used;
+ u32 buffer_max_used;
+ u32 buffer_limit;
+ u32 buffer_config_limit;
+
+ /* indices for dequeue */
+ u16 cur_tin;
+ u16 cur_flow;
+
+ struct qdisc_watchdog watchdog;
+ const u8 *tin_index;
+ const u8 *tin_order;
+
+ /* bandwidth capacity estimate */
+ u64 last_packet_time;
+ u64 avg_packet_interval;
+ u64 avg_window_begin;
+ u32 avg_window_bytes;
+ u32 avg_peak_bandwidth;
+ u64 last_reconfig_time;
+
+ /* packet length stats */
+ u32 avg_netoff;
+ u16 max_netlen;
+ u16 max_adjlen;
+ u16 min_netlen;
+ u16 min_adjlen;
+};
+
+enum {
+ CAKE_FLAG_OVERHEAD = BIT(0),
+ CAKE_FLAG_AUTORATE_INGRESS = BIT(1),
+ CAKE_FLAG_INGRESS = BIT(2),
+ CAKE_FLAG_WASH = BIT(3)
+};
+
+/* COBALT operates the Codel and BLUE algorithms in parallel, in order to
+ * obtain the best features of each. Codel is excellent on flows which
+ * respond to congestion signals in a TCP-like way. BLUE is more effective on
+ * unresponsive flows.
+ */
+
+struct cobalt_skb_cb {
+ cobalt_time_t enqueue_time;
+ u32 adjusted_len;
+};
+
+static inline cobalt_time_t cobalt_get_time(void)
+{
+ return ktime_get_ns();
+}
+
+static inline u32 cobalt_time_to_us(cobalt_time_t val)
+{
+ do_div(val, NSEC_PER_USEC);
+ return (u32)val;
+}
+
+static inline struct cobalt_skb_cb *get_cobalt_cb(const struct sk_buff *skb)
+{
+ qdisc_cb_private_validate(skb, sizeof(struct cobalt_skb_cb));
+ return (struct cobalt_skb_cb *)qdisc_skb_cb(skb)->data;
+}
+
+static inline cobalt_time_t cobalt_get_enqueue_time(const struct sk_buff *skb)
+{
+ return get_cobalt_cb(skb)->enqueue_time;
+}
+
+static inline void cobalt_set_enqueue_time(struct sk_buff *skb,
+ cobalt_time_t now)
+{
+ get_cobalt_cb(skb)->enqueue_time = now;
+}
+
+static u16 quantum_div[CAKE_QUEUES + 1] = {0};
+
+/* Diffserv lookup tables */
+
+static const u8 precedence[] = {
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 1, 1, 1, 1, 1, 1, 1, 1,
+ 2, 2, 2, 2, 2, 2, 2, 2,
+ 3, 3, 3, 3, 3, 3, 3, 3,
+ 4, 4, 4, 4, 4, 4, 4, 4,
+ 5, 5, 5, 5, 5, 5, 5, 5,
+ 6, 6, 6, 6, 6, 6, 6, 6,
+ 7, 7, 7, 7, 7, 7, 7, 7,
+};
+
+static const u8 diffserv8[] = {
+ 2, 5, 1, 2, 4, 2, 2, 2,
+ 0, 2, 1, 2, 1, 2, 1, 2,
+ 5, 2, 4, 2, 4, 2, 4, 2,
+ 3, 2, 3, 2, 3, 2, 3, 2,
+ 6, 2, 3, 2, 3, 2, 3, 2,
+ 6, 2, 2, 2, 6, 2, 6, 2,
+ 7, 2, 2, 2, 2, 2, 2, 2,
+ 7, 2, 2, 2, 2, 2, 2, 2,
+};
+
+static const u8 diffserv4[] = {
+ 0, 2, 0, 0, 2, 0, 0, 0,
+ 1, 0, 0, 0, 0, 0, 0, 0,
+ 2, 0, 2, 0, 2, 0, 2, 0,
+ 2, 0, 2, 0, 2, 0, 2, 0,
+ 3, 0, 2, 0, 2, 0, 2, 0,
+ 3, 0, 0, 0, 3, 0, 3, 0,
+ 3, 0, 0, 0, 0, 0, 0, 0,
+ 3, 0, 0, 0, 0, 0, 0, 0,
+};
+
+static const u8 diffserv3[] = {
+ 0, 0, 0, 0, 2, 0, 0, 0,
+ 1, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 2, 0, 2, 0,
+ 2, 0, 0, 0, 0, 0, 0, 0,
+ 2, 0, 0, 0, 0, 0, 0, 0,
+};
+
+static const u8 besteffort[] = {
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0,
+};
+
+/* tin priority order for stats dumping */
+
+static const u8 normal_order[] = {0, 1, 2, 3, 4, 5, 6, 7};
+static const u8 bulk_order[] = {1, 0, 2, 3};
+
+#define REC_INV_SQRT_CACHE (16)
+static u32 cobalt_rec_inv_sqrt_cache[REC_INV_SQRT_CACHE] = {0};
+
+/* http://en.wikipedia.org/wiki/Methods_of_computing_square_roots
+ * new_invsqrt = (invsqrt / 2) * (3 - count * invsqrt^2)
+ *
+ * Here, invsqrt is a fixed point number (< 1.0), 32bit mantissa, aka Q0.32
+ */
+
+static void cobalt_newton_step(struct cobalt_vars *vars)
+{
+ u32 invsqrt = vars->rec_inv_sqrt;
+ u32 invsqrt2 = ((u64)invsqrt * invsqrt) >> 32;
+ u64 val = (3LL << 32) - ((u64)vars->count * invsqrt2);
+
+ val >>= 2; /* avoid overflow in following multiply */
+ val = (val * invsqrt) >> (32 - 2 + 1);
+
+ vars->rec_inv_sqrt = val;
+}
+
+static void cobalt_invsqrt(struct cobalt_vars *vars)
+{
+ if (vars->count < REC_INV_SQRT_CACHE)
+ vars->rec_inv_sqrt = cobalt_rec_inv_sqrt_cache[vars->count];
+ else
+ cobalt_newton_step(vars);
+}
+
+/* There is a big difference in timing between the accurate values placed in
+ * the cache and the approximations given by a single Newton step for small
+ * count values, particularly when stepping from count 1 to 2 or vice versa.
+ * Above 16, a single Newton step gives sufficient accuracy in either
+ * direction, given the precision stored.
+ *
+ * The magnitude of the error when stepping up to count 2 is such as to give
+ * the value that *should* have been produced at count 4.
+ */
+
+static void cobalt_cache_init(void)
+{
+ struct cobalt_vars v;
+
+ memset(&v, 0, sizeof(v));
+ v.rec_inv_sqrt = ~0U;
+ cobalt_rec_inv_sqrt_cache[0] = v.rec_inv_sqrt;
+
+ for (v.count = 1; v.count < REC_INV_SQRT_CACHE; v.count++) {
+ cobalt_newton_step(&v);
+ cobalt_newton_step(&v);
+ cobalt_newton_step(&v);
+ cobalt_newton_step(&v);
+
+ cobalt_rec_inv_sqrt_cache[v.count] = v.rec_inv_sqrt;
+ }
+}
+
+static void cobalt_vars_init(struct cobalt_vars *vars)
+{
+ memset(vars, 0, sizeof(*vars));
+
+ if (!cobalt_rec_inv_sqrt_cache[0]) {
+ cobalt_cache_init();
+ cobalt_rec_inv_sqrt_cache[0] = ~0;
+ }
+}
+
+/* CoDel control_law is t + interval/sqrt(count)
+ * We maintain in rec_inv_sqrt the reciprocal value of sqrt(count) to avoid
+ * both sqrt() and divide operation.
+ */
+static cobalt_time_t cobalt_control(cobalt_time_t t,
+ cobalt_time_t interval,
+ u32 rec_inv_sqrt)
+{
+ return t + reciprocal_scale(interval, rec_inv_sqrt);
+}
+
+/* Call this when a packet had to be dropped due to queue overflow. Returns
+ * true if the BLUE state was quiescent before but active after this call.
+ */
+static bool cobalt_queue_full(struct cobalt_vars *vars,
+ struct cobalt_params *p,
+ cobalt_time_t now)
+{
+ bool up = false;
+
+ if ((now - vars->blue_timer) > p->target) {
+ up = !vars->p_drop;
+ vars->p_drop += p->p_inc;
+ if (vars->p_drop < p->p_inc)
+ vars->p_drop = ~0;
+ vars->blue_timer = now;
+ }
+ vars->dropping = true;
+ vars->drop_next = now;
+ if (!vars->count)
+ vars->count = 1;
+
+ return up;
+}
+
+/* Call this when the queue was serviced but turned out to be empty. Returns
+ * true if the BLUE state was active before but quiescent after this call.
+ */
+static bool cobalt_queue_empty(struct cobalt_vars *vars,
+ struct cobalt_params *p,
+ cobalt_time_t now)
+{
+ bool down = false;
+
+ if (vars->p_drop && (now - vars->blue_timer) > p->target) {
+ if (vars->p_drop < p->p_dec)
+ vars->p_drop = 0;
+ else
+ vars->p_drop -= p->p_dec;
+ vars->blue_timer = now;
+ down = !vars->p_drop;
+ }
+ vars->dropping = false;
+
+ if (vars->count && (now - vars->drop_next) >= 0) {
+ vars->count--;
+ cobalt_invsqrt(vars);
+ vars->drop_next = cobalt_control(vars->drop_next,
+ p->interval,
+ vars->rec_inv_sqrt);
+ }
+
+ return down;
+}
+
+/* Call this with a freshly dequeued packet for possible congestion marking.
+ * Returns true as an instruction to drop the packet, false for delivery.
+ */
+static bool cobalt_should_drop(struct cobalt_vars *vars,
+ struct cobalt_params *p,
+ cobalt_time_t now,
+ struct sk_buff *skb,
+ u32 bulk_flows)
+{
+ bool drop = false;
+
+ /* Simplified Codel implementation */
+ cobalt_tdiff_t sojourn = now - cobalt_get_enqueue_time(skb);
+
+/* The 'schedule' variable records, in its sign, whether 'now' is before or
+ * after 'drop_next'. This allows 'drop_next' to be updated before the next
+ * scheduling decision is actually branched, without destroying that
+ * information. Similarly, the first 'schedule' value calculated is preserved
+ * in the boolean 'next_due'.
+ *
+ * As for 'drop_next', we take advantage of the fact that 'interval' is both
+ * the delay between first exceeding 'target' and the first signalling event,
+ * *and* the scaling factor for the signalling frequency. It's therefore very
+ * natural to use a single mechanism for both purposes, and eliminates a
+ * significant amount of reference Codel's spaghetti code. To help with this,
+ * both the '0' and '1' entries in the invsqrt cache are 0xFFFFFFFF, as close
+ * as possible to 1.0 in fixed-point.
+ */
+
+ cobalt_tdiff_t schedule = now - vars->drop_next;
+
+ bool over_target = sojourn > p->target &&
+ sojourn > p->mtu_time * bulk_flows * 2 &&
+ sojourn > p->mtu_time * 4;
+ bool next_due = vars->count && schedule >= 0;
+
+ vars->ecn_marked = false;
+
+ if (over_target) {
+ if (!vars->dropping) {
+ vars->dropping = true;
+ vars->drop_next = cobalt_control(now,
+ p->interval,
+ vars->rec_inv_sqrt);
+ }
+ if (!vars->count)
+ vars->count = 1;
+ } else if (vars->dropping) {
+ vars->dropping = false;
+ }
+
+ if (next_due && vars->dropping) {
+ /* Use ECN mark if possible, otherwise drop */
+ drop = !(vars->ecn_marked = INET_ECN_set_ce(skb));
+
+ vars->count++;
+ if (!vars->count)
+ vars->count--;
+ cobalt_invsqrt(vars);
+ vars->drop_next = cobalt_control(vars->drop_next,
+ p->interval,
+ vars->rec_inv_sqrt);
+ schedule = now - vars->drop_next;
+ } else {
+ while (next_due) {
+ vars->count--;
+ cobalt_invsqrt(vars);
+ vars->drop_next = cobalt_control(vars->drop_next,
+ p->interval,
+ vars->rec_inv_sqrt);
+ schedule = now - vars->drop_next;
+ next_due = vars->count && schedule >= 0;
+ }
+ }
+
+ /* Simple BLUE implementation. Lack of ECN is deliberate. */
+ if (vars->p_drop)
+ drop |= (prandom_u32() < vars->p_drop);
+
+ /* Overload the drop_next field as an activity timeout */
+ if (!vars->count)
+ vars->drop_next = now + p->interval;
+ else if (schedule > 0 && !drop)
+ vars->drop_next = now;
+
+ return drop;
+}
+
+#if IS_REACHABLE(CONFIG_NF_CONNTRACK)
+
+static inline void cake_update_flowkeys(struct flow_keys *keys,
+ const struct sk_buff *skb)
+{
+ enum ip_conntrack_info ctinfo;
+ bool rev = false;
+
+ struct nf_conn *ct;
+ const struct nf_conntrack_tuple *tuple;
+
+ if (tc_skb_protocol(skb) != htons(ETH_P_IP))
+ return;
+
+ ct = nf_ct_get(skb, &ctinfo);
+ if (ct) {
+ tuple = nf_ct_tuple(ct, CTINFO2DIR(ctinfo));
+ } else {
+ const struct nf_conntrack_tuple_hash *hash;
+ struct nf_conntrack_tuple srctuple;
+
+ if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb),
+ NFPROTO_IPV4, dev_net(skb->dev),
+ &srctuple))
+ return;
+
+ hash = nf_conntrack_find_get(dev_net(skb->dev),
+ &nf_ct_zone_dflt,
+ &srctuple);
+ if (!hash)
+ return;
+
+ rev = true;
+ ct = nf_ct_tuplehash_to_ctrack(hash);
+ tuple = nf_ct_tuple(ct, !hash->tuple.dst.dir);
+ }
+
+ keys->addrs.v4addrs.src = rev ? tuple->dst.u3.ip : tuple->src.u3.ip;
+ keys->addrs.v4addrs.dst = rev ? tuple->src.u3.ip : tuple->dst.u3.ip;
+
+ if (keys->ports.ports) {
+ keys->ports.src = rev ? tuple->dst.u.all : tuple->src.u.all;
+ keys->ports.dst = rev ? tuple->src.u.all : tuple->dst.u.all;
+ }
+ if (rev)
+ nf_ct_put(ct);
+}
+#else
+static inline void cake_update_flowkeys(struct flow_keys *keys,
+ const struct sk_buff *skb)
+{
+ /* There is nothing we can do here without CONNTRACK */
+}
+#endif
+
+/* Cake has several subtle multiple bit settings. In these cases you
+ * would be matching triple isolate mode as well.
+ */
+
+static inline bool cake_dsrc(int flow_mode)
+{
+ return (flow_mode & CAKE_FLOW_DUAL_SRC) == CAKE_FLOW_DUAL_SRC;
+}
+
+static inline bool cake_ddst(int flow_mode)
+{
+ return (flow_mode & CAKE_FLOW_DUAL_DST) == CAKE_FLOW_DUAL_DST;
+}
+
+static inline u32
+cake_hash(struct cake_tin_data *q, const struct sk_buff *skb, int flow_mode)
+{
+ struct flow_keys keys, host_keys;
+ u32 flow_hash = 0, srchost_hash, dsthost_hash;
+ u16 reduced_hash, srchost_idx, dsthost_idx;
+
+ if (unlikely(flow_mode == CAKE_FLOW_NONE))
+ return 0;
+
+ skb_flow_dissect_flow_keys(skb, &keys,
+ FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
+
+ if (flow_mode & CAKE_FLOW_NAT_FLAG)
+ cake_update_flowkeys(&keys, skb);
+
+ /* flow_hash_from_keys() sorts the addresses by value, so we have
+ * to preserve their order in a separate data structure to treat
+ * src and dst host addresses as independently selectable.
+ */
+ host_keys = keys;
+ host_keys.ports.ports = 0;
+ host_keys.basic.ip_proto = 0;
+ host_keys.keyid.keyid = 0;
+ host_keys.tags.flow_label = 0;
+
+ switch (host_keys.control.addr_type) {
+ case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
+ host_keys.addrs.v4addrs.src = 0;
+ dsthost_hash = flow_hash_from_keys(&host_keys);
+ host_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src;
+ host_keys.addrs.v4addrs.dst = 0;
+ srchost_hash = flow_hash_from_keys(&host_keys);
+ break;
+
+ case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
+ memset(&host_keys.addrs.v6addrs.src, 0,
+ sizeof(host_keys.addrs.v6addrs.src));
+ dsthost_hash = flow_hash_from_keys(&host_keys);
+ host_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src;
+ memset(&host_keys.addrs.v6addrs.dst, 0,
+ sizeof(host_keys.addrs.v6addrs.dst));
+ srchost_hash = flow_hash_from_keys(&host_keys);
+ break;
+
+ default:
+ dsthost_hash = 0;
+ srchost_hash = 0;
+ };
+
+ /* This *must* be after the above switch, since as a
+ * side-effect it sorts the src and dst addresses.
+ */
+ if (flow_mode & CAKE_FLOW_FLOWS)
+ flow_hash = flow_hash_from_keys(&keys);
+
+ if (!(flow_mode & CAKE_FLOW_FLOWS)) {
+ if (flow_mode & CAKE_FLOW_SRC_IP)
+ flow_hash ^= srchost_hash;
+
+ if (flow_mode & CAKE_FLOW_DST_IP)
+ flow_hash ^= dsthost_hash;
+ }
+
+ reduced_hash = flow_hash % CAKE_QUEUES;
+
+ /* set-associative hashing */
+ /* fast path if no hash collision (direct lookup succeeds) */
+ if (likely(q->tags[reduced_hash] == flow_hash &&
+ q->flows[reduced_hash].set)) {
+ q->way_directs++;
+ } else {
+ u32 inner_hash = reduced_hash % CAKE_SET_WAYS;
+ u32 outer_hash = reduced_hash - inner_hash;
+ u32 i, k;
+ bool allocate_src = false;
+ bool allocate_dst = false;
+
+ /* check if any active queue in the set is reserved for
+ * this flow.
+ */
+ for (i = 0, k = inner_hash; i < CAKE_SET_WAYS;
+ i++, k = (k + 1) % CAKE_SET_WAYS) {
+ if (q->tags[outer_hash + k] == flow_hash) {
+ if (i)
+ q->way_hits++;
+
+ if (!q->flows[outer_hash + k].set) {
+ /* need to increment host refcnts */
+ allocate_src = cake_dsrc(flow_mode);
+ allocate_dst = cake_ddst(flow_mode);
+ }
+
+ goto found;
+ }
+ }
+
+ /* no queue is reserved for this flow, look for an
+ * empty one.
+ */
+ for (i = 0; i < CAKE_SET_WAYS;
+ i++, k = (k + 1) % CAKE_SET_WAYS) {
+ if (!q->flows[outer_hash + k].set) {
+ q->way_misses++;
+ allocate_src = cake_dsrc(flow_mode);
+ allocate_dst = cake_ddst(flow_mode);
+ goto found;
+ }
+ }
+
+ /* With no empty queues, default to the original
+ * queue, accept the collision, update the host tags.
+ */
+ q->way_collisions++;
+ q->hosts[q->flows[reduced_hash].srchost].srchost_refcnt--;
+ q->hosts[q->flows[reduced_hash].dsthost].dsthost_refcnt--;
+ allocate_src = cake_dsrc(flow_mode);
+ allocate_dst = cake_ddst(flow_mode);
+found:
+ /* reserve queue for future packets in same flow */
+ reduced_hash = outer_hash + k;
+ q->tags[reduced_hash] = flow_hash;
+
+ if (allocate_src) {
+ srchost_idx = srchost_hash % CAKE_QUEUES;
+ inner_hash = srchost_idx % CAKE_SET_WAYS;
+ outer_hash = srchost_idx - inner_hash;
+ for (i = 0, k = inner_hash; i < CAKE_SET_WAYS;
+ i++, k = (k + 1) % CAKE_SET_WAYS) {
+ if (q->hosts[outer_hash + k].srchost_tag ==
+ srchost_hash)
+ goto found_src;
+ }
+ for (i = 0; i < CAKE_SET_WAYS;
+ i++, k = (k + 1) % CAKE_SET_WAYS) {
+ if (!q->hosts[outer_hash + k].srchost_refcnt)
+ break;
+ }
+ q->hosts[outer_hash + k].srchost_tag = srchost_hash;
+found_src:
+ srchost_idx = outer_hash + k;
+ q->hosts[srchost_idx].srchost_refcnt++;
+ q->flows[reduced_hash].srchost = srchost_idx;
+ }
+
+ if (allocate_dst) {
+ dsthost_idx = dsthost_hash % CAKE_QUEUES;
+ inner_hash = dsthost_idx % CAKE_SET_WAYS;
+ outer_hash = dsthost_idx - inner_hash;
+ for (i = 0, k = inner_hash; i < CAKE_SET_WAYS;
+ i++, k = (k + 1) % CAKE_SET_WAYS) {
+ if (q->hosts[outer_hash + k].dsthost_tag ==
+ dsthost_hash)
+ goto found_dst;
+ }
+ for (i = 0; i < CAKE_SET_WAYS;
+ i++, k = (k + 1) % CAKE_SET_WAYS) {
+ if (!q->hosts[outer_hash + k].dsthost_refcnt)
+ break;
+ }
+ q->hosts[outer_hash + k].dsthost_tag = dsthost_hash;
+found_dst:
+ dsthost_idx = outer_hash + k;
+ q->hosts[dsthost_idx].dsthost_refcnt++;
+ q->flows[reduced_hash].dsthost = dsthost_idx;
+ }
+ }
+
+ return reduced_hash;
+}
+
+/* helper functions : might be changed when/if skb use a standard list_head */
+/* remove one skb from head of slot queue */
+
+static inline struct sk_buff *dequeue_head(struct cake_flow *flow)
+{
+ struct sk_buff *skb = flow->head;
+
+ if (skb) {
+ flow->head = skb->next;
+ skb->next = NULL;
+
+ if (skb == flow->ackcheck)
+ flow->ackcheck = NULL;
+ }
+
+ return skb;
+}
+
+/* add skb to flow queue (tail add) */
+
+static inline void
+flow_queue_add(struct cake_flow *flow, struct sk_buff *skb)
+{
+ if (!flow->head)
+ flow->head = skb;
+ else
+ flow->tail->next = skb;
+ flow->tail = skb;
+ skb->next = NULL;
+}
+
+static struct sk_buff *cake_ack_filter(struct cake_sched_data *q,
+ struct cake_flow *flow)
+{
+ int seglen;
+ struct sk_buff *skb = flow->tail, *skb_check, *skb_check_prev;
+ struct iphdr *iph, *iph_check;
+ struct ipv6hdr *ipv6h, *ipv6h_check;
+ struct tcphdr *tcph, *tcph_check;
+ bool otherconn_ack_seen = false;
+ struct sk_buff *otherconn_checked_to = NULL;
+ bool thisconn_redundant_seen = false, thisconn_seen_last = false;
+ struct sk_buff *thisconn_checked_to = NULL, *thisconn_ack = NULL;
+ bool aggressive = q->ack_filter == CAKE_ACK_AGGRESSIVE;
+
+ /* no other possible ACKs to filter */
+ if (flow->head == skb)
+ return NULL;
+
+ iph = skb->encapsulation ? inner_ip_hdr(skb) : ip_hdr(skb);
+ ipv6h = skb->encapsulation ? inner_ipv6_hdr(skb) : ipv6_hdr(skb);
+
+ /* check that the innermost network header is v4/v6, and contains TCP */
+ if (iph->version == 4) {
+ if (iph->protocol != IPPROTO_TCP)
+ return NULL;
+ seglen = ntohs(iph->tot_len) - (4 * iph->ihl);
+ tcph = (struct tcphdr *)((void *)iph + (4 * iph->ihl));
+ } else if (ipv6h->version == 6) {
+ if (ipv6h->nexthdr != IPPROTO_TCP)
+ return NULL;
+ seglen = ntohs(ipv6h->payload_len);
+ tcph = (struct tcphdr *)((void *)ipv6h +
+ sizeof(struct ipv6hdr));
+ } else {
+ return NULL;
+ }
+
+ /* the 'triggering' packet need only have the ACK flag set.
+ * also check that SYN is not set, as there won't be any previous ACKs.
+ */
+ if ((tcp_flag_word(tcph) &
+ (TCP_FLAG_ACK | TCP_FLAG_SYN)) != TCP_FLAG_ACK)
+ return NULL;
+
+ /* the 'triggering' ACK is at the end of the queue,
+ * we have already returned if it is the only packet in the flow.
+ * stop before last packet in queue, don't compare trigger ACK to itself
+ * start where we finished last time if recorded in ->ackcheck
+ * otherwise start from the the head of the flow queue.
+ */
+ skb_check_prev = flow->ackcheck;
+ skb_check = flow->ackcheck ?: flow->head;
+
+ while (skb_check->next) {
+ bool pure_ack, thisconn;
+
+ /* don't increment if at head of flow queue (_prev == NULL) */
+ if (skb_check_prev) {
+ skb_check_prev = skb_check;
+ skb_check = skb_check->next;
+ if (!skb_check->next)
+ break;
+ } else {
+ skb_check_prev = ERR_PTR(-1);
+ }
+
+ iph_check = skb_check->encapsulation ?
+ inner_ip_hdr(skb_check) : ip_hdr(skb_check);
+ ipv6h_check = skb_check->encapsulation ?
+ inner_ipv6_hdr(skb_check) : ipv6_hdr(skb_check);
+
+ if (iph_check->version == 4) {
+ if (iph_check->protocol != IPPROTO_TCP)
+ continue;
+ seglen = (ntohs(iph_check->tot_len) -
+ (4 * iph_check->ihl));
+ tcph_check = (struct tcphdr *)((void *)iph_check
+ + (4 * iph_check->ihl));
+ if (iph->version == 4 &&
+ iph_check->saddr == iph->saddr &&
+ iph_check->daddr == iph->daddr) {
+ thisconn = true;
+ } else {
+ thisconn = false;
+ }
+ } else if (ipv6h_check->version == 6) {
+ if (ipv6h_check->nexthdr != IPPROTO_TCP)
+ continue;
+ seglen = ntohs(ipv6h_check->payload_len);
+ tcph_check = (struct tcphdr *)((void *)ipv6h_check +
+ sizeof(struct ipv6hdr));
+ if (ipv6h->version == 6 &&
+ ipv6_addr_cmp(&ipv6h_check->saddr, &ipv6h->saddr) &&
+ ipv6_addr_cmp(&ipv6h_check->daddr,
+ &ipv6h->daddr)) {
+ thisconn = true;
+ } else {
+ thisconn = false;
+ }
+ } else {
+ continue;
+ }
+
+ /* stricter criteria apply to ACKs that we may filter
+ * 3 reserved flags must be unset to avoid future breakage
+ * ECE/CWR/NS can be safely ignored
+ * ACK must be set
+ * All other flags URG/PSH/RST/SYN/FIN must be unset
+ * 0x0FFF0000 = all TCP flags (confirm ACK=1, others zero)
+ * 0x01C00000 = NS/CWR/ECE (safe to ignore)
+ * 0x0E3F0000 = 0x0FFF0000 & ~0x01C00000
+ * must be 'pure' ACK, contain zero bytes of segment data
+ * options are ignored
+ */
+ if ((tcp_flag_word(tcph_check) &
+ (TCP_FLAG_ACK | TCP_FLAG_SYN)) != TCP_FLAG_ACK) {
+ continue;
+ } else if (((tcp_flag_word(tcph_check) &
+ cpu_to_be32(0x0E3F0000)) != TCP_FLAG_ACK) ||
+ ((seglen - 4 * tcph_check->doff) != 0)) {
+ pure_ack = false;
+ } else {
+ pure_ack = true;
+ }
+
+ /* if we find an ACK belonging to a different connection
+ * continue checking for other ACKs this round however
+ * restart checking from the other connection next time.
+ */
+ if (thisconn && (tcph_check->source != tcph->source ||
+ tcph_check->dest != tcph->dest)) {
+ thisconn = false;
+ }
+
+ /* new ack sequence must be greater
+ */
+ if (thisconn &&
+ (ntohl(tcph_check->ack_seq) > ntohl(tcph->ack_seq)))
+ continue;
+
+ /* DupACKs with an equal sequence number shouldn't be filtered,
+ * but we can filter if the triggering packet is a SACK
+ */
+ if (thisconn &&
+ (ntohl(tcph_check->ack_seq) == ntohl(tcph->ack_seq))) {
+ /* inspired by tcp_parse_options in tcp_input.c */
+ bool sack = false;
+ int length = (tcph->doff * 4) - sizeof(struct tcphdr);
+ const u8 *ptr = (const u8 *)(tcph + 1);
+
+ while (length > 0) {
+ int opcode = *ptr++;
+ int opsize;
+
+ if (opcode == TCPOPT_EOL)
+ break;
+ if (opcode == TCPOPT_NOP) {
+ length--;
+ continue;
+ }
+ opsize = *ptr++;
+ if (opsize < 2 || opsize > length)
+ break;
+ if (opcode == TCPOPT_SACK) {
+ sack = true;
+ break;
+ }
+ ptr += opsize - 2;
+ length -= opsize;
+ }
+ if (!sack)
+ continue;
+ }
+
+ /* somewhat complicated control flow for 'conservative'
+ * ACK filtering that aims to be more polite to slow-start and
+ * in the presence of packet loss.
+ * does not filter if there is one 'redundant' ACK in the queue.
+ * 'data' ACKs won't be filtered but do count as redundant ACKs.
+ */
+ if (thisconn) {
+ thisconn_seen_last = true;
+ /* if aggressive and this is a data ack we can skip
+ * checking it next time.
+ */
+ thisconn_checked_to = (aggressive && !pure_ack) ?
+ skb_check : skb_check_prev;
+ /* the first pure ack for this connection.
+ * record where it is, but only break if aggressive
+ * or already seen data ack from the same connection
+ */
+ if (pure_ack && !thisconn_ack) {
+ thisconn_ack = skb_check_prev;
+ if (aggressive || thisconn_redundant_seen)
+ break;
+ /* data ack or subsequent pure ack */
+ } else {
+ thisconn_redundant_seen = true;
+ /* this is the second ack for this connection
+ * break to filter the first pure ack
+ */
+ if (thisconn_ack)
+ break;
+ }
+ /* track packets from non-matching tcp connections that will
+ * need evaluation on the next run.
+ * if there are packets from both the matching connection and
+ * others that requre checking next run, track which was updated
+ * last and return the older of the two to ensure full coverage.
+ * if a non-matching pure ack has been seen, cannot skip any
+ * further on the next run so don't update.
+ */
+ } else if (!otherconn_ack_seen) {
+ thisconn_seen_last = false;
+ if (pure_ack) {
+ otherconn_ack_seen = true;
+ /* if aggressive we don't care about old data,
+ * start from the pure ack.
+ * otherwise if there is a previous data ack,
+ * start checking from it next time.
+ */
+ if (aggressive || !otherconn_checked_to)
+ otherconn_checked_to = skb_check_prev;
+ } else {
+ otherconn_checked_to = aggressive ?
+ skb_check : skb_check_prev;
+ }
+ }
+ }
+
+ /* skb_check is reused at this point
+ * it is the pure ACK to be filtered (if any)
+ */
+ skb_check = NULL;
+
+ /* next time start checking from the older/nearest to head of unfiltered
+ * but important tcp packets from this connection and other connections.
+ * if none seen, start after the last packet evaluated in the loop.
+ */
+ if (thisconn_checked_to && otherconn_checked_to)
+ flow->ackcheck = thisconn_seen_last ?
+ otherconn_checked_to : thisconn_checked_to;
+ else if (thisconn_checked_to)
+ flow->ackcheck = thisconn_checked_to;
+ else if (otherconn_checked_to)
+ flow->ackcheck = otherconn_checked_to;
+ else
+ flow->ackcheck = skb_check_prev;
+
+ /* if filtering, the pure ACK from the flow queue */
+ if (thisconn_ack && (aggressive || thisconn_redundant_seen)) {
+ if (PTR_ERR(thisconn_ack) == -1) {
+ skb_check = flow->head;
+ flow->head = flow->head->next;
+ } else {
+ skb_check = thisconn_ack->next;
+ thisconn_ack->next = thisconn_ack->next->next;
+ }
+ }
+
+ /* we just filtered that ack, fix up the list */
+ if (flow->ackcheck == skb_check)
+ flow->ackcheck = thisconn_ack;
+ /* check the entire flow queue next time */
+ if (PTR_ERR(flow->ackcheck) == -1)
+ flow->ackcheck = NULL;
+
+ return skb_check;
+}
+
+static inline cobalt_time_t cake_ewma(cobalt_time_t avg, cobalt_time_t sample,
+ u32 shift)
+{
+ avg -= avg >> shift;
+ avg += sample >> shift;
+ return avg;
+}
+
+static inline u32 cake_overhead(struct cake_sched_data *q, struct sk_buff *skb)
+{
+ u32 len = qdisc_pkt_len(skb);
+ u32 off = skb_network_offset(skb);
+
+ q->avg_netoff = cake_ewma(q->avg_netoff, off << 16, 8);
+
+ if (q->rate_flags & CAKE_FLAG_OVERHEAD)
+ len -= off;
+
+ if (q->max_netlen < len)
+ q->max_netlen = len;
+ if (q->min_netlen > len)
+ q->min_netlen = len;
+
+ len += q->rate_overhead;
+
+ if (len < q->rate_mpu)
+ len = q->rate_mpu;
+
+ if (q->atm_mode == CAKE_ATM_ATM) {
+ len += 47;
+ len /= 48;
+ len *= 53;
+ } else if (q->atm_mode == CAKE_ATM_PTM) {
+ /* Add one byte per 64 bytes or part thereof.
+ * This is conservative and easier to calculate than the
+ * precise value.
+ */
+ len += (len + 63) / 64;
+ }
+
+ if (q->max_adjlen < len)
+ q->max_adjlen = len;
+ if (q->min_adjlen > len)
+ q->min_adjlen = len;
+
+ get_cobalt_cb(skb)->adjusted_len = len;
+ return len;
+}
+
+static inline void cake_heap_swap(struct cake_sched_data *q, u16 i, u16 j)
+{
+ struct cake_heap_entry ii = q->overflow_heap[i];
+ struct cake_heap_entry jj = q->overflow_heap[j];
+
+ q->overflow_heap[i] = jj;
+ q->overflow_heap[j] = ii;
+
+ q->tins[ii.t].overflow_idx[ii.b] = j;
+ q->tins[jj.t].overflow_idx[jj.b] = i;
+}
+
+static inline u32 cake_heap_get_backlog(const struct cake_sched_data *q, u16 i)
+{
+ struct cake_heap_entry ii = q->overflow_heap[i];
+
+ return q->tins[ii.t].backlogs[ii.b];
+}
+
+static void cake_heapify(struct cake_sched_data *q, u16 i)
+{
+ static const u32 a = CAKE_MAX_TINS * CAKE_QUEUES;
+ u32 m = i;
+ u32 mb = cake_heap_get_backlog(q, m);
+
+ while (m < a) {
+ u32 l = m + m + 1;
+ u32 r = l + 1;
+
+ if (l < a) {
+ u32 lb = cake_heap_get_backlog(q, l);
+
+ if (lb > mb) {
+ m = l;
+ mb = lb;
+ }
+ }
+
+ if (r < a) {
+ u32 rb = cake_heap_get_backlog(q, r);
+
+ if (rb > mb) {
+ m = r;
+ mb = rb;
+ }
+ }
+
+ if (m != i) {
+ cake_heap_swap(q, i, m);
+ i = m;
+ } else {
+ break;
+ }
+ }
+}
+
+static void cake_heapify_up(struct cake_sched_data *q, u16 i)
+{
+ while (i > 0 && i < CAKE_MAX_TINS * CAKE_QUEUES) {
+ u16 p = (i - 1) >> 1;
+ u32 ib = cake_heap_get_backlog(q, i);
+ u32 pb = cake_heap_get_backlog(q, p);
+
+ if (ib > pb) {
+ cake_heap_swap(q, i, p);
+ i = p;
+ } else {
+ break;
+ }
+ }
+}
+
+static int cake_advance_shaper(struct cake_sched_data *q,
+ struct cake_tin_data *b,
+ struct sk_buff *skb,
+ u64 now, bool drop)
+{
+ u32 len = get_cobalt_cb(skb)->adjusted_len;
+
+ /* charge packet bandwidth to this tin
+ * and to the global shaper.
+ */
+ if (q->rate_ns) {
+ s64 tdiff1 = b->tin_time_next_packet - now;
+ s64 tdiff2 = (len * (u64)b->tin_rate_ns) >> b->tin_rate_shft;
+ s64 tdiff3 = (len * (u64)q->rate_ns) >> q->rate_shft;
+ s64 tdiff4 = tdiff3 + (tdiff3 >> 1);
+
+ if (tdiff1 < 0)
+ b->tin_time_next_packet += tdiff2;
+ else if (tdiff1 < tdiff2)
+ b->tin_time_next_packet = now + tdiff2;
+
+ q->time_next_packet += tdiff3;
+ if (!drop)
+ q->failsafe_next_packet += tdiff4;
+ }
+ return len;
+}
+
+static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ struct sk_buff *skb;
+ u32 idx = 0, tin = 0, len;
+ struct cake_tin_data *b;
+ struct cake_flow *flow;
+ struct cake_heap_entry qq;
+ u64 now = cobalt_get_time();
+
+ if (!q->overflow_timeout) {
+ int i;
+ /* Build fresh max-heap */
+ for (i = CAKE_MAX_TINS * CAKE_QUEUES / 2; i >= 0; i--)
+ cake_heapify(q, i);
+ }
+ q->overflow_timeout = 65535;
+
+ /* select longest queue for pruning */
+ qq = q->overflow_heap[0];
+ tin = qq.t;
+ idx = qq.b;
+
+ b = &q->tins[tin];
+ flow = &b->flows[idx];
+ skb = dequeue_head(flow);
+ if (unlikely(!skb)) {
+ /* heap has gone wrong, rebuild it next time */
+ q->overflow_timeout = 0;
+ return idx + (tin << 16);
+ }
+
+ if (cobalt_queue_full(&flow->cvars, &b->cparams, now))
+ b->unresponsive_flow_count++;
+
+ len = qdisc_pkt_len(skb);
+ q->buffer_used -= skb->truesize;
+ b->backlogs[idx] -= len;
+ b->tin_backlog -= len;
+ sch->qstats.backlog -= len;
+ qdisc_tree_reduce_backlog(sch, 1, len);
+
+ b->tin_dropped++;
+ sch->qstats.drops++;
+
+ if (q->rate_flags & CAKE_FLAG_INGRESS)
+ cake_advance_shaper(q, b, skb, now, true);
+
+ __qdisc_drop(skb, to_free);
+ sch->q.qlen--;
+
+ cake_heapify(q, 0);
+
+ return idx + (tin << 16);
+}
+
+static inline void cake_wash_diffserv(struct sk_buff *skb)
+{
+ switch (skb->protocol) {
+ case htons(ETH_P_IP):
+ ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0);
+ break;
+ case htons(ETH_P_IPV6):
+ ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0);
+ break;
+ default:
+ break;
+ };
+}
+
+static inline u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash)
+{
+ u8 dscp;
+
+ switch (skb->protocol) {
+ case htons(ETH_P_IP):
+ dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2;
+ if (wash && dscp)
+ ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0);
+ return dscp;
+
+ case htons(ETH_P_IPV6):
+ dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2;
+ if (wash && dscp)
+ ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0);
+ return dscp;
+
+ case htons(ETH_P_ARP):
+ return 0x38; /* CS7 - Net Control */
+
+ default:
+ /* If there is no Diffserv field, treat as best-effort */
+ return 0;
+ };
+}
+
+static void cake_reconfigure(struct Qdisc *sch);
+
+static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+ struct sk_buff **to_free)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ u32 idx, tin;
+ struct cake_tin_data *b;
+ struct cake_flow *flow;
+ /* signed len to handle corner case filtered ACK larger than trigger */
+ int len = qdisc_pkt_len(skb);
+ u64 now = cobalt_get_time();
+ struct sk_buff *ack = NULL;
+
+ /* extract the Diffserv Precedence field, if it exists */
+ /* and clear DSCP bits if washing */
+ if (q->tin_mode != CAKE_DIFFSERV_BESTEFFORT) {
+ tin = q->tin_index[cake_handle_diffserv(skb,
+ q->rate_flags & CAKE_FLAG_WASH)];
+ if (unlikely(tin >= q->tin_cnt))
+ tin = 0;
+ } else {
+ tin = 0;
+ if (q->rate_flags & CAKE_FLAG_WASH)
+ cake_wash_diffserv(skb);
+ }
+
+ b = &q->tins[tin];
+
+ /* choose flow to insert into */
+ idx = cake_hash(b, skb, q->flow_mode);
+ flow = &b->flows[idx];
+
+ /* ensure shaper state isn't stale */
+ if (!b->tin_backlog) {
+ if (b->tin_time_next_packet < now)
+ b->tin_time_next_packet = now;
+
+ if (!sch->q.qlen) {
+ if (q->time_next_packet < now) {
+ q->failsafe_next_packet = now;
+ q->time_next_packet = now;
+ } else if (q->time_next_packet > now &&
+ q->failsafe_next_packet > now) {
+ u64 next = min(q->time_next_packet,
+ q->failsafe_next_packet);
+ sch->qstats.overlimits++;
+ qdisc_watchdog_schedule_ns(&q->watchdog, next);
+ }
+ }
+ }
+
+ if (unlikely(len > b->max_skblen))
+ b->max_skblen = len;
+
+ /* Split GSO aggregates if they're likely to impair flow isolation
+ * or if we need to know individual packet sizes for framing overhead.
+ */
+
+ if (skb_is_gso(skb)) {
+ struct sk_buff *segs, *nskb;
+ netdev_features_t features = netif_skb_features(skb);
+ /* signed slen to handle corner case
+ * suppressed ACK larger than trigger
+ */
+ int slen = 0;
+
+ segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+ if (IS_ERR_OR_NULL(segs))
+ return qdisc_drop(skb, sch, to_free);
+
+ while (segs) {
+ nskb = segs->next;
+ segs->next = NULL;
+ qdisc_skb_cb(segs)->pkt_len = segs->len;
+ cobalt_set_enqueue_time(segs, now);
+ get_cobalt_cb(segs)->adjusted_len = cake_overhead(q,
+ segs);
+ flow_queue_add(flow, segs);
+
+ if (q->ack_filter)
+ ack = cake_ack_filter(q, flow);
+
+ if (ack) {
+ b->ack_drops++;
+ sch->qstats.drops++;
+ b->bytes += ack->len;
+ slen += segs->len - ack->len;
+ q->buffer_used += segs->truesize -
+ ack->truesize;
+ if (q->rate_flags & CAKE_FLAG_INGRESS)
+ cake_advance_shaper(q, b, ack,
+ now, true);
+
+ qdisc_tree_reduce_backlog(sch, 1,
+ qdisc_pkt_len(ack));
+ consume_skb(ack);
+ } else {
+ sch->q.qlen++;
+ slen += segs->len;
+ q->buffer_used += segs->truesize;
+ }
+ b->packets++;
+ segs = nskb;
+ }
+ /* stats */
+ b->bytes += slen;
+ b->backlogs[idx] += slen;
+ b->tin_backlog += slen;
+ sch->qstats.backlog += slen;
+ q->avg_window_bytes += slen;
+
+ qdisc_tree_reduce_backlog(sch, 1, len);
+ consume_skb(skb);
+ } else {
+ /* not splitting */
+ cobalt_set_enqueue_time(skb, now);
+ get_cobalt_cb(skb)->adjusted_len = cake_overhead(q, skb);
+ flow_queue_add(flow, skb);
+
+ if (q->ack_filter)
+ ack = cake_ack_filter(q, flow);
+
+ if (ack) {
+ b->ack_drops++;
+ sch->qstats.drops++;
+ b->bytes += qdisc_pkt_len(ack);
+ len -= qdisc_pkt_len(ack);
+ q->buffer_used += skb->truesize - ack->truesize;
+ if (q->rate_flags & CAKE_FLAG_INGRESS)
+ cake_advance_shaper(q, b, ack, now, true);
+
+ qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(ack));
+ consume_skb(ack);
+ } else {
+ sch->q.qlen++;
+ q->buffer_used += skb->truesize;
+ }
+ /* stats */
+ b->packets++;
+ b->bytes += len;
+ b->backlogs[idx] += len;
+ b->tin_backlog += len;
+ sch->qstats.backlog += len;
+ q->avg_window_bytes += len;
+ }
+
+ if (q->overflow_timeout)
+ cake_heapify_up(q, b->overflow_idx[idx]);
+
+ /* incoming bandwidth capacity estimate */
+ if (q->rate_flags & CAKE_FLAG_AUTORATE_INGRESS) {
+ u64 packet_interval = now - q->last_packet_time;
+
+ if (packet_interval > NSEC_PER_SEC)
+ packet_interval = NSEC_PER_SEC;
+
+ /* filter out short-term bursts, eg. wifi aggregation */
+ q->avg_packet_interval = cake_ewma(q->avg_packet_interval,
+ packet_interval,
+ packet_interval > q->avg_packet_interval ? 2 : 8);
+
+ q->last_packet_time = now;
+
+ if (packet_interval > q->avg_packet_interval) {
+ u64 window_interval = now - q->avg_window_begin;
+ u64 b = q->avg_window_bytes * (u64)NSEC_PER_SEC;
+
+ do_div(b, window_interval);
+ q->avg_peak_bandwidth =
+ cake_ewma(q->avg_peak_bandwidth, b,
+ b > q->avg_peak_bandwidth ? 2 : 8);
+ q->avg_window_bytes = 0;
+ q->avg_window_begin = now;
+
+ if (q->rate_flags & CAKE_FLAG_AUTORATE_INGRESS &&
+ now - q->last_reconfig_time >
+ (NSEC_PER_SEC / 4)) {
+ q->rate_bps = (q->avg_peak_bandwidth * 15) >> 4;
+ cake_reconfigure(sch);
+ }
+ }
+ } else {
+ q->avg_window_bytes = 0;
+ q->last_packet_time = now;
+ }
+
+ /* flowchain */
+ if (!flow->set || flow->set == CAKE_SET_DECAYING) {
+ struct cake_host *srchost = &b->hosts[flow->srchost];
+ struct cake_host *dsthost = &b->hosts[flow->dsthost];
+ u16 host_load = 1;
+
+ if (!flow->set) {
+ list_add_tail(&flow->flowchain, &b->new_flows);
+ } else {
+ b->decaying_flow_count--;
+ list_move_tail(&flow->flowchain, &b->new_flows);
+ }
+ flow->set = CAKE_SET_SPARSE;
+ b->sparse_flow_count++;
+
+ if (cake_dsrc(q->flow_mode))
+ host_load = max(host_load, srchost->srchost_refcnt);
+
+ if (cake_ddst(q->flow_mode))
+ host_load = max(host_load, dsthost->dsthost_refcnt);
+
+ flow->deficit = (b->flow_quantum *
+ quantum_div[host_load]) >> 16;
+ } else if (flow->set == CAKE_SET_SPARSE_WAIT) {
+ /* this flow was empty, accounted as a sparse flow, but actually
+ * in the bulk rotation.
+ */
+ flow->set = CAKE_SET_BULK;
+ b->sparse_flow_count--;
+ b->bulk_flow_count++;
+ }
+
+ if (q->buffer_used > q->buffer_max_used)
+ q->buffer_max_used = q->buffer_used;
+
+ if (q->buffer_used > q->buffer_limit) {
+ u32 dropped = 0;
+
+ while (q->buffer_used > q->buffer_limit) {
+ dropped++;
+ cake_drop(sch, to_free);
+ }
+ b->drop_overlimit += dropped;
+ }
+ return NET_XMIT_SUCCESS;
+}
+
+static struct sk_buff *cake_dequeue_one(struct Qdisc *sch)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ struct cake_tin_data *b = &q->tins[q->cur_tin];
+ struct cake_flow *flow = &b->flows[q->cur_flow];
+ struct sk_buff *skb = NULL;
+ u32 len;
+
+ /* WARN_ON(flow != container_of(vars, struct cake_flow, cvars)); */
+
+ if (flow->head) {
+ skb = dequeue_head(flow);
+ len = qdisc_pkt_len(skb);
+ b->backlogs[q->cur_flow] -= len;
+ b->tin_backlog -= len;
+ sch->qstats.backlog -= len;
+ q->buffer_used -= skb->truesize;
+ sch->q.qlen--;
+
+ if (q->overflow_timeout)
+ cake_heapify(q, b->overflow_idx[q->cur_flow]);
+ }
+ return skb;
+}
+
+/* Discard leftover packets from a tin no longer in use. */
+static void cake_clear_tin(struct Qdisc *sch, u16 tin)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ struct sk_buff *skb;
+
+ q->cur_tin = tin;
+ for (q->cur_flow = 0; q->cur_flow < CAKE_QUEUES; q->cur_flow++)
+ while (!!(skb = cake_dequeue_one(sch)))
+ kfree_skb(skb);
+}
+
+static struct sk_buff *cake_dequeue(struct Qdisc *sch)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ struct sk_buff *skb;
+ struct cake_tin_data *b = &q->tins[q->cur_tin];
+ struct cake_flow *flow;
+ struct cake_host *srchost, *dsthost;
+ struct list_head *head;
+ u32 len;
+ u16 host_load;
+ cobalt_time_t now = ktime_get_ns();
+ cobalt_time_t delay;
+ bool first_flow = true;
+
+begin:
+ if (!sch->q.qlen)
+ return NULL;
+
+ /* global hard shaper */
+ if (q->time_next_packet > now && q->failsafe_next_packet > now) {
+ u64 next = min(q->time_next_packet, q->failsafe_next_packet);
+
+ sch->qstats.overlimits++;
+ qdisc_watchdog_schedule_ns(&q->watchdog, next);
+ return NULL;
+ }
+
+ /* Choose a class to work on. */
+ if (!q->rate_ns) {
+ /* In unlimited mode, can't rely on shaper timings, just balance
+ * with DRR
+ */
+ while (b->tin_deficit < 0 ||
+ !(b->sparse_flow_count + b->bulk_flow_count)) {
+ if (b->tin_deficit <= 0)
+ b->tin_deficit += b->tin_quantum_band;
+
+ q->cur_tin++;
+ b++;
+ if (q->cur_tin >= q->tin_cnt) {
+ q->cur_tin = 0;
+ b = q->tins;
+ }
+ }
+ } else {
+ /* In shaped mode, choose:
+ * - Highest-priority tin with queue and meeting schedule, or
+ * - The earliest-scheduled tin with queue.
+ */
+ int tin, best_tin = 0;
+ s64 best_time = 0xFFFFFFFFFFFFUL;
+
+ for (tin = 0; tin < q->tin_cnt; tin++) {
+ b = q->tins + tin;
+ if ((b->sparse_flow_count + b->bulk_flow_count) > 0) {
+ s64 tdiff = b->tin_time_next_packet - now;
+
+ if (tdiff <= 0 || tdiff <= best_time) {
+ best_time = tdiff;
+ best_tin = tin;
+ }
+ }
+ }
+
+ q->cur_tin = best_tin;
+ b = q->tins + best_tin;
+ }
+
+retry:
+ /* service this class */
+ head = &b->decaying_flows;
+ if (!first_flow || list_empty(head)) {
+ head = &b->new_flows;
+ if (list_empty(head)) {
+ head = &b->old_flows;
+ if (unlikely(list_empty(head))) {
+ head = &b->decaying_flows;
+ if (unlikely(list_empty(head)))
+ goto begin;
+ }
+ }
+ }
+ flow = list_first_entry(head, struct cake_flow, flowchain);
+ q->cur_flow = flow - b->flows;
+ first_flow = false;
+
+ /* triple isolation (modified DRR++) */
+ srchost = &b->hosts[flow->srchost];
+ dsthost = &b->hosts[flow->dsthost];
+ host_load = 1;
+
+ if (cake_dsrc(q->flow_mode))
+ host_load = max(host_load, srchost->srchost_refcnt);
+
+ if (cake_ddst(q->flow_mode))
+ host_load = max(host_load, dsthost->dsthost_refcnt);
+
+ WARN_ON(host_load > CAKE_QUEUES);
+
+ /* flow isolation (DRR++) */
+ if (flow->deficit <= 0) {
+ /* The shifted prandom_u32() is a way to apply dithering to
+ * avoid accumulating roundoff errors
+ */
+ flow->deficit += (b->flow_quantum * quantum_div[host_load] +
+ (prandom_u32() >> 16)) >> 16;
+ list_move_tail(&flow->flowchain, &b->old_flows);
+
+ /* Keep all flows with deficits out of the sparse and decaying
+ * rotations. No non-empty flow can go into the decaying
+ * rotation, so they can't get deficits
+ */
+ if (flow->set == CAKE_SET_SPARSE) {
+ if (flow->head) {
+ b->sparse_flow_count--;
+ b->bulk_flow_count++;
+ flow->set = CAKE_SET_BULK;
+ } else {
+ /* we've moved it to the bulk rotation for
+ * correct deficit accounting but we still want
+ * to count it as a sparse flow, not a bulk one.
+ */
+ flow->set = CAKE_SET_SPARSE_WAIT;
+ }
+ }
+ goto retry;
+ }
+
+ /* Retrieve a packet via the AQM */
+ while (1) {
+ skb = cake_dequeue_one(sch);
+ if (!skb) {
+ /* this queue was actually empty */
+ if (cobalt_queue_empty(&flow->cvars, &b->cparams, now))
+ b->unresponsive_flow_count--;
+
+ if (flow->cvars.p_drop || flow->cvars.count ||
+ now < flow->cvars.drop_next) {
+ /* keep in the flowchain until the state has
+ * decayed to rest
+ */
+ list_move_tail(&flow->flowchain,
+ &b->decaying_flows);
+ if (flow->set == CAKE_SET_BULK) {
+ b->bulk_flow_count--;
+ b->decaying_flow_count++;
+ } else if (flow->set == CAKE_SET_SPARSE ||
+ flow->set == CAKE_SET_SPARSE_WAIT) {
+ b->sparse_flow_count--;
+ b->decaying_flow_count++;
+ }
+ flow->set = CAKE_SET_DECAYING;
+ } else {
+ /* remove empty queue from the flowchain */
+ list_del_init(&flow->flowchain);
+ if (flow->set == CAKE_SET_SPARSE ||
+ flow->set == CAKE_SET_SPARSE_WAIT)
+ b->sparse_flow_count--;
+ else if (flow->set == CAKE_SET_BULK)
+ b->bulk_flow_count--;
+ else
+ b->decaying_flow_count--;
+
+ flow->set = CAKE_SET_NONE;
+ srchost->srchost_refcnt--;
+ dsthost->dsthost_refcnt--;
+ }
+ goto begin;
+ }
+
+ /* Last packet in queue may be marked, shouldn't be dropped */
+ if (!cobalt_should_drop(&flow->cvars, &b->cparams, now, skb,
+ (b->bulk_flow_count *
+ !!(q->rate_flags & CAKE_FLAG_INGRESS))) ||
+ !flow->head)
+ break;
+
+ /* drop this packet, get another one */
+ if (q->rate_flags & CAKE_FLAG_INGRESS) {
+ len = cake_advance_shaper(q, b, skb,
+ now, true);
+ flow->deficit -= len;
+ b->tin_deficit -= len;
+ }
+ b->tin_dropped++;
+ qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb));
+ qdisc_qstats_drop(sch);
+ kfree_skb(skb);
+ if (q->rate_flags & CAKE_FLAG_INGRESS)
+ goto retry;
+ }
+
+ b->tin_ecn_mark += !!flow->cvars.ecn_marked;
+ qdisc_bstats_update(sch, skb);
+
+ /* collect delay stats */
+ delay = now - cobalt_get_enqueue_time(skb);
+ b->avge_delay = cake_ewma(b->avge_delay, delay, 8);
+ b->peak_delay = cake_ewma(b->peak_delay, delay,
+ delay > b->peak_delay ? 2 : 8);
+ b->base_delay = cake_ewma(b->base_delay, delay,
+ delay < b->base_delay ? 2 : 8);
+
+ len = cake_advance_shaper(q, b, skb, now, false);
+ flow->deficit -= len;
+ b->tin_deficit -= len;
+
+ if (q->time_next_packet > now && sch->q.qlen) {
+ u64 next = min(q->time_next_packet, q->failsafe_next_packet);
+
+ qdisc_watchdog_schedule_ns(&q->watchdog, next);
+ } else if (!sch->q.qlen) {
+ int i;
+
+ for (i = 0; i < q->tin_cnt; i++) {
+ if (q->tins[i].decaying_flow_count) {
+ u64 next = now + q->tins[i].cparams.target;
+
+ qdisc_watchdog_schedule_ns(&q->watchdog, next);
+ break;
+ }
+ }
+ }
+
+ if (q->overflow_timeout)
+ q->overflow_timeout--;
+
+ return skb;
+}
+
+static void cake_reset(struct Qdisc *sch)
+{
+ u32 c;
+
+ for (c = 0; c < CAKE_MAX_TINS; c++)
+ cake_clear_tin(sch, c);
+}
+
+static const struct nla_policy cake_policy[TCA_CAKE_MAX + 1] = {
+ [TCA_CAKE_BASE_RATE] = { .type = NLA_U32 },
+ [TCA_CAKE_DIFFSERV_MODE] = { .type = NLA_U32 },
+ [TCA_CAKE_ATM] = { .type = NLA_U32 },
+ [TCA_CAKE_FLOW_MODE] = { .type = NLA_U32 },
+ [TCA_CAKE_OVERHEAD] = { .type = NLA_S32 },
+ [TCA_CAKE_RTT] = { .type = NLA_U32 },
+ [TCA_CAKE_TARGET] = { .type = NLA_U32 },
+ [TCA_CAKE_AUTORATE] = { .type = NLA_U32 },
+ [TCA_CAKE_MEMORY] = { .type = NLA_U32 },
+ [TCA_CAKE_NAT] = { .type = NLA_U32 },
+ [TCA_CAKE_RAW] = { .type = NLA_U32 },
+ [TCA_CAKE_WASH] = { .type = NLA_U32 },
+ [TCA_CAKE_MPU] = { .type = NLA_U32 },
+ [TCA_CAKE_INGRESS] = { .type = NLA_U32 },
+ [TCA_CAKE_ACK_FILTER] = { .type = NLA_U32 },
+};
+
+static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu,
+ cobalt_time_t ns_target, cobalt_time_t rtt_est_ns)
+{
+ /* convert byte-rate into time-per-byte
+ * so it will always unwedge in reasonable time.
+ */
+ static const u64 MIN_RATE = 64;
+ u64 rate_ns = 0;
+ u8 rate_shft = 0;
+ cobalt_time_t byte_target_ns;
+ u32 byte_target = mtu;
+
+ b->flow_quantum = 1514;
+ if (rate) {
+ b->flow_quantum = max(min(rate >> 12, 1514ULL), 300ULL);
+ rate_shft = 32;
+ rate_ns = ((u64)NSEC_PER_SEC) << rate_shft;
+ do_div(rate_ns, max(MIN_RATE, rate));
+ while (!!(rate_ns >> 32)) {
+ rate_ns >>= 1;
+ rate_shft--;
+ }
+ } /* else unlimited, ie. zero delay */
+
+ b->tin_rate_bps = rate;
+ b->tin_rate_ns = rate_ns;
+ b->tin_rate_shft = rate_shft;
+
+ byte_target_ns = (byte_target * rate_ns) >> rate_shft;
+
+ b->cparams.target = max((byte_target_ns * 3) / 2, ns_target);
+ b->cparams.interval = max(rtt_est_ns +
+ b->cparams.target - ns_target,
+ b->cparams.target * 2);
+ b->cparams.mtu_time = byte_target_ns;
+ b->cparams.p_inc = 1 << 24; /* 1/256 */
+ b->cparams.p_dec = 1 << 20; /* 1/4096 */
+}
+
+static int cake_config_besteffort(struct Qdisc *sch)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ struct cake_tin_data *b = &q->tins[0];
+ u32 rate = q->rate_bps;
+ u32 mtu = psched_mtu(qdisc_dev(sch));
+
+ q->tin_cnt = 1;
+
+ q->tin_index = besteffort;
+ q->tin_order = normal_order;
+
+ cake_set_rate(b, rate, mtu, US2TIME(q->target), US2TIME(q->interval));
+ b->tin_quantum_band = 65535;
+ b->tin_quantum_prio = 65535;
+
+ return 0;
+}
+
+static int cake_config_precedence(struct Qdisc *sch)
+{
+ /* convert high-level (user visible) parameters into internal format */
+ struct cake_sched_data *q = qdisc_priv(sch);
+ u32 rate = q->rate_bps;
+ u32 mtu = psched_mtu(qdisc_dev(sch));
+ u32 quantum1 = 256;
+ u32 quantum2 = 256;
+ u32 i;
+
+ q->tin_cnt = 8;
+ q->tin_index = precedence;
+ q->tin_order = normal_order;
+
+ for (i = 0; i < q->tin_cnt; i++) {
+ struct cake_tin_data *b = &q->tins[i];
+
+ cake_set_rate(b, rate, mtu, US2TIME(q->target),
+ US2TIME(q->interval));
+
+ b->tin_quantum_prio = max_t(u16, 1U, quantum1);
+ b->tin_quantum_band = max_t(u16, 1U, quantum2);
+
+ /* calculate next class's parameters */
+ rate *= 7;
+ rate >>= 3;
+
+ quantum1 *= 3;
+ quantum1 >>= 1;
+
+ quantum2 *= 7;
+ quantum2 >>= 3;
+ }
+
+ return 0;
+}
+
+/* List of known Diffserv codepoints:
+ *
+ * Least Effort (CS1)
+ * Best Effort (CS0)
+ * Max Reliability & LLT "Lo" (TOS1)
+ * Max Throughput (TOS2)
+ * Min Delay (TOS4)
+ * LLT "La" (TOS5)
+ * Assured Forwarding 1 (AF1x) - x3
+ * Assured Forwarding 2 (AF2x) - x3
+ * Assured Forwarding 3 (AF3x) - x3
+ * Assured Forwarding 4 (AF4x) - x3
+ * Precedence Class 2 (CS2)
+ * Precedence Class 3 (CS3)
+ * Precedence Class 4 (CS4)
+ * Precedence Class 5 (CS5)
+ * Precedence Class 6 (CS6)
+ * Precedence Class 7 (CS7)
+ * Voice Admit (VA)
+ * Expedited Forwarding (EF)
+
+ * Total 25 codepoints.
+ */
+
+/* List of traffic classes in RFC 4594:
+ * (roughly descending order of contended priority)
+ * (roughly ascending order of uncontended throughput)
+ *
+ * Network Control (CS6,CS7) - routing traffic
+ * Telephony (EF,VA) - aka. VoIP streams
+ * Signalling (CS5) - VoIP setup
+ * Multimedia Conferencing (AF4x) - aka. video calls
+ * Realtime Interactive (CS4) - eg. games
+ * Multimedia Streaming (AF3x) - eg. YouTube, NetFlix, Twitch
+ * Broadcast Video (CS3)
+ * Low Latency Data (AF2x,TOS4) - eg. database
+ * Ops, Admin, Management (CS2,TOS1) - eg. ssh
+ * Standard Service (CS0 & unrecognised codepoints)
+ * High Throughput Data (AF1x,TOS2) - eg. web traffic
+ * Low Priority Data (CS1) - eg. BitTorrent
+
+ * Total 12 traffic classes.
+ */
+
+static int cake_config_diffserv8(struct Qdisc *sch)
+{
+/* Pruned list of traffic classes for typical applications:
+ *
+ * Network Control (CS6, CS7)
+ * Minimum Latency (EF, VA, CS5, CS4)
+ * Interactive Shell (CS2, TOS1)
+ * Low Latency Transactions (AF2x, TOS4)
+ * Video Streaming (AF4x, AF3x, CS3)
+ * Bog Standard (CS0 etc.)
+ * High Throughput (AF1x, TOS2)
+ * Background Traffic (CS1)
+ *
+ * Total 8 traffic classes.
+ */
+
+ struct cake_sched_data *q = qdisc_priv(sch);
+ u32 rate = q->rate_bps;
+ u32 mtu = psched_mtu(qdisc_dev(sch));
+ u32 quantum1 = 256;
+ u32 quantum2 = 256;
+ u32 i;
+
+ q->tin_cnt = 8;
+
+ /* codepoint to class mapping */
+ q->tin_index = diffserv8;
+ q->tin_order = normal_order;
+
+ /* class characteristics */
+ for (i = 0; i < q->tin_cnt; i++) {
+ struct cake_tin_data *b = &q->tins[i];
+
+ cake_set_rate(b, rate, mtu, US2TIME(q->target),
+ US2TIME(q->interval));
+
+ b->tin_quantum_prio = max_t(u16, 1U, quantum1);
+ b->tin_quantum_band = max_t(u16, 1U, quantum2);
+
+ /* calculate next class's parameters */
+ rate *= 7;
+ rate >>= 3;
+
+ quantum1 *= 3;
+ quantum1 >>= 1;
+
+ quantum2 *= 7;
+ quantum2 >>= 3;
+ }
+
+ return 0;
+}
+
+static int cake_config_diffserv4(struct Qdisc *sch)
+{
+/* Further pruned list of traffic classes for four-class system:
+ *
+ * Latency Sensitive (CS7, CS6, EF, VA, CS5, CS4)
+ * Streaming Media (AF4x, AF3x, CS3, AF2x, TOS4, CS2, TOS1)
+ * Best Effort (CS0, AF1x, TOS2, and those not specified)
+ * Background Traffic (CS1)
+ *
+ * Total 4 traffic classes.
+ */
+
+ struct cake_sched_data *q = qdisc_priv(sch);
+ u32 rate = q->rate_bps;
+ u32 mtu = psched_mtu(qdisc_dev(sch));
+ u32 quantum = 1024;
+
+ q->tin_cnt = 4;
+
+ /* codepoint to class mapping */
+ q->tin_index = diffserv4;
+ q->tin_order = bulk_order;
+
+ /* class characteristics */
+ cake_set_rate(&q->tins[0], rate, mtu,
+ US2TIME(q->target), US2TIME(q->interval));
+ cake_set_rate(&q->tins[1], rate >> 4, mtu,
+ US2TIME(q->target), US2TIME(q->interval));
+ cake_set_rate(&q->tins[2], rate >> 1, mtu,
+ US2TIME(q->target), US2TIME(q->interval));
+ cake_set_rate(&q->tins[3], rate >> 2, mtu,
+ US2TIME(q->target), US2TIME(q->interval));
+
+ /* priority weights */
+ q->tins[0].tin_quantum_prio = quantum;
+ q->tins[1].tin_quantum_prio = quantum >> 4;
+ q->tins[2].tin_quantum_prio = quantum << 2;
+ q->tins[3].tin_quantum_prio = quantum << 4;
+
+ /* bandwidth-sharing weights */
+ q->tins[0].tin_quantum_band = quantum;
+ q->tins[1].tin_quantum_band = quantum >> 4;
+ q->tins[2].tin_quantum_band = quantum >> 1;
+ q->tins[3].tin_quantum_band = quantum >> 2;
+
+ return 0;
+}
+
+static int cake_config_diffserv3(struct Qdisc *sch)
+{
+/* Simplified Diffserv structure with 3 tins.
+ * Low Priority (CS1)
+ * Best Effort
+ * Latency Sensitive (TOS4, VA, EF, CS6, CS7)
+ */
+ struct cake_sched_data *q = qdisc_priv(sch);
+ u32 rate = q->rate_bps;
+ u32 mtu = psched_mtu(qdisc_dev(sch));
+ u32 quantum = 1024;
+
+ q->tin_cnt = 3;
+
+ /* codepoint to class mapping */
+ q->tin_index = diffserv3;
+ q->tin_order = bulk_order;
+
+ /* class characteristics */
+ cake_set_rate(&q->tins[0], rate, mtu,
+ US2TIME(q->target), US2TIME(q->interval));
+ cake_set_rate(&q->tins[1], rate >> 4, mtu,
+ US2TIME(q->target), US2TIME(q->interval));
+ cake_set_rate(&q->tins[2], rate >> 2, mtu,
+ US2TIME(q->target), US2TIME(q->interval));
+
+ /* priority weights */
+ q->tins[0].tin_quantum_prio = quantum;
+ q->tins[1].tin_quantum_prio = quantum >> 4;
+ q->tins[2].tin_quantum_prio = quantum << 4;
+
+ /* bandwidth-sharing weights */
+ q->tins[0].tin_quantum_band = quantum;
+ q->tins[1].tin_quantum_band = quantum >> 4;
+ q->tins[2].tin_quantum_band = quantum >> 2;
+
+ return 0;
+}
+
+static void cake_reconfigure(struct Qdisc *sch)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ int c, ft;
+
+ switch (q->tin_mode) {
+ case CAKE_DIFFSERV_BESTEFFORT:
+ ft = cake_config_besteffort(sch);
+ break;
+
+ case CAKE_DIFFSERV_PRECEDENCE:
+ ft = cake_config_precedence(sch);
+ break;
+
+ case CAKE_DIFFSERV_DIFFSERV8:
+ ft = cake_config_diffserv8(sch);
+ break;
+
+ case CAKE_DIFFSERV_DIFFSERV4:
+ ft = cake_config_diffserv4(sch);
+ break;
+
+ case CAKE_DIFFSERV_DIFFSERV3:
+ default:
+ ft = cake_config_diffserv3(sch);
+ break;
+ };
+
+ for (c = q->tin_cnt; c < CAKE_MAX_TINS; c++) {
+ cake_clear_tin(sch, c);
+ q->tins[c].cparams.mtu_time = q->tins[ft].cparams.mtu_time;
+ }
+
+ q->rate_ns = q->tins[ft].tin_rate_ns;
+ q->rate_shft = q->tins[ft].tin_rate_shft;
+
+ if (q->buffer_config_limit) {
+ q->buffer_limit = q->buffer_config_limit;
+ } else if (q->rate_bps) {
+ u64 t = (u64)q->rate_bps * q->interval;
+
+ do_div(t, USEC_PER_SEC / 4);
+ q->buffer_limit = max_t(u32, t, 4U << 20);
+ } else {
+ q->buffer_limit = ~0;
+ }
+
+ sch->flags &= ~TCQ_F_CAN_BYPASS;
+
+ q->buffer_limit = min(q->buffer_limit,
+ max(sch->limit * psched_mtu(qdisc_dev(sch)),
+ q->buffer_config_limit));
+}
+
+static int cake_change(struct Qdisc *sch, struct nlattr *opt,
+ struct netlink_ext_ack *extack)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ struct nlattr *tb[TCA_CAKE_MAX + 1];
+ int err;
+
+ if (!opt)
+ return -EINVAL;
+
+ err = nla_parse_nested(tb, TCA_CAKE_MAX, opt, cake_policy, extack);
+ if (err < 0)
+ return err;
+
+ if (tb[TCA_CAKE_BASE_RATE])
+ q->rate_bps = nla_get_u32(tb[TCA_CAKE_BASE_RATE]);
+
+ if (tb[TCA_CAKE_DIFFSERV_MODE])
+ q->tin_mode = nla_get_u32(tb[TCA_CAKE_DIFFSERV_MODE]);
+
+ if (tb[TCA_CAKE_ATM])
+ q->atm_mode = nla_get_u32(tb[TCA_CAKE_ATM]);
+
+ if (tb[TCA_CAKE_WASH]) {
+ if (!!nla_get_u32(tb[TCA_CAKE_WASH]))
+ q->rate_flags |= CAKE_FLAG_WASH;
+ else
+ q->rate_flags &= ~CAKE_FLAG_WASH;
+ }
+
+ if (tb[TCA_CAKE_FLOW_MODE])
+ q->flow_mode = nla_get_u32(tb[TCA_CAKE_FLOW_MODE]);
+
+ if (tb[TCA_CAKE_NAT]) {
+ q->flow_mode &= ~CAKE_FLOW_NAT_FLAG;
+ q->flow_mode |= CAKE_FLOW_NAT_FLAG *
+ !!nla_get_u32(tb[TCA_CAKE_NAT]);
+ }
+
+ if (tb[TCA_CAKE_OVERHEAD]) {
+ q->rate_overhead = nla_get_s32(tb[TCA_CAKE_OVERHEAD]);
+ q->rate_flags |= CAKE_FLAG_OVERHEAD;
+
+ q->max_netlen = q->max_adjlen = 0;
+ q->min_netlen = q->min_adjlen = ~0;
+ }
+
+ if (tb[TCA_CAKE_RAW]) {
+ q->rate_flags &= ~CAKE_FLAG_OVERHEAD;
+
+ q->max_netlen = q->max_adjlen = 0;
+ q->min_netlen = q->min_adjlen = ~0;
+ }
+
+ if (tb[TCA_CAKE_MPU])
+ q->rate_mpu = nla_get_u32(tb[TCA_CAKE_MPU]);
+
+ if (tb[TCA_CAKE_RTT]) {
+ q->interval = nla_get_u32(tb[TCA_CAKE_RTT]);
+
+ if (!q->interval)
+ q->interval = 1;
+ }
+
+ if (tb[TCA_CAKE_TARGET]) {
+ q->target = nla_get_u32(tb[TCA_CAKE_TARGET]);
+
+ if (!q->target)
+ q->target = 1;
+ }
+
+ if (tb[TCA_CAKE_AUTORATE]) {
+ if (!!nla_get_u32(tb[TCA_CAKE_AUTORATE]))
+ q->rate_flags |= CAKE_FLAG_AUTORATE_INGRESS;
+ else
+ q->rate_flags &= ~CAKE_FLAG_AUTORATE_INGRESS;
+ }
+
+ if (tb[TCA_CAKE_INGRESS]) {
+ if (!!nla_get_u32(tb[TCA_CAKE_INGRESS]))
+ q->rate_flags |= CAKE_FLAG_INGRESS;
+ else
+ q->rate_flags &= ~CAKE_FLAG_INGRESS;
+ }
+
+ if (tb[TCA_CAKE_ACK_FILTER])
+ q->ack_filter = nla_get_u32(tb[TCA_CAKE_ACK_FILTER]);
+
+ if (tb[TCA_CAKE_MEMORY])
+ q->buffer_config_limit = nla_get_u32(tb[TCA_CAKE_MEMORY]);
+
+ if (q->tins) {
+ sch_tree_lock(sch);
+ cake_reconfigure(sch);
+ sch_tree_unlock(sch);
+ }
+
+ return 0;
+}
+
+static void *cake_zalloc(size_t sz)
+{
+ void *ptr = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN);
+
+ if (!ptr)
+ ptr = vzalloc(sz);
+ return ptr;
+}
+
+static void cake_free(void *addr)
+{
+ if (addr)
+ kvfree(addr);
+}
+
+static void cake_destroy(struct Qdisc *sch)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+
+ qdisc_watchdog_cancel(&q->watchdog);
+
+ if (q->tins)
+ cake_free(q->tins);
+}
+
+static int cake_init(struct Qdisc *sch, struct nlattr *opt,
+ struct netlink_ext_ack *extack)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ int i, j;
+
+ sch->limit = 10240;
+ q->tin_mode = CAKE_DIFFSERV_DIFFSERV3;
+ q->flow_mode = CAKE_FLOW_TRIPLE;
+
+ q->rate_bps = 0; /* unlimited by default */
+
+ q->interval = 100000; /* 100ms default */
+ q->target = 5000; /* 5ms: codel RFC argues
+ * for 5 to 10% of interval
+ */
+
+ q->cur_tin = 0;
+ q->cur_flow = 0;
+
+ if (opt) {
+ int err = cake_change(sch, opt, extack);
+
+ if (err)
+ return err;
+ }
+
+ qdisc_watchdog_init(&q->watchdog, sch);
+
+ quantum_div[0] = ~0;
+ for (i = 1; i <= CAKE_QUEUES; i++)
+ quantum_div[i] = 65535 / i;
+
+ q->tins = cake_zalloc(CAKE_MAX_TINS * sizeof(struct cake_tin_data));
+ if (!q->tins)
+ goto nomem;
+
+ for (i = 0; i < CAKE_MAX_TINS; i++) {
+ struct cake_tin_data *b = q->tins + i;
+
+ b->perturb = prandom_u32();
+ INIT_LIST_HEAD(&b->new_flows);
+ INIT_LIST_HEAD(&b->old_flows);
+ INIT_LIST_HEAD(&b->decaying_flows);
+ b->sparse_flow_count = 0;
+ b->bulk_flow_count = 0;
+ b->decaying_flow_count = 0;
+
+ for (j = 0; j < CAKE_QUEUES; j++) {
+ struct cake_flow *flow = b->flows + j;
+ u32 k = j * CAKE_MAX_TINS + i;
+
+ INIT_LIST_HEAD(&flow->flowchain);
+ cobalt_vars_init(&flow->cvars);
+
+ q->overflow_heap[k].t = i;
+ q->overflow_heap[k].b = j;
+ b->overflow_idx[j] = k;
+ }
+ }
+
+ cake_reconfigure(sch);
+ q->avg_peak_bandwidth = q->rate_bps;
+ q->min_netlen = q->min_adjlen = ~0;
+ return 0;
+
+nomem:
+ cake_destroy(sch);
+ return -ENOMEM;
+}
+
+static int cake_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ struct nlattr *opts;
+
+ opts = nla_nest_start(skb, TCA_OPTIONS);
+ if (!opts)
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_BASE_RATE, q->rate_bps))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_DIFFSERV_MODE, q->tin_mode))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_ATM, q->atm_mode))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_FLOW_MODE,
+ q->flow_mode & ~CAKE_FLOW_NAT_FLAG))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_NAT,
+ !!(q->flow_mode & CAKE_FLOW_NAT_FLAG)))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_WASH,
+ !!(q->rate_flags & CAKE_FLAG_WASH)))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_OVERHEAD, q->rate_overhead))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_MPU, q->rate_mpu))
+ goto nla_put_failure;
+
+ if (!(q->rate_flags & CAKE_FLAG_OVERHEAD))
+ if (nla_put_u32(skb, TCA_CAKE_RAW, 0))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_RTT, q->interval))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_TARGET, q->target))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_AUTORATE,
+ !!(q->rate_flags & CAKE_FLAG_AUTORATE_INGRESS)))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_INGRESS,
+ !!(q->rate_flags & CAKE_FLAG_INGRESS)))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_ACK_FILTER, q->ack_filter))
+ goto nla_put_failure;
+
+ if (nla_put_u32(skb, TCA_CAKE_MEMORY, q->buffer_config_limit))
+ goto nla_put_failure;
+
+ return nla_nest_end(skb, opts);
+
+nla_put_failure:
+ return -1;
+}
+
+static int cake_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
+{
+ struct cake_sched_data *q = qdisc_priv(sch);
+ struct nlattr *stats = nla_nest_start(d->skb, TCA_STATS_APP);
+ struct nlattr *tstats, *ts;
+ int i;
+
+ if (!stats)
+ return -1;
+
+#define PUT_STAT_U32(attr, data) do { \
+ if(nla_put_u32(d->skb, TCA_CAKE_STATS_ ## attr, data)) \
+ goto nla_put_failure; \
+ } while (0);
+
+ PUT_STAT_U32(CAPACITY_ESTIMATE, q->avg_peak_bandwidth);
+ PUT_STAT_U32(MEMORY_LIMIT, q->buffer_limit);
+ PUT_STAT_U32(MEMORY_USED, q->buffer_max_used);
+ PUT_STAT_U32(AVG_NETOFF, ((q->avg_netoff + 0x8000) >> 16));
+ PUT_STAT_U32(MAX_NETLEN, q->max_netlen);
+ PUT_STAT_U32(MAX_ADJLEN, q->max_adjlen);
+ PUT_STAT_U32(MIN_NETLEN, q->min_netlen);
+ PUT_STAT_U32(MIN_ADJLEN, q->min_adjlen);
+
+#undef PUT_STAT_U32
+
+ tstats = nla_nest_start(d->skb, TCA_CAKE_STATS_TIN_STATS);
+ if (!tstats)
+ goto nla_put_failure;
+
+#define PUT_TSTAT_U32(attr, data) do { \
+ if(nla_put_u32(d->skb, TCA_CAKE_TIN_STATS_ ## attr, data)) \
+ goto nla_put_failure; \
+ } while (0);
+#define PUT_TSTAT_U64(attr, data) do { \
+ if(nla_put_u64_64bit(d->skb, TCA_CAKE_TIN_STATS_ ## attr, \
+ data, TCA_CAKE_TIN_STATS_PAD)) \
+ goto nla_put_failure; \
+ } while (0);
+
+ for (i = 0; i < q->tin_cnt; i++) {
+ struct cake_tin_data *b = &q->tins[q->tin_order[i]];
+
+ ts = nla_nest_start(d->skb, i + 1);
+ if (!ts)
+ goto nla_put_failure;
+
+ PUT_TSTAT_U32(THRESHOLD_RATE, b->tin_rate_bps);
+ PUT_TSTAT_U32(TARGET_US, cobalt_time_to_us(b->cparams.target));
+ PUT_TSTAT_U32(INTERVAL_US, cobalt_time_to_us(b->cparams.interval));
+
+ PUT_TSTAT_U32(SENT_PACKETS, b->packets);
+ PUT_TSTAT_U64(SENT_BYTES64, b->bytes);
+ PUT_TSTAT_U32(DROPPED_PACKETS, b->tin_dropped);
+ PUT_TSTAT_U32(ECN_MARKED_PACKETS, b->tin_ecn_mark);
+ PUT_TSTAT_U64(BACKLOG_BYTES64, b->tin_backlog);
+ PUT_TSTAT_U32(ACKS_DROPPED_PACKETS, b->ack_drops);
+
+ PUT_TSTAT_U32(PEAK_DELAY_US, cobalt_time_to_us(b->peak_delay));
+ PUT_TSTAT_U32(AVG_DELAY_US, cobalt_time_to_us(b->avge_delay));
+ PUT_TSTAT_U32(BASE_DELAY_US, cobalt_time_to_us(b->base_delay));
+
+ PUT_TSTAT_U32(WAY_INDIRECT_HITS, b->way_hits);
+ PUT_TSTAT_U32(WAY_MISSES, b->way_misses);
+ PUT_TSTAT_U32(WAY_COLLISIONS, b->way_collisions);
+
+ PUT_TSTAT_U32(SPARSE_FLOWS, b->sparse_flow_count +
+ b->decaying_flow_count);
+ PUT_TSTAT_U32(BULK_FLOWS, b->bulk_flow_count);
+ PUT_TSTAT_U32(UNRESPONSIVE_FLOWS, b->unresponsive_flow_count);
+ PUT_TSTAT_U32(MAX_SKBLEN, b->max_skblen);
+
+ PUT_TSTAT_U32(FLOW_QUANTUM, b->flow_quantum);
+ nla_nest_end(d->skb, ts);
+ }
+
+#undef PUT_TSTAT_U32
+#undef PUT_TSTAT_U64
+
+ nla_nest_end(d->skb, tstats);
+ return nla_nest_end(d->skb, stats);
+
+nla_put_failure:
+ nla_nest_cancel(d->skb, stats);
+ return -1;
+}
+
+static struct Qdisc_ops cake_qdisc_ops __read_mostly = {
+ .id = "cake",
+ .priv_size = sizeof(struct cake_sched_data),
+ .enqueue = cake_enqueue,
+ .dequeue = cake_dequeue,
+ .peek = qdisc_peek_dequeued,
+ .init = cake_init,
+ .reset = cake_reset,
+ .destroy = cake_destroy,
+ .change = cake_change,
+ .dump = cake_dump,
+ .dump_stats = cake_dump_stats,
+ .owner = THIS_MODULE,
+};
+
+static int __init cake_module_init(void)
+{
+ return register_qdisc(&cake_qdisc_ops);
+}
+
+static void __exit cake_module_exit(void)
+{
+ unregister_qdisc(&cake_qdisc_ops);
+}
+
+module_init(cake_module_init)
+module_exit(cake_module_exit)
+MODULE_AUTHOR("Jonathan Morton");
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("The CAKE shaper.");
--
2.17.0
^ permalink raw reply related
* Re: [PATCH net-next 1/2] tcp: add TCP_ZEROCOPY_RECEIVE support for zerocopy receive
From: Eric Dumazet @ 2018-04-25 13:42 UTC (permalink / raw)
To: Eric Dumazet, David S . Miller
Cc: netdev, Andy Lutomirski, linux-kernel, linux-mm,
Soheil Hassas Yeganeh, Eric Dumazet
In-Reply-To: <20180425052722.73022-2-edumazet@google.com>
On 04/24/2018 10:27 PM, Eric Dumazet wrote:
> When adding tcp mmap() implementation, I forgot that socket lock
> had to be taken before current->mm->mmap_sem. syzbot eventually caught
> the bug.
> +
...
> + down_read(¤t->mm->mmap_sem);
> +
> + ret = -EINVAL;
> + vma = find_vma(current->mm, address);
> + if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops)
> goto out;
> - }
> + zc->length = min_t(unsigned long, zc->length, vma->vm_end - address);
> +
> tp = tcp_sk(sk);
> seq = tp->copied_seq;
> - /* Abort if urgent data is in the area */
> - if (unlikely(tp->urg_data)) {
> - u32 urg_offset = tp->urg_seq - seq;
> + zc->length = min_t(u32, zc->length, tcp_inq(sk));
>
>
I might have to make sure zc->length is page aligned before calling zap_page_range() ?
zc->length &= ~(PAGE_SIZE - 1);
+ zap_page_range(vma, address, zc->length);
^ permalink raw reply
* Re: [PATCH net-next] sctp: remove the unused sctp_assoc_is_match function
From: Marcelo Ricardo Leitner @ 2018-04-25 13:41 UTC (permalink / raw)
To: Xin Long; +Cc: network dev, linux-sctp, Neil Horman, davem
In-Reply-To: <0acb8eaec9a5be9959d39bb5017d49bb31d0d5e5.1524649607.git.lucien.xin@gmail.com>
On Wed, Apr 25, 2018 at 05:46:47PM +0800, Xin Long wrote:
> After Commit 4f0087812648 ("sctp: apply rhashtable api to send/recv
> path"), there's no place using sctp_assoc_is_match, so remove it.
>
> Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
> ---
> include/net/sctp/structs.h | 4 ----
> net/sctp/associola.c | 25 -------------------------
> 2 files changed, 29 deletions(-)
>
> diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
> index a0ec462..05594b2 100644
> --- a/include/net/sctp/structs.h
> +++ b/include/net/sctp/structs.h
> @@ -2091,10 +2091,6 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
> enum sctp_transport_cmd command,
> sctp_sn_error_t error);
> struct sctp_transport *sctp_assoc_lookup_tsn(struct sctp_association *, __u32);
> -struct sctp_transport *sctp_assoc_is_match(struct sctp_association *,
> - struct net *,
> - const union sctp_addr *,
> - const union sctp_addr *);
> void sctp_assoc_migrate(struct sctp_association *, struct sock *);
> int sctp_assoc_update(struct sctp_association *old,
> struct sctp_association *new);
> diff --git a/net/sctp/associola.c b/net/sctp/associola.c
> index 837806d..a8f3b08 100644
> --- a/net/sctp/associola.c
> +++ b/net/sctp/associola.c
> @@ -988,31 +988,6 @@ struct sctp_transport *sctp_assoc_lookup_tsn(struct sctp_association *asoc,
> return match;
> }
>
> -/* Is this the association we are looking for? */
> -struct sctp_transport *sctp_assoc_is_match(struct sctp_association *asoc,
> - struct net *net,
> - const union sctp_addr *laddr,
> - const union sctp_addr *paddr)
> -{
> - struct sctp_transport *transport;
> -
> - if ((htons(asoc->base.bind_addr.port) == laddr->v4.sin_port) &&
> - (htons(asoc->peer.port) == paddr->v4.sin_port) &&
> - net_eq(sock_net(asoc->base.sk), net)) {
> - transport = sctp_assoc_lookup_paddr(asoc, paddr);
> - if (!transport)
> - goto out;
> -
> - if (sctp_bind_addr_match(&asoc->base.bind_addr, laddr,
> - sctp_sk(asoc->base.sk)))
> - goto out;
> - }
> - transport = NULL;
> -
> -out:
> - return transport;
> -}
> -
> /* Do delayed input processing. This is scheduled by sctp_rcv(). */
> static void sctp_assoc_bh_rcv(struct work_struct *work)
> {
> --
> 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
>
^ permalink raw reply
* [PATCH net-next] microchipT1phy: Add driver for Microchip LAN87XX T1 PHYs
From: Nisar Sayed @ 2018-04-25 18:49 UTC (permalink / raw)
To: davem; +Cc: UNGLinuxDriver, netdev
Add driver for Microchip LAN87XX T1 PHYs
This patch support driver for Microchp T1 PHYs.
There will be followup patches to this driver to support T1 PHY
features such as cable diagnostics, signal quality indicator(SQI),
sleep and wakeup (TC10) support.
Signed-off-by: Nisar Sayed <Nisar.Sayed@microchip.com>
---
drivers/net/phy/Kconfig | 5 ++
drivers/net/phy/Makefile | 1 +
drivers/net/phy/microchipT1phy.c | 116 +++++++++++++++++++++++++++++++++++++++
include/linux/microchipT1phy.h | 28 ++++++++++
4 files changed, 150 insertions(+)
create mode 100644 drivers/net/phy/microchipT1phy.c
create mode 100644 include/linux/microchipT1phy.h
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index bdfbabb..7b0b351 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -354,6 +354,11 @@ config MICROCHIP_PHY
help
Supports the LAN88XX PHYs.
+config MICROCHIP_T1_PHY
+ tristate "Microchip T1 PHYs"
+ ---help---
+ Supports the LAN87XX PHYs.
+
config MICROSEMI_PHY
tristate "Microsemi PHYs"
---help---
diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index 01acbcb..5706613 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -70,6 +70,7 @@ obj-$(CONFIG_MESON_GXL_PHY) += meson-gxl.o
obj-$(CONFIG_MICREL_KS8995MA) += spi_ks8995.o
obj-$(CONFIG_MICREL_PHY) += micrel.o
obj-$(CONFIG_MICROCHIP_PHY) += microchip.o
+obj-$(CONFIG_MICROCHIP_T1_PHY) += microchipT1phy.o
obj-$(CONFIG_MICROSEMI_PHY) += mscc.o
obj-$(CONFIG_NATIONAL_PHY) += national.o
obj-$(CONFIG_QSEMI_PHY) += qsemi.o
diff --git a/drivers/net/phy/microchipT1phy.c b/drivers/net/phy/microchipT1phy.c
new file mode 100644
index 0000000..15fbb04
--- /dev/null
+++ b/drivers/net/phy/microchipT1phy.c
@@ -0,0 +1,116 @@
+/*
+ * Copyright (C) 2018 Microchip Technology
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mii.h>
+#include <linux/phy.h>
+#include <linux/microchipT1phy.h>
+
+#define DRIVER_AUTHOR "Nisar Sayed <nisar.sayed@microchip.com>"
+#define DRIVER_DESC "Microchip LAN87XX T1 PHY driver"
+
+struct lan87xx_priv {
+ int chip_id;
+ int chip_rev;
+};
+
+static int lan87xx_phy_config_intr(struct phy_device *phydev)
+{
+ int rc = 0;
+
+ if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+ /* unmask all source and clear them before enable */
+ rc = phy_write(phydev, LAN87XX_INTERRUPT_MASK, 0x7FFF);
+ rc = phy_read(phydev, LAN87XX_INTERRUPT_SOURCE);
+ rc = phy_write(phydev, LAN87XX_INTERRUPT_MASK,
+ LAN87XX_MASK_LINK_UP | LAN87XX_MASK_LINK_DOWN);
+ } else {
+ rc = phy_write(phydev, LAN87XX_INTERRUPT_MASK, 0);
+ }
+
+ return rc < 0 ? rc : 0;
+}
+
+static int lan87xx_phy_ack_interrupt(struct phy_device *phydev)
+{
+ int rc = phy_read(phydev, LAN87XX_INTERRUPT_SOURCE);
+
+ return rc < 0 ? rc : 0;
+}
+
+static int lan87xx_probe(struct phy_device *phydev)
+{
+ struct device *dev = &phydev->mdio.dev;
+ struct lan87xx_priv *priv;
+
+ priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+ if (!priv)
+ return -ENOMEM;
+
+ /* these values can be used to identify internal PHY */
+ priv->chip_id = phy_read(phydev, MII_PHYSID1);
+ priv->chip_rev = phy_read(phydev, MII_PHYSID2);
+
+ phydev->priv = priv;
+
+ return 0;
+}
+
+static void lan87xx_remove(struct phy_device *phydev)
+{
+ struct device *dev = &phydev->mdio.dev;
+ struct lan87xx_priv *priv = phydev->priv;
+
+ if (priv)
+ devm_kfree(dev, priv);
+}
+
+static struct phy_driver microchip_T1_phy_driver[] = {
+ {
+ .phy_id = 0x0007c150,
+ .phy_id_mask = 0xfffffff0,
+ .name = "Microchip LAN87xx",
+
+ .features = SUPPORTED_100baseT_Full,
+ .flags = PHY_HAS_INTERRUPT,
+
+ .probe = lan87xx_probe,
+ .remove = lan87xx_remove,
+
+ .config_init = genphy_config_init,
+ .config_aneg = genphy_config_aneg,
+
+ .ack_interrupt = lan87xx_phy_ack_interrupt,
+ .config_intr = lan87xx_phy_config_intr,
+
+ .suspend = genphy_suspend,
+ .resume = genphy_resume,
+ }
+};
+
+module_phy_driver(microchip_T1_phy_driver);
+
+static struct mdio_device_id __maybe_unused microchip_T1_tbl[] = {
+ { 0x0007c150, 0xfffffff0 },
+ { }
+};
+
+MODULE_DEVICE_TABLE(mdio, microchip_T1_tbl);
+
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
diff --git a/include/linux/microchipT1phy.h b/include/linux/microchipT1phy.h
new file mode 100644
index 0000000..7353e7c
--- /dev/null
+++ b/include/linux/microchipT1phy.h
@@ -0,0 +1,28 @@
+/*
+ * Copyright (C) 2018 Microchip Technology
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef _MICROCHIPT1PHY_H_
+#define _MICROCHIPT1PHY_H_
+
+/* Interrupt Source Register */
+#define LAN87XX_INTERRUPT_SOURCE (0x18)
+
+/* Interrupt Mask Register */
+#define LAN87XX_INTERRUPT_MASK (0x19)
+#define LAN87XX_MASK_LINK_UP (0x0004)
+#define LAN87XX_MASK_LINK_DOWN (0x0002)
+
+#endif /* _MICROCHIPT1PHY_H_ */
--
2.14.1
^ permalink raw reply related
* Re: [PATCH net-next 1/2] tcp: add TCP_ZEROCOPY_RECEIVE support for zerocopy receive
From: Eric Dumazet @ 2018-04-25 13:01 UTC (permalink / raw)
To: Christoph Hellwig, Eric Dumazet
Cc: David S . Miller, netdev, Andy Lutomirski, linux-kernel, linux-mm,
Soheil Hassas Yeganeh
In-Reply-To: <20180425062859.GA23914@infradead.org>
On 04/24/2018 11:28 PM, Christoph Hellwig wrote:
> On Tue, Apr 24, 2018 at 10:27:21PM -0700, Eric Dumazet wrote:
>> When adding tcp mmap() implementation, I forgot that socket lock
>> had to be taken before current->mm->mmap_sem. syzbot eventually caught
>> the bug.
>>
>> Since we can not lock the socket in tcp mmap() handler we have to
>> split the operation in two phases.
>>
>> 1) mmap() on a tcp socket simply reserves VMA space, and nothing else.
>> This operation does not involve any TCP locking.
>>
>> 2) setsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, ...) implements
>> the transfert of pages from skbs to one VMA.
>> This operation only uses down_read(¤t->mm->mmap_sem) after
>> holding TCP lock, thus solving the lockdep issue.
>>
>> This new implementation was suggested by Andy Lutomirski with great details.
>
> Thanks, this looks much more sensible to me.
>
Thanks Christoph
Note the high cost of zap_page_range(), needed to avoid -EBUSY being returned
from vm_insert_page() the second time TCP_ZEROCOPY_RECEIVE is used on one VMA.
Ideally a vm_replace_page() would avoid this cost ?
6.51% tcp_mmap [kernel.kallsyms] [k] unmap_page_range
5.90% tcp_mmap [kernel.kallsyms] [k] vm_insert_page
4.85% tcp_mmap [kernel.kallsyms] [k] _raw_spin_lock
4.50% tcp_mmap [kernel.kallsyms] [k] mark_page_accessed
3.51% tcp_mmap [kernel.kallsyms] [k] page_remove_rmap
2.99% tcp_mmap [kernel.kallsyms] [k] page_add_file_rmap
2.53% tcp_mmap [kernel.kallsyms] [k] release_pages
2.38% tcp_mmap [kernel.kallsyms] [k] put_page
2.37% tcp_mmap [kernel.kallsyms] [k] smp_call_function_single
2.28% tcp_mmap [kernel.kallsyms] [k] __get_locked_pte
2.25% tcp_mmap [kernel.kallsyms] [k] do_tcp_setsockopt.isra.35
2.21% tcp_mmap [kernel.kallsyms] [k] page_clear_age
^ permalink raw reply
* Re: [PATCH 1/8] net: ethernet: stmmac: add adaptation for stm32mp157c.
From: Andrew Lunn @ 2018-04-25 12:40 UTC (permalink / raw)
To: Christophe ROULLIER
Cc: mark.rutland@arm.com, mcoquelin.stm32@gmail.com, Alexandre TORGUE,
Peppe CAVALLARO, devicetree@vger.kernel.org,
linux-arm-kernel@lists.infradead.org, netdev@vger.kernel.org
In-Reply-To: <fa12bb221b1b4cf380812c0fed03f74d@SFHDAG5NODE3.st.com>
On Wed, Apr 25, 2018 at 07:12:29AM +0000, Christophe ROULLIER wrote:
> Hi Andrew,
>
> For moment, I've only tested with PHY RGMII, RMII, MII, GMII, I do not have other kind of PHY interface.
> Normally there is no impact in my glue, the value of syscfg register will be the same for RGMII/ID/TXID/RXID.
> Do you think that I should add these interfaces in my case ?
>
> case PHY_INTERFACE_MODE_RGMII:
> > + case PHY_INTERFACE_MODE_RGMII_ID:
> > + case PHY_INTERFACE_MODE_RGMII_RXID:
> > + case PHY_INTERFACE_MODE_RGMII_TXID:
Yes
Andrew
^ permalink raw reply
* Re: [PATCH net-next] lan78xx: Lan7801 Support for Fixed PHY
From: Andrew Lunn @ 2018-04-25 12:39 UTC (permalink / raw)
To: RaghuramChary.Jallipalli; +Cc: davem, netdev, UNGLinuxDriver, Woojung.Huh
In-Reply-To: <0573C9D4B793EF43BF95221F2F4CC85153DA07@CHN-SV-EXMX06.mchp-main.com>
> OK. Will modify to netdev_dbg()
>
> > > + dev->interface = PHY_INTERFACE_MODE_RGMII;
> > > + dev->fixedphy = phydev;
> >
> > You can use
> >
> > if (!phy_is_pseudo_fixed_link(phydev))
> >
> > to determine is a PHY is a fixed phy. I think you can then do without
> > dev->fixedphy.
> >
> dev->fixedphy stores the fixed phydev, which will be passed to the
> fixed_phy_unregister routine , so I think phy_is_pseudo_fixed_link check is not necessary.
I'm saying you can get rid of dev->fixedphy, and just use
netdev->phydev, and phy_is_pseudo_fixed_link(netdev->phydev)
Andrew
^ permalink raw reply
* Re: [PATCH bpf-next 03/15] xsk: add umem fill queue support and mmap
From: Björn Töpel @ 2018-04-25 12:37 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: Karlsson, Magnus, Duyck, Alexander H, Alexander Duyck,
John Fastabend, Alexei Starovoitov, Jesper Dangaard Brouer,
Willem de Bruijn, Daniel Borkmann, Netdev, michael.lundkvist,
Brandeburg, Jesse, Singhai, Anjali, Zhang, Qi Z
In-Reply-To: <20180424021605-mutt-send-email-mst@kernel.org>
2018-04-24 1:16 GMT+02:00 Michael S. Tsirkin <mst@redhat.com>:
> On Mon, Apr 23, 2018 at 03:56:07PM +0200, Björn Töpel wrote:
>> From: Magnus Karlsson <magnus.karlsson@intel.com>
>>
>> Here, we add another setsockopt for registered user memory (umem)
>> called XDP_UMEM_FILL_QUEUE. Using this socket option, the process can
>> ask the kernel to allocate a queue (ring buffer) and also mmap it
>> (XDP_UMEM_PGOFF_FILL_QUEUE) into the process.
>>
>> The queue is used to explicitly pass ownership of umem frames from the
>> user process to the kernel. These frames will in a later patch be
>> filled in with Rx packet data by the kernel.
>>
>> Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
>> ---
>> include/uapi/linux/if_xdp.h | 15 +++++++++++
>> net/xdp/Makefile | 2 +-
>> net/xdp/xdp_umem.c | 5 ++++
>> net/xdp/xdp_umem.h | 2 ++
>> net/xdp/xsk.c | 62 ++++++++++++++++++++++++++++++++++++++++++++-
>> net/xdp/xsk_queue.c | 58 ++++++++++++++++++++++++++++++++++++++++++
>> net/xdp/xsk_queue.h | 38 +++++++++++++++++++++++++++
>> 7 files changed, 180 insertions(+), 2 deletions(-)
>> create mode 100644 net/xdp/xsk_queue.c
>> create mode 100644 net/xdp/xsk_queue.h
>>
>> diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
>> index 41252135a0fe..975661e1baca 100644
>> --- a/include/uapi/linux/if_xdp.h
>> +++ b/include/uapi/linux/if_xdp.h
>> @@ -23,6 +23,7 @@
>>
>> /* XDP socket options */
>> #define XDP_UMEM_REG 3
>> +#define XDP_UMEM_FILL_RING 4
>>
>> struct xdp_umem_reg {
>> __u64 addr; /* Start of packet data area */
>> @@ -31,4 +32,18 @@ struct xdp_umem_reg {
>> __u32 frame_headroom; /* Frame head room */
>> };
>>
>> +/* Pgoff for mmaping the rings */
>> +#define XDP_UMEM_PGOFF_FILL_RING 0x100000000
>> +
>> +struct xdp_ring {
>> + __u32 producer __attribute__((aligned(64)));
>> + __u32 consumer __attribute__((aligned(64)));
>> +};
>> +
>> +/* Used for the fill and completion queues for buffers */
>> +struct xdp_umem_ring {
>> + struct xdp_ring ptrs;
>> + __u32 desc[0] __attribute__((aligned(64)));
>> +};
>> +
>> #endif /* _LINUX_IF_XDP_H */
>> diff --git a/net/xdp/Makefile b/net/xdp/Makefile
>> index a5d736640a0f..074fb2b2d51c 100644
>> --- a/net/xdp/Makefile
>> +++ b/net/xdp/Makefile
>> @@ -1,2 +1,2 @@
>> -obj-$(CONFIG_XDP_SOCKETS) += xsk.o xdp_umem.o
>> +obj-$(CONFIG_XDP_SOCKETS) += xsk.o xdp_umem.o xsk_queue.o
>>
>> diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
>> index bff058f5a769..6fc233e03f30 100644
>> --- a/net/xdp/xdp_umem.c
>> +++ b/net/xdp/xdp_umem.c
>> @@ -62,6 +62,11 @@ static void xdp_umem_release(struct xdp_umem *umem)
>> struct mm_struct *mm;
>> unsigned long diff;
>>
>> + if (umem->fq) {
>> + xskq_destroy(umem->fq);
>> + umem->fq = NULL;
>> + }
>> +
>> if (umem->pgs) {
>> xdp_umem_unpin_pages(umem);
>>
>> diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h
>> index 58714f4f7f25..3086091aebdd 100644
>> --- a/net/xdp/xdp_umem.h
>> +++ b/net/xdp/xdp_umem.h
>> @@ -18,9 +18,11 @@
>> #include <linux/mm.h>
>> #include <linux/if_xdp.h>
>>
>> +#include "xsk_queue.h"
>> #include "xdp_umem_props.h"
>>
>> struct xdp_umem {
>> + struct xsk_queue *fq;
>> struct page **pgs;
>> struct xdp_umem_props props;
>> u32 npgs;
>> diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
>> index 19fc719cbe0d..bf6a1151df28 100644
>> --- a/net/xdp/xsk.c
>> +++ b/net/xdp/xsk.c
>> @@ -32,6 +32,7 @@
>> #include <linux/netdevice.h>
>> #include <net/sock.h>
>>
>> +#include "xsk_queue.h"
>> #include "xdp_umem.h"
>>
>> struct xdp_sock {
>> @@ -47,6 +48,21 @@ static struct xdp_sock *xdp_sk(struct sock *sk)
>> return (struct xdp_sock *)sk;
>> }
>>
>> +static int xsk_init_queue(u32 entries, struct xsk_queue **queue)
>> +{
>> + struct xsk_queue *q;
>> +
>> + if (entries == 0 || *queue || !is_power_of_2(entries))
>> + return -EINVAL;
>> +
>> + q = xskq_create(entries);
>> + if (!q)
>> + return -ENOMEM;
>> +
>> + *queue = q;
>> + return 0;
>> +}
>> +
>> static int xsk_release(struct socket *sock)
>> {
>> struct sock *sk = sock->sk;
>> @@ -109,6 +125,23 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
>> mutex_unlock(&xs->mutex);
>> return 0;
>> }
>> + case XDP_UMEM_FILL_RING:
>> + {
>> + struct xsk_queue **q;
>> + int entries;
>> +
>> + if (!xs->umem)
>> + return -EINVAL;
>> +
>> + if (copy_from_user(&entries, optval, sizeof(entries)))
>> + return -EFAULT;
>> +
>> + mutex_lock(&xs->mutex);
>> + q = &xs->umem->fq;
>> + err = xsk_init_queue(entries, q);
>> + mutex_unlock(&xs->mutex);
>> + return err;
>> + }
>> default:
>> break;
>> }
>> @@ -116,6 +149,33 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
>> return -ENOPROTOOPT;
>> }
>>
>> +static int xsk_mmap(struct file *file, struct socket *sock,
>> + struct vm_area_struct *vma)
>> +{
>> + unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
>> + unsigned long size = vma->vm_end - vma->vm_start;
>> + struct xdp_sock *xs = xdp_sk(sock->sk);
>> + struct xsk_queue *q;
>> + unsigned long pfn;
>> + struct page *qpg;
>> +
>> + if (!xs->umem)
>> + return -EINVAL;
>> +
>> + if (offset == XDP_UMEM_PGOFF_FILL_RING)
>> + q = xs->umem->fq;
>> + else
>> + return -EINVAL;
>> +
>> + qpg = virt_to_head_page(q->ring);
>> + if (size > (PAGE_SIZE << compound_order(qpg)))
>> + return -EINVAL;
>> +
>> + pfn = virt_to_phys(q->ring) >> PAGE_SHIFT;
>> + return remap_pfn_range(vma, vma->vm_start, pfn,
>> + size, vma->vm_page_prot);
>> +}
>> +
>> static struct proto xsk_proto = {
>> .name = "XDP",
>> .owner = THIS_MODULE,
>> @@ -139,7 +199,7 @@ static const struct proto_ops xsk_proto_ops = {
>> .getsockopt = sock_no_getsockopt,
>> .sendmsg = sock_no_sendmsg,
>> .recvmsg = sock_no_recvmsg,
>> - .mmap = sock_no_mmap,
>> + .mmap = xsk_mmap,
>> .sendpage = sock_no_sendpage,
>> };
>>
>> diff --git a/net/xdp/xsk_queue.c b/net/xdp/xsk_queue.c
>> new file mode 100644
>> index 000000000000..23da4f29d3fb
>> --- /dev/null
>> +++ b/net/xdp/xsk_queue.c
>> @@ -0,0 +1,58 @@
>> +// SPDX-License-Identifier: GPL-2.0
>> +/* XDP user-space ring structure
>> + * Copyright(c) 2018 Intel Corporation.
>> + *
>> + * This program is free software; you can redistribute it and/or modify it
>> + * under the terms and conditions of the GNU General Public License,
>> + * version 2, as published by the Free Software Foundation.
>> + *
>> + * This program is distributed in the hope it will be useful, but WITHOUT
>> + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
>> + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
>> + * more details.
>> + */
>> +
>> +#include <linux/slab.h>
>> +
>> +#include "xsk_queue.h"
>> +
>> +static u32 xskq_umem_get_ring_size(struct xsk_queue *q)
>> +{
>> + return sizeof(struct xdp_umem_ring) + q->nentries * sizeof(u32);
>> +}
>> +
>> +struct xsk_queue *xskq_create(u32 nentries)
>> +{
>> + struct xsk_queue *q;
>> + gfp_t gfp_flags;
>> + size_t size;
>> +
>> + q = kzalloc(sizeof(*q), GFP_KERNEL);
>> + if (!q)
>> + return NULL;
>> +
>> + q->nentries = nentries;
>> + q->ring_mask = nentries - 1;
>> +
>> + gfp_flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN |
>> + __GFP_COMP | __GFP_NORETRY;
>> + size = xskq_umem_get_ring_size(q);
>> +
>> + q->ring = (struct xdp_ring *)__get_free_pages(gfp_flags,
>> + get_order(size));
>> + if (!q->ring) {
>> + kfree(q);
>> + return NULL;
>> + }
>> +
>> + return q;
>> +}
>> +
>> +void xskq_destroy(struct xsk_queue *q)
>> +{
>> + if (!q)
>> + return;
>> +
>> + page_frag_free(q->ring);
>> + kfree(q);
>> +}
>> diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
>> new file mode 100644
>> index 000000000000..7eb556bf73be
>> --- /dev/null
>> +++ b/net/xdp/xsk_queue.h
>> @@ -0,0 +1,38 @@
>> +/* SPDX-License-Identifier: GPL-2.0
>> + * XDP user-space ring structure
>> + * Copyright(c) 2018 Intel Corporation.
>> + *
>> + * This program is free software; you can redistribute it and/or modify it
>> + * under the terms and conditions of the GNU General Public License,
>> + * version 2, as published by the Free Software Foundation.
>> + *
>> + * This program is distributed in the hope it will be useful, but WITHOUT
>> + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
>> + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
>> + * more details.
>> + */
>> +
>> +#ifndef _LINUX_XSK_QUEUE_H
>> +#define _LINUX_XSK_QUEUE_H
>> +
>> +#include <linux/types.h>
>> +#include <linux/if_xdp.h>
>> +
>> +#include "xdp_umem_props.h"
>> +
>> +struct xsk_queue {
>> + struct xdp_umem_props umem_props;
>> + u32 ring_mask;
>> + u32 nentries;
>> + u32 prod_head;
>> + u32 prod_tail;
>> + u32 cons_head;
>> + u32 cons_tail;
>> + struct xdp_ring *ring;
>> + u64 invalid_descs;
>> +};
>
> Any documentation on how e.g. the locking works here?
>
It's a SPSC queue. On the kernel side we guarantee synchronization via
the NAPI context. As for the user-space application, it's the
responsibility of the application to do the synchronization.
Even though the xsk_queue structure has both cons/prod members, for a
certain queue, only prod_ *or* cons_ will be used. For the kernel it
means that it will consume from fill and tx queues, and produce to
completion and rx queues.
Note that prod_/cons_ are the *cached* local variables, the actual
produce/consumer pointers reside in the kernel/user shared xdp_ring.
I'll try to make it clearer in the documentation!
>
>> +
>> +struct xsk_queue *xskq_create(u32 nentries);
>> +void xskq_destroy(struct xsk_queue *q);
>> +
>> +#endif /* _LINUX_XSK_QUEUE_H */
>> --
>> 2.14.1
^ permalink raw reply
* IT Helpdesk! Treat Very Urgently!!!
From: Paula Peterson @ 2018-04-25 12:30 UTC (permalink / raw)
To: Paula Peterson
In-Reply-To: <EA828B2E9707E34ABC6E5CBD7AACD681013B42C5C2@SDOEXMBX1-08E.SCCCD.NET>
Dear User,
Please take note of this important update that our new web-mail has been improved with a new messaging system from Microsoft Exchange\Outlook which also include faster usage on email, shared calendar,web-documents also with the new Anti-spam version.
Kindly use the link below to Switch to the New Microsoft Exchange/Outlook.
Click on Microsoft Exchange<http://2w0g99hp69vbla66jukqhmdtm.designmysite.pro/> to Switch immediately.
© IT Technical Support
Copyright 2018, Web-mail Maintenance,
All Rights Reserved.
^ permalink raw reply
* Re: [PATCH net 3/3] ARM64: dts: marvell: armada-cp110: Add clocks for the xmdio node
From: Gregory CLEMENT @ 2018-04-25 12:30 UTC (permalink / raw)
To: Maxime Chevallier
Cc: davem, netdev, linux-kernel, Antoine Tenart, thomas.petazzoni,
miquel.raynal, nadavh, stefanc, ymarkman, mw, linux,
linux-arm-kernel
In-Reply-To: <87muxrecnf.fsf@bootlin.com>
Hi agin,
On mer., avril 25 2018, Gregory CLEMENT <gregory.clement@bootlin.com> wrote:
> Hi Maxime,
>
> On mer., avril 25 2018, Maxime Chevallier <maxime.chevallier@bootlin.com> wrote:
>
>> The Marvell XSMI controller needs 3 clocks to operate correctly :
>> - The MG clock (clk 5)
>> - The MG Core clock (clk 6)
>> - The GOP clock (clk 18)
>>
>> This commit adds them, to avoid system hangs when using these
>> interfaces.
>>
>> Fixes: c7e92def1ef4 ("clk: mvebu: cp110: Fix clock tree representation")
>> Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
>
> This patch should not have been sent with the net prefix and should not
> be merge through the net subsystem.
>
> I will take care of it to avoid conflict in the devei tree file during
> the merge windows.
So, applied on mvebu/fixes
Thanks,
Gregory
>
> Thanks,
>
> Gregory
>
>> ---
>> arch/arm64/boot/dts/marvell/armada-cp110.dtsi | 2 ++
>> 1 file changed, 2 insertions(+)
>>
>> diff --git a/arch/arm64/boot/dts/marvell/armada-cp110.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
>> index 6c137ac656e9..ed2f1237ea1e 100644
>> --- a/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
>> +++ b/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
>> @@ -142,6 +142,8 @@
>> #size-cells = <0>;
>> compatible = "marvell,xmdio";
>> reg = <0x12a600 0x10>;
>> + clocks = <&CP110_LABEL(clk) 1 5>,
>> + <&CP110_LABEL(clk) 1 6>, <&CP110_LABEL(clk) 1 18>;
>> status = "disabled";
>> };
>>
>> --
>> 2.11.0
>>
>
> --
> Gregory Clement, Bootlin (formerly Free Electrons)
> Embedded Linux and Kernel engineering
> http://bootlin.com
--
Gregory Clement, Bootlin (formerly Free Electrons)
Embedded Linux and Kernel engineering
http://bootlin.com
^ permalink raw reply
* Re: [PATCH net 1/3] net: mvpp2: Fix clk error path in mvpp2_probe
From: Gregory CLEMENT @ 2018-04-25 12:05 UTC (permalink / raw)
To: Maxime Chevallier
Cc: davem, netdev, linux-kernel, Antoine Tenart, thomas.petazzoni,
miquel.raynal, nadavh, stefanc, ymarkman, mw, linux,
linux-arm-kernel
In-Reply-To: <20180425110731.20153-2-maxime.chevallier@bootlin.com>
Hi Maxime,
On mer., avril 25 2018, Maxime Chevallier <maxime.chevallier@bootlin.com> wrote:
> When clk_prepare_enable fails for the axi_clk, the mg_clk isn't properly
> cleaned up. Add another jump label to handle that case, and make sure we
> jump to it in the later error cases.
>
> Fixes: 4792ea04bcd0 ("net: mvpp2: Fix clock resource by adding an optional bus clock")
> Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Acked-by: Gregory CLEMENT <gregory.clement@bootlin.com>
Thanks,
Gregory
> ---
> drivers/net/ethernet/marvell/mvpp2.c | 15 ++++++++-------
> 1 file changed, 8 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
> index 4202f9b5b966..0c2f04813d42 100644
> --- a/drivers/net/ethernet/marvell/mvpp2.c
> +++ b/drivers/net/ethernet/marvell/mvpp2.c
> @@ -8774,12 +8774,12 @@ static int mvpp2_probe(struct platform_device *pdev)
> if (IS_ERR(priv->axi_clk)) {
> err = PTR_ERR(priv->axi_clk);
> if (err == -EPROBE_DEFER)
> - goto err_gop_clk;
> + goto err_mg_clk;
> priv->axi_clk = NULL;
> } else {
> err = clk_prepare_enable(priv->axi_clk);
> if (err < 0)
> - goto err_gop_clk;
> + goto err_mg_clk;
> }
>
> /* Get system's tclk rate */
> @@ -8793,7 +8793,7 @@ static int mvpp2_probe(struct platform_device *pdev)
> if (priv->hw_version == MVPP22) {
> err = dma_set_mask(&pdev->dev, MVPP2_DESC_DMA_MASK);
> if (err)
> - goto err_mg_clk;
> + goto err_axi_clk;
> /* Sadly, the BM pools all share the same register to
> * store the high 32 bits of their address. So they
> * must all have the same high 32 bits, which forces
> @@ -8801,14 +8801,14 @@ static int mvpp2_probe(struct platform_device *pdev)
> */
> err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
> if (err)
> - goto err_mg_clk;
> + goto err_axi_clk;
> }
>
> /* Initialize network controller */
> err = mvpp2_init(pdev, priv);
> if (err < 0) {
> dev_err(&pdev->dev, "failed to initialize controller\n");
> - goto err_mg_clk;
> + goto err_axi_clk;
> }
>
> /* Initialize ports */
> @@ -8821,7 +8821,7 @@ static int mvpp2_probe(struct platform_device *pdev)
> if (priv->port_count == 0) {
> dev_err(&pdev->dev, "no ports enabled\n");
> err = -ENODEV;
> - goto err_mg_clk;
> + goto err_axi_clk;
> }
>
> /* Statistics must be gathered regularly because some of them (like
> @@ -8849,8 +8849,9 @@ static int mvpp2_probe(struct platform_device *pdev)
> mvpp2_port_remove(priv->port_list[i]);
> i++;
> }
> -err_mg_clk:
> +err_axi_clk:
> clk_disable_unprepare(priv->axi_clk);
> +err_mg_clk:
> if (priv->hw_version == MVPP22)
> clk_disable_unprepare(priv->mg_clk);
> err_gop_clk:
> --
> 2.11.0
>
--
Gregory Clement, Bootlin (formerly Free Electrons)
Embedded Linux and Kernel engineering
http://bootlin.com
^ permalink raw reply
* Re: How to detect libbfd when building tools/bpf?
From: Quentin Monnet @ 2018-04-25 12:01 UTC (permalink / raw)
To: shhuiw, Daniel Borkmann
Cc: ast, kstewart, gregkh, tglx, pombredanne, netdev, acme,
jakub.kicinski
In-Reply-To: <5ade9631.046f370a.24af5.a921SMTPIN_ADDED_BROKEN@mx.google.com>
2018-04-24 10:27 UTC+0800 ~ shhuiw <shhuiw@foxmail.com>
>
>
> On 04/23/18 18:05, Daniel Borkmann wrote:
>> On 04/22/2018 09:51 AM, Wang Sheng-Hui wrote:
>>> Sorry to trouble you !
>>>
>>> I run debian and installed binutils-dev beforehand.
>>> Then I copied tools/build/feature/test-libbfd.c to t.c and run:
>>> ------------------------------------------------------------------------
>>> root@lazyfintech:~# cat t.c
>>> #include <bfd.h>
>>>
>>> extern int printf(const char *format, ...);
>>>
>>> int main(void)
>>> {
>>> char symbol[4096] = "FieldName__9ClassNameFd";
>>> char *tmp;
>>>
>>> tmp = bfd_demangle(0, symbol, 0);
>>>
>>> printf("demangled symbol: {%s}\n", tmp);
- On some distributions (e.g. OpenSUSE), there is no default alias
>>>
>>> return 0;
>>> }
>>> root@lazyfintech:~# gcc t.c -lbfd
>> Can you run with 'gcc t.c -lbfd -lz -liberty -ldl' since this is
>> what the Makefile for the feature test is doing:
>>
>> $(OUTPUT)test-libbfd.bin:
>> $(BUILD) -DPACKAGE='"perf"' -lbfd -lz -liberty -ldl
>>
>> Seems most likely that you're missing some of the remaining libs
>> to have the feature test properly detect it?
> I missed the lib iberty. After the lib installed, the auto-detect can work.
>
> Thanks, Daniel!
For the record, we (at least Jakub and I) know about this issue with
libbfd detection for bpf tools. In theory the Makefile *should* refuse
to build if libbfd is not detected (since libbfd is required), but
checking the result from the detection was apparently omitted when
detection itself was added to the Makefile. This would be trivial to
patch in the Makefile, but I would like to have the detection itself
fixed before that:
- On some distributions (e.g. OpenSUSE), there is no default alias
libbfd.so to libbfd-<version>.so, which causes the static library
libbfd.a to be picked. But the latter does not include libiberty, which
must be available on the system, and called on the command line
("-liberty") for the feature to be detected (or for bpftool to be compiled).
- Some other distributions (e.g. Debian and derivatives) have this
alias, and for them it is not required to link against any version of
libiberty (it seems to be already included in libbfd.so). On such
systems, installing libiberty is not a requirement to compile the tools.
So fixing the Makefile to make libbfd detection mandatory would force
all users to install libiberty to compile bpftool, when it is actually
not required for many of them. I have proposed, internally, a couple of
patches to fix libbfd detection, but I haven't found something clean
enough so far to propose it on this list. But I intend to come back to
it and to fix it eventually, so that libbfd detection would no longer
appear as "OFF" when all needed components are present on the system.
Cheers,
Quentin
^ permalink raw reply
* Re: [PATCH net 2/3] net: mvpp2: Fix clock resource by adding missing mg_core_clk
From: Maxime Chevallier @ 2018-04-25 11:52 UTC (permalink / raw)
To: Gregory CLEMENT
Cc: davem, netdev, linux-kernel, Antoine Tenart, thomas.petazzoni,
miquel.raynal, nadavh, stefanc, ymarkman, mw, linux,
linux-arm-kernel
In-Reply-To: <87in8feckt.fsf@bootlin.com>
Hi Gregory,
On Wed, 25 Apr 2018 13:43:14 +0200
Gregory CLEMENT <gregory.clement@bootlin.com> wrote:
>Hi Maxime,
>
> On mer., avril 25 2018, Maxime Chevallier
> <maxime.chevallier@bootlin.com> wrote:
>
>> Marvell's PPv2.2 IP needs an additional clock named "MG Core clock".
>> This is required on Armada 7K and 8K.
>>
>> This commit adds the required clock, updates the devicetree and its
>> documentation accordingly, also fixing a small typo in the
>> marvell-mpp2.txt examples.
>>
>> Fixes: c7e92def1ef4 ("clk: mvebu: cp110: Fix clock tree
>> representation") Signed-off-by: Maxime Chevallier
>> <maxime.chevallier@bootlin.com> ---
>> .../devicetree/bindings/net/marvell-pp2.txt | 9 +++++----
>> arch/arm64/boot/dts/marvell/armada-cp110.dtsi | 5 +++--
>
>Could you remove the dtsi part and submit it as a separate patch. Then
>I will take care of it.
Ok no problem, I'll split that and re-send it.
Thanks,
Maxime
--
Maxime Chevallier, Bootlin (formerly Free Electrons)
Embedded Linux and kernel engineering
https://bootlin.com
^ permalink raw reply
* Re: [PATCH net-next] sctp: remove the unused sctp_assoc_is_match function
From: Neil Horman @ 2018-04-25 11:49 UTC (permalink / raw)
To: Xin Long; +Cc: network dev, linux-sctp, Marcelo Ricardo Leitner, davem
In-Reply-To: <0acb8eaec9a5be9959d39bb5017d49bb31d0d5e5.1524649607.git.lucien.xin@gmail.com>
On Wed, Apr 25, 2018 at 05:46:47PM +0800, Xin Long wrote:
> After Commit 4f0087812648 ("sctp: apply rhashtable api to send/recv
> path"), there's no place using sctp_assoc_is_match, so remove it.
>
> Signed-off-by: Xin Long <lucien.xin@gmail.com>
> ---
> include/net/sctp/structs.h | 4 ----
> net/sctp/associola.c | 25 -------------------------
> 2 files changed, 29 deletions(-)
>
> diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
> index a0ec462..05594b2 100644
> --- a/include/net/sctp/structs.h
> +++ b/include/net/sctp/structs.h
> @@ -2091,10 +2091,6 @@ void sctp_assoc_control_transport(struct sctp_association *asoc,
> enum sctp_transport_cmd command,
> sctp_sn_error_t error);
> struct sctp_transport *sctp_assoc_lookup_tsn(struct sctp_association *, __u32);
> -struct sctp_transport *sctp_assoc_is_match(struct sctp_association *,
> - struct net *,
> - const union sctp_addr *,
> - const union sctp_addr *);
> void sctp_assoc_migrate(struct sctp_association *, struct sock *);
> int sctp_assoc_update(struct sctp_association *old,
> struct sctp_association *new);
> diff --git a/net/sctp/associola.c b/net/sctp/associola.c
> index 837806d..a8f3b08 100644
> --- a/net/sctp/associola.c
> +++ b/net/sctp/associola.c
> @@ -988,31 +988,6 @@ struct sctp_transport *sctp_assoc_lookup_tsn(struct sctp_association *asoc,
> return match;
> }
>
> -/* Is this the association we are looking for? */
> -struct sctp_transport *sctp_assoc_is_match(struct sctp_association *asoc,
> - struct net *net,
> - const union sctp_addr *laddr,
> - const union sctp_addr *paddr)
> -{
> - struct sctp_transport *transport;
> -
> - if ((htons(asoc->base.bind_addr.port) == laddr->v4.sin_port) &&
> - (htons(asoc->peer.port) == paddr->v4.sin_port) &&
> - net_eq(sock_net(asoc->base.sk), net)) {
> - transport = sctp_assoc_lookup_paddr(asoc, paddr);
> - if (!transport)
> - goto out;
> -
> - if (sctp_bind_addr_match(&asoc->base.bind_addr, laddr,
> - sctp_sk(asoc->base.sk)))
> - goto out;
> - }
> - transport = NULL;
> -
> -out:
> - return transport;
> -}
> -
> /* Do delayed input processing. This is scheduled by sctp_rcv(). */
> static void sctp_assoc_bh_rcv(struct work_struct *work)
> {
> --
> 2.1.0
>
>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
^ permalink raw reply
* Re: [PATCH net-next] sctp: fix identification of new acks for SFR-CACC
From: Neil Horman @ 2018-04-25 11:47 UTC (permalink / raw)
To: Marcelo Ricardo Leitner; +Cc: netdev, linux-sctp, Xin Long, Vlad Yasevich
In-Reply-To: <4e837f7eaf67a1a964d1b3418aa3cf759f512535.1524603870.git.marcelo.leitner@gmail.com>
On Tue, Apr 24, 2018 at 06:17:35PM -0300, Marcelo Ricardo Leitner wrote:
> It's currently written as:
>
> if (!tchunk->tsn_gap_acked) { [1]
> tchunk->tsn_gap_acked = 1;
> ...
> }
>
> if (TSN_lte(tsn, sack_ctsn)) {
> if (!tchunk->tsn_gap_acked) {
> /* SFR-CACC processing */
> ...
> }
> }
>
> Which causes the SFR-CACC processing on ack reception to never process,
> as tchunk->tsn_gap_acked is always true by then. Block [1] was
> moved to that position by the commit marked below.
>
> This patch fixes it by doing SFR-CACC processing earlier, before
> tsn_gap_acked is set to true.
>
> Fixes: 31b02e154940 ("sctp: Failover transmitted list on transport delete")
> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
> ---
>
> Even though this is a -stable candidate, please apply it to net-next
> to avoid conflicts with subsequent patches in my queue. Thanks.
>
> net/sctp/outqueue.c | 48 +++++++++++++++++++++++-------------------------
> 1 file changed, 23 insertions(+), 25 deletions(-)
>
> diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
> index f211b3db6a3543073e113da121bb28518b0af491..dee7cbd5483149024f2f3195db2fe4d473b1a00a 100644
> --- a/net/sctp/outqueue.c
> +++ b/net/sctp/outqueue.c
> @@ -1457,7 +1457,7 @@ static void sctp_check_transmitted(struct sctp_outq *q,
> * the outstanding bytes for this chunk, so only
> * count bytes associated with a transport.
> */
> - if (transport) {
> + if (transport && !tchunk->tsn_gap_acked) {
> /* If this chunk is being used for RTT
> * measurement, calculate the RTT and update
> * the RTO using this value.
> @@ -1469,14 +1469,34 @@ static void sctp_check_transmitted(struct sctp_outq *q,
> * first instance of the packet or a later
> * instance).
> */
> - if (!tchunk->tsn_gap_acked &&
> - !sctp_chunk_retransmitted(tchunk) &&
> + if (!sctp_chunk_retransmitted(tchunk) &&
> tchunk->rtt_in_progress) {
> tchunk->rtt_in_progress = 0;
> rtt = jiffies - tchunk->sent_at;
> sctp_transport_update_rto(transport,
> rtt);
> }
> +
> + if (TSN_lte(tsn, sack_ctsn)) {
> + /*
> + * SFR-CACC algorithm:
> + * 2) If the SACK contains gap acks
> + * and the flag CHANGEOVER_ACTIVE is
> + * set the receiver of the SACK MUST
> + * take the following action:
> + *
> + * B) For each TSN t being acked that
> + * has not been acked in any SACK so
> + * far, set cacc_saw_newack to 1 for
> + * the destination that the TSN was
> + * sent to.
> + */
> + if (sack->num_gap_ack_blocks &&
> + q->asoc->peer.primary_path->cacc.
> + changeover_active)
> + transport->cacc.cacc_saw_newack
> + = 1;
> + }
> }
>
> /* If the chunk hasn't been marked as ACKED,
> @@ -1508,28 +1528,6 @@ static void sctp_check_transmitted(struct sctp_outq *q,
> restart_timer = 1;
> forward_progress = true;
>
> - if (!tchunk->tsn_gap_acked) {
> - /*
> - * SFR-CACC algorithm:
> - * 2) If the SACK contains gap acks
> - * and the flag CHANGEOVER_ACTIVE is
> - * set the receiver of the SACK MUST
> - * take the following action:
> - *
> - * B) For each TSN t being acked that
> - * has not been acked in any SACK so
> - * far, set cacc_saw_newack to 1 for
> - * the destination that the TSN was
> - * sent to.
> - */
> - if (transport &&
> - sack->num_gap_ack_blocks &&
> - q->asoc->peer.primary_path->cacc.
> - changeover_active)
> - transport->cacc.cacc_saw_newack
> - = 1;
> - }
> -
> list_add_tail(&tchunk->transmitted_list,
> &q->sacked);
> } else {
> --
> 2.14.3
>
>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
^ permalink raw reply
* Re: [PATCH net-next] sctp: fix const parameter violation in sctp_make_sack
From: Neil Horman @ 2018-04-25 11:45 UTC (permalink / raw)
To: Marcelo Ricardo Leitner; +Cc: netdev, linux-sctp, Xin Long, Vlad Yasevich
In-Reply-To: <b9065b3cfb0a2bf3c83008ff53967f473e081766.1524603855.git.marcelo.leitner@gmail.com>
On Tue, Apr 24, 2018 at 06:17:34PM -0300, Marcelo Ricardo Leitner wrote:
> sctp_make_sack() make changes to the asoc and this cast is just
> bypassing the const attribute. As there is no need to have the const
> there, just remove it and fix the violation.
>
> Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
> ---
>
> This one can go to net or net-next, but targetting net-next here just to
> keep it together with the rest (which I'll post as patches get in).
>
> include/net/sctp/sm.h | 2 +-
> net/sctp/sm_make_chunk.c | 9 ++++-----
> 2 files changed, 5 insertions(+), 6 deletions(-)
>
> diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
> index 2d0e782c90551377ad654bcef1224bbdb75ba394..f4b657478a304050851f33d92c71162a4a4a2e50 100644
> --- a/include/net/sctp/sm.h
> +++ b/include/net/sctp/sm.h
> @@ -207,7 +207,7 @@ struct sctp_chunk *sctp_make_datafrag_empty(const struct sctp_association *asoc,
> int len, __u8 flags, gfp_t gfp);
> struct sctp_chunk *sctp_make_ecne(const struct sctp_association *asoc,
> const __u32 lowest_tsn);
> -struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc);
> +struct sctp_chunk *sctp_make_sack(struct sctp_association *asoc);
> struct sctp_chunk *sctp_make_shutdown(const struct sctp_association *asoc,
> const struct sctp_chunk *chunk);
> struct sctp_chunk *sctp_make_shutdown_ack(const struct sctp_association *asoc,
> diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
> index 5a4fb1dc8400a0316177ce65be8126857297eb5e..db93eabd6ef500ab20be6e091ee06bd3b60923c9 100644
> --- a/net/sctp/sm_make_chunk.c
> +++ b/net/sctp/sm_make_chunk.c
> @@ -779,10 +779,9 @@ struct sctp_chunk *sctp_make_datafrag_empty(const struct sctp_association *asoc,
> * association. This reports on which TSN's we've seen to date,
> * including duplicates and gaps.
> */
> -struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc)
> +struct sctp_chunk *sctp_make_sack(struct sctp_association *asoc)
> {
> struct sctp_tsnmap *map = (struct sctp_tsnmap *)&asoc->peer.tsn_map;
> - struct sctp_association *aptr = (struct sctp_association *)asoc;
> struct sctp_gap_ack_block gabs[SCTP_MAX_GABS];
> __u16 num_gabs, num_dup_tsns;
> struct sctp_transport *trans;
> @@ -857,7 +856,7 @@ struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc)
>
> /* Add the duplicate TSN information. */
> if (num_dup_tsns) {
> - aptr->stats.idupchunks += num_dup_tsns;
> + asoc->stats.idupchunks += num_dup_tsns;
> sctp_addto_chunk(retval, sizeof(__u32) * num_dup_tsns,
> sctp_tsnmap_get_dups(map));
> }
> @@ -869,11 +868,11 @@ struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc)
> * association so no transport will match after a wrap event like this,
> * Until the next sack
> */
> - if (++aptr->peer.sack_generation == 0) {
> + if (++asoc->peer.sack_generation == 0) {
> list_for_each_entry(trans, &asoc->peer.transport_addr_list,
> transports)
> trans->sack_generation = 0;
> - aptr->peer.sack_generation = 1;
> + asoc->peer.sack_generation = 1;
> }
> nodata:
> return retval;
> --
> 2.14.3
>
>
Acked-by: Neil Horman <nhorman@tuxdriver.com
^ permalink raw reply
* Re: [PATCH net 2/3] net: mvpp2: Fix clock resource by adding missing mg_core_clk
From: Gregory CLEMENT @ 2018-04-25 11:43 UTC (permalink / raw)
To: Maxime Chevallier
Cc: davem, netdev, linux-kernel, Antoine Tenart, thomas.petazzoni,
miquel.raynal, nadavh, stefanc, ymarkman, mw, linux,
linux-arm-kernel
In-Reply-To: <20180425110731.20153-3-maxime.chevallier@bootlin.com>
Hi Maxime,
On mer., avril 25 2018, Maxime Chevallier <maxime.chevallier@bootlin.com> wrote:
> Marvell's PPv2.2 IP needs an additional clock named "MG Core clock".
> This is required on Armada 7K and 8K.
>
> This commit adds the required clock, updates the devicetree and its
> documentation accordingly, also fixing a small typo in the
> marvell-mpp2.txt examples.
>
> Fixes: c7e92def1ef4 ("clk: mvebu: cp110: Fix clock tree representation")
> Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
> ---
> .../devicetree/bindings/net/marvell-pp2.txt | 9 +++++----
> arch/arm64/boot/dts/marvell/armada-cp110.dtsi | 5 +++--
Could you remove the dtsi part and submit it as a separate patch. Then I
will take care of it.
Thanks,
Gregory
> drivers/net/ethernet/marvell/mvpp2.c | 20 ++++++++++++++++++--
> 3 files changed, 26 insertions(+), 8 deletions(-)
>
> diff --git a/Documentation/devicetree/bindings/net/marvell-pp2.txt b/Documentation/devicetree/bindings/net/marvell-pp2.txt
> index 1814fa13f6ab..fc019df0d863 100644
> --- a/Documentation/devicetree/bindings/net/marvell-pp2.txt
> +++ b/Documentation/devicetree/bindings/net/marvell-pp2.txt
> @@ -21,9 +21,10 @@ Required properties:
> - main controller clock (for both armada-375-pp2 and armada-7k-pp2)
> - GOP clock (for both armada-375-pp2 and armada-7k-pp2)
> - MG clock (only for armada-7k-pp2)
> + - MG Core clock (only for armada-7k-pp2)
> - AXI clock (only for armada-7k-pp2)
> -- clock-names: names of used clocks, must be "pp_clk", "gop_clk", "mg_clk"
> - and "axi_clk" (the 2 latter only for armada-7k-pp2).
> +- clock-names: names of used clocks, must be "pp_clk", "gop_clk", "mg_clk",
> + "mg_core_clk" and "axi_clk" (the 3 latter only for armada-7k-pp2).
>
> The ethernet ports are represented by subnodes. At least one port is
> required.
> @@ -80,8 +81,8 @@ cpm_ethernet: ethernet@0 {
> compatible = "marvell,armada-7k-pp22";
> reg = <0x0 0x100000>, <0x129000 0xb000>;
> clocks = <&cpm_syscon0 1 3>, <&cpm_syscon0 1 9>,
> - <&cpm_syscon0 1 5>, <&cpm_syscon0 1 18>;
> - clock-names = "pp_clk", "gop_clk", "gp_clk", "axi_clk";
> + <&cpm_syscon0 1 5>, <&cpm_syscon0 1 6>, <&cpm_syscon0 1 18>;
> + clock-names = "pp_clk", "gop_clk", "mg_clk", "mg_core_clk", "axi_clk";
>
> eth0: eth0 {
> interrupts = <ICU_GRP_NSR 39 IRQ_TYPE_LEVEL_HIGH>,
> diff --git a/arch/arm64/boot/dts/marvell/armada-cp110.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
> index 48cad7919efa..6c137ac656e9 100644
> --- a/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
> +++ b/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
> @@ -38,9 +38,10 @@
> compatible = "marvell,armada-7k-pp22";
> reg = <0x0 0x100000>, <0x129000 0xb000>;
> clocks = <&CP110_LABEL(clk) 1 3>, <&CP110_LABEL(clk) 1 9>,
> - <&CP110_LABEL(clk) 1 5>, <&CP110_LABEL(clk) 1 18>;
> + <&CP110_LABEL(clk) 1 5>, <&CP110_LABEL(clk) 1 6>,
> + <&CP110_LABEL(clk) 1 18>;
> clock-names = "pp_clk", "gop_clk",
> - "mg_clk", "axi_clk";
> + "mg_clk", "mg_core_clk", "axi_clk";
> marvell,system-controller = <&CP110_LABEL(syscon0)>;
> status = "disabled";
> dma-coherent;
> diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
> index 0c2f04813d42..6a17b67a0d61 100644
> --- a/drivers/net/ethernet/marvell/mvpp2.c
> +++ b/drivers/net/ethernet/marvell/mvpp2.c
> @@ -942,6 +942,7 @@ struct mvpp2 {
> struct clk *pp_clk;
> struct clk *gop_clk;
> struct clk *mg_clk;
> + struct clk *mg_core_clk;
> struct clk *axi_clk;
>
> /* List of pointers to port structures */
> @@ -8768,18 +8769,28 @@ static int mvpp2_probe(struct platform_device *pdev)
> err = clk_prepare_enable(priv->mg_clk);
> if (err < 0)
> goto err_gop_clk;
> +
> + priv->mg_core_clk = devm_clk_get(&pdev->dev, "mg_core_clk");
> + if (IS_ERR(priv->mg_core_clk)) {
> + err = PTR_ERR(priv->mg_core_clk);
> + goto err_mg_clk;
> + }
> +
> + err = clk_prepare_enable(priv->mg_core_clk);
> + if (err < 0)
> + goto err_mg_clk;
> }
>
> priv->axi_clk = devm_clk_get(&pdev->dev, "axi_clk");
> if (IS_ERR(priv->axi_clk)) {
> err = PTR_ERR(priv->axi_clk);
> if (err == -EPROBE_DEFER)
> - goto err_mg_clk;
> + goto err_mg_core_clk;
> priv->axi_clk = NULL;
> } else {
> err = clk_prepare_enable(priv->axi_clk);
> if (err < 0)
> - goto err_mg_clk;
> + goto err_mg_core_clk;
> }
>
> /* Get system's tclk rate */
> @@ -8851,6 +8862,10 @@ static int mvpp2_probe(struct platform_device *pdev)
> }
> err_axi_clk:
> clk_disable_unprepare(priv->axi_clk);
> +
> +err_mg_core_clk:
> + if (priv->hw_version == MVPP22)
> + clk_disable_unprepare(priv->mg_core_clk);
> err_mg_clk:
> if (priv->hw_version == MVPP22)
> clk_disable_unprepare(priv->mg_clk);
> @@ -8898,6 +8913,7 @@ static int mvpp2_remove(struct platform_device *pdev)
> return 0;
>
> clk_disable_unprepare(priv->axi_clk);
> + clk_disable_unprepare(priv->mg_core_clk);
> clk_disable_unprepare(priv->mg_clk);
> clk_disable_unprepare(priv->pp_clk);
> clk_disable_unprepare(priv->gop_clk);
> --
> 2.11.0
>
--
Gregory Clement, Bootlin (formerly Free Electrons)
Embedded Linux and Kernel engineering
http://bootlin.com
^ permalink raw reply
* Re: [PATCH net 3/3] ARM64: dts: marvell: armada-cp110: Add clocks for the xmdio node
From: Gregory CLEMENT @ 2018-04-25 11:41 UTC (permalink / raw)
To: Maxime Chevallier
Cc: davem, netdev, linux-kernel, Antoine Tenart, thomas.petazzoni,
miquel.raynal, nadavh, stefanc, ymarkman, mw, linux,
linux-arm-kernel
In-Reply-To: <20180425110731.20153-4-maxime.chevallier@bootlin.com>
Hi Maxime,
On mer., avril 25 2018, Maxime Chevallier <maxime.chevallier@bootlin.com> wrote:
> The Marvell XSMI controller needs 3 clocks to operate correctly :
> - The MG clock (clk 5)
> - The MG Core clock (clk 6)
> - The GOP clock (clk 18)
>
> This commit adds them, to avoid system hangs when using these
> interfaces.
>
> Fixes: c7e92def1ef4 ("clk: mvebu: cp110: Fix clock tree representation")
> Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
This patch should not have been sent with the net prefix and should not
be merge through the net subsystem.
I will take care of it to avoid conflict in the devei tree file during
the merge windows.
Thanks,
Gregory
> ---
> arch/arm64/boot/dts/marvell/armada-cp110.dtsi | 2 ++
> 1 file changed, 2 insertions(+)
>
> diff --git a/arch/arm64/boot/dts/marvell/armada-cp110.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
> index 6c137ac656e9..ed2f1237ea1e 100644
> --- a/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
> +++ b/arch/arm64/boot/dts/marvell/armada-cp110.dtsi
> @@ -142,6 +142,8 @@
> #size-cells = <0>;
> compatible = "marvell,xmdio";
> reg = <0x12a600 0x10>;
> + clocks = <&CP110_LABEL(clk) 1 5>,
> + <&CP110_LABEL(clk) 1 6>, <&CP110_LABEL(clk) 1 18>;
> status = "disabled";
> };
>
> --
> 2.11.0
>
--
Gregory Clement, Bootlin (formerly Free Electrons)
Embedded Linux and Kernel engineering
http://bootlin.com
^ permalink raw reply
* [PATCH] rds: ib: Fix missing call to rds_ib_dev_put in rds_ib_setup_qp
From: Dag Moxnes @ 2018-04-25 11:22 UTC (permalink / raw)
To: Santosh Shilimkar, David S. Miller, netdev, linux-rdma, rds-devel,
linux-kernel
The function rds_ib_setup_qp is calling rds_ib_get_client_data and
should correspondingly call rds_ib_dev_put. This call was lost in
the non-error path with the introduction of error handling done in
commit 3b12f73a5c29 ("rds: ib: add error handle")
Signed-off-by: Dag Moxnes <dag.moxnes@oracle.com>
---
net/rds/ib_cm.c | 3 ++-
1 files changed, 2 insertions(+), 1 deletions(-)
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index eea1d86..13b38ad 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -547,7 +547,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
rdsdebug("conn %p pd %p cq %p %p\n", conn, ic->i_pd,
ic->i_send_cq, ic->i_recv_cq);
- return ret;
+ goto out;
sends_out:
vfree(ic->i_sends);
@@ -572,6 +572,7 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
ic->i_send_cq = NULL;
rds_ibdev_out:
rds_ib_remove_conn(rds_ibdev, conn);
+out:
rds_ib_dev_put(rds_ibdev);
return ret;
--
1.7.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox