* Re: [Xen-devel] [PATCH 1/1] xen-netback: process malformed sk_buff correctly to avoid BUG_ON()
From: Dongli Zhang @ 2018-03-27 23:49 UTC (permalink / raw)
To: xen-devel, linux-kernel; +Cc: netdev, paul.durrant, wei.liu2
In-Reply-To: <1522194136-11985-1-git-send-email-dongli.zhang@oracle.com>
Below is the sample kernel module used to reproduce the issue on purpose with
"vif1.0" hard coded:
#include <linux/init.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
static int __init test_skb_init(void)
{
struct sk_buff *skb;
struct skb_shared_info *si;
struct net_device *dev;
dev = dev_get_by_name(&init_net, "vif1.0");
if (!dev) {
pr_alert("failed to get net_device\n");
return 0;
}
skb = alloc_skb(2000, GFP_ATOMIC | __GFP_NOWARN);
if (!skb) {
pr_alert("failed to allocate sk_buff\n");
return 0;
}
si = skb_shinfo(skb);
skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
skb->dev = dev;
skb->len = 386;
skb->data_len = 352;
skb->mac_len = 14;
skb->pkt_type = 3;
skb->protocol = 8;
skb->transport_header = 98;
skb->network_header = 78;
skb->mac_header = 64;
skb->tail = 98;
skb->end = 384;
pr_alert("skb->data = 0x%016llx\n", (u64) skb->data);
dev->netdev_ops->ndo_start_xmit(skb, dev);
return 0;
}
static void __exit test_skb_exit(void)
{
}
MODULE_LICENSE("GPL");
module_init(test_skb_init);
module_exit(test_skb_exit);
Dongli Zhang
On 03/28/2018 07:42 AM, Dongli Zhang wrote:
> The "BUG_ON(!frag_iter)" in function xenvif_rx_next_chunk() is triggered if
> the received sk_buff is malformed, that is, when the sk_buff has pattern
> (skb->data_len && !skb_shinfo(skb)->nr_frags). Below is a sample call
> stack:
>
> [ 438.652658] ------------[ cut here ]------------
> [ 438.652660] kernel BUG at drivers/net/xen-netback/rx.c:325!
> [ 438.652714] invalid opcode: 0000 [#1] SMP NOPTI
> [ 438.652813] CPU: 0 PID: 2492 Comm: vif1.0-q0-guest Tainted: G O 4.16.0-rc6+ #1
> [ 438.652896] RIP: e030:xenvif_rx_skb+0x3c2/0x5e0 [xen_netback]
> [ 438.652926] RSP: e02b:ffffc90040877dc8 EFLAGS: 00010246
> [ 438.652956] RAX: 0000000000000160 RBX: 0000000000000022 RCX: 0000000000000001
> [ 438.652993] RDX: ffffc900402890d0 RSI: 0000000000000000 RDI: ffffc90040889000
> [ 438.653029] RBP: ffff88002b460040 R08: ffffc90040877de0 R09: 0100000000000000
> [ 438.653065] R10: 0000000000007ff0 R11: 0000000000000002 R12: ffffc90040889000
> [ 438.653100] R13: ffffffff80000000 R14: 0000000000000022 R15: 0000000080000000
> [ 438.653149] FS: 00007f15603778c0(0000) GS:ffff880030400000(0000) knlGS:0000000000000000
> [ 438.653188] CS: e033 DS: 0000 ES: 0000 CR0: 0000000080050033
> [ 438.653219] CR2: 0000000001832a08 CR3: 0000000029c12000 CR4: 0000000000042660
> [ 438.653262] Call Trace:
> [ 438.653284] ? xen_hypercall_event_channel_op+0xa/0x20
> [ 438.653313] xenvif_rx_action+0x41/0x80 [xen_netback]
> [ 438.653341] xenvif_kthread_guest_rx+0xb2/0x2a8 [xen_netback]
> [ 438.653374] ? __schedule+0x352/0x700
> [ 438.653398] ? wait_woken+0x80/0x80
> [ 438.653421] kthread+0xf3/0x130
> [ 438.653442] ? xenvif_rx_action+0x80/0x80 [xen_netback]
> [ 438.653470] ? kthread_destroy_worker+0x40/0x40
> [ 438.653497] ret_from_fork+0x35/0x40
>
> The issue is hit by xen-netback when there is bug with other networking
> interface (e.g., dom0 physical NIC), who has generated and forwarded
> malformed sk_buff to dom0 vifX.Y. It is possible to reproduce the issue on
> purpose with below sample code in a kernel module:
>
> skb->dev = dev; // dev of vifX.Y
> skb->len = 386;
> skb->data_len = 352;
> skb->tail = 98;
> skb->end = 384;
> dev->netdev_ops->ndo_start_xmit(skb, dev);
>
> This patch stops processing sk_buff immediately if it is detected as
> malformed, that is, pkt->frag_iter is NULL but there is still remaining
> pkt->remaining_len.
>
> Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
> ---
> drivers/net/xen-netback/rx.c | 8 ++++++++
> 1 file changed, 8 insertions(+)
>
> diff --git a/drivers/net/xen-netback/rx.c b/drivers/net/xen-netback/rx.c
> index b1cf7c6..289cc82 100644
> --- a/drivers/net/xen-netback/rx.c
> +++ b/drivers/net/xen-netback/rx.c
> @@ -369,6 +369,14 @@ static void xenvif_rx_data_slot(struct xenvif_queue *queue,
> offset += len;
> pkt->remaining_len -= len;
>
> + if (unlikely(!pkt->frag_iter && pkt->remaining_len)) {
> + pkt->remaining_len = 0;
> + pkt->extra_count = 0;
> + pr_err_ratelimited("malformed sk_buff at %s\n",
> + queue->name);
> + break;
> + }
> +
> } while (offset < XEN_PAGE_SIZE && pkt->remaining_len > 0);
>
> if (pkt->remaining_len > 0)
>
^ permalink raw reply
* Re: RFC on writel and writel_relaxed
From: Benjamin Herrenschmidt @ 2018-03-27 23:43 UTC (permalink / raw)
To: Alexander Duyck
Cc: Sinan Kaya, Arnd Bergmann, Jason Gunthorpe, David Laight, Oliver,
open list:LINUX FOR POWERPC (32-BIT AND 64-BIT),
linux-rdma@vger.kernel.org, Will Deacon, Paul E. McKenney,
netdev@vger.kernel.org
In-Reply-To: <CAKgT0UfZKBTYPCqWtBF=N5TPFrbsv0ZU+2GHMqF3J4BM9Hw4yw@mail.gmail.com>
On Tue, 2018-03-27 at 14:54 -0700, Alexander Duyck wrote:
> On Tue, Mar 27, 2018 at 2:35 PM, Benjamin Herrenschmidt
> <benh@kernel.crashing.org> wrote:
> > On Tue, 2018-03-27 at 10:46 -0400, Sinan Kaya wrote:
> > > combined buffers.
> > >
> > > Alex:
> > > "Don't bother. I can tell you right now that for x86 you have to have a
> > > wmb() before the writel().
> >
> > No, this isn't the semantics of writel. You shouldn't need it unless
> > something changed and we need to revisit our complete understanding of
> > *all* MMIO accessor semantics.
>
> The issue seems to be that there have been two different ways of
> dealing with this. There has historically been a number of different
> drivers that have been carrying this wmb() workaround since something
> like 2002. I get that the semantics for writel might have changed
> since then, but those of us who already have the wmb() in our drivers
> will be very wary of anyone wanting to go through and remove them
> since writel is supposed to be "good enough". I would much rather err
> on the side of caution here.
>
> I view the wmb() + writel_relaxed() as more of a driver owning and
> handling this itself. Besides in the Intel Ethernet driver case it is
> better performance as our wmb() placement for us also provides a
> secondary barrier so we don't need to add a separate smp_wmb() to deal
> with a potential race we have with the Tx cleanup.
>
> > At least for UC space, it has always been accepted (and enforced) that
> > writel would not require any other barrier to order vs. previous stores
> > to memory.
>
> So the one thing I would question here is if this is UC vs UC or if
> this extends to other types as well? So for x86 we could find
> references to Write Combining being flushed by a write to UC memory,
> however I have yet to find a clear explanation of what a write to UC
> does to WB.
Well, this is the standard write memory + trigger DMA case, the one
specific case for which Linus was adamant we don't need another barrier
back then ...
> My personal inclination would be to err on the side of
> caution.
Which means writel_relaxed is now pointless ?
We need clear semantics here. In this case the "side of caution" means
we are randomly doing things not understanding what really happens and
that makes me *more* nervous.
> I just don't want us going through and removing the wmb()
> calls because it "should" work. I would want to know for certain it
> will work.
We need to know for certain anyway. Otherwise, all the drivers that do
not have wmb's are potentially broken.
So I dont agree with the status quo.
We need to establish precisely what x86 does, decide what we want the
semantic of writel to be, and implement things accordingly.
Ben.
^ permalink raw reply
* [PATCH 1/1] xen-netback: process malformed sk_buff correctly to avoid BUG_ON()
From: Dongli Zhang @ 2018-03-27 23:42 UTC (permalink / raw)
To: xen-devel, linux-kernel; +Cc: netdev, wei.liu2, paul.durrant
The "BUG_ON(!frag_iter)" in function xenvif_rx_next_chunk() is triggered if
the received sk_buff is malformed, that is, when the sk_buff has pattern
(skb->data_len && !skb_shinfo(skb)->nr_frags). Below is a sample call
stack:
[ 438.652658] ------------[ cut here ]------------
[ 438.652660] kernel BUG at drivers/net/xen-netback/rx.c:325!
[ 438.652714] invalid opcode: 0000 [#1] SMP NOPTI
[ 438.652813] CPU: 0 PID: 2492 Comm: vif1.0-q0-guest Tainted: G O 4.16.0-rc6+ #1
[ 438.652896] RIP: e030:xenvif_rx_skb+0x3c2/0x5e0 [xen_netback]
[ 438.652926] RSP: e02b:ffffc90040877dc8 EFLAGS: 00010246
[ 438.652956] RAX: 0000000000000160 RBX: 0000000000000022 RCX: 0000000000000001
[ 438.652993] RDX: ffffc900402890d0 RSI: 0000000000000000 RDI: ffffc90040889000
[ 438.653029] RBP: ffff88002b460040 R08: ffffc90040877de0 R09: 0100000000000000
[ 438.653065] R10: 0000000000007ff0 R11: 0000000000000002 R12: ffffc90040889000
[ 438.653100] R13: ffffffff80000000 R14: 0000000000000022 R15: 0000000080000000
[ 438.653149] FS: 00007f15603778c0(0000) GS:ffff880030400000(0000) knlGS:0000000000000000
[ 438.653188] CS: e033 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 438.653219] CR2: 0000000001832a08 CR3: 0000000029c12000 CR4: 0000000000042660
[ 438.653262] Call Trace:
[ 438.653284] ? xen_hypercall_event_channel_op+0xa/0x20
[ 438.653313] xenvif_rx_action+0x41/0x80 [xen_netback]
[ 438.653341] xenvif_kthread_guest_rx+0xb2/0x2a8 [xen_netback]
[ 438.653374] ? __schedule+0x352/0x700
[ 438.653398] ? wait_woken+0x80/0x80
[ 438.653421] kthread+0xf3/0x130
[ 438.653442] ? xenvif_rx_action+0x80/0x80 [xen_netback]
[ 438.653470] ? kthread_destroy_worker+0x40/0x40
[ 438.653497] ret_from_fork+0x35/0x40
The issue is hit by xen-netback when there is bug with other networking
interface (e.g., dom0 physical NIC), who has generated and forwarded
malformed sk_buff to dom0 vifX.Y. It is possible to reproduce the issue on
purpose with below sample code in a kernel module:
skb->dev = dev; // dev of vifX.Y
skb->len = 386;
skb->data_len = 352;
skb->tail = 98;
skb->end = 384;
dev->netdev_ops->ndo_start_xmit(skb, dev);
This patch stops processing sk_buff immediately if it is detected as
malformed, that is, pkt->frag_iter is NULL but there is still remaining
pkt->remaining_len.
Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
---
drivers/net/xen-netback/rx.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/drivers/net/xen-netback/rx.c b/drivers/net/xen-netback/rx.c
index b1cf7c6..289cc82 100644
--- a/drivers/net/xen-netback/rx.c
+++ b/drivers/net/xen-netback/rx.c
@@ -369,6 +369,14 @@ static void xenvif_rx_data_slot(struct xenvif_queue *queue,
offset += len;
pkt->remaining_len -= len;
+ if (unlikely(!pkt->frag_iter && pkt->remaining_len)) {
+ pkt->remaining_len = 0;
+ pkt->extra_count = 0;
+ pr_err_ratelimited("malformed sk_buff at %s\n",
+ queue->name);
+ break;
+ }
+
} while (offset < XEN_PAGE_SIZE && pkt->remaining_len > 0);
if (pkt->remaining_len > 0)
--
2.7.4
^ permalink raw reply related
* Re: [iproute PATCH 2/3] ss: Put filter DB parsing into a separate function
From: Phil Sutter @ 2018-03-27 23:39 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: netdev
In-Reply-To: <20180327114601.62112467@xeon-e3>
On Tue, Mar 27, 2018 at 11:46:01AM -0700, Stephen Hemminger wrote:
> On Sat, 24 Mar 2018 19:18:10 +0100
> Phil Sutter <phil@nwl.cc> wrote:
>
> > +#define ENTRY(name, ...) { #name, { __VA_ARGS__, MAX_DB }}
>
> > + ENTRY(all, UDP_DB, DCCP_DB, TCP_DB, RAW_DB, \
> > + UNIX_ST_DB, UNIX_DG_DB, UNIX_SQ_DB, \
> > + PACKET_R_DB, PACKET_DG_DB, NETLINK_DB, \
> > + SCTP_DB, VSOCK_ST_DB, VSOCK_DG_DB),
>
> Checkpatch complains that line continuations are not necessary here;
> and it is right. Macro usage can cross lines.
Interesting. Seems I should fix my muscle memory when it comes to
macros. :)
I'll follow-up with a fixed version.
Thanks, Phil
^ permalink raw reply
* Re: [RFC v3 net-next 13/18] net/sched: Introduce the TBS Qdisc
From: Jesus Sanchez-Palencia @ 2018-03-27 23:26 UTC (permalink / raw)
To: Thomas Gleixner
Cc: netdev, jhs, xiyou.wangcong, jiri, vinicius.gomes, richardcochran,
anna-maria, henrik, John Stultz, levi.pearson, edumazet, willemb,
mlichvar
In-Reply-To: <alpine.DEB.2.21.1803241325500.1481@nanos.tec.linutronix.de>
Hi Thomas,
On 03/25/2018 04:46 AM, Thomas Gleixner wrote:
> On Fri, 23 Mar 2018, Jesus Sanchez-Palencia wrote:
>> On 03/22/2018 03:52 PM, Thomas Gleixner wrote:
>>> So what's the plan for this? Having TAS as a separate entity or TAS feeding
>>> into the proposed 'basic' time transmission thing?
>>
>> The second one, I guess.
>
> That's just wrong. It won't work. See below.
Yes, our proposal does not handle the scenarios you are bringing into the
discussion.
I think we have more points of convergence than divergence already. I will just
go through some pieces of the discussion first, and then let's see if we can
agree on where we are trying to get.
>
>> Elaborating, the plan is at some point having TAS as a separate entity,
>> but which can use tbs for one of its classes (and cbs for another, and
>> strict priority for everything else, etc).
>>
>> Basically, the design would something along the lines of 'taprio'. A root qdisc
>> that is both time and priority aware, and capable of running a schedule for the
>> port. That schedule can run inside the kernel with hrtimers, or just be
>> offloaded into the controller if Qbv is supported on HW.
>>
>> Because it would expose the inner traffic classes in a mq / mqprio / prio style,
>> then it would allow for other per-queue qdiscs to be attached to it. On a system
>> using the i210, for instance, we could then have tbs installed on traffic class
>> 0 just dialing hw offload. The Qbv schedule would be running in SW on the TAS
>> entity (i.e. 'taprio') which would be setting the packets' txtime before
>> dequeueing packets on a fast path -> tbs -> NIC.
>>
>> Similarly, other qdisc, like cbs, could be installed if all that traffic class
>> requires is traffic shaping once its 'gate' is allowed to execute the selected
>> tx algorithm attached to it.
>>
>>> I've not yet seen a convincing argument why this low level stuff with all
>>> of its weird flavours is superiour over something which reflects the basic
>>> operating principle of TSN.
>>
>>
>> As you know, not all TSN systems are designed the same. Take AVB systems, for
>> example. These not always are running on networks that are aware of any time
>> schedule, or at least not quite like what is described by Qbv.
>>
>> On those systems there is usually a certain number of streams with different
>> priorities that care mostly about having their bandwidth reserved along the
>> network. The applications running on such systems are usually based on AVTP,
>> thus they already have to calculate and set the "avtp presentation time"
>> per-packet themselves. A Qbv scheduler would probably provide very little
>> benefits to this domain, IMHO. For "talkers" of these AVB systems, shaping
>> traffic using txtime (i.e. tbs) can provide a low-jitter alternative to cbs, for
>> instance.
>
> You're looking at it from particular use cases and try to accomodate for
> them in the simplest possible way. I don't think that cuts it.
>
> Let's take a step back and look at it from a more general POV without
> trying to make it fit to any of the standards first. I'm deliberately NOT
> using any of the standard defined terms.
>
> At the (local) network level you have always an explicit plan. This plan
> might range from no plan at all to an very elaborate plan which is strict
> about when each node is allowed to TX a particular class of packets.
Ok, we are aligned here.
>
> So lets assume we have the following picture:
>
> [NIC]
> |
> [ Time slice manager ]
>
> Now in the simplest case, the time slice manager has no constraints and
> exposes a single input which allows the application to say: "Send my packet
> at time X". There is no restriction on 'time X' except if there is a time
> collision with an already queued packet or the requested TX time has
> already passed. That's close to what you implemented.
>
> Is the TX timestamp which you defined in the user space ABI a fixed
> scheduling point or is it a deadline?
>
> That's an important distinction and for this all to work accross various
> use cases you need a way to express that in the ABI. It might be an
> implicit property of the socket/channel to which the application connects
> to but still you want to express it from the application side to do
> proper sanity checking.
>
> Just think about stuff like audio/video streaming. The point of
> transmission does not have to be fixed if you have some intelligent
> controller at the receiving end which can buffer stuff. The only relevant
> information is the deadline, i.e. the latest point in time where the
> packet needs to go out on the wire in order to keep the stream steady at
> the consumer side. Having the notion of a deadline and that's the only
> thing the provider knows about allows you proper utilization by using an
> approriate scheduling algorithm like EDF.
>
> Contrary to that you want very explicit TX points for applications like
> automation control. For this kind of use case there is no wiggle room, it
> has to go out at a fixed time because that's the way control systems
> work.
>
> This is missing right now and you want to get that right from the very
> beginning. Duct taping it on the interface later on is a bad idea.
Agreed that this is needed. On the SO_TXTIME + tbs proposal, I believe it's been
covered by the (per-packet) SCM_DROP_IF_LATE. Do you think we need a different
mechanism for expressing that?
>
> Now lets go one step further and create two time slices for whatever
> purpose still on the single node (not network wide). You want to do that
> because you want temporal separation of services. The reason might be
> bandwidth guarantee, collission avoidance or whatever.
>
> How does the application which was written for the simple manager which
> had no restrictions learn about this?
>
> Does it learn it the hard way because now the packets which fall into the
> reserved timeslice are rejected? The way you created your interface, the
> answer is yes. That's patently bad as it requires to change the
> application once it runs on a partitioned node.
>
> So you really want a way for the application to query the timing
> constraints and perhaps other properties of the channel it connects
> to. And you want that now before the first application starts to use the
> new ABI. If the application developer does not use it, you still have to
> fix the application, but you have to fix it because the developer was a
> lazy bastard and not because the design was bad. That's a major
> difference.
Ok, this is something that we have considered in the past, but then the feedback
here drove us onto a different direction. The overall input we got here was that
applications would have to be adjusted or that userspace would have to handle
the coordination between applications somehow (e.g.: a daemon could be developed
separately to accommodate the fully dynamic use-cases, etc).
>
> Now that we have two time slices, I'm coming back to your idea of having
> your proposed qdisc as the entity which sits right at the network
> interface. Lets assume the following:
>
> [Slice 1: Timed traffic ] [Slice 2: Other Traffic]
>
> Lets assume further that 'Other traffic' has no idea about time slices at
> all. It's just stuff like ssh, http, etc. So if you keep that design
>
> [ NIC ]
> |
> [ Time slice manager ]
> | |
> [ Timed traffic ] [ Other traffic ]
>
> feeding into your proposed TBS thingy, then in case of underutilization
> of the 'Timed traffic' slot you prevent utilization of remaining time by
> pulling 'Other traffic' into the empty slots because 'Other traffic' is
> restricted to Slice 2 and 'Timed traffic' does not know about 'Other
> traffic' at all. And no, you cannot make TBS magically pull packets from
> 'Other traffic' just because its not designed for it. So your design
> becomes strictly partitioned and forces underutilization.
>
> That's becoming even worse, when you switch to the proposed full hardware
> offloading scheme. In that case the only way to do admission control is
> the TX time of the farthest out packet which is already queued. That
> might work for a single application which controls all of the network
> traffic, but it wont ever work for something more flexible. The more I
> think about it the less interesting full hardware offload becomes. It's
> nice if you have a fully strict scheduling plan for everything, but then
> your admission control is bogus once you have more than one channel as
> input. So yes, it can be used when the card supports it and you have
> other ways to enforce admission control w/o hurting utilization or if you
> don't care about utilization at all. It's also useful for channels which
> are strictly isolated and have a defined TX time. Such traffic can be
> directly fed into the hardware.
This is a new requirement for the entire discussion.
If I'm not missing anything, however, underutilization of the time slots is only
a problem:
1) for the fully dynamic use-cases and;
2) because now you are designing applications in terms of time slices, right?
We have not thought of making any of the proposed qdiscs capable of (optionally)
adjusting the "time slices", but mainly because this is not a problem we had
here before. Our assumption was that per-port Tx schedules would only be used
for static systems. In other words, no, we didn't think that re-balancing the
slots was a requirement, not even for 'taprio'.
>
> Coming back to the overall scheme. If you start upfront with a time slice
> manager which is designed to:
>
> - Handle multiple channels
>
> - Expose the time constraints, properties per channel
>
> then you can fit all kind of use cases, whether designed by committee or
> not. You can configure that thing per node or network wide. It does not
> make a difference. The only difference are the resulting constraints.
Ok, and I believe the above was covered by what we had proposed before, unless
what you meant by time constraints is beyond the configured port schedule.
Are you suggesting that we'll need to have a kernel entity that is not only
aware of the current traffic classes 'schedule', but also of the resources that
are still available for new streams to be accommodated into the classes? Putting
it differently, is the TAS you envision just an entity that runs a schedule, or
is it a time-aware 'orchestrator'?
>
> We really want to accomodate everything between the 'no restrictions' and
> the 'full network wide explicit plan' case. And it's not rocket science
> once you realize that the 'no restrictions' case is just a subset of the
> 'full network wide explicit plan' simply because it exposes a single
> channel where:
>
> slice period = slice length.
>
> It's that easy, but at the same time you teach the application from the
> very beginning to ask for the time constraints so if it runs on a more
> sophisticated system/network, then it will see a different slice period and
> a different slice length and can accomodate or react in a useful way
> instead of just dying on the 17th packet it tries to send because it is
> rejected.
Ok.
>
> We really want to design for this as we want to be able to run the video
> stream on the same node and network which does robot control without
> changing the video application. That's not a theoretical problem. These use
> cases exist today, but they are forced to use different networks for the
> two. But if you look at the utilization of both then they very well fit
> into one and industry certainly wants to go for that.
>
> That implies that you need constraint aware applications from the very
> beginning and that requires a proper ABI in the first place. The proposed
> ad hoc mode does not qualify. Please be aware, that you are creating a user
> space ABI and not a random in kernel interface which can be changed at any
> given time.
>
> So lets look once more at the picture in an abstract way:
>
> [ NIC ]
> |
> [ Time slice manager ]
> | |
> [ Ch 0 ] ... [ Ch N ]
>
> So you have a bunch of properties here:
>
> 1) Number of Channels ranging from 1 to N
>
> 2) Start point, slice period and slice length per channel
Ok, so we agree that a TAS entity is needed. Assuming that channels are traffic
classes, do you have something else in mind other than a new root qdisc?
>
> 3) Queueing modes assigned per channel. Again that might be anything from
> 'feed through' over FIFO, PRIO to more complex things like EDF.
>
> The queueing mode can also influence properties like the meaning of the
> TX time, i.e. strict or deadline.
Ok, but how are the queueing modes assigned / configured per channel?
Just to make sure we re-visit some ideas from the past:
* TAS:
The idea we are currently exploring is to add a "time-aware", priority based
qdisc, that also exposes the Tx queues available and provides a mechanism for
mapping priority <-> traffic class <-> Tx queues in a similar fashion as
mqprio. We are calling this qdisc 'taprio', and its 'tc' cmd line would be:
$ $ tc qdisc add dev ens4 parent root handle 100 taprio num_tc 4 \
map 2 2 1 0 3 3 3 3 3 3 3 3 3 3 3 3 \
queues 0 1 2 3 \
sched-file gates.sched [base-time <interval>] \
[cycle-time <interval>] [extension-time <interval>]
<file> is multi-line, with each line being of the following format:
<cmd> <gate mask> <interval in nanoseconds>
Qbv only defines one <cmd>: "S" for 'SetGates'
For example:
S 0x01 300
S 0x03 500
This means that there are two intervals, the first will have the gate
for traffic class 0 open for 300 nanoseconds, the second will have
both traffic classes open for 500 nanoseconds.
It would handle multiple channels and expose their constraints / properties.
Each channel also becomes a traffic class, so other qdiscs can be attached to
them separately.
So, in summary, because our entire design is based on qdisc interfaces, what we
had proposed was a root qdisc (the time slice manager, as you put) that allows
for other qdiscs to be attached to each channel. The inner qdiscs define the
queueing modes for each channel, and tbs is just one of those modes. I
understand now that you want to allow for fully dynamic use-cases to be
supported as well, which we hadn't covered with our TAS proposal before because
we hadn't envisioned it being used for these systems' design.
Have I missed anything?
Thanks,
Jesus
>
> Please sit back and map your use cases, standards or whatever you care
> about into the above and I would be very surprised if they don't fit.
>
> Thanks,
>
> tglx
>
>
>
>
^ permalink raw reply
* [PATCH net-next 2/2] net: bgmac: Mask interrupts during probe
From: Florian Fainelli @ 2018-03-27 23:20 UTC (permalink / raw)
To: netdev
Cc: Florian Fainelli, David S. Miller, Scott Branden, Abhishek Shah,
Florian Westphal, open list, bcm-kernel-feedback-list
In-Reply-To: <20180327232002.29399-1-f.fainelli@gmail.com>
We can have interrupts left enabled form e.g: the bootloader which used
the network device for network boot. Make sure we have those disabled as
early as possible to avoid spurious interrupts.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
drivers/net/ethernet/broadcom/bgmac.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index 46d7b8068425..2326cc219c46 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -1492,6 +1492,8 @@ int bgmac_enet_probe(struct bgmac *bgmac)
struct net_device *net_dev = bgmac->net_dev;
int err;
+ bgmac_chip_intrs_off(bgmac);
+
net_dev->irq = bgmac->irq;
SET_NETDEV_DEV(net_dev, bgmac->dev);
dev_set_drvdata(bgmac->dev, bgmac);
--
2.14.1
^ permalink raw reply related
* [PATCH net-next 1/2] net: bgmac: Use interface name to request interrupt
From: Florian Fainelli @ 2018-03-27 23:20 UTC (permalink / raw)
To: netdev
Cc: Florian Fainelli, David S. Miller, Scott Branden, Abhishek Shah,
Florian Westphal, open list, bcm-kernel-feedback-list
In-Reply-To: <20180327232002.29399-1-f.fainelli@gmail.com>
When the system contains several BGMAC adapters, it is nice to be able
to tell which one is which by looking at /proc/interrupts. Use the
network device name as a name to request_irq() with.
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
drivers/net/ethernet/broadcom/bgmac.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index 8eef9fb6b1fe..46d7b8068425 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -1190,7 +1190,7 @@ static int bgmac_open(struct net_device *net_dev)
bgmac_chip_init(bgmac);
err = request_irq(bgmac->irq, bgmac_interrupt, IRQF_SHARED,
- KBUILD_MODNAME, net_dev);
+ net_dev->name, net_dev);
if (err < 0) {
dev_err(bgmac->dev, "IRQ request error: %d!\n", err);
bgmac_dma_cleanup(bgmac);
--
2.14.1
^ permalink raw reply related
* [PATCH net-next 0/2] net: bgmac: Couple of small bgmac changes
From: Florian Fainelli @ 2018-03-27 23:20 UTC (permalink / raw)
To: netdev
Cc: Florian Fainelli, David S. Miller, Scott Branden, Abhishek Shah,
Florian Westphal, open list, bcm-kernel-feedback-list
Hi all,
This patch series addresses two minor issues with the bgmac driver:
- provides the interface name through /proc/interrupts rather than "bgmac"
- makes sure the interrupts are masked during probe, in case the block was
not properly reset
Florian Fainelli (2):
net: bgmac: Use interface name to request interrupt
net: bgmac: Mask interrupts during probe
drivers/net/ethernet/broadcom/bgmac.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
--
2.14.1
^ permalink raw reply
* Re: [PATCH v6 bpf-next 08/11] bpf: introduce BPF_RAW_TRACEPOINT
From: Mathieu Desnoyers @ 2018-03-27 23:13 UTC (permalink / raw)
To: Alexei Starovoitov
Cc: rostedt, David S. Miller, Daniel Borkmann, Linus Torvalds,
Peter Zijlstra, netdev, kernel-team, linux-api, Kees Cook
In-Reply-To: <563f7fa0-5fea-00d3-1eb3-fa00d8cf7e29@fb.com>
----- On Mar 27, 2018, at 6:48 PM, Alexei Starovoitov ast@fb.com wrote:
> On 3/27/18 2:04 PM, Steven Rostedt wrote:
>>
>> +#ifdef CONFIG_BPF_EVENTS
>> +#define BPF_RAW_TP() . = ALIGN(8); \
Given that the section consists of a 16-bytes structure elements
on architectures with 8 bytes pointers, this ". = ALIGN(8)" should
be turned into a STRUCT_ALIGN(), especially given that the compiler
is free to up-align the structure on 32 bytes.
This could explain the kasan splat you are experiencing.
Thanks,
Mathieu
>> + VMLINUX_SYMBOL(__start__bpf_raw_tp) = .; \
>> + KEEP(*(__bpf_raw_tp_map)) \
>> + VMLINUX_SYMBOL(__stop__bpf_raw_tp) = .;
>
> that looks to be correct, but something wrong with it.
>
> Can you try your mini test with kasan on ?
>
> I'm seeing this crash:
> test_stacktrace_[ 18.760662] start ffffffff84642438 stop ffffffff84644f60
> map_raw_tp:PASS:[ 18.761467] i 1 btp->tp cccccccccccccccc
> prog_load raw tp[ 18.762064] kasan: CONFIG_KASAN_INLINE enabled
> 0 nsec
> [ 18.762704] kasan: GPF could be caused by NULL-ptr deref or user
> memory access
> [ 18.765125] general protection fault: 0000 [#1] SMP KASAN PTI
> [ 18.765830] Modules linked in:
> [ 18.778358] Call Trace:
> [ 18.778674] bpf_raw_tracepoint_open.isra.27+0x92/0x380
>
> for some reason the start_bpf_raw_tp is off by 8.
> Not sure how it works for you.
>
> (gdb) p &__bpf_trace_tp_map_sys_exit
> $10 = (struct bpf_raw_event_map *) 0xffffffff84642440
> <__bpf_trace_tp_map_sys_exit>
>
> (gdb) p &__start__bpf_raw_tp
> $7 = (<data variable, no debug info> *) 0xffffffff84642438
>
> (gdb) p (void*)(&__start__bpf_raw_tp)+8
> $11 = (void *) 0xffffffff84642440 <__bpf_trace_tp_map_sys_exit>
--
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com
^ permalink raw reply
* Re: [PATCH V4 net-next 06/14] net/tls: Add generic NIC offload infrastructure
From: Saeed Mahameed @ 2018-03-27 23:02 UTC (permalink / raw)
To: Dave Watson
Cc: Saeed Mahameed, David S. Miller, Linux Netdev List,
Boris Pismenny, Ilya Lesokhin, Aviad Yehezkel
In-Reply-To: <20180327222648.GA58978@davejwatson-mba.local>
On Tue, Mar 27, 2018 at 3:26 PM, Dave Watson <davejwatson@fb.com> wrote:
> Thanks for doing the merge, it looks good to me. One issue below,
> otherwise all my SW tests still pass.
>
> On 03/27/18 02:51 PM, Saeed Mahameed wrote:
>> - if (ctx->conf == TLS_SW_TX ||
>> - ctx->conf == TLS_SW_RX ||
>> - ctx->conf == TLS_SW_RXTX) {
>> - tls_sw_free_resources(sk);
>> + if (ctx->rx_conf == TLS_SW) {
>> + kfree(ctx->rx.rec_seq);
>> + kfree(ctx->rx.iv);
>> + tls_sw_free_resources_rx(sk);
>> }
>>
>> + if (ctx->tx_conf != TLS_HW)
>> + kfree(ctx);
>
> Looks like this needs to be hidden behind CONFIG_TLS_DEVICE, otherwise
> it doesn't compile if false because TLS_HW is not defined
>
Correct, Will fix.
Thanks Dave !
^ permalink raw reply
* Re: [pci PATCH v7 0/5] Add support for unmanaged SR-IOV
From: Alexander Duyck @ 2018-03-27 23:00 UTC (permalink / raw)
To: Bjorn Helgaas, linux-pci
Cc: Duyck, Alexander H, virtio-dev, kvm, Netdev, Daly, Dan, LKML,
linux-nvme, Keith Busch, netanel, Maximilian Heyne,
Wang, Liang-min, Rustad, Mark D, David Woodhouse,
Christoph Hellwig, dwmw, Don Dutile
On Fri, Mar 16, 2018 at 2:42 PM, Don Dutile <ddutile@redhat.com> wrote:
> On 03/15/2018 02:40 PM, Alexander Duyck wrote:
>>
>> This series is meant to add support for SR-IOV on devices when the VFs are
>> not managed by the kernel. Examples of recent patches attempting to do
>> this
>> include:
>> virto - https://patchwork.kernel.org/patch/10241225/
>> pci-stub - https://patchwork.kernel.org/patch/10109935/
>> vfio - https://patchwork.kernel.org/patch/10103353/
>> uio - https://patchwork.kernel.org/patch/9974031/
>>
>> Since this is quickly blowing up into a multi-driver problem it is
>> probably
>> best to implement this solution as generically as possible.
>>
>> This series is an attempt to do that. What we do with this patch set is
>> provide a generic framework to enable SR-IOV in the case that the PF
>> driver
>> doesn't support managing the VFs itself.
>>
>> I based my patch set originally on the patch by Mark Rustad but there
>> isn't
>> much left after going through and cleaning out the bits that were no
>> longer
>> needed, and after incorporating the feedback from David Miller. At this
>> point
>> the only items to be fully reused was his patch description which is now
>> present in patch 3 of the set.
>>
>> This solution is limited in scope to just adding support for devices that
>> provide no functionality for SR-IOV other than allocating the VFs by
>> calling pci_enable_sriov. Previous sets had included patches for VFIO, but
>> for now I am dropping that as the scope of that work is larger then I
>> think I can take on at this time.
>>
>> v2: Reduced scope back to just virtio_pci and vfio-pci
>> Broke into 3 patch set from single patch
>> Changed autoprobe behavior to always set when num_vfs is set non-zero
>> v3: Updated Documentation to clarify when sriov_unmanaged_autoprobe is
>> used
>> Wrapped vfio_pci_sriov_configure to fix build errors w/o SR-IOV in
>> kernel
>> v4: Dropped vfio-pci patch
>> Added ena and nvme to drivers now using pci_sriov_configure_unmanaged
>> Dropped pci_disable_sriov call in virtio_pci to be consistent with
>> ena
>> v5: Dropped sriov_unmanaged_autoprobe and pci_sriov_conifgure_unmanaged
>> Added new patch that enables pci_sriov_configure_simple
>> Updated drivers to use pci_sriov_configure_simple
>> v6: Defined pci_sriov_configure_simple as NULL when SR-IOV is not enabled
>> Updated drivers to drop "#ifdef" checks for IOV
>> Added pci-pf-stub as place for PF-only drivers to add support
>> v7: Dropped pci_id table explanation from pci-pf-stub driver
>> Updated pci_sriov_configure_simple to drop need for err value
>> Fixed comment explaining why pci_sriov_configure_simple is NULL
>>
>> Cc: Mark Rustad <mark.d.rustad@intel.com>
>> Cc: Maximilian Heyne <mheyne@amazon.de>
>> Cc: Liang-Min Wang <liang-min.wang@intel.com>
>> Cc: David Woodhouse <dwmw@amazon.co.uk>
>>
>> ---
>>
>> Alexander Duyck (5):
>> pci: Add pci_sriov_configure_simple for PFs that don't manage VF
>> resources
>> virtio_pci: Add support for unmanaged SR-IOV on virtio_pci devices
>> ena: Migrate over to unmanaged SR-IOV support
>> nvme: Migrate over to unmanaged SR-IOV support
>> pci-pf-stub: Add PF driver stub for PFs that function only to
>> enable VFs
>>
>>
>> drivers/net/ethernet/amazon/ena/ena_netdev.c | 28 -------------
>> drivers/nvme/host/pci.c | 20 ----------
>> drivers/pci/Kconfig | 12 ++++++
>> drivers/pci/Makefile | 2 +
>> drivers/pci/iov.c | 31 +++++++++++++++
>> drivers/pci/pci-pf-stub.c | 54
>> ++++++++++++++++++++++++++
>> drivers/virtio/virtio_pci_common.c | 1
>> include/linux/pci.h | 3 +
>> include/linux/pci_ids.h | 2 +
>> 9 files changed, 107 insertions(+), 46 deletions(-)
>> create mode 100644 drivers/pci/pci-pf-stub.c
>>
>> --
>>
> For what it's worth.
>
> Good, simpler start for this type of support/effort.
> Thanks for the multiple versions to get to this point.
>
> Reviewed-by: Donald Dutile <ddutile@redhat.com>
Any issues with getting this pulled into the linux-pci tree? When I
submitted these that was the original target for this set, or do I
need to look at breaking them up and/or submitting them submitted
somewhere else?
Thanks.
- Alex
^ permalink raw reply
* [PATCH net-next 3/3] rxrpc: Trace call completion
From: David Howells @ 2018-03-27 22:58 UTC (permalink / raw)
To: netdev; +Cc: dhowells, linux-afs, linux-kernel
In-Reply-To: <152219147024.24730.12727053395895392426.stgit@warthog.procyon.org.uk>
Add a tracepoint to track rxrpc calls moving into the completed state and
to log the completion type and the recorded error value and abort code.
Signed-off-by: David Howells <dhowells@redhat.com>
---
include/trace/events/rxrpc.h | 33 +++++++++++++++++++++++++++++++++
net/rxrpc/ar-internal.h | 1 +
2 files changed, 34 insertions(+)
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 4d2c2d35c5cb..2ea788f6f95d 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -400,6 +400,13 @@ enum rxrpc_congest_change {
EM(RXRPC_ACK_IDLE, "IDL") \
E_(RXRPC_ACK__INVALID, "-?-")
+#define rxrpc_completions \
+ EM(RXRPC_CALL_SUCCEEDED, "Succeeded") \
+ EM(RXRPC_CALL_REMOTELY_ABORTED, "RemoteAbort") \
+ EM(RXRPC_CALL_LOCALLY_ABORTED, "LocalAbort") \
+ EM(RXRPC_CALL_LOCAL_ERROR, "LocalError") \
+ E_(RXRPC_CALL_NETWORK_ERROR, "NetError")
+
/*
* Export enum symbols via userspace.
*/
@@ -624,6 +631,32 @@ TRACE_EVENT(rxrpc_abort,
__entry->abort_code, __entry->error, __entry->why)
);
+TRACE_EVENT(rxrpc_call_complete,
+ TP_PROTO(struct rxrpc_call *call),
+
+ TP_ARGS(call),
+
+ TP_STRUCT__entry(
+ __field(unsigned int, call )
+ __field(enum rxrpc_call_completion, compl )
+ __field(int, error )
+ __field(u32, abort_code )
+ ),
+
+ TP_fast_assign(
+ __entry->call = call->debug_id;
+ __entry->compl = call->completion;
+ __entry->error = call->error;
+ __entry->abort_code = call->abort_code;
+ ),
+
+ TP_printk("c=%08x %s r=%d ac=%d",
+ __entry->call,
+ __print_symbolic(__entry->compl, rxrpc_completions),
+ __entry->error,
+ __entry->abort_code)
+ );
+
TRACE_EVENT(rxrpc_transmit,
TP_PROTO(struct rxrpc_call *call, enum rxrpc_transmit_trace why),
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 9c9817ddafc5..21cf164b6d85 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -778,6 +778,7 @@ static inline bool __rxrpc_set_call_completion(struct rxrpc_call *call,
call->error = error;
call->completion = compl,
call->state = RXRPC_CALL_COMPLETE;
+ trace_rxrpc_call_complete(call);
wake_up(&call->waitq);
return true;
}
^ permalink raw reply related
* [PATCH net-next 2/3] rxrpc, afs: Use debug_ids rather than pointers in traces
From: David Howells @ 2018-03-27 22:58 UTC (permalink / raw)
To: netdev; +Cc: dhowells, linux-afs, linux-kernel
In-Reply-To: <152219147024.24730.12727053395895392426.stgit@warthog.procyon.org.uk>
In rxrpc and afs, use the debug_ids that are monotonically allocated to
various objects as they're allocated rather than pointers as kernel
pointers are now hashed making them less useful. Further, the debug ids
aren't reused anywhere nearly as quickly.
In addition, allow kernel services that use rxrpc, such as afs, to take
numbers from the rxrpc counter, assign them to their own call struct and
pass them in to rxrpc for both client and service calls so that the trace
lines for each will have the same ID tag.
Signed-off-by: David Howells <dhowells@redhat.com>
---
fs/afs/internal.h | 1
fs/afs/rxrpc.c | 12 ++-
include/net/af_rxrpc.h | 11 ++-
include/trace/events/afs.h | 69 ++++++++-----------
include/trace/events/rxrpc.h | 155 +++++++++++++++++++++---------------------
net/rxrpc/af_rxrpc.c | 7 +-
net/rxrpc/ar-internal.h | 8 +-
net/rxrpc/call_accept.c | 18 +++--
net/rxrpc/call_object.c | 15 ++--
net/rxrpc/conn_event.c | 3 +
net/rxrpc/input.c | 6 +-
net/rxrpc/sendmsg.c | 3 +
12 files changed, 163 insertions(+), 145 deletions(-)
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index f38d6a561a84..72217170b155 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -118,6 +118,7 @@ struct afs_call {
bool ret_reply0; /* T if should return reply[0] on success */
bool upgrade; /* T to request service upgrade */
u16 service_id; /* Actual service ID (after upgrade) */
+ unsigned int debug_id; /* Trace ID */
u32 operation_ID; /* operation ID for an incoming call */
u32 count; /* count for use in unmarshalling */
__be32 tmp; /* place to extract temporary data */
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index e1126659f043..b819900916e6 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -131,6 +131,7 @@ static struct afs_call *afs_alloc_call(struct afs_net *net,
call->type = type;
call->net = net;
+ call->debug_id = atomic_inc_return(&rxrpc_debug_id);
atomic_set(&call->usage, 1);
INIT_WORK(&call->async_work, afs_process_async_call);
init_waitqueue_head(&call->waitq);
@@ -169,11 +170,12 @@ void afs_put_call(struct afs_call *call)
afs_put_server(call->net, call->cm_server);
afs_put_cb_interest(call->net, call->cbi);
kfree(call->request);
- kfree(call);
- o = atomic_dec_return(&net->nr_outstanding_calls);
trace_afs_call(call, afs_call_trace_free, 0, o,
__builtin_return_address(0));
+ kfree(call);
+
+ o = atomic_dec_return(&net->nr_outstanding_calls);
if (o == 0)
wake_up_atomic_t(&net->nr_outstanding_calls);
}
@@ -378,7 +380,8 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call,
(async ?
afs_wake_up_async_call :
afs_wake_up_call_waiter),
- call->upgrade);
+ call->upgrade,
+ call->debug_id);
if (IS_ERR(rxcall)) {
ret = PTR_ERR(rxcall);
goto error_kill_call;
@@ -727,7 +730,8 @@ void afs_charge_preallocation(struct work_struct *work)
afs_wake_up_async_call,
afs_rx_attach,
(unsigned long)call,
- GFP_KERNEL) < 0)
+ GFP_KERNEL,
+ call->debug_id) < 0)
break;
call = NULL;
}
diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
index 2b3a6eec4570..8ae8ee004258 100644
--- a/include/net/af_rxrpc.h
+++ b/include/net/af_rxrpc.h
@@ -31,6 +31,11 @@ enum rxrpc_call_completion {
NR__RXRPC_CALL_COMPLETIONS
};
+/*
+ * Debug ID counter for tracing.
+ */
+extern atomic_t rxrpc_debug_id;
+
typedef void (*rxrpc_notify_rx_t)(struct sock *, struct rxrpc_call *,
unsigned long);
typedef void (*rxrpc_notify_end_tx_t)(struct sock *, struct rxrpc_call *,
@@ -50,7 +55,8 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *,
s64,
gfp_t,
rxrpc_notify_rx_t,
- bool);
+ bool,
+ unsigned int);
int rxrpc_kernel_send_data(struct socket *, struct rxrpc_call *,
struct msghdr *, size_t,
rxrpc_notify_end_tx_t);
@@ -63,7 +69,8 @@ void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *,
struct sockaddr_rxrpc *);
u64 rxrpc_kernel_get_rtt(struct socket *, struct rxrpc_call *);
int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t,
- rxrpc_user_attach_call_t, unsigned long, gfp_t);
+ rxrpc_user_attach_call_t, unsigned long, gfp_t,
+ unsigned int);
void rxrpc_kernel_set_tx_length(struct socket *, struct rxrpc_call *, s64);
int rxrpc_kernel_retry_call(struct socket *, struct rxrpc_call *,
struct sockaddr_rxrpc *, struct key *);
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 6b59c63a8e51..63815f66b274 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -133,8 +133,7 @@ TRACE_EVENT(afs_recv_data,
TP_ARGS(call, count, offset, want_more, ret),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, rxcall )
- __field(struct afs_call *, call )
+ __field(unsigned int, call )
__field(enum afs_call_state, state )
__field(unsigned int, count )
__field(unsigned int, offset )
@@ -144,8 +143,7 @@ TRACE_EVENT(afs_recv_data,
),
TP_fast_assign(
- __entry->rxcall = call->rxcall;
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->state = call->state;
__entry->unmarshall = call->unmarshall;
__entry->count = count;
@@ -154,8 +152,7 @@ TRACE_EVENT(afs_recv_data,
__entry->ret = ret;
),
- TP_printk("c=%p ac=%p s=%u u=%u %u/%u wm=%u ret=%d",
- __entry->rxcall,
+ TP_printk("c=%08x s=%u u=%u %u/%u wm=%u ret=%d",
__entry->call,
__entry->state, __entry->unmarshall,
__entry->offset, __entry->count,
@@ -168,21 +165,18 @@ TRACE_EVENT(afs_notify_call,
TP_ARGS(rxcall, call),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, rxcall )
- __field(struct afs_call *, call )
+ __field(unsigned int, call )
__field(enum afs_call_state, state )
__field(unsigned short, unmarshall )
),
TP_fast_assign(
- __entry->rxcall = rxcall;
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->state = call->state;
__entry->unmarshall = call->unmarshall;
),
- TP_printk("c=%p ac=%p s=%u u=%u",
- __entry->rxcall,
+ TP_printk("c=%08x s=%u u=%u",
__entry->call,
__entry->state, __entry->unmarshall)
);
@@ -193,21 +187,18 @@ TRACE_EVENT(afs_cb_call,
TP_ARGS(call),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, rxcall )
- __field(struct afs_call *, call )
+ __field(unsigned int, call )
__field(const char *, name )
__field(u32, op )
),
TP_fast_assign(
- __entry->rxcall = call->rxcall;
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->name = call->type->name;
__entry->op = call->operation_ID;
),
- TP_printk("c=%p ac=%p %s o=%u",
- __entry->rxcall,
+ TP_printk("c=%08x %s o=%u",
__entry->call,
__entry->name,
__entry->op)
@@ -220,7 +211,7 @@ TRACE_EVENT(afs_call,
TP_ARGS(call, op, usage, outstanding, where),
TP_STRUCT__entry(
- __field(struct afs_call *, call )
+ __field(unsigned int, call )
__field(int, op )
__field(int, usage )
__field(int, outstanding )
@@ -228,14 +219,14 @@ TRACE_EVENT(afs_call,
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->op = op;
__entry->usage = usage;
__entry->outstanding = outstanding;
__entry->where = where;
),
- TP_printk("c=%p %s u=%d o=%d sp=%pSR",
+ TP_printk("c=%08x %s u=%d o=%d sp=%pSR",
__entry->call,
__print_symbolic(__entry->op, afs_call_traces),
__entry->usage,
@@ -249,13 +240,13 @@ TRACE_EVENT(afs_make_fs_call,
TP_ARGS(call, fid),
TP_STRUCT__entry(
- __field(struct afs_call *, call )
+ __field(unsigned int, call )
__field(enum afs_fs_operation, op )
__field_struct(struct afs_fid, fid )
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->op = call->operation_ID;
if (fid) {
__entry->fid = *fid;
@@ -266,7 +257,7 @@ TRACE_EVENT(afs_make_fs_call,
}
),
- TP_printk("c=%p %06x:%06x:%06x %s",
+ TP_printk("c=%08x %06x:%06x:%06x %s",
__entry->call,
__entry->fid.vid,
__entry->fid.vnode,
@@ -280,16 +271,16 @@ TRACE_EVENT(afs_make_vl_call,
TP_ARGS(call),
TP_STRUCT__entry(
- __field(struct afs_call *, call )
+ __field(unsigned int, call )
__field(enum afs_vl_operation, op )
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->op = call->operation_ID;
),
- TP_printk("c=%p %s",
+ TP_printk("c=%08x %s",
__entry->call,
__print_symbolic(__entry->op, afs_vl_operations))
);
@@ -300,20 +291,20 @@ TRACE_EVENT(afs_call_done,
TP_ARGS(call),
TP_STRUCT__entry(
- __field(struct afs_call *, call )
+ __field(unsigned int, call )
__field(struct rxrpc_call *, rx_call )
__field(int, ret )
__field(u32, abort_code )
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->rx_call = call->rxcall;
__entry->ret = call->error;
__entry->abort_code = call->abort_code;
),
- TP_printk(" c=%p ret=%d ab=%d [%p]",
+ TP_printk(" c=%08x ret=%d ab=%d [%p]",
__entry->call,
__entry->ret,
__entry->abort_code,
@@ -327,7 +318,7 @@ TRACE_EVENT(afs_send_pages,
TP_ARGS(call, msg, first, last, offset),
TP_STRUCT__entry(
- __field(struct afs_call *, call )
+ __field(unsigned int, call )
__field(pgoff_t, first )
__field(pgoff_t, last )
__field(unsigned int, nr )
@@ -337,7 +328,7 @@ TRACE_EVENT(afs_send_pages,
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->first = first;
__entry->last = last;
__entry->nr = msg->msg_iter.nr_segs;
@@ -346,7 +337,7 @@ TRACE_EVENT(afs_send_pages,
__entry->flags = msg->msg_flags;
),
- TP_printk(" c=%p %lx-%lx-%lx b=%x o=%x f=%x",
+ TP_printk(" c=%08x %lx-%lx-%lx b=%x o=%x f=%x",
__entry->call,
__entry->first, __entry->first + __entry->nr - 1, __entry->last,
__entry->bytes, __entry->offset,
@@ -360,7 +351,7 @@ TRACE_EVENT(afs_sent_pages,
TP_ARGS(call, first, last, cursor, ret),
TP_STRUCT__entry(
- __field(struct afs_call *, call )
+ __field(unsigned int, call )
__field(pgoff_t, first )
__field(pgoff_t, last )
__field(pgoff_t, cursor )
@@ -368,14 +359,14 @@ TRACE_EVENT(afs_sent_pages,
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->first = first;
__entry->last = last;
__entry->cursor = cursor;
__entry->ret = ret;
),
- TP_printk(" c=%p %lx-%lx c=%lx r=%d",
+ TP_printk(" c=%08x %lx-%lx c=%lx r=%d",
__entry->call,
__entry->first, __entry->last,
__entry->cursor, __entry->ret)
@@ -450,7 +441,7 @@ TRACE_EVENT(afs_call_state,
TP_ARGS(call, from, to, ret, remote_abort),
TP_STRUCT__entry(
- __field(struct afs_call *, call )
+ __field(unsigned int, call )
__field(enum afs_call_state, from )
__field(enum afs_call_state, to )
__field(int, ret )
@@ -458,14 +449,14 @@ TRACE_EVENT(afs_call_state,
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->from = from;
__entry->to = to;
__entry->ret = ret;
__entry->abort = remote_abort;
),
- TP_printk("c=%p %u->%u r=%d ab=%d",
+ TP_printk("c=%08x %u->%u r=%d ab=%d",
__entry->call,
__entry->from, __entry->to,
__entry->ret, __entry->abort)
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 41979f907575..4d2c2d35c5cb 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -439,20 +439,20 @@ TRACE_EVENT(rxrpc_conn,
TP_ARGS(conn, op, usage, where),
TP_STRUCT__entry(
- __field(struct rxrpc_connection *, conn )
- __field(int, op )
- __field(int, usage )
- __field(const void *, where )
+ __field(unsigned int, conn )
+ __field(int, op )
+ __field(int, usage )
+ __field(const void *, where )
),
TP_fast_assign(
- __entry->conn = conn;
+ __entry->conn = conn->debug_id;
__entry->op = op;
__entry->usage = usage;
__entry->where = where;
),
- TP_printk("C=%p %s u=%d sp=%pSR",
+ TP_printk("C=%08x %s u=%d sp=%pSR",
__entry->conn,
__print_symbolic(__entry->op, rxrpc_conn_traces),
__entry->usage,
@@ -466,7 +466,7 @@ TRACE_EVENT(rxrpc_client,
TP_ARGS(conn, channel, op),
TP_STRUCT__entry(
- __field(struct rxrpc_connection *, conn )
+ __field(unsigned int, conn )
__field(u32, cid )
__field(int, channel )
__field(int, usage )
@@ -475,7 +475,7 @@ TRACE_EVENT(rxrpc_client,
),
TP_fast_assign(
- __entry->conn = conn;
+ __entry->conn = conn->debug_id;
__entry->channel = channel;
__entry->usage = atomic_read(&conn->usage);
__entry->op = op;
@@ -483,7 +483,7 @@ TRACE_EVENT(rxrpc_client,
__entry->cs = conn->cache_state;
),
- TP_printk("C=%p h=%2d %s %s i=%08x u=%d",
+ TP_printk("C=%08x h=%2d %s %s i=%08x u=%d",
__entry->conn,
__entry->channel,
__print_symbolic(__entry->op, rxrpc_client_traces),
@@ -499,7 +499,7 @@ TRACE_EVENT(rxrpc_call,
TP_ARGS(call, op, usage, where, aux),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, call )
+ __field(unsigned int, call )
__field(int, op )
__field(int, usage )
__field(const void *, where )
@@ -507,14 +507,14 @@ TRACE_EVENT(rxrpc_call,
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->op = op;
__entry->usage = usage;
__entry->where = where;
__entry->aux = aux;
),
- TP_printk("c=%p %s u=%d sp=%pSR a=%p",
+ TP_printk("c=%08x %s u=%d sp=%pSR a=%p",
__entry->call,
__print_symbolic(__entry->op, rxrpc_call_traces),
__entry->usage,
@@ -593,12 +593,13 @@ TRACE_EVENT(rxrpc_rx_done,
);
TRACE_EVENT(rxrpc_abort,
- TP_PROTO(const char *why, u32 cid, u32 call_id, rxrpc_seq_t seq,
- int abort_code, int error),
+ TP_PROTO(unsigned int call_nr, const char *why, u32 cid, u32 call_id,
+ rxrpc_seq_t seq, int abort_code, int error),
- TP_ARGS(why, cid, call_id, seq, abort_code, error),
+ TP_ARGS(call_nr, why, cid, call_id, seq, abort_code, error),
TP_STRUCT__entry(
+ __field(unsigned int, call_nr )
__array(char, why, 4 )
__field(u32, cid )
__field(u32, call_id )
@@ -609,6 +610,7 @@ TRACE_EVENT(rxrpc_abort,
TP_fast_assign(
memcpy(__entry->why, why, 4);
+ __entry->call_nr = call_nr;
__entry->cid = cid;
__entry->call_id = call_id;
__entry->abort_code = abort_code;
@@ -616,7 +618,8 @@ TRACE_EVENT(rxrpc_abort,
__entry->seq = seq;
),
- TP_printk("%08x:%08x s=%u a=%d e=%d %s",
+ TP_printk("c=%08x %08x:%08x s=%u a=%d e=%d %s",
+ __entry->call_nr,
__entry->cid, __entry->call_id, __entry->seq,
__entry->abort_code, __entry->error, __entry->why)
);
@@ -627,7 +630,7 @@ TRACE_EVENT(rxrpc_transmit,
TP_ARGS(call, why),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, call )
+ __field(unsigned int, call )
__field(enum rxrpc_transmit_trace, why )
__field(rxrpc_seq_t, tx_hard_ack )
__field(rxrpc_seq_t, tx_top )
@@ -635,14 +638,14 @@ TRACE_EVENT(rxrpc_transmit,
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->why = why;
__entry->tx_hard_ack = call->tx_hard_ack;
__entry->tx_top = call->tx_top;
__entry->tx_winsize = call->tx_winsize;
),
- TP_printk("c=%p %s f=%08x n=%u/%u",
+ TP_printk("c=%08x %s f=%08x n=%u/%u",
__entry->call,
__print_symbolic(__entry->why, rxrpc_transmit_traces),
__entry->tx_hard_ack + 1,
@@ -657,7 +660,7 @@ TRACE_EVENT(rxrpc_rx_data,
TP_ARGS(call, seq, serial, flags, anno),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, call )
+ __field(unsigned int, call )
__field(rxrpc_seq_t, seq )
__field(rxrpc_serial_t, serial )
__field(u8, flags )
@@ -665,14 +668,14 @@ TRACE_EVENT(rxrpc_rx_data,
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->seq = seq;
__entry->serial = serial;
__entry->flags = flags;
__entry->anno = anno;
),
- TP_printk("c=%p DATA %08x q=%08x fl=%02x a=%02x",
+ TP_printk("c=%08x DATA %08x q=%08x fl=%02x a=%02x",
__entry->call,
__entry->serial,
__entry->seq,
@@ -688,7 +691,7 @@ TRACE_EVENT(rxrpc_rx_ack,
TP_ARGS(call, serial, ack_serial, first, prev, reason, n_acks),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, call )
+ __field(unsigned int, call )
__field(rxrpc_serial_t, serial )
__field(rxrpc_serial_t, ack_serial )
__field(rxrpc_seq_t, first )
@@ -698,7 +701,7 @@ TRACE_EVENT(rxrpc_rx_ack,
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->serial = serial;
__entry->ack_serial = ack_serial;
__entry->first = first;
@@ -707,7 +710,7 @@ TRACE_EVENT(rxrpc_rx_ack,
__entry->n_acks = n_acks;
),
- TP_printk("c=%p %08x %s r=%08x f=%08x p=%08x n=%u",
+ TP_printk("c=%08x %08x %s r=%08x f=%08x p=%08x n=%u",
__entry->call,
__entry->serial,
__print_symbolic(__entry->reason, rxrpc_ack_names),
@@ -724,18 +727,18 @@ TRACE_EVENT(rxrpc_rx_abort,
TP_ARGS(call, serial, abort_code),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, call )
+ __field(unsigned int, call )
__field(rxrpc_serial_t, serial )
__field(u32, abort_code )
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->serial = serial;
__entry->abort_code = abort_code;
),
- TP_printk("c=%p ABORT %08x ac=%d",
+ TP_printk("c=%08x ABORT %08x ac=%d",
__entry->call,
__entry->serial,
__entry->abort_code)
@@ -748,20 +751,20 @@ TRACE_EVENT(rxrpc_rx_rwind_change,
TP_ARGS(call, serial, rwind, wake),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, call )
+ __field(unsigned int, call )
__field(rxrpc_serial_t, serial )
__field(u32, rwind )
__field(bool, wake )
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->serial = serial;
__entry->rwind = rwind;
__entry->wake = wake;
),
- TP_printk("c=%p %08x rw=%u%s",
+ TP_printk("c=%08x %08x rw=%u%s",
__entry->call,
__entry->serial,
__entry->rwind,
@@ -775,7 +778,7 @@ TRACE_EVENT(rxrpc_tx_data,
TP_ARGS(call, seq, serial, flags, retrans, lose),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, call )
+ __field(unsigned int, call )
__field(rxrpc_seq_t, seq )
__field(rxrpc_serial_t, serial )
__field(u8, flags )
@@ -784,7 +787,7 @@ TRACE_EVENT(rxrpc_tx_data,
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->seq = seq;
__entry->serial = serial;
__entry->flags = flags;
@@ -792,7 +795,7 @@ TRACE_EVENT(rxrpc_tx_data,
__entry->lose = lose;
),
- TP_printk("c=%p DATA %08x q=%08x fl=%02x%s%s",
+ TP_printk("c=%08x DATA %08x q=%08x fl=%02x%s%s",
__entry->call,
__entry->serial,
__entry->seq,
@@ -809,7 +812,7 @@ TRACE_EVENT(rxrpc_tx_ack,
TP_ARGS(call, serial, ack_first, ack_serial, reason, n_acks),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, call )
+ __field(unsigned int, call )
__field(rxrpc_serial_t, serial )
__field(rxrpc_seq_t, ack_first )
__field(rxrpc_serial_t, ack_serial )
@@ -818,7 +821,7 @@ TRACE_EVENT(rxrpc_tx_ack,
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call ? call->debug_id : 0;
__entry->serial = serial;
__entry->ack_first = ack_first;
__entry->ack_serial = ack_serial;
@@ -826,7 +829,7 @@ TRACE_EVENT(rxrpc_tx_ack,
__entry->n_acks = n_acks;
),
- TP_printk(" c=%p ACK %08x %s f=%08x r=%08x n=%u",
+ TP_printk(" c=%08x ACK %08x %s f=%08x r=%08x n=%u",
__entry->call,
__entry->serial,
__print_symbolic(__entry->reason, rxrpc_ack_names),
@@ -842,7 +845,7 @@ TRACE_EVENT(rxrpc_receive,
TP_ARGS(call, why, serial, seq),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, call )
+ __field(unsigned int, call )
__field(enum rxrpc_receive_trace, why )
__field(rxrpc_serial_t, serial )
__field(rxrpc_seq_t, seq )
@@ -851,7 +854,7 @@ TRACE_EVENT(rxrpc_receive,
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->why = why;
__entry->serial = serial;
__entry->seq = seq;
@@ -859,7 +862,7 @@ TRACE_EVENT(rxrpc_receive,
__entry->top = call->rx_top;
),
- TP_printk("c=%p %s r=%08x q=%08x w=%08x-%08x",
+ TP_printk("c=%08x %s r=%08x q=%08x w=%08x-%08x",
__entry->call,
__print_symbolic(__entry->why, rxrpc_receive_traces),
__entry->serial,
@@ -876,7 +879,7 @@ TRACE_EVENT(rxrpc_recvmsg,
TP_ARGS(call, why, seq, offset, len, ret),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, call )
+ __field(unsigned int, call )
__field(enum rxrpc_recvmsg_trace, why )
__field(rxrpc_seq_t, seq )
__field(unsigned int, offset )
@@ -885,7 +888,7 @@ TRACE_EVENT(rxrpc_recvmsg,
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->why = why;
__entry->seq = seq;
__entry->offset = offset;
@@ -893,7 +896,7 @@ TRACE_EVENT(rxrpc_recvmsg,
__entry->ret = ret;
),
- TP_printk("c=%p %s q=%08x o=%u l=%u ret=%d",
+ TP_printk("c=%08x %s q=%08x o=%u l=%u ret=%d",
__entry->call,
__print_symbolic(__entry->why, rxrpc_recvmsg_traces),
__entry->seq,
@@ -909,18 +912,18 @@ TRACE_EVENT(rxrpc_rtt_tx,
TP_ARGS(call, why, send_serial),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, call )
+ __field(unsigned int, call )
__field(enum rxrpc_rtt_tx_trace, why )
__field(rxrpc_serial_t, send_serial )
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->why = why;
__entry->send_serial = send_serial;
),
- TP_printk("c=%p %s sr=%08x",
+ TP_printk("c=%08x %s sr=%08x",
__entry->call,
__print_symbolic(__entry->why, rxrpc_rtt_tx_traces),
__entry->send_serial)
@@ -934,7 +937,7 @@ TRACE_EVENT(rxrpc_rtt_rx,
TP_ARGS(call, why, send_serial, resp_serial, rtt, nr, avg),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, call )
+ __field(unsigned int, call )
__field(enum rxrpc_rtt_rx_trace, why )
__field(u8, nr )
__field(rxrpc_serial_t, send_serial )
@@ -944,7 +947,7 @@ TRACE_EVENT(rxrpc_rtt_rx,
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->why = why;
__entry->send_serial = send_serial;
__entry->resp_serial = resp_serial;
@@ -953,7 +956,7 @@ TRACE_EVENT(rxrpc_rtt_rx,
__entry->avg = avg;
),
- TP_printk("c=%p %s sr=%08x rr=%08x rtt=%lld nr=%u avg=%lld",
+ TP_printk("c=%08x %s sr=%08x rr=%08x rtt=%lld nr=%u avg=%lld",
__entry->call,
__print_symbolic(__entry->why, rxrpc_rtt_rx_traces),
__entry->send_serial,
@@ -970,7 +973,7 @@ TRACE_EVENT(rxrpc_timer,
TP_ARGS(call, why, now),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, call )
+ __field(unsigned int, call )
__field(enum rxrpc_timer_trace, why )
__field(long, now )
__field(long, ack_at )
@@ -984,7 +987,7 @@ TRACE_EVENT(rxrpc_timer,
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->why = why;
__entry->now = now;
__entry->ack_at = call->ack_at;
@@ -996,7 +999,7 @@ TRACE_EVENT(rxrpc_timer,
__entry->timer = call->timer.expires;
),
- TP_printk("c=%p %s a=%ld la=%ld r=%ld xr=%ld xq=%ld xt=%ld t=%ld",
+ TP_printk("c=%08x %s a=%ld la=%ld r=%ld xr=%ld xq=%ld xt=%ld t=%ld",
__entry->call,
__print_symbolic(__entry->why, rxrpc_timer_traces),
__entry->ack_at - __entry->now,
@@ -1039,7 +1042,7 @@ TRACE_EVENT(rxrpc_propose_ack,
outcome),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, call )
+ __field(unsigned int, call )
__field(enum rxrpc_propose_ack_trace, why )
__field(rxrpc_serial_t, serial )
__field(u8, ack_reason )
@@ -1049,7 +1052,7 @@ TRACE_EVENT(rxrpc_propose_ack,
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->why = why;
__entry->serial = serial;
__entry->ack_reason = ack_reason;
@@ -1058,7 +1061,7 @@ TRACE_EVENT(rxrpc_propose_ack,
__entry->outcome = outcome;
),
- TP_printk("c=%p %s %s r=%08x i=%u b=%u%s",
+ TP_printk("c=%08x %s %s r=%08x i=%u b=%u%s",
__entry->call,
__print_symbolic(__entry->why, rxrpc_propose_ack_traces),
__print_symbolic(__entry->ack_reason, rxrpc_ack_names),
@@ -1075,20 +1078,20 @@ TRACE_EVENT(rxrpc_retransmit,
TP_ARGS(call, seq, annotation, expiry),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, call )
+ __field(unsigned int, call )
__field(rxrpc_seq_t, seq )
__field(u8, annotation )
__field(s64, expiry )
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->seq = seq;
__entry->annotation = annotation;
__entry->expiry = expiry;
),
- TP_printk("c=%p q=%x a=%02x xp=%lld",
+ TP_printk("c=%08x q=%x a=%02x xp=%lld",
__entry->call,
__entry->seq,
__entry->annotation,
@@ -1102,7 +1105,7 @@ TRACE_EVENT(rxrpc_congest,
TP_ARGS(call, summary, ack_serial, change),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, call )
+ __field(unsigned int, call )
__field(enum rxrpc_congest_change, change )
__field(rxrpc_seq_t, hard_ack )
__field(rxrpc_seq_t, top )
@@ -1112,7 +1115,7 @@ TRACE_EVENT(rxrpc_congest,
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->change = change;
__entry->hard_ack = call->tx_hard_ack;
__entry->top = call->tx_top;
@@ -1121,7 +1124,7 @@ TRACE_EVENT(rxrpc_congest,
memcpy(&__entry->sum, summary, sizeof(__entry->sum));
),
- TP_printk("c=%p r=%08x %s q=%08x %s cw=%u ss=%u nr=%u,%u nw=%u,%u r=%u b=%u u=%u d=%u l=%x%s%s%s",
+ TP_printk("c=%08x r=%08x %s q=%08x %s cw=%u ss=%u nr=%u,%u nw=%u,%u r=%u b=%u u=%u d=%u l=%x%s%s%s",
__entry->call,
__entry->ack_serial,
__print_symbolic(__entry->sum.ack_reason, rxrpc_ack_names),
@@ -1146,16 +1149,16 @@ TRACE_EVENT(rxrpc_disconnect_call,
TP_ARGS(call),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, call )
+ __field(unsigned int, call )
__field(u32, abort_code )
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->abort_code = call->abort_code;
),
- TP_printk("c=%p ab=%08x",
+ TP_printk("c=%08x ab=%08x",
__entry->call,
__entry->abort_code)
);
@@ -1166,16 +1169,16 @@ TRACE_EVENT(rxrpc_improper_term,
TP_ARGS(call),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, call )
+ __field(unsigned int, call )
__field(u32, abort_code )
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->abort_code = call->abort_code;
),
- TP_printk("c=%p ab=%08x",
+ TP_printk("c=%08x ab=%08x",
__entry->call,
__entry->abort_code)
);
@@ -1187,18 +1190,18 @@ TRACE_EVENT(rxrpc_rx_eproto,
TP_ARGS(call, serial, why),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, call )
+ __field(unsigned int, call )
__field(rxrpc_serial_t, serial )
__field(const char *, why )
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->serial = serial;
__entry->why = why;
),
- TP_printk("c=%p EPROTO %08x %s",
+ TP_printk("c=%08x EPROTO %08x %s",
__entry->call,
__entry->serial,
__entry->why)
@@ -1210,20 +1213,20 @@ TRACE_EVENT(rxrpc_connect_call,
TP_ARGS(call),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, call )
+ __field(unsigned int, call )
__field(unsigned long, user_call_ID )
__field(u32, cid )
__field(u32, call_id )
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->user_call_ID = call->user_call_ID;
__entry->cid = call->cid;
__entry->call_id = call->call_id;
),
- TP_printk("c=%p u=%p %08x:%08x",
+ TP_printk("c=%08x u=%p %08x:%08x",
__entry->call,
(void *)__entry->user_call_ID,
__entry->cid,
@@ -1236,18 +1239,18 @@ TRACE_EVENT(rxrpc_resend,
TP_ARGS(call, ix),
TP_STRUCT__entry(
- __field(struct rxrpc_call *, call )
+ __field(unsigned int, call )
__field(int, ix )
__array(u8, anno, 64 )
),
TP_fast_assign(
- __entry->call = call;
+ __entry->call = call->debug_id;
__entry->ix = ix;
memcpy(__entry->anno, call->rxtx_annotations, 64);
),
- TP_printk("c=%p ix=%u a=%64phN",
+ TP_printk("c=%08x ix=%u a=%64phN",
__entry->call,
__entry->ix,
__entry->anno)
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 9e1c2c6b6a67..ec5ec68be1aa 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -40,6 +40,7 @@ static const struct proto_ops rxrpc_rpc_ops;
/* current debugging ID */
atomic_t rxrpc_debug_id;
+EXPORT_SYMBOL(rxrpc_debug_id);
/* count of skbs currently in use */
atomic_t rxrpc_n_tx_skbs, rxrpc_n_rx_skbs;
@@ -267,6 +268,7 @@ static int rxrpc_listen(struct socket *sock, int backlog)
* @gfp: The allocation constraints
* @notify_rx: Where to send notifications instead of socket queue
* @upgrade: Request service upgrade for call
+ * @debug_id: The debug ID for tracing to be assigned to the call
*
* Allow a kernel service to begin a call on the nominated socket. This just
* sets up all the internal tracking structures and allocates connection and
@@ -282,7 +284,8 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
s64 tx_total_len,
gfp_t gfp,
rxrpc_notify_rx_t notify_rx,
- bool upgrade)
+ bool upgrade,
+ unsigned int debug_id)
{
struct rxrpc_conn_parameters cp;
struct rxrpc_call_params p;
@@ -314,7 +317,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
cp.exclusive = false;
cp.upgrade = upgrade;
cp.service_id = srx->srx_service;
- call = rxrpc_new_client_call(rx, &cp, srx, &p, gfp);
+ call = rxrpc_new_client_call(rx, &cp, srx, &p, gfp, debug_id);
/* The socket has been unlocked. */
if (!IS_ERR(call)) {
call->notify_rx = notify_rx;
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 416688381eb7..9c9817ddafc5 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -691,7 +691,6 @@ struct rxrpc_send_params {
* af_rxrpc.c
*/
extern atomic_t rxrpc_n_tx_skbs, rxrpc_n_rx_skbs;
-extern atomic_t rxrpc_debug_id;
extern struct workqueue_struct *rxrpc_workqueue;
/*
@@ -732,11 +731,12 @@ extern unsigned int rxrpc_max_call_lifetime;
extern struct kmem_cache *rxrpc_call_jar;
struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *, unsigned long);
-struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *, gfp_t);
+struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *, gfp_t, unsigned int);
struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *,
struct rxrpc_conn_parameters *,
struct sockaddr_rxrpc *,
- struct rxrpc_call_params *, gfp_t);
+ struct rxrpc_call_params *, gfp_t,
+ unsigned int);
int rxrpc_retry_client_call(struct rxrpc_sock *,
struct rxrpc_call *,
struct rxrpc_conn_parameters *,
@@ -822,7 +822,7 @@ static inline bool __rxrpc_abort_call(const char *why, struct rxrpc_call *call,
rxrpc_seq_t seq,
u32 abort_code, int error)
{
- trace_rxrpc_abort(why, call->cid, call->call_id, seq,
+ trace_rxrpc_abort(call->debug_id, why, call->cid, call->call_id, seq,
abort_code, error);
return __rxrpc_set_call_completion(call, RXRPC_CALL_LOCALLY_ABORTED,
abort_code, error);
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 3028298ca561..92ebd1d7e0bb 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -34,7 +34,8 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
struct rxrpc_backlog *b,
rxrpc_notify_rx_t notify_rx,
rxrpc_user_attach_call_t user_attach_call,
- unsigned long user_call_ID, gfp_t gfp)
+ unsigned long user_call_ID, gfp_t gfp,
+ unsigned int debug_id)
{
const void *here = __builtin_return_address(0);
struct rxrpc_call *call;
@@ -94,7 +95,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx,
/* Now it gets complicated, because calls get registered with the
* socket here, particularly if a user ID is preassigned by the user.
*/
- call = rxrpc_alloc_call(rx, gfp);
+ call = rxrpc_alloc_call(rx, gfp, debug_id);
if (!call)
return -ENOMEM;
call->flags |= (1 << RXRPC_CALL_IS_SERVICE);
@@ -174,7 +175,8 @@ int rxrpc_service_prealloc(struct rxrpc_sock *rx, gfp_t gfp)
if (rx->discard_new_call)
return 0;
- while (rxrpc_service_prealloc_one(rx, b, NULL, NULL, 0, gfp) == 0)
+ while (rxrpc_service_prealloc_one(rx, b, NULL, NULL, 0, gfp,
+ atomic_inc_return(&rxrpc_debug_id)) == 0)
;
return 0;
@@ -347,7 +349,7 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
service_id == rx->second_service))
goto found_service;
- trace_rxrpc_abort("INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+ trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
RX_INVALID_OPERATION, EOPNOTSUPP);
skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT;
skb->priority = RX_INVALID_OPERATION;
@@ -358,7 +360,7 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
spin_lock(&rx->incoming_lock);
if (rx->sk.sk_state == RXRPC_SERVER_LISTEN_DISABLED ||
rx->sk.sk_state == RXRPC_CLOSE) {
- trace_rxrpc_abort("CLS", sp->hdr.cid, sp->hdr.callNumber,
+ trace_rxrpc_abort(0, "CLS", sp->hdr.cid, sp->hdr.callNumber,
sp->hdr.seq, RX_INVALID_OPERATION, ESHUTDOWN);
skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT;
skb->priority = RX_INVALID_OPERATION;
@@ -635,6 +637,7 @@ int rxrpc_reject_call(struct rxrpc_sock *rx)
* @user_attach_call: Func to attach call to user_call_ID
* @user_call_ID: The tag to attach to the preallocated call
* @gfp: The allocation conditions.
+ * @debug_id: The tracing debug ID.
*
* Charge up the socket with preallocated calls, each with a user ID. A
* function should be provided to effect the attachment from the user's side.
@@ -645,7 +648,8 @@ int rxrpc_reject_call(struct rxrpc_sock *rx)
int rxrpc_kernel_charge_accept(struct socket *sock,
rxrpc_notify_rx_t notify_rx,
rxrpc_user_attach_call_t user_attach_call,
- unsigned long user_call_ID, gfp_t gfp)
+ unsigned long user_call_ID, gfp_t gfp,
+ unsigned int debug_id)
{
struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
struct rxrpc_backlog *b = rx->backlog;
@@ -655,6 +659,6 @@ int rxrpc_kernel_charge_accept(struct socket *sock,
return rxrpc_service_prealloc_one(rx, b, notify_rx,
user_attach_call, user_call_ID,
- gfp);
+ gfp, debug_id);
}
EXPORT_SYMBOL(rxrpc_kernel_charge_accept);
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 0b2db38dd32d..147657dfe757 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -99,7 +99,8 @@ struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *rx,
/*
* allocate a new call
*/
-struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp)
+struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp,
+ unsigned int debug_id)
{
struct rxrpc_call *call;
@@ -138,7 +139,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp)
spin_lock_init(&call->notify_lock);
rwlock_init(&call->state_lock);
atomic_set(&call->usage, 1);
- call->debug_id = atomic_inc_return(&rxrpc_debug_id);
+ call->debug_id = debug_id;
call->tx_total_len = -1;
call->next_rx_timo = 20 * HZ;
call->next_req_timo = 1 * HZ;
@@ -166,14 +167,15 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp)
*/
static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx,
struct sockaddr_rxrpc *srx,
- gfp_t gfp)
+ gfp_t gfp,
+ unsigned int debug_id)
{
struct rxrpc_call *call;
ktime_t now;
_enter("");
- call = rxrpc_alloc_call(rx, gfp);
+ call = rxrpc_alloc_call(rx, gfp, debug_id);
if (!call)
return ERR_PTR(-ENOMEM);
call->state = RXRPC_CALL_CLIENT_AWAIT_CONN;
@@ -214,7 +216,8 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
struct rxrpc_conn_parameters *cp,
struct sockaddr_rxrpc *srx,
struct rxrpc_call_params *p,
- gfp_t gfp)
+ gfp_t gfp,
+ unsigned int debug_id)
__releases(&rx->sk.sk_lock.slock)
{
struct rxrpc_call *call, *xcall;
@@ -225,7 +228,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
_enter("%p,%lx", rx, p->user_call_ID);
- call = rxrpc_alloc_client_call(rx, srx, gfp);
+ call = rxrpc_alloc_client_call(rx, srx, gfp, debug_id);
if (IS_ERR(call)) {
release_sock(&rx->sk);
_leave(" = %ld", PTR_ERR(call));
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index b1dfae107431..d2ec3fd593e8 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -160,7 +160,8 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn,
lockdep_is_held(&conn->channel_lock));
if (call) {
if (compl == RXRPC_CALL_LOCALLY_ABORTED)
- trace_rxrpc_abort("CON", call->cid,
+ trace_rxrpc_abort(call->debug_id,
+ "CON", call->cid,
call->call_id, 0,
abort_code, error);
if (rxrpc_set_call_completion(call, compl,
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 6fc61400337f..2a868fdab0ae 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -1307,21 +1307,21 @@ void rxrpc_data_ready(struct sock *udp_sk)
wrong_security:
rcu_read_unlock();
- trace_rxrpc_abort("SEC", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+ trace_rxrpc_abort(0, "SEC", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
RXKADINCONSISTENCY, EBADMSG);
skb->priority = RXKADINCONSISTENCY;
goto post_abort;
reupgrade:
rcu_read_unlock();
- trace_rxrpc_abort("UPG", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+ trace_rxrpc_abort(0, "UPG", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
RX_PROTOCOL_ERROR, EBADMSG);
goto protocol_error;
bad_message_unlock:
rcu_read_unlock();
bad_message:
- trace_rxrpc_abort("BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+ trace_rxrpc_abort(0, "BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
RX_PROTOCOL_ERROR, EBADMSG);
protocol_error:
skb->priority = RX_PROTOCOL_ERROR;
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 09f2a3e05221..8503f279b467 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -579,7 +579,8 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg,
cp.exclusive = rx->exclusive | p->exclusive;
cp.upgrade = p->upgrade;
cp.service_id = srx->srx_service;
- call = rxrpc_new_client_call(rx, &cp, srx, &p->call, GFP_KERNEL);
+ call = rxrpc_new_client_call(rx, &cp, srx, &p->call, GFP_KERNEL,
+ atomic_inc_return(&rxrpc_debug_id));
/* The socket is now unlocked */
_leave(" = %p\n", call);
^ permalink raw reply related
* [PATCH net-next 1/3] rxrpc: Trace resend
From: David Howells @ 2018-03-27 22:57 UTC (permalink / raw)
To: netdev; +Cc: dhowells, linux-afs, linux-kernel
In-Reply-To: <152219147024.24730.12727053395895392426.stgit@warthog.procyon.org.uk>
Add a tracepoint to trace packet resend events and to dump the Tx
annotation buffer for added illumination.
Signed-off-by: David Howells <dhowells@rdhat.com>
---
include/trace/events/rxrpc.h | 24 ++++++++++++++++++++++++
net/rxrpc/call_event.c | 1 +
2 files changed, 25 insertions(+)
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 36cb50c111a6..41979f907575 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -420,6 +420,7 @@ rxrpc_rtt_rx_traces;
rxrpc_timer_traces;
rxrpc_propose_ack_traces;
rxrpc_propose_ack_outcomes;
+rxrpc_congest_modes;
rxrpc_congest_changes;
/*
@@ -1229,6 +1230,29 @@ TRACE_EVENT(rxrpc_connect_call,
__entry->call_id)
);
+TRACE_EVENT(rxrpc_resend,
+ TP_PROTO(struct rxrpc_call *call, int ix),
+
+ TP_ARGS(call, ix),
+
+ TP_STRUCT__entry(
+ __field(struct rxrpc_call *, call )
+ __field(int, ix )
+ __array(u8, anno, 64 )
+ ),
+
+ TP_fast_assign(
+ __entry->call = call;
+ __entry->ix = ix;
+ memcpy(__entry->anno, call->rxtx_annotations, 64);
+ ),
+
+ TP_printk("c=%p ix=%u a=%64phN",
+ __entry->call,
+ __entry->ix,
+ __entry->anno)
+ );
+
#endif /* _TRACE_RXRPC_H */
/* This part must be outside protection */
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index ad2ab1103189..6a62e42e1d8d 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -195,6 +195,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
* the packets in the Tx buffer we're going to resend and what the new
* resend timeout will be.
*/
+ trace_rxrpc_resend(call, (cursor + 1) & RXRPC_RXTX_BUFF_MASK);
oldest = now;
for (seq = cursor + 1; before_eq(seq, top); seq++) {
ix = seq & RXRPC_RXTX_BUFF_MASK;
^ permalink raw reply related
* [PATCH net-next 0/3] rxrpc: Tracing updates
From: David Howells @ 2018-03-27 22:57 UTC (permalink / raw)
To: netdev; +Cc: dhowells, linux-afs, linux-kernel
Here are some patches that update tracing in AF_RXRPC and AFS:
(1) Add a tracepoint for tracking resend events.
(2) Use debug_ids in traces rather than pointers (as pointers are now hashed)
and allow use of the same debug_id in AFS calls as in the corresponding
AF_RXRPC calls. This makes filtering the trace output much easier.
(3) Add a tracepoint for tracking call completion.
The patches are tagged here:
git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs.git
rxrpc-next-20180327
and can also be found on this branch:
http://git.kernel.org/cgit/linux/kernel/git/dhowells/linux-fs.git/log/?h=rxrpc-next
David
---
David Howells (3):
rxrpc: Trace resend
rxrpc, afs: Use debug_ids rather than pointers in traces
rxrpc: Trace call completion
fs/afs/internal.h | 1
fs/afs/rxrpc.c | 12 ++
include/net/af_rxrpc.h | 11 ++
include/trace/events/afs.h | 69 ++++++--------
include/trace/events/rxrpc.h | 206 +++++++++++++++++++++++++++---------------
net/rxrpc/af_rxrpc.c | 7 +
net/rxrpc/ar-internal.h | 9 +-
net/rxrpc/call_accept.c | 18 ++--
net/rxrpc/call_event.c | 1
net/rxrpc/call_object.c | 15 ++-
net/rxrpc/conn_event.c | 3 -
net/rxrpc/input.c | 6 +
net/rxrpc/sendmsg.c | 3 -
13 files changed, 219 insertions(+), 142 deletions(-)
^ permalink raw reply
* Re: [PATCH v3 1/2] of_net: Implement of_get_nvmem_mac_address helper
From: Florian Fainelli @ 2018-03-27 22:50 UTC (permalink / raw)
To: Mike Looijmans, netdev
Cc: linux-kernel, devicetree, andrew, robh+dt, frowand.list
In-Reply-To: <1522144346-32367-2-git-send-email-mike.looijmans@topic.nl>
On 03/27/2018 02:52 AM, Mike Looijmans wrote:
> It's common practice to store MAC addresses for network interfaces into
> nvmem devices. However the code to actually do this in the kernel lacks,
> so this patch adds of_get_nvmem_mac_address() for drivers to obtain the
> address from an nvmem cell provider.
>
> This is particulary useful on devices where the ethernet interface cannot
> be configured by the bootloader, for example because it's in an FPGA.
>
> Signed-off-by: Mike Looijmans <mike.looijmans@topic.nl>
> ---
> Documentation/devicetree/bindings/net/ethernet.txt | 2 ++
> drivers/of/of_net.c | 40 ++++++++++++++++++++++
> include/linux/of_net.h | 6 ++++
> 3 files changed, 48 insertions(+)
>
> diff --git a/Documentation/devicetree/bindings/net/ethernet.txt b/Documentation/devicetree/bindings/net/ethernet.txt
> index 2974e63..cfc376b 100644
> --- a/Documentation/devicetree/bindings/net/ethernet.txt
> +++ b/Documentation/devicetree/bindings/net/ethernet.txt
> @@ -10,6 +10,8 @@ Documentation/devicetree/bindings/phy/phy-bindings.txt.
> the boot program; should be used in cases where the MAC address assigned to
> the device by the boot program is different from the "local-mac-address"
> property;
> +- nvmem-cells: phandle, reference to an nvmem node for the MAC address;
> +- nvmem-cell-names: string, should be "mac-address" if nvmem is to be used;
> - max-speed: number, specifies maximum speed in Mbit/s supported by the device;
> - max-frame-size: number, maximum transfer unit (IEEE defined MTU), rather than
> the maximum frame size (there's contradiction in the Devicetree
> diff --git a/drivers/of/of_net.c b/drivers/of/of_net.c
> index d820f3e..1c5d372 100644
> --- a/drivers/of/of_net.c
> +++ b/drivers/of/of_net.c
> @@ -7,6 +7,7 @@
> */
> #include <linux/etherdevice.h>
> #include <linux/kernel.h>
> +#include <linux/nvmem-consumer.h>
> #include <linux/of_net.h>
> #include <linux/phy.h>
> #include <linux/export.h>
> @@ -80,3 +81,42 @@ const void *of_get_mac_address(struct device_node *np)
> return of_get_mac_addr(np, "address");
> }
> EXPORT_SYMBOL(of_get_mac_address);
> +
> +/**
> + * Obtain the MAC address from an nvmem provider named 'mac-address' through
> + * device tree.
> + * On success, copies the new address into memory pointed to by addr and
> + * returns 0. Returns a negative error code otherwise.
> + * @np: Device tree node containing the nvmem-cells phandle
> + * @addr: Pointer to receive the MAC address using ether_addr_copy()
> + */
> +int of_get_nvmem_mac_address(struct device_node *np, void *addr)
> +{
> + struct nvmem_cell *cell;
> + const void *mac;
> + size_t len;
> + int ret;
> +
> + cell = of_nvmem_cell_get(np, "mac-address");
> + if (IS_ERR(cell))
> + return PTR_ERR(cell);
> +
> + mac = nvmem_cell_read(cell, &len);
> +
> + nvmem_cell_put(cell);
> +
> + if (IS_ERR(mac))
> + return PTR_ERR(mac);
> +
> + if (len < 6 || !is_valid_ether_addr(mac)) {
> + ret = -EINVAL;
Just one nit here, can you use ETH_ALEN instead of 6? With that fixed:
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
--
Florian
^ permalink raw reply
* Re: [PATCH v6 bpf-next 08/11] bpf: introduce BPF_RAW_TRACEPOINT
From: Alexei Starovoitov @ 2018-03-27 22:48 UTC (permalink / raw)
To: Steven Rostedt
Cc: davem, daniel, torvalds, peterz, netdev, kernel-team, linux-api,
Mathieu Desnoyers, Kees Cook
In-Reply-To: <20180327170438.77c0f8fd@gandalf.local.home>
On 3/27/18 2:04 PM, Steven Rostedt wrote:
>
> +#ifdef CONFIG_BPF_EVENTS
> +#define BPF_RAW_TP() . = ALIGN(8); \
> + VMLINUX_SYMBOL(__start__bpf_raw_tp) = .; \
> + KEEP(*(__bpf_raw_tp_map)) \
> + VMLINUX_SYMBOL(__stop__bpf_raw_tp) = .;
that looks to be correct, but something wrong with it.
Can you try your mini test with kasan on ?
I'm seeing this crash:
test_stacktrace_[ 18.760662] start ffffffff84642438 stop ffffffff84644f60
map_raw_tp:PASS:[ 18.761467] i 1 btp->tp cccccccccccccccc
prog_load raw tp[ 18.762064] kasan: CONFIG_KASAN_INLINE enabled
0 nsec
[ 18.762704] kasan: GPF could be caused by NULL-ptr deref or user
memory access
[ 18.765125] general protection fault: 0000 [#1] SMP KASAN PTI
[ 18.765830] Modules linked in:
[ 18.778358] Call Trace:
[ 18.778674] bpf_raw_tracepoint_open.isra.27+0x92/0x380
for some reason the start_bpf_raw_tp is off by 8.
Not sure how it works for you.
(gdb) p &__bpf_trace_tp_map_sys_exit
$10 = (struct bpf_raw_event_map *) 0xffffffff84642440
<__bpf_trace_tp_map_sys_exit>
(gdb) p &__start__bpf_raw_tp
$7 = (<data variable, no debug info> *) 0xffffffff84642438
(gdb) p (void*)(&__start__bpf_raw_tp)+8
$11 = (void *) 0xffffffff84642440 <__bpf_trace_tp_map_sys_exit>
^ permalink raw reply
* Re: [PATCH net-next 0/6] rxrpc: Fixes
From: David Howells @ 2018-03-27 22:46 UTC (permalink / raw)
Cc: dhowells, netdev, linux-afs, linux-kernel
In-Reply-To: <152219064515.24098.9428175357244257284.stgit@warthog.procyon.org.uk>
Sorry, that should be net, not net-next, in the subject line.
David
^ permalink raw reply
* Re: [PATCH 1/6] rhashtable: improve documentation for rhashtable_walk_peek()
From: Andreas Grünbacher @ 2018-03-27 22:46 UTC (permalink / raw)
To: NeilBrown
Cc: Thomas Graf, Herbert Xu, netdev, Linux Kernel Mailing List,
Bob Peterson
In-Reply-To: <152210718418.11435.11573013181393548255.stgit@noble>
Neil,
2018-03-27 1:33 GMT+02:00 NeilBrown <neilb@suse.com>:
> The documentation for rhashtable_walk_peek() wrong. It claims to
> return the *next* entry, whereas it in fact returns the *previous*
> entry.
> However if no entries have yet been returned - or if the iterator
> was reset due to a resize event, then rhashtable_walk_peek()
> *does* return the next entry, but also advances the iterator.
>
> I suspect that this interface should be discarded and the one user
> should be changed to not require it. Possibly this patch should be
> seen as a first step in that conversation.
>
> This patch mostly corrects the documentation, but does make a
> small code change so that the documentation can be correct without
> listing too many special cases. I don't think the one user will
> be affected by the code change.
how about I come up with a replacement so that we can remove
rhashtable_walk_peek straight away without making it differently
broken in the meantime?
Thanks,
Andreas
^ permalink raw reply
* [PATCH net 6/6] rxrpc: remove unused static variables
From: David Howells @ 2018-03-27 22:44 UTC (permalink / raw)
To: netdev; +Cc: dhowells, linux-afs, linux-kernel
In-Reply-To: <152219064515.24098.9428175357244257284.stgit@warthog.procyon.org.uk>
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
The rxrpc_security_methods and rxrpc_security_sem user has been removed
in 648af7fca159 ("rxrpc: Absorb the rxkad security module"). This was
noticed by kbuild test robot for the -RT tree but is also true for !RT.
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: David Howells <dhowells@redhat.com>
---
net/rxrpc/security.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c
index e9f428351293..c4479afe8ae7 100644
--- a/net/rxrpc/security.c
+++ b/net/rxrpc/security.c
@@ -19,9 +19,6 @@
#include <keys/rxrpc-type.h>
#include "ar-internal.h"
-static LIST_HEAD(rxrpc_security_methods);
-static DECLARE_RWSEM(rxrpc_security_sem);
-
static const struct rxrpc_security *rxrpc_security_types[] = {
[RXRPC_SECURITY_NONE] = &rxrpc_no_security,
#ifdef CONFIG_RXKAD
^ permalink raw reply related
* [PATCH net 5/6] rxrpc: Fix resend event time calculation
From: David Howells @ 2018-03-27 22:44 UTC (permalink / raw)
To: netdev; +Cc: dhowells, linux-afs, linux-kernel
In-Reply-To: <152219064515.24098.9428175357244257284.stgit@warthog.procyon.org.uk>
From: Marc Dionne <marc.dionne@auristor.com>
Commit a158bdd3 ("rxrpc: Fix call timeouts") reworked the time calculation
for the next resend event. For this calculation, "oldest" will be before
"now", so ktime_sub(oldest, now) will yield a negative value. When passed
to nsecs_to_jiffies which expects an unsigned value, the end result will be
a very large value, and a resend event scheduled far into the future. This
could cause calls to stall if some packets were lost.
Fix by ordering the arguments to ktime_sub correctly.
Fixes: a158bdd3247b ("rxrpc: Fix call timeouts")
Signed-off-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
---
net/rxrpc/call_event.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index 27f77b7d0ead..87ec697ca117 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -225,7 +225,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
ktime_to_ns(ktime_sub(skb->tstamp, max_age)));
}
- resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(oldest, now)));
+ resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest)));
resend_at += jiffies + rxrpc_resend_timeout;
WRITE_ONCE(call->resend_at, resend_at);
^ permalink raw reply related
* [PATCH net 4/6] rxrpc: Don't treat call aborts as conn aborts
From: David Howells @ 2018-03-27 22:44 UTC (permalink / raw)
To: netdev; +Cc: dhowells, linux-afs, linux-kernel
In-Reply-To: <152219064515.24098.9428175357244257284.stgit@warthog.procyon.org.uk>
If a call-level abort is received for the previous call to complete on a
connection channel, then that abort is queued for the connection processor
to handle. Unfortunately, the connection processor then assumes without
checking that the abort is connection-level (ie. callNumber is 0) and
distributes it over all active calls on that connection, thereby
incorrectly aborting them.
Fix this by discarding aborts aimed at a completed call.
Further, discard all packets aimed at a call that's complete if there's
currently an active call on a channel, since the DATA packets associated
with the new call automatically terminate the old call.
Fixes: 18bfeba50dfd ("rxrpc: Perform terminal call ACK/ABORT retransmission from conn processor")
Reported-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
---
net/rxrpc/input.c | 15 +++++++++------
1 file changed, 9 insertions(+), 6 deletions(-)
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 31bf954480b6..846ec0938953 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -1242,16 +1242,19 @@ void rxrpc_data_ready(struct sock *udp_sk)
goto discard_unlock;
if (sp->hdr.callNumber == chan->last_call) {
- /* For the previous service call, if completed successfully, we
- * discard all further packets.
+ if (chan->call ||
+ sp->hdr.type == RXRPC_PACKET_TYPE_ABORT)
+ goto discard_unlock;
+
+ /* For the previous service call, if completed
+ * successfully, we discard all further packets.
*/
if (rxrpc_conn_is_service(conn) &&
- (chan->last_type == RXRPC_PACKET_TYPE_ACK ||
- sp->hdr.type == RXRPC_PACKET_TYPE_ABORT))
+ chan->last_type == RXRPC_PACKET_TYPE_ACK)
goto discard_unlock;
- /* But otherwise we need to retransmit the final packet from
- * data cached in the connection record.
+ /* But otherwise we need to retransmit the final packet
+ * from data cached in the connection record.
*/
rxrpc_post_packet_to_conn(conn, skb);
goto out_unlock;
^ permalink raw reply related
* [PATCH net 3/6] rxrpc: Fix Tx ring annotation after initial Tx failure
From: David Howells @ 2018-03-27 22:44 UTC (permalink / raw)
To: netdev; +Cc: dhowells, linux-afs, linux-kernel
In-Reply-To: <152219064515.24098.9428175357244257284.stgit@warthog.procyon.org.uk>
rxrpc calls have a ring of packets that are awaiting ACK or retransmission
and a parallel ring of annotations that tracks the state of those packets.
If the initial transmission of a packet on the underlying UDP socket fails
then the packet annotation is marked for resend - but the setting of this
mark accidentally erases the last-packet mark also stored in the same
annotation slot. If this happens, a call won't switch out of the Tx phase
when all the packets have been transmitted.
Fix this by retaining the last-packet mark and only altering the packet
state.
Fixes: 248f219cb8bc ("rxrpc: Rewrite the data and ack handling code")
Signed-off-by: David Howells <dhowells@redhat.com>
---
net/rxrpc/sendmsg.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 09f2a3e05221..7a94ce92ffdc 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -130,7 +130,9 @@ static inline void rxrpc_instant_resend(struct rxrpc_call *call, int ix)
spin_lock_bh(&call->lock);
if (call->state < RXRPC_CALL_COMPLETE) {
- call->rxtx_annotations[ix] = RXRPC_TX_ANNO_RETRANS;
+ call->rxtx_annotations[ix] =
+ (call->rxtx_annotations[ix] & RXRPC_TX_ANNO_LAST) |
+ RXRPC_TX_ANNO_RETRANS;
if (!test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events))
rxrpc_queue_call(call);
}
^ permalink raw reply related
* [PATCH net 2/6] rxrpc: Fix a bit of time confusion
From: David Howells @ 2018-03-27 22:44 UTC (permalink / raw)
To: netdev; +Cc: dhowells, linux-afs, linux-kernel
In-Reply-To: <152219064515.24098.9428175357244257284.stgit@warthog.procyon.org.uk>
The rxrpc_reduce_call_timer() function should be passed the 'current time'
in jiffies, not the current ktime time. It's confusing in rxrpc_resend
because that has to deal with both. Pass the correct current time in.
Note that this only affects the trace produced and not the functioning of
the code.
Fixes: a158bdd3247b ("rxrpc: Fix call timeouts")
Signed-off-by: David Howells <dhowells@redhat.com>
---
net/rxrpc/call_event.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index ad2ab1103189..27f77b7d0ead 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -237,7 +237,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
* retransmitting data.
*/
if (!retrans) {
- rxrpc_reduce_call_timer(call, resend_at, now,
+ rxrpc_reduce_call_timer(call, resend_at, now_j,
rxrpc_timer_set_for_resend);
spin_unlock_bh(&call->lock);
ack_ts = ktime_sub(now, call->acks_latest_ts);
^ permalink raw reply related
* [PATCH net 1/6] rxrpc: Fix firewall route keepalive
From: David Howells @ 2018-03-27 22:44 UTC (permalink / raw)
To: netdev; +Cc: dhowells, linux-afs, linux-kernel
In-Reply-To: <152219064515.24098.9428175357244257284.stgit@warthog.procyon.org.uk>
Fix the firewall route keepalive part of AF_RXRPC which is currently
function incorrectly by replying to VERSION REPLY packets from the server
with VERSION REQUEST packets.
Instead, send VERSION REPLY packets to the peers of service connections to
act as keep-alives 20s after the latest packet was transmitted to that
peer.
Also, just discard VERSION REPLY packets rather than replying to them.
Signed-off-by: David Howells <dhowells@redhat.com>
---
net/rxrpc/af_rxrpc.c | 4 ++
net/rxrpc/ar-internal.h | 14 ++++++-
net/rxrpc/conn_event.c | 3 +
net/rxrpc/input.c | 2 +
net/rxrpc/net_ns.c | 21 ++++++++++
net/rxrpc/output.c | 59 ++++++++++++++++++++++++++++-
net/rxrpc/peer_event.c | 96 +++++++++++++++++++++++++++++++++++++++++++++++
net/rxrpc/peer_object.c | 7 +++
net/rxrpc/rxkad.c | 2 +
9 files changed, 204 insertions(+), 4 deletions(-)
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 0c9c18aa7c77..eca50b495021 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -759,6 +759,7 @@ static __poll_t rxrpc_poll(struct file *file, struct socket *sock,
static int rxrpc_create(struct net *net, struct socket *sock, int protocol,
int kern)
{
+ struct rxrpc_net *rxnet;
struct rxrpc_sock *rx;
struct sock *sk;
@@ -798,6 +799,9 @@ static int rxrpc_create(struct net *net, struct socket *sock, int protocol,
rwlock_init(&rx->call_lock);
memset(&rx->srx, 0, sizeof(rx->srx));
+ rxnet = rxrpc_net(sock_net(&rx->sk));
+ timer_reduce(&rxnet->peer_keepalive_timer, jiffies + 1);
+
_leave(" = 0 [%p]", rx);
return 0;
}
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 416688381eb7..352ef8d546f9 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -97,8 +97,16 @@ struct rxrpc_net {
struct list_head local_endpoints;
struct mutex local_mutex; /* Lock for ->local_endpoints */
- spinlock_t peer_hash_lock; /* Lock for ->peer_hash */
DECLARE_HASHTABLE (peer_hash, 10);
+ spinlock_t peer_hash_lock; /* Lock for ->peer_hash */
+
+#define RXRPC_KEEPALIVE_TIME 20 /* NAT keepalive time in seconds */
+ u8 peer_keepalive_cursor;
+ ktime_t peer_keepalive_base;
+ struct hlist_head peer_keepalive[RXRPC_KEEPALIVE_TIME + 1];
+ struct hlist_head peer_keepalive_new;
+ struct timer_list peer_keepalive_timer;
+ struct work_struct peer_keepalive_work;
};
/*
@@ -285,6 +293,8 @@ struct rxrpc_peer {
struct hlist_head error_targets; /* targets for net error distribution */
struct work_struct error_distributor;
struct rb_root service_conns; /* Service connections */
+ struct hlist_node keepalive_link; /* Link in net->peer_keepalive[] */
+ time64_t last_tx_at; /* Last time packet sent here */
seqlock_t service_conn_lock;
spinlock_t lock; /* access lock */
unsigned int if_mtu; /* interface MTU for this peer */
@@ -1025,6 +1035,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *, bool, rxrpc_serial_t *);
int rxrpc_send_abort_packet(struct rxrpc_call *);
int rxrpc_send_data_packet(struct rxrpc_call *, struct sk_buff *, bool);
void rxrpc_reject_packets(struct rxrpc_local *);
+void rxrpc_send_keepalive(struct rxrpc_peer *);
/*
* peer_event.c
@@ -1033,6 +1044,7 @@ void rxrpc_error_report(struct sock *);
void rxrpc_peer_error_distributor(struct work_struct *);
void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace,
rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t);
+void rxrpc_peer_keepalive_worker(struct work_struct *);
/*
* peer_object.c
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index b1dfae107431..5f06dc8266bf 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -136,6 +136,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
}
kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len);
+ conn->params.peer->last_tx_at = ktime_get_real();
_leave("");
return;
}
@@ -238,6 +239,8 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
return -EAGAIN;
}
+ conn->params.peer->last_tx_at = ktime_get_real();
+
_leave(" = 0");
return 0;
}
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 6fc61400337f..31bf954480b6 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -1183,6 +1183,8 @@ void rxrpc_data_ready(struct sock *udp_sk)
switch (sp->hdr.type) {
case RXRPC_PACKET_TYPE_VERSION:
+ if (!(sp->hdr.flags & RXRPC_CLIENT_INITIATED))
+ goto discard;
rxrpc_post_packet_to_local(local, skb);
goto out;
diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c
index f18c9248e0d4..66baf2b80b6c 100644
--- a/net/rxrpc/net_ns.c
+++ b/net/rxrpc/net_ns.c
@@ -32,13 +32,22 @@ static void rxrpc_service_conn_reap_timeout(struct timer_list *timer)
rxrpc_queue_work(&rxnet->service_conn_reaper);
}
+static void rxrpc_peer_keepalive_timeout(struct timer_list *timer)
+{
+ struct rxrpc_net *rxnet =
+ container_of(timer, struct rxrpc_net, peer_keepalive_timer);
+
+ if (rxnet->live)
+ rxrpc_queue_work(&rxnet->peer_keepalive_work);
+}
+
/*
* Initialise a per-network namespace record.
*/
static __net_init int rxrpc_init_net(struct net *net)
{
struct rxrpc_net *rxnet = rxrpc_net(net);
- int ret;
+ int ret, i;
rxnet->live = true;
get_random_bytes(&rxnet->epoch, sizeof(rxnet->epoch));
@@ -70,8 +79,16 @@ static __net_init int rxrpc_init_net(struct net *net)
INIT_LIST_HEAD(&rxnet->local_endpoints);
mutex_init(&rxnet->local_mutex);
+
hash_init(rxnet->peer_hash);
spin_lock_init(&rxnet->peer_hash_lock);
+ for (i = 0; i < ARRAY_SIZE(rxnet->peer_keepalive); i++)
+ INIT_HLIST_HEAD(&rxnet->peer_keepalive[i]);
+ INIT_HLIST_HEAD(&rxnet->peer_keepalive_new);
+ timer_setup(&rxnet->peer_keepalive_timer,
+ rxrpc_peer_keepalive_timeout, 0);
+ INIT_WORK(&rxnet->peer_keepalive_work, rxrpc_peer_keepalive_worker);
+ rxnet->peer_keepalive_base = ktime_add(ktime_get_real(), NSEC_PER_SEC);
ret = -ENOMEM;
rxnet->proc_net = proc_net_mkdir(net, "rxrpc", net->proc_net);
@@ -95,6 +112,8 @@ static __net_exit void rxrpc_exit_net(struct net *net)
struct rxrpc_net *rxnet = rxrpc_net(net);
rxnet->live = false;
+ del_timer_sync(&rxnet->peer_keepalive_timer);
+ cancel_work_sync(&rxnet->peer_keepalive_work);
rxrpc_destroy_all_calls(rxnet);
rxrpc_destroy_all_connections(rxnet);
rxrpc_destroy_all_locals(rxnet);
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index cf73dc006c3b..7f1fc04775b3 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -32,6 +32,8 @@ struct rxrpc_abort_buffer {
__be32 abort_code;
};
+static const char rxrpc_keepalive_string[] = "";
+
/*
* Arrange for a keepalive ping a certain time after we last transmitted. This
* lets the far side know we're still interested in this call and helps keep
@@ -122,6 +124,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
struct kvec iov[2];
rxrpc_serial_t serial;
rxrpc_seq_t hard_ack, top;
+ ktime_t now;
size_t len, n;
int ret;
u8 reason;
@@ -203,8 +206,10 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
}
ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
+ now = ktime_get_real();
if (ping)
- call->ping_time = ktime_get_real();
+ call->ping_time = now;
+ conn->params.peer->last_tx_at = ktime_get_real();
if (call->state < RXRPC_CALL_COMPLETE) {
if (ret < 0) {
@@ -288,6 +293,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
ret = kernel_sendmsg(conn->params.local->socket,
&msg, iov, 1, sizeof(pkt));
+ conn->params.peer->last_tx_at = ktime_get_real();
rxrpc_put_connection(conn);
return ret;
@@ -378,6 +384,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
* message and update the peer record
*/
ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
+ conn->params.peer->last_tx_at = ktime_get_real();
up_read(&conn->params.local->defrag_sem);
if (ret == -EMSGSIZE)
@@ -429,6 +436,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
if (ret == 0) {
ret = kernel_sendmsg(conn->params.local->socket, &msg,
iov, 2, len);
+ conn->params.peer->last_tx_at = ktime_get_real();
opt = IP_PMTUDISC_DO;
kernel_setsockopt(conn->params.local->socket, SOL_IP,
@@ -446,6 +454,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
if (ret == 0) {
ret = kernel_sendmsg(conn->params.local->socket, &msg,
iov, 2, len);
+ conn->params.peer->last_tx_at = ktime_get_real();
opt = IPV6_PMTUDISC_DO;
kernel_setsockopt(conn->params.local->socket,
@@ -515,3 +524,51 @@ void rxrpc_reject_packets(struct rxrpc_local *local)
_leave("");
}
+
+/*
+ * Send a VERSION reply to a peer as a keepalive.
+ */
+void rxrpc_send_keepalive(struct rxrpc_peer *peer)
+{
+ struct rxrpc_wire_header whdr;
+ struct msghdr msg;
+ struct kvec iov[2];
+ size_t len;
+ int ret;
+
+ _enter("");
+
+ msg.msg_name = &peer->srx.transport;
+ msg.msg_namelen = peer->srx.transport_len;
+ msg.msg_control = NULL;
+ msg.msg_controllen = 0;
+ msg.msg_flags = 0;
+
+ whdr.epoch = htonl(peer->local->rxnet->epoch);
+ whdr.cid = 0;
+ whdr.callNumber = 0;
+ whdr.seq = 0;
+ whdr.serial = 0;
+ whdr.type = RXRPC_PACKET_TYPE_VERSION; /* Not client-initiated */
+ whdr.flags = RXRPC_LAST_PACKET;
+ whdr.userStatus = 0;
+ whdr.securityIndex = 0;
+ whdr._rsvd = 0;
+ whdr.serviceId = 0;
+
+ iov[0].iov_base = &whdr;
+ iov[0].iov_len = sizeof(whdr);
+ iov[1].iov_base = (char *)rxrpc_keepalive_string;
+ iov[1].iov_len = sizeof(rxrpc_keepalive_string);
+
+ len = iov[0].iov_len + iov[1].iov_len;
+
+ _proto("Tx VERSION (keepalive)");
+
+ ret = kernel_sendmsg(peer->local->socket, &msg, iov, 2, len);
+ if (ret < 0)
+ _debug("sendmsg failed: %d", ret);
+
+ peer->last_tx_at = ktime_get_real();
+ _leave("");
+}
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index 7f749505e699..d01eb9a06448 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -348,3 +348,99 @@ void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial, rtt,
usage, avg);
}
+
+/*
+ * Perform keep-alive pings with VERSION packets to keep any NAT alive.
+ */
+void rxrpc_peer_keepalive_worker(struct work_struct *work)
+{
+ struct rxrpc_net *rxnet =
+ container_of(work, struct rxrpc_net, peer_keepalive_work);
+ struct rxrpc_peer *peer;
+ unsigned long delay;
+ ktime_t base, now = ktime_get_real();
+ s64 diff;
+ u8 cursor, slot;
+
+ base = rxnet->peer_keepalive_base;
+ cursor = rxnet->peer_keepalive_cursor;
+
+ _enter("%u,%lld", cursor, ktime_sub(now, base));
+
+next_bucket:
+ diff = ktime_to_ns(ktime_sub(now, base));
+ if (diff < 0)
+ goto resched;
+
+ _debug("at %u", cursor);
+ spin_lock_bh(&rxnet->peer_hash_lock);
+next_peer:
+ if (!rxnet->live) {
+ spin_unlock_bh(&rxnet->peer_hash_lock);
+ goto out;
+ }
+
+ /* Everything in the bucket at the cursor is processed this second; the
+ * bucket at cursor + 1 goes now + 1s and so on...
+ */
+ if (hlist_empty(&rxnet->peer_keepalive[cursor])) {
+ if (hlist_empty(&rxnet->peer_keepalive_new)) {
+ spin_unlock_bh(&rxnet->peer_hash_lock);
+ goto emptied_bucket;
+ }
+
+ hlist_move_list(&rxnet->peer_keepalive_new,
+ &rxnet->peer_keepalive[cursor]);
+ }
+
+ peer = hlist_entry(rxnet->peer_keepalive[cursor].first,
+ struct rxrpc_peer, keepalive_link);
+ hlist_del_init(&peer->keepalive_link);
+ if (!rxrpc_get_peer_maybe(peer))
+ goto next_peer;
+
+ spin_unlock_bh(&rxnet->peer_hash_lock);
+
+ _debug("peer %u {%pISp}", peer->debug_id, &peer->srx.transport);
+
+recalc:
+ diff = ktime_divns(ktime_sub(peer->last_tx_at, base), NSEC_PER_SEC);
+ if (diff < -30 || diff > 30)
+ goto send; /* LSW of 64-bit time probably wrapped on 32-bit */
+ diff += RXRPC_KEEPALIVE_TIME - 1;
+ if (diff < 0)
+ goto send;
+
+ slot = (diff > RXRPC_KEEPALIVE_TIME - 1) ? RXRPC_KEEPALIVE_TIME - 1 : diff;
+ if (slot == 0)
+ goto send;
+
+ /* A transmission to this peer occurred since last we examined it so
+ * put it into the appropriate future bucket.
+ */
+ slot = (slot + cursor) % ARRAY_SIZE(rxnet->peer_keepalive);
+ spin_lock_bh(&rxnet->peer_hash_lock);
+ hlist_add_head(&peer->keepalive_link, &rxnet->peer_keepalive[slot]);
+ rxrpc_put_peer(peer);
+ goto next_peer;
+
+send:
+ rxrpc_send_keepalive(peer);
+ now = ktime_get_real();
+ goto recalc;
+
+emptied_bucket:
+ cursor++;
+ if (cursor >= ARRAY_SIZE(rxnet->peer_keepalive))
+ cursor = 0;
+ base = ktime_add_ns(base, NSEC_PER_SEC);
+ goto next_bucket;
+
+resched:
+ rxnet->peer_keepalive_base = base;
+ rxnet->peer_keepalive_cursor = cursor;
+ delay = nsecs_to_jiffies(-diff) + 1;
+ timer_reduce(&rxnet->peer_keepalive_timer, jiffies + delay);
+out:
+ _leave("");
+}
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index d02a99f37f5f..94a6dbfcf129 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -322,6 +322,7 @@ struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *local,
if (!peer) {
peer = prealloc;
hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key);
+ hlist_add_head(&peer->keepalive_link, &rxnet->peer_keepalive_new);
}
spin_unlock(&rxnet->peer_hash_lock);
@@ -363,9 +364,12 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local,
peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key);
if (peer && !rxrpc_get_peer_maybe(peer))
peer = NULL;
- if (!peer)
+ if (!peer) {
hash_add_rcu(rxnet->peer_hash,
&candidate->hash_link, hash_key);
+ hlist_add_head(&candidate->keepalive_link,
+ &rxnet->peer_keepalive_new);
+ }
spin_unlock_bh(&rxnet->peer_hash_lock);
@@ -392,6 +396,7 @@ void __rxrpc_put_peer(struct rxrpc_peer *peer)
spin_lock_bh(&rxnet->peer_hash_lock);
hash_del_rcu(&peer->hash_link);
+ hlist_del_init(&peer->keepalive_link);
spin_unlock_bh(&rxnet->peer_hash_lock);
kfree_rcu(peer, rcu);
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index 77cb23c7bd0a..588fea0dd362 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -668,6 +668,7 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn)
return -EAGAIN;
}
+ conn->params.peer->last_tx_at = ktime_get_real();
_leave(" = 0");
return 0;
}
@@ -722,6 +723,7 @@ static int rxkad_send_response(struct rxrpc_connection *conn,
return -EAGAIN;
}
+ conn->params.peer->last_tx_at = ktime_get_real();
_leave(" = 0");
return 0;
}
^ 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