On Wed, Jun 15, 2016 at 2:37 PM, Richard Henderson via iovisor-dev
wrote:
> This same value for EM_BPF is being propagated to glibc,
> elfutils, and binutils.
great!
Can you share the link to glibc and the other patches?
> diff --git a/include/llvm/Support/ELF.h b/include/llvm/Support/ELF.h
> in
On Wed, Jun 15, 2016 at 2:37 PM, Richard Henderson via iovisor-dev
wrote:
> Avoid duplicating lots of field definitions.
>
> Signed-off-by: Richard Henderson
> ---
> lib/Target/BPF/BPFInstrFormats.td | 45 +++-
> lib/Target/BPF/BPFInstrInfo.td| 536
> +++---
On Wed, Jun 15, 2016 at 2:37 PM, Richard Henderson via iovisor-dev
wrote:
> Since all 32-bit operations zero-extend, the move operations are
> immediately usable for loading unsigned constants and zero-extension.
>
> Signed-off-by: Richard Henderson
> ---
> lib/Target/BPF/BPFInstrInfo.td | 39 ++
On Wed, Jun 15, 2016 at 2:37 PM, Richard Henderson via iovisor-dev
wrote:
> We can represent a 64-bit AND with unsigned immediate
> with a 32-bit AND opcode.
>
> Signed-off-by: Richard Henderson
> ---
> lib/Target/BPF/BPFInstrInfo.td | 15 +++
> 1 file changed, 15 insertions(+)
>
> d
On Thu, Jun 16, 2016 at 10:28 AM, Richard Henderson wrote:
> On 06/15/2016 10:38 PM, Alexei Starovoitov wrote:
>> but before we go too far with new asm syntax like 'movw',
>> Do you want to revamp the whole thing?
>> imo the kernel verifier asm output is easier to read
>> due to being C-like and n
On Thu, Jun 16, 2016 at 10:42 AM, Richard Henderson wrote:
> On 06/15/2016 10:41 PM, Alexei Starovoitov wrote:
>> Do you have further optimizations that take advantage of 32-bit
>> subregisters and zero extension?
>> Should it be added in more generic way instead of pattern match?
>
> This is the
On Mon, Jun 20, 2016 at 10:17 AM, Richard Henderson via iovisor-dev
wrote:
> Well, that was quick.
thanks!
> Would someone from the iovisor project like to be the official contact for
> this? Otherwise I'll give them contact details for Red Hat.
can probably put my name or something generic li
On Tue, Jun 21, 2016 at 11:03 AM, William Tu via iovisor-dev
wrote:
> Hi,
>
> I'm trying to run sockex2 and sockex3 but got the error:
> [root@vm-dev bpf]# ./sockex2
> failed to create a map: 1 Operation not permitted
>
> Then I found that I have max locked memory set to 64K, after reconfig
> to u
On Tue, Jun 21, 2016 at 11:48 AM, William Tu via iovisor-dev
wrote:
> Hi,
>
> I'm running test_maps under net-next/samples/bpf/, commit
> 601009780635. The code logic all make sense but I got the assertion
> errors / coredump for some unknown reason under different compiler
> optimization flags (-
On Wed, Jun 22, 2016 at 3:21 AM, Jesper Dangaard Brouer via
iovisor-dev wrote:
>
> On Tue, 21 Jun 2016 18:25:14 -0700
> Tom Herbert via iovisor-dev wrote:
>
>> Here is an agenda for the XDP summit. We expect this to be a lot of
>> interactive conversation so the agenda can be dynamic as needed!
>
On Wed, Jun 22, 2016 at 8:54 AM, Jesper Dangaard Brouer
wrote:
> On Tue, 21 Jun 2016 18:54:53 -0700
> Alexei Starovoitov wrote:
>
>> On Tue, Jun 21, 2016 at 11:48 AM, William Tu via iovisor-dev
>> wrote:
>> > Hi,
>> >
>> > I'm running test_maps under net-next/samples/bpf/, commit
>> > 6010097806
On Wed, Jun 22, 2016 at 9:52 AM, Jesper Dangaard Brouer
wrote:
> On Wed, 22 Jun 2016 08:59:14 -0700
> Alexei Starovoitov wrote:
>
>> On Wed, Jun 22, 2016 at 8:54 AM, Jesper Dangaard Brouer
>> wrote:
>> > On Tue, 21 Jun 2016 18:54:53 -0700
>> > Alexei Starovoitov wrote:
>> >
>> >> On Tue, Jun 21
On Wed, Jun 15, 2016 at 2:37 PM, Richard Henderson via iovisor-dev
wrote:
> Hi,
>
> Using EM_NONE for the bpf backend e_machine value is less than optimal.
> With a unique value we can interact with other tools, e.g. objdump for
> disassembly.
>
> As a bonus, I noticed a few missing patterns that
On Thu, Jun 23, 2016 at 3:52 PM, Richard Henderson via iovisor-dev
wrote:
> Avoid duplicating lots of field definitions.
>
> Signed-off-by: Richard Henderson
> ---
> lib/Target/BPF/BPFInstrFormats.td | 39 ++-
> lib/Target/BPF/BPFInstrInfo.td| 536
> +++---
>
On Mon, Jul 04, 2016 at 04:21:23PM +0200, Thomas Graf wrote:
> 2016-07-04 13:02 GMT+02:00 Daniel Borkmann :
> > Yeah, checks cannot be carried over in two occasions: i) calling helpers
> > that change skb->data (and therefore prior checks become invalid) and
> > ii) tail calls. For tail calls the v
On Wed, Jul 06, 2016 at 05:21:53PM +0200, Jesper Dangaard Brouer wrote:
>
> How easy is it to extend the XDP/eBPF program with a new input
> parameter?
trivial. do git blame include/uapi/linux/bpf.h
and see commits for struct __sk_buff
We've been adding input md fields non stop without breaking e
On Thu, Jul 07, 2016 at 03:18:11PM +, Fastabend, John R wrote:
> Hi Jesper,
>
> I have done some previous work on proprietary systems where we used hardware
> to do the classification/parsing then passed a cookie to the software which
> used the cookie to lookup a program to run on the packe
On Thu, Jul 07, 2016 at 09:05:29PM -0700, John Fastabend wrote:
> On 16-07-07 07:22 PM, Alexei Starovoitov wrote:
> > On Thu, Jul 07, 2016 at 03:18:11PM +, Fastabend, John R wrote:
> >> Hi Jesper,
> >>
> >> I have done some previous work on proprietary systems where we
> >> used hardware to do
On Sat, Jul 09, 2016 at 01:27:26PM +0200, Jesper Dangaard Brouer wrote:
> On Fri, 8 Jul 2016 18:51:07 +0100
> Jakub Kicinski wrote:
>
> > On Fri, 8 Jul 2016 09:45:25 -0700, John Fastabend wrote:
> > > The only distinction between VFs and queue groupings on my side is VFs
> > > provide RSS where a
On Wed, Jul 13, 2016 at 4:17 PM, Kyle Laracey via iovisor-dev
wrote:
>
> An additional issue brought up on the call (I apologize for forgetting by
> whom) was that any comparisons on long strings would bloat the program,
> perhaps beyond the maximum allowed program size. Would the solution to this
On Fri, Jul 15, 2016 at 12:56 AM, Sasha Goldshtein wrote:
> On Fri, Jul 15, 2016 at 3:59 AM Alexei Starovoitov
> wrote:
>>
>> On Wed, Jul 13, 2016 at 4:17 PM, Kyle Laracey via iovisor-dev
>> wrote:
>> >
>> > An additional issue brought up on the call (I apologize for forgetting
>> > by
>> > whom
just pushed Richard's patch
https://github.com/llvm-mirror/llvm/commit/36b9c09330bfb5e771914cfe307588f30d5510d2
tested with bcc and different bpf loaders.
Thankfully none of them rely on old and arguably
buggy em_none value, so no breakage expected.
if you're using special bpf elf loader, please t
On Mon, Jul 18, 2016 at 01:57:24PM -0700, Kyle Laracey wrote:
> Alexei,
>
>
> > What is your use case that needs strings?
>
>
> We are trying to filter on SQL query strings at USDT probes in our product
> (a database). We would like to be able to compare a string probe parameter
> to another st
On Tue, Jul 19, 2016 at 05:19:20PM -0700, Kyle Laracey wrote:
> Alexei,
>
> with stringmap the user space process will be able to populate the map
> > with its own strings, then the bpf prog can do bpf_get_unsafe_string
> > to put a string pointed to by uprobe parameter into a map.
> > The helper
On Sun, Jul 31, 2016 at 11:05:55PM -0700, William Tu via iovisor-dev wrote:
> Hi,
>
> I'm looking at definition of xdp_md:
> struct xdp_md {
> __u32 data;
> __u32 data_end;
> };
>
> I'm curious why are we using __u32? Isn't data and data_end an 8-byte
> pointer to the packet's buffer? For
On Mon, Aug 8, 2016 at 10:56 AM, William Tu wrote:
> Hi Alexei,
>
> I wonder if anyone is working on this issue currently?
> Or I could start learning from your "direct packet access" patch and
> see if could implement it? Thanks.
This patch does direct packet access from helpers (like lookup and
On Mon, Aug 8, 2016 at 11:29 AM, William Tu wrote:
> Hi Alexei,
>
> Thanks.
>>
>> This patch does direct packet access from helpers (like lookup and csum):
>> https://git.kernel.org/cgit/linux/kernel/git/ast/bpf.git/commit/?id=d2c24a2769693524d
>> it's waiting for net-next to reopen.
>
> I'm confu
On Fri, Aug 12, 2016 at 4:50 PM, Brenden Blanco via iovisor-dev
wrote:
>
>
> On Fri, Aug 12, 2016 at 4:46 PM, Mark Drayton via iovisor-dev
> wrote:
>>
>> Here’s a version that works:
>>
>>
>>
>> https://gist.github.com/markdrayton/d077459b7ed23ce25bb3eff2d5e220ba
>>
>>
>>
>> It looks like SSL_rea
On Fri, Aug 12, 2016 at 10:35:08AM -0700, William Tu via iovisor-dev wrote:
> The patch creates sample code exercising bpf_skb_{set,get}_tunnel_key,
> and bpf_skb_{set,get}_tunnel_opt for GRE, VXLAN, and GENEVE. A native
> tunnel device is created in a namespace to interact with a lwtunnel
> devic
On Thu, Aug 11, 2016 at 12:06 PM, Sargun Dhillon via iovisor-dev
wrote:
> Hello all,
> Sorry for my bumbling on the phone yesterday. I promised to share the
> use cases for the LSM. I'd love to get opinions.
>
> There is a large enterprise that runs between 8-24 containers on each
> server. These
On Tue, Aug 16, 2016 at 5:09 PM, Sargun Dhillon wrote:
> On Fri, Aug 12, 2016 at 6:16 PM, Alexei Starovoitov
> wrote:
>> On Thu, Aug 11, 2016 at 12:06 PM, Sargun Dhillon via iovisor-dev
>> wrote:
>>> Hello all,
>>> Sorry for my bumbling on the phone yesterday. I promised to share the
>>> use cas
On Tue, Aug 16, 2016 at 9:16 PM, Sargun Dhillon wrote:
> On Tue, Aug 16, 2016 at 07:38:45PM -0700, Alexei Starovoitov wrote:
>> On Tue, Aug 16, 2016 at 5:09 PM, Sargun Dhillon wrote:
>> > On Fri, Aug 12, 2016 at 6:16 PM, Alexei Starovoitov
>> > wrote:
>> >> On Thu, Aug 11, 2016 at 12:06 PM, Sarg
On Mon, Aug 22, 2016 at 4:26 PM, William Tu via iovisor-dev
wrote:
> Hi,
>
> I'm not sure if we discussed this before, but I'm thinking that if I
> have two identical NICs (ex: two e1000 cards with ifindex 1 and 2),
> and I load the e1000.ko driver. At userspace, I run
> $ /samples/bpf/xdp 1
> $ /
On Wed, Sep 07, 2016 at 03:42:22PM +0300, Saeed Mahameed wrote:
> From: Tariq Toukan
>
> To improve the memory consumption scheme, we omit the flow that
> demands and splits high-order pages in Striding RQ, and stay
> with a single Striding RQ flow that uses order-0 pages.
>
> Moving to fragment
On Wed, Sep 07, 2016 at 03:42:25PM +0300, Saeed Mahameed wrote:
> For non-striding RQ configuration before this patch we had a ring
> with pre-allocated SKBs and mapped the SKB->data buffers for
> device.
>
> For robustness and better RX data buffers management, we allocate a
> page per packet and
On Thu, Sep 08, 2016 at 10:11:47AM +0200, Jesper Dangaard Brouer wrote:
>
> I'm sorry but I have a problem with this patch!
is it because the variable is called 'xdp_doorbell'?
Frankly I see nothing scary in this patch.
It extends existing code by adding a flag to ring doorbell or not.
The end of
On Fri, Sep 09, 2016 at 07:36:52AM +0200, Jesper Dangaard Brouer wrote:
> > > Lets do bundling/bulking from the start!
> >
> > mlx4 already does bulking and this proposed mlx5 set of patches
> > does bulking as well.
> > See nothing wrong about it. RX side processes the packets and
> > when it'
On Mon, Sep 12, 2016 at 10:56:55AM +0200, Jesper Dangaard Brouer wrote:
> On Thu, 8 Sep 2016 23:30:50 -0700
> Alexei Starovoitov wrote:
>
> > On Fri, Sep 09, 2016 at 07:36:52AM +0200, Jesper Dangaard Brouer wrote:
> > > > > Lets do bundling/bulking from the start!
> > > >
> > > > mlx4 alrea
On Mon, Sep 12, 2016 at 01:30:25PM +0200, Jesper Dangaard Brouer wrote:
> On Thu, 8 Sep 2016 23:30:50 -0700
> Alexei Starovoitov wrote:
>
> > On Fri, Sep 09, 2016 at 07:36:52AM +0200, Jesper Dangaard Brouer wrote:
> [...]
> > > Imagine you have packets intermixed towards the stack and XDP_TX.
>
On Tue, Sep 20, 2016 at 11:08:44AM +0200, Jesper Dangaard Brouer via
iovisor-dev wrote:
> Hi all,
>
> As promised, I've started documenting the XDP eXpress Data Path):
>
> [1]
> https://prototype-kernel.readthedocs.io/en/latest/networking/XDP/index.html
>
> IMHO the documentation have reached
On Tue, Sep 27, 2016 at 11:32:37AM +0200, Jesper Dangaard Brouer wrote:
>
> Let me try in a calm way (not like [1]) to explain how I imagine that
> the XDP processing RX-stage should be implemented. As I've pointed out
> before[2], I'm proposing splitting up the driver into RX-stages. This
> is a
On Wed, Sep 28, 2016 at 12:44:31PM +0200, Jesper Dangaard Brouer wrote:
>
> The idea is quite different. It has nothing to do with Edward's
> proposal[3]. The RX packet-vector is simply an array, either of pointers
> or index numbers (into the RX-ring). The needed changes are completely
> conta
On Fri, Oct 21, 2016 at 11:38 PM, William Tu via iovisor-dev
wrote:
> Hi,
> I'm running into this LLVM ERROR at compile time. Does anyone seem
> this before or can give me some suggestions? thanks!
>
> ---
> LLVM ERROR: Cannot select: 0x3bafa28: ch = brind 0x3bc98f0:1,
> 0x3bc98f0 [ORD=1] [ID=
On Mon, Oct 24, 2016 at 2:22 PM, William Tu via iovisor-dev
wrote:
> Hi,
>
> Is there an easy way to clear all entries in a BPF hash map?
>
> My use case:
> When my BPF userspace program and kernel BPF is running, I want to
> dynamically adding a new BPF hash map. IIUC, there is no way to do
> tha
On Mon, Oct 24, 2016 at 10:42:44PM -0700, William Tu wrote:
> Hi Alexei,
> Thanks for your reply.
>
> On Mon, Oct 24, 2016 at 7:01 PM, Alexei Starovoitov
> wrote:
> > On Mon, Oct 24, 2016 at 2:22 PM, William Tu via iovisor-dev
> > wrote:
> >> Hi,
> >>
> >> Is there an easy way to clear all entri
On Tue, Oct 25, 2016 at 5:19 PM, Krister Johansen via iovisor-dev
wrote:
> Folks,
> I have a bcc script that I've been using to debug the packet path in a
> project that I'm working on. I've been using kprobes and tracepoints to
> grab skb pointers. Most of the time enough of the skb's data is l
On Sat, Nov 19, 2016 at 9:45 AM, Mazhar Naqvi via iovisor-dev
wrote:
> Hi,
>
>
> I am trying to attach my function to a tracepoint. I followed brendangregg's
> script "urandomread.py" and modified it to attach to
> syscalls:sys_enters_socket but the program gives me an error.
>
>
> Here's a code s
sorry. I cannot make it tomorrow.
On Tue, Nov 29, 2016 at 8:58 PM, Brenden Blanco via iovisor-dev <
iovisor-dev@lists.iovisor.org> wrote:
> Hi All,
>
> Please join us for our bi-weekly call. This meeting is open to everybody
> and completely optional.
>
> *IOVisor TSC/Dev Meeting*
> Every 2 weeks
On Tue, Nov 29, 2016 at 10:21 AM, Alban Crequy via iovisor-dev
wrote:
> Hi,
>
> I think that's a good idea to make it easier to try bcc.
>
> There is this Docker image but I don't know who is managing it:
> https://github.com/zlim/bcc-docker
> https://hub.docker.com/r/zlim/bcc/
Hi Zi,
looks like
On Thu, Dec 8, 2016 at 8:20 AM, Ming Lei via iovisor-dev
wrote:
> Hi,
>
> Bcc can be installed on ubuntu 16.04/arm64 successfully, but when
> I try to trace, the folllowing failure[1] is triggered.
>
> So is bcc not ready for arm64? Or something is wrong?
>
> BTW, clang/llvm is 3.8, and I am happy
On Sun, Dec 11, 2016 at 5:27 PM, Ming Lei via iovisor-dev
wrote:
> On Sun, Dec 11, 2016 at 9:21 AM, Chaiken, Alison via iovisor-dev
> wrote:
>> Ming Lei inquires:
>>
>> Bcc can be installed on ubuntu 16.04/arm64 successfully, but when
>> I try to trace, the folllowing failure[1] is triggered.
>>
On Mon, Dec 12, 2016 at 9:44 PM, Ming Lei wrote:
>
>> so you can send me a pre-processed .c file or even better .ll file ?
>> I don't have arm64 to reproduce it...
>
> Please see the whole log of building the prog.
that raw asm outside of any function body comes from
arch/arm64/include/asm/sysreg
On Mon, Dec 12, 2016 at 10:33 PM, Ming Lei wrote:
> On Tue, Dec 13, 2016 at 2:11 PM, Alexei Starovoitov
> wrote:
>> On Mon, Dec 12, 2016 at 9:44 PM, Ming Lei wrote:
>>>
so you can send me a pre-processed .c file or even better .ll file ?
I don't have arm64 to reproduce it...
>>>
>>> Pl
On Tue, Dec 13, 2016 at 8:43 AM, Brenden Blanco wrote:
>
>
> On Mon, Dec 12, 2016 at 10:38 PM, Alexei Starovoitov
> wrote:
>>
>> On Mon, Dec 12, 2016 at 10:33 PM, Ming Lei wrote:
>> > On Tue, Dec 13, 2016 at 2:11 PM, Alexei Starovoitov
>> > wrote:
>> >> On Mon, Dec 12, 2016 at 9:44 PM, Ming Lei
when you change the prototype to 'const void *' does it help compiler
to unroll it?
On Tue, Dec 13, 2016 at 12:06 PM, Mauricio Vasquez via iovisor-dev
wrote:
> Hello,
>
> We are having some doubts about the use of the const qualifier for the key
> argument in functions to access eBPF maps, both,
On Mon, Nov 14, 2016 at 7:34 AM, Joe Lawrence wrote:
> On 11/11/2016 09:41 PM, Alexei Starovoitov wrote:
>> On Thu, Nov 10, 2016 at 7:36 AM, Joe Lawrence
>> wrote:
>>> On 11/09/2016 11:11 PM, Alexei Starovoitov wrote:
On Wed, Nov 9, 2016 at 8:59 AM, Joe Lawrence
wrote:
> Hi Alexe
On Tue, Dec 20, 2016 at 1:47 PM, Brendan Gregg via iovisor-dev
wrote:
> I'd like to BPF_PERF_OUTPUT() at a high rate (>1000/s), and have these
> buffered and read in groups by bcc. But the typical loop we're using:
>
> b["events"].open_perf_buffer(print_event)
> while 1:
> b.kprobe_poll()
>
>
"couldn't allocate output register for constraint 'r' "
means that inline asm was used.
Try preprocessing C and look for inline asm usage.
On Fri, Jan 6, 2017 at 1:30 PM, William Tu via iovisor-dev
wrote:
> thanks
> the code is at
> https://gist.github.com/williamtu/7e41392a34672d7b4574aee063ea4a
On Mon, Jan 9, 2017 at 8:00 AM, Quentin Monnet via iovisor-dev
wrote:
> Hello,
>
> Just in case some people might be interested, I ported the user space
> eBPF implementation from Rich Lane (uBPF, in C,
> https://github.com/iovisor/ubpf/) to Rust, and it is available on
> GitHub: https://github.co
On Wed, Jan 11, 2017 at 4:23 PM, Konstantin Bukin
wrote:
> Here is a diff against kernel 4.9.2:
>
> build-test1:linux-4.9.2$git diff
> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
> index c201017..64516be 100644
> --- a/include/linux/bpf.h
> +++ b/include/linux/bpf.h
> @@ -327,6 +327,7
dhcp function is a slow path and has quite a bit of complexity that
is not appropriate for datapath. Normal dhcp is handled by user space dhclient.
So I think it would be better to do the same in your case.
As an orthogonal discussion it would be useful indeed
to have push()/pop() like logic in bpf
On Tue, Jan 24, 2017 at 2:16 AM, Jesper Dangaard Brouer
wrote:
> On Tue, 24 Jan 2017 10:52:39 +0100
> Jesper Dangaard Brouer wrote:
>
>> Hi IOvisor-group,
>>
>> I'm playing with kernels samples/bpf, and want so advice on debugging
>> eBPF programs.
>>
>> First question: I noticed bpf_trace_printk
On Tue, Jan 31, 2017 at 9:54 AM, Jesper Dangaard Brouer via
iovisor-dev wrote:
>
> On Sat, 28 Jan 2017 10:14:58 +1100 Brendan Gregg
> wrote:
>
>> I did some in the bcc ref guide, but it's incomplete, and the bcc versions:
>> https://github.com/iovisor/bcc/blob/master/docs/reference_guide.md
>
>
On Tue, Jan 31, 2017 at 4:19 AM, Sasha Goldshtein via iovisor-dev
wrote:
> Hi all,
>
> I'm trying to attach a BPF program to a tracepoint that has a __string
> field, such as net:net_dev_start_xmit. This tracepoint has the following
> format (from debugfs/events/.../format):
>
> name: net_dev_star
On Wed, Feb 1, 2017 at 1:25 AM, Sasha Goldshtein wrote:
>
> Do you expect the data_loc field structure to change? E.g., do you expect
> the size to be != 4 bytes, and the two words (length, offset) to mean
> something
> else in the future?
I don't expect it to change any time soon, but it can.
__
On Thu, Feb 02, 2017 at 06:00:09PM +0100, Jesper Dangaard Brouer wrote:
>
> [PATCH] doc: how interacting with eBPF maps works
>
> Documented by reading the code.
looks great!
please submit the patch to net-next and cc Jonathan ?
Comments below:
> I hope someone more knowledgeable will review th
On Fri, Feb 3, 2017 at 5:52 AM, Jesper Dangaard Brouer
wrote:
> On Thu, 2 Feb 2017 20:27:15 -0800
> Alexei Starovoitov wrote:
>
>> On Thu, Feb 02, 2017 at 06:00:09PM +0100, Jesper Dangaard Brouer wrote:
> [...]
>> Comments below:
> [...]
>
>> > +Interacting with maps
>> > +=
>
On Tue, Feb 7, 2017 at 4:07 PM, Brenden Blanco via iovisor-dev
wrote:
>
> === IO Visor Dev/TSC Meeting ===
> Every 2 weeks on Wednesday, from Wednesday, January 25, 2017, to no end date
> 11:00 am | Pacific Standard Time (San Francisco, GMT-08:00) | 1 hr
i have a dental appointment at that ti
On Thu, Feb 9, 2017 at 8:43 AM, William Tu via iovisor-dev
wrote:
>
> $(CLANG) \
> -D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \
> -Wno-compare-distinct-pointer-types \
> -Wno-gnu-variable-sized-type-not-at-end \
> -Wno-tautological-compare
On Fri, Feb 10, 2017 at 9:08 AM, William Tu wrote:
> my program is too huge so I start with simple example using xdp1_kern.c
> I tried adding an ethernet header as local variable:
>
> --- a/samples/bpf/xdp1_kern.c
> +++ b/samples/bpf/xdp1_kern.c
> @@ -51,10 +51,19 @@ int xdp_prog1(struct xdp_md *c
On Mon, Mar 6, 2017 at 3:53 AM, Jesper Dangaard Brouer
wrote:
> Hi All,
>
> I've added a section to my eBPF documentation, about how to read the
> eBPF generated ELF binary, and deduct the size of the compiled program
> (mostly for kernel/samples/bpf).
>
> https://prototype-kernel.readthedocs.io/e
On Mon, Mar 6, 2017 at 10:29 AM, Jesper Dangaard Brouer
wrote:
> On Mon, 6 Mar 2017 09:11:46 -0800
> Alexei Starovoitov via iovisor-dev wrote:
>
>> On Mon, Mar 6, 2017 at 3:53 AM, Jesper Dangaard Brouer
>> wrote:
>> > Hi All,
>> >
>> > I've a
On Tue, Mar 7, 2017 at 3:07 AM, Jesper Dangaard Brouer
wrote:
> On Mon, 6 Mar 2017 16:14:06 -0800
> Alexei Starovoitov via iovisor-dev wrote:
>
>> On Mon, Mar 6, 2017 at 10:29 AM, Jesper Dangaard Brouer
>> wrote:
>> > On Mon, 6 Mar 2017 09:11:46 -0800
>>
On Tue, Mar 07, 2017 at 10:13:13PM +0100, Jesper Dangaard Brouer wrote:
> On Tue, 7 Mar 2017 21:54:42 +0100
> Jesper Dangaard Brouer wrote:
>
> > > I also suggest to replace it with 'llvm-objdump -h file.o'
> > > since it prints the same info as 'readelf -SW'
> > > but less verbose.
> >
> > Go
On Mon, Mar 20, 2017 at 10:08:57AM +0100, Fulvio Risso via iovisor-dev wrote:
> Dear all,
>
> perhaps a naive question.
>
> Instead of attaching an Iomodule to a NIC and perform statistics/whatever,
> can we attach the Iomodule to a pcap file?
>
> The classical BPF (with libpcap) has this featur
On Tue, Mar 28, 2017 at 7:08 PM, Marek Vavruša via iovisor-dev
wrote:
> Hi,
>
> so I was tinkering with programs attached to reuseport groups again, and
> simple decisions work as expected.
> The problem comes when I want to make decisions based on source or
> destination IP address. Since the soc
On Mon, Apr 10, 2017 at 9:18 AM, Fulvio Risso via iovisor-dev
wrote:
> Dear all,
>
> since IOVisor is an in-kernel paradigm, is there anyone aware of any study
> regarding how RT scheduling within the linux kernel is impacted by the
> presence (and operation) of various IO-Modules?
I don't think
On Tue, Apr 11, 2017 at 1:06 PM, Fulvio Risso wrote:
>
> Is there any documentation that presents the interrupt context in which the
> different iomodules operate, according to the attaching point?
BPF_PROG_TYPE_SCHED_CLS and BPF_PROG_TYPE_XDP programs run in softirq.
BPF_PROG_TYPE_KPROBE and BPF
On Tue, Apr 11, 2017 at 8:48 PM, Nadav Amit wrote:
> Using the LLVM backend of BPF, I sometimes get the wrong code to be
> generated.
>
> For example, for the following program:
>
> int bpf_prog1(void *ign)
> {
> volatile unsigned long t = 0x8983984739ull;
> return *(unsigned long *)((
On Thu, Apr 13, 2017 at 2:53 PM, Nadav Amit wrote:
>
> I sent a patch to https://reviews.llvm.org/D32055 .
>
> I do not know the LLVM test-suite, so please prepare a test based on the
> example and the bug-fix.
pushed with the test.
Do you mind sharing how did you find this issue?
What kind of p
On Fri, Apr 14, 2017 at 12:48:11PM -0700, William Tu wrote:
> Thanks for all the feedbacks from the iovisor summit. Since then,
> we've tried a couple of workarounds for this issue, the following
> shares the observations and code.
>
> === Original code, xdp9.c ===
> xdp9.c is to parse IPv4, TCP,
On Tue, Apr 18, 2017 at 5:48 PM, William Tu via iovisor-dev
wrote:
> Hi,
>
> I have a struct like below:
> struct bpf_flow_keys {
>long src;
> };
>
> I'm initializing an array of it using structures like below:
>struct bpf_flow_keys flow_mask_array[] = {
> {.src = },
>
On Tue, May 16, 2017 at 5:40 PM, Brenden Blanco via iovisor-dev
wrote:
> 11:00 am | Pacific Daylight Time (San Francisco, GMT-07:00) | 1 hr
> https://bluejeans.com/568677804/
few topics for the agenda:
- Plumbers Conference will be happening Sep 13-15 in LA
if you're planning to attend pleas
On Wed, May 17, 2017 at 2:14 PM, Brenden Blanco via iovisor-dev
wrote:
> Hi All,
>
> Thanks for attending the call today, here are the notes.
thanks a lot for taking and publishing these notes!
> CFP for Linux Plumbers
> Sept 13-15, Los Angeles
> Tracing microconference accepted
> (Alexei, Bren
On 6/2/17 7:42 AM, Edward Cree wrote:
Also, I feel I haven't fully understood the semantics of {min,max}_value and
signed vs. unsigned comparisons. It seems that currently reg_set_min_max
[_inv] assumes that any given register-value will either only be used as
signed, or only be used as unsig
On Wed, Jun 07, 2017 at 03:58:31PM +0100, Edward Cree wrote:
> Tracks value alignment by means of tracking known & unknown bits.
> Tightens some min/max value checks and fixes a couple of bugs therein.
>
> Signed-off-by: Edward Cree
> ---
> include/linux/bpf.h | 34 +-
> include/linux
On Wed, Jun 07, 2017 at 03:58:50PM +0100, Edward Cree wrote:
> If pointer leaks are allowed, and adjust_ptr_min_max_vals returns -EACCES,
> treat the pointer as an unknown scalar and try again, because we might be
> able to conclude something about the result (e.g. pointer & 0x40 is either
> 0 o
On Wed, Jun 07, 2017 at 03:59:25PM +0100, Edward Cree wrote:
> Allows us to, sometimes, combine information from a signed check of one
> bound and an unsigned check of the other.
> We now track the full range of possible values, rather than restricting
> ourselves to [0, 1<<30) and considering an
On Wed, Jun 07, 2017 at 04:00:02PM +0100, Edward Cree wrote:
> Some of the verifier's error messages have changed, and some constructs
> that previously couldn't be verified are now accepted.
>
> Signed-off-by: Edward Cree
> ---
> tools/testing/selftests/bpf/test_verifier.c | 226
> +++
On Thu, Jun 08, 2017 at 03:53:36PM +0100, Edward Cree wrote:
> >>
> >> - } else if (reg->type == FRAME_PTR || reg->type == PTR_TO_STACK) {
> >> + } else if (reg->type == PTR_TO_STACK) {
> >> + /* stack accesses must be at a fixed offset, so that we can
> >> + * determine what
On Thu, Jun 08, 2017 at 04:23:24PM +0100, Edward Cree wrote:
> On 08/06/17 03:40, Alexei Starovoitov wrote:
> > On Wed, Jun 07, 2017 at 03:59:25PM +0100, Edward Cree wrote:
> >> Allows us to, sometimes, combine information from a signed check of one
> >> bound and an unsigned check of the other.
>
On Thu, Jun 08, 2017 at 04:25:39PM +0100, Edward Cree wrote:
> On 08/06/17 03:35, Alexei Starovoitov wrote:
> > such large back and forth move doesn't help reviewing.
> > may be just merge it into previous patch?
> > Or keep that function in the right place in patch 2 already?
> I think 'diff' got
On Thu, Jun 08, 2017 at 06:12:39PM +0100, Edward Cree wrote:
> On 08/06/17 17:50, Alexei Starovoitov wrote:
> > On Thu, Jun 08, 2017 at 04:25:39PM +0100, Edward Cree wrote:
> >> On 08/06/17 03:35, Alexei Starovoitov wrote:
> >>> such large back and forth move doesn't help reviewing.
> >>> may be ju
On Thu, Jun 08, 2017 at 08:07:53PM +0100, Edward Cree wrote:
> On 08/06/17 19:41, Alexei Starovoitov wrote:
> > On Thu, Jun 08, 2017 at 06:12:39PM +0100, Edward Cree wrote:
> >> On 08/06/17 17:50, Alexei Starovoitov wrote:
> >>> On Thu, Jun 08, 2017 at 04:25:39PM +0100, Edward Cree wrote:
> On
On Thu, Jun 08, 2017 at 08:38:29PM +0100, Edward Cree wrote:
> On 08/06/17 17:45, Alexei Starovoitov wrote:
> > On Thu, Jun 08, 2017 at 03:53:36PM +0100, Edward Cree wrote:
>
> -} else if (reg->type == FRAME_PTR || reg->type == PTR_TO_STACK)
> {
> +} else if (
On Wed, Jun 28, 2017 at 10:38:02PM +0200, Daniel Borkmann wrote:
> On 06/28/2017 04:11 PM, Edward Cree wrote:
> > On 28/06/17 14:50, Daniel Borkmann wrote:
> > > Hi Edward,
> > >
> > > Did you also have a chance in the meantime to look at reducing complexity
> > > along with your unification? I di
On Fri, Jun 30, 2017 at 6:05 AM, carlos antonio neira bustos via
iovisor-dev wrote:
> Hi,
>
> I just integrated changes from this commit for Kernel version 3.15
>
>
> https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=bd4cf0ed331a275e9bf5a49e6d0fd55dffc551b8
that is just
On 6/30/17 9:44 AM, Edward Cree wrote:
I haven't measured the test_progs ones, because I *still* haven't gotten
around to actually setting up a BPF toolchain (it doesn't help that I'm
building everything on a test server that gets reimaged every night to
run our nightly tests...).
then you'r
On 8/15/17 12:34 PM, Edward Cree wrote:
State of a register doesn't matter if it wasn't read in reaching an exit;
a write screens off all reads downstream of it from all explored_states
upstream of it.
This allows us to prune many more branches; here are some processed insn
counts for some Cil
On 8/18/17 7:16 AM, Edward Cree wrote:
On 18/08/17 04:21, Alexei Starovoitov wrote:
On 8/15/17 12:34 PM, Edward Cree wrote:
State of a register doesn't matter if it wasn't read in reaching an exit;
a write screens off all reads downstream of it from all explored_states
upstream of it.
This al
1 - 100 of 130 matches
Mail list logo
