Discussion:
bunnie about riscv
(too old to reply)
r***@Safe-mail.net
2017-06-10 15:54:46 UTC
Permalink
Raw Message


It was very informative. A lot of the technical matter I did not understand.
Can you explain:
23.04 The 2 lowermost boxes?
What is a stepper?
What is fuse?
25.15 The 4 lowermost boxes?

27.35 It appears there is money.

31.21 Alex Bradbury has said, it is difficult to verify, you get
the hardware, you were told, you would get.

46.31 I agree.

_______________________________________________
arm-netbook mailing list arm-***@lists.phcomp.co.uk
http://lists.phcomp.co.uk/mailman/listinfo/arm-netbook
Send large attachmen
Neil Jansen
2017-06-11 15:07:56 UTC
Permalink
Raw Message
Post by r***@Safe-mail.net
It was very informative. A lot of the technical matter I did not understand.
This was a GREAT talk. Thanks for the link.
Post by r***@Safe-mail.net
23.04 The 2 lowermost boxes?
1) PDK / Foundries. The factories in which the chips are made in. They're
not open. They're proprietary and there's a implication of trust.
2) Equipment / Raw Materials. The equipment that makes the chips and the
raw materials that go into the chips. All a very cloudy and and murky area
that is not open, and very proprietary.

He's basically saying that those that want *100%* open source hardware
would require infinite recursion down to the raw components, which is
impossible. That's the whole point of the talk. The 'impedance mismatch'
thing is a sort of metaphor to describe the unrealistic expectations of
those idealists that want 100% open source hardware. He's saying it cannot
happen today. And BTW I've met Bunnie on several occasions, he's legit,
and you can trust what he's saying to be technically correct. He's the
real deal.
Post by r***@Safe-mail.net
What is a stepper?
A stepper motor. That is, do you trust the motors that move the machines
that made the integrated circuits?
Post by r***@Safe-mail.net
What is fuse?
See this link:
https://electronics.stackexchange.com/questions/1262/what-are-atmel-fuses
Post by r***@Safe-mail.net
25.15 The 4 lowermost boxes?
* BIOS
* Firmware
* Hidden / fused silicon blocks - Blocks of silicon on the chip that aren't
usually turned on, but are there. Lots of big vendors are doing this now:
Intel, AMD, Nvidia, and it's anyone's guess as to what their real purpose
is. That leads to conspiracy theories, as Bunnie said. This is a problem
because if you put a chip like this into an open source laptop, it begs the
question of what would happen if something turned on that section and
started execution code from it? Nobody will know until (A) documentation
is leaked from the company or (B) someone reverse engineers it. Basically
if you use anything application processor chip made in the last 5-10 years,
you probably have some hidden / fused silicon blocks doing god knows what.
* Pre-boot microcode - Microcode (https://en.wikipedia.org/wiki/Microcode)
that executes BEFORE your computer boots. This is a big deal, because
everything that happens after this point can be considered suspect.
(similar to how a boot virus would spread because it executes first).
* IP industry practices - Intellectual property used by silicon
manufacturers that are not open. What he's saying is, say that you're a
silicon vendor and you just bought a intellectual property from ARM to make
an ARM chip. They're giving you HDL (hardware description language) and
netlists (a large list of the connections to be made in the die), and guess
what, they gave them to you encrypted so that their intellectual property
is safe. You (the guy that runs a third party chip factory) cannot review
or inspect the intellectual property that ARM gave you. The point here is
that unless you're using an open source (RISC-V, etc) core, then using an
ARM isn't really 100% open source hardware.
* Mask trojans & glitches - These are malicious things in the CPU die
itself, that even if you were looking at the silicon die under a microscope
and studying it, you'd still completely miss it. Very nasty but they
exist. Hackaday.com has a lot of interesting articles that break these
sort of things down in layman's terms. Very interesting. Basically
because these exist, there's no way to know that you are really executing
what you think you are executing unless you built the foundry and
supervised the chips being made, and analyzed everything that went into the
manufacture of them. It's a trust problem.

These are all highly complex subjects that hardware engineers like Bunnie
deal with a lot, and other (I'll say idealist) software guys probably have
never thought of. They're important in that when you realize that they're
there, you will then understand how silly wanting 100% open hardware really
is. It's a huge problem that hardly anybody is trying to fix.


Recently the 6502 was completely dissected and recreated, so that's one of
the only fully documented (and I'd say fully trusted) cores out there
today. And that was made probably before I was born. Everything since
that should be assumed to be compromised and < 100% open. Oh, and even
then, the 6502 would have to hook up to OTHER chips like flash, RAM, and
whatever generates the video and handles the peripherals. Those have not
been completely dissected, and could be suspect. Do you see what Bunnie
means now? That's the impedance mismatch.


P.S. my apologies to LKCL and others, I don't have a plain text email
client.
_______________________________________________
arm-netbook mailing list arm-***@lists.phcomp.co.uk
http://lists.phcomp.co.uk/mailman/listinfo/arm-netbook
Sen
Luke Kenneth Casson Leighton
2017-06-11 17:28:27 UTC
Permalink
Raw Message
Post by Neil Jansen
P.S. my apologies to LKCL and others, I don't have a plain text email
client.
i've enabled attachment-stripping and automatic HTML-to-plaintext
conversion: it seems to be working well except in the circumstances
where people use html-only-and-attachment-only mail clients.

l.

_______________________________________________
arm-netbook mailing list arm-***@lists.phcomp.co.uk
http://lists.phcomp.co.uk/mailman/listinfo/arm-netbook
Send large attachments to arm-***@files.phcomp.co
Neil Jansen
2017-06-11 23:51:27 UTC
Permalink
Raw Message
Post by Luke Kenneth Casson Leighton
i've enabled attachment-stripping and automatic HTML-to-plaintext
conversion: it seems to be working well except in the circumstances
where people use html-only-and-attachment-only mail clients.
Are mine showing up OK then, or no? I'm using the little button in the
google webmail that strips all formatting, however I assume that it's still
being sent as HTML (albeit HTML that looks good when stripped of
formatting).
_______________________________________________
arm-netbook mailing list arm-***@lists.phcomp.co.uk
http://lists.phcomp.co.uk/mailman/listinfo/arm-netbook
Send lar
r***@Safe-mail.net
2017-06-11 20:38:04 UTC
Permalink
Raw Message
-------- Original Message --------
From: Neil Jansen <***@gmail.com>
Apparently from: arm-netbook-***@lists.phcomp.co.uk
To: Eco-Conscious Computing <arm-***@lists.phcomp.co.uk>
Subject: Re: [Arm-netbook] bunnie about riscv
Date: Sun, 11 Jun 2017 11:07:56 -0400



Thank you for the information.
I have watched a rutkowska video on how complicated
intel's management features are.
Difficult.
Post by r***@Safe-mail.net
Post by r***@Safe-mail.net
It was very informative. A lot of the technical matter I did not
understand.
This was a GREAT talk. Thanks for the link.
Post by r***@Safe-mail.net
23.04 The 2 lowermost boxes?
1) PDK / Foundries. The factories in which the chips are made in. They're
not open. They're proprietary and there's a implication of trust.
2) Equipment / Raw Materials. The equipment that makes the chips and the
raw materials that go into the chips. All a very cloudy and and murky area
that is not open, and very proprietary.
He's basically saying that those that want *100%* open source hardware
would require infinite recursion down to the raw components, which is
impossible. That's the whole point of the talk. The 'impedance mismatch'
thing is a sort of metaphor to describe the unrealistic expectations of
those idealists that want 100% open source hardware. He's saying it cannot
happen today. And BTW I've met Bunnie on several occasions, he's legit,
and you can trust what he's saying to be technically correct. He's the
real deal.
Post by r***@Safe-mail.net
What is a stepper?
A stepper motor. That is, do you trust the motors that move the machines
that made the integrated circuits?
Post by r***@Safe-mail.net
What is fuse?
https://electronics.stackexchange.com/questions/1262/what-are-atmel-fuses
Post by r***@Safe-mail.net
25.15 The 4 lowermost boxes?
* BIOS
* Firmware
* Hidden / fused silicon blocks - Blocks of silicon on the chip that aren't
Intel, AMD, Nvidia, and it's anyone's guess as to what their real purpose
is. That leads to conspiracy theories, as Bunnie said. This is a problem
because if you put a chip like this into an open source laptop, it begs the
question of what would happen if something turned on that section and
started execution code from it? Nobody will know until (A) documentation
is leaked from the company or (B) someone reverse engineers it. Basically
if you use anything application processor chip made in the last 5-10 years,
you probably have some hidden / fused silicon blocks doing god knows what.
* Pre-boot microcode - Microcode (https://en.wikipedia.org/wiki/Microcode)
that executes BEFORE your computer boots. This is a big deal, because
everything that happens after this point can be considered suspect.
(similar to how a boot virus would spread because it executes first).
* IP industry practices - Intellectual property used by silicon
manufacturers that are not open. What he's saying is, say that you're a
silicon vendor and you just bought a intellectual property from ARM to make
an ARM chip. They're giving you HDL (hardware description language) and
netlists (a large list of the connections to be made in the die), and guess
what, they gave them to you encrypted so that their intellectual property
is safe. You (the guy that runs a third party chip factory) cannot review
or inspect the intellectual property that ARM gave you. The point here is
that unless you're using an open source (RISC-V, etc) core, then using an
ARM isn't really 100% open source hardware.
* Mask trojans & glitches - These are malicious things in the CPU die
itself, that even if you were looking at the silicon die under a microscope
and studying it, you'd still completely miss it. Very nasty but they
Remarkable that you cannot do a verification using a microscope.
Post by r***@Safe-mail.net
exist. Hackaday.com has a lot of interesting articles that break these
sort of things down in layman's terms. Very interesting. Basically
because these exist, there's no way to know that you are really executing
what you think you are executing unless you built the foundry and
supervised the chips being made, and analyzed everything that went into the
manufacture of them. It's a trust problem.
These are all highly complex subjects that hardware engineers like Bunnie
deal with a lot, and other (I'll say idealist) software guys probably have
never thought of. They're important in that when you realize that they're
there, you will then understand how silly wanting 100% open hardware really
is. It's a huge problem that hardly anybody is trying to fix.
Recently the 6502 was completely dissected and recreated, so that's one of
the only fully documented (and I'd say fully trusted) cores out there
today. And that was made probably before I was born. Everything since
that should be assumed to be compromised and < 100% open. Oh, and even
then, the 6502 would have to hook up to OTHER chips like flash, RAM, and
whatever generates the video and handles the peripherals. Those have not
been completely dissected, and could be suspect. Do you see what Bunnie
means now? That's the impedance mismatch.
We should have libre software hdds and ram.
Post by r***@Safe-mail.net
P.S. my apologies to LKCL and others, I don't have a plain text email
client.
_______________________________________________
http://lists.phcomp.co.uk/mailman/listinfo/arm-netbook
_______________________________________________
arm-netbook mailing list arm-***@lists.phcomp.co.uk
http://lists.phcomp.co.uk/mailman/listinfo/arm-netbook
Send large attachments to arm-netb
Neil Jansen
2017-06-12 00:02:30 UTC
Permalink
Raw Message
Post by r***@Safe-mail.net
Thank you for the information.
I have watched a rutkowska video on how complicated
intel's management features are.
Difficult.
That's why I'm here, lol. The Intel stuff is getting bad enough that it
has me wondering what I can do for the open source hardware world. Moving
to ARM via EOMA68 is a good near-term solution, but even that's not going
to be 100% trustable at lest by bunnie's standards in the lecture.
Something like RISC-V has the potential to get there, but as he pointed
out, even that's not completely open. I think right now the important
thing is to just be an early adopter of this stuff to show that the
market's there. bunnie broke the demographics down pretty well, there's
definitely money to be made. Back to Intel though. It makes me want to
jump on eBay and pick up some older vintage Intel CPU's that didn't have
the management features, but obviously there's no way to know if those
aren't blown wide open by other means. Man, very interesting times we live
in.
Post by r***@Safe-mail.net
Remarkable that you cannot do a verification using a microscope.
You can do exactly this, and it'll get you to maybe 99% of the way there.
Companies like ChipWorks do exactly this for money. Others do it for hobby
(see: http://www.visual6502.org/, http://siliconpr0n.org/,
https://zeptobars.com/en/, http://www.righto.com/). It can often get great
results. bunnie was playing devils advocate by saying even if you did
this, there are still things that can be present but in an obfuscated
manner, that could be malicious or careless. This doesn't really mean to
throw the baby out with the bathwater. Having a reverse engineered CPU
with a small possibility of shenanigans is still better than having a 100%
proprietary CPU or a 50% proprietary CPU. Security through obscurity and
all that.
Post by r***@Safe-mail.net
We should have libre software hdds and ram.
Can you elaborate on that a bit? I don't understand what you mean.
_______________________________________________
arm-netbook mailing list arm-***@lists.phcomp.co.uk
http://lists.phcomp.co.uk/mailman/listinfo/arm-netbook
Send large attac
Luke Kenneth Casson Leighton
2017-06-12 00:26:03 UTC
Permalink
Raw Message
Post by Neil Jansen
results. bunnie was playing devils advocate by saying even if you did
this, there are still things that can be present but in an obfuscated
manner, that could be malicious or careless.
there was a research paper a few years back which outlined that it
would only take about 3,000 gates to compromise a processor (easily
enough to implement a full RISC CPU).

that's about a million times less than what is in the current intel processors.

the point of the exercise was to illustrate how pointless it is do
perform reverse-engineering of modern CPUs, given that the review
process would be insanely complex and would almost certainly miss such
obfuscated / hidden backdoors.

this is why both the chinese and the russian governments now design
and make their own CPUs. in the case of china that's FROM SCRATCH.
and using only trusted foundries.

l.

_______________________________________________
arm-netbook mailing list arm-***@lists.phcomp.co.uk
http://lists.phcomp.co.uk/mailman/listinfo/arm-netbook
Send large attachments to arm-***@files.
Bill Kontos
2017-06-12 08:53:25 UTC
Permalink
Raw Message
Post by Luke Kenneth Casson Leighton
this is why both the chinese and the russian governments now design
and make their own CPUs. in the case of china that's FROM SCRATCH.
and using only trusted foundries.
l.
I got a question: Assuming we got a decent design for a core( maybe based
on this https://github.com/ucb-bar/riscv-boom) , how would we deal with the
rest of the ip blocks needed to run peripherals ? I assume the most
complicated ones would be usb and ethernet, and I fail to see the point of
a SoC without usb.
_______________________________________________
arm-netbook mailing list arm-***@lists.phcomp.co.uk
http://lists.phcomp.co.uk/mailman/listinfo/arm-netbook
Send large attachments to arm-***@files.phco
Luke Kenneth Casson Leighton
2017-06-12 15:47:20 UTC
Permalink
Raw Message
---
crowd-funded eco-conscious hardware: https://www.crowdsupply.com/eoma68
Post by Luke Kenneth Casson Leighton
I got a question: Assuming we got a decent design for a core( maybe based
on this https://github.com/ucb-bar/riscv-boom) , how would we deal with the
rest of the ip blocks needed to run peripherals ? I assume the most
complicated ones would be usb and ethernet, and I fail to see the point of
a SoC without usb.
https://opencores.org/project,usb
https://opencores.org/project,usbhostslave
https://opencores.org/project,openarty for the UART (special, has
debug capability)
https://opencores.org/project,vga_lcd
https://opencores.org/project,ddr3_sdram

i have the source for a linux kernel driver which uses that VGA/LCD
hard macro: it was used by ICubeCorp for the IC3128. they ran it at
too slow a speed so it would only do 1366x768 @ 30fps 8bpp: this is
probably because the bus speed for the framebuffer access was too
heavy for the Wishbone bus. ramping up the clockrate and/or using a
larger bus width should fix that, but it will need checking.

also i believe the Gaisler Research LEON3 (SPARCv8) has an SMP implementation.

all of these are GPL licensed.... hilariously many people licensed
their hard macros under the GPLv2 in the belief that nobody in their
right mind would utilise GPLv2 hard macros for a commercial venture.

mwaahahahah

_______________________________________________
arm-netbook mailing list arm-***@lists.phcomp.co.uk
http://lists.phcomp.co.uk/mailman/listinfo/arm-netbook
Send large attachm
m***@gmail.com
2017-06-14 10:13:59 UTC
Permalink
Raw Message
Post by Neil Jansen
Post by r***@Safe-mail.net
We should have libre software hdds and ram.
Can you elaborate on that a bit? I don't understand what you mean.
It's the same principle as explained by bunnie in the video. HDD and RAM
process all the data. But they have hard/soft programming which proces that
data.

If you can't audit the hard/soft programming then you don't know if your
data is being read/copied/manipulated.

http://spritesmods.com/?art=hddhack

More and more hardware is using CPU to function. And thus have soft
programming (firrmware) which can be altered.
_______________________________________________
arm-netbook mailing list arm-***@lists.phcomp.co.uk
http://lists.phcomp.co.uk/mailman/listinfo/arm-netbook
Send large attachment
r***@Safe-mail.net
2017-06-13 17:30:06 UTC
Permalink
Raw Message
Post by Neil Jansen
Post by r***@Safe-mail.net
Thank you for the information.
I have watched a rutkowska video on how complicated
intel's management features are.
Difficult.
That's why I'm here, lol. The Intel stuff is getting bad enough that it
has me wondering what I can do for the open source hardware world. Moving
to ARM via EOMA68 is a good near-term solution, but even that's not going
to be 100% trustable at lest by bunnie's standards in the lecture.
Something like RISC-V has the potential to get there, but as he pointed
out, even that's not completely open. I think right now the important
thing is to just be an early adopter of this stuff to show that the
market's there. bunnie broke the demographics down pretty well, there's
definitely money to be made. Back to Intel though. It makes me want to
jump on eBay and pick up some older vintage Intel CPU's that didn't have
the management features, but obviously there's no way to know if those
aren't blown wide open by other means. Man, very interesting times we live
in.
Post by r***@Safe-mail.net
Remarkable that you cannot do a verification using a microscope.
You can do exactly this, and it'll get you to maybe 99% of the way there.
Companies like ChipWorks do exactly this for money. Others do it for hobby
(see: http://www.visual6502.org/, http://siliconpr0n.org/,
https://zeptobars.com/en/, http://www.righto.com/). It can often get great
results. bunnie was playing devils advocate by saying even if you did
this, there are still things that can be present but in an obfuscated
manner, that could be malicious or careless. This doesn't really mean to
throw the baby out with the bathwater. Having a reverse engineered CPU
with a small possibility of shenanigans is still better than having a 100%
proprietary CPU or a 50% proprietary CPU. Security through obscurity and
all that.
Post by r***@Safe-mail.net
We should have libre software hdds and ram.
Can you elaborate on that a bit? I don't understand what you mean.
https://www.theverge.com/2015/2/16/8048243/nsa-hard-drive-firmware-virus-stuxnet




Devices like hdd, ram, sd card have their own system software.
You cannot access it and do not know what it can do.
https://opencores.org/
Post by Neil Jansen
_______________________________________________
http://lists.phcomp.co.uk/mailman/listinfo/arm-netbook
_______________________________________________
arm-netbook mailing list arm-***@lists.phcomp.co.uk
http://lists.phcomp.co.uk/mailman/listinfo/arm-netbook
Send large atta
Luke Kenneth Casson Leighton
2017-06-14 08:30:45 UTC
Permalink
Raw Message
ron hi please remember to cut context. there is 3 paragraphs
comprising several hundred words, repeated, followed by a single
sentence and then a single-sentence question.

these last two sentences are the only relevant context: the rest of
the context you have forced over 400 people to re-read unnecessarily.

please consider the impact that you are having on the members of the
list by following the required etiquette which, by following it, i am
permitting you to be a member of this list.

thank you for understanding and respecting the interaction rules of this list.

l.
Post by r***@Safe-mail.net
Post by Neil Jansen
Post by r***@Safe-mail.net
We should have libre software hdds and ram.
Can you elaborate on that a bit? I don't understand what you mean.
https://www.theverge.com/2015/2/16/8048243/nsa-hard-drive-firmware-virus-stuxnet
Devices like hdd, ram, sd card have their own system software.
You cannot access it and do not know what it can do.
https://opencores.org/
_______________________________________________
arm-netbook mailing list arm-***@lists.phcomp.co.uk
http://lists.phcomp.co.uk/mailman/listinfo/arm-netbook
Send large attachments to ar
r***@Safe-mail.net
2017-06-17 17:35:59 UTC
Permalink
Raw Message
-------- Original Message --------
From: Luke Kenneth Casson Leighton <***@lkcl.net>
Apparently from: arm-netbook-***@lists.phcomp.co.uk
To: Eco-Conscious Computing <arm-***@lists.phcomp.co.uk>
Subject: Re: [Arm-netbook] bunnie about riscv
Date: Wed, 14 Jun 2017 09:30:45 +0100
Post by Luke Kenneth Casson Leighton
ron hi please remember to cut context. there is 3 paragraphs
comprising several hundred words, repeated, followed by a single
sentence and then a single-sentence question.
these last two sentences are the only relevant context: the rest of
the context you have forced over 400 people to re -read unnecessarily.
I have not forced anyone to read anything. Anyone may
ignore my emails.

You know where to look. It is where there are no '>'.
I prefere if others leave the full text in their emails.
I prefere to not delete text in my own replies.
I cannot make that decision about my replies?
Post by Luke Kenneth Casson Leighton
please consider the impact that you are having on the members of the
list by following the required etiquette which, by following it, i am
permitting you to be a member of this list.
thank you for understanding and respecting the interaction rules of this list.
l.
Post by r***@Safe-mail.net
Post by Neil Jansen
Post by r***@Safe-mail.net
We should have libre software hdds and ram.
Can you elaborate on that a bit? I don't understand what you mean.
https://www.theverge.com/2015/2/16/8048243/nsa-hard-drive-firmware-virus-stuxnet
Devices like hdd, ram, sd card have their own system software.
You cannot access it and do not know what it can do.
https://opencores.org/
_______________________________________________
http://lists.phcomp.co.uk/mailman/listinfo/arm-netbook
_______________________________________________
arm-netbook mailing list arm-***@lists.phcomp.co.uk
http://lists.phcomp.co.uk/mailman/listinfo/arm-netbook
Send large attachments to
Lars Kruse
2017-06-17 18:14:53 UTC
Permalink
Raw Message
Hi Ron,


Am Sat, 17 Jun 2017 13:35:59 -0400
Post by r***@Safe-mail.net
[..]
I prefere if others leave the full text in their emails.
I prefere to not delete text in my own replies.
I cannot make that decision about my replies?
I could image, that Luke would like the participants of this mailinglist to use
a style similar to the one defined in RFC1985 ("Netiquette", see section 2.1.1):

Be brief without being overly terse. When replying to a message,
include enough original material to be understood but no more. It
is extremely bad form to simply reply to a message by including
all the previous message: edit out all the irrelevant material.


Since Luke maintains this mailinglist, I find it to be acceptable, that he
can define the communication policy of this list, if he prefers so.
Specifically in this case he is following a widely used style - even though we
are all aware of the fact, that there are different communities or contexts out
there using very different styles with regard to quoting.

Cheers,
Lars

_______________________________________________
arm-netbook mailing list arm-***@lists.phcomp.co.uk
http://lists.phcomp.co.uk/mailman/listinfo/arm-netbook
Send large attachments to arm-***@files.ph

Loading...