Date: Thu, 23 Jul 2015 07:45:14 -0600 From: Scott Long <scott4long@yahoo.com> To: Mark R V Murray <markm@FreeBSD.org> Cc: Warner Losh <imp@bsdimp.com>, src-committers <src-committers@freebsd.org>, svn-src-all@freebsd.org, svn-src-head@freebsd.org Subject: Re: svn commit: r284959 - in head: . share/man/man4 share/man/man9 sys/conf sys/dev/glxsb sys/dev/hifn sys/dev/random sys/dev/rndtest sys/dev/safe sys/dev/syscons sys/dev/ubsec sys/dev/virtio/random sy... Message-ID: <F54A96A8-D9AD-409A-814F-538B6AD3CD50@yahoo.com> In-Reply-To: <E20B169F-4C8A-4D11-9853-5C2EFC116450@FreeBSD.org> References: <201506301700.t5UH0jPq001498@svn.freebsd.org> <alpine.BSF.2.20.1507221138360.1071@desktop> <FFAED695-145A-45F5-988D-B843EF5F544B@FreeBSD.org> <alpine.BSF.2.20.1507221249120.1071@desktop> <FFFB06D7-164B-40B3-AFC3-A6630BCF074E@bsdimp.com> <E20B169F-4C8A-4D11-9853-5C2EFC116450@FreeBSD.org>
next in thread | previous in thread | raw e-mail | index | archive | help
> On Jul 23, 2015, at 1:03 AM, Mark R V Murray <markm@FreeBSD.org> = wrote: >=20 >=20 >> On 23 Jul 2015, at 00:53, Warner Losh <imp@bsdimp.com> wrote: >>=20 >>>>> Neither filesystem operations nor allocations are random events. = They are trivially influenced by user code. A malicious attacker could = create repeated patterns of allocations or filesystem activity through = the syscall path to degrade your random sample source. >>>>=20 >>>> I?m not sure I accept that - Fortuna is very careful about using = non-reversible hashing in it?s accumulation, and countering such = degradation is one of the algorithm?s strong points. There is perhaps = risk of *no* entropy, but even the per-event timing jitter will be = providing this, if nothing else. >>=20 >> I=E2=80=99m not sure I=E2=80=99m happy about this answer. Do you have = some research backing up such cavalier claims? >=20 > It was not my intention to sound cavalier. Apologies. >=20 > Fortuna was developed to account for many sources of entropy, good and = bad alike, and Jeff=E2=80=99s observation is an attack on that design. I = accept that the randomness of these events is poor, but they are = high-rate, and this product of high-rate*low entropy is what I seek. I = pulled out numbers with dtrace, and basic statistics showed that the = harvesting was not useless. I completely understand that under the right = circumstances these numbers might be lousy - please read the Fortuna = design document to understand why this doesn=E2=80=99t matter. *ALL* = entropy inputs to Fortuna are considered attackable, including the = dedicated hardware sources. >=20 > I have also read cryptanalyses of Fortuna, not all of them to be sure, = and so far the design appears strong. The best attack that I have seen = (very academic) suggests an improvement which I may incorporate. >=20 >>>>> Perhaps more importantly to me, this is an unacceptable = performance burden for the allocator. At a minimum it should compile = out by default. Great care has been taken to reduce the fast path of the = allocator to the minimum number of cycles and even cache misses. >>>>=20 >>>> As currently set up in etc/rc.d/* by default, there is a simple = check at each UMA harvesting opportunity, and no further action. I asked = Robert Watson if this was burdensome, and he said it was not. >>>=20 >>> I find this burdensome. You can easily add a macro around the calls = or hide them in an inline with a default to off. Even a function call = that checks a global and does nothing else is a handful of new cache = misses. A microbenchmark will not realize the full cost of this. You = will instead get the dozen or so instructions of overhead which I still = find objectionable. >>>=20 >>> Kip's observations about packet cycle budgets in high-performance = applications are accurate and this is something we have put great care = into over time. >>=20 >> A certain video streaming company will be pushing the envelope to get = to 100Gbps very soon. Even a few extra instructions on every packet / = allocation will be a killer. Especially if one is an almost guaranteed = cache miss. This most certainly will be burdensome. There absolutely = must be a way to turn this off at compile time. We don=E2=80=99t care = that much about entropy to leave performance on the table. >=20 > OK - I=E2=80=99m sold! I=E2=80=99ll make a kernel option defaulting to = off. :-) >=20 >=20 Hi Mark, Thanks for making this concession. I wanted to add a bit of historical = perspective. When Yarrow was introduced in the previous decade, it was = initially wired into nearly all interrupt sources. It turned out to be = so expensive to those sources, especially for high-speed sources at the = time like network and caching RAID drivers, that we then spent months = disabling it from those sources. In the end, a lot of code thrash = happened and the effectiveness of Yarrow was questionable. Fast forward to now with your recent work. If UMA becomes expensive for = high-speed use, everyone will go back to developing private per-driver = and per-subsystem allocators to avoid it. This will happen whether or = not the UMA collector is controllable at run-time; if it=E2=80=99s = enabled by default, benchmarks will be impacted and people will react. = That=E2=80=99ll be a huge step backwards for FreeBSD. I also strongly agree with Jeff=E2=80=99s point on the questionable = nature of this kind of fast-and-monotonic entropy collection, and Warner = and Kip=E2=80=99s point on the finite number of clock cycles available = for doing 100Gb networking. If really high quality entropy is desired, = won=E2=80=99t most serious people use a hardware source instead of a = software source? Not that I think that software entropy is useless, but = it=E2=80=99s a question of how much effort and tradeoffs are put into it = for what result. An academically beautiful entropy system that = hamstrings the OS from doing other essential things isn=E2=80=99t all = that interesting, IMO. Scott
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?F54A96A8-D9AD-409A-814F-538B6AD3CD50>