Date: Mon, 11 Jun 2007 13:54:28 -0700 From: Chuck Swiger <cswiger@mac.com> To: Kevin K. <freebsd-stable@magma.ca> Cc: freebsd-stable@freebsd.org Subject: Re: DDoS in FreeBSD 6.2-STABLE And Problen With The Clock Message-ID: <7F6FEDFB-EB48-4882-B033-5026EB037641@mac.com> In-Reply-To: <002b01c7ac50$6cd44400$467ccc00$@ca> References: <468d29450706110830k5faf022n9a417157bcf3f544@mail.gmail.com> <002b01c7ac50$6cd44400$467ccc00$@ca>
next in thread | previous in thread | raw e-mail | index | archive | help
On Jun 11, 2007, at 10:46 AM, Kevin K. wrote: >> There are some problems, first DDoS (hardware DDoS) in the system. > > I'd like to know what you mean by "hardware DDoS" I'm not sure what the OP meant, but I can provide examples of a hardware DDoS. Way back when, certain machines were equipped with a Motorola/TI 56001 DSP, which had three separate, parallel execution units, and was an early example of SIMD/VLIW design. It turns out that if you issued an instruction to all three pipelines [1] which loaded or saved to the same memory address, you would fry the DSP chip. The compiler used to generate the code for the 56K DSP chip would prevent this unfortunate event by reordering instructions if needed, but if you wrote your own assembly, you could in fact do a hardware DDoS if you weren't careful. :-) -- -Chuck [1] IIRC, it could deal with two pipelines hitting the same address, but not all three.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?7F6FEDFB-EB48-4882-B033-5026EB037641>