Date: Tue, 14 Aug 2018 08:38:49 -0700 From: Ravi Pokala <rpokala@freebsd.org> To: Andriy Gapon <avg@FreeBSD.org>, Mark Johnston <markj@freebsd.org>, <src-committers@freebsd.org>, <svn-src-all@freebsd.org>, <svn-src-head@freebsd.org> Subject: Re: svn commit: r337754 - head/sys/x86/x86 Message-ID: <4C558668-E3D9-4EEF-BE93-7D2147E7B17E@panasas.com> In-Reply-To: <afb7b9a8-19d8-e763-e3ed-c12e2f7094d6@FreeBSD.org> References: <201808141402.w7EE2seW007725@repo.freebsd.org> <afb7b9a8-19d8-e763-e3ed-c12e2f7094d6@FreeBSD.org>
next in thread | previous in thread | raw e-mail | index | archive | help
-----Original Message----- From: <owner-src-committers@freebsd.org> on behalf of Andriy Gapon <avg@FreeBSD.org> Date: 2018-08-14, Tuesday at 08:34 To: Mark Johnston <markj@freebsd.org>, <src-committers@freebsd.org>, <svn-src-all@freebsd.org>, <svn-src-head@freebsd.org> Subject: Re: svn commit: r337754 - head/sys/x86/x86 > On 14/08/2018 17:02, Mark Johnston wrote: >> At some point memcpy() may be an ifunc, ifunc resolution cannot be done >> until CPU identification has been performed, and CPU identification must >> be done after loading any microcode updates. > > Wouldn't it be cool if before an ifunc is resolved (to a proper > optimized version) it pointed to a default implementation that is > sufficiently naive and robust that it can work on all CPUs? > But I don't know much about ifunc implementation, so no idea if it can > work like that. Or, if that can't be done, have a pre_ifunc_memcpy() with the default implementation, which is explicitly for use before ifuncs are set up. -Ravi > -- > Andriy Gapon
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4C558668-E3D9-4EEF-BE93-7D2147E7B17E>