Date: Tue, 5 Apr 2016 09:10:13 +0300 From: Konstantin Belousov <kostikbel@gmail.com> To: John Baldwin <jhb@freebsd.org> Cc: Ryan Stone <rysto32@gmail.com>, FreeBSD Current <freebsd-current@freebsd.org> Subject: Re: accessing a PCIe register from userspace through kmem or other ways ? Message-ID: <20160405061013.GE1741@kib.kiev.ua> In-Reply-To: <5009932.qXoZ6E4rhX@ralph.baldwin.cx> References: <CA%2BhQ2%2BiU4odjhaNicFA4QjvSZR2OZOOy%2BFu4LTqsibdoK4M8zg@mail.gmail.com> <9376230.YZMFsgSvTf@ralph.baldwin.cx> <CAFMmRNzpOgBPsBezOyUZ_=qjCywfADx8MuJWdaWb_D%2B7UCmi7Q@mail.gmail.com> <5009932.qXoZ6E4rhX@ralph.baldwin.cx>
next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, Apr 04, 2016 at 09:02:49PM -0700, John Baldwin wrote: > kib@ fixed /dev/mem to handle addresses beyond the direct map limit to use > temporary mappings instead of failing with EFAULT in 277051 which was only > committed to HEAD last January, so well after 8.2. The mmap(2) interface to /dev/mem did not have the issue ever. The problem was only with the read(2)/write(2) accesses. >From what I understand, since the goal of the OP was to measure BAR access latencies, read(2) (or write) is unsuitable for him for obvious reasons.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20160405061013.GE1741>