Skip site navigation (1)Skip section navigation (2)
Date:      Mon, 29 Jun 2009 14:14:45 +0200
From:      Hans Petter Selasky <hselasky@c2i.net>
To:        Stanislav Sedov <stas@freebsd.org>
Cc:        thompsa@freebsd.org, freebsd-arm@freebsd.org, freebsd-usb@freebsd.org
Subject:   Re: CPU Cache and busdma usage in USB
Message-ID:  <200906291414.46341.hselasky@c2i.net>
In-Reply-To: <20090629161011.2a657c4b.stas@FreeBSD.org>
References:  <200906231035.43096.kosmo@semihalf.com> <200906291337.43635.hselasky@c2i.net> <20090629161011.2a657c4b.stas@FreeBSD.org>

next in thread | previous in thread | raw e-mail | index | archive | help
On Monday 29 June 2009 14:10:11 Stanislav Sedov wrote:
> On Mon, 29 Jun 2009 13:37:41 +0200
>
> Hans Petter Selasky <hselasky@c2i.net> mentioned:
> > USB is currently _updating_ (!!) the PAGE offset part of "vaddr". If
> > cpu_dcache_inv_range() is called with an address not starting at the
> > cache line what will the cpu_dcache_inv_range() do? Will it skip to the
> > next cache line? Or will it completely skip the whole cache sync
> > operation?!
>
> Currently, the address passed to cpu_dcache_inv_range will be rounded up
> to the cache line boundary and the whole line will be invalidated if the
> range requested is smaller than 16KiB.  Otherwise, the whole cache will
> be invalidated.

That maybe explains it, because USB will require rounding down the address and 
rounding up the length accordingly, because it uses the 
"BUS_DMA_KEEP_PG_OFFSET" flag.

--HPS



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200906291414.46341.hselasky>