Re: [PATCH] POWERPC: MTD: Add cached map support to physmap_of MTD driver

2008-12-17 Thread Trent Piepho
On Tue, 16 Dec 2008, Benjamin Herrenschmidt wrote: > On Mon, 2008-12-15 at 17:11 -0800, Trent Piepho wrote: >> Shame, as it provides a huge speed up. I suppose an alternative would be >> to map the chip twice at different physical addresses, by just configuring >> the chip select to be twice the s

Re: [PATCH] POWERPC: MTD: Add cached map support to physmap_of MTD driver

2008-12-16 Thread Benjamin Herrenschmidt
On Mon, 2008-12-15 at 17:11 -0800, Trent Piepho wrote: > Shame, as it provides a huge speed up. I suppose an alternative would be > to map the chip twice at different physical addresses, by just configuring > the chip select to be twice the size it should be, and giving them > different cacheabili

Re: [PATCH] POWERPC: MTD: Add cached map support to physmap_of MTD driver

2008-12-16 Thread Benjamin Herrenschmidt
On Mon, 2008-12-15 at 10:25 -0800, Trent Piepho wrote: > The MTD system supports operation where a direct mapped flash chip is > mapped twice. The normal mapping is a standard ioremap(), which is > non-cached and guarded on powerpc. The second mapping is used only for > reads and can be cached an

Re: [PATCH] POWERPC: MTD: Add cached map support to physmap_of MTD driver

2008-12-15 Thread Trent Piepho
On Tue, 16 Dec 2008, Paul Mackerras wrote: > Trent Piepho writes: >> The MTD system supports operation where a direct mapped flash chip is >> mapped twice. The normal mapping is a standard ioremap(), which is >> non-cached and guarded on powerpc. The second mapping is used only for >> reads and c

Re: [PATCH] POWERPC: MTD: Add cached map support to physmap_of MTD driver

2008-12-15 Thread Paul Mackerras
Trent Piepho writes: > The MTD system supports operation where a direct mapped flash chip is > mapped twice. The normal mapping is a standard ioremap(), which is > non-cached and guarded on powerpc. The second mapping is used only for > reads and can be cached and non-guarded. Currently, only t

Re: [PATCH] POWERPC: MTD: Add cached map support to physmap_of MTD driver

2008-12-15 Thread Trent Piepho
On Mon, 15 Dec 2008, Josh Boyer wrote: > > Did you actually change anything in this version when compared to the > version you sent out last week? If not, is there a reason you sent it > again without flagging it as a resend? I sent it out last week? I'm trying to tie up loose ends before I leav

Re: [PATCH] POWERPC: MTD: Add cached map support to physmap_of MTD driver

2008-12-15 Thread Josh Boyer
On Mon, 15 Dec 2008 10:25:18 -0800 Trent Piepho wrote: > The MTD system supports operation where a direct mapped flash chip is > mapped twice. The normal mapping is a standard ioremap(), which is > non-cached and guarded on powerpc. The second mapping is used only for > reads and can be cached

[PATCH] POWERPC: MTD: Add cached map support to physmap_of MTD driver

2008-12-15 Thread Trent Piepho
The MTD system supports operation where a direct mapped flash chip is mapped twice. The normal mapping is a standard ioremap(), which is non-cached and guarded on powerpc. The second mapping is used only for reads and can be cached and non-guarded. Currently, only the pxa2xx mapping driver makes