Re: [PATCH v4 2/2] add icswx support

2011-03-04 Thread Benjamin Herrenschmidt
On Fri, 2011-03-04 at 17:07 -0600, Tseng-Hui (Frank) Lin wrote: > I don't have any measurable numbers. That's why I made it an option in > case people wants to disable it. I do agree that the kernel has so many > options that we should refrain from adding more. If the chance that the > lazy switchi

Re: [PATCH v3 0/9] fsldma: lockup fixes

2011-03-04 Thread Felix Radensky
Hi Ira, I've successfully tested this version on P2020RDB, with 10 threads per channel, 10 iterations per thread. Tested-by: Felix Radensky Felix. ___ Linuxppc-dev mailing list Linuxppc-dev@lists.ozlabs.org https://lists.ozlabs.org/listinfo/linux

Re: [PATCH v4 2/2] add icswx support

2011-03-04 Thread Tseng-Hui (Frank) Lin
On Sat, 2011-03-05 at 09:40 +1100, Benjamin Herrenschmidt wrote: > > The lazy switching checks the shadow variable first before setting ACOP > > register. This saves mtspr() only if the new value is the same as > > current. If there are several coprocessors on the system, the ACOP > > register may

Re: [PATCH] Fix masking of interrupts for 52xx GPT IRQ.

2011-03-04 Thread Benjamin Herrenschmidt
On Fri, 2011-03-04 at 23:40 +0100, Henk Stegeman wrote: > What if the unmask/mask functions are dropped and only interrupt > enable/disable functions are provided? No, that's backward. enable/disable are handled by the core, leave them there. > I.e: rename the old unmask/mask functions to enable/

Re: [PATCH v4 2/2] add icswx support

2011-03-04 Thread Benjamin Herrenschmidt
On Fri, 2011-03-04 at 16:22 -0600, Tseng-Hui (Frank) Lin wrote: > > Well, I don't know how you use icswx on P7+, but on Prism it's > > definitely issued directly by userspace. > > > OK. You've got a point. I wasn't aware of Prism. HFI device driver is > currently the only icswx user on P7. Could

Re: [PATCH] Fix masking of interrupts for 52xx GPT IRQ.

2011-03-04 Thread Henk Stegeman
What if the unmask/mask functions are dropped and only interrupt enable/disable functions are provided? I.e: rename the old unmask/mask functions to enable/disable and register them as enable/disable? I did try that, and it works too, no spurious IRQ's and no missing IRQ's. Cheers, Henk. On Wed

Re: [PATCH v4 2/2] add icswx support

2011-03-04 Thread Tseng-Hui (Frank) Lin
On Sat, 2011-03-05 at 07:26 +1100, Benjamin Herrenschmidt wrote: > On Fri, 2011-03-04 at 11:29 -0600, Tseng-Hui (Frank) Lin wrote: > > On Fri, 2011-03-04 at 12:02 +1100, Benjamin Herrenschmidt wrote: > > > On Wed, 2011-03-02 at 11:20 -0600, Tseng-Hui (Frank) Lin wrote: > > > > > > > +#define CPU_F

Re: [PATCH v4 2/2] add icswx support

2011-03-04 Thread Benjamin Herrenschmidt
On Fri, 2011-03-04 at 11:29 -0600, Tseng-Hui (Frank) Lin wrote: > On Fri, 2011-03-04 at 12:02 +1100, Benjamin Herrenschmidt wrote: > > On Wed, 2011-03-02 at 11:20 -0600, Tseng-Hui (Frank) Lin wrote: > > > > > +#define CPU_FTR_ICSWX LONG_ASM_CONST(0x1000) > > > > Do we

Re: [PATCH v4 2/2] add icswx support

2011-03-04 Thread Tseng-Hui (Frank) Lin
On Fri, 2011-03-04 at 12:02 +1100, Benjamin Herrenschmidt wrote: > On Wed, 2011-03-02 at 11:20 -0600, Tseng-Hui (Frank) Lin wrote: > > > +#define CPU_FTR_ICSWX LONG_ASM_CONST(0x1000) > > Do we want a userspace visible feature as well ? Or some other way to > inform us

Re: [PATCH] powerpc: disable MSI using new interface if possible

2011-03-04 Thread Florian Mickler
On Thu, 03 Mar 2011 19:29:19 -0800 Joe Perches wrote: > > $ git log --pretty=format:"%an %ae" arch/powerpc/platforms/pseries/msi.c > > Andre Detsch adet...@br.ibm.com > > Michael Ellerman mich...@ellerman.id.au > > Michael Ellerman mich...@ellerman.id.au > > Michael Ellerman mich...@ellerman.id.a