Re: [PATCH 0/2] x86: per-device dma_mapping_ops

[Muli Ben-Yehuda <muli@il.ibm.com>]

On Wed, May 14, 2008 at 07:00:13PM -0700, Alexis Bruemmer wrote:

> I wanted to try and create a test version of this, at least for the
> calgary side, but ran into an error with this patch set:
> 
> Fusion MPT SAS Host driver 3.04.06
> ACPI: PCI Interrupt 0000:34:00.0[A] -> GSI 142 (level, low) -> IRQ 142
> mptbase: ioc0: Initiating bringup
> ioc0: LSISAS1078 C1: Capabilities={Initiator}
> mptbase: ioc0: PCI-MSI enabled
> Calgary: DMA error on CalIOC2 PHB 0x33
> Calgary: 0x02000000@CSR 0x00000000@PLSSR 0xb0008000@CSMR 0x00000000@MCK
> Calgary: 0x00000000@0x810 0xfee0c000@0x820 0x00000000@0x830
> 0x00000000@0x840 0x03804a00@0x850 0x00000000@0x860 0x00000000@0x870
> Calgary: 0x00000000@0xcb0

Calgary caught an errant DMA. If it was working before, we are
probably mis-programming the TCE tables. The first thing to check is
whether all dma_map_xxx calls by mptbase end up calling the Calgary
dma_ops.

Cheers,
Muli