Re: [PATCH v2] PCI/MSI: Improve MSI alias detection

2017-08-14 Thread Bjorn Helgaas
On Tue, Aug 01, 2017 at 06:59:08PM +0100, Robin Murphy wrote: > Currently, we handle all DMA aliases equally when calculating MSI > requester IDs for the generic infrastructure. This turns out to be the > wrong thing to do in the face of pure DMA quirks like those of Marvell > SATA cards, where in

Re: [PATCH v2] PCI/MSI: Improve MSI alias detection

2017-08-14 Thread Bjorn Helgaas
On Tue, Aug 01, 2017 at 06:59:08PM +0100, Robin Murphy wrote: > Currently, we handle all DMA aliases equally when calculating MSI > requester IDs for the generic infrastructure. This turns out to be the > wrong thing to do in the face of pure DMA quirks like those of Marvell > SATA cards, where in

Re: [PATCH v2] PCI/MSI: Improve MSI alias detection

2017-08-03 Thread Marc Zyngier
On 01/08/17 18:59, Robin Murphy wrote: > Currently, we handle all DMA aliases equally when calculating MSI > requester IDs for the generic infrastructure. This turns out to be the > wrong thing to do in the face of pure DMA quirks like those of Marvell > SATA cards, where in the usual case the

Re: [PATCH v2] PCI/MSI: Improve MSI alias detection

2017-08-03 Thread Marc Zyngier
On 01/08/17 18:59, Robin Murphy wrote: > Currently, we handle all DMA aliases equally when calculating MSI > requester IDs for the generic infrastructure. This turns out to be the > wrong thing to do in the face of pure DMA quirks like those of Marvell > SATA cards, where in the usual case the

[PATCH v2] PCI/MSI: Improve MSI alias detection

2017-08-01 Thread Robin Murphy
Currently, we handle all DMA aliases equally when calculating MSI requester IDs for the generic infrastructure. This turns out to be the wrong thing to do in the face of pure DMA quirks like those of Marvell SATA cards, where in the usual case the last thing seen in the alias walk is the DMA

[PATCH v2] PCI/MSI: Improve MSI alias detection

2017-08-01 Thread Robin Murphy
Currently, we handle all DMA aliases equally when calculating MSI requester IDs for the generic infrastructure. This turns out to be the wrong thing to do in the face of pure DMA quirks like those of Marvell SATA cards, where in the usual case the last thing seen in the alias walk is the DMA