On Mon, Mar 02, 2015 at 03:50:37PM +0800, Wei Yang wrote: > On Tue, Feb 24, 2015 at 02:46:53AM -0600, Bjorn Helgaas wrote: > >On Tue, Feb 24, 2015 at 02:34:35AM -0600, Bjorn Helgaas wrote: > >> From: Wei Yang <weiyang@xxxxxxxxxxxxxxxxxx> > >> > >> Current iommu_table of a PE is a static field. This will have a problem > >> when iommu_free_table() is called. > >> > >> Allocate iommu_table dynamically. > > > >I'd like a little more explanation about why we're calling > >iommu_free_table() now when we didn't call it before. Maybe this happens > >when we disable SR-IOV and the VFs go away? > > Yes, it is called in disable path. > > pcibios_sriov_disable > pnv_pci_sriov_disable > pnv_ioda_release_vf_PE > pnv_pci_ioda2_release_dma_pe > iommu_free_table <--- here it is invoked > > > > > >Is there a hotplug remove path where we should also be calling > >iommu_free_table()? > > When VF is not introduced, no one calls this on powernv platform. > > Each PCI bus is a PE and it has its own iommu table, even a device is > hotpluged, the iommu table will not be released. None of this explanation made it into the v13 patch. And I don't quite understand it anyway. Something like "Previously the iommu_table had the same lifetime as a struct pnv_ioda_pe and was embedded in it. The pnv_ioda_pe was allocated when XXX and freed when YYY. This no longer works: we can't allocate the iommu_table at the same time as the pnv_ioda_pe because XXX, so we allocate it when XXX and free it when YYY." Bjorn -- To unsubscribe from this list: send the line "unsubscribe linux-pci" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
