Re: [PATCH kernel v10 01/34] powerpc/eeh/ioda2: Use device::iommu_group to check IOMMU group

[Gavin Shan <gwshan@linux.vnet.ibm.com>]

On Tue, May 12, 2015 at 01:38:50AM +1000, Alexey Kardashevskiy wrote:
>This relies on the fact that a PCI device always has an IOMMU table
>which may not be the case when we get dynamic DMA windows so
>let's use more reliable check for IOMMU group here.
>
>As we do not rely on the table presence here, remove the workaround
>from pnv_pci_ioda2_set_bypass(); also remove the @add_to_iommu_group
>parameter from pnv_ioda_setup_bus_dma().
>
>Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>

Acked-by: Gavin Shan <gwshan@linux.vnet.ibm.com>

Thanks,
Gavin

>---
> arch/powerpc/kernel/eeh.c                 |  4 +---
> arch/powerpc/platforms/powernv/pci-ioda.c | 27 +++++----------------------
> 2 files changed, 6 insertions(+), 25 deletions(-)
>
>diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
>index 9ee61d1..defd874 100644
>--- a/arch/powerpc/kernel/eeh.c
>+++ b/arch/powerpc/kernel/eeh.c
>@@ -1412,13 +1412,11 @@ static int dev_has_iommu_table(struct device *dev, void *data)
> {
> 	struct pci_dev *pdev = to_pci_dev(dev);
> 	struct pci_dev **ppdev = data;
>-	struct iommu_table *tbl;
>
> 	if (!dev)
> 		return 0;
>
>-	tbl = get_iommu_table_base(dev);
>-	if (tbl && tbl->it_group) {
>+	if (dev->iommu_group) {
> 		*ppdev = pdev;
> 		return 1;
> 	}
>diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
>index f8bc950..2f092bb 100644
>--- a/arch/powerpc/platforms/powernv/pci-ioda.c
>+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
>@@ -1654,21 +1654,15 @@ static u64 pnv_pci_ioda_dma_get_required_mask(struct pnv_phb *phb,
> }
>
> static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe,
>-				   struct pci_bus *bus,
>-				   bool add_to_iommu_group)
>+				   struct pci_bus *bus)
> {
> 	struct pci_dev *dev;
>
> 	list_for_each_entry(dev, &bus->devices, bus_list) {
>-		if (add_to_iommu_group)
>-			set_iommu_table_base_and_group(&dev->dev,
>-						       pe->tce32_table);
>-		else
>-			set_iommu_table_base(&dev->dev, pe->tce32_table);
>+		set_iommu_table_base_and_group(&dev->dev, pe->tce32_table);
>
> 		if (dev->subordinate)
>-			pnv_ioda_setup_bus_dma(pe, dev->subordinate,
>-					       add_to_iommu_group);
>+			pnv_ioda_setup_bus_dma(pe, dev->subordinate);
> 	}
> }
>
>@@ -1845,7 +1839,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
> 	} else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) {
> 		iommu_register_group(tbl, phb->hose->global_number,
> 				     pe->pe_number);
>-		pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
>+		pnv_ioda_setup_bus_dma(pe, pe->pbus);
> 	} else if (pe->flags & PNV_IODA_PE_VF) {
> 		iommu_register_group(tbl, phb->hose->global_number,
> 				     pe->pe_number);
>@@ -1882,17 +1876,6 @@ static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable)
> 						     window_id,
> 						     pe->tce_bypass_base,
> 						     0);
>-
>-		/*
>-		 * EEH needs the mapping between IOMMU table and group
>-		 * of those VFIO/KVM pass-through devices. We can postpone
>-		 * resetting DMA ops until the DMA mask is configured in
>-		 * host side.
>-		 */
>-		if (pe->pdev)
>-			set_iommu_table_base(&pe->pdev->dev, tbl);
>-		else
>-			pnv_ioda_setup_bus_dma(pe, pe->pbus, false);
> 	}
> 	if (rc)
> 		pe_err(pe, "OPAL error %lld configuring bypass window\n", rc);
>@@ -1984,7 +1967,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
> 	} else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) {
> 		iommu_register_group(tbl, phb->hose->global_number,
> 				     pe->pe_number);
>-		pnv_ioda_setup_bus_dma(pe, pe->pbus, true);
>+		pnv_ioda_setup_bus_dma(pe, pe->pbus);
> 	} else if (pe->flags & PNV_IODA_PE_VF) {
> 		iommu_register_group(tbl, phb->hose->global_number,
> 				     pe->pe_number);
>-- 
>2.4.0.rc3.8.gfb3e7d5
>