Re: [PATCH kernel v10 02/34] powerpc/iommu/powernv: Get rid of set_iommu_table_base_and_group

From: Gavin Shan
Date: Wed May 13 2015 - 01:19:40 EST


On Tue, May 12, 2015 at 01:38:51AM +1000, Alexey Kardashevskiy wrote:
>The set_iommu_table_base_and_group() name suggests that the function
>sets table base and add a device to an IOMMU group. However actual
>table base setting happens in pnv_pci_ioda_dma_dev_setup().
>

On PHB3, the DMA32 IOMMU table is created during PHB fixup time
in ppc_md.pcibios_fixup(), which is invoked at end of PCI enumeration.
The IOMMU table of PCI devices are initialized at same time.
pnv_pci_ioda_dma_dev_setup() is called when adding PCI device
or fixing up PCI bus at PCI enumeration time. So the commit logs
here isn't accurate enough.

Basically, set_iommu_table_base_and_group() which does two things
in one function, which is nice. I guess you don't need this function
any more after DDW is supported and it's the reason to remove it?

>The actual purpose for table base setting is to put some reference
>into a device so later iommu_add_device() can get the IOMMU group
>reference and the device to the group.
>
>At the moment a group cannot be explicitly passed to iommu_add_device()
>as we want it to work from the bus notifier, we can fix it later and
>remove confusing calls of set_iommu_table_base().
>
>This replaces set_iommu_table_base_and_group() with a couple of
>set_iommu_table_base() + iommu_add_device() which makes reading the code
>easier.
>
>This adds few comments why set_iommu_table_base() and iommu_add_device()
>are called where they are called.
>
>For IODA1/2, this essentially removes iommu_add_device() call from
>the pnv_pci_ioda_dma_dev_setup() as it will always fail at this particular
>place:
>- for physical PE, the device is already attached by iommu_add_device()
>in pnv_pci_ioda_setup_dma_pe();
>- for virtual PE, the sysfs entries are not ready to create all symlinks
>so actual adding is happening in tce_iommu_bus_notifier.
>
>Signed-off-by: Alexey Kardashevskiy <aik@xxxxxxxxx>

Reviewed-by: Gavin Shan <gwshan@xxxxxxxxxxxxxxxxxx>

>---
>Changes:
>v10:
>* new to the series
>---
> arch/powerpc/include/asm/iommu.h | 7 -------
> arch/powerpc/platforms/powernv/pci-ioda.c | 27 +++++++++++++++++++++++----
> arch/powerpc/platforms/powernv/pci-p5ioc2.c | 3 ++-
> arch/powerpc/platforms/pseries/iommu.c | 15 ++++++++-------
> 4 files changed, 33 insertions(+), 19 deletions(-)
>
>diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
>index 1e27d63..8353c86 100644
>--- a/arch/powerpc/include/asm/iommu.h
>+++ b/arch/powerpc/include/asm/iommu.h
>@@ -140,13 +140,6 @@ static inline int __init tce_iommu_bus_notifier_init(void)
> }
> #endif /* !CONFIG_IOMMU_API */
>
>-static inline void set_iommu_table_base_and_group(struct device *dev,
>- void *base)
>-{
>- set_iommu_table_base(dev, base);
>- iommu_add_device(dev);
>-}
>-
> extern int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
> struct scatterlist *sglist, int nelems,
> unsigned long mask,
>diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
>index 2f092bb..9a77f3c 100644
>--- a/arch/powerpc/platforms/powernv/pci-ioda.c
>+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
>@@ -1598,7 +1598,13 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
>
> pe = &phb->ioda.pe_array[pdn->pe_number];
> WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops);
>- set_iommu_table_base_and_group(&pdev->dev, pe->tce32_table);
>+ set_iommu_table_base(&pdev->dev, pe->tce32_table);
>+ /*
>+ * Note: iommu_add_device() will fail here as
>+ * for physical PE: the device is already added by now;
>+ * for virtual PE: sysfs entries are not ready yet and
>+ * tce_iommu_bus_notifier will add the device to a group later.
>+ */

I didn't figure out how the IOMMU table is initialized for PCI device in this
function during bootup time. At system bootup time, the function is only called
when applying fixup to PCI bus in pcibios_fixup_bus(). At that time, we don't
have PE# yet, which is allocated at PHB fixup time (ppc_md.pcibios_fixup_phb).

> }
>
> static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
>@@ -1659,7 +1665,8 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe,
> struct pci_dev *dev;
>
> list_for_each_entry(dev, &bus->devices, bus_list) {
>- set_iommu_table_base_and_group(&dev->dev, pe->tce32_table);
>+ set_iommu_table_base(&dev->dev, pe->tce32_table);
>+ iommu_add_device(&dev->dev);
>
> if (dev->subordinate)
> pnv_ioda_setup_bus_dma(pe, dev->subordinate);
>@@ -1835,7 +1842,13 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
> if (pe->flags & PNV_IODA_PE_DEV) {
> iommu_register_group(tbl, phb->hose->global_number,
> pe->pe_number);
>- set_iommu_table_base_and_group(&pe->pdev->dev, tbl);
>+ /*
>+ * Setting table base here only for carrying iommu_group
>+ * further down to let iommu_add_device() do the job.
>+ * pnv_pci_ioda_dma_dev_setup will override it later anyway.
>+ */
>+ set_iommu_table_base(&pe->pdev->dev, tbl);
>+ iommu_add_device(&pe->pdev->dev);
> } else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) {
> iommu_register_group(tbl, phb->hose->global_number,
> pe->pe_number);
>@@ -1963,7 +1976,13 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
> if (pe->flags & PNV_IODA_PE_DEV) {
> iommu_register_group(tbl, phb->hose->global_number,
> pe->pe_number);
>- set_iommu_table_base_and_group(&pe->pdev->dev, tbl);
>+ /*
>+ * Setting table base here only for carrying iommu_group
>+ * further down to let iommu_add_device() do the job.
>+ * pnv_pci_ioda_dma_dev_setup will override it later anyway.
>+ */
>+ set_iommu_table_base(&pe->pdev->dev, tbl);
>+ iommu_add_device(&pe->pdev->dev);
> } else if (pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL)) {
> iommu_register_group(tbl, phb->hose->global_number,
> pe->pe_number);
>diff --git a/arch/powerpc/platforms/powernv/pci-p5ioc2.c b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
>index 4729ca7..b17d93615 100644
>--- a/arch/powerpc/platforms/powernv/pci-p5ioc2.c
>+++ b/arch/powerpc/platforms/powernv/pci-p5ioc2.c
>@@ -92,7 +92,8 @@ static void pnv_pci_p5ioc2_dma_dev_setup(struct pnv_phb *phb,
> pci_domain_nr(phb->hose->bus), phb->opal_id);
> }
>
>- set_iommu_table_base_and_group(&pdev->dev, &phb->p5ioc2.iommu_table);
>+ set_iommu_table_base(&pdev->dev, &phb->p5ioc2.iommu_table);
>+ iommu_add_device(&pdev->dev);
> }
>
> static void __init pnv_pci_init_p5ioc2_phb(struct device_node *np, u64 hub_id,
>diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
>index 61d5a17..05ab06d 100644
>--- a/arch/powerpc/platforms/pseries/iommu.c
>+++ b/arch/powerpc/platforms/pseries/iommu.c
>@@ -688,8 +688,8 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
> iommu_table_setparms(phb, dn, tbl);
> PCI_DN(dn)->iommu_table = iommu_init_table(tbl, phb->node);
> iommu_register_group(tbl, pci_domain_nr(phb->bus), 0);
>- set_iommu_table_base_and_group(&dev->dev,
>- PCI_DN(dn)->iommu_table);
>+ set_iommu_table_base(&dev->dev, tbl);
>+ iommu_add_device(&dev->dev);
> return;
> }
>
>@@ -700,10 +700,10 @@ static void pci_dma_dev_setup_pSeries(struct pci_dev *dev)
> while (dn && PCI_DN(dn) && PCI_DN(dn)->iommu_table == NULL)
> dn = dn->parent;
>
>- if (dn && PCI_DN(dn))
>- set_iommu_table_base_and_group(&dev->dev,
>- PCI_DN(dn)->iommu_table);
>- else
>+ if (dn && PCI_DN(dn)) {
>+ set_iommu_table_base(&dev->dev, PCI_DN(dn)->iommu_table);
>+ iommu_add_device(&dev->dev);
>+ } else
> printk(KERN_WARNING "iommu: Device %s has no iommu table\n",
> pci_name(dev));
> }
>@@ -1115,7 +1115,8 @@ static void pci_dma_dev_setup_pSeriesLP(struct pci_dev *dev)
> pr_debug(" found DMA window, table: %p\n", pci->iommu_table);
> }
>
>- set_iommu_table_base_and_group(&dev->dev, pci->iommu_table);
>+ set_iommu_table_base(&dev->dev, pci->iommu_table);
>+ iommu_add_device(&dev->dev);
> }
>
> static int dma_set_mask_pSeriesLP(struct device *dev, u64 dma_mask)

Thanks,
Gavin

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/