diff mbox

[v12,14/21] powerpc/powernv: Allocate struct pnv_ioda_pe iommu_table dynamically

Message ID 20150224083435.32124.65099.stgit@bhelgaas-glaptop2.roam.corp.google.com (mailing list archive)
State Not Applicable
Headers show

Commit Message

Bjorn Helgaas Feb. 24, 2015, 8:34 a.m. UTC 
From: Wei Yang <weiyang@linux.vnet.ibm.com>

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.

Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 arch/powerpc/include/asm/iommu.h          |    3 +++
 arch/powerpc/platforms/powernv/pci-ioda.c |   26 ++++++++++++++------------
 arch/powerpc/platforms/powernv/pci.h      |    2 +-
 3 files changed, 18 insertions(+), 13 deletions(-)

Comments

Bjorn Helgaas Feb. 24, 2015, 8:46 a.m. UTC | #1 
On Tue, Feb 24, 2015 at 02:34:35AM -0600, Bjorn Helgaas wrote:
> From: Wei Yang <weiyang@linux.vnet.ibm.com>
> 
> 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?

Is there a hotplug remove path where we should also be calling
iommu_free_table()?

> Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
> ---
>  arch/powerpc/include/asm/iommu.h          |    3 +++
>  arch/powerpc/platforms/powernv/pci-ioda.c |   26 ++++++++++++++------------
>  arch/powerpc/platforms/powernv/pci.h      |    2 +-
>  3 files changed, 18 insertions(+), 13 deletions(-)
> 
> diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
> index 9cfa3706a1b8..5574eeb97634 100644
> --- a/arch/powerpc/include/asm/iommu.h
> +++ b/arch/powerpc/include/asm/iommu.h
> @@ -78,6 +78,9 @@ struct iommu_table {
>  	struct iommu_group *it_group;
>  #endif
>  	void (*set_bypass)(struct iommu_table *tbl, bool enable);
> +#ifdef CONFIG_PPC_POWERNV
> +	void           *data;
> +#endif
>  };
>  
>  /* Pure 2^n version of get_order */
> diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
> index 58c4fc4ab63c..cd1a56160ded 100644
> --- a/arch/powerpc/platforms/powernv/pci-ioda.c
> +++ b/arch/powerpc/platforms/powernv/pci-ioda.c
> @@ -916,6 +916,10 @@ static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, int all)
>  		return;
>  	}
>  
> +	pe->tce32_table = kzalloc_node(sizeof(struct iommu_table),
> +			GFP_KERNEL, hose->node);
> +	pe->tce32_table->data = pe;
> +
>  	/* Associate it with all child devices */
>  	pnv_ioda_setup_same_PE(bus, pe);
>  
> @@ -1005,7 +1009,7 @@ 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_and_group(&pdev->dev, pe->tce32_table);
>  }
>  
>  static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
> @@ -1032,7 +1036,7 @@ static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
>  	} else {
>  		dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n");
>  		set_dma_ops(&pdev->dev, &dma_iommu_ops);
> -		set_iommu_table_base(&pdev->dev, &pe->tce32_table);
> +		set_iommu_table_base(&pdev->dev, pe->tce32_table);
>  	}
>  	*pdev->dev.dma_mask = dma_mask;
>  	return 0;
> @@ -1069,9 +1073,9 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe,
>  	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);
> +						       pe->tce32_table);
>  		else
> -			set_iommu_table_base(&dev->dev, &pe->tce32_table);
> +			set_iommu_table_base(&dev->dev, pe->tce32_table);
>  
>  		if (dev->subordinate)
>  			pnv_ioda_setup_bus_dma(pe, dev->subordinate,
> @@ -1161,8 +1165,7 @@ static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe,
>  void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
>  				 __be64 *startp, __be64 *endp, bool rm)
>  {
> -	struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
> -					      tce32_table);
> +	struct pnv_ioda_pe *pe = tbl->data;
>  	struct pnv_phb *phb = pe->phb;
>  
>  	if (phb->type == PNV_PHB_IODA1)
> @@ -1228,7 +1231,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
>  	}
>  
>  	/* Setup linux iommu table */
> -	tbl = &pe->tce32_table;
> +	tbl = pe->tce32_table;
>  	pnv_pci_setup_iommu_table(tbl, addr, TCE32_TABLE_SIZE * segs,
>  				  base << 28, IOMMU_PAGE_SHIFT_4K);
>  
> @@ -1266,8 +1269,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
>  
>  static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable)
>  {
> -	struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
> -					      tce32_table);
> +	struct pnv_ioda_pe *pe = tbl->data;
>  	uint16_t window_id = (pe->pe_number << 1 ) + 1;
>  	int64_t rc;
>  
> @@ -1312,10 +1314,10 @@ static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb,
>  	pe->tce_bypass_base = 1ull << 59;
>  
>  	/* Install set_bypass callback for VFIO */
> -	pe->tce32_table.set_bypass = pnv_pci_ioda2_set_bypass;
> +	pe->tce32_table->set_bypass = pnv_pci_ioda2_set_bypass;
>  
>  	/* Enable bypass by default */
> -	pnv_pci_ioda2_set_bypass(&pe->tce32_table, true);
> +	pnv_pci_ioda2_set_bypass(pe->tce32_table, true);
>  }
>  
>  static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
> @@ -1363,7 +1365,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
>  	}
>  
>  	/* Setup linux iommu table */
> -	tbl = &pe->tce32_table;
> +	tbl = pe->tce32_table;
>  	pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, 0,
>  			IOMMU_PAGE_SHIFT_4K);
>  
> diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
> index e5b75b298d95..731777734bca 100644
> --- a/arch/powerpc/platforms/powernv/pci.h
> +++ b/arch/powerpc/platforms/powernv/pci.h
> @@ -53,7 +53,7 @@ struct pnv_ioda_pe {
>  	/* "Base" iommu table, ie, 4K TCEs, 32-bit DMA */
>  	int			tce32_seg;
>  	int			tce32_segcount;
> -	struct iommu_table	tce32_table;
> +	struct iommu_table	*tce32_table;
>  	phys_addr_t		tce_inval_reg_phys;
>  
>  	/* 64-bit TCE bypass region */
>
Wei Yang March 2, 2015, 7:50 a.m. UTC | #2 
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@linux.vnet.ibm.com>
>> 
>> 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.

>
>> Signed-off-by: Wei Yang <weiyang@linux.vnet.ibm.com>
>> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
>> ---
>>  arch/powerpc/include/asm/iommu.h          |    3 +++
>>  arch/powerpc/platforms/powernv/pci-ioda.c |   26 ++++++++++++++------------
>>  arch/powerpc/platforms/powernv/pci.h      |    2 +-
>>  3 files changed, 18 insertions(+), 13 deletions(-)
>> 
>> diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
>> index 9cfa3706a1b8..5574eeb97634 100644
>> --- a/arch/powerpc/include/asm/iommu.h
>> +++ b/arch/powerpc/include/asm/iommu.h
>> @@ -78,6 +78,9 @@ struct iommu_table {
>>  	struct iommu_group *it_group;
>>  #endif
>>  	void (*set_bypass)(struct iommu_table *tbl, bool enable);
>> +#ifdef CONFIG_PPC_POWERNV
>> +	void           *data;
>> +#endif
>>  };
>>  
>>  /* Pure 2^n version of get_order */
>> diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
>> index 58c4fc4ab63c..cd1a56160ded 100644
>> --- a/arch/powerpc/platforms/powernv/pci-ioda.c
>> +++ b/arch/powerpc/platforms/powernv/pci-ioda.c
>> @@ -916,6 +916,10 @@ static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, int all)
>>  		return;
>>  	}
>>  
>> +	pe->tce32_table = kzalloc_node(sizeof(struct iommu_table),
>> +			GFP_KERNEL, hose->node);
>> +	pe->tce32_table->data = pe;
>> +
>>  	/* Associate it with all child devices */
>>  	pnv_ioda_setup_same_PE(bus, pe);
>>  
>> @@ -1005,7 +1009,7 @@ 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_and_group(&pdev->dev, pe->tce32_table);
>>  }
>>  
>>  static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
>> @@ -1032,7 +1036,7 @@ static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
>>  	} else {
>>  		dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n");
>>  		set_dma_ops(&pdev->dev, &dma_iommu_ops);
>> -		set_iommu_table_base(&pdev->dev, &pe->tce32_table);
>> +		set_iommu_table_base(&pdev->dev, pe->tce32_table);
>>  	}
>>  	*pdev->dev.dma_mask = dma_mask;
>>  	return 0;
>> @@ -1069,9 +1073,9 @@ static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe,
>>  	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);
>> +						       pe->tce32_table);
>>  		else
>> -			set_iommu_table_base(&dev->dev, &pe->tce32_table);
>> +			set_iommu_table_base(&dev->dev, pe->tce32_table);
>>  
>>  		if (dev->subordinate)
>>  			pnv_ioda_setup_bus_dma(pe, dev->subordinate,
>> @@ -1161,8 +1165,7 @@ static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe,
>>  void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
>>  				 __be64 *startp, __be64 *endp, bool rm)
>>  {
>> -	struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
>> -					      tce32_table);
>> +	struct pnv_ioda_pe *pe = tbl->data;
>>  	struct pnv_phb *phb = pe->phb;
>>  
>>  	if (phb->type == PNV_PHB_IODA1)
>> @@ -1228,7 +1231,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
>>  	}
>>  
>>  	/* Setup linux iommu table */
>> -	tbl = &pe->tce32_table;
>> +	tbl = pe->tce32_table;
>>  	pnv_pci_setup_iommu_table(tbl, addr, TCE32_TABLE_SIZE * segs,
>>  				  base << 28, IOMMU_PAGE_SHIFT_4K);
>>  
>> @@ -1266,8 +1269,7 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
>>  
>>  static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable)
>>  {
>> -	struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
>> -					      tce32_table);
>> +	struct pnv_ioda_pe *pe = tbl->data;
>>  	uint16_t window_id = (pe->pe_number << 1 ) + 1;
>>  	int64_t rc;
>>  
>> @@ -1312,10 +1314,10 @@ static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb,
>>  	pe->tce_bypass_base = 1ull << 59;
>>  
>>  	/* Install set_bypass callback for VFIO */
>> -	pe->tce32_table.set_bypass = pnv_pci_ioda2_set_bypass;
>> +	pe->tce32_table->set_bypass = pnv_pci_ioda2_set_bypass;
>>  
>>  	/* Enable bypass by default */
>> -	pnv_pci_ioda2_set_bypass(&pe->tce32_table, true);
>> +	pnv_pci_ioda2_set_bypass(pe->tce32_table, true);
>>  }
>>  
>>  static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
>> @@ -1363,7 +1365,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
>>  	}
>>  
>>  	/* Setup linux iommu table */
>> -	tbl = &pe->tce32_table;
>> +	tbl = pe->tce32_table;
>>  	pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, 0,
>>  			IOMMU_PAGE_SHIFT_4K);
>>  
>> diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
>> index e5b75b298d95..731777734bca 100644
>> --- a/arch/powerpc/platforms/powernv/pci.h
>> +++ b/arch/powerpc/platforms/powernv/pci.h
>> @@ -53,7 +53,7 @@ struct pnv_ioda_pe {
>>  	/* "Base" iommu table, ie, 4K TCEs, 32-bit DMA */
>>  	int			tce32_seg;
>>  	int			tce32_segcount;
>> -	struct iommu_table	tce32_table;
>> +	struct iommu_table	*tce32_table;
>>  	phys_addr_t		tce_inval_reg_phys;
>>  
>>  	/* 64-bit TCE bypass region */
>> 
>--
>To unsubscribe from this list: send the line "unsubscribe linux-pci" in
>the body of a message to majordomo@vger.kernel.org
>More majordomo info at  http://vger.kernel.org/majordomo-info.html
Benjamin Herrenschmidt March 2, 2015, 7:56 a.m. UTC | #3 
On Mon, 2015-03-02 at 15:50 +0800, Wei Yang wrote:
> >
> >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.

Actually, I believe Alexey patches to add support for dynamic DMA
windows for KVM guests using VFIO will also alloc/free iommu tables. In
fact his patches somewhat change quite a few things in that area, and
I'm currently reviewing them.

Wei, can you post a new series when you've finished sync'ing with
Bjorn ? At that point, I'll try to work with Alexey to evaluate the
impact of his changes on your patches.

Cheers,
Ben.
Wei Yang March 2, 2015, 8:02 a.m. UTC | #4 
On Mon, Mar 02, 2015 at 06:56:19PM +1100, Benjamin Herrenschmidt wrote:
>On Mon, 2015-03-02 at 15:50 +0800, Wei Yang wrote:
>> >
>> >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.
>
>Actually, I believe Alexey patches to add support for dynamic DMA
>windows for KVM guests using VFIO will also alloc/free iommu tables. In
>fact his patches somewhat change quite a few things in that area, and
>I'm currently reviewing them.

Yes, I see these changes before.

>
>Wei, can you post a new series when you've finished sync'ing with
>Bjorn ? At that point, I'll try to work with Alexey to evaluate the
>impact of his changes on your patches.

Sure, I will do it ASAP.

>
>Cheers,
>Ben.
>
Bjorn Helgaas March 11, 2015, 2:47 a.m. UTC | #5 
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@linux.vnet.ibm.com>
> >> 
> >> 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
Wei Yang March 11, 2015, 6:13 a.m. UTC | #6 
On Tue, Mar 10, 2015 at 09:47:37PM -0500, Bjorn Helgaas wrote:
>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@linux.vnet.ibm.com>
>> >> 
>> >> 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."

Got it, I have put the explanation in change log in next version.

>
>Bjorn
>_______________________________________________
>Linuxppc-dev mailing list
>Linuxppc-dev@lists.ozlabs.org
>https://lists.ozlabs.org/listinfo/linuxppc-dev
diff mbox

Patch

diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index 9cfa3706a1b8..5574eeb97634 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -78,6 +78,9 @@  struct iommu_table {
 	struct iommu_group *it_group;
 #endif
 	void (*set_bypass)(struct iommu_table *tbl, bool enable);
+#ifdef CONFIG_PPC_POWERNV
+	void           *data;
+#endif
 };
 
 /* Pure 2^n version of get_order */
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 58c4fc4ab63c..cd1a56160ded 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -916,6 +916,10 @@  static void pnv_ioda_setup_bus_PE(struct pci_bus *bus, int all)
 		return;
 	}
 
+	pe->tce32_table = kzalloc_node(sizeof(struct iommu_table),
+			GFP_KERNEL, hose->node);
+	pe->tce32_table->data = pe;
+
 	/* Associate it with all child devices */
 	pnv_ioda_setup_same_PE(bus, pe);
 
@@ -1005,7 +1009,7 @@  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_and_group(&pdev->dev, pe->tce32_table);
 }
 
 static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
@@ -1032,7 +1036,7 @@  static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
 	} else {
 		dev_info(&pdev->dev, "Using 32-bit DMA via iommu\n");
 		set_dma_ops(&pdev->dev, &dma_iommu_ops);
-		set_iommu_table_base(&pdev->dev, &pe->tce32_table);
+		set_iommu_table_base(&pdev->dev, pe->tce32_table);
 	}
 	*pdev->dev.dma_mask = dma_mask;
 	return 0;
@@ -1069,9 +1073,9 @@  static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe,
 	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);
+						       pe->tce32_table);
 		else
-			set_iommu_table_base(&dev->dev, &pe->tce32_table);
+			set_iommu_table_base(&dev->dev, pe->tce32_table);
 
 		if (dev->subordinate)
 			pnv_ioda_setup_bus_dma(pe, dev->subordinate,
@@ -1161,8 +1165,7 @@  static void pnv_pci_ioda2_tce_invalidate(struct pnv_ioda_pe *pe,
 void pnv_pci_ioda_tce_invalidate(struct iommu_table *tbl,
 				 __be64 *startp, __be64 *endp, bool rm)
 {
-	struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
-					      tce32_table);
+	struct pnv_ioda_pe *pe = tbl->data;
 	struct pnv_phb *phb = pe->phb;
 
 	if (phb->type == PNV_PHB_IODA1)
@@ -1228,7 +1231,7 @@  static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 	}
 
 	/* Setup linux iommu table */
-	tbl = &pe->tce32_table;
+	tbl = pe->tce32_table;
 	pnv_pci_setup_iommu_table(tbl, addr, TCE32_TABLE_SIZE * segs,
 				  base << 28, IOMMU_PAGE_SHIFT_4K);
 
@@ -1266,8 +1269,7 @@  static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb,
 
 static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable)
 {
-	struct pnv_ioda_pe *pe = container_of(tbl, struct pnv_ioda_pe,
-					      tce32_table);
+	struct pnv_ioda_pe *pe = tbl->data;
 	uint16_t window_id = (pe->pe_number << 1 ) + 1;
 	int64_t rc;
 
@@ -1312,10 +1314,10 @@  static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb,
 	pe->tce_bypass_base = 1ull << 59;
 
 	/* Install set_bypass callback for VFIO */
-	pe->tce32_table.set_bypass = pnv_pci_ioda2_set_bypass;
+	pe->tce32_table->set_bypass = pnv_pci_ioda2_set_bypass;
 
 	/* Enable bypass by default */
-	pnv_pci_ioda2_set_bypass(&pe->tce32_table, true);
+	pnv_pci_ioda2_set_bypass(pe->tce32_table, true);
 }
 
 static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
@@ -1363,7 +1365,7 @@  static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 	}
 
 	/* Setup linux iommu table */
-	tbl = &pe->tce32_table;
+	tbl = pe->tce32_table;
 	pnv_pci_setup_iommu_table(tbl, addr, tce_table_size, 0,
 			IOMMU_PAGE_SHIFT_4K);
 
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index e5b75b298d95..731777734bca 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -53,7 +53,7 @@  struct pnv_ioda_pe {
 	/* "Base" iommu table, ie, 4K TCEs, 32-bit DMA */
 	int			tce32_seg;
 	int			tce32_segcount;
-	struct iommu_table	tce32_table;
+	struct iommu_table	*tce32_table;
 	phys_addr_t		tce_inval_reg_phys;
 
 	/* 64-bit TCE bypass region */