[PATCH v2 0/2] powerpc/pci: unmap interrupts when a PHB is removed

[PATCH v2 0/2] powerpc/pci: unmap interrupts when a PHB is removed

[Cédric Le Goater]

Hello,

When a passthrough IO adapter is removed from a pseries machine using
hash MMU and the XIVE interrupt mode, the POWER hypervisor expects the
guest OS to clear all page table entries related to the adapter. If
some are still present, the RTAS call which isolates the PCI slot
returns error 9001 "valid outstanding translations" and the removal of
the IO adapter fails. This is because when the PHBs are scanned, Linux
maps automatically some interrupts in the Linux interrupt number space
but these are never removed.

To solve this problem, we introduce a PPC platform specific
pcibios_remove_bus() routine which clears all interrupt mappings when
the bus is removed. This also clears the associated page table entries
of the ESB pages when using XIVE.

For this purpose, we record the logical interrupt numbers of the
mapped interrupt under the PHB structure and let pcibios_remove_bus()
do the clean up.

Tested on :

  - PowerNV with PCI, OpenCAPI, CAPI and GPU adapters. I don't know
    how to inject a failure on a PHB but that would be a good test.
  - KVM P8+P9 guests with passthrough PCI adapters, but PHBs can not
    be removed under QEMU/KVM.   
  - PowerVM with passthrough PCI adapters (main target)
  
Thanks,

C.

Changes since v1:

 - extended the removal to interrupts other than the legacy INTx.

Cédric Le Goater (2):
  powerpc/pci: unmap legacy INTx interrupts when a PHB is removed
  powerpc/pci: unmap all interrupts when a PHB is removed

 arch/powerpc/include/asm/pci-bridge.h |   6 ++
 arch/powerpc/kernel/pci-common.c      | 114 ++++++++++++++++++++++++++
 2 files changed, 120 insertions(+)

-- 
2.25.4

[PATCH v2 1/2] powerpc/pci: unmap legacy INTx interrupts when a PHB is removed

[Cédric Le Goater]

When a passthrough IO adapter is removed from a pseries machine using
hash MMU and the XIVE interrupt mode, the POWER hypervisor expects the
guest OS to clear all page table entries related to the adapter. If
some are still present, the RTAS call which isolates the PCI slot
returns error 9001 "valid outstanding translations" and the removal of
the IO adapter fails. This is because when the PHBs are scanned, Linux
maps automatically the INTx interrupts in the Linux interrupt number
space but these are never removed.

To solve this problem, we introduce a PPC platform specific
pcibios_remove_bus() routine which clears all interrupt mappings when
the bus is removed. This also clears the associated page table entries
of the ESB pages when using XIVE.

For this purpose, we record the logical interrupt numbers of the
mapped interrupt under the PHB structure and let pcibios_remove_bus()
do the clean up.

Signed-off-by: Cédric Le Goater <clg@kaod.org>
---
 arch/powerpc/include/asm/pci-bridge.h |  6 +++
 arch/powerpc/kernel/pci-common.c      | 67 +++++++++++++++++++++++++++
 2 files changed, 73 insertions(+)

diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index b92e81b256e5..ca75cf264ddf 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -48,6 +48,9 @@ struct pci_controller_ops {
 
 /*
  * Structure of a PCI controller (host bridge)
+ *
+ * @irq_count: number of interrupt mappings
+ * @irq_map: interrupt mappings
  */
 struct pci_controller {
 	struct pci_bus *bus;
@@ -127,6 +130,9 @@ struct pci_controller {
 
 	void *private_data;
 	struct npu *npu;
+
+	unsigned int irq_count;
+	unsigned int *irq_map;
 };
 
 /* These are used for config access before all the PCI probing
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index be108616a721..515480a4bac6 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -353,6 +353,68 @@ struct pci_controller *pci_find_controller_for_domain(int domain_nr)
 	return NULL;
 }
 
+static void pcibios_irq_map_init(struct pci_controller *phb)
+{
+	phb->irq_count = PCI_NUM_INTX;
+
+	pr_debug("%pOF : interrupt map #%d\n", phb->dn, phb->irq_count);
+
+	phb->irq_map = kcalloc(phb->irq_count, sizeof(unsigned int),
+			       GFP_KERNEL);
+}
+
+static void pci_irq_map_register(struct pci_dev *pdev, unsigned int virq)
+{
+	struct pci_controller *phb = pci_bus_to_host(pdev->bus);
+	int i;
+
+	if (!phb->irq_map)
+		return;
+
+	for (i = 0; i < phb->irq_count; i++) {
+		/*
+		 * Look for an empty or an equivalent slot, as INTx
+		 * interrupts can be shared between adapters.
+		 */
+		if (phb->irq_map[i] == virq || !phb->irq_map[i]) {
+			phb->irq_map[i] = virq;
+			break;
+		}
+	}
+
+	if (i == phb->irq_count)
+		pr_err("PCI:%s all platform interrupts mapped\n",
+		       pci_name(pdev));
+}
+
+/*
+ * Clearing the mapped interrupts will also clear the underlying
+ * mappings of the ESB pages of the interrupts when under XIVE. It is
+ * a requirement of PowerVM to clear all memory mappings before
+ * removing a PHB.
+ */
+static void pci_irq_map_dispose(struct pci_bus *bus)
+{
+	struct pci_controller *phb = pci_bus_to_host(bus);
+	int i;
+
+	if (!phb->irq_map)
+		return;
+
+	pr_debug("PCI: Clearing interrupt mappings for PHB %04x:%02x...\n",
+		 pci_domain_nr(bus), bus->number);
+	for (i = 0; i < phb->irq_count; i++)
+		irq_dispose_mapping(phb->irq_map[i]);
+
+	kfree(phb->irq_map);
+}
+
+void pcibios_remove_bus(struct pci_bus *bus)
+{
+	pci_irq_map_dispose(bus);
+}
+EXPORT_SYMBOL_GPL(pcibios_remove_bus);
+
 /*
  * Reads the interrupt pin to determine if interrupt is use by card.
  * If the interrupt is used, then gets the interrupt line from the
@@ -401,6 +463,8 @@ static int pci_read_irq_line(struct pci_dev *pci_dev)
 
 	pci_dev->irq = virq;
 
+	/* Record all interrut mappings for later removal of a PHB */
+	pci_irq_map_register(pci_dev, virq);
 	return 0;
 }
 
@@ -1554,6 +1618,9 @@ void pcibios_scan_phb(struct pci_controller *hose)
 
 	pr_debug("PCI: Scanning PHB %pOF\n", node);
 
+	/* Allocate interrupt mappings array */
+	pcibios_irq_map_init(hose);
+
 	/* Get some IO space for the new PHB */
 	pcibios_setup_phb_io_space(hose);
 
-- 
2.25.4

[PATCH v2 2/2] powerpc/pci: unmap all interrupts when a PHB is removed

[Cédric Le Goater]

Some PCI adapters, like GPUs, use the "interrupt-map" property to
describe interrupt mappings other than the legacy INTx interrupts.
There can be more than 4 mappings.

To clear all interrupts when a PHB is removed, we need to increase the
'irq_map' array in which mappings are recorded. Compute the number of
interrupt mappings from the "interrupt-map" property and allocate a
bigger 'irq_map' array.

Signed-off-by: Cédric Le Goater <clg@kaod.org>
---
 arch/powerpc/kernel/pci-common.c | 49 +++++++++++++++++++++++++++++++-
 1 file changed, 48 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 515480a4bac6..deb831f0ae13 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -353,9 +353,56 @@ struct pci_controller *pci_find_controller_for_domain(int domain_nr)
 	return NULL;
 }
 
+/*
+ * Assumption is made on the interrupt parent. All interrupt-map
+ * entries are considered to have the same parent.
+ */
+static int pcibios_irq_map_count(struct pci_controller *phb)
+{
+	const __be32 *imap;
+	int imaplen;
+	struct device_node *parent;
+	u32 intsize, addrsize, parintsize, paraddrsize;
+
+	if (of_property_read_u32(phb->dn, "#interrupt-cells", &intsize))
+		return 0;
+	if (of_property_read_u32(phb->dn, "#address-cells", &addrsize))
+		return 0;
+
+	imap = of_get_property(phb->dn, "interrupt-map", &imaplen);
+	if (!imap) {
+		pr_debug("%pOF : no interrupt-map\n", phb->dn);
+		return 0;
+	}
+	imaplen /= sizeof(u32);
+	pr_debug("%pOF : imaplen=%d\n", phb->dn, imaplen);
+
+	if (imaplen < (addrsize + intsize + 1))
+		return 0;
+
+	imap += intsize + addrsize;
+	parent = of_find_node_by_phandle(be32_to_cpup(imap));
+	if (!parent) {
+		pr_debug("%pOF : no imap parent found !\n", phb->dn);
+		return 0;
+	}
+
+	if (of_property_read_u32(parent, "#interrupt-cells", &parintsize)) {
+		pr_debug("%pOF : parent lacks #interrupt-cells!\n", phb->dn);
+		return 0;
+	}
+
+	if (of_property_read_u32(parent, "#address-cells", &paraddrsize))
+		paraddrsize = 0;
+
+	return imaplen / (addrsize + intsize + 1 + paraddrsize + parintsize);
+}
+
 static void pcibios_irq_map_init(struct pci_controller *phb)
 {
-	phb->irq_count = PCI_NUM_INTX;
+	phb->irq_count = pcibios_irq_map_count(phb);
+	if (phb->irq_count < PCI_NUM_INTX)
+		phb->irq_count = PCI_NUM_INTX;
 
 	pr_debug("%pOF : interrupt map #%d\n", phb->dn, phb->irq_count);
 
-- 
2.25.4

Re: [PATCH v2 0/2] powerpc/pci: unmap interrupts when a PHB is removed

[Cédric Le Goater]

On 6/17/20 6:29 PM, Cédric Le Goater wrote:
> Hello,
> 
> When a passthrough IO adapter is removed from a pseries machine using
> hash MMU and the XIVE interrupt mode, the POWER hypervisor expects the
> guest OS to clear all page table entries related to the adapter. If
> some are still present, the RTAS call which isolates the PCI slot
> returns error 9001 "valid outstanding translations" and the removal of
> the IO adapter fails. This is because when the PHBs are scanned, Linux
> maps automatically some interrupts in the Linux interrupt number space
> but these are never removed.
> 
> To solve this problem, we introduce a PPC platform specific
> pcibios_remove_bus() routine which clears all interrupt mappings when
> the bus is removed. This also clears the associated page table entries
> of the ESB pages when using XIVE.
> 
> For this purpose, we record the logical interrupt numbers of the
> mapped interrupt under the PHB structure and let pcibios_remove_bus()
> do the clean up.
> 
> Tested on :
> 
>   - PowerNV with PCI, OpenCAPI, CAPI and GPU adapters. I don't know
>     how to inject a failure on a PHB but that would be a good test.

I found out that powering down the slot is enough :

	echo 0 > /sys/bus/pci/slots/<slot name>/power

The IRQ cleanup is done as expected on baremetal also.

Cheers,

C. 

>   - KVM P8+P9 guests with passthrough PCI adapters, but PHBs can not
>     be removed under QEMU/KVM.   
>   - PowerVM with passthrough PCI adapters (main target)
>   
> Thanks,
> 
> C.
> 
> Changes since v1:
> 
>  - extended the removal to interrupts other than the legacy INTx.
> 
> Cédric Le Goater (2):
>   powerpc/pci: unmap legacy INTx interrupts when a PHB is removed
>   powerpc/pci: unmap all interrupts when a PHB is removed
> 
>  arch/powerpc/include/asm/pci-bridge.h |   6 ++
>  arch/powerpc/kernel/pci-common.c      | 114 ++++++++++++++++++++++++++
>  2 files changed, 120 insertions(+)
> 

Re: [PATCH v2 2/2] powerpc/pci: unmap all interrupts when a PHB is removed

[Alexey Kardashevskiy]

On 18/06/2020 02:29, Cédric Le Goater wrote:
> Some PCI adapters, like GPUs, use the "interrupt-map" property to
> describe interrupt mappings other than the legacy INTx interrupts.
> There can be more than 4 mappings.
> 
> To clear all interrupts when a PHB is removed, we need to increase the
> 'irq_map' array in which mappings are recorded. Compute the number of
> interrupt mappings from the "interrupt-map" property and allocate a
> bigger 'irq_map' array.
> 
> Signed-off-by: Cédric Le Goater <clg@kaod.org>
> ---
>  arch/powerpc/kernel/pci-common.c | 49 +++++++++++++++++++++++++++++++-
>  1 file changed, 48 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
> index 515480a4bac6..deb831f0ae13 100644
> --- a/arch/powerpc/kernel/pci-common.c
> +++ b/arch/powerpc/kernel/pci-common.c
> @@ -353,9 +353,56 @@ struct pci_controller *pci_find_controller_for_domain(int domain_nr)
>  	return NULL;
>  }
>  
> +/*
> + * Assumption is made on the interrupt parent. All interrupt-map
> + * entries are considered to have the same parent.
> + */
> +static int pcibios_irq_map_count(struct pci_controller *phb)

I wonder if
int of_irq_count(struct device_node *dev)
could work here too. If it does not, then never mind.


Other than that, the only other comment is - merge this one into 1/2 as
1/2 alone won't properly fix the problem but it may look like that it does:

for phyp, the test machine just happens to have 4 entries in the map but
this is the phyp implementation detail;

for qemu, there are more but we only unregister 4 but kvm does not care
in general so it is ok which is also implementation detail;

and 2/2 just makes these details not matter. Thanks,



> +{
> +	const __be32 *imap;
> +	int imaplen;
> +	struct device_node *parent;
> +	u32 intsize, addrsize, parintsize, paraddrsize;
> +
> +	if (of_property_read_u32(phb->dn, "#interrupt-cells", &intsize))
> +		return 0;
> +	if (of_property_read_u32(phb->dn, "#address-cells", &addrsize))
> +		return 0;
> +
> +	imap = of_get_property(phb->dn, "interrupt-map", &imaplen);
> +	if (!imap) {
> +		pr_debug("%pOF : no interrupt-map\n", phb->dn);
> +		return 0;
> +	}
> +	imaplen /= sizeof(u32);
> +	pr_debug("%pOF : imaplen=%d\n", phb->dn, imaplen);
> +
> +	if (imaplen < (addrsize + intsize + 1))
> +		return 0;
> +
> +	imap += intsize + addrsize;
> +	parent = of_find_node_by_phandle(be32_to_cpup(imap));
> +	if (!parent) {
> +		pr_debug("%pOF : no imap parent found !\n", phb->dn);
> +		return 0;
> +	}
> +
> +	if (of_property_read_u32(parent, "#interrupt-cells", &parintsize)) {
> +		pr_debug("%pOF : parent lacks #interrupt-cells!\n", phb->dn);
> +		return 0;
> +	}
> +
> +	if (of_property_read_u32(parent, "#address-cells", &paraddrsize))
> +		paraddrsize = 0;
> +
> +	return imaplen / (addrsize + intsize + 1 + paraddrsize + parintsize);
> +}
> +
>  static void pcibios_irq_map_init(struct pci_controller *phb)
>  {
> -	phb->irq_count = PCI_NUM_INTX;
> +	phb->irq_count = pcibios_irq_map_count(phb);
> +	if (phb->irq_count < PCI_NUM_INTX)
> +		phb->irq_count = PCI_NUM_INTX;
>  
>  	pr_debug("%pOF : interrupt map #%d\n", phb->dn, phb->irq_count);
>  
> 

-- 
Alexey

Re: [PATCH v2 2/2] powerpc/pci: unmap all interrupts when a PHB is removed

[Cédric Le Goater]

On 8/7/20 8:01 AM, Alexey Kardashevskiy wrote:
> 
> 
> On 18/06/2020 02:29, Cédric Le Goater wrote:
>> Some PCI adapters, like GPUs, use the "interrupt-map" property to
>> describe interrupt mappings other than the legacy INTx interrupts.
>> There can be more than 4 mappings.
>>
>> To clear all interrupts when a PHB is removed, we need to increase the
>> 'irq_map' array in which mappings are recorded. Compute the number of
>> interrupt mappings from the "interrupt-map" property and allocate a
>> bigger 'irq_map' array.
>>
>> Signed-off-by: Cédric Le Goater <clg@kaod.org>
>> ---
>>  arch/powerpc/kernel/pci-common.c | 49 +++++++++++++++++++++++++++++++-
>>  1 file changed, 48 insertions(+), 1 deletion(-)
>>
>> diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
>> index 515480a4bac6..deb831f0ae13 100644
>> --- a/arch/powerpc/kernel/pci-common.c
>> +++ b/arch/powerpc/kernel/pci-common.c
>> @@ -353,9 +353,56 @@ struct pci_controller *pci_find_controller_for_domain(int domain_nr)
>>  	return NULL;
>>  }
>>  
>> +/*
>> + * Assumption is made on the interrupt parent. All interrupt-map
>> + * entries are considered to have the same parent.
>> + */
>> +static int pcibios_irq_map_count(struct pci_controller *phb)
> 
> I wonder if
> int of_irq_count(struct device_node *dev)
> could work here too. If it does not, then never mind.

I wished it would, but no.

> Other than that, the only other comment is - merge this one into 1/2 as
> 1/2 alone won't properly fix the problem but it may look like that it does:
> 
> for phyp, the test machine just happens to have 4 entries in the map but
> this is the phyp implementation detail;

yes
 
> for qemu, there are more but we only unregister 4 but kvm does not care
> in general so it is ok which is also implementation detail;
>
> and 2/2 just makes these details not matter. Thanks,

OK. It will ease backport. Sending a v2.

Thanks for the review Alexey !

C.
 
> 
> 
>> +{
>> +	const __be32 *imap;
>> +	int imaplen;
>> +	struct device_node *parent;
>> +	u32 intsize, addrsize, parintsize, paraddrsize;
>> +
>> +	if (of_property_read_u32(phb->dn, "#interrupt-cells", &intsize))
>> +		return 0;
>> +	if (of_property_read_u32(phb->dn, "#address-cells", &addrsize))
>> +		return 0;
>> +
>> +	imap = of_get_property(phb->dn, "interrupt-map", &imaplen);
>> +	if (!imap) {
>> +		pr_debug("%pOF : no interrupt-map\n", phb->dn);
>> +		return 0;
>> +	}
>> +	imaplen /= sizeof(u32);
>> +	pr_debug("%pOF : imaplen=%d\n", phb->dn, imaplen);
>> +
>> +	if (imaplen < (addrsize + intsize + 1))
>> +		return 0;
>> +
>> +	imap += intsize + addrsize;
>> +	parent = of_find_node_by_phandle(be32_to_cpup(imap));
>> +	if (!parent) {
>> +		pr_debug("%pOF : no imap parent found !\n", phb->dn);
>> +		return 0;
>> +	}
>> +
>> +	if (of_property_read_u32(parent, "#interrupt-cells", &parintsize)) {
>> +		pr_debug("%pOF : parent lacks #interrupt-cells!\n", phb->dn);
>> +		return 0;
>> +	}
>> +
>> +	if (of_property_read_u32(parent, "#address-cells", &paraddrsize))
>> +		paraddrsize = 0;
>> +
>> +	return imaplen / (addrsize + intsize + 1 + paraddrsize + parintsize);
>> +}
>> +
>>  static void pcibios_irq_map_init(struct pci_controller *phb)
>>  {
>> -	phb->irq_count = PCI_NUM_INTX;
>> +	phb->irq_count = pcibios_irq_map_count(phb);
>> +	if (phb->irq_count < PCI_NUM_INTX)
>> +		phb->irq_count = PCI_NUM_INTX;
>>  
>>  	pr_debug("%pOF : interrupt map #%d\n", phb->dn, phb->irq_count);
>>  
>>
>