* Re: [PATCH v3 rc] iommu: Skip PASID validation for devices without PASID capability
2025-05-05 21:15 [PATCH v3 rc] iommu: Skip PASID validation for devices without PASID capability Tushar Dave
@ 2025-05-06 9:58 ` Vasant Hegde
2025-05-06 18:08 ` Jason Gunthorpe
` (3 subsequent siblings)
4 siblings, 0 replies; 9+ messages in thread
From: Vasant Hegde @ 2025-05-06 9:58 UTC (permalink / raw)
To: Tushar Dave, joro, will, robin.murphy, kevin.tian, jgg, yi.l.liu,
iommu, linux-kernel
Cc: linux-pci, stable
On 5/6/2025 2:45 AM, Tushar Dave wrote:
> Generally PASID support requires ACS settings that usually create
> single device groups, but there are some niche cases where we can get
> multi-device groups and still have working PASID support. The primary
> issue is that PCI switches are not required to treat PASID tagged TLPs
> specially so appropriate ACS settings are required to route all TLPs to
> the host bridge if PASID is going to work properly.
>
> pci_enable_pasid() does check that each device that will use PASID has
> the proper ACS settings to achieve this routing.
>
> However, no-PASID devices can be combined with PASID capable devices
> within the same topology using non-uniform ACS settings. In this case
> the no-PASID devices may not have strict route to host ACS flags and
> end up being grouped with the PASID devices.
>
> This configuration fails to allow use of the PASID within the iommu
> core code which wrongly checks if the no-PASID device supports PASID.
>
> Fix this by ignoring no-PASID devices during the PASID validation. They
> will never issue a PASID TLP anyhow so they can be ignored.
>
> Fixes: c404f55c26fc ("iommu: Validate the PASID in iommu_attach_device_pasid()")
> Cc: stable@vger.kernel.org
> Signed-off-by: Tushar Dave <tdave@nvidia.com>
Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
-Vasant
> ---
>
> changes in v3:
> - addressed review comment from Vasant.
>
> drivers/iommu/iommu.c | 27 +++++++++++++++++++--------
> 1 file changed, 19 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
> index 60aed01e54f2..636fc68a8ec0 100644
> --- a/drivers/iommu/iommu.c
> +++ b/drivers/iommu/iommu.c
> @@ -3329,10 +3329,12 @@ static int __iommu_set_group_pasid(struct iommu_domain *domain,
> int ret;
>
> for_each_group_device(group, device) {
> - ret = domain->ops->set_dev_pasid(domain, device->dev,
> - pasid, NULL);
> - if (ret)
> - goto err_revert;
> + if (device->dev->iommu->max_pasids > 0) {
> + ret = domain->ops->set_dev_pasid(domain, device->dev,
> + pasid, NULL);
> + if (ret)
> + goto err_revert;
> + }
> }
>
> return 0;
> @@ -3342,7 +3344,8 @@ static int __iommu_set_group_pasid(struct iommu_domain *domain,
> for_each_group_device(group, device) {
> if (device == last_gdev)
> break;
> - iommu_remove_dev_pasid(device->dev, pasid, domain);
> + if (device->dev->iommu->max_pasids > 0)
> + iommu_remove_dev_pasid(device->dev, pasid, domain);
> }
> return ret;
> }
> @@ -3353,8 +3356,10 @@ static void __iommu_remove_group_pasid(struct iommu_group *group,
> {
> struct group_device *device;
>
> - for_each_group_device(group, device)
> - iommu_remove_dev_pasid(device->dev, pasid, domain);
> + for_each_group_device(group, device) {
> + if (device->dev->iommu->max_pasids > 0)
> + iommu_remove_dev_pasid(device->dev, pasid, domain);
> + }
> }
>
> /*
> @@ -3391,7 +3396,13 @@ int iommu_attach_device_pasid(struct iommu_domain *domain,
>
> mutex_lock(&group->mutex);
> for_each_group_device(group, device) {
> - if (pasid >= device->dev->iommu->max_pasids) {
> + /*
> + * Skip PASID validation for devices without PASID support
> + * (max_pasids = 0). These devices cannot issue transactions
> + * with PASID, so they don't affect group's PASID usage.
> + */
> + if ((device->dev->iommu->max_pasids > 0) &&
> + (pasid >= device->dev->iommu->max_pasids)) {
> ret = -EINVAL;
> goto out_unlock;
> }
^ permalink raw reply [flat|nested] 9+ messages in thread* Re: [PATCH v3 rc] iommu: Skip PASID validation for devices without PASID capability
2025-05-05 21:15 [PATCH v3 rc] iommu: Skip PASID validation for devices without PASID capability Tushar Dave
2025-05-06 9:58 ` Vasant Hegde
@ 2025-05-06 18:08 ` Jason Gunthorpe
2025-05-07 7:34 ` Tian, Kevin
` (2 subsequent siblings)
4 siblings, 0 replies; 9+ messages in thread
From: Jason Gunthorpe @ 2025-05-06 18:08 UTC (permalink / raw)
To: Tushar Dave
Cc: joro, will, robin.murphy, kevin.tian, yi.l.liu, iommu,
linux-kernel, linux-pci, stable
On Mon, May 05, 2025 at 02:15:24PM -0700, Tushar Dave wrote:
> Generally PASID support requires ACS settings that usually create
> single device groups, but there are some niche cases where we can get
> multi-device groups and still have working PASID support. The primary
> issue is that PCI switches are not required to treat PASID tagged TLPs
> specially so appropriate ACS settings are required to route all TLPs to
> the host bridge if PASID is going to work properly.
>
> pci_enable_pasid() does check that each device that will use PASID has
> the proper ACS settings to achieve this routing.
>
> However, no-PASID devices can be combined with PASID capable devices
> within the same topology using non-uniform ACS settings. In this case
> the no-PASID devices may not have strict route to host ACS flags and
> end up being grouped with the PASID devices.
>
> This configuration fails to allow use of the PASID within the iommu
> core code which wrongly checks if the no-PASID device supports PASID.
>
> Fix this by ignoring no-PASID devices during the PASID validation. They
> will never issue a PASID TLP anyhow so they can be ignored.
>
> Fixes: c404f55c26fc ("iommu: Validate the PASID in iommu_attach_device_pasid()")
> Cc: stable@vger.kernel.org
> Signed-off-by: Tushar Dave <tdave@nvidia.com>
> ---
>
> changes in v3:
> - addressed review comment from Vasant.
>
> drivers/iommu/iommu.c | 27 +++++++++++++++++++--------
> 1 file changed, 19 insertions(+), 8 deletions(-)
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Jason
^ permalink raw reply [flat|nested] 9+ messages in thread* RE: [PATCH v3 rc] iommu: Skip PASID validation for devices without PASID capability
2025-05-05 21:15 [PATCH v3 rc] iommu: Skip PASID validation for devices without PASID capability Tushar Dave
2025-05-06 9:58 ` Vasant Hegde
2025-05-06 18:08 ` Jason Gunthorpe
@ 2025-05-07 7:34 ` Tian, Kevin
2025-05-07 13:59 ` Yi Liu
2025-05-16 6:45 ` Joerg Roedel
4 siblings, 0 replies; 9+ messages in thread
From: Tian, Kevin @ 2025-05-07 7:34 UTC (permalink / raw)
To: Dave, Tushar, joro@8bytes.org, will@kernel.org,
robin.murphy@arm.com, jgg@nvidia.com, Liu, Yi L,
iommu@lists.linux.dev, linux-kernel@vger.kernel.org
Cc: linux-pci@vger.kernel.org, stable@vger.kernel.org
> From: Tushar Dave <tdave@nvidia.com>
> Sent: Tuesday, May 6, 2025 5:15 AM
>
> Generally PASID support requires ACS settings that usually create
> single device groups, but there are some niche cases where we can get
> multi-device groups and still have working PASID support. The primary
> issue is that PCI switches are not required to treat PASID tagged TLPs
> specially so appropriate ACS settings are required to route all TLPs to
> the host bridge if PASID is going to work properly.
>
> pci_enable_pasid() does check that each device that will use PASID has
> the proper ACS settings to achieve this routing.
>
> However, no-PASID devices can be combined with PASID capable devices
> within the same topology using non-uniform ACS settings. In this case
> the no-PASID devices may not have strict route to host ACS flags and
> end up being grouped with the PASID devices.
>
> This configuration fails to allow use of the PASID within the iommu
> core code which wrongly checks if the no-PASID device supports PASID.
>
> Fix this by ignoring no-PASID devices during the PASID validation. They
> will never issue a PASID TLP anyhow so they can be ignored.
>
> Fixes: c404f55c26fc ("iommu: Validate the PASID in
> iommu_attach_device_pasid()")
> Cc: stable@vger.kernel.org
> Signed-off-by: Tushar Dave <tdave@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
^ permalink raw reply [flat|nested] 9+ messages in thread* Re: [PATCH v3 rc] iommu: Skip PASID validation for devices without PASID capability
2025-05-05 21:15 [PATCH v3 rc] iommu: Skip PASID validation for devices without PASID capability Tushar Dave
` (2 preceding siblings ...)
2025-05-07 7:34 ` Tian, Kevin
@ 2025-05-07 13:59 ` Yi Liu
2025-05-08 0:21 ` Tushar Dave
2025-05-16 6:45 ` Joerg Roedel
4 siblings, 1 reply; 9+ messages in thread
From: Yi Liu @ 2025-05-07 13:59 UTC (permalink / raw)
To: Tushar Dave, joro, will, robin.murphy, kevin.tian, jgg, iommu,
linux-kernel
Cc: linux-pci, stable
On 2025/5/6 05:15, Tushar Dave wrote:
> Generally PASID support requires ACS settings that usually create
> single device groups, but there are some niche cases where we can get
> multi-device groups and still have working PASID support. The primary
> issue is that PCI switches are not required to treat PASID tagged TLPs
> specially so appropriate ACS settings are required to route all TLPs to
> the host bridge if PASID is going to work properly.
>
> pci_enable_pasid() does check that each device that will use PASID has
> the proper ACS settings to achieve this routing.
>
> However, no-PASID devices can be combined with PASID capable devices
> within the same topology using non-uniform ACS settings. In this case
> the no-PASID devices may not have strict route to host ACS flags and
> end up being grouped with the PASID devices.
>
> This configuration fails to allow use of the PASID within the iommu
> core code which wrongly checks if the no-PASID device supports PASID.
>
> Fix this by ignoring no-PASID devices during the PASID validation. They
> will never issue a PASID TLP anyhow so they can be ignored.
>
> Fixes: c404f55c26fc ("iommu: Validate the PASID in iommu_attach_device_pasid()")
> Cc: stable@vger.kernel.org
> Signed-off-by: Tushar Dave <tdave@nvidia.com>
> ---
>
> changes in v3:
> - addressed review comment from Vasant.
>
> drivers/iommu/iommu.c | 27 +++++++++++++++++++--------
> 1 file changed, 19 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
> index 60aed01e54f2..636fc68a8ec0 100644
> --- a/drivers/iommu/iommu.c
> +++ b/drivers/iommu/iommu.c
> @@ -3329,10 +3329,12 @@ static int __iommu_set_group_pasid(struct iommu_domain *domain,
> int ret;
>
> for_each_group_device(group, device) {
> - ret = domain->ops->set_dev_pasid(domain, device->dev,
> - pasid, NULL);
> - if (ret)
> - goto err_revert;
> + if (device->dev->iommu->max_pasids > 0) {
> + ret = domain->ops->set_dev_pasid(domain, device->dev,
> + pasid, NULL);
> + if (ret)
> + goto err_revert;
> + }
> }
>
> return 0;
> @@ -3342,7 +3344,8 @@ static int __iommu_set_group_pasid(struct iommu_domain *domain,
> for_each_group_device(group, device) {
> if (device == last_gdev)
> break;
> - iommu_remove_dev_pasid(device->dev, pasid, domain);
> + if (device->dev->iommu->max_pasids > 0)
> + iommu_remove_dev_pasid(device->dev, pasid, domain);
Reviewed-by: Yi Liu <yi.l.liu@intel.com>
with a nit. would it save some loc by adding the max_pasids check in
iommu_remove_dev_pasid()?
> }
> return ret;
> }
> @@ -3353,8 +3356,10 @@ static void __iommu_remove_group_pasid(struct iommu_group *group,
> {
> struct group_device *device;
>
> - for_each_group_device(group, device)
> - iommu_remove_dev_pasid(device->dev, pasid, domain);
> + for_each_group_device(group, device) {
> + if (device->dev->iommu->max_pasids > 0)
> + iommu_remove_dev_pasid(device->dev, pasid, domain);
> + }
> }
>
> /*
> @@ -3391,7 +3396,13 @@ int iommu_attach_device_pasid(struct iommu_domain *domain,
>
> mutex_lock(&group->mutex);
> for_each_group_device(group, device) {
> - if (pasid >= device->dev->iommu->max_pasids) {
> + /*
> + * Skip PASID validation for devices without PASID support
> + * (max_pasids = 0). These devices cannot issue transactions
> + * with PASID, so they don't affect group's PASID usage.
> + */
> + if ((device->dev->iommu->max_pasids > 0) &&
> + (pasid >= device->dev->iommu->max_pasids)) {
> ret = -EINVAL;
> goto out_unlock;
> }
--
Regards,
Yi Liu
^ permalink raw reply [flat|nested] 9+ messages in thread* Re: [PATCH v3 rc] iommu: Skip PASID validation for devices without PASID capability
2025-05-07 13:59 ` Yi Liu
@ 2025-05-08 0:21 ` Tushar Dave
2025-05-14 1:51 ` Tushar Dave
0 siblings, 1 reply; 9+ messages in thread
From: Tushar Dave @ 2025-05-08 0:21 UTC (permalink / raw)
To: Yi Liu, joro, will, robin.murphy, kevin.tian, jgg, iommu,
linux-kernel
Cc: linux-pci, stable
On 5/7/25 06:59, Yi Liu wrote:
>
> On 2025/5/6 05:15, Tushar Dave wrote:
>> Generally PASID support requires ACS settings that usually create
>> single device groups, but there are some niche cases where we can get
>> multi-device groups and still have working PASID support. The primary
>> issue is that PCI switches are not required to treat PASID tagged TLPs
>> specially so appropriate ACS settings are required to route all TLPs to
>> the host bridge if PASID is going to work properly.
>>
>> pci_enable_pasid() does check that each device that will use PASID has
>> the proper ACS settings to achieve this routing.
>>
>> However, no-PASID devices can be combined with PASID capable devices
>> within the same topology using non-uniform ACS settings. In this case
>> the no-PASID devices may not have strict route to host ACS flags and
>> end up being grouped with the PASID devices.
>>
>> This configuration fails to allow use of the PASID within the iommu
>> core code which wrongly checks if the no-PASID device supports PASID.
>>
>> Fix this by ignoring no-PASID devices during the PASID validation. They
>> will never issue a PASID TLP anyhow so they can be ignored.
>>
>> Fixes: c404f55c26fc ("iommu: Validate the PASID in iommu_attach_device_pasid()")
>> Cc: stable@vger.kernel.org
>> Signed-off-by: Tushar Dave <tdave@nvidia.com>
>> ---
>>
>> changes in v3:
>> - addressed review comment from Vasant.
>>
>> drivers/iommu/iommu.c | 27 +++++++++++++++++++--------
>> 1 file changed, 19 insertions(+), 8 deletions(-)
>>
>> diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
>> index 60aed01e54f2..636fc68a8ec0 100644
>> --- a/drivers/iommu/iommu.c
>> +++ b/drivers/iommu/iommu.c
>> @@ -3329,10 +3329,12 @@ static int __iommu_set_group_pasid(struct iommu_domain
>> *domain,
>> int ret;
>> for_each_group_device(group, device) {
>> - ret = domain->ops->set_dev_pasid(domain, device->dev,
>> - pasid, NULL);
>> - if (ret)
>> - goto err_revert;
>> + if (device->dev->iommu->max_pasids > 0) {
>> + ret = domain->ops->set_dev_pasid(domain, device->dev,
>> + pasid, NULL);
>> + if (ret)
>> + goto err_revert;
>> + }
>> }
>> return 0;
>> @@ -3342,7 +3344,8 @@ static int __iommu_set_group_pasid(struct iommu_domain
>> *domain,
>> for_each_group_device(group, device) {
>> if (device == last_gdev)
>> break;
>> - iommu_remove_dev_pasid(device->dev, pasid, domain);
>> + if (device->dev->iommu->max_pasids > 0)
>> + iommu_remove_dev_pasid(device->dev, pasid, domain);
>
> Reviewed-by: Yi Liu <yi.l.liu@intel.com>
>
> with a nit. would it save some loc by adding the max_pasids check in
> iommu_remove_dev_pasid()?
With current code:
drivers/iommu/iommu.c | 27 +++++++++++++++++++--------
1 file changed, 19 insertions(+), 8 deletions(-)
If I move the pasid check in iommu_remove_dev_pasid(), it would be:
drivers/iommu/iommu.c | 23 ++++++++++++++++-------
1 file changed, 16 insertions(+), 7 deletions(-)
e.g.
@@ -3318,8 +3318,9 @@ static void iommu_remove_dev_pasid(struct device *dev,
ioasid_t pasid,
const struct iommu_ops *ops = dev_iommu_ops(dev);
struct iommu_domain *blocked_domain = ops->blocked_domain;
- WARN_ON(blocked_domain->ops->set_dev_pasid(blocked_domain,
- dev, pasid, domain));
+ if (dev->iommu->max_pasids > 0)
+ WARN_ON(blocked_domain->ops->set_dev_pasid(blocked_domain,
+ dev, pasid, domain));
}
static int __iommu_set_group_pasid(struct iommu_domain *domain,
@@ -3329,10 +3330,12 @@ static int __iommu_set_group_pasid(struct iommu_domain
*domain,
int ret;
for_each_group_device(group, device) {
- ret = domain->ops->set_dev_pasid(domain, device->dev,
- pasid, NULL);
- if (ret)
- goto err_revert;
+ if (device->dev->iommu->max_pasids > 0) {
+ ret = domain->ops->set_dev_pasid(domain, device->dev,
+ pasid, NULL);
+ if (ret)
+ goto err_revert;
+ }
}
return 0;
Last hunk remain same as before for iommu_attach_device_pasid()
Let me know.
-Tushar
>
>
>> }
>> return ret;
>> }
>> @@ -3353,8 +3356,10 @@ static void __iommu_remove_group_pasid(struct
>> iommu_group *group,
>> {
>> struct group_device *device;
>> - for_each_group_device(group, device)
>> - iommu_remove_dev_pasid(device->dev, pasid, domain);
>> + for_each_group_device(group, device) {
>> + if (device->dev->iommu->max_pasids > 0)
>> + iommu_remove_dev_pasid(device->dev, pasid, domain);
>> + }
>> }
>> /*
>> @@ -3391,7 +3396,13 @@ int iommu_attach_device_pasid(struct iommu_domain *domain,
>> mutex_lock(&group->mutex);
>> for_each_group_device(group, device) {
>> - if (pasid >= device->dev->iommu->max_pasids) {
>> + /*
>> + * Skip PASID validation for devices without PASID support
>> + * (max_pasids = 0). These devices cannot issue transactions
>> + * with PASID, so they don't affect group's PASID usage.
>> + */
>> + if ((device->dev->iommu->max_pasids > 0) &&
>> + (pasid >= device->dev->iommu->max_pasids)) {
>> ret = -EINVAL;
>> goto out_unlock;
>> }
>
^ permalink raw reply [flat|nested] 9+ messages in thread* Re: [PATCH v3 rc] iommu: Skip PASID validation for devices without PASID capability
2025-05-08 0:21 ` Tushar Dave
@ 2025-05-14 1:51 ` Tushar Dave
0 siblings, 0 replies; 9+ messages in thread
From: Tushar Dave @ 2025-05-14 1:51 UTC (permalink / raw)
To: Yi Liu, joro@8bytes.org, will@kernel.org, robin.murphy@arm.com,
kevin.tian@intel.com, Jason Gunthorpe, iommu@lists.linux.dev,
linux-kernel@vger.kernel.org
Cc: linux-pci@vger.kernel.org, stable@vger.kernel.org
On 5/7/25 17:21, Tushar Dave wrote:
>
>
> On 5/7/25 06:59, Yi Liu wrote:
>>
>> On 2025/5/6 05:15, Tushar Dave wrote:
>>> Generally PASID support requires ACS settings that usually create
>>> single device groups, but there are some niche cases where we can get
>>> multi-device groups and still have working PASID support. The primary
>>> issue is that PCI switches are not required to treat PASID tagged TLPs
>>> specially so appropriate ACS settings are required to route all TLPs to
>>> the host bridge if PASID is going to work properly.
>>>
>>> pci_enable_pasid() does check that each device that will use PASID has
>>> the proper ACS settings to achieve this routing.
>>>
>>> However, no-PASID devices can be combined with PASID capable devices
>>> within the same topology using non-uniform ACS settings. In this case
>>> the no-PASID devices may not have strict route to host ACS flags and
>>> end up being grouped with the PASID devices.
>>>
>>> This configuration fails to allow use of the PASID within the iommu
>>> core code which wrongly checks if the no-PASID device supports PASID.
>>>
>>> Fix this by ignoring no-PASID devices during the PASID validation. They
>>> will never issue a PASID TLP anyhow so they can be ignored.
>>>
>>> Fixes: c404f55c26fc ("iommu: Validate the PASID in iommu_attach_device_pasid()")
>>> Cc: stable@vger.kernel.org
>>> Signed-off-by: Tushar Dave <tdave@nvidia.com>
>>> ---
>>>
>>> changes in v3:
>>> - addressed review comment from Vasant.
>>>
>>> drivers/iommu/iommu.c | 27 +++++++++++++++++++--------
>>> 1 file changed, 19 insertions(+), 8 deletions(-)
>>>
>>> diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
>>> index 60aed01e54f2..636fc68a8ec0 100644
>>> --- a/drivers/iommu/iommu.c
>>> +++ b/drivers/iommu/iommu.c
>>> @@ -3329,10 +3329,12 @@ static int __iommu_set_group_pasid(struct iommu_domain
>>> *domain,
>>> int ret;
>>> for_each_group_device(group, device) {
>>> - ret = domain->ops->set_dev_pasid(domain, device->dev,
>>> - pasid, NULL);
>>> - if (ret)
>>> - goto err_revert;
>>> + if (device->dev->iommu->max_pasids > 0) {
>>> + ret = domain->ops->set_dev_pasid(domain, device->dev,
>>> + pasid, NULL);
>>> + if (ret)
>>> + goto err_revert;
>>> + }
>>> }
>>> return 0;
>>> @@ -3342,7 +3344,8 @@ static int __iommu_set_group_pasid(struct iommu_domain
>>> *domain,
>>> for_each_group_device(group, device) {
>>> if (device == last_gdev)
>>> break;
>>> - iommu_remove_dev_pasid(device->dev, pasid, domain);
>>> + if (device->dev->iommu->max_pasids > 0)
>>> + iommu_remove_dev_pasid(device->dev, pasid, domain);
>>
>> Reviewed-by: Yi Liu <yi.l.liu@intel.com>
>>
>> with a nit. would it save some loc by adding the max_pasids check in
>> iommu_remove_dev_pasid()?
>
> With current code:
>
> drivers/iommu/iommu.c | 27 +++++++++++++++++++--------
> 1 file changed, 19 insertions(+), 8 deletions(-)
>
>
> If I move the pasid check in iommu_remove_dev_pasid(), it would be:
>
> drivers/iommu/iommu.c | 23 ++++++++++++++++-------
> 1 file changed, 16 insertions(+), 7 deletions(-)
>
Yi Liu,
Should I send v4 with the change below or we are good with v3?
-Tushar
>
> e.g.
>
> @@ -3318,8 +3318,9 @@ static void iommu_remove_dev_pasid(struct device *dev,
> ioasid_t pasid,
> const struct iommu_ops *ops = dev_iommu_ops(dev);
> struct iommu_domain *blocked_domain = ops->blocked_domain;
>
> - WARN_ON(blocked_domain->ops->set_dev_pasid(blocked_domain,
> - dev, pasid, domain));
> + if (dev->iommu->max_pasids > 0)
> + WARN_ON(blocked_domain->ops->set_dev_pasid(blocked_domain,
> + dev, pasid, domain));
> }
>
> static int __iommu_set_group_pasid(struct iommu_domain *domain,
> @@ -3329,10 +3330,12 @@ static int __iommu_set_group_pasid(struct iommu_domain
> *domain,
> int ret;
>
> for_each_group_device(group, device) {
> - ret = domain->ops->set_dev_pasid(domain, device->dev,
> - pasid, NULL);
> - if (ret)
> - goto err_revert;
> + if (device->dev->iommu->max_pasids > 0) {
> + ret = domain->ops->set_dev_pasid(domain, device->dev,
> + pasid, NULL);
> + if (ret)
> + goto err_revert;
> + }
> }
>
> return 0;
>
> Last hunk remain same as before for iommu_attach_device_pasid()
>
>
> Let me know.
>
> -Tushar
>
>
>>
>>
>>> }
>>> return ret;
>>> }
>>> @@ -3353,8 +3356,10 @@ static void __iommu_remove_group_pasid(struct
>>> iommu_group *group,
>>> {
>>> struct group_device *device;
>>> - for_each_group_device(group, device)
>>> - iommu_remove_dev_pasid(device->dev, pasid, domain);
>>> + for_each_group_device(group, device) {
>>> + if (device->dev->iommu->max_pasids > 0)
>>> + iommu_remove_dev_pasid(device->dev, pasid, domain);
>>> + }
>>> }
>>> /*
>>> @@ -3391,7 +3396,13 @@ int iommu_attach_device_pasid(struct iommu_domain *domain,
>>> mutex_lock(&group->mutex);
>>> for_each_group_device(group, device) {
>>> - if (pasid >= device->dev->iommu->max_pasids) {
>>> + /*
>>> + * Skip PASID validation for devices without PASID support
>>> + * (max_pasids = 0). These devices cannot issue transactions
>>> + * with PASID, so they don't affect group's PASID usage.
>>> + */
>>> + if ((device->dev->iommu->max_pasids > 0) &&
>>> + (pasid >= device->dev->iommu->max_pasids)) {
>>> ret = -EINVAL;
>>> goto out_unlock;
>>> }
>>
>
^ permalink raw reply [flat|nested] 9+ messages in thread
* Re: [PATCH v3 rc] iommu: Skip PASID validation for devices without PASID capability
2025-05-05 21:15 [PATCH v3 rc] iommu: Skip PASID validation for devices without PASID capability Tushar Dave
` (3 preceding siblings ...)
2025-05-07 13:59 ` Yi Liu
@ 2025-05-16 6:45 ` Joerg Roedel
2025-05-16 23:27 ` Tushar Dave
4 siblings, 1 reply; 9+ messages in thread
From: Joerg Roedel @ 2025-05-16 6:45 UTC (permalink / raw)
To: Tushar Dave
Cc: will, robin.murphy, kevin.tian, jgg, yi.l.liu, iommu,
linux-kernel, linux-pci, stable
Hi Tushar,
On Mon, May 05, 2025 at 02:15:24PM -0700, Tushar Dave wrote:
> drivers/iommu/iommu.c | 27 +++++++++++++++++++--------
> 1 file changed, 19 insertions(+), 8 deletions(-)
This doesn't apply to v6.15-rc6, can you please rebase and send a new
version?
Thanks,
Joerg
>
^ permalink raw reply [flat|nested] 9+ messages in thread* Re: [PATCH v3 rc] iommu: Skip PASID validation for devices without PASID capability
2025-05-16 6:45 ` Joerg Roedel
@ 2025-05-16 23:27 ` Tushar Dave
0 siblings, 0 replies; 9+ messages in thread
From: Tushar Dave @ 2025-05-16 23:27 UTC (permalink / raw)
To: Joerg Roedel
Cc: will, robin.murphy, kevin.tian, jgg, yi.l.liu, iommu,
linux-kernel, linux-pci, stable
On 5/15/25 23:45, Joerg Roedel wrote:
> Hi Tushar,
>
> On Mon, May 05, 2025 at 02:15:24PM -0700, Tushar Dave wrote:
>> drivers/iommu/iommu.c | 27 +++++++++++++++++++--------
>> 1 file changed, 19 insertions(+), 8 deletions(-)
>
> This doesn't apply to v6.15-rc6, can you please rebase and send a new
> version?
Joerg,
Yes, I will rebase and send v4.
Thanks.
-Tushar
>
> Thanks,
>
> Joerg
>>
^ permalink raw reply [flat|nested] 9+ messages in thread