Subject: [PATCH v2 1/1] PCI/IOV: Fix incorrect cfg_size for VF > 0

From: Kuppuswamy Sathyanarayanan <[email protected]>

Commit 975bb8b4dc93 ("PCI/IOV: Use VF0 cached config space size for
other VFs") calculates and caches the cfg_size for VF0 device before
initializing the pcie_cap of the device which results in using incorrect
cfg_size for all VF devices > 0. So set pcie_cap of the device before
calculating the cfg_size of VF0 device.

Fixes: 975bb8b4dc93 ("PCI/IOV: Use VF0 cached config space size for
other VFs")
Cc: Ashok Raj <[email protected]>
Suggested-by: Mike Campin <[email protected]>
Signed-off-by: Kuppuswamy Sathyanarayanan <[email protected]>
---

Changes since v1:
* Fixed a typo in commit message.

drivers/pci/iov.c | 1 +
1 file changed, 1 insertion(+)

diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 3aa115ed3a65..2869011c0e35 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -160,6 +160,7 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id)
virtfn->device = iov->vf_device;
virtfn->is_virtfn = 1;
virtfn->physfn = pci_dev_get(dev);
+ virtfn->pcie_cap = pci_find_capability(virtfn, PCI_CAP_ID_EXP);

if (id == 0)
pci_read_vf_config_common(virtfn);
--
2.21.0


2019-06-12 18:18:24

by Myron Stowe

[permalink] [raw]
Subject: Re: [PATCH v2 1/1] PCI/IOV: Fix incorrect cfg_size for VF > 0

This looks to basically be a duplicate of what Alex Williamson posted
8 days ago: https://lore.kernel.org/linux-pci/[email protected]/
Alex says Hao Zheng had a similar patch as well.

On Wed, Jun 12, 2019 at 12:08 PM
<[email protected]> wrote:
>
> From: Kuppuswamy Sathyanarayanan <[email protected]>
>
> Commit 975bb8b4dc93 ("PCI/IOV: Use VF0 cached config space size for
> other VFs") calculates and caches the cfg_size for VF0 device before
> initializing the pcie_cap of the device which results in using incorrect
> cfg_size for all VF devices > 0. So set pcie_cap of the device before
> calculating the cfg_size of VF0 device.
>
> Fixes: 975bb8b4dc93 ("PCI/IOV: Use VF0 cached config space size for
> other VFs")
> Cc: Ashok Raj <[email protected]>
> Suggested-by: Mike Campin <[email protected]>
> Signed-off-by: Kuppuswamy Sathyanarayanan <[email protected]>
> ---
>
> Changes since v1:
> * Fixed a typo in commit message.
>
> drivers/pci/iov.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
> index 3aa115ed3a65..2869011c0e35 100644
> --- a/drivers/pci/iov.c
> +++ b/drivers/pci/iov.c
> @@ -160,6 +160,7 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id)
> virtfn->device = iov->vf_device;
> virtfn->is_virtfn = 1;
> virtfn->physfn = pci_dev_get(dev);
> + virtfn->pcie_cap = pci_find_capability(virtfn, PCI_CAP_ID_EXP);
>
> if (id == 0)
> pci_read_vf_config_common(virtfn);
> --
> 2.21.0
>

2019-06-12 18:19:39

by Alex Williamson

[permalink] [raw]
Subject: Re: [PATCH v2 1/1] PCI/IOV: Fix incorrect cfg_size for VF > 0

On Wed, 12 Jun 2019 10:06:47 -0700
[email protected] wrote:

> From: Kuppuswamy Sathyanarayanan <[email protected]>
>
> Commit 975bb8b4dc93 ("PCI/IOV: Use VF0 cached config space size for
> other VFs") calculates and caches the cfg_size for VF0 device before
> initializing the pcie_cap of the device which results in using incorrect
> cfg_size for all VF devices > 0. So set pcie_cap of the device before
> calculating the cfg_size of VF0 device.
>
> Fixes: 975bb8b4dc93 ("PCI/IOV: Use VF0 cached config space size for
> other VFs")
> Cc: Ashok Raj <[email protected]>
> Suggested-by: Mike Campin <[email protected]>
> Signed-off-by: Kuppuswamy Sathyanarayanan <[email protected]>
> ---
>
> Changes since v1:
> * Fixed a typo in commit message.
>
> drivers/pci/iov.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
> index 3aa115ed3a65..2869011c0e35 100644
> --- a/drivers/pci/iov.c
> +++ b/drivers/pci/iov.c
> @@ -160,6 +160,7 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id)
> virtfn->device = iov->vf_device;
> virtfn->is_virtfn = 1;
> virtfn->physfn = pci_dev_get(dev);
> + virtfn->pcie_cap = pci_find_capability(virtfn, PCI_CAP_ID_EXP);
>
> if (id == 0)
> pci_read_vf_config_common(virtfn);

Why not re-order until after we've setup pcie_cap?

https://lore.kernel.org/linux-pci/[email protected]/T/#

Thanks,
Alex

Subject: Re: [PATCH v2 1/1] PCI/IOV: Fix incorrect cfg_size for VF > 0


On 6/12/19 11:19 AM, Alex Williamson wrote:
> On Wed, 12 Jun 2019 10:06:47 -0700
> [email protected] wrote:
>
>> From: Kuppuswamy Sathyanarayanan <[email protected]>
>>
>> Commit 975bb8b4dc93 ("PCI/IOV: Use VF0 cached config space size for
>> other VFs") calculates and caches the cfg_size for VF0 device before
>> initializing the pcie_cap of the device which results in using incorrect
>> cfg_size for all VF devices > 0. So set pcie_cap of the device before
>> calculating the cfg_size of VF0 device.
>>
>> Fixes: 975bb8b4dc93 ("PCI/IOV: Use VF0 cached config space size for
>> other VFs")
>> Cc: Ashok Raj <[email protected]>
>> Suggested-by: Mike Campin <[email protected]>
>> Signed-off-by: Kuppuswamy Sathyanarayanan <[email protected]>
>> ---
>>
>> Changes since v1:
>> * Fixed a typo in commit message.
>>
>> drivers/pci/iov.c | 1 +
>> 1 file changed, 1 insertion(+)
>>
>> diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
>> index 3aa115ed3a65..2869011c0e35 100644
>> --- a/drivers/pci/iov.c
>> +++ b/drivers/pci/iov.c
>> @@ -160,6 +160,7 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id)
>> virtfn->device = iov->vf_device;
>> virtfn->is_virtfn = 1;
>> virtfn->physfn = pci_dev_get(dev);
>> + virtfn->pcie_cap = pci_find_capability(virtfn, PCI_CAP_ID_EXP);
>>
>> if (id == 0)
>> pci_read_vf_config_common(virtfn);
> Why not re-order until after we've setup pcie_cap?
>
> https://lore.kernel.org/linux-pci/[email protected]/T/#

pci_read_vf_config_common() also caches values for properties like
class, hdr_type, susbsystem_vendor/device. These values are read/used in
pci_setup_device(). So if we can use cached values in
pci_setup_device(), we don't have to read them from registers twice for
each device.

>
> Thanks,
> Alex
>
--
Sathyanarayanan Kuppuswamy
Linux kernel developer

2019-06-12 19:00:18

by Alex Williamson

[permalink] [raw]
Subject: Re: [PATCH v2 1/1] PCI/IOV: Fix incorrect cfg_size for VF > 0

On Wed, 12 Jun 2019 11:41:36 -0700
sathyanarayanan kuppuswamy <[email protected]>
wrote:

> On 6/12/19 11:19 AM, Alex Williamson wrote:
> > On Wed, 12 Jun 2019 10:06:47 -0700
> > [email protected] wrote:
> >
> >> From: Kuppuswamy Sathyanarayanan <[email protected]>
> >>
> >> Commit 975bb8b4dc93 ("PCI/IOV: Use VF0 cached config space size for
> >> other VFs") calculates and caches the cfg_size for VF0 device before
> >> initializing the pcie_cap of the device which results in using incorrect
> >> cfg_size for all VF devices > 0. So set pcie_cap of the device before
> >> calculating the cfg_size of VF0 device.
> >>
> >> Fixes: 975bb8b4dc93 ("PCI/IOV: Use VF0 cached config space size for
> >> other VFs")
> >> Cc: Ashok Raj <[email protected]>
> >> Suggested-by: Mike Campin <[email protected]>
> >> Signed-off-by: Kuppuswamy Sathyanarayanan <[email protected]>
> >> ---
> >>
> >> Changes since v1:
> >> * Fixed a typo in commit message.
> >>
> >> drivers/pci/iov.c | 1 +
> >> 1 file changed, 1 insertion(+)
> >>
> >> diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
> >> index 3aa115ed3a65..2869011c0e35 100644
> >> --- a/drivers/pci/iov.c
> >> +++ b/drivers/pci/iov.c
> >> @@ -160,6 +160,7 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id)
> >> virtfn->device = iov->vf_device;
> >> virtfn->is_virtfn = 1;
> >> virtfn->physfn = pci_dev_get(dev);
> >> + virtfn->pcie_cap = pci_find_capability(virtfn, PCI_CAP_ID_EXP);
> >>
> >> if (id == 0)
> >> pci_read_vf_config_common(virtfn);
> > Why not re-order until after we've setup pcie_cap?
> >
> > https://lore.kernel.org/linux-pci/[email protected]/T/#
>
> pci_read_vf_config_common() also caches values for properties like
> class, hdr_type, susbsystem_vendor/device. These values are read/used in
> pci_setup_device(). So if we can use cached values in
> pci_setup_device(), we don't have to read them from registers twice for
> each device.

Sorry, I missed that dependency, a bit too subtle. It's still pretty
ugly that pci_setup_device()->set_pcie_port_type() is the canonical
location for setting pcie_cap and now we need to kludge it earlier.
What about the question in the self follow-up to my patch in the link
above, can we simply assume 4K config space on a VF? Thanks,

Alex

2019-06-12 19:03:28

by Ashok Raj

[permalink] [raw]
Subject: Re: [PATCH v2 1/1] PCI/IOV: Fix incorrect cfg_size for VF > 0

On Wed, Jun 12, 2019 at 12:58:17PM -0600, Alex Williamson wrote:
> On Wed, 12 Jun 2019 11:41:36 -0700
> sathyanarayanan kuppuswamy <[email protected]>
> wrote:
>
> > On 6/12/19 11:19 AM, Alex Williamson wrote:
> > > On Wed, 12 Jun 2019 10:06:47 -0700
> > > [email protected] wrote:
> > >
> > >> From: Kuppuswamy Sathyanarayanan <[email protected]>
> > >>
> > >> Commit 975bb8b4dc93 ("PCI/IOV: Use VF0 cached config space size for
> > >> other VFs") calculates and caches the cfg_size for VF0 device before
> > >> initializing the pcie_cap of the device which results in using incorrect
> > >> cfg_size for all VF devices > 0. So set pcie_cap of the device before
> > >> calculating the cfg_size of VF0 device.
> > >>
> > >> Fixes: 975bb8b4dc93 ("PCI/IOV: Use VF0 cached config space size for
> > >> other VFs")
> > >> Cc: Ashok Raj <[email protected]>
> > >> Suggested-by: Mike Campin <[email protected]>
> > >> Signed-off-by: Kuppuswamy Sathyanarayanan <[email protected]>
> > >> ---
> > >>
> > >> Changes since v1:
> > >> * Fixed a typo in commit message.
> > >>
> > >> drivers/pci/iov.c | 1 +
> > >> 1 file changed, 1 insertion(+)
> > >>
> > >> diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
> > >> index 3aa115ed3a65..2869011c0e35 100644
> > >> --- a/drivers/pci/iov.c
> > >> +++ b/drivers/pci/iov.c
> > >> @@ -160,6 +160,7 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id)
> > >> virtfn->device = iov->vf_device;
> > >> virtfn->is_virtfn = 1;
> > >> virtfn->physfn = pci_dev_get(dev);
> > >> + virtfn->pcie_cap = pci_find_capability(virtfn, PCI_CAP_ID_EXP);
> > >>
> > >> if (id == 0)
> > >> pci_read_vf_config_common(virtfn);
> > > Why not re-order until after we've setup pcie_cap?
> > >
> > > https://lore.kernel.org/linux-pci/[email protected]/T/#
> >
> > pci_read_vf_config_common() also caches values for properties like
> > class, hdr_type, susbsystem_vendor/device. These values are read/used in
> > pci_setup_device(). So if we can use cached values in
> > pci_setup_device(), we don't have to read them from registers twice for
> > each device.
>
> Sorry, I missed that dependency, a bit too subtle. It's still pretty
> ugly that pci_setup_device()->set_pcie_port_type() is the canonical
> location for setting pcie_cap and now we need to kludge it earlier.
> What about the question in the self follow-up to my patch in the link
> above, can we simply assume 4K config space on a VF? Thanks,

There should be no issue simply reading them once? I don't know
what that exact optimization saves, unless some broken VFs didn't
actually expose all the capabilities in config space and this happens
to workaround the problem.

+ Karim

Cheers,
Ashok

2019-06-12 19:13:27

by Alex Williamson

[permalink] [raw]
Subject: Re: [PATCH v2 1/1] PCI/IOV: Fix incorrect cfg_size for VF > 0

On Wed, 12 Jun 2019 12:03:03 -0700
"Raj, Ashok" <[email protected]> wrote:

> On Wed, Jun 12, 2019 at 12:58:17PM -0600, Alex Williamson wrote:
> > On Wed, 12 Jun 2019 11:41:36 -0700
> > sathyanarayanan kuppuswamy <[email protected]>
> > wrote:
> >
> > > On 6/12/19 11:19 AM, Alex Williamson wrote:
> > > > On Wed, 12 Jun 2019 10:06:47 -0700
> > > > [email protected] wrote:
> > > >
> > > >> From: Kuppuswamy Sathyanarayanan <[email protected]>
> > > >>
> > > >> Commit 975bb8b4dc93 ("PCI/IOV: Use VF0 cached config space size for
> > > >> other VFs") calculates and caches the cfg_size for VF0 device before
> > > >> initializing the pcie_cap of the device which results in using incorrect
> > > >> cfg_size for all VF devices > 0. So set pcie_cap of the device before
> > > >> calculating the cfg_size of VF0 device.
> > > >>
> > > >> Fixes: 975bb8b4dc93 ("PCI/IOV: Use VF0 cached config space size for
> > > >> other VFs")
> > > >> Cc: Ashok Raj <[email protected]>
> > > >> Suggested-by: Mike Campin <[email protected]>
> > > >> Signed-off-by: Kuppuswamy Sathyanarayanan <[email protected]>
> > > >> ---
> > > >>
> > > >> Changes since v1:
> > > >> * Fixed a typo in commit message.
> > > >>
> > > >> drivers/pci/iov.c | 1 +
> > > >> 1 file changed, 1 insertion(+)
> > > >>
> > > >> diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
> > > >> index 3aa115ed3a65..2869011c0e35 100644
> > > >> --- a/drivers/pci/iov.c
> > > >> +++ b/drivers/pci/iov.c
> > > >> @@ -160,6 +160,7 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id)
> > > >> virtfn->device = iov->vf_device;
> > > >> virtfn->is_virtfn = 1;
> > > >> virtfn->physfn = pci_dev_get(dev);
> > > >> + virtfn->pcie_cap = pci_find_capability(virtfn, PCI_CAP_ID_EXP);
> > > >>
> > > >> if (id == 0)
> > > >> pci_read_vf_config_common(virtfn);
> > > > Why not re-order until after we've setup pcie_cap?
> > > >
> > > > https://lore.kernel.org/linux-pci/[email protected]/T/#
> > >
> > > pci_read_vf_config_common() also caches values for properties like
> > > class, hdr_type, susbsystem_vendor/device. These values are read/used in
> > > pci_setup_device(). So if we can use cached values in
> > > pci_setup_device(), we don't have to read them from registers twice for
> > > each device.
> >
> > Sorry, I missed that dependency, a bit too subtle. It's still pretty
> > ugly that pci_setup_device()->set_pcie_port_type() is the canonical
> > location for setting pcie_cap and now we need to kludge it earlier.
> > What about the question in the self follow-up to my patch in the link
> > above, can we simply assume 4K config space on a VF? Thanks,
>
> There should be no issue simply reading them once? I don't know
> what that exact optimization saves, unless some broken VFs didn't
> actually expose all the capabilities in config space and this happens
> to workaround the problem.

AIUI the original commit only saves us a few config space reads for VFs
after the first where we test that extended config space is available
and not simply an alias of standard config space. Thanks,

Alex

2019-06-12 19:53:48

by KarimAllah Ahmed

[permalink] [raw]
Subject: Re: [PATCH v2 1/1] PCI/IOV: Fix incorrect cfg_size for VF > 0

On Wed, 2019-06-12 at 12:03 -0700, Raj, Ashok wrote:
> On Wed, Jun 12, 2019 at 12:58:17PM -0600, Alex Williamson wrote:
> >
> > On Wed, 12 Jun 2019 11:41:36 -0700
> > sathyanarayanan kuppuswamy <[email protected]>
> > wrote:
> >
> > >
> > > On 6/12/19 11:19 AM, Alex Williamson wrote:
> > > >
> > > > On Wed, 12 Jun 2019 10:06:47 -0700
> > > > [email protected] wrote:
> > > >
> > > > >
> > > > > From: Kuppuswamy Sathyanarayanan <[email protected]>
> > > > >
> > > > > Commit 975bb8b4dc93 ("PCI/IOV: Use VF0 cached config space size for
> > > > > other VFs") calculates and caches the cfg_size for VF0 device before
> > > > > initializing the pcie_cap of the device which results in using incorrect
> > > > > cfg_size for all VF devices > 0. So set pcie_cap of the device before
> > > > > calculating the cfg_size of VF0 device.
> > > > >
> > > > > Fixes: 975bb8b4dc93 ("PCI/IOV: Use VF0 cached config space size for
> > > > > other VFs")
> > > > > Cc: Ashok Raj <[email protected]>
> > > > > Suggested-by: Mike Campin <[email protected]>
> > > > > Signed-off-by: Kuppuswamy Sathyanarayanan <[email protected]>
> > > > > ---
> > > > >
> > > > > Changes since v1:
> > > > > * Fixed a typo in commit message.
> > > > >
> > > > > drivers/pci/iov.c | 1 +
> > > > > 1 file changed, 1 insertion(+)
> > > > >
> > > > > diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
> > > > > index 3aa115ed3a65..2869011c0e35 100644
> > > > > --- a/drivers/pci/iov.c
> > > > > +++ b/drivers/pci/iov.c
> > > > > @@ -160,6 +160,7 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id)
> > > > > virtfn->device = iov->vf_device;
> > > > > virtfn->is_virtfn = 1;
> > > > > virtfn->physfn = pci_dev_get(dev);
> > > > > + virtfn->pcie_cap = pci_find_capability(virtfn, PCI_CAP_ID_EXP);
> > > > >
> > > > > if (id == 0)
> > > > > pci_read_vf_config_common(virtfn);
> > > > Why not re-order until after we've setup pcie_cap?
> > > >
> > > > https://lore.kernel.org/linux-pci/[email protected]/T/#
> > >
> > > pci_read_vf_config_common() also caches values for properties like
> > > class, hdr_type, susbsystem_vendor/device. These values are read/used in
> > > pci_setup_device(). So if we can use cached values in
> > > pci_setup_device(), we don't have to read them from registers twice for
> > > each device.
> >
> > Sorry, I missed that dependency, a bit too subtle. It's still pretty
> > ugly that pci_setup_device()->set_pcie_port_type() is the canonical
> > location for setting pcie_cap and now we need to kludge it earlier.
> > What about the question in the self follow-up to my patch in the link
> > above, can we simply assume 4K config space on a VF? Thanks,
>
> There should be no issue simply reading them once? I don't know
> what that exact optimization saves, unless some broken VFs didn't
> actually expose all the capabilities in config space and this happens
> to workaround the problem.

The original patch was to save time when you have hundreds of VFs in the system 
and doing this for each one of them is just a waste of time.

>
> + Karim
>
> Cheers,
> Ashok



Amazon Development Center Germany GmbH
Krausenstr. 38
10117 Berlin
Geschaeftsfuehrung: Christian Schlaeger, Ralf Herbrich
Eingetragen am Amtsgericht Charlottenburg unter HRB 149173 B
Sitz: Berlin
Ust-ID: DE 289 237 879