<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux-toradex.git/drivers/vfio/Kconfig, branch v4.4.73</title>
<subtitle>Linux kernel for Apalis and Colibri modules</subtitle>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/'/>
<entry>
<title>Revert: "vfio: Include No-IOMMU mode"</title>
<updated>2015-12-04T15:38:42+00:00</updated>
<author>
<name>Alex Williamson</name>
<email>alex.williamson@redhat.com</email>
</author>
<published>2015-12-04T15:38:42+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=ae5515d66362b9d96cdcfce504567f0b8b7bd83e'/>
<id>ae5515d66362b9d96cdcfce504567f0b8b7bd83e</id>
<content type='text'>
Revert commit 033291eccbdb ("vfio: Include No-IOMMU mode") due to lack
of a user.  This was originally intended to fill a need for the DPDK
driver, but uptake has been slow so rather than support an unproven
kernel interface revert it and revisit when userspace catches up.

Signed-off-by: Alex Williamson &lt;alex.williamson@redhat.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Revert commit 033291eccbdb ("vfio: Include No-IOMMU mode") due to lack
of a user.  This was originally intended to fill a need for the DPDK
driver, but uptake has been slow so rather than support an unproven
kernel interface revert it and revisit when userspace catches up.

Signed-off-by: Alex Williamson &lt;alex.williamson@redhat.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>Merge tag 'vfio-v4.4-rc1' of git://github.com/awilliam/linux-vfio</title>
<updated>2015-11-14T01:05:32+00:00</updated>
<author>
<name>Linus Torvalds</name>
<email>torvalds@linux-foundation.org</email>
</author>
<published>2015-11-14T01:05:32+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=934f98d7e8123892bd9ca8ea08728ee0784e6597'/>
<id>934f98d7e8123892bd9ca8ea08728ee0784e6597</id>
<content type='text'>
Pull VFIO updates from Alex Williamson:
 - Use kernel interfaces for VPD emulation (Alex Williamson)
 - Platform fix for releasing IRQs (Eric Auger)
 - Type1 IOMMU always advertises PAGE_SIZE support when smaller mapping
   sizes are available (Eric Auger)
 - Platform fixes for incorrectly using copies of structures rather than
   pointers to structures (James Morse)
 - Rework platform reset modules, fix leak, and add AMD xgbe reset
   module (Eric Auger)
 - Fix vfio_device_get_from_name() return value (Joerg Roedel)
 - No-IOMMU interface (Alex Williamson)
 - Fix potential out of bounds array access in PCI config handling (Dan
   Carpenter)

* tag 'vfio-v4.4-rc1' of git://github.com/awilliam/linux-vfio:
  vfio/pci: make an array larger
  vfio: Include No-IOMMU mode
  vfio: Fix bug in vfio_device_get_from_name()
  VFIO: platform: reset: AMD xgbe reset module
  vfio: platform: reset: calxedaxgmac: fix ioaddr leak
  vfio: platform: add dev_info on device reset
  vfio: platform: use list of registered reset function
  vfio: platform: add compat in vfio_platform_device
  vfio: platform: reset: calxedaxgmac: add reset function registration
  vfio: platform: introduce module_vfio_reset_handler macro
  vfio: platform: add capability to register a reset function
  vfio: platform: introduce vfio-platform-base module
  vfio/platform: store mapped memory in region, instead of an on-stack copy
  vfio/type1: handle case where IOMMU does not support PAGE_SIZE size
  VFIO: platform: clear IRQ_NOAUTOEN when de-assigning the IRQ
  vfio/pci: Use kernel VPD access functions
  vfio: Whitelist PCI bridges
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Pull VFIO updates from Alex Williamson:
 - Use kernel interfaces for VPD emulation (Alex Williamson)
 - Platform fix for releasing IRQs (Eric Auger)
 - Type1 IOMMU always advertises PAGE_SIZE support when smaller mapping
   sizes are available (Eric Auger)
 - Platform fixes for incorrectly using copies of structures rather than
   pointers to structures (James Morse)
 - Rework platform reset modules, fix leak, and add AMD xgbe reset
   module (Eric Auger)
 - Fix vfio_device_get_from_name() return value (Joerg Roedel)
 - No-IOMMU interface (Alex Williamson)
 - Fix potential out of bounds array access in PCI config handling (Dan
   Carpenter)

* tag 'vfio-v4.4-rc1' of git://github.com/awilliam/linux-vfio:
  vfio/pci: make an array larger
  vfio: Include No-IOMMU mode
  vfio: Fix bug in vfio_device_get_from_name()
  VFIO: platform: reset: AMD xgbe reset module
  vfio: platform: reset: calxedaxgmac: fix ioaddr leak
  vfio: platform: add dev_info on device reset
  vfio: platform: use list of registered reset function
  vfio: platform: add compat in vfio_platform_device
  vfio: platform: reset: calxedaxgmac: add reset function registration
  vfio: platform: introduce module_vfio_reset_handler macro
  vfio: platform: add capability to register a reset function
  vfio: platform: introduce vfio-platform-base module
  vfio/platform: store mapped memory in region, instead of an on-stack copy
  vfio/type1: handle case where IOMMU does not support PAGE_SIZE size
  VFIO: platform: clear IRQ_NOAUTOEN when de-assigning the IRQ
  vfio/pci: Use kernel VPD access functions
  vfio: Whitelist PCI bridges
</pre>
</div>
</content>
</entry>
<entry>
<title>vfio: Include No-IOMMU mode</title>
<updated>2015-11-04T16:56:16+00:00</updated>
<author>
<name>Alex Williamson</name>
<email>alex.williamson@redhat.com</email>
</author>
<published>2015-10-15T21:08:48+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=033291eccbdb1b70ffc02641edae19ac825dc75d'/>
<id>033291eccbdb1b70ffc02641edae19ac825dc75d</id>
<content type='text'>
There is really no way to safely give a user full access to a DMA
capable device without an IOMMU to protect the host system.  There is
also no way to provide DMA translation, for use cases such as device
assignment to virtual machines.  However, there are still those users
that want userspace drivers even under those conditions.  The UIO
driver exists for this use case, but does not provide the degree of
device access and programming that VFIO has.  In an effort to avoid
code duplication, this introduces a No-IOMMU mode for VFIO.

This mode requires building VFIO with CONFIG_VFIO_NOIOMMU and enabling
the "enable_unsafe_noiommu_mode" option on the vfio driver.  This
should make it very clear that this mode is not safe.  Additionally,
CAP_SYS_RAWIO privileges are necessary to work with groups and
containers using this mode.  Groups making use of this support are
named /dev/vfio/noiommu-$GROUP and can only make use of the special
VFIO_NOIOMMU_IOMMU for the container.  Use of this mode, specifically
binding a device without a native IOMMU group to a VFIO bus driver
will taint the kernel and should therefore not be considered
supported.  This patch includes no-iommu support for the vfio-pci bus
driver only.

Signed-off-by: Alex Williamson &lt;alex.williamson@redhat.com&gt;
Acked-by: Michael S. Tsirkin &lt;mst@redhat.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
There is really no way to safely give a user full access to a DMA
capable device without an IOMMU to protect the host system.  There is
also no way to provide DMA translation, for use cases such as device
assignment to virtual machines.  However, there are still those users
that want userspace drivers even under those conditions.  The UIO
driver exists for this use case, but does not provide the degree of
device access and programming that VFIO has.  In an effort to avoid
code duplication, this introduces a No-IOMMU mode for VFIO.

This mode requires building VFIO with CONFIG_VFIO_NOIOMMU and enabling
the "enable_unsafe_noiommu_mode" option on the vfio driver.  This
should make it very clear that this mode is not safe.  Additionally,
CAP_SYS_RAWIO privileges are necessary to work with groups and
containers using this mode.  Groups making use of this support are
named /dev/vfio/noiommu-$GROUP and can only make use of the special
VFIO_NOIOMMU_IOMMU for the container.  Use of this mode, specifically
binding a device without a native IOMMU group to a VFIO bus driver
will taint the kernel and should therefore not be considered
supported.  This patch includes no-iommu support for the vfio-pci bus
driver only.

Signed-off-by: Alex Williamson &lt;alex.williamson@redhat.com&gt;
Acked-by: Michael S. Tsirkin &lt;mst@redhat.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>vfio: Register/unregister irq_bypass_producer</title>
<updated>2015-10-01T13:06:50+00:00</updated>
<author>
<name>Feng Wu</name>
<email>feng.wu@intel.com</email>
</author>
<published>2015-09-18T14:29:50+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=6d7425f109d2629d1f4b4b146eca8e43701bf966'/>
<id>6d7425f109d2629d1f4b4b146eca8e43701bf966</id>
<content type='text'>
This patch adds the registration/unregistration of an
irq_bypass_producer for MSI/MSIx on vfio pci devices.

Acked-by: Alex Williamson &lt;alex.williamson@redhat.com&gt;
Signed-off-by: Feng Wu &lt;feng.wu@intel.com&gt;
Signed-off-by: Paolo Bonzini &lt;pbonzini@redhat.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This patch adds the registration/unregistration of an
irq_bypass_producer for MSI/MSIx on vfio pci devices.

Acked-by: Alex Williamson &lt;alex.williamson@redhat.com&gt;
Signed-off-by: Feng Wu &lt;feng.wu@intel.com&gt;
Signed-off-by: Paolo Bonzini &lt;pbonzini@redhat.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drivers/vfio: Allow type-1 IOMMU instantiation on top of an ARM SMMUv3</title>
<updated>2015-05-29T09:12:40+00:00</updated>
<author>
<name>Will Deacon</name>
<email>will.deacon@arm.com</email>
</author>
<published>2015-05-27T16:26:00+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=8a0a01bff855a6763d937acc70a876cb0bed063d'/>
<id>8a0a01bff855a6763d937acc70a876cb0bed063d</id>
<content type='text'>
The ARM SMMUv3 driver is compatible with the notion of a type-1 IOMMU in
VFIO.

This patch allows VFIO_IOMMU_TYPE1 to be selected if ARM_SMMU_V3=y.

Signed-off-by: Will Deacon &lt;will.deacon@arm.com&gt;
Acked-by: Alex Williamson &lt;alex.williamson@redhat.com&gt;
Signed-off-by: Joerg Roedel &lt;jroedel@suse.de&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The ARM SMMUv3 driver is compatible with the notion of a type-1 IOMMU in
VFIO.

This patch allows VFIO_IOMMU_TYPE1 to be selected if ARM_SMMU_V3=y.

Signed-off-by: Will Deacon &lt;will.deacon@arm.com&gt;
Acked-by: Alex Williamson &lt;alex.williamson@redhat.com&gt;
Signed-off-by: Joerg Roedel &lt;jroedel@suse.de&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>vfio: Split virqfd into a separate module for vfio bus drivers</title>
<updated>2015-03-17T14:33:38+00:00</updated>
<author>
<name>Alex Williamson</name>
<email>alex.williamson@redhat.com</email>
</author>
<published>2015-03-17T14:33:38+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=71be3423a62be548c56bab5b818e1a1383e659d2'/>
<id>71be3423a62be548c56bab5b818e1a1383e659d2</id>
<content type='text'>
An unintended consequence of commit 42ac9bd18d4f ("vfio: initialize
the virqfd workqueue in VFIO generic code") is that the vfio module
is renamed to vfio_core so that it can include both vfio and virqfd.
That's a user visible change that may break module loading scritps
and it imposes eventfd support as a dependency on the core vfio code,
which it's really not.  virqfd is intended to be provided as a service
to vfio bus drivers, so instead of wrapping it into vfio.ko, we can
make it a stand-alone module toggled by vfio bus drivers.  This has
the additional benefit of removing initialization and exit from the
core vfio code.

Signed-off-by: Alex Williamson &lt;alex.williamson@redhat.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
An unintended consequence of commit 42ac9bd18d4f ("vfio: initialize
the virqfd workqueue in VFIO generic code") is that the vfio module
is renamed to vfio_core so that it can include both vfio and virqfd.
That's a user visible change that may break module loading scritps
and it imposes eventfd support as a dependency on the core vfio code,
which it's really not.  virqfd is intended to be provided as a service
to vfio bus drivers, so instead of wrapping it into vfio.ko, we can
make it a stand-alone module toggled by vfio bus drivers.  This has
the additional benefit of removing initialization and exit from the
core vfio code.

Signed-off-by: Alex Williamson &lt;alex.williamson@redhat.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>vfio: platform: add the VFIO PLATFORM module to Kconfig</title>
<updated>2015-03-16T20:08:44+00:00</updated>
<author>
<name>Antonios Motakis</name>
<email>a.motakis@virtualopensystems.com</email>
</author>
<published>2015-03-16T20:08:44+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=53161532394b3b3c7e1ec9c80658edd75446ac77'/>
<id>53161532394b3b3c7e1ec9c80658edd75446ac77</id>
<content type='text'>
Enable building the VFIO PLATFORM driver that allows to use Linux platform
devices with VFIO.

Signed-off-by: Antonios Motakis &lt;a.motakis@virtualopensystems.com&gt;
Signed-off-by: Baptiste Reynal &lt;b.reynal@virtualopensystems.com&gt;
Reviewed-by: Eric Auger &lt;eric.auger@linaro.org&gt;
Tested-by: Eric Auger &lt;eric.auger@linaro.org&gt;
Signed-off-by: Alex Williamson &lt;alex.williamson@redhat.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Enable building the VFIO PLATFORM driver that allows to use Linux platform
devices with VFIO.

Signed-off-by: Antonios Motakis &lt;a.motakis@virtualopensystems.com&gt;
Signed-off-by: Baptiste Reynal &lt;b.reynal@virtualopensystems.com&gt;
Reviewed-by: Eric Auger &lt;eric.auger@linaro.org&gt;
Tested-by: Eric Auger &lt;eric.auger@linaro.org&gt;
Signed-off-by: Alex Williamson &lt;alex.williamson@redhat.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drivers/vfio: allow type-1 IOMMU instantiation on top of an ARM SMMU</title>
<updated>2014-11-14T16:10:59+00:00</updated>
<author>
<name>Will Deacon</name>
<email>will.deacon@arm.com</email>
</author>
<published>2014-11-14T16:10:59+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=5e9f36c59a4883c6d8db4a3c097e4fc2234742de'/>
<id>5e9f36c59a4883c6d8db4a3c097e4fc2234742de</id>
<content type='text'>
The ARM SMMU driver is compatible with the notion of a type-1 IOMMU in
VFIO.

This patch allows VFIO_IOMMU_TYPE1 to be selected if ARM_SMMU=y.

Signed-off-by: Will Deacon &lt;will.deacon@arm.com&gt;
[aw: update for existing S390 patch]
Signed-off-by: Alex Williamson &lt;alex.williamson@redhat.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The ARM SMMU driver is compatible with the notion of a type-1 IOMMU in
VFIO.

This patch allows VFIO_IOMMU_TYPE1 to be selected if ARM_SMMU=y.

Signed-off-by: Will Deacon &lt;will.deacon@arm.com&gt;
[aw: update for existing S390 patch]
Signed-off-by: Alex Williamson &lt;alex.williamson@redhat.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>vfio: make vfio run on s390</title>
<updated>2014-11-07T16:52:22+00:00</updated>
<author>
<name>Frank Blaschka</name>
<email>frank.blaschka@de.ibm.com</email>
</author>
<published>2014-11-07T16:52:22+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=1d53a3a7d3b886bcc60b90e41693b82a791c25ba'/>
<id>1d53a3a7d3b886bcc60b90e41693b82a791c25ba</id>
<content type='text'>
add Kconfig switch to hide INTx
add Kconfig switch to let vfio announce PCI BARs are not mapable

Signed-off-by: Frank Blaschka &lt;frank.blaschka@de.ibm.com&gt;
Signed-off-by: Alex Williamson &lt;alex.williamson@redhat.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
add Kconfig switch to hide INTx
add Kconfig switch to let vfio announce PCI BARs are not mapable

Signed-off-by: Frank Blaschka &lt;frank.blaschka@de.ibm.com&gt;
Signed-off-by: Alex Williamson &lt;alex.williamson@redhat.com&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>drivers/vfio: Fix EEH build error</title>
<updated>2014-08-08T16:36:20+00:00</updated>
<author>
<name>Gavin Shan</name>
<email>gwshan@linux.vnet.ibm.com</email>
</author>
<published>2014-08-08T16:36:20+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=92d18a6851fb6295466657ad1cf7fe88c2054ffa'/>
<id>92d18a6851fb6295466657ad1cf7fe88c2054ffa</id>
<content type='text'>
The VFIO related components could be built as dynamic modules.
Unfortunately, CONFIG_EEH can't be configured to "m". The patch
fixes the build errors when configuring VFIO related components
as dynamic modules as follows:

  CC [M]  drivers/vfio/vfio_iommu_spapr_tce.o
In file included from drivers/vfio/vfio.c:33:0:
include/linux/vfio.h:101:43: warning: ‘struct pci_dev’ declared \
inside parameter list [enabled by default]
   :
  WRAP    arch/powerpc/boot/zImage.pseries
  WRAP    arch/powerpc/boot/zImage.maple
  WRAP    arch/powerpc/boot/zImage.pmac
  WRAP    arch/powerpc/boot/zImage.epapr
  MODPOST 1818 modules
ERROR: ".vfio_spapr_iommu_eeh_ioctl" [drivers/vfio/vfio_iommu_spapr_tce.ko]\
undefined!
ERROR: ".vfio_spapr_pci_eeh_open" [drivers/vfio/pci/vfio-pci.ko] undefined!
ERROR: ".vfio_spapr_pci_eeh_release" [drivers/vfio/pci/vfio-pci.ko] undefined!

Reported-by: Alexey Kardashevskiy &lt;aik@ozlabs.ru&gt;
Signed-off-by: Gavin Shan &lt;gwshan@linux.vnet.ibm.com&gt;
Signed-off-by: Alexey Kardashevskiy &lt;aik@ozlabs.ru&gt;
Signed-off-by: Alex Williamson &lt;alex.williamson@redhat.com&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The VFIO related components could be built as dynamic modules.
Unfortunately, CONFIG_EEH can't be configured to "m". The patch
fixes the build errors when configuring VFIO related components
as dynamic modules as follows:

  CC [M]  drivers/vfio/vfio_iommu_spapr_tce.o
In file included from drivers/vfio/vfio.c:33:0:
include/linux/vfio.h:101:43: warning: ‘struct pci_dev’ declared \
inside parameter list [enabled by default]
   :
  WRAP    arch/powerpc/boot/zImage.pseries
  WRAP    arch/powerpc/boot/zImage.maple
  WRAP    arch/powerpc/boot/zImage.pmac
  WRAP    arch/powerpc/boot/zImage.epapr
  MODPOST 1818 modules
ERROR: ".vfio_spapr_iommu_eeh_ioctl" [drivers/vfio/vfio_iommu_spapr_tce.ko]\
undefined!
ERROR: ".vfio_spapr_pci_eeh_open" [drivers/vfio/pci/vfio-pci.ko] undefined!
ERROR: ".vfio_spapr_pci_eeh_release" [drivers/vfio/pci/vfio-pci.ko] undefined!

Reported-by: Alexey Kardashevskiy &lt;aik@ozlabs.ru&gt;
Signed-off-by: Gavin Shan &lt;gwshan@linux.vnet.ibm.com&gt;
Signed-off-by: Alexey Kardashevskiy &lt;aik@ozlabs.ru&gt;
Signed-off-by: Alex Williamson &lt;alex.williamson@redhat.com&gt;
</pre>
</div>
</content>
</entry>
</feed>
