There's no need to have a public header for Intel SVA implementation.
The device driver should interact with Intel SVA implementation via
the IOMMU generic APIs.
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20230109014955.147068-2-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Jason Gunthorpe says:
====================
iommufd follows the same design as KVM and uses memory cgroups to limit
the amount of kernel memory a iommufd file descriptor can pin down. The
various internal data structures already use GFP_KERNEL_ACCOUNT to charge
its own memory.
However, one of the biggest consumers of kernel memory is the IOPTEs
stored under the iommu_domain and these allocations are not tracked.
This series is the first step in fixing it.
The iommu driver contract already includes a 'gfp' argument to the
map_pages op, allowing iommufd to specify GFP_KERNEL_ACCOUNT and then
having the driver allocate the IOPTE tables with that flag will capture a
significant amount of the allocations.
Update the iommu_map() API to pass in the GFP argument, and fix all call
sites. Replace iommu_map_atomic().
Audit the "enterprise" iommu drivers to make sure they do the right thing.
Intel and S390 ignore the GFP argument and always use GFP_ATOMIC. This is
problematic for iommufd anyhow, so fix it. AMD and ARM SMMUv2/3 are
already correct.
A follow up series will be needed to capture the allocations made when the
iommu_domain itself is allocated, which will complete the job.
====================
* 'iommu-memory-accounting' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
iommu/s390: Use GFP_KERNEL in sleepable contexts
iommu/s390: Push the gfp parameter to the kmem_cache_alloc()'s
iommu/intel: Use GFP_KERNEL in sleepable contexts
iommu/intel: Support the gfp argument to the map_pages op
iommu/intel: Add a gfp parameter to alloc_pgtable_page()
iommufd: Use GFP_KERNEL_ACCOUNT for iommu_map()
iommu/dma: Use the gfp parameter in __iommu_dma_alloc_noncontiguous()
iommu: Add a gfp parameter to iommu_map_sg()
iommu: Remove iommu_map_atomic()
iommu: Add a gfp parameter to iommu_map()
Link: https://lore.kernel.org/linux-iommu/0-v3-76b587fe28df+6e3-iommu_map_gfp_jgg@nvidia.com
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
These contexts are sleepable, so use the proper annotation. The GFP_ATOMIC
was added mechanically in the prior patches.
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/8-v3-76b587fe28df+6e3-iommu_map_gfp_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Flow it down to alloc_pgtable_page() via pfn_to_dma_pte() and
__domain_mapping().
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/7-v3-76b587fe28df+6e3-iommu_map_gfp_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
This is eventually called by iommufd through intel_iommu_map_pages() and
it should not be forced to atomic. Push the GFP_ATOMIC to all callers.
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/6-v3-76b587fe28df+6e3-iommu_map_gfp_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
On x86 platforms when the HW can support interrupt remapping the iommu
driver creates an irq_domain for the IR hardware and creates a child MSI
irq_domain.
When the global irq_remapping_enabled is set, the IR MSI domain is
assigned to the PCI devices (by intel_irq_remap_add_device(), or
amd_iommu_set_pci_msi_domain()) making those devices have the isolated MSI
property.
Due to how interrupt domains work, setting IRQ_DOMAIN_FLAG_ISOLATED_MSI on
the parent IR domain will cause all struct devices attached to it to
return true from msi_device_has_isolated_msi(). This replaces the
IOMMU_CAP_INTR_REMAP flag as all places using IOMMU_CAP_INTR_REMAP also
call msi_device_has_isolated_msi()
Set the flag and delete the cap.
Link: https://lore.kernel.org/r/7-v3-3313bb5dd3a3+10f11-secure_msi_jgg@nvidia.com
Tested-by: Matthew Rosato <mjrosato@linux.ibm.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Including:
- Core code:
- map/unmap_pages() cleanup
- SVA and IOPF refactoring
- Clean up and document return codes from device/domain
attachment code
- AMD driver:
- Rework and extend parsing code for ivrs_ioapic, ivrs_hpet
and ivrs_acpihid command line options
- Some smaller cleanups
- Intel driver:
- Blocking domain support
- Cleanups
- S390 driver:
- Fixes and improvements for attach and aperture handling
- PAMU driver:
- Resource leak fix and cleanup
- Rockchip driver:
- Page table permission bit fix
- Mediatek driver:
- Improve safety from invalid dts input
- Smaller fixes and improvements
- Exynos driver:
- Fix driver initialization sequence
- Sun50i driver:
- Remove IOMMU_DOMAIN_IDENTITY as it has not been working
forever
- Various other fixes
-----BEGIN PGP SIGNATURE-----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=ZM/m
-----END PGP SIGNATURE-----
Merge tag 'iommu-updates-v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu
Pull iommu updates from Joerg Roedel:
"Core code:
- map/unmap_pages() cleanup
- SVA and IOPF refactoring
- Clean up and document return codes from device/domain attachment
AMD driver:
- Rework and extend parsing code for ivrs_ioapic, ivrs_hpet and
ivrs_acpihid command line options
- Some smaller cleanups
Intel driver:
- Blocking domain support
- Cleanups
S390 driver:
- Fixes and improvements for attach and aperture handling
PAMU driver:
- Resource leak fix and cleanup
Rockchip driver:
- Page table permission bit fix
Mediatek driver:
- Improve safety from invalid dts input
- Smaller fixes and improvements
Exynos driver:
- Fix driver initialization sequence
Sun50i driver:
- Remove IOMMU_DOMAIN_IDENTITY as it has not been working forever
- Various other fixes"
* tag 'iommu-updates-v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (74 commits)
iommu/mediatek: Fix forever loop in error handling
iommu/mediatek: Fix crash on isr after kexec()
iommu/sun50i: Remove IOMMU_DOMAIN_IDENTITY
iommu/amd: Fix typo in macro parameter name
iommu/mediatek: Remove unused "mapping" member from mtk_iommu_data
iommu/mediatek: Improve safety for mediatek,smi property in larb nodes
iommu/mediatek: Validate number of phandles associated with "mediatek,larbs"
iommu/mediatek: Add error path for loop of mm_dts_parse
iommu/mediatek: Use component_match_add
iommu/mediatek: Add platform_device_put for recovering the device refcnt
iommu/fsl_pamu: Fix resource leak in fsl_pamu_probe()
iommu/vt-d: Use real field for indication of first level
iommu/vt-d: Remove unnecessary domain_context_mapped()
iommu/vt-d: Rename domain_add_dev_info()
iommu/vt-d: Rename iommu_disable_dev_iotlb()
iommu/vt-d: Add blocking domain support
iommu/vt-d: Add device_block_translation() helper
iommu/vt-d: Allocate pasid table in device probe path
iommu/amd: Check return value of mmu_notifier_register()
iommu/amd: Fix pci device refcount leak in ppr_notifier()
...
* Randomize the per-cpu entry areas
Cleanups:
* Have CR3_ADDR_MASK use PHYSICAL_PAGE_MASK instead of open
coding it
* Move to "native" set_memory_rox() helper
* Clean up pmd_get_atomic() and i386-PAE
* Remove some unused page table size macros
-----BEGIN PGP SIGNATURE-----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=wwVF
-----END PGP SIGNATURE-----
Merge tag 'x86_mm_for_6.2_v2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 mm updates from Dave Hansen:
"New Feature:
- Randomize the per-cpu entry areas
Cleanups:
- Have CR3_ADDR_MASK use PHYSICAL_PAGE_MASK instead of open coding it
- Move to "native" set_memory_rox() helper
- Clean up pmd_get_atomic() and i386-PAE
- Remove some unused page table size macros"
* tag 'x86_mm_for_6.2_v2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (35 commits)
x86/mm: Ensure forced page table splitting
x86/kasan: Populate shadow for shared chunk of the CPU entry area
x86/kasan: Add helpers to align shadow addresses up and down
x86/kasan: Rename local CPU_ENTRY_AREA variables to shorten names
x86/mm: Populate KASAN shadow for entire per-CPU range of CPU entry area
x86/mm: Recompute physical address for every page of per-CPU CEA mapping
x86/mm: Rename __change_page_attr_set_clr(.checkalias)
x86/mm: Inhibit _PAGE_NX changes from cpa_process_alias()
x86/mm: Untangle __change_page_attr_set_clr(.checkalias)
x86/mm: Add a few comments
x86/mm: Fix CR3_ADDR_MASK
x86/mm: Remove P*D_PAGE_MASK and P*D_PAGE_SIZE macros
mm: Convert __HAVE_ARCH_P..P_GET to the new style
mm: Remove pointless barrier() after pmdp_get_lockless()
x86/mm/pae: Get rid of set_64bit()
x86_64: Remove pointless set_64bit() usage
x86/mm/pae: Be consistent with pXXp_get_and_clear()
x86/mm/pae: Use WRITE_ONCE()
x86/mm/pae: Don't (ab)use atomic64
mm/gup: Fix the lockless PMD access
...
The use of set_64bit() in X86_64 only code is pretty pointless, seeing
how it's a direct assignment. Remove all this nonsense.
[nathanchance: unbreak irte]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20221022114425.168036718%40infradead.org
iommufd is the user API to control the IOMMU subsystem as it relates to
managing IO page tables that point at user space memory.
It takes over from drivers/vfio/vfio_iommu_type1.c (aka the VFIO
container) which is the VFIO specific interface for a similar idea.
We see a broad need for extended features, some being highly IOMMU device
specific:
- Binding iommu_domain's to PASID/SSID
- Userspace IO page tables, for ARM, x86 and S390
- Kernel bypassed invalidation of user page tables
- Re-use of the KVM page table in the IOMMU
- Dirty page tracking in the IOMMU
- Runtime Increase/Decrease of IOPTE size
- PRI support with faults resolved in userspace
Many of these HW features exist to support VM use cases - for instance the
combination of PASID, PRI and Userspace IO Page Tables allows an
implementation of DMA Shared Virtual Addressing (vSVA) within a
guest. Dirty tracking enables VM live migration with SRIOV devices and
PASID support allow creating "scalable IOV" devices, among other things.
As these features are fundamental to a VM platform they need to be
uniformly exposed to all the driver families that do DMA into VMs, which
is currently VFIO and VDPA.
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQRRRCHOFoQz/8F5bUaFwuHvBreFYQUCY5ct7wAKCRCFwuHvBreF
YZZ5AQDciXfcgXLt0UBEmWupNb0f/asT6tk717pdsKm8kAZMNAEAsIyLiKT5HqGl
s7fAu+CQ1pr9+9NKGevD+frw8Solsw4=
=jJkd
-----END PGP SIGNATURE-----
Merge tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd
Pull iommufd implementation from Jason Gunthorpe:
"iommufd is the user API to control the IOMMU subsystem as it relates
to managing IO page tables that point at user space memory.
It takes over from drivers/vfio/vfio_iommu_type1.c (aka the VFIO
container) which is the VFIO specific interface for a similar idea.
We see a broad need for extended features, some being highly IOMMU
device specific:
- Binding iommu_domain's to PASID/SSID
- Userspace IO page tables, for ARM, x86 and S390
- Kernel bypassed invalidation of user page tables
- Re-use of the KVM page table in the IOMMU
- Dirty page tracking in the IOMMU
- Runtime Increase/Decrease of IOPTE size
- PRI support with faults resolved in userspace
Many of these HW features exist to support VM use cases - for instance
the combination of PASID, PRI and Userspace IO Page Tables allows an
implementation of DMA Shared Virtual Addressing (vSVA) within a guest.
Dirty tracking enables VM live migration with SRIOV devices and PASID
support allow creating "scalable IOV" devices, among other things.
As these features are fundamental to a VM platform they need to be
uniformly exposed to all the driver families that do DMA into VMs,
which is currently VFIO and VDPA"
For more background, see the extended explanations in Jason's pull request:
https://lore.kernel.org/lkml/Y5dzTU8dlmXTbzoJ@nvidia.com/
* tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd: (62 commits)
iommufd: Change the order of MSI setup
iommufd: Improve a few unclear bits of code
iommufd: Fix comment typos
vfio: Move vfio group specific code into group.c
vfio: Refactor dma APIs for emulated devices
vfio: Wrap vfio group module init/clean code into helpers
vfio: Refactor vfio_device open and close
vfio: Make vfio_device_open() truly device specific
vfio: Swap order of vfio_device_container_register() and open_device()
vfio: Set device->group in helper function
vfio: Create wrappers for group register/unregister
vfio: Move the sanity check of the group to vfio_create_group()
vfio: Simplify vfio_create_group()
iommufd: Allow iommufd to supply /dev/vfio/vfio
vfio: Make vfio_container optionally compiled
vfio: Move container related MODULE_ALIAS statements into container.c
vfio-iommufd: Support iommufd for emulated VFIO devices
vfio-iommufd: Support iommufd for physical VFIO devices
vfio-iommufd: Allow iommufd to be used in place of a container fd
vfio: Use IOMMU_CAP_ENFORCE_CACHE_COHERENCY for vfio_file_enforced_coherent()
...
- Core:
The bulk is the rework of the MSI subsystem to support per device MSI
interrupt domains. This solves conceptual problems of the current
PCI/MSI design which are in the way of providing support for PCI/MSI[-X]
and the upcoming PCI/IMS mechanism on the same device.
IMS (Interrupt Message Store] is a new specification which allows device
manufactures to provide implementation defined storage for MSI messages
contrary to the uniform and specification defined storage mechanisms for
PCI/MSI and PCI/MSI-X. IMS not only allows to overcome the size limitations
of the MSI-X table, but also gives the device manufacturer the freedom to
store the message in arbitrary places, even in host memory which is shared
with the device.
There have been several attempts to glue this into the current MSI code,
but after lengthy discussions it turned out that there is a fundamental
design problem in the current PCI/MSI-X implementation. This needs some
historical background.
When PCI/MSI[-X] support was added around 2003, interrupt management was
completely different from what we have today in the actively developed
architectures. Interrupt management was completely architecture specific
and while there were attempts to create common infrastructure the
commonalities were rudimentary and just providing shared data structures and
interfaces so that drivers could be written in an architecture agnostic
way.
The initial PCI/MSI[-X] support obviously plugged into this model which
resulted in some basic shared infrastructure in the PCI core code for
setting up MSI descriptors, which are a pure software construct for holding
data relevant for a particular MSI interrupt, but the actual association to
Linux interrupts was completely architecture specific. This model is still
supported today to keep museum architectures and notorious stranglers
alive.
In 2013 Intel tried to add support for hot-pluggable IO/APICs to the kernel,
which was creating yet another architecture specific mechanism and resulted
in an unholy mess on top of the existing horrors of x86 interrupt handling.
The x86 interrupt management code was already an incomprehensible maze of
indirections between the CPU vector management, interrupt remapping and the
actual IO/APIC and PCI/MSI[-X] implementation.
At roughly the same time ARM struggled with the ever growing SoC specific
extensions which were glued on top of the architected GIC interrupt
controller.
This resulted in a fundamental redesign of interrupt management and
provided the today prevailing concept of hierarchical interrupt
domains. This allowed to disentangle the interactions between x86 vector
domain and interrupt remapping and also allowed ARM to handle the zoo of
SoC specific interrupt components in a sane way.
The concept of hierarchical interrupt domains aims to encapsulate the
functionality of particular IP blocks which are involved in interrupt
delivery so that they become extensible and pluggable. The X86
encapsulation looks like this:
|--- device 1
[Vector]---[Remapping]---[PCI/MSI]--|...
|--- device N
where the remapping domain is an optional component and in case that it is
not available the PCI/MSI[-X] domains have the vector domain as their
parent. This reduced the required interaction between the domains pretty
much to the initialization phase where it is obviously required to
establish the proper parent relation ship in the components of the
hierarchy.
While in most cases the model is strictly representing the chain of IP
blocks and abstracting them so they can be plugged together to form a
hierarchy, the design stopped short on PCI/MSI[-X]. Looking at the hardware
it's clear that the actual PCI/MSI[-X] interrupt controller is not a global
entity, but strict a per PCI device entity.
Here we took a short cut on the hierarchical model and went for the easy
solution of providing "global" PCI/MSI domains which was possible because
the PCI/MSI[-X] handling is uniform across the devices. This also allowed
to keep the existing PCI/MSI[-X] infrastructure mostly unchanged which in
turn made it simple to keep the existing architecture specific management
alive.
A similar problem was created in the ARM world with support for IP block
specific message storage. Instead of going all the way to stack a IP block
specific domain on top of the generic MSI domain this ended in a construct
which provides a "global" platform MSI domain which allows overriding the
irq_write_msi_msg() callback per allocation.
In course of the lengthy discussions we identified other abuse of the MSI
infrastructure in wireless drivers, NTB etc. where support for
implementation specific message storage was just mindlessly glued into the
existing infrastructure. Some of this just works by chance on particular
platforms but will fail in hard to diagnose ways when the driver is used
on platforms where the underlying MSI interrupt management code does not
expect the creative abuse.
Another shortcoming of today's PCI/MSI-X support is the inability to
allocate or free individual vectors after the initial enablement of
MSI-X. This results in an works by chance implementation of VFIO (PCI
pass-through) where interrupts on the host side are not set up upfront to
avoid resource exhaustion. They are expanded at run-time when the guest
actually tries to use them. The way how this is implemented is that the
host disables MSI-X and then re-enables it with a larger number of
vectors again. That works by chance because most device drivers set up
all interrupts before the device actually will utilize them. But that's
not universally true because some drivers allocate a large enough number
of vectors but do not utilize them until it's actually required,
e.g. for acceleration support. But at that point other interrupts of the
device might be in active use and the MSI-X disable/enable dance can
just result in losing interrupts and therefore hard to diagnose subtle
problems.
Last but not least the "global" PCI/MSI-X domain approach prevents to
utilize PCI/MSI[-X] and PCI/IMS on the same device due to the fact that IMS
is not longer providing a uniform storage and configuration model.
The solution to this is to implement the missing step and switch from
global PCI/MSI domains to per device PCI/MSI domains. The resulting
hierarchy then looks like this:
|--- [PCI/MSI] device 1
[Vector]---[Remapping]---|...
|--- [PCI/MSI] device N
which in turn allows to provide support for multiple domains per device:
|--- [PCI/MSI] device 1
|--- [PCI/IMS] device 1
[Vector]---[Remapping]---|...
|--- [PCI/MSI] device N
|--- [PCI/IMS] device N
This work converts the MSI and PCI/MSI core and the x86 interrupt
domains to the new model, provides new interfaces for post-enable
allocation/free of MSI-X interrupts and the base framework for PCI/IMS.
PCI/IMS has been verified with the work in progress IDXD driver.
There is work in progress to convert ARM over which will replace the
platform MSI train-wreck. The cleanup of VFIO, NTB and other creative
"solutions" are in the works as well.
- Drivers:
- Updates for the LoongArch interrupt chip drivers
- Support for MTK CIRQv2
- The usual small fixes and updates all over the place
-----BEGIN PGP SIGNATURE-----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=9erA
-----END PGP SIGNATURE-----
Merge tag 'irq-core-2022-12-10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull irq updates from Thomas Gleixner:
"Updates for the interrupt core and driver subsystem:
The bulk is the rework of the MSI subsystem to support per device MSI
interrupt domains. This solves conceptual problems of the current
PCI/MSI design which are in the way of providing support for
PCI/MSI[-X] and the upcoming PCI/IMS mechanism on the same device.
IMS (Interrupt Message Store] is a new specification which allows
device manufactures to provide implementation defined storage for MSI
messages (as opposed to PCI/MSI and PCI/MSI-X that has a specified
message store which is uniform accross all devices). The PCI/MSI[-X]
uniformity allowed us to get away with "global" PCI/MSI domains.
IMS not only allows to overcome the size limitations of the MSI-X
table, but also gives the device manufacturer the freedom to store the
message in arbitrary places, even in host memory which is shared with
the device.
There have been several attempts to glue this into the current MSI
code, but after lengthy discussions it turned out that there is a
fundamental design problem in the current PCI/MSI-X implementation.
This needs some historical background.
When PCI/MSI[-X] support was added around 2003, interrupt management
was completely different from what we have today in the actively
developed architectures. Interrupt management was completely
architecture specific and while there were attempts to create common
infrastructure the commonalities were rudimentary and just providing
shared data structures and interfaces so that drivers could be written
in an architecture agnostic way.
The initial PCI/MSI[-X] support obviously plugged into this model
which resulted in some basic shared infrastructure in the PCI core
code for setting up MSI descriptors, which are a pure software
construct for holding data relevant for a particular MSI interrupt,
but the actual association to Linux interrupts was completely
architecture specific. This model is still supported today to keep
museum architectures and notorious stragglers alive.
In 2013 Intel tried to add support for hot-pluggable IO/APICs to the
kernel, which was creating yet another architecture specific mechanism
and resulted in an unholy mess on top of the existing horrors of x86
interrupt handling. The x86 interrupt management code was already an
incomprehensible maze of indirections between the CPU vector
management, interrupt remapping and the actual IO/APIC and PCI/MSI[-X]
implementation.
At roughly the same time ARM struggled with the ever growing SoC
specific extensions which were glued on top of the architected GIC
interrupt controller.
This resulted in a fundamental redesign of interrupt management and
provided the today prevailing concept of hierarchical interrupt
domains. This allowed to disentangle the interactions between x86
vector domain and interrupt remapping and also allowed ARM to handle
the zoo of SoC specific interrupt components in a sane way.
The concept of hierarchical interrupt domains aims to encapsulate the
functionality of particular IP blocks which are involved in interrupt
delivery so that they become extensible and pluggable. The X86
encapsulation looks like this:
|--- device 1
[Vector]---[Remapping]---[PCI/MSI]--|...
|--- device N
where the remapping domain is an optional component and in case that
it is not available the PCI/MSI[-X] domains have the vector domain as
their parent. This reduced the required interaction between the
domains pretty much to the initialization phase where it is obviously
required to establish the proper parent relation ship in the
components of the hierarchy.
While in most cases the model is strictly representing the chain of IP
blocks and abstracting them so they can be plugged together to form a
hierarchy, the design stopped short on PCI/MSI[-X]. Looking at the
hardware it's clear that the actual PCI/MSI[-X] interrupt controller
is not a global entity, but strict a per PCI device entity.
Here we took a short cut on the hierarchical model and went for the
easy solution of providing "global" PCI/MSI domains which was possible
because the PCI/MSI[-X] handling is uniform across the devices. This
also allowed to keep the existing PCI/MSI[-X] infrastructure mostly
unchanged which in turn made it simple to keep the existing
architecture specific management alive.
A similar problem was created in the ARM world with support for IP
block specific message storage. Instead of going all the way to stack
a IP block specific domain on top of the generic MSI domain this ended
in a construct which provides a "global" platform MSI domain which
allows overriding the irq_write_msi_msg() callback per allocation.
In course of the lengthy discussions we identified other abuse of the
MSI infrastructure in wireless drivers, NTB etc. where support for
implementation specific message storage was just mindlessly glued into
the existing infrastructure. Some of this just works by chance on
particular platforms but will fail in hard to diagnose ways when the
driver is used on platforms where the underlying MSI interrupt
management code does not expect the creative abuse.
Another shortcoming of today's PCI/MSI-X support is the inability to
allocate or free individual vectors after the initial enablement of
MSI-X. This results in an works by chance implementation of VFIO (PCI
pass-through) where interrupts on the host side are not set up upfront
to avoid resource exhaustion. They are expanded at run-time when the
guest actually tries to use them. The way how this is implemented is
that the host disables MSI-X and then re-enables it with a larger
number of vectors again. That works by chance because most device
drivers set up all interrupts before the device actually will utilize
them. But that's not universally true because some drivers allocate a
large enough number of vectors but do not utilize them until it's
actually required, e.g. for acceleration support. But at that point
other interrupts of the device might be in active use and the MSI-X
disable/enable dance can just result in losing interrupts and
therefore hard to diagnose subtle problems.
Last but not least the "global" PCI/MSI-X domain approach prevents to
utilize PCI/MSI[-X] and PCI/IMS on the same device due to the fact
that IMS is not longer providing a uniform storage and configuration
model.
The solution to this is to implement the missing step and switch from
global PCI/MSI domains to per device PCI/MSI domains. The resulting
hierarchy then looks like this:
|--- [PCI/MSI] device 1
[Vector]---[Remapping]---|...
|--- [PCI/MSI] device N
which in turn allows to provide support for multiple domains per
device:
|--- [PCI/MSI] device 1
|--- [PCI/IMS] device 1
[Vector]---[Remapping]---|...
|--- [PCI/MSI] device N
|--- [PCI/IMS] device N
This work converts the MSI and PCI/MSI core and the x86 interrupt
domains to the new model, provides new interfaces for post-enable
allocation/free of MSI-X interrupts and the base framework for
PCI/IMS. PCI/IMS has been verified with the work in progress IDXD
driver.
There is work in progress to convert ARM over which will replace the
platform MSI train-wreck. The cleanup of VFIO, NTB and other creative
"solutions" are in the works as well.
Drivers:
- Updates for the LoongArch interrupt chip drivers
- Support for MTK CIRQv2
- The usual small fixes and updates all over the place"
* tag 'irq-core-2022-12-10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (134 commits)
irqchip/ti-sci-inta: Fix kernel doc
irqchip/gic-v2m: Mark a few functions __init
irqchip/gic-v2m: Include arm-gic-common.h
irqchip/irq-mvebu-icu: Fix works by chance pointer assignment
iommu/amd: Enable PCI/IMS
iommu/vt-d: Enable PCI/IMS
x86/apic/msi: Enable PCI/IMS
PCI/MSI: Provide pci_ims_alloc/free_irq()
PCI/MSI: Provide IMS (Interrupt Message Store) support
genirq/msi: Provide constants for PCI/IMS support
x86/apic/msi: Enable MSI_FLAG_PCI_MSIX_ALLOC_DYN
PCI/MSI: Provide post-enable dynamic allocation interfaces for MSI-X
PCI/MSI: Provide prepare_desc() MSI domain op
PCI/MSI: Split MSI-X descriptor setup
genirq/msi: Provide MSI_FLAG_MSIX_ALLOC_DYN
genirq/msi: Provide msi_domain_alloc_irq_at()
genirq/msi: Provide msi_domain_ops:: Prepare_desc()
genirq/msi: Provide msi_desc:: Msi_data
genirq/msi: Provide struct msi_map
x86/apic/msi: Remove arch_create_remap_msi_irq_domain()
...
PCI/IMS works like PCI/MSI-X in the remapping. Just add the feature flag,
but only when on real hardware.
Virtualized IOMMUs need additional support, e.g. for PASID.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Acked-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221124232327.081482253@linutronix.de
Remove the global PCI/MSI irqdomain implementation and provide the required
MSI parent ops so the PCI/MSI code can detect the new parent and setup per
device domains.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Acked-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221124232326.151226317@linutronix.de
Enable MSI parent domain support in the x86 vector domain and fixup the
checks in the iommu implementations to check whether device::msi::domain is
the default MSI parent domain. That keeps the existing logic to protect
e.g. devices behind VMD working.
The interrupt remap PCI/MSI code still works because the underlying vector
domain still provides the same functionality.
None of the other x86 PCI/MSI, e.g. XEN and HyperV, implementations are
affected either. They still work the same way both at the low level and the
PCI/MSI implementations they provide.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Acked-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20221124232326.034672592@linutronix.de
Impacted QAT device IDs that need extra dtlb flush quirk is ranging
from 0x4940 to 0x4943. After bitwise AND device ID with 0xfffc the
result should be 0x4940 instead of 0x494c to identify these devices.
Fixes: e65a6897be ("iommu/vt-d: Add a fix for devices need extra dtlb flush")
Reported-by: Raghunathan Srinivasan <raghunathan.srinivasan@intel.com>
Signed-off-by: Ashok Raj <ashok.raj@intel.com>
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Link: https://lore.kernel.org/r/20221203005610.2927487-1-jacob.jun.pan@linux.intel.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Resolve conflicts in drivers/vfio/vfio_main.c by using the iommfd version.
The rc fix was done a different way when iommufd patches reworked this
code.
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
for_each_pci_dev() is implemented by pci_get_device(). The comment of
pci_get_device() says that it will increase the reference count for the
returned pci_dev and also decrease the reference count for the input
pci_dev @from if it is not NULL.
If we break for_each_pci_dev() loop with pdev not NULL, we need to call
pci_dev_put() to decrease the reference count. Add the missing
pci_dev_put() for the error path to avoid reference count leak.
Fixes: 2e45528930 ("iommu/vt-d: Unify the way to process DMAR device scope array")
Signed-off-by: Xiongfeng Wang <wangxiongfeng2@huawei.com>
Link: https://lore.kernel.org/r/20221121113649.190393-3-wangxiongfeng2@huawei.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
for_each_pci_dev() is implemented by pci_get_device(). The comment of
pci_get_device() says that it will increase the reference count for the
returned pci_dev and also decrease the reference count for the input
pci_dev @from if it is not NULL.
If we break for_each_pci_dev() loop with pdev not NULL, we need to call
pci_dev_put() to decrease the reference count. Add the missing
pci_dev_put() before 'return true' to avoid reference count leak.
Fixes: 89a6079df7 ("iommu/vt-d: Force IOMMU on for platform opt in hint")
Signed-off-by: Xiongfeng Wang <wangxiongfeng2@huawei.com>
Link: https://lore.kernel.org/r/20221121113649.190393-2-wangxiongfeng2@huawei.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
As comment of pci_get_domain_bus_and_slot() says, it returns a pci device
with refcount increment, when finish using it, the caller must decrease
the reference count by calling pci_dev_put(). So call pci_dev_put() after
using the 'pdev' to avoid refcount leak.
Besides, if the 'pdev' is null or intel_svm_prq_report() returns error,
there is no need to trace this fault.
Fixes: 06f4b8d09d ("iommu/vt-d: Remove unnecessary SVA data accesses in page fault path")
Suggested-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Link: https://lore.kernel.org/r/20221119144028.2452731-1-yangyingliang@huawei.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
QAT devices on Intel Sapphire Rapids and Emerald Rapids have a defect in
address translation service (ATS). These devices may inadvertently issue
ATS invalidation completion before posted writes initiated with
translated address that utilized translations matching the invalidation
address range, violating the invalidation completion ordering.
This patch adds an extra device TLB invalidation for the affected devices,
it is needed to ensure no more posted writes with translated address
following the invalidation completion. Therefore, the ordering is
preserved and data-corruption is prevented.
Device TLBs are invalidated under the following six conditions:
1. Device driver does DMA API unmap IOVA
2. Device driver unbind a PASID from a process, sva_unbind_device()
3. PASID is torn down, after PASID cache is flushed. e.g. process
exit_mmap() due to crash
4. Under SVA usage, called by mmu_notifier.invalidate_range() where
VM has to free pages that were unmapped
5. userspace driver unmaps a DMA buffer
6. Cache invalidation in vSVA usage (upcoming)
For #1 and #2, device drivers are responsible for stopping DMA traffic
before unmap/unbind. For #3, iommu driver gets mmu_notifier to
invalidate TLB the same way as normal user unmap which will do an extra
invalidation. The dTLB invalidation after PASID cache flush does not
need an extra invalidation.
Therefore, we only need to deal with #4 and #5 in this patch. #1 is also
covered by this patch due to common code path with #5.
Tested-by: Yuzhang Luo <yuzhang.luo@intel.com>
Reviewed-by: Ashok Raj <ashok.raj@intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Link: https://lore.kernel.org/r/20221130062449.1360063-1-jacob.jun.pan@linux.intel.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
This queries if a domain linked to a device should expect to support
enforce_cache_coherency() so iommufd can negotiate the rules for when a
domain should be shared or not.
For iommufd a device that declares IOMMU_CAP_ENFORCE_CACHE_COHERENCY will
not be attached to a domain that does not support it.
Link: https://lore.kernel.org/r/1-v6-a196d26f289e+11787-iommufd_jgg@nvidia.com
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Tested-by: Yi Liu <yi.l.liu@intel.com>
Tested-by: Lixiao Yang <lixiao.yang@intel.com>
Tested-by: Matthew Rosato <mjrosato@linux.ibm.com>
Tested-by: Yu He <yu.he@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The dmar_domain uses bit field members to indicate the behaviors. Add
a bit field for using first level and remove the flags member to avoid
duplication.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20221118132451.114406-8-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The device_domain_info::domain accurately records the domain attached to
the device. It is unnecessary to check whether the context is present in
the attach_dev path. Remove it to make the code neat.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20221118132451.114406-7-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
dmar_domain_attach_device() is more meaningful according to what this
helper does.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20221118132451.114406-6-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Rename iommu_disable_dev_iotlb() to iommu_disable_pci_caps() to pair with
iommu_enable_pci_caps().
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20221118132451.114406-5-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The Intel IOMMU hardwares support blocking DMA transactions by clearing
the translation table entries. This implements a real blocking domain to
avoid using an empty UNMANAGED domain. The detach_dev callback of the
domain ops is not used in any path. Remove it to avoid dead code as well.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20221118132451.114406-4-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
If domain attaching to device fails, the IOMMU driver should bring the
device to blocking DMA state. The upper layer is expected to recover it
by attaching a new domain. Use device_block_translation() in the error
path of dev_attach to make the behavior specific.
The difference between device_block_translation() and the previous
dmar_remove_one_dev_info() is that, in the scalable mode, it is the
RID2PASID entry instead of context entry being cleared. As a result,
enabling PCI capabilities is moved up.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20221118132451.114406-3-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Whether or not a domain is attached to the device, the pasid table should
always be valid as long as it has been probed. This moves the pasid table
allocation from the domain attaching device path to device probe path and
frees it in the device release path.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20221118132451.114406-2-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
SRS cap is the hardware cap telling if the hardware IOMMU can support
requests seeking supervisor privilege or not. SRE bit in scalable-mode
PASID table entry is treated as Reserved(0) for implementation not
supporting SRS cap.
Checking SRS cap before setting SRE bit can avoid the non-recoverable
fault of "Non-zero reserved field set in PASID Table Entry" caused by
setting SRE bit while there is no SRS cap support. The fault messages
look like below:
DMAR: DRHD: handling fault status reg 2
DMAR: [DMA Read NO_PASID] Request device [00:0d.0] fault addr 0x1154e1000
[fault reason 0x5a]
SM: Non-zero reserved field set in PASID Table Entry
Fixes: 6f7db75e1c ("iommu/vt-d: Add second level page table interface")
Cc: stable@vger.kernel.org
Signed-off-by: Tina Zhang <tina.zhang@intel.com>
Link: https://lore.kernel.org/r/20221115070346.1112273-1-tina.zhang@intel.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20221116051544.26540-3-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The A/D bits are preseted for IOVA over first level(FL) usage for both
kernel DMA (i.e, domain typs is IOMMU_DOMAIN_DMA) and user space DMA
usage (i.e., domain type is IOMMU_DOMAIN_UNMANAGED).
Presetting A bit in FL requires to preset the bit in every related paging
entries, including the non-leaf ones. Otherwise, hardware may treat this
as an error. For example, in a case of ECAP_REG.SMPWC==0, DMA faults might
occur with below DMAR fault messages (wrapped for line length) dumped.
DMAR: DRHD: handling fault status reg 2
DMAR: [DMA Read NO_PASID] Request device [aa:00.0] fault addr 0x10c3a6000
[fault reason 0x90]
SM: A/D bit update needed in first-level entry when set up in no snoop
Fixes: 289b3b005c ("iommu/vt-d: Preset A/D bits for user space DMA usage")
Cc: stable@vger.kernel.org
Signed-off-by: Tina Zhang <tina.zhang@intel.com>
Link: https://lore.kernel.org/r/20221113010324.1094483-1-tina.zhang@intel.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20221116051544.26540-2-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Now that the PCI/MSI core code does early checking for multi-MSI support
X86_IRQ_ALLOC_CONTIGUOUS_VECTORS is not required anymore.
Remove the flag and rely on MSI_FLAG_MULTI_PCI_MSI.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20221111122015.865042356@linutronix.de
This series is to replace the previous EMEDIUMTYPE patch in a VFIO series:
https://lore.kernel.org/kvm/Yxnt9uQTmbqul5lf@8bytes.org/
The purpose is to regulate all existing ->attach_dev callback functions to
use EINVAL exclusively for an incompatibility error between a device and a
domain. This allows VFIO and IOMMUFD to detect such a soft error, and then
try a different domain with the same device.
Among all the patches, the first two are preparatory changes. And then one
patch to update kdocs and another three patches for the enforcement
effort.
Link: https://lore.kernel.org/r/cover.1666042872.git.nicolinc@nvidia.com
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQRRRCHOFoQz/8F5bUaFwuHvBreFYQUCY2JjUQAKCRCFwuHvBreF
YaFbAP492zvOEaZaRxiK4XcdsU1ZBCovB/2Keh/QIQdb7Ig6hgD/dW7TygTP1+4a
Oqpcu/6aLeHvhayfZt1142S3e0HuHwU=
=g5C+
-----END PGP SIGNATURE-----
Merge tag 'for-joerg' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd into core
iommu: Define EINVAL as device/domain incompatibility
This series is to replace the previous EMEDIUMTYPE patch in a VFIO series:
https://lore.kernel.org/kvm/Yxnt9uQTmbqul5lf@8bytes.org/
The purpose is to regulate all existing ->attach_dev callback functions to
use EINVAL exclusively for an incompatibility error between a device and a
domain. This allows VFIO and IOMMUFD to detect such a soft error, and then
try a different domain with the same device.
Among all the patches, the first two are preparatory changes. And then one
patch to update kdocs and another three patches for the enforcement
effort.
Link: https://lore.kernel.org/r/cover.1666042872.git.nicolinc@nvidia.com
Rename iommu-sva-lib.c[h] to iommu-sva.c[h] as it contains all code
for SVA implementation in iommu core.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Tested-by: Zhangfei Gao <zhangfei.gao@linaro.org>
Tested-by: Tony Zhu <tony.zhu@intel.com>
Link: https://lore.kernel.org/r/20221031005917.45690-14-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
These ops'es have been deprecated. There's no need for them anymore.
Remove them to avoid dead code.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Yi Liu <yi.l.liu@intel.com>
Tested-by: Zhangfei Gao <zhangfei.gao@linaro.org>
Tested-by: Tony Zhu <tony.zhu@intel.com>
Link: https://lore.kernel.org/r/20221031005917.45690-11-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Add support for SVA domain allocation and provide an SVA-specific
iommu_domain_ops. This implementation is based on the existing SVA
code. Possible cleanup and refactoring are left for incremental
changes later.
The VT-d driver will also need to support setting a DMA domain to a
PASID of device. Current SVA implementation uses different data
structures to track the domain and device PASID relationship. That's
the reason why we need to check the domain type in remove_dev_pasid
callback. Eventually we'll consolidate the data structures and remove
the need of domain type check.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Yi Liu <yi.l.liu@intel.com>
Tested-by: Tony Zhu <tony.zhu@intel.com>
Link: https://lore.kernel.org/r/20221031005917.45690-8-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The current kernel DMA with PASID support is based on the SVA with a flag
SVM_FLAG_SUPERVISOR_MODE. The IOMMU driver binds the kernel memory address
space to a PASID of the device. The device driver programs the device with
kernel virtual address (KVA) for DMA access. There have been security and
functional issues with this approach:
- The lack of IOTLB synchronization upon kernel page table updates.
(vmalloc, module/BPF loading, CONFIG_DEBUG_PAGEALLOC etc.)
- Other than slight more protection, using kernel virtual address (KVA)
has little advantage over physical address. There are also no use
cases yet where DMA engines need kernel virtual addresses for in-kernel
DMA.
This removes SVM_FLAG_SUPERVISOR_MODE support from the IOMMU interface.
The device drivers are suggested to handle kernel DMA with PASID through
the kernel DMA APIs.
The drvdata parameter in iommu_sva_bind_device() and all callbacks is not
needed anymore. Cleanup them as well.
Link: https://lore.kernel.org/linux-iommu/20210511194726.GP1002214@nvidia.com/
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Fenghua Yu <fenghua.yu@intel.com>
Tested-by: Zhangfei Gao <zhangfei.gao@linaro.org>
Tested-by: Tony Zhu <tony.zhu@intel.com>
Link: https://lore.kernel.org/r/20221031005917.45690-4-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Use this field to keep the number of supported PASIDs that an IOMMU
hardware is able to support. This is a generic attribute of an IOMMU
and lifting it into the per-IOMMU device structure makes it possible
to allocate a PASID for device without calls into the IOMMU drivers.
Any iommu driver that supports PASID related features should set this
field before enabling them on the devices.
In the Intel IOMMU driver, intel_iommu_sm is moved to CONFIG_INTEL_IOMMU
enclave so that the pasid_supported() helper could be used in dmar.c
without compilation errors.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Yi Liu <yi.l.liu@intel.com>
Tested-by: Zhangfei Gao <zhangfei.gao@linaro.org>
Tested-by: Tony Zhu <tony.zhu@intel.com>
Link: https://lore.kernel.org/r/20221031005917.45690-2-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Following the new rules in include/linux/iommu.h kdocs, update all drivers
->attach_dev callback functions to return EINVAL in the failure paths that
are related to domain incompatibility.
Also, drop adjacent error prints to prevent a kernel log spam.
Link: https://lore.kernel.org/r/f52a07f7320da94afe575c9631340d0019a203a7.1666042873.git.nicolinc@nvidia.com
Reviewed-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Following the new rules in include/linux/iommu.h kdocs, EINVAL now can be
used to indicate that domain and device are incompatible by a caller that
treats it as a soft failure and tries attaching to another domain.
On the other hand, there are ->attach_dev callback functions returning it
for obvious device-specific errors. They will result in some inefficiency
in the caller handling routine.
Update these places to corresponding errnos following the new rules.
Link: https://lore.kernel.org/r/5924c03bea637f05feb2a20d624bae086b555ec5.1666042872.git.nicolinc@nvidia.com
Reviewed-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
A splat from kmem_cache_destroy() was seen with a kernel prior to
commit ee2653bbe8 ("iommu/vt-d: Remove domain and devinfo mempool")
when there was a failure in init_dmars(), because the iommu_domain
cache still had objects. While the mempool code is now gone, there
still is a leak of the si_domain memory if init_dmars() fails. So
clean up si_domain in the init_dmars() error path.
Cc: Lu Baolu <baolu.lu@linux.intel.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Will Deacon <will@kernel.org>
Cc: Robin Murphy <robin.murphy@arm.com>
Fixes: 86080ccc22 ("iommu/vt-d: Allocate si_domain in init_dmars()")
Signed-off-by: Jerry Snitselaar <jsnitsel@redhat.com>
Link: https://lore.kernel.org/r/20221010144842.308890-1-jsnitsel@redhat.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Commit 5f64ce5411 ("iommu/vt-d: Duplicate iommu_resv_region objects
per device list") converted rcu_lock in get_resv_regions to
dmar_global_lock to allow sleeping in iommu_alloc_resv_region(). This
introduced possible recursive locking if get_resv_regions is called from
within a section where intel_iommu_init() already holds dmar_global_lock.
Especially, after commit 57365a04c9 ("iommu: Move bus setup to IOMMU
device registration"), below lockdep splats could always be seen.
============================================
WARNING: possible recursive locking detected
6.0.0-rc4+ #325 Tainted: G I
--------------------------------------------
swapper/0/1 is trying to acquire lock:
ffffffffa8a18c90 (dmar_global_lock){++++}-{3:3}, at:
intel_iommu_get_resv_regions+0x25/0x270
but task is already holding lock:
ffffffffa8a18c90 (dmar_global_lock){++++}-{3:3}, at:
intel_iommu_init+0x36d/0x6ea
...
Call Trace:
<TASK>
dump_stack_lvl+0x48/0x5f
__lock_acquire.cold.73+0xad/0x2bb
lock_acquire+0xc2/0x2e0
? intel_iommu_get_resv_regions+0x25/0x270
? lock_is_held_type+0x9d/0x110
down_read+0x42/0x150
? intel_iommu_get_resv_regions+0x25/0x270
intel_iommu_get_resv_regions+0x25/0x270
iommu_create_device_direct_mappings.isra.28+0x8d/0x1c0
? iommu_get_dma_cookie+0x6d/0x90
bus_iommu_probe+0x19f/0x2e0
iommu_device_register+0xd4/0x130
intel_iommu_init+0x3e1/0x6ea
? iommu_setup+0x289/0x289
? rdinit_setup+0x34/0x34
pci_iommu_init+0x12/0x3a
do_one_initcall+0x65/0x320
? rdinit_setup+0x34/0x34
? rcu_read_lock_sched_held+0x5a/0x80
kernel_init_freeable+0x28a/0x2f3
? rest_init+0x1b0/0x1b0
kernel_init+0x1a/0x130
ret_from_fork+0x1f/0x30
</TASK>
This rolls back dmar_global_lock to rcu_lock in get_resv_regions to avoid
the lockdep splat.
Fixes: 57365a04c9 ("iommu: Move bus setup to IOMMU device registration")
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Tested-by: Alex Williamson <alex.williamson@redhat.com>
Link: https://lore.kernel.org/r/20220927053109.4053662-3-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Add gfp parameter to iommu_alloc_resv_region() for the callers to specify
the memory allocation behavior. Thus iommu_alloc_resv_region() could also
be available in critical contexts.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Tested-by: Alex Williamson <alex.williamson@redhat.com>
Link: https://lore.kernel.org/r/20220927053109.4053662-2-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Some VT-d hardware implementations invalidate all DMA remapping hardware
translation caches as part of SRTP flow. The VT-d spec adds a ESRTPS
(Enhanced Set Root Table Pointer Support, section 11.4.2 in VT-d spec)
capability bit to indicate this. With this bit set, software has no need
to issue the global invalidation request.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20220919062523.3438951-3-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Some VT-d hardware implementations invalidate all interrupt remapping
hardware translation caches as part of SIRTP flow. The VT-d spec adds
a ESIRTPS (Enhanced Set Interrupt Remap Table Pointer Support, section
11.4.2 in VT-d spec) capability bit to indicate this.
The spec also states in 11.4.4 that hardware also performs global
invalidation on all interrupt remapping caches as part of Interrupt
Remapping Disable operation if ESIRTPS capability bit is set.
This checks the ESIRTPS capability bit and skip software global cache
invalidation if it's set.
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20220921065741.3572495-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
This renaming better describes it is for first level page table (a.k.a
first stage page table since VT-d spec 3.4).
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20220916071326.2223901-1-yi.l.liu@intel.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
It is not used anywhere in the tree. Remove it to avoid dead code.
No functional change intended.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20220915081645.1834555-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Previously the PCI PASID and PRI capabilities are enabled in the path of
iommu device probe only if INTEL_IOMMU_SVM is configured and the device
supports ATS. As we've already decoupled the I/O page fault handler from
SVA, we could also decouple PASID and PRI enabling from it to make room
for growth of new features like kernel DMA with PASID, SIOV and nested
translation.
At the same time, the iommu_enable_dev_iotlb() helper is also called in
iommu_dev_enable_feature(dev, IOMMU_DEV_FEAT_SVA) path. It's unnecessary
and duplicate. This cleanups this helper to make the code neat.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20220915085814.2261409-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The existing I/O page fault handling code accesses the per-PASID SVA data
structures. This is unnecessary and makes the fault handling code only
suitable for SVA scenarios. This removes the SVA data accesses from the
I/O page fault reporting and responding code, so that the fault handling
code could be generic.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20220914011821.400986-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
This reverts commit 9cd4f14344.
Some issues were reported on the original commit. Some thunderbolt devices
don't work anymore due to the following DMA fault.
DMAR: DRHD: handling fault status reg 2
DMAR: [INTR-REMAP] Request device [09:00.0] fault index 0x8080
[fault reason 0x25]
Blocked a compatibility format interrupt request
Bring it back for now to avoid functional regression.
Fixes: 9cd4f14344 ("iommu/vt-d: Fix possible recursive locking in intel_iommu_init()")
Link: https://lore.kernel.org/linux-iommu/485A6EA5-6D58-42EA-B298-8571E97422DE@getmailspring.com/
Link: https://bugzilla.kernel.org/show_bug.cgi?id=216497
Cc: Mika Westerberg <mika.westerberg@linux.intel.com>
Cc: <stable@vger.kernel.org> # 5.19.x
Reported-and-tested-by: George Hilliard <thirtythreeforty@gmail.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20220920081701.3453504-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The global rwsem dmar_global_lock was introduced by commit 3a5670e8ac
("iommu/vt-d: Introduce a rwsem to protect global data structures"). It
is used to protect DMAR related global data from DMAR hotplug operations.
The dmar_global_lock used in the intel_iommu_init() might cause recursive
locking issue, for example, intel_iommu_get_resv_regions() is taking the
dmar_global_lock from within a section where intel_iommu_init() already
holds it via probe_acpi_namespace_devices().
Using dmar_global_lock in intel_iommu_init() could be relaxed since it is
unlikely that any IO board must be hot added before the IOMMU subsystem is
initialized. This eliminates the possible recursive locking issue by moving
down DMAR hotplug support after the IOMMU is initialized and removing the
uses of dmar_global_lock in intel_iommu_init().
Fixes: d5692d4af0 ("iommu/vt-d: Fix suspicious RCU usage in probe_acpi_namespace_devices()")
Reported-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/894db0ccae854b35c73814485569b634237b5538.1657034828.git.robin.murphy@arm.com
Link: https://lore.kernel.org/r/20220718235325.3952426-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
With CONFIG_INTEL_IOMMU_DEBUGFS enabled, below lockdep splat are seen
when an I/O fault occurs on a machine with an Intel IOMMU in it.
DMAR: DRHD: handling fault status reg 3
DMAR: [DMA Write NO_PASID] Request device [00:1a.0] fault addr 0x0
[fault reason 0x05] PTE Write access is not set
DMAR: Dump dmar0 table entries for IOVA 0x0
DMAR: root entry: 0x0000000127f42001
DMAR: context entry: hi 0x0000000000001502, low 0x000000012d8ab001
================================
WARNING: inconsistent lock state
5.20.0-0.rc0.20220812git7ebfc85e2cd7.10.fc38.x86_64 #1 Not tainted
--------------------------------
inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage.
rngd/1006 [HC1[1]:SC0[0]:HE0:SE1] takes:
ff177021416f2d78 (&k->k_lock){?.+.}-{2:2}, at: klist_next+0x1b/0x160
{HARDIRQ-ON-W} state was registered at:
lock_acquire+0xce/0x2d0
_raw_spin_lock+0x33/0x80
klist_add_tail+0x46/0x80
bus_add_device+0xee/0x150
device_add+0x39d/0x9a0
add_memory_block+0x108/0x1d0
memory_dev_init+0xe1/0x117
driver_init+0x43/0x4d
kernel_init_freeable+0x1c2/0x2cc
kernel_init+0x16/0x140
ret_from_fork+0x1f/0x30
irq event stamp: 7812
hardirqs last enabled at (7811): [<ffffffff85000e86>] asm_sysvec_apic_timer_interrupt+0x16/0x20
hardirqs last disabled at (7812): [<ffffffff84f16894>] irqentry_enter+0x54/0x60
softirqs last enabled at (7794): [<ffffffff840ff669>] __irq_exit_rcu+0xf9/0x170
softirqs last disabled at (7787): [<ffffffff840ff669>] __irq_exit_rcu+0xf9/0x170
The klist iterator functions using spin_*lock_irq*() but the klist
insertion functions using spin_*lock(), combined with the Intel DMAR
IOMMU driver iterating over klists from atomic (hardirq) context, where
pci_get_domain_bus_and_slot() calls into bus_find_device() which iterates
over klists.
As currently there's no plan to fix the klist to make it safe to use in
atomic context, this fixes the lockdep splat by avoid calling
pci_get_domain_bus_and_slot() in the hardirq context.
Fixes: 8ac0b64b97 ("iommu/vt-d: Use pci_get_domain_bus_and_slot() in pgtable_walk()")
Reported-by: Lennert Buytenhek <buytenh@wantstofly.org>
Link: https://lore.kernel.org/linux-iommu/Yvo2dfpEh%2FWC+Wrr@wantstofly.org/
Link: https://lore.kernel.org/linux-iommu/YvyBdPwrTuHHbn5X@wantstofly.org/
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20220819015949.4795-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The per domain spinlock is acquired in iommu_flush_dev_iotlb(), which
is possbile to be called in the interrupt context. For example, the
drm-intel's CI system got completely blocked with below error:
WARNING: inconsistent lock state
6.0.0-rc1-CI_DRM_11990-g6590d43d39b9+ #1 Not tainted
--------------------------------
inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
swapper/6/0 [HC0[0]:SC1[1]:HE1:SE0] takes:
ffff88810440d678 (&domain->lock){+.?.}-{2:2}, at: iommu_flush_dev_iotlb.part.61+0x23/0x80
{SOFTIRQ-ON-W} state was registered at:
lock_acquire+0xd3/0x310
_raw_spin_lock+0x2a/0x40
domain_update_iommu_cap+0x20b/0x2c0
intel_iommu_attach_device+0x5bd/0x860
__iommu_attach_device+0x18/0xe0
bus_iommu_probe+0x1f3/0x2d0
bus_set_iommu+0x82/0xd0
intel_iommu_init+0xe45/0x102a
pci_iommu_init+0x9/0x31
do_one_initcall+0x53/0x2f0
kernel_init_freeable+0x18f/0x1e1
kernel_init+0x11/0x120
ret_from_fork+0x1f/0x30
irq event stamp: 162354
hardirqs last enabled at (162354): [<ffffffff81b59274>] _raw_spin_unlock_irqrestore+0x54/0x70
hardirqs last disabled at (162353): [<ffffffff81b5901b>] _raw_spin_lock_irqsave+0x4b/0x50
softirqs last enabled at (162338): [<ffffffff81e00323>] __do_softirq+0x323/0x48e
softirqs last disabled at (162349): [<ffffffff810c1588>] irq_exit_rcu+0xb8/0xe0
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&domain->lock);
<Interrupt>
lock(&domain->lock);
*** DEADLOCK ***
1 lock held by swapper/6/0:
This coverts the spin_lock/unlock() into the irq save/restore varieties
to fix the recursive locking issues.
Fixes: ffd5869d93 ("iommu/vt-d: Replace spin_lock_irqsave() with spin_lock()")
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Acked-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://lore.kernel.org/r/20220817025650.3253959-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The Intel IOMMU driver possibly selects between the first-level and the
second-level translation tables for DMA address translation. However,
the levels of page-table walks for the 4KB base page size are calculated
from the SAGAW field of the capability register, which is only valid for
the second-level page table. This causes the IOMMU driver to stop working
if the hardware (or the emulated IOMMU) advertises only first-level
translation capability and reports the SAGAW field as 0.
This solves the above problem by considering both the first level and the
second level when calculating the supported page table levels.
Fixes: b802d070a5 ("iommu/vt-d: Use iova over first level")
Cc: stable@vger.kernel.org
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20220817023558.3253263-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The translation table copying code for kdump kernels is currently based
on the extended root/context entry formats of ECS mode defined in older
VT-d v2.5, and doesn't handle the scalable mode formats. This causes
the kexec capture kernel boot failure with DMAR faults if the IOMMU was
enabled in scalable mode by the previous kernel.
The ECS mode has already been deprecated by the VT-d spec since v3.0 and
Intel IOMMU driver doesn't support this mode as there's no real hardware
implementation. Hence this converts ECS checking in copying table code
into scalable mode.
The existing copying code consumes a bit in the context entry as a mark
of copied entry. It needs to work for the old format as well as for the
extended context entries. As it's hard to find such a common bit for both
legacy and scalable mode context entries. This replaces it with a per-
IOMMU bitmap.
Fixes: 7373a8cc38 ("iommu/vt-d: Setup context and enable RID2PASID support")
Cc: stable@vger.kernel.org
Reported-by: Jerry Snitselaar <jsnitsel@redhat.com>
Tested-by: Wen Jin <wen.jin@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20220817011035.3250131-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Although iommu-dma is a per-architecture chonce, that is currently
implemented in a rather haphazard way. Selecting from the arch Kconfig
was the original logical approach, but is complicated by having to
manage dependencies; conversely, selecting from drivers ends up hiding
the architecture dependency *too* well. Instead, let's just have it
enable itself automatically when IOMMU API support is enabled for the
relevant architectures. It can't get much clearer than that.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/2e33c8bc2b1bb478157b7964bfed976cb7466139.1660668998.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Clean up the remaining trivial bus_set_iommu() callsites along
with the implementation. Now drivers only have to know and care
about iommu_device instances, phew!
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Tested-by: Matthew Rosato <mjrosato@linux.ibm.com> # s390
Tested-by: Niklas Schnelle <schnelle@linux.ibm.com> # s390
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/ea383d5f4d74ffe200ab61248e5de6e95846180a.1660572783.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Currently we rely on registering all our instances before initially
allowing any .probe_device calls via bus_set_iommu(). In preparation for
phasing out the latter, make sure we won't inadvertently return success
for a device associated with a known but not yet registered instance,
otherwise we'll run straight into iommu_group_get_for_dev() trying to
use NULL ops.
That also highlights an issue with intel_iommu_get_resv_regions() taking
dmar_global_lock from within a section where intel_iommu_init() already
holds it, which already exists via probe_acpi_namespace_devices() when
an ANDD device is probed, but gets more obvious with the upcoming change
to iommu_device_register(). Since they are both read locks it manages
not to deadlock in practice, and a more in-depth rework of this locking
is underway, so no attempt is made to address it here.
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/579f2692291bcbfc3ac64f7456fcff0d629af131.1660572783.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
With all callers now converted to the device-specific version, retire
the old bus-based interface, and give drivers the chance to indicate
accurate per-instance capabilities.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/d8bd8777d06929ad8f49df7fc80e1b9af32a41b5.1660574547.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
This branch consists of:
Qu Wenruo:
lib: bitmap: fix the duplicated comments on bitmap_to_arr64()
https://lore.kernel.org/lkml/0d85e1dbad52ad7fb5787c4432bdb36cbd24f632.1656063005.git.wqu@suse.com/
Alexander Lobakin:
bitops: let optimize out non-atomic bitops on compile-time constants
https://lore.kernel.org/lkml/20220624121313.2382500-1-alexandr.lobakin@intel.com/T/
Yury Norov:
lib: cleanup bitmap-related headers
https://lore.kernel.org/linux-arm-kernel/YtCVeOGLiQ4gNPSf@yury-laptop/T/#m305522194c4d38edfdaffa71fcaaf2e2ca00a961
Alexander Lobakin:
x86/olpc: fix 'logical not is only applied to the left hand side'
https://www.spinics.net/lists/kernel/msg4440064.html
Yury Norov:
lib/nodemask: inline wrappers around bitmap
https://lore.kernel.org/all/20220723214537.2054208-1-yury.norov@gmail.com/
-----BEGIN PGP SIGNATURE-----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=4dTW
-----END PGP SIGNATURE-----
Merge tag 'bitmap-6.0-rc1' of https://github.com/norov/linux
Pull bitmap updates from Yury Norov:
- fix the duplicated comments on bitmap_to_arr64() (Qu Wenruo)
- optimize out non-atomic bitops on compile-time constants (Alexander
Lobakin)
- cleanup bitmap-related headers (Yury Norov)
- x86/olpc: fix 'logical not is only applied to the left hand side'
(Alexander Lobakin)
- lib/nodemask: inline wrappers around bitmap (Yury Norov)
* tag 'bitmap-6.0-rc1' of https://github.com/norov/linux: (26 commits)
lib/nodemask: inline next_node_in() and node_random()
powerpc: drop dependency on <asm/machdep.h> in archrandom.h
x86/olpc: fix 'logical not is only applied to the left hand side'
lib/cpumask: move some one-line wrappers to header file
headers/deps: mm: align MANITAINERS and Docs with new gfp.h structure
headers/deps: mm: Split <linux/gfp_types.h> out of <linux/gfp.h>
headers/deps: mm: Optimize <linux/gfp.h> header dependencies
lib/cpumask: move trivial wrappers around find_bit to the header
lib/cpumask: change return types to unsigned where appropriate
cpumask: change return types to bool where appropriate
lib/bitmap: change type of bitmap_weight to unsigned long
lib/bitmap: change return types to bool where appropriate
arm: align find_bit declarations with generic kernel
iommu/vt-d: avoid invalid memory access via node_online(NUMA_NO_NODE)
lib/test_bitmap: test the tail after bitmap_to_arr64()
lib/bitmap: fix off-by-one in bitmap_to_arr64()
lib: test_bitmap: add compile-time optimization/evaluations assertions
bitmap: don't assume compiler evaluates small mem*() builtins calls
net/ice: fix initializing the bitmap in the switch code
bitops: let optimize out non-atomic bitops on compile-time constants
...
bitmap_weight() doesn't return negative values, so change it's type
to unsigned long. It may help compiler to generate better code and
catch bugs.
Signed-off-by: Yury Norov <yury.norov@gmail.com>
The g_iommus and g_num_of_iommus is not used anywhere. Remove them to
avoid dead code.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Steve Wahl <steve.wahl@hpe.com>
Link: https://lore.kernel.org/r/20220702015610.2849494-6-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The Intel IOMMU hot-add process starts from dmar_device_hotplug(). It
uses the global dmar_global_lock to synchronize all the hot-add and
hot-remove paths. In the hot-add path, the new IOMMU data structures
are allocated firstly by dmar_parse_one_drhd() and then initialized by
dmar_hp_add_drhd(). All the IOMMU units are allocated and initialized
in the same synchronized path. There is no case where any IOMMU unit
is created and then initialized for multiple times.
This removes the unnecessary check in intel_iommu_add() which is the
last reference place of the global IOMMU array.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Steve Wahl <steve.wahl@hpe.com>
Link: https://lore.kernel.org/r/20220702015610.2849494-5-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
When a DMA domain is attached to a device, it needs to allocate a domain
ID from its IOMMU. Currently, the domain ID information is stored in two
static arrays embedded in the domain structure. This can lead to memory
waste when the driver is running on a small platform.
This optimizes these static arrays by replacing them with an xarray and
consuming memory on demand.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Steve Wahl <steve.wahl@hpe.com>
Link: https://lore.kernel.org/r/20220702015610.2849494-4-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Switch dmar unit sequence id allocation and release from bitmap to IDA
interface.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Steve Wahl <steve.wahl@hpe.com>
Link: https://lore.kernel.org/r/20220702015610.2849494-3-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
It is not used anywhere. Remove it to avoid dead code.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Steve Wahl <steve.wahl@hpe.com>
Link: https://lore.kernel.org/r/20220702015610.2849494-2-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Using a global device_domain_lock spinlock to protect per-domain device
tracking lists is an inefficient way, especially considering this lock
is also needed in the hot paths. This optimizes the locking mechanism
by converting the global lock to per domain lock.
On the other hand, as the device tracking lists are never accessed in
any interrupt context, there is no need to disable interrupts while
spinning. Replace irqsave variant with spinlock calls.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20220706025524.2904370-12-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The device_domain_lock is used to protect the device tracking list of
a domain. Remove unnecessary spin_lock/unlock()'s and move the necessary
ones around the list access.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20220706025524.2904370-11-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Fold __dmar_remove_one_dev_info() into dmar_remove_one_dev_info() which
is its only caller. Make the spin lock critical range only cover the
device list change code and remove some unnecessary checks.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20220706025524.2904370-10-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
When the IOMMU domain is about to be freed, it should not be set on any
device. Instead of silently dealing with some bug cases, it's better to
trigger a warning to report and fix any potential bugs at the first time.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20220706025524.2904370-9-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The iommu->lock is used to protect the per-IOMMU pasid directory table
and pasid table. Move the spinlock acquisition/release into the helpers
to make the code self-contained.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20220706025524.2904370-8-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The iommu->lock is used to protect the per-IOMMU domain ID resource.
Moving the lock into the ID alloc/free helpers makes the code more
compact. At the same time, the device_domain_lock is irrelevant to
the domain ID resource, remove its assertion as well.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20220706025524.2904370-7-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The iommu->lock is used to protect changes in root/context/pasid tables
and domain ID allocation. There's no use case to change these resources
in any interrupt context. Therefore, it is unnecessary to disable the
interrupts when the spinlock is held. The same thing happens on the
device_domain_lock side, which protects the device domain attachment
information. This replaces spin_lock/unlock_irqsave/irqrestore() calls
with the normal spin_lock/unlock().
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20220706025524.2904370-6-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The IOMMU root table is allocated and freed in the IOMMU initialization
code in static boot or hot-remove paths. There's no need for a spinlock.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20220706025524.2904370-5-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Use pci_get_domain_bus_and_slot() instead of searching the global list
to retrieve the pci device pointer. This also removes the global
device_domain_list as there isn't any consumer anymore.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20220706025524.2904370-4-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The disable_dmar_iommu() is called when IOMMU initialization fails or
the IOMMU is hot-removed from the system. In both cases, there is no
need to clear the IOMMU translation data structures for devices.
On the initialization path, the device probing only happens after the
IOMMU is initialized successfully, hence there're no translation data
structures.
On the hot-remove path, there is no real use case where the IOMMU is
hot-removed, but the devices that it manages are still alive in the
system. The translation data structures were torn down during device
release, hence there's no need to repeat it in IOMMU hot-remove path
either. This removes the unnecessary code and only leaves a check.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20220706025524.2904370-3-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The domain_translation_struct debugfs node is used to dump the DMAR page
tables for the PCI devices. It potentially races with setting domains to
devices. The existing code uses the global spinlock device_domain_lock to
avoid the races.
This removes the use of device_domain_lock outside of iommu.c by replacing
it with the group mutex lock. Using the group mutex lock is cleaner and
more compatible to following cleanups.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20220706025524.2904370-2-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
This header file is private to the Intel IOMMU driver. Move it to the
driver folder.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Steve Wahl <steve.wahl@hpe.com>
Link: https://lore.kernel.org/r/20220514014322.2927339-8-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
tboot_force_iommu() is only called by the Intel IOMMU driver. Move the
helper into that driver. No functional change intended.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Steve Wahl <steve.wahl@hpe.com>
Link: https://lore.kernel.org/r/20220514014322.2927339-7-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The exported symbol intel_iommu_gfx_mapped is not used anywhere in the
tree. Remove it to avoid dead code.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Steve Wahl <steve.wahl@hpe.com>
Link: https://lore.kernel.org/r/20220514014322.2927339-4-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
This header file is private to the Intel IOMMU driver. Move it to the
driver folder.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Steve Wahl <steve.wahl@hpe.com>
Link: https://lore.kernel.org/r/20220514014322.2927339-2-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
All drivers that implement get_resv_regions just use
generic_put_resv_regions to implement the put side. Remove the
indirections and document the allocations constraints.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20220708080616.238833-4-hch@lst.de
Signed-off-by: Joerg Roedel <jroedel@suse.de>
KASAN reports:
[ 4.668325][ T0] BUG: KASAN: wild-memory-access in dmar_parse_one_rhsa (arch/x86/include/asm/bitops.h:214 arch/x86/include/asm/bitops.h:226 include/asm-generic/bitops/instrumented-non-atomic.h:142 include/linux/nodemask.h:415 drivers/iommu/intel/dmar.c:497)
[ 4.676149][ T0] Read of size 8 at addr 1fffffff85115558 by task swapper/0/0
[ 4.683454][ T0]
[ 4.685638][ T0] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.19.0-rc3-00004-g0e862838f290 #1
[ 4.694331][ T0] Hardware name: Supermicro SYS-5018D-FN4T/X10SDV-8C-TLN4F, BIOS 1.1 03/02/2016
[ 4.703196][ T0] Call Trace:
[ 4.706334][ T0] <TASK>
[ 4.709133][ T0] ? dmar_parse_one_rhsa (arch/x86/include/asm/bitops.h:214 arch/x86/include/asm/bitops.h:226 include/asm-generic/bitops/instrumented-non-atomic.h:142 include/linux/nodemask.h:415 drivers/iommu/intel/dmar.c:497)
after converting the type of the first argument (@nr, bit number)
of arch_test_bit() from `long` to `unsigned long`[0].
Under certain conditions (for example, when ACPI NUMA is disabled
via command line), pxm_to_node() can return %NUMA_NO_NODE (-1).
It is valid 'magic' number of NUMA node, but not valid bit number
to use in bitops.
node_online() eventually descends to test_bit() without checking
for the input, assuming it's on caller side (which might be good
for perf-critical tasks). There, -1 becomes %ULONG_MAX which leads
to an insane array index when calculating bit position in memory.
For now, add an explicit check for @node being not %NUMA_NO_NODE
before calling test_bit(). The actual logics didn't change here
at all.
[0] 0e862838f2
Fixes: ee34b32d8c ("dmar: support for parsing Remapping Hardware Static Affinity structure")
Cc: stable@vger.kernel.org # 2.6.33+
Reported-by: kernel test robot <oliver.sang@intel.com>
Signed-off-by: Alexander Lobakin <alexandr.lobakin@intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Yury Norov <yury.norov@gmail.com>
The IOMMU driver shares the pasid table for PCI alias devices. When the
RID2PASID entry of the shared pasid table has been filled by the first
device, the subsequent device will encounter the "DMAR: Setup RID2PASID
failed" failure as the pasid entry has already been marked as present.
As the result, the IOMMU probing process will be aborted.
On the contrary, when any alias device is hot-removed from the system,
for example, by writing to /sys/bus/pci/devices/.../remove, the shared
RID2PASID will be cleared without any notifications to other devices.
As the result, any DMAs from those rest devices are blocked.
Sharing pasid table among PCI alias devices could save two memory pages
for devices underneath the PCIe-to-PCI bridges. Anyway, considering that
those devices are rare on modern platforms that support VT-d in scalable
mode and the saved memory is negligible, it's reasonable to remove this
part of immature code to make the driver feasible and stable.
Fixes: ef848b7e5a ("iommu/vt-d: Setup pasid entry for RID2PASID support")
Reported-by: Chenyi Qiang <chenyi.qiang@intel.com>
Reported-by: Ethan Zhao <haifeng.zhao@linux.intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Ethan Zhao <haifeng.zhao@linux.intel.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20220623065720.727849-1-baolu.lu@linux.intel.com
Link: https://lore.kernel.org/r/20220625133430.2200315-2-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Notifier calling chain uses priority to determine the execution
order of the notifiers or listeners registered to the chain.
PCI bus device hot add utilizes the notification mechanism.
The current code sets low priority (INT_MIN) to Intel
dmar_pci_bus_notifier and postpones DMAR decoding after adding
new device into IOMMU. The result is that struct device pointer
cannot be found in DRHD search for the new device's DMAR/IOMMU.
Subsequently, the device is put under the "catch-all" IOMMU
instead of the correct one. This could cause system hang when
device TLB invalidation is sent to the wrong IOMMU. Invalidation
timeout error and hard lockup have been observed and data
inconsistency/crush may occur as well.
This patch fixes the issue by setting a positive priority(1) for
dmar_pci_bus_notifier while the priority of IOMMU bus notifier
uses the default value(0), therefore DMAR decoding will be in
advance of DRHD search for a new device to find the correct IOMMU.
Following is a 2-step example that triggers the bug by simulating
PCI device hot add behavior in Intel Sapphire Rapids server.
echo 1 > /sys/bus/pci/devices/0000:6a:01.0/remove
echo 1 > /sys/bus/pci/rescan
Fixes: 59ce0515cd ("iommu/vt-d: Update DRHD/RMRR/ATSR device scope")
Cc: stable@vger.kernel.org # v3.15+
Reported-by: Zhang, Bernice <bernice.zhang@intel.com>
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: Yian Chen <yian.chen@intel.com>
Link: https://lore.kernel.org/r/20220521002115.1624069-1-yian.chen@intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Including:
- Intel VT-d driver updates
- Domain force snooping improvement.
- Cleanups, no intentional functional changes.
- ARM SMMU driver updates
- Add new Qualcomm device-tree compatible strings
- Add new Nvidia device-tree compatible string for Tegra234
- Fix UAF in SMMUv3 shared virtual addressing code
- Force identity-mapped domains for users of ye olde SMMU
legacy binding
- Minor cleanups
- Patches to fix a BUG_ON in the vfio_iommu_group_notifier
- Groundwork for upcoming iommufd framework
- Introduction of DMA ownership so that an entire IOMMU group
is either controlled by the kernel or by user-space
- MT8195 and MT8186 support in the Mediatek IOMMU driver
- Patches to make forcing of cache-coherent DMA more coherent
between IOMMU drivers
- Fixes for thunderbolt device DMA protection
- Various smaller fixes and cleanups
-----BEGIN PGP SIGNATURE-----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=W0hj
-----END PGP SIGNATURE-----
Merge tag 'iommu-updates-v5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu
Pull iommu updates from Joerg Roedel:
- Intel VT-d driver updates:
- Domain force snooping improvement.
- Cleanups, no intentional functional changes.
- ARM SMMU driver updates:
- Add new Qualcomm device-tree compatible strings
- Add new Nvidia device-tree compatible string for Tegra234
- Fix UAF in SMMUv3 shared virtual addressing code
- Force identity-mapped domains for users of ye olde SMMU legacy
binding
- Minor cleanups
- Fix a BUG_ON in the vfio_iommu_group_notifier:
- Groundwork for upcoming iommufd framework
- Introduction of DMA ownership so that an entire IOMMU group is
either controlled by the kernel or by user-space
- MT8195 and MT8186 support in the Mediatek IOMMU driver
- Make forcing of cache-coherent DMA more coherent between IOMMU
drivers
- Fixes for thunderbolt device DMA protection
- Various smaller fixes and cleanups
* tag 'iommu-updates-v5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (88 commits)
iommu/amd: Increase timeout waiting for GA log enablement
iommu/s390: Tolerate repeat attach_dev calls
iommu/vt-d: Remove hard coding PGSNP bit in PASID entries
iommu/vt-d: Remove domain_update_iommu_snooping()
iommu/vt-d: Check domain force_snooping against attached devices
iommu/vt-d: Block force-snoop domain attaching if no SC support
iommu/vt-d: Size Page Request Queue to avoid overflow condition
iommu/vt-d: Fold dmar_insert_one_dev_info() into its caller
iommu/vt-d: Change return type of dmar_insert_one_dev_info()
iommu/vt-d: Remove unneeded validity check on dev
iommu/dma: Explicitly sort PCI DMA windows
iommu/dma: Fix iova map result check bug
iommu/mediatek: Fix NULL pointer dereference when printing dev_name
iommu: iommu_group_claim_dma_owner() must always assign a domain
iommu/arm-smmu: Force identity domains for legacy binding
iommu/arm-smmu: Support Tegra234 SMMU
dt-bindings: arm-smmu: Add compatible for Tegra234 SOC
dt-bindings: arm-smmu: Document nvidia,memory-controller property
iommu/arm-smmu-qcom: Add SC8280XP support
dt-bindings: arm-smmu: Add compatible for Qualcomm SC8280XP
...
- don't over-decrypt memory (Robin Murphy)
- takes min align mask into account for the swiotlb max mapping size
(Tianyu Lan)
- use GFP_ATOMIC in dma-debug (Mikulas Patocka)
- fix DMA_ATTR_NO_KERNEL_MAPPING on xen/arm (me)
- don't fail on highmem CMA pages in dma_direct_alloc_pages (me)
- cleanup swiotlb initialization and share more code with swiotlb-xen
(me, Stefano Stabellini)
-----BEGIN PGP SIGNATURE-----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=n2rk
-----END PGP SIGNATURE-----
Merge tag 'dma-mapping-5.19-2022-05-25' of git://git.infradead.org/users/hch/dma-mapping
Pull dma-mapping updates from Christoph Hellwig:
- don't over-decrypt memory (Robin Murphy)
- takes min align mask into account for the swiotlb max mapping size
(Tianyu Lan)
- use GFP_ATOMIC in dma-debug (Mikulas Patocka)
- fix DMA_ATTR_NO_KERNEL_MAPPING on xen/arm (me)
- don't fail on highmem CMA pages in dma_direct_alloc_pages (me)
- cleanup swiotlb initialization and share more code with swiotlb-xen
(me, Stefano Stabellini)
* tag 'dma-mapping-5.19-2022-05-25' of git://git.infradead.org/users/hch/dma-mapping: (23 commits)
dma-direct: don't over-decrypt memory
swiotlb: max mapping size takes min align mask into account
swiotlb: use the right nslabs-derived sizes in swiotlb_init_late
swiotlb: use the right nslabs value in swiotlb_init_remap
swiotlb: don't panic when the swiotlb buffer can't be allocated
dma-debug: change allocation mode from GFP_NOWAIT to GFP_ATIOMIC
dma-direct: don't fail on highmem CMA pages in dma_direct_alloc_pages
swiotlb-xen: fix DMA_ATTR_NO_KERNEL_MAPPING on arm
x86: remove cruft from <asm/dma-mapping.h>
swiotlb: remove swiotlb_init_with_tbl and swiotlb_init_late_with_tbl
swiotlb: merge swiotlb-xen initialization into swiotlb
swiotlb: provide swiotlb_init variants that remap the buffer
swiotlb: pass a gfp_mask argument to swiotlb_init_late
swiotlb: add a SWIOTLB_ANY flag to lift the low memory restriction
swiotlb: make the swiotlb_init interface more useful
x86: centralize setting SWIOTLB_FORCE when guest memory encryption is enabled
x86: remove the IOMMU table infrastructure
MIPS/octeon: use swiotlb_init instead of open coding it
arm/xen: don't check for xen_initial_domain() in xen_create_contiguous_region
swiotlb: rename swiotlb_late_init_with_default_size
...
As domain->force_snooping only impacts the devices attached with the
domain, there's no need to check against all IOMMU units. On the other
hand, force_snooping could be set on a domain no matter whether it has
been attached or not, and once set it is an immutable flag. If no
device attached, the operation always succeeds. Then this empty domain
can be only attached to a device of which the IOMMU supports snoop
control.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20220508123525.1973626-1-baolu.lu@linux.intel.com
Link: https://lore.kernel.org/r/20220510023407.2759143-7-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Lu Baolu