To include a pointer to per PCI segment device table.
Also include struct amd_iommu as one of the function parameter to
amd_iommu_apply_erratum_63() since it is needed when setting up DTE.
Co-developed-by: Vasant Hegde <vasant.hegde@amd.com>
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Link: https://lore.kernel.org/r/20220706113825.25582-27-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Include struct amd_iommu_pci_seg as a function parameter since
we need to access per PCI segment device table.
Co-developed-by: Vasant Hegde <vasant.hegde@amd.com>
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Link: https://lore.kernel.org/r/20220706113825.25582-26-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Start using per PCI segment data structures instead of global data
structures.
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Link: https://lore.kernel.org/r/20220706113825.25582-22-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Pass amd_iommu structure as one of the parameter to these functions
as its needed to retrieve variable tables inside these functions.
Co-developed-by: Vasant Hegde <vasant.hegde@amd.com>
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Link: https://lore.kernel.org/r/20220706113825.25582-20-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Pass amd_iommu structure as one of the parameter to amd_irte_ops functions
since its needed to activate/deactivate the iommu.
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Link: https://lore.kernel.org/r/20220706113825.25582-19-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Add a pointer to struct amd_iommu to amd_ir_data structure, which
can be used to correlate interrupt remapping data to a per-PCI-segment
interrupt remapping table.
Co-developed-by: Vasant Hegde <vasant.hegde@amd.com>
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Link: https://lore.kernel.org/r/20220706113825.25582-18-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Use rlookup_amd_iommu() helper function which will give per PCI
segment rlookup_table.
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Link: https://lore.kernel.org/r/20220706113825.25582-16-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
With multiple pci segment support, number of BDF supported by each
segment may differ. Hence introduce per segment device table size
which depends on last_bdf. This will replace global
"device_table_size" variable.
Co-developed-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Link: https://lore.kernel.org/r/20220706113825.25582-12-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Current code uses global "amd_iommu_last_bdf" to track the last bdf
supported by the system. This value is used for various memory
allocation, device data flushing, etc.
Introduce per PCI segment last_bdf which will be used to track last bdf
supported by the given PCI segment and use this value for all per
segment memory allocations. Eventually it will replace global
"amd_iommu_last_bdf".
Co-developed-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Link: https://lore.kernel.org/r/20220706113825.25582-11-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Newer AMD systems can support multiple PCI segments. In order to support
multiple PCI segments IVMD table in IVRS structure is enhanced to
include pci segment id. Update ivmd_header structure to include "pci_seg".
Also introduce per PCI segment unity map list. It will replace global
amd_iommu_unity_map list.
Note that we have used "reserved" field in IVMD table to include "pci_seg
id" which was set to zero. It will take care of backward compatibility
(new kernel will work fine on older systems).
Co-developed-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Link: https://lore.kernel.org/r/20220706113825.25582-10-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
This will replace global rlookup table (amd_iommu_rlookup_table).
Add helper functions to set/get rlookup table for the given device.
Also add macros to get seg/devid from sbdf.
Co-developed-by: Vasant Hegde <vasant.hegde@amd.com>
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Link: https://lore.kernel.org/r/20220706113825.25582-5-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Introduce per PCI segment device table. All IOMMUs within the segment
will share this device table. This will replace global device
table i.e. amd_iommu_dev_table.
Also introduce helper function to get the device table for the given IOMMU.
Co-developed-by: Vasant Hegde <vasant.hegde@amd.com>
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Link: https://lore.kernel.org/r/20220706113825.25582-4-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Newer AMD systems can support multiple PCI segments, where each segment
contains one or more IOMMU instances. However, an IOMMU instance can only
support a single PCI segment.
Current code assumes that system contains only one pci segment (segment 0)
and creates global data structures such as device table, rlookup table,
etc.
Introducing per PCI segment data structure, which contains segment
specific data structures. This will eventually replace the global
data structures.
Also update `amd_iommu->pci_seg` variable to point to PCI segment
structure instead of PCI segment ID.
Co-developed-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Link: https://lore.kernel.org/r/20220706113825.25582-3-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
struct iommu_dev_data contains member "pdev" to point to pci_dev. This is
valid for only PCI devices and for other devices this will be NULL. This
causes unnecessary "pdev != NULL" check at various places.
Replace "struct pci_dev" member with "struct device" and use to_pci_dev()
to get pci device reference as needed. Also adjust setup_aliases() and
clone_aliases() function.
No functional change intended.
Co-developed-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Link: https://lore.kernel.org/r/20220706113825.25582-2-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Use try_cmpxchg64 instead of cmpxchg64 (*ptr, old, new) != old in
alloc_pte and free_clear_pte. cmpxchg returns success in ZF flag, so this
change saves a compare after cmpxchg (and related move instruction
in front of cmpxchg). Also, remove racy explicit assignment to pteval
when cmpxchg fails, this is what try_cmpxchg does implicitly from
*pte in an atomic way.
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20220525145416.10816-1-ubizjak@gmail.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
...
On some systems it can take a long time for the hardware to enable the
GA log of the AMD IOMMU. The current wait time is only 0.1ms, but
testing showed that it can take up to 14ms for the GA log to enter
running state after it has been enabled.
Sometimes the long delay happens when booting the system, sometimes
only on resume. Adjust the timeout accordingly to not print a warning
when hardware takes a longer than usual.
There has already been an attempt to fix this with commit
9b45a7738e ("iommu/amd: Fix loop timeout issue in iommu_ga_log_enable()")
But that commit was based on some wrong math and did not fix the issue
in all cases.
Cc: "D. Ziegfeld" <dzigg@posteo.de>
Cc: Jörg-Volker Peetz <jvpeetz@web.de>
Fixes: 8bda0cfbdc ("iommu/amd: Detect and initialize guest vAPIC log")
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Link: https://lore.kernel.org/r/20220520102214.12563-1-joro@8bytes.org
Smatch static checker warns:
drivers/iommu/amd/iommu_v2.c:133 free_device_state()
warn: sleeping in atomic context
Fixes by storing the list of struct device_state in a temporary
list, and then free the memory after releasing the spinlock.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Fixes: 9f968fc70d ("iommu/amd: Improve amd_iommu_v2_exit()")
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Link: https://lore.kernel.org/r/20220314024321.37411-1-suravee.suthikulpanit@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
This new mechanism will replace using IOMMU_CAP_CACHE_COHERENCY and
IOMMU_CACHE to control the no-snoop blocking behavior of the IOMMU.
Currently only Intel and AMD IOMMUs are known to support this
feature. They both implement it as an IOPTE bit, that when set, will cause
PCIe TLPs to that IOVA with the no-snoop bit set to be treated as though
the no-snoop bit was clear.
The new API is triggered by calling enforce_cache_coherency() before
mapping any IOVA to the domain which globally switches on no-snoop
blocking. This allows other implementations that might block no-snoop
globally and outside the IOPTE - AMD also documents such a HW capability.
Leave AMD out of sync with Intel and have it block no-snoop even for
in-kernel users. This can be trivially resolved in a follow up patch.
Only VFIO needs to call this API because it does not have detailed control
over the device to avoid requesting no-snoop behavior at the device
level. Other places using domains with real kernel drivers should simply
avoid asking their devices to set the no-snoop bit.
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Acked-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/1-v3-2cf356649677+a32-intel_no_snoop_jgg@nvidia.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Previously the AMD IOMMU would only enable SWIOTLB in certain
circumstances:
* IOMMU in passthrough mode
* SME enabled
This logic however doesn't work when an untrusted device is plugged in
that doesn't do page aligned DMA transactions. The expectation is
that a bounce buffer is used for those transactions.
This fails like this:
swiotlb buffer is full (sz: 4096 bytes), total 0 (slots), used 0 (slots)
That happens because the bounce buffers have been allocated, followed by
freed during startup but the bounce buffering code expects that all IOMMUs
have left it enabled.
Remove the criteria to set up bounce buffers on AMD systems to ensure
they're always available for supporting untrusted devices.
Fixes: 82612d66d5 ("iommu: Allow the dma-iommu api to use bounce buffers")
Suggested-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20220404204723.9767-2-mario.limonciello@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The IOMMU table tries to separate the different IOMMUs into different
backends, but actually requires various cross calls.
Rewrite the code to do the generic swiotlb/swiotlb-xen setup directly
in pci-dma.c and then just call into the IOMMU drivers.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Tested-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
During module exit, the current logic loops through all possible
16-bit device ID space to search for existing devices and clean up
device state structures. This can be simplified by looping through
the device state list.
Also, refactor various clean up logic into free_device_state()
for better reusability.
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Link: https://lore.kernel.org/r/20220301085626.87680-6-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
This variable has not been used since it was introduced.
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Vasant Hegde <vasant.hegde@amd.com>
Link: https://lore.kernel.org/r/20220301085626.87680-5-vasant.hegde@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Move the domain specific operations out of struct iommu_ops into a new
structure that only has domain specific operations. This solves the
problem of needing to know if the method vector for a given operation
needs to be retrieved from the device or the domain. Logically the domain
ops are the ones that make sense for external subsystems and endpoint
drivers to use, while device ops, with the sole exception of domain_alloc,
are IOMMU API internals.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20220216025249.3459465-10-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The is_attach_deferred iommu_ops callback is a device op. The domain
argument is unnecessary and never used. Remove it to make code clean.
Suggested-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20220216025249.3459465-9-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The current logic updates the I/O page table mode for the domain
before calling the logic to free memory used for the page table.
This results in IOMMU page table memory leak, and can be observed
when launching VM w/ pass-through devices.
Fix by freeing the memory used for page table before updating the mode.
Cc: Joerg Roedel <joro@8bytes.org>
Reported-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Tested-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Fixes: e42ba06330 ("iommu/amd: Restructure code for freeing page table")
Link: https://lore.kernel.org/all/20220118194720.urjgi73b7c3tq2o6@oracle.com/
Link: https://lore.kernel.org/r/20220210154745.11524-1-suravee.suthikulpanit@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The AMD IOMMU logs I/O page faults and such to a ring buffer in
system memory, and this ring buffer can overflow. The AMD IOMMU
spec has the following to say about the interrupt status bit that
signals this overflow condition:
EventOverflow: Event log overflow. RW1C. Reset 0b. 1 = IOMMU
event log overflow has occurred. This bit is set when a new
event is to be written to the event log and there is no usable
entry in the event log, causing the new event information to
be discarded. An interrupt is generated when EventOverflow = 1b
and MMIO Offset 0018h[EventIntEn] = 1b. No new event log
entries are written while this bit is set. Software Note: To
resume logging, clear EventOverflow (W1C), and write a 1 to
MMIO Offset 0018h[EventLogEn].
The AMD IOMMU driver doesn't currently implement this recovery
sequence, meaning that if a ring buffer overflow occurs, logging
of EVT/PPR/GA events will cease entirely.
This patch implements the spec-mandated reset sequence, with the
minor tweak that the hardware seems to want to have a 0 written to
MMIO Offset 0018h[EventLogEn] first, before writing an 1 into this
field, or the IOMMU won't actually resume logging events.
Signed-off-by: Lennert Buytenhek <buytenh@arista.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/YVrSXEdW2rzEfOvk@wantstofly.org
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The polling loop for the register change in iommu_ga_log_enable() needs
to have a udelay() in it. Otherwise the CPU might be faster than the
IOMMU hardware and wrongly trigger the WARN_ON() further down the code
stream. Use a 10us for udelay(), has there is some hardware where
activation of the GA log can take more than a 100ms.
A future optimization should move the activation check of the GA log
to the point where it gets used for the first time. But that is a
bigger change and not suitable for a fix.
Fixes: 8bda0cfbdc ("iommu/amd: Detect and initialize guest vAPIC log")
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Link: https://lore.kernel.org/r/20220204115537.3894-1-joro@8bytes.org
page->freelist is for the use of slab. We already have the ability
to free a list of pages in the core mm, but it requires the use of a
list_head and for the pages to be chained together through page->lru.
Switch the AMD IOMMU code over to using free_pages_list().
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
[rm: split from original patch, cosmetic tweaks]
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/73af128f651aaa1f38f69e586c66765a88ad2de0.1639753638.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
For reasons unclear, pagetable freeing is an effectively recursive
method implemented via an elaborate system of templated functions that
turns out to account for 25% of the object file size. Implementing it
using regular straightforward recursion makes the code simpler, and
seems like a good thing to do before we work on it further. As part of
that, also fix the types to avoid all the needless casting back and
forth which just gets in the way.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/d3d00c9f3fa0df4756b867072c201e6e82f9ce39.1639753638.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
iommu->intcapxt_notify field is no longer used
after a switch to a separate domain was done
Fixes: d1adcfbb52 ("iommu/amd: Fix IOMMU interrupt generation in X2APIC mode")
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Link: https://lore.kernel.org/r/20211123161038.48009-6-mlevitsk@redhat.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Use IRQCHIP_MASK_ON_SUSPEND to make the core irq code to
mask the iommu interrupt on suspend and unmask it on the resume.
Since now the unmask function updates the INTX settings,
that will restore them on resume from s3/s4.
Since IRQCHIP_MASK_ON_SUSPEND is only effective for interrupts
which are not wakeup sources, remove IRQCHIP_SKIP_SET_WAKE flag
and instead implement a dummy .irq_set_wake which doesn't allow
the interrupt to become a wakeup source.
Fixes: 6692981295 ("iommu/amd: Add support for X2APIC IOMMU interrupts")
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Link: https://lore.kernel.org/r/20211123161038.48009-5-mlevitsk@redhat.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
This is more logically correct and will also allow us to
to use mask/unmask logic to restore INTX setttings after
the resume from s3/s4.
Fixes: 6692981295 ("iommu/amd: Add support for X2APIC IOMMU interrupts")
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Link: https://lore.kernel.org/r/20211123161038.48009-4-mlevitsk@redhat.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
This will give IOMMU GA log a chance to work after resume
from s3/s4.
Fixes: 8bda0cfbdc ("iommu/amd: Detect and initialize guest vAPIC log")
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
Link: https://lore.kernel.org/r/20211123161038.48009-2-mlevitsk@redhat.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Including:
- Intel IOMMU Updates fro Lu Baolu:
- Dump DMAR translation structure when DMA fault occurs
- An optimization in the page table manipulation code
- Use second level for GPA->HPA translation
- Various cleanups
- Arm SMMU Updates from Will
- Minor optimisations to SMMUv3 command creation and submission
- Numerous new compatible string for Qualcomm SMMUv2 implementations
- Fixes for the SWIOTLB based implemenation of dma-iommu code for
untrusted devices
- Add support for r8a779a0 to the Renesas IOMMU driver and DT matching
code for r8a77980
- A couple of cleanups and fixes for the Apple DART IOMMU driver
- Make use of generic report_iommu_fault() interface in the AMD IOMMU
driver
- Various smaller fixes and cleanups
-----BEGIN PGP SIGNATURE-----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=waUR
-----END PGP SIGNATURE-----
Merge tag 'iommu-updates-v5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu
Pull iommu updates from Joerg Roedel:
- Intel IOMMU Updates fro Lu Baolu:
- Dump DMAR translation structure when DMA fault occurs
- An optimization in the page table manipulation code
- Use second level for GPA->HPA translation
- Various cleanups
- Arm SMMU Updates from Will
- Minor optimisations to SMMUv3 command creation and submission
- Numerous new compatible string for Qualcomm SMMUv2 implementations
- Fixes for the SWIOTLB based implemenation of dma-iommu code for
untrusted devices
- Add support for r8a779a0 to the Renesas IOMMU driver and DT matching
code for r8a77980
- A couple of cleanups and fixes for the Apple DART IOMMU driver
- Make use of generic report_iommu_fault() interface in the AMD IOMMU
driver
- Various smaller fixes and cleanups
* tag 'iommu-updates-v5.16' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (35 commits)
iommu/dma: Fix incorrect error return on iommu deferred attach
iommu/dart: Initialize DART_STREAMS_ENABLE
iommu/dma: Use kvcalloc() instead of kvzalloc()
iommu/tegra-smmu: Use devm_bitmap_zalloc when applicable
iommu/dart: Use kmemdup instead of kzalloc and memcpy
iommu/vt-d: Avoid duplicate removing in __domain_mapping()
iommu/vt-d: Convert the return type of first_pte_in_page to bool
iommu/vt-d: Clean up unused PASID updating functions
iommu/vt-d: Delete dev_has_feat callback
iommu/vt-d: Use second level for GPA->HPA translation
iommu/vt-d: Check FL and SL capability sanity in scalable mode
iommu/vt-d: Remove duplicate identity domain flag
iommu/vt-d: Dump DMAR translation structure when DMA fault occurs
iommu/vt-d: Do not falsely log intel_iommu is unsupported kernel option
iommu/arm-smmu-qcom: Request direct mapping for modem device
iommu: arm-smmu-qcom: Add compatible for QCM2290
dt-bindings: arm-smmu: Add compatible for QCM2290 SoC
iommu/arm-smmu-qcom: Add SM6350 SMMU compatible
dt-bindings: arm-smmu: Add compatible for SM6350 SoC
iommu/arm-smmu-v3: Properly handle the return value of arm_smmu_cmdq_build_cmd()
...
The end goal of the current buffer overflow detection work[0] is to gain
full compile-time and run-time coverage of all detectable buffer overflows
seen via array indexing or memcpy(), memmove(), and memset(). The str*()
family of functions already have full coverage.
While much of the work for these changes have been on-going for many
releases (i.e. 0-element and 1-element array replacements, as well as
avoiding false positives and fixing discovered overflows[1]), this series
contains the foundational elements of several related buffer overflow
detection improvements by providing new common helpers and FORTIFY_SOURCE
changes needed to gain the introspection required for compiler visibility
into array sizes. Also included are a handful of already Acked instances
using the helpers (or related clean-ups), with many more waiting at the
ready to be taken via subsystem-specific trees[2]. The new helpers are:
- struct_group() for gaining struct member range introspection.
- memset_after() and memset_startat() for clearing to the end of structures.
- DECLARE_FLEX_ARRAY() for using flex arrays in unions or alone in structs.
Also included is the beginning of the refactoring of FORTIFY_SOURCE to
support memcpy() introspection, fix missing and regressed coverage under
GCC, and to prepare to fix the currently broken Clang support. Finishing
this work is part of the larger series[0], but depends on all the false
positives and buffer overflow bug fixes to have landed already and those
that depend on this series to land.
As part of the FORTIFY_SOURCE refactoring, a set of both a compile-time
and run-time tests are added for FORTIFY_SOURCE and the mem*()-family
functions respectively. The compile time tests have found a legitimate
(though corner-case) bug[6] already.
Please note that the appearance of "panic" and "BUG" in the
FORTIFY_SOURCE refactoring are the result of relocating existing code,
and no new use of those code-paths are expected nor desired.
Finally, there are two tree-wide conversions for 0-element arrays and
flexible array unions to gain sane compiler introspection coverage that
result in no known object code differences.
After this series (and the changes that have now landed via netdev
and usb), we are very close to finally being able to build with
-Warray-bounds and -Wzero-length-bounds. However, due corner cases in
GCC[3] and Clang[4], I have not included the last two patches that turn
on these options, as I don't want to introduce any known warnings to
the build. Hopefully these can be solved soon.
[0] https://lore.kernel.org/lkml/20210818060533.3569517-1-keescook@chromium.org/
[1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/log/?qt=grep&q=FORTIFY_SOURCE
[2] https://lore.kernel.org/lkml/202108220107.3E26FE6C9C@keescook/
[3] https://lore.kernel.org/lkml/3ab153ec-2798-da4c-f7b1-81b0ac8b0c5b@roeck-us.net/
[4] https://bugs.llvm.org/show_bug.cgi?id=51682
[5] https://lore.kernel.org/lkml/202109051257.29B29745C0@keescook/
[6] https://lore.kernel.org/lkml/20211020200039.170424-1-keescook@chromium.org/
-----BEGIN PGP SIGNATURE-----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=9xbT
-----END PGP SIGNATURE-----
Merge tag 'overflow-v5.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux
Pull overflow updates from Kees Cook:
"The end goal of the current buffer overflow detection work[0] is to
gain full compile-time and run-time coverage of all detectable buffer
overflows seen via array indexing or memcpy(), memmove(), and
memset(). The str*() family of functions already have full coverage.
While much of the work for these changes have been on-going for many
releases (i.e. 0-element and 1-element array replacements, as well as
avoiding false positives and fixing discovered overflows[1]), this
series contains the foundational elements of several related buffer
overflow detection improvements by providing new common helpers and
FORTIFY_SOURCE changes needed to gain the introspection required for
compiler visibility into array sizes. Also included are a handful of
already Acked instances using the helpers (or related clean-ups), with
many more waiting at the ready to be taken via subsystem-specific
trees[2].
The new helpers are:
- struct_group() for gaining struct member range introspection
- memset_after() and memset_startat() for clearing to the end of
structures
- DECLARE_FLEX_ARRAY() for using flex arrays in unions or alone in
structs
Also included is the beginning of the refactoring of FORTIFY_SOURCE to
support memcpy() introspection, fix missing and regressed coverage
under GCC, and to prepare to fix the currently broken Clang support.
Finishing this work is part of the larger series[0], but depends on
all the false positives and buffer overflow bug fixes to have landed
already and those that depend on this series to land.
As part of the FORTIFY_SOURCE refactoring, a set of both a
compile-time and run-time tests are added for FORTIFY_SOURCE and the
mem*()-family functions respectively. The compile time tests have
found a legitimate (though corner-case) bug[6] already.
Please note that the appearance of "panic" and "BUG" in the
FORTIFY_SOURCE refactoring are the result of relocating existing code,
and no new use of those code-paths are expected nor desired.
Finally, there are two tree-wide conversions for 0-element arrays and
flexible array unions to gain sane compiler introspection coverage
that result in no known object code differences.
After this series (and the changes that have now landed via netdev and
usb), we are very close to finally being able to build with
-Warray-bounds and -Wzero-length-bounds.
However, due corner cases in GCC[3] and Clang[4], I have not included
the last two patches that turn on these options, as I don't want to
introduce any known warnings to the build. Hopefully these can be
solved soon"
Link: https://lore.kernel.org/lkml/20210818060533.3569517-1-keescook@chromium.org/ [0]
Link: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/log/?qt=grep&q=FORTIFY_SOURCE [1]
Link: https://lore.kernel.org/lkml/202108220107.3E26FE6C9C@keescook/ [2]
Link: https://lore.kernel.org/lkml/3ab153ec-2798-da4c-f7b1-81b0ac8b0c5b@roeck-us.net/ [3]
Link: https://bugs.llvm.org/show_bug.cgi?id=51682 [4]
Link: https://lore.kernel.org/lkml/202109051257.29B29745C0@keescook/ [5]
Link: https://lore.kernel.org/lkml/20211020200039.170424-1-keescook@chromium.org/ [6]
* tag 'overflow-v5.16-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux: (30 commits)
fortify: strlen: Avoid shadowing previous locals
compiler-gcc.h: Define __SANITIZE_ADDRESS__ under hwaddress sanitizer
treewide: Replace 0-element memcpy() destinations with flexible arrays
treewide: Replace open-coded flex arrays in unions
stddef: Introduce DECLARE_FLEX_ARRAY() helper
btrfs: Use memset_startat() to clear end of struct
string.h: Introduce memset_startat() for wiping trailing members and padding
xfrm: Use memset_after() to clear padding
string.h: Introduce memset_after() for wiping trailing members/padding
lib: Introduce CONFIG_MEMCPY_KUNIT_TEST
fortify: Add compile-time FORTIFY_SOURCE tests
fortify: Allow strlen() and strnlen() to pass compile-time known lengths
fortify: Prepare to improve strnlen() and strlen() warnings
fortify: Fix dropped strcpy() compile-time write overflow check
fortify: Explicitly disable Clang support
fortify: Move remaining fortify helpers into fortify-string.h
lib/string: Move helper functions out of string.c
compiler_types.h: Remove __compiletime_object_size()
cm4000_cs: Use struct_group() to zero struct cm4000_dev region
can: flexcan: Use struct_group() to zero struct flexcan_regs regions
...
Replace uses of mem_encrypt_active() with calls to cc_platform_has() with
the CC_ATTR_MEM_ENCRYPT attribute.
Remove the implementation of mem_encrypt_active() across all arches.
For s390, since the default implementation of the cc_platform_has()
matches the s390 implementation of mem_encrypt_active(), cc_platform_has()
does not need to be implemented in s390 (the config option
ARCH_HAS_CC_PLATFORM is not set).
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20210928191009.32551-9-bp@alien8.de
Replace uses of sme_active() with the more generic cc_platform_has()
using CC_ATTR_HOST_MEM_ENCRYPT. If future support is added for other
memory encryption technologies, the use of CC_ATTR_HOST_MEM_ENCRYPT
can be updated, as required.
This also replaces two usages of sev_active() that are really geared
towards detecting if SME is active.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20210928191009.32551-6-bp@alien8.de
This patch makes iommu/amd call report_iommu_fault() when an I/O page
fault occurs, which has two effects:
1) It allows device drivers to register a callback to be notified of
I/O page faults, via the iommu_set_fault_handler() API.
2) It triggers the io_page_fault tracepoint in report_iommu_fault()
when an I/O page fault occurs.
The latter point is the main aim of this patch, as it allows
rasdaemon-like daemons to be notified of I/O page faults, and to
possibly initiate corrective action in response.
A number of other IOMMU drivers already use report_iommu_fault(), and
I/O page faults on those IOMMUs therefore already trigger this
tracepoint -- but this isn't yet the case for AMD-Vi and Intel DMAR.
The AMD IOMMU specification suggests that the bit in an I/O page fault
event log entry that signals whether an I/O page fault was for a read
request or for a write request is only meaningful when the faulting
access was to a present page, but some testing on a Ryzen 3700X suggests
that this bit encodes the correct value even for I/O page faults to
non-present pages, and therefore, this patch passes the R/W information
up the stack even for I/O page faults to non-present pages.
Signed-off-by: Lennert Buytenhek <buytenh@arista.com>
Link: https://lore.kernel.org/r/YVLyBW97vZLpOaAp@wantstofly.org
Signed-off-by: Joerg Roedel <jroedel@suse.de>
In preparation for FORTIFY_SOURCE performing compile-time and run-time
field bounds checking for memcpy(), memmove(), and memset(), avoid
intentionally writing across neighboring fields.
Use struct_group() in struct ivhd_entry around members ext and hidh, so
they can be referenced together. This will allow memcpy() and sizeof()
to more easily reason about sizes, improve readability, and avoid future
warnings about writing beyond the end of ext.
"pahole" shows no size nor member offset changes to struct ivhd_entry.
"objdump -d" shows no object code changes.
Cc: Will Deacon <will@kernel.org>
Cc: iommu@lists.linux-foundation.org
Acked-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Kees Cook <keescook@chromium.org>
Since the function has been simplified and only call iommu_init_ga_log(),
remove the function and replace with iommu_init_ga_log() instead.
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Link: https://lore.kernel.org/r/20210820202957.187572-4-suravee.suthikulpanit@amd.com
Fixes: 8bda0cfbdc ("iommu/amd: Detect and initialize guest vAPIC log")
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Currently, iommu_init_ga() checks and disables IOMMU VAPIC support
(i.e. AMD AVIC support in IOMMU) when GAMSup feature bit is not set.
However it forgets to clear IRQ_POSTING_CAP from the previously set
amd_iommu_irq_ops.capability.
This triggers an invalid page fault bug during guest VM warm reboot
if AVIC is enabled since the irq_remapping_cap(IRQ_POSTING_CAP) is
incorrectly set, and crash the system with the following kernel trace.
BUG: unable to handle page fault for address: 0000000000400dd8
RIP: 0010:amd_iommu_deactivate_guest_mode+0x19/0xbc
Call Trace:
svm_set_pi_irte_mode+0x8a/0xc0 [kvm_amd]
? kvm_make_all_cpus_request_except+0x50/0x70 [kvm]
kvm_request_apicv_update+0x10c/0x150 [kvm]
svm_toggle_avic_for_irq_window+0x52/0x90 [kvm_amd]
svm_enable_irq_window+0x26/0xa0 [kvm_amd]
vcpu_enter_guest+0xbbe/0x1560 [kvm]
? avic_vcpu_load+0xd5/0x120 [kvm_amd]
? kvm_arch_vcpu_load+0x76/0x240 [kvm]
? svm_get_segment_base+0xa/0x10 [kvm_amd]
kvm_arch_vcpu_ioctl_run+0x103/0x590 [kvm]
kvm_vcpu_ioctl+0x22a/0x5d0 [kvm]
__x64_sys_ioctl+0x84/0xc0
do_syscall_64+0x33/0x40
entry_SYSCALL_64_after_hwframe+0x44/0xae
Fixes by moving the initializing of AMD IOMMU interrupt remapping mode
(amd_iommu_guest_ir) earlier before setting up the
amd_iommu_irq_ops.capability with appropriate IRQ_POSTING_CAP flag.
[joro: Squashed the two patches and limited
check_features_on_all_iommus() to CONFIG_IRQ_REMAP
to fix a compile warning.]
Signed-off-by: Wei Huang <wei.huang2@amd.com>
Co-developed-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Link: https://lore.kernel.org/r/20210820202957.187572-2-suravee.suthikulpanit@amd.com
Link: https://lore.kernel.org/r/20210820202957.187572-3-suravee.suthikulpanit@amd.com
Fixes: 8bda0cfbdc ("iommu/amd: Detect and initialize guest vAPIC log")
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Remove the new use of the variable introduced in the AMD driver branch.
The variable was removed already in the iommu core branch, causing build
errors when the brances are merged.
Cc: Nadav Amit <namit@vmware.com>
Cc: Zhen Lei <thunder.leizhen@huawei.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Link: https://lore.kernel.org/r/20210802150643.3634-1-joro@8bytes.org
When running on an AMD vIOMMU, it is better to avoid TLB flushes
of unmodified PTEs. vIOMMUs require the hypervisor to synchronize the
virtualized IOMMU's PTEs with the physical ones. This process induce
overheads.
AMD IOMMU allows us to flush any range that is aligned to the power of
2. So when running on top of a vIOMMU, break the range into sub-ranges
that are naturally aligned, and flush each one separately. This apporach
is better when running with a vIOMMU, but on physical IOMMUs, the
penalty of IOTLB misses due to unnecessary flushed entries is likely to
be low.
Repurpose (i.e., keeping the name, changing the logic)
domain_flush_pages() so it is used to choose whether to perform one
flush of the whole range or multiple ones to avoid flushing unnecessary
ranges. Use NpCache, as usual, to infer whether the IOMMU is physical or
virtual.
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Will Deacon <will@kernel.org>
Cc: Jiajun Cao <caojiajun@vmware.com>
Cc: Lu Baolu <baolu.lu@linux.intel.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-kernel@vger.kernel.org
Suggested-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Nadav Amit <namit@vmware.com>
Link: https://lore.kernel.org/r/20210723093209.714328-8-namit@vmware.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
On virtual machines, software must flush the IOTLB after each page table
entry update.
The iommu_map_sg() code iterates through the given scatter-gather list
and invokes iommu_map() for each element in the scatter-gather list,
which calls into the vendor IOMMU driver through iommu_ops callback. As
the result, a single sg mapping may lead to multiple IOTLB flushes.
Fix this by adding amd_iotlb_sync_map() callback and flushing at this
point after all sg mappings we set.
This commit is followed and inspired by commit 933fcd01e9
("iommu/vt-d: Add iotlb_sync_map callback").
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Will Deacon <will@kernel.org>
Cc: Jiajun Cao <caojiajun@vmware.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Lu Baolu <baolu.lu@linux.intel.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Nadav Amit <namit@vmware.com>
Link: https://lore.kernel.org/r/20210723093209.714328-7-namit@vmware.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
AMD's IOMMU can flush efficiently (i.e., in a single flush) any range.
This is in contrast, for instnace, to Intel IOMMUs that have a limit on
the number of pages that can be flushed in a single flush. In addition,
AMD's IOMMU do not care about the page-size, so changes of the page size
do not need to trigger a TLB flush.
So in most cases, a TLB flush due to disjoint range is not needed for
AMD. Yet, vIOMMUs require the hypervisor to synchronize the virtualized
IOMMU's PTEs with the physical ones. This process induce overheads, so
it is better not to cause unnecessary flushes, i.e., flushes of PTEs
that were not modified.
Implement and use amd_iommu_iotlb_gather_add_page() and use it instead
of the generic iommu_iotlb_gather_add_page(). Ignore disjoint regions
unless "non-present cache" feature is reported by the IOMMU
capabilities, as this is an indication we are running on a physical
IOMMU. A similar indication is used by VT-d (see "caching mode"). The
new logic retains the same flushing behavior that we had before the
introduction of page-selective IOTLB flushes for AMD.
On virtualized environments, check if the newly flushed region and the
gathered one are disjoint and flush if it is.
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Will Deacon <will@kernel.org>
Cc: Jiajun Cao <caojiajun@vmware.com>
Cc: Lu Baolu <baolu.lu@linux.intel.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-kernel@vger.kernel.org>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Nadav Amit <namit@vmware.com>
Link: https://lore.kernel.org/r/20210723093209.714328-6-namit@vmware.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Do not use flush-queue on virtualized environments, where the NpCache
capability of the IOMMU is set. This is required to reduce
virtualization overheads.
This change follows a similar change to Intel's VT-d and a detailed
explanation as for the rationale is described in commit 29b3283972
("iommu/vt-d: Do not use flush-queue when caching-mode is on").
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Will Deacon <will@kernel.org>
Cc: Jiajun Cao <caojiajun@vmware.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Lu Baolu <baolu.lu@linux.intel.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Nadav Amit <namit@vmware.com>
Link: https://lore.kernel.org/r/20210723093209.714328-3-namit@vmware.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Recent patch attempted to enable selective page flushes on AMD IOMMU but
neglected to adapt amd_iommu_iotlb_sync() to use the selective flushes.
Adapt amd_iommu_iotlb_sync() to use selective flushes and change
amd_iommu_unmap() to collect the flushes. As a defensive measure, to
avoid potential issues as those that the Intel IOMMU driver encountered
recently, flush the page-walk caches by always setting the "pde"
parameter. This can be removed later.
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Will Deacon <will@kernel.org>
Cc: Jiajun Cao <caojiajun@vmware.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Lu Baolu <baolu.lu@linux.intel.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Nadav Amit <namit@vmware.com>
Link: https://lore.kernel.org/r/20210723093209.714328-2-namit@vmware.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
For the printing of RMP_HW_ERROR / RMP_PAGE_FAULT / IO_PAGE_FAULT
events, the AMD IOMMU code uses such logic:
if (pdev)
dev_data = dev_iommu_priv_get(&pdev->dev);
if (dev_data && __ratelimit(&dev_data->rs)) {
pci_err(pdev, ...
} else {
printk_ratelimit() / pr_err{,_ratelimited}(...
}
This means that if we receive an event for a PCI devid which actually
does have a struct pci_dev and an attached struct iommu_dev_data, but
rate limiting kicks in, we'll fall back to the non-PCI branch of the
test, and print the event in a different format.
Fix this by changing the logic to:
if (dev_data) {
if (__ratelimit(&dev_data->rs)) {
pci_err(pdev, ...
}
} else {
pr_err_ratelimited(...
}
Suggested-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Lennert Buytenhek <buytenh@wantstofly.org>
Reviewed-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Link: https://lore.kernel.org/r/YPgk1dD1gPMhJXgY@wantstofly.org
Signed-off-by: Joerg Roedel <jroedel@suse.de>
refcount_t type and corresponding API can protect refcounters from
accidental underflow and overflow and further use-after-free situations.
Signed-off-by: Xiyu Yang <xiyuyang19@fudan.edu.cn>
Signed-off-by: Xin Tan <tanxin.ctf@gmail.com>
Reviewed-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Link: https://lore.kernel.org/r/1626683578-64214-1-git-send-email-xiyuyang19@fudan.edu.cn
Signed-off-by: Joerg Roedel <jroedel@suse.de>
If people are going to insist on calling iommu_iova_to_phys()
pointlessly and expecting it to work, we can at least do ourselves a
favour by handling those cases in the core code, rather than repeatedly
across an inconsistent handful of drivers.
Since all the existing drivers implement the internal callback, and any
future ones are likely to want to work with iommu-dma which relies on
iova_to_phys a fair bit, we may as well remove that currently-redundant
check as well and consider it mandatory.
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/f564f3f6ff731b898ff7a898919bf871c2c7745a.1626354264.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
We only ever now set strict mode enabled in iommu_set_dma_strict(), so
just remove the argument.
Signed-off-by: John Garry <john.garry@huawei.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/1626088340-5838-7-git-send-email-john.garry@huawei.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Make IOMMU_DEFAULT_LAZY default for when AMD_IOMMU config is set, which
matches current behaviour.
For "fullflush" param, just call iommu_set_dma_strict(true) directly.
Since we get a strict vs lazy mode print already in iommu_subsys_init(),
and maintain a deprecation print when "fullflush" param is passed, drop the
prints in amd_iommu_init_dma_ops().
Finally drop global flag amd_iommu_unmap_flush, as it has no longer has any
purpose.
[jpg: Rebase for relocated file and drop amd_iommu_unmap_flush]
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Link: https://lore.kernel.org/r/1626088340-5838-6-git-send-email-john.garry@huawei.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Now that the x86 drivers support iommu.strict, deprecate the custom
methods.
Signed-off-by: John Garry <john.garry@huawei.com>
Acked-by: Robin Murphy <robin.murphy@arm.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/1626088340-5838-2-git-send-email-john.garry@huawei.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Passing a 64-bit address width to iommu_setup_dma_ops() is valid on
virtual platforms, but isn't currently possible. The overflow check in
iommu_dma_init_domain() prevents this even when @dma_base isn't 0. Pass
a limit address instead of a size, so callers don't have to fake a size
to work around the check.
The base and limit parameters are being phased out, because:
* they are redundant for x86 callers. dma-iommu already reserves the
first page, and the upper limit is already in domain->geometry.
* they can now be obtained from dev->dma_range_map on Arm.
But removing them on Arm isn't completely straightforward so is left for
future work. As an intermediate step, simplify the x86 callers by
passing dummy limits.
Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/20210618152059.1194210-5-jean-philippe@linaro.org
Signed-off-by: Joerg Roedel <jroedel@suse.de>
A recent commit introduced this section mismatch warning:
WARNING: modpost: vmlinux.o(.text.unlikely+0x22a1f): Section mismatch in reference from the function detect_ivrs() to the variable .init.data:amd_iommu_force_enable
The reason is that detect_ivrs() is not marked __init while it should
be, because it is only called from another __init function. Mark
detect_ivrs() __init to get rid of the warning.
Fixes: b1e650db2c ("iommu/amd: Add amd_iommu=force_enable option")
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Link: https://lore.kernel.org/r/20210608122843.8413-1-joro@8bytes.org
Now that DMA ops are part of the core API via iommu-dma, fold the
vestigial remains of the IOMMU_DMA_OPS init state into the IOMMU API
phase, and clean up a few other leftovers. This should also close the
race window wherein bus_set_iommu() effectively makes the DMA ops state
visible before its nominal initialisation - it seems this was previously
fairly benign, but since commit a250c23f15 ("iommu: remove
DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE") it can now lead to the strict flush
queue policy inadvertently being picked for default domains allocated
during that window, with a corresponding unexpected perfomance impact.
Reported-by: Jussi Maki <joamaki@gmail.com>
Tested-by: Jussi Maki <joamaki@gmail.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Fixes: a250c23f15 ("iommu: remove DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE")
Link: https://lore.kernel.org/r/665db61e23ff8d54ac5eb391bef520b3a803fcb9.1622727974.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Add this option to enable the IOMMU on platforms like AMD Stoney,
where the kernel usually disables it because it may cause problems in
some scenarios.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://lore.kernel.org/r/20210603130203.29016-1-joro@8bytes.org
print_iommu_info prints the EFR register and then the decoded list of
features on a separate line:
pci 0000:00:00.2: AMD-Vi: Extended features (0x206d73ef22254ade):
PPR X2APIC NX GT IA GA PC GA_vAPIC
The second line is emitted via 'pr_cont', which causes it to have a
different ('warn') loglevel compared to the previous line ('info').
Commit 9a295ff0ff attempted to rectify this by removing the newline
from the pci_info format string, but this doesn't work, as pci_info
calls implicitly append a newline anyway.
Printing the decoded features on the same line would make it quite long.
Instead, change pci_info() to pr_info() to omit PCI bus location info,
which is also shown in the preceding message. This results in:
pci 0000:00:00.2: AMD-Vi: Found IOMMU cap 0x40
AMD-Vi: Extended features (0x206d73ef22254ade): PPR X2APIC NX GT IA GA PC GA_vAPIC
AMD-Vi: Interrupt remapping enabled
Fixes: 9a295ff0ff ("iommu/amd: Print extended features in one line to fix divergent log levels")
Link: https://lore.kernel.org/lkml/alpine.LNX.2.20.13.2104112326460.11104@monopod.intra.ispras.ru
Signed-off-by: Alexander Monakov <amonakov@ispras.ru>
Cc: Paul Menzel <pmenzel@molgen.mpg.de>
Cc: Joerg Roedel <jroedel@suse.de>
Cc: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Cc: iommu@lists.linux-foundation.org
Reviewed-by: Paul Menzel <pmenzel@molgen.mpg.de>
Link: https://lore.kernel.org/r/20210504102220.1793-1-amonakov@ispras.ru
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The logic to determine the mask of page-specific invalidations was
tested in userspace. As the code was copied into the kernel, the
parentheses were mistakenly set in the wrong place, resulting in the
wrong mask.
Fix it.
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Will Deacon <will@kernel.org>
Cc: Jiajun Cao <caojiajun@vmware.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-kernel@vger.kernel.org
Fixes: 268aa45482 ("iommu/amd: Page-specific invalidations for more than one page")
Signed-off-by: Nadav Amit <namit@vmware.com>
Link: https://lore.kernel.org/r/20210502070001.1559127-2-namit@vmware.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Since commit 08a27c1c3e ("iommu: Add support to change default domain
of an iommu group") a user can switch a device between IOMMU and direct
DMA through sysfs. This doesn't work for AMD IOMMU at the moment because
dev->dma_ops is not cleared when switching from a DMA to an identity
IOMMU domain. The DMA layer thus attempts to use the dma-iommu ops on an
identity domain, causing an oops:
# echo 0000:00:05.0 > /sys/sys/bus/pci/drivers/e1000e/unbind
# echo identity > /sys/bus/pci/devices/0000:00:05.0/iommu_group/type
# echo 0000:00:05.0 > /sys/sys/bus/pci/drivers/e1000e/bind
...
BUG: kernel NULL pointer dereference, address: 0000000000000028
...
Call Trace:
iommu_dma_alloc
e1000e_setup_tx_resources
e1000e_open
Since iommu_change_dev_def_domain() calls probe_finalize() again, clear
the dma_ops there like Vt-d does.
Fixes: 08a27c1c3e ("iommu: Add support to change default domain of an iommu group")
Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Link: https://lore.kernel.org/r/20210422094216.2282097-1-jean-philippe@linaro.org
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Rather than have separate opaque setter functions that are easy to
overlook and lead to repetitive boilerplate in drivers, let's pass the
relevant initialisation parameters directly to iommu_device_register().
Acked-by: Will Deacon <will@kernel.org>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/ab001b87c533b6f4db71eb90db6f888953986c36.1617285386.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
In early AMD desktop/mobile platforms (during 2013), when the IOMMU
Performance Counter (PMC) support was first introduced in
commit 30861ddc9c ("perf/x86/amd: Add IOMMU Performance Counter
resource management"), there was a HW bug where the counters could not
be accessed. The result was reading of the counter always return zero.
At the time, the suggested workaround was to add a test logic prior
to initializing the PMC feature to check if the counters can be programmed
and read back the same value. This has been working fine until the more
recent desktop/mobile platforms start enabling power gating for the PMC,
which prevents access to the counters. This results in the PMC support
being disabled unnecesarily.
Unfortunatly, there is no documentation of since which generation
of hardware the original PMC HW bug was fixed. Although, it was fixed
soon after the first introduction of the PMC. Base on this, we assume
that the buggy platforms are less likely to be in used, and it should
be relatively safe to remove this legacy logic.
Link: https://lore.kernel.org/linux-iommu/alpine.LNX.3.20.13.2006030935570.3181@monopod.intra.ispras.ru/
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=201753
Cc: Tj (Elloe Linux) <ml.linux@elloe.vision>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Cc: Alexander Monakov <amonakov@ispras.ru>
Cc: David Coe <david.coe@live.co.uk>
Cc: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Tested-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/20210409085848.3908-3-suravee.suthikulpanit@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
This reverts commit 6778ff5b21.
The original commit tries to address an issue, where PMC power-gating
causing the IOMMU PMC pre-init test to fail on certain desktop/mobile
platforms where the power-gating is normally enabled.
There have been several reports that the workaround still does not
guarantee to work, and can add up to 100 ms (on the worst case)
to the boot process on certain platforms such as the MSI B350M MORTAR
with AMD Ryzen 3 2200G.
Therefore, revert this commit as a prelude to removing the pre-init
test.
Link: https://lore.kernel.org/linux-iommu/alpine.LNX.3.20.13.2006030935570.3181@monopod.intra.ispras.ru/
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=201753
Cc: Tj (Elloe Linux) <ml.linux@elloe.vision>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Cc: Alexander Monakov <amonakov@ispras.ru>
Cc: David Coe <david.coe@live.co.uk>
Signed-off-by: Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Link: https://lore.kernel.org/r/20210409085848.3908-2-suravee.suthikulpanit@amd.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
'devid' has been checked in function check_device, no need to double
check and clean up this.
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
Link: https://lore.kernel.org/r/1617939040-35579-1-git-send-email-zhangshaokun@hisilicon.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Currently, IOMMU invalidations and device-IOTLB invalidations using
AMD IOMMU fall back to full address-space invalidation if more than a
single page need to be flushed.
Full flushes are especially inefficient when the IOMMU is virtualized by
a hypervisor, since it requires the hypervisor to synchronize the entire
address-space.
AMD IOMMUs allow to provide a mask to perform page-specific
invalidations for multiple pages that match the address. The mask is
encoded as part of the address, and the first zero bit in the address
(in bits [51:12]) indicates the mask size.
Use this hardware feature to perform selective IOMMU and IOTLB flushes.
Combine the logic between both for better code reuse.
The IOMMU invalidations passed a smoke-test. The device IOTLB
invalidations are untested.
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Will Deacon <will@kernel.org>
Cc: Jiajun Cao <caojiajun@vmware.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Nadav Amit <namit@vmware.com>
Link: https://lore.kernel.org/r/20210323210619.513069-1-namit@vmware.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
A few functions that were intentended for the perf events support are
currently declared in arch/x86/events/amd/iommu.h, which mens they are
not in scope for the actual function definition. Also amdkfd has started
using a few of them using externs in a .c file. End that misery by
moving the prototypes to the proper header.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20210402143312.372386-5-hch@lst.de
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Suravee Suthikulpanit