[ Upstream commit 42662d1983 ]
PCIe endpoints with ATS enabled and passed through to userspace
(e.g., QEMU, DPDK) can hard-lock the host when their link drops,
either by surprise removal or by a link fault.
Commit 4fc82cd907 ("iommu/vt-d: Don't issue ATS Invalidation
request when device is disconnected") adds pci_dev_is_disconnected()
to devtlb_invalidation_with_pasid() so ATS invalidation is skipped
only when the device is being safely removed, but it applies only
when Intel IOMMU scalable mode is enabled.
With scalable mode disabled or unsupported, a system hard-lock
occurs when a PCIe endpoint's link drops because the Intel IOMMU
waits indefinitely for an ATS invalidation that cannot complete.
Call Trace:
qi_submit_sync
qi_flush_dev_iotlb
__context_flush_dev_iotlb.part.0
domain_context_clear_one_cb
pci_for_each_dma_alias
device_block_translation
blocking_domain_attach_dev
iommu_deinit_device
__iommu_group_remove_device
iommu_release_device
iommu_bus_notifier
blocking_notifier_call_chain
bus_notify
device_del
pci_remove_bus_device
pci_stop_and_remove_bus_device
pciehp_unconfigure_device
pciehp_disable_slot
pciehp_handle_presence_or_link_change
pciehp_ist
Commit 81e921fd32 ("iommu/vt-d: Fix NULL domain on device release")
adds intel_pasid_teardown_sm_context() to intel_iommu_release_device(),
which calls qi_flush_dev_iotlb() and can also hard-lock the system
when a PCIe endpoint's link drops.
Call Trace:
qi_submit_sync
qi_flush_dev_iotlb
__context_flush_dev_iotlb.part.0
intel_context_flush_no_pasid
device_pasid_table_teardown
pci_pasid_table_teardown
pci_for_each_dma_alias
intel_pasid_teardown_sm_context
intel_iommu_release_device
iommu_deinit_device
__iommu_group_remove_device
iommu_release_device
iommu_bus_notifier
blocking_notifier_call_chain
bus_notify
device_del
pci_remove_bus_device
pci_stop_and_remove_bus_device
pciehp_unconfigure_device
pciehp_disable_slot
pciehp_handle_presence_or_link_change
pciehp_ist
Sometimes the endpoint loses connection without a link-down event
(e.g., due to a link fault); killing the process (virsh destroy)
then hard-locks the host.
Call Trace:
qi_submit_sync
qi_flush_dev_iotlb
__context_flush_dev_iotlb.part.0
domain_context_clear_one_cb
pci_for_each_dma_alias
device_block_translation
blocking_domain_attach_dev
__iommu_attach_device
__iommu_device_set_domain
__iommu_group_set_domain_internal
iommu_detach_group
vfio_iommu_type1_detach_group
vfio_group_detach_container
vfio_group_fops_release
__fput
pci_dev_is_disconnected() only covers safe-removal paths;
pci_device_is_present() tests accessibility by reading
vendor/device IDs and internally calls pci_dev_is_disconnected().
On a ConnectX-5 (8 GT/s, x2) this costs ~70 µs.
Since __context_flush_dev_iotlb() is only called on
{attach,release}_dev paths (not hot), add pci_device_is_present()
there to skip inaccessible devices and avoid the hard-lock.
Fixes: 37764b952e ("iommu/vt-d: Global devTLB flush when present context entry changed")
Fixes: 81e921fd32 ("iommu/vt-d: Fix NULL domain on device release")
Cc: stable@vger.kernel.org
Signed-off-by: Jinhui Guo <guojinhui.liam@bytedance.com>
Link: https://lore.kernel.org/r/20251211035946.2071-2-guojinhui.liam@bytedance.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 10e60d8781 ]
Commit 4fc82cd907 ("iommu/vt-d: Don't issue ATS Invalidation
request when device is disconnected") relies on
pci_dev_is_disconnected() to skip ATS invalidation for
safely-removed devices, but it does not cover link-down caused
by faults, which can still hard-lock the system.
For example, if a VM fails to connect to the PCIe device,
"virsh destroy" is executed to release resources and isolate
the fault, but a hard-lockup occurs while releasing the group fd.
Call Trace:
qi_submit_sync
qi_flush_dev_iotlb
intel_pasid_tear_down_entry
device_block_translation
blocking_domain_attach_dev
__iommu_attach_device
__iommu_device_set_domain
__iommu_group_set_domain_internal
iommu_detach_group
vfio_iommu_type1_detach_group
vfio_group_detach_container
vfio_group_fops_release
__fput
Although pci_device_is_present() is slower than
pci_dev_is_disconnected(), it still takes only ~70 µs on a
ConnectX-5 (8 GT/s, x2) and becomes even faster as PCIe speed
and width increase.
Besides, devtlb_invalidation_with_pasid() is called only in the
paths below, which are far less frequent than memory map/unmap.
1. mm-struct release
2. {attach,release}_dev
3. set/remove PASID
4. dirty-tracking setup
The gain in system stability far outweighs the negligible cost
of using pci_device_is_present() instead of pci_dev_is_disconnected()
to decide when to skip ATS invalidation, especially under GDR
high-load conditions.
Fixes: 4fc82cd907 ("iommu/vt-d: Don't issue ATS Invalidation request when device is disconnected")
Cc: stable@vger.kernel.org
Signed-off-by: Jinhui Guo <guojinhui.liam@bytedance.com>
Link: https://lore.kernel.org/r/20251211035946.2071-3-guojinhui.liam@bytedance.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 75ed00055c ]
The Intel VT-d Scalable Mode PASID table entry consists of 512 bits (64
bytes). When tearing down an entry, the current implementation zeros the
entire 64-byte structure immediately using multiple 64-bit writes.
Since the IOMMU hardware may fetch these 64 bytes using multiple
internal transactions (e.g., four 128-bit bursts), updating or zeroing
the entire entry while it is active (P=1) risks a "torn" read. If a
hardware fetch occurs simultaneously with the CPU zeroing the entry, the
hardware could observe an inconsistent state, leading to unpredictable
behavior or spurious faults.
Follow the "Guidance to Software for Invalidations" in the VT-d spec
(Section 6.5.3.3) by implementing the recommended ownership handshake:
1. Clear only the 'Present' (P) bit of the PASID entry.
2. Use a dma_wmb() to ensure the cleared bit is visible to hardware
before proceeding.
3. Execute the required invalidation sequence (PASID cache, IOTLB, and
Device-TLB flush) to ensure the hardware has released all cached
references.
4. Only after the flushes are complete, zero out the remaining fields
of the PASID entry.
Also, add a dma_wmb() in pasid_set_present() to ensure that all other
fields of the PASID entry are visible to the hardware before the Present
bit is set.
Fixes: 0bbeb01a4f ("iommu/vt-d: Manage scalalble mode PASID tables")
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Dmytro Maluka <dmaluka@chromium.org>
Reviewed-by: Samiullah Khawaja <skhawaja@google.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20260120061816.2132558-2-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit dda2b8c3c6 ]
When a PASID is used for SVA by a device, it's possible that the PASID
entry is cleared before the device flushes all ongoing DMA requests and
removes the SVA domain. This can occur when an exception happens and the
process terminates before the device driver stops DMA and calls the
iommu driver to unbind the PASID.
There's no need to drain the PRQ in the mm release path. Instead, the PRQ
will be drained in the SVA unbind path.
Unfortunately, commit c43e1ccdeb ("iommu/vt-d: Drain PRQs when domain
removed from RID") changed this behavior by unconditionally draining the
PRQ in intel_pasid_tear_down_entry(). This can lead to a potential
sleeping-in-atomic-context issue.
Smatch static checker warning:
drivers/iommu/intel/prq.c:95 intel_iommu_drain_pasid_prq()
warn: sleeping in atomic context
To avoid this issue, prevent draining the PRQ in the SVA mm release path
and restore the previous behavior.
Fixes: c43e1ccdeb ("iommu/vt-d: Drain PRQs when domain removed from RID")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/linux-iommu/c5187676-2fa2-4e29-94e0-4a279dc88b49@stanley.mountain/
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20241212021529.1104745-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Stable-dep-of: 75ed00055c ("iommu/vt-d: Clear Present bit before tearing down PASID entry")
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit c43e1ccdeb ]
As this iommu driver now supports page faults for requests without
PASID, page requests should be drained when a domain is removed from
the RID2PASID entry.
This results in the intel_iommu_drain_pasid_prq() call being moved to
intel_pasid_tear_down_entry(). This indicates that when a translation
is removed from any PASID entry and the PRI has been enabled on the
device, page requests are drained in the domain detachment path.
The intel_iommu_drain_pasid_prq() helper has been modified to support
sending device TLB invalidation requests for both PASID and non-PASID
cases.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Yi Liu <yi.l.liu@intel.com>
Link: https://lore.kernel.org/r/20241101045543.70086-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Stable-dep-of: 75ed00055c ("iommu/vt-d: Clear Present bit before tearing down PASID entry")
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 4d54409576 ]
IO page faults are no longer dependent on CONFIG_INTEL_IOMMU_SVM. Move
all Page Request Queue (PRQ) functions that handle prq events to a new
file in drivers/iommu/intel/prq.c. The page_req_des struct is now
declared in drivers/iommu/intel/prq.c.
No functional changes are intended. This is a preparation patch to
enable the use of IO page faults outside the SVM/PASID use cases.
Signed-off-by: Joel Granados <joel.granados@kernel.org>
Link: https://lore.kernel.org/r/20241015-jag-iopfv8-v4-1-b696ca89ba29@kernel.org
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Stable-dep-of: 75ed00055c ("iommu/vt-d: Clear Present bit before tearing down PASID entry")
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 22d169bdd2 ]
When writing the address of a freshly allocated zero-initialized PASID
table to a PASID directory entry, do that after the CPU cache flush for
this PASID table, not before it, to avoid the time window when this
PASID table may be already used by non-coherent IOMMU hardware while
its contents in RAM is still some random old data, not zero-initialized.
Fixes: 194b3348bd ("iommu/vt-d: Fix PASID directory pointer coherency")
Signed-off-by: Dmytro Maluka <dmaluka@chromium.org>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20251221123508.37495-1-dmaluka@chromium.org
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 0edc78b82b ]
Luigi reported that retriggering a posted MSI interrupt does not work
correctly.
The reason is that the retrigger happens at the vector domain by sending an
IPI to the actual vector on the target CPU. That works correctly exactly
once because the posted MSI interrupt chip does not issue an EOI as that's
only required for the posted MSI notification vector itself.
As a consequence the vector becomes stale in the ISR, which not only
affects this vector but also any lower priority vector in the affected
APIC because the ISR bit is not cleared.
Luigi proposed to set the vector in the remap PIR bitmap and raise the
posted MSI notification vector. That works, but that still does not cure a
related problem:
If there is ever a stray interrupt on such a vector, then the related
APIC ISR bit becomes stale due to the lack of EOI as described above.
Unlikely to happen, but if it happens it's not debuggable at all.
So instead of playing games with the PIR, this can be actually solved
for both cases by:
1) Keeping track of the posted interrupt vector handler state
2) Implementing a posted MSI specific irq_ack() callback which checks that
state. If the posted vector handler is inactive it issues an EOI,
otherwise it delegates that to the posted handler.
This is correct versus affinity changes and concurrent events on the posted
vector as the actual handler invocation is serialized through the interrupt
descriptor lock.
Fixes: ed1e48ea43 ("iommu/vt-d: Enable posted mode for device MSIs")
Reported-by: Luigi Rizzo <lrizzo@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Luigi Rizzo <lrizzo@google.com>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20251125214631.044440658@linutronix.de
Closes: https://lore.kernel.org/lkml/20251124104836.3685533-1-lrizzo@google.com
[ DEFINE_PER_CPU_CACHE_HOT => DEFINE_PER_CPU ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 75c02a0376 ]
snprintf() returns the number of bytes that would have been written, not
the number actually written. Using this for offset tracking can cause
buffer overruns if truncation occurs.
Replace snprintf() with scnprintf() to ensure the offset stays within
bounds.
Since scnprintf() never returns a negative value, and zero is not possible
in this context because 'bytes' starts at 0 and 'size - bytes' is
DEBUG_BUFFER_SIZE in the first call, which is large enough to hold the
string literals used, the return value is always positive. An integer
overflow is also completely out of reach here due to the small and fixed
buffer size. The error check in latency_show_one() is therefore
unnecessary. Remove it and make dmar_latency_snapshot() return void.
Signed-off-by: Seyediman Seyedarab <ImanDevel@gmail.com>
Link: https://lore.kernel.org/r/20250731225048.131364-1-ImanDevel@gmail.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit 5ef7e24c74 upstream.
The specification, Section 7.10, "Software Steps to Drain Page Requests &
Responses," requires software to submit an Invalidation Wait Descriptor
(inv_wait_dsc) with the Page-request Drain (PD=1) flag set, along with
the Invalidation Wait Completion Status Write flag (SW=1). It then waits
for the Invalidation Wait Descriptor's completion.
However, the PD field in the Invalidation Wait Descriptor is optional, as
stated in Section 6.5.2.9, "Invalidation Wait Descriptor":
"Page-request Drain (PD): Remapping hardware implementations reporting
Page-request draining as not supported (PDS = 0 in ECAP_REG) treat this
field as reserved."
This implies that if the IOMMU doesn't support the PDS capability, software
can't drain page requests and group responses as expected.
Do not enable PCI/PRI if the IOMMU doesn't support PDS.
Reported-by: Joel Granados <joel.granados@kernel.org>
Closes: https://lore.kernel.org/r/20250909-jag-pds-v1-1-ad8cba0e494e@kernel.org
Fixes: 66ac4db36f ("iommu/vt-d: Add page request draining support")
Cc: stable@vger.kernel.org
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20250915062946.120196-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 57f55048e5 ]
Dirty page tracking relies on the IOMMU atomically updating the dirty bit
in the paging-structure entry. For this operation to succeed, the paging-
structure memory must be coherent between the IOMMU and the CPU. In
another word, if the iommu page walk is incoherent, dirty page tracking
doesn't work.
The Intel VT-d specification, Section 3.10 "Snoop Behavior" states:
"Remapping hardware encountering the need to atomically update A/EA/D bits
in a paging-structure entry that is not snooped will result in a non-
recoverable fault."
To prevent an IOMMU from being incorrectly configured for dirty page
tracking when it is operating in an incoherent mode, mark SSADS as
supported only when both ecap_slads and ecap_smpwc are supported.
Fixes: f35f22cc76 ("iommu/vt-d: Access/Dirty bit support for SS domains")
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/20250924083447.123224-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit dce043c07c upstream.
switch_to_super_page() assumes the memory range it's working on is aligned
to the target large page level. Unfortunately, __domain_mapping() doesn't
take this into account when using it, and will pass unaligned ranges
ultimately freeing a PTE range larger than expected.
Take for example a mapping with the following iov_pfn range [0x3fe400,
0x4c0600), which should be backed by the following mappings:
iov_pfn [0x3fe400, 0x3fffff] covered by 2MiB pages
iov_pfn [0x400000, 0x4bffff] covered by 1GiB pages
iov_pfn [0x4c0000, 0x4c05ff] covered by 2MiB pages
Under this circumstance, __domain_mapping() will pass [0x400000, 0x4c05ff]
to switch_to_super_page() at a 1 GiB granularity, which will in turn
free PTEs all the way to iov_pfn 0x4fffff.
Mitigate this by rounding down the iov_pfn range passed to
switch_to_super_page() in __domain_mapping()
to the target large page level.
Additionally add range alignment checks to switch_to_super_page.
Fixes: 9906b9352a ("iommu/vt-d: Avoid duplicate removing in __domain_mapping()")
Signed-off-by: Eugene Koira <eugkoira@amazon.com>
Cc: stable@vger.kernel.org
Reviewed-by: Nicolas Saenz Julienne <nsaenz@amazon.com>
Reviewed-by: David Woodhouse <dwmw@amazon.co.uk>
Link: https://lore.kernel.org/r/20250826143816.38686-1-eugkoira@amazon.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 12724ce3fe upstream.
The iotlb_sync_map iommu ops allows drivers to perform necessary cache
flushes when new mappings are established. For the Intel iommu driver,
this callback specifically serves two purposes:
- To flush caches when a second-stage page table is attached to a device
whose iommu is operating in caching mode (CAP_REG.CM==1).
- To explicitly flush internal write buffers to ensure updates to memory-
resident remapping structures are visible to hardware (CAP_REG.RWBF==1).
However, in scenarios where neither caching mode nor the RWBF flag is
active, the cache_tag_flush_range_np() helper, which is called in the
iotlb_sync_map path, effectively becomes a no-op.
Despite being a no-op, cache_tag_flush_range_np() involves iterating
through all cache tags of the iommu's attached to the domain, protected
by a spinlock. This unnecessary execution path introduces overhead,
leading to a measurable I/O performance regression. On systems with NVMes
under the same bridge, performance was observed to drop from approximately
~6150 MiB/s down to ~4985 MiB/s.
Introduce a flag in the dmar_domain structure. This flag will only be set
when iotlb_sync_map is required (i.e., when CM or RWBF is set). The
cache_tag_flush_range_np() is called only for domains where this flag is
set. This flag, once set, is immutable, given that there won't be mixed
configurations in real-world scenarios where some IOMMUs in a system
operate in caching mode while others do not. Theoretically, the
immutability of this flag does not impact functionality.
Reported-by: Ioanna Alifieraki <ioanna-maria.alifieraki@canonical.com>
Closes: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2115738
Link: https://lore.kernel.org/r/20250701171154.52435-1-ioanna-maria.alifieraki@canonical.com
Fixes: 129dab6e12 ("iommu/vt-d: Use cache_tag_flush_range_np() in iotlb_sync_map")
Cc: stable@vger.kernel.org
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20250703031545.3378602-1-baolu.lu@linux.intel.com
Link: https://lore.kernel.org/r/20250714045028.958850-3-baolu.lu@linux.intel.com
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 2c8a7c66c9 upstream.
On the Lenovo ThinkPad X201, when Intel VT-d is enabled in the BIOS, the
kernel boots with errors related to DMAR, the graphical interface appeared
quite choppy, and the system resets erratically within a minute after it
booted:
DMAR: DRHD: handling fault status reg 3
DMAR: [DMA Write NO_PASID] Request device [00:02.0] fault addr 0xb97ff000
[fault reason 0x05] PTE Write access is not set
Upon comparing boot logs with VT-d on/off, I found that the Intel Calpella
quirk (`quirk_calpella_no_shadow_gtt()') correctly applied the igfx IOMMU
disable/quirk correctly:
pci 0000:00:00.0: DMAR: BIOS has allocated no shadow GTT; disabling IOMMU
for graphics
Whereas with VT-d on, it went into the "else" branch, which then
triggered the DMAR handling fault above:
... else if (!disable_igfx_iommu) {
/* we have to ensure the gfx device is idle before we flush */
pci_info(dev, "Disabling batched IOTLB flush on Ironlake\n");
iommu_set_dma_strict();
}
Now, this is not exactly scientific, but moving 0x0044 to quirk_iommu_igfx
seems to have fixed the aforementioned issue. Running a few `git blame'
runs on the function, I have found that the quirk was originally
introduced as a fix specific to ThinkPad X201:
commit 9eecabcb9a ("intel-iommu: Abort IOMMU setup for igfx if BIOS gave
no shadow GTT space")
Which was later revised twice to the "else" branch we saw above:
- 2011: commit 6fbcfb3e46 ("intel-iommu: Workaround IOTLB hang on
Ironlake GPU")
- 2024: commit ba00196ca4 ("iommu/vt-d: Decouple igfx_off from graphic
identity mapping")
I'm uncertain whether further testings on this particular laptops were
done in 2011 and (honestly I'm not sure) 2024, but I would be happy to do
some distro-specific testing if that's what would be required to verify
this patch.
P.S., I also see IDs 0x0040, 0x0062, and 0x006a listed under the same
`quirk_calpella_no_shadow_gtt()' quirk, but I'm not sure how similar these
chipsets are (if they share the same issue with VT-d or even, indeed, if
this issue is specific to a bug in the Lenovo BIOS). With regards to
0x0062, it seems to be a Centrino wireless card, but not a chipset?
I have also listed a couple (distro and kernel) bug reports below as
references (some of them are from 7-8 years ago!), as they seem to be
similar issue found on different Westmere/Ironlake, Haswell, and Broadwell
hardware setups.
Cc: stable@vger.kernel.org
Fixes: 6fbcfb3e46 ("intel-iommu: Workaround IOTLB hang on Ironlake GPU")
Fixes: ba00196ca4 ("iommu/vt-d: Decouple igfx_off from graphic identity mapping")
Link: https://groups.google.com/g/qubes-users/c/4NP4goUds2c?pli=1
Link: https://bugs.archlinux.org/task/65362
Link: https://bbs.archlinux.org/viewtopic.php?id=230323
Reported-by: Wenhao Sun <weiguangtwk@outlook.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=197029
Signed-off-by: Mingcong Bai <jeffbai@aosc.io>
Link: https://lore.kernel.org/r/20250415133330.12528-1-jeffbai@aosc.io
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 548183ea38 upstream.
Set the posted MSI irq_chip's irq_ack() hook to irq_move_irq() instead of
a dummy/empty callback so that posted MSIs process pending changes to the
IRQ's SMP affinity. Failure to honor a pending set-affinity results in
userspace being unable to change the effective affinity of the IRQ, as
IRQD_SETAFFINITY_PENDING is never cleared and so irq_set_affinity_locked()
always defers moving the IRQ.
The issue is most easily reproducible by setting /proc/irq/xx/smp_affinity
multiple times in quick succession, as only the first update is likely to
be handled in process context.
Fixes: ed1e48ea43 ("iommu/vt-d: Enable posted mode for device MSIs")
Cc: Robert Lippert <rlippert@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Reported-by: Wentao Yang <wentaoyang@google.com>
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20250321194249.1217961-1-seanjc@google.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 93ae6e68b6 upstream.
We have recently seen report of lockdep circular lock dependency warnings
on platforms like Skylake and Kabylake:
======================================================
WARNING: possible circular locking dependency detected
6.14.0-rc6-CI_DRM_16276-gca2c04fe76e8+ #1 Not tainted
------------------------------------------------------
swapper/0/1 is trying to acquire lock:
ffffffff8360ee48 (iommu_probe_device_lock){+.+.}-{3:3},
at: iommu_probe_device+0x1d/0x70
but task is already holding lock:
ffff888102c7efa8 (&device->physical_node_lock){+.+.}-{3:3},
at: intel_iommu_init+0xe75/0x11f0
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #6 (&device->physical_node_lock){+.+.}-{3:3}:
__mutex_lock+0xb4/0xe40
mutex_lock_nested+0x1b/0x30
intel_iommu_init+0xe75/0x11f0
pci_iommu_init+0x13/0x70
do_one_initcall+0x62/0x3f0
kernel_init_freeable+0x3da/0x6a0
kernel_init+0x1b/0x200
ret_from_fork+0x44/0x70
ret_from_fork_asm+0x1a/0x30
-> #5 (dmar_global_lock){++++}-{3:3}:
down_read+0x43/0x1d0
enable_drhd_fault_handling+0x21/0x110
cpuhp_invoke_callback+0x4c6/0x870
cpuhp_issue_call+0xbf/0x1f0
__cpuhp_setup_state_cpuslocked+0x111/0x320
__cpuhp_setup_state+0xb0/0x220
irq_remap_enable_fault_handling+0x3f/0xa0
apic_intr_mode_init+0x5c/0x110
x86_late_time_init+0x24/0x40
start_kernel+0x895/0xbd0
x86_64_start_reservations+0x18/0x30
x86_64_start_kernel+0xbf/0x110
common_startup_64+0x13e/0x141
-> #4 (cpuhp_state_mutex){+.+.}-{3:3}:
__mutex_lock+0xb4/0xe40
mutex_lock_nested+0x1b/0x30
__cpuhp_setup_state_cpuslocked+0x67/0x320
__cpuhp_setup_state+0xb0/0x220
page_alloc_init_cpuhp+0x2d/0x60
mm_core_init+0x18/0x2c0
start_kernel+0x576/0xbd0
x86_64_start_reservations+0x18/0x30
x86_64_start_kernel+0xbf/0x110
common_startup_64+0x13e/0x141
-> #3 (cpu_hotplug_lock){++++}-{0:0}:
__cpuhp_state_add_instance+0x4f/0x220
iova_domain_init_rcaches+0x214/0x280
iommu_setup_dma_ops+0x1a4/0x710
iommu_device_register+0x17d/0x260
intel_iommu_init+0xda4/0x11f0
pci_iommu_init+0x13/0x70
do_one_initcall+0x62/0x3f0
kernel_init_freeable+0x3da/0x6a0
kernel_init+0x1b/0x200
ret_from_fork+0x44/0x70
ret_from_fork_asm+0x1a/0x30
-> #2 (&domain->iova_cookie->mutex){+.+.}-{3:3}:
__mutex_lock+0xb4/0xe40
mutex_lock_nested+0x1b/0x30
iommu_setup_dma_ops+0x16b/0x710
iommu_device_register+0x17d/0x260
intel_iommu_init+0xda4/0x11f0
pci_iommu_init+0x13/0x70
do_one_initcall+0x62/0x3f0
kernel_init_freeable+0x3da/0x6a0
kernel_init+0x1b/0x200
ret_from_fork+0x44/0x70
ret_from_fork_asm+0x1a/0x30
-> #1 (&group->mutex){+.+.}-{3:3}:
__mutex_lock+0xb4/0xe40
mutex_lock_nested+0x1b/0x30
__iommu_probe_device+0x24c/0x4e0
probe_iommu_group+0x2b/0x50
bus_for_each_dev+0x7d/0xe0
iommu_device_register+0xe1/0x260
intel_iommu_init+0xda4/0x11f0
pci_iommu_init+0x13/0x70
do_one_initcall+0x62/0x3f0
kernel_init_freeable+0x3da/0x6a0
kernel_init+0x1b/0x200
ret_from_fork+0x44/0x70
ret_from_fork_asm+0x1a/0x30
-> #0 (iommu_probe_device_lock){+.+.}-{3:3}:
__lock_acquire+0x1637/0x2810
lock_acquire+0xc9/0x300
__mutex_lock+0xb4/0xe40
mutex_lock_nested+0x1b/0x30
iommu_probe_device+0x1d/0x70
intel_iommu_init+0xe90/0x11f0
pci_iommu_init+0x13/0x70
do_one_initcall+0x62/0x3f0
kernel_init_freeable+0x3da/0x6a0
kernel_init+0x1b/0x200
ret_from_fork+0x44/0x70
ret_from_fork_asm+0x1a/0x30
other info that might help us debug this:
Chain exists of:
iommu_probe_device_lock --> dmar_global_lock -->
&device->physical_node_lock
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(&device->physical_node_lock);
lock(dmar_global_lock);
lock(&device->physical_node_lock);
lock(iommu_probe_device_lock);
*** DEADLOCK ***
This driver uses a global lock to protect the list of enumerated DMA
remapping units. It is necessary due to the driver's support for dynamic
addition and removal of remapping units at runtime.
Two distinct code paths require iteration over this remapping unit list:
- Device registration and probing: the driver iterates the list to
register each remapping unit with the upper layer IOMMU framework
and subsequently probe the devices managed by that unit.
- Global configuration: Upper layer components may also iterate the list
to apply configuration changes.
The lock acquisition order between these two code paths was reversed. This
caused lockdep warnings, indicating a risk of deadlock. Fix this warning
by releasing the global lock before invoking upper layer interfaces for
device registration.
Fixes: b150654f74 ("iommu/vt-d: Fix suspicious RCU usage")
Closes: https://lore.kernel.org/linux-iommu/SJ1PR11MB612953431F94F18C954C4A9CB9D32@SJ1PR11MB6129.namprd11.prod.outlook.com/
Tested-by: Chaitanya Kumar Borah <chaitanya.kumar.borah@intel.com>
Cc: stable@vger.kernel.org
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20250317035714.1041549-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 688124cc54 upstream.
Don't overwrite an IRTE that is posting IRQs to a vCPU with a posted MSI
entry if the host IRQ affinity happens to change. If/when the IRTE is
reverted back to "host mode", it will be reconfigured as a posted MSI or
remapped entry as appropriate.
Drop the "mode" field, which doesn't differentiate between posted MSIs and
posted vCPUs, in favor of a dedicated posted_vcpu flag. Note! The two
posted_{msi,vcpu} flags are intentionally not mutually exclusive; an IRTE
can transition between posted MSI and posted vCPU.
Fixes: ed1e48ea43 ("iommu/vt-d: Enable posted mode for device MSIs")
Cc: stable@vger.kernel.org
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Link: https://lore.kernel.org/r/20250315025135.2365846-3-seanjc@google.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit b150654f74 upstream.
Commit <d74169ceb0d2> ("iommu/vt-d: Allocate DMAR fault interrupts
locally") moved the call to enable_drhd_fault_handling() to a code
path that does not hold any lock while traversing the drhd list. Fix
it by ensuring the dmar_global_lock lock is held when traversing the
drhd list.
Without this fix, the following warning is triggered:
=============================
WARNING: suspicious RCU usage
6.14.0-rc3 #55 Not tainted
-----------------------------
drivers/iommu/intel/dmar.c:2046 RCU-list traversed in non-reader section!!
other info that might help us debug this:
rcu_scheduler_active = 1, debug_locks = 1
2 locks held by cpuhp/1/23:
#0: ffffffff84a67c50 (cpu_hotplug_lock){++++}-{0:0}, at: cpuhp_thread_fun+0x87/0x2c0
#1: ffffffff84a6a380 (cpuhp_state-up){+.+.}-{0:0}, at: cpuhp_thread_fun+0x87/0x2c0
stack backtrace:
CPU: 1 UID: 0 PID: 23 Comm: cpuhp/1 Not tainted 6.14.0-rc3 #55
Call Trace:
<TASK>
dump_stack_lvl+0xb7/0xd0
lockdep_rcu_suspicious+0x159/0x1f0
? __pfx_enable_drhd_fault_handling+0x10/0x10
enable_drhd_fault_handling+0x151/0x180
cpuhp_invoke_callback+0x1df/0x990
cpuhp_thread_fun+0x1ea/0x2c0
smpboot_thread_fn+0x1f5/0x2e0
? __pfx_smpboot_thread_fn+0x10/0x10
kthread+0x12a/0x2d0
? __pfx_kthread+0x10/0x10
ret_from_fork+0x4a/0x60
? __pfx_kthread+0x10/0x10
ret_from_fork_asm+0x1a/0x30
</TASK>
Holding the lock in enable_drhd_fault_handling() triggers a lockdep splat
about a possible deadlock between dmar_global_lock and cpu_hotplug_lock.
This is avoided by not holding dmar_global_lock when calling
iommu_device_register(), which initiates the device probe process.
Fixes: d74169ceb0 ("iommu/vt-d: Allocate DMAR fault interrupts locally")
Reported-and-tested-by: Ido Schimmel <idosch@nvidia.com>
Closes: https://lore.kernel.org/linux-iommu/Zx9OwdLIc_VoQ0-a@shredder.mtl.com/
Tested-by: Breno Leitao <leitao@debian.org>
Cc: stable@vger.kernel.org
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20250218022422.2315082-1-baolu.lu@linux.intel.com
Tested-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 74536f9196 upstream.
The qi_batch is allocated when assigning cache tag for a domain. While
for nested parent domain, it is missed. Hence, when trying to map pages
to the nested parent, NULL dereference occurred. Also, there is potential
memleak since there is no lock around domain->qi_batch allocation.
To solve it, add a helper for qi_batch allocation, and call it in both
the __cache_tag_assign_domain() and __cache_tag_assign_parent_domain().
BUG: kernel NULL pointer dereference, address: 0000000000000200
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
PGD 8104795067 P4D 0
Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI
CPU: 223 UID: 0 PID: 4357 Comm: qemu-system-x86 Not tainted 6.13.0-rc1-00028-g4b50c3c3b998-dirty #2632
Call Trace:
? __die+0x24/0x70
? page_fault_oops+0x80/0x150
? do_user_addr_fault+0x63/0x7b0
? exc_page_fault+0x7c/0x220
? asm_exc_page_fault+0x26/0x30
? cache_tag_flush_range_np+0x13c/0x260
intel_iommu_iotlb_sync_map+0x1a/0x30
iommu_map+0x61/0xf0
batch_to_domain+0x188/0x250
iopt_area_fill_domains+0x125/0x320
? rcu_is_watching+0x11/0x50
iopt_map_pages+0x63/0x100
iopt_map_common.isra.0+0xa7/0x190
iopt_map_user_pages+0x6a/0x80
iommufd_ioas_map+0xcd/0x1d0
iommufd_fops_ioctl+0x118/0x1c0
__x64_sys_ioctl+0x93/0xc0
do_syscall_64+0x71/0x140
entry_SYSCALL_64_after_hwframe+0x76/0x7e
Fixes: 705c1cdf1e ("iommu/vt-d: Introduce batched cache invalidation")
Cc: stable@vger.kernel.org
Co-developed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20241210130322.17175-1-yi.l.liu@intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 1f2557e08a upstream.
The current implementation removes cache tags after disabling ATS,
leading to potential memory leaks and kernel crashes. Specifically,
CACHE_TAG_DEVTLB type cache tags may still remain in the list even
after the domain is freed, causing a use-after-free condition.
This issue really shows up when multiple VFs from different PFs
passed through to a single user-space process via vfio-pci. In such
cases, the kernel may crash with kernel messages like:
BUG: kernel NULL pointer dereference, address: 0000000000000014
PGD 19036a067 P4D 1940a3067 PUD 136c9b067 PMD 0
Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI
CPU: 74 UID: 0 PID: 3183 Comm: testCli Not tainted 6.11.9 #2
RIP: 0010:cache_tag_flush_range+0x9b/0x250
Call Trace:
<TASK>
? __die+0x1f/0x60
? page_fault_oops+0x163/0x590
? exc_page_fault+0x72/0x190
? asm_exc_page_fault+0x22/0x30
? cache_tag_flush_range+0x9b/0x250
? cache_tag_flush_range+0x5d/0x250
intel_iommu_tlb_sync+0x29/0x40
intel_iommu_unmap_pages+0xfe/0x160
__iommu_unmap+0xd8/0x1a0
vfio_unmap_unpin+0x182/0x340 [vfio_iommu_type1]
vfio_remove_dma+0x2a/0xb0 [vfio_iommu_type1]
vfio_iommu_type1_ioctl+0xafa/0x18e0 [vfio_iommu_type1]
Move cache_tag_unassign_domain() before iommu_disable_pci_caps() to fix
it.
Fixes: 3b1d9e2b2d ("iommu/vt-d: Add cache tag assignment interface")
Cc: stable@vger.kernel.org
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20241129020506.576413-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit f1645676f2 ]
There are some issues in pgtable_walk():
1. Super page is dumped as non-present page
2. dma_pte_superpage() should not check against leaf page table entries
3. Pointer pte is never NULL so checking it is meaningless
4. When an entry is not present, it still makes sense to dump the entry
content.
Fix 1,2 by checking dma_pte_superpage()'s returned value after level check.
Fix 3 by removing pte check.
Fix 4 by checking present bit after printing.
By this chance, change to print "page table not present" instead of "PTE
not present" to be clearer.
Fixes: 914ff7719e ("iommu/vt-d: Dump DMAR translation structure when DMA fault occurs")
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Link: https://lore.kernel.org/r/20241024092146.715063-3-zhenzhong.duan@intel.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 6ceb93f952 ]
There are some issues in dmar_fault_dump_ptes():
1. return value of phys_to_virt() is used for checking if an entry is
present.
2. dump is confusing, e.g., "pasid table entry is not present", confusing
by unpresent pasid table vs. unpresent pasid table entry. Current code
means the former.
3. pgtable_walk() is called without checking if page table is present.
Fix 1 by checking present bit of an entry before dump a lower level entry.
Fix 2 by removing "entry" string, e.g., "pasid table is not present".
Fix 3 by checking page table present before walk.
Take issue 3 for example, before fix:
[ 442.240357] DMAR: pasid dir entry: 0x000000012c83e001
[ 442.246661] DMAR: pasid table entry[0]: 0x0000000000000000
[ 442.253429] DMAR: pasid table entry[1]: 0x0000000000000000
[ 442.260203] DMAR: pasid table entry[2]: 0x0000000000000000
[ 442.266969] DMAR: pasid table entry[3]: 0x0000000000000000
[ 442.273733] DMAR: pasid table entry[4]: 0x0000000000000000
[ 442.280479] DMAR: pasid table entry[5]: 0x0000000000000000
[ 442.287234] DMAR: pasid table entry[6]: 0x0000000000000000
[ 442.293989] DMAR: pasid table entry[7]: 0x0000000000000000
[ 442.300742] DMAR: PTE not present at level 2
After fix:
...
[ 357.241214] DMAR: pasid table entry[6]: 0x0000000000000000
[ 357.248022] DMAR: pasid table entry[7]: 0x0000000000000000
[ 357.254824] DMAR: scalable mode page table is not present
Fixes: 914ff7719e ("iommu/vt-d: Dump DMAR translation structure when DMA fault occurs")
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Link: https://lore.kernel.org/r/20241024092146.715063-2-zhenzhong.duan@intel.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Pull dma-mapping updates from Christoph Hellwig:
- support DMA zones for arm64 systems where memory starts at > 4GB
(Baruch Siach, Catalin Marinas)
- support direct calls into dma-iommu and thus obsolete dma_map_ops for
many common configurations (Leon Romanovsky)
- add DMA-API tracing (Sean Anderson)
- remove the not very useful return value from various dma_set_* APIs
(Christoph Hellwig)
- misc cleanups and minor optimizations (Chen Y, Yosry Ahmed, Christoph
Hellwig)
* tag 'dma-mapping-6.12-2024-09-19' of git://git.infradead.org/users/hch/dma-mapping:
dma-mapping: reflow dma_supported
dma-mapping: reliably inform about DMA support for IOMMU
dma-mapping: add tracing for dma-mapping API calls
dma-mapping: use IOMMU DMA calls for common alloc/free page calls
dma-direct: optimize page freeing when it is not addressable
dma-mapping: clearly mark DMA ops as an architecture feature
vdpa_sim: don't select DMA_OPS
arm64: mm: keep low RAM dma zone
dma-mapping: don't return errors from dma_set_max_seg_size
dma-mapping: don't return errors from dma_set_seg_boundary
dma-mapping: don't return errors from dma_set_min_align_mask
scsi: check that busses support the DMA API before setting dma parameters
arm64: mm: fix DMA zone when dma-ranges is missing
dma-mapping: direct calls for dma-iommu
dma-mapping: call ->unmap_page and ->unmap_sg unconditionally
arm64: support DMA zone above 4GB
dma-mapping: replace zone_dma_bits by zone_dma_limit
dma-mapping: use bit masking to check VM_DMA_COHERENT
Pull perf events updates from Ingo Molnar:
- Implement per-PMU context rescheduling to significantly improve
single-PMU performance, and related cleanups/fixes (Peter Zijlstra
and Namhyung Kim)
- Fix ancient bug resulting in a lot of events being dropped
erroneously at higher sampling frequencies (Luo Gengkun)
- uprobes enhancements:
- Implement RCU-protected hot path optimizations for better
performance:
"For baseline vs SRCU, peak througput increased from 3.7 M/s
(million uprobe triggerings per second) up to about 8 M/s. For
uretprobes it's a bit more modest with bump from 2.4 M/s to
5 M/s.
For SRCU vs RCU Tasks Trace, peak throughput for uprobes
increases further from 8 M/s to 10.3 M/s (+28%!), and for
uretprobes from 5.3 M/s to 5.8 M/s (+11%), as we have more
work to do on uretprobes side.
Even single-thread (no contention) performance is slightly
better: 3.276 M/s to 3.396 M/s (+3.5%) for uprobes, and 2.055
M/s to 2.174 M/s (+5.8%) for uretprobes."
(Andrii Nakryiko et al)
- Document mmap_lock, don't abuse get_user_pages_remote() (Oleg
Nesterov)
- Cleanups & fixes to prepare for future work:
- Remove uprobe_register_refctr()
- Simplify error handling for alloc_uprobe()
- Make uprobe_register() return struct uprobe *
- Fold __uprobe_unregister() into uprobe_unregister()
- Shift put_uprobe() from delete_uprobe() to uprobe_unregister()
- BPF: Fix use-after-free in bpf_uprobe_multi_link_attach()
(Oleg Nesterov)
- New feature & ABI extension: allow events to use PERF_SAMPLE READ
with inheritance, enabling sample based profiling of a group of
counters over a hierarchy of processes or threads (Ben Gainey)
- Intel uncore & power events updates:
- Add Arrow Lake and Lunar Lake support
- Add PERF_EV_CAP_READ_SCOPE
- Clean up and enhance cpumask and hotplug support
(Kan Liang)
- Add LNL uncore iMC freerunning support
- Use D0:F0 as a default device
(Zhenyu Wang)
- Intel PT: fix AUX snapshot handling race (Adrian Hunter)
- Misc fixes and cleanups (James Clark, Jiri Olsa, Oleg Nesterov and
Peter Zijlstra)
* tag 'perf-core-2024-09-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (40 commits)
dmaengine: idxd: Clean up cpumask and hotplug for perfmon
iommu/vt-d: Clean up cpumask and hotplug for perfmon
perf/x86/intel/cstate: Clean up cpumask and hotplug
perf: Add PERF_EV_CAP_READ_SCOPE
perf: Generic hotplug support for a PMU with a scope
uprobes: perform lockless SRCU-protected uprobes_tree lookup
rbtree: provide rb_find_rcu() / rb_find_add_rcu()
perf/uprobe: split uprobe_unregister()
uprobes: travers uprobe's consumer list locklessly under SRCU protection
uprobes: get rid of enum uprobe_filter_ctx in uprobe filter callbacks
uprobes: protected uprobe lifetime with SRCU
uprobes: revamp uprobe refcounting and lifetime management
bpf: Fix use-after-free in bpf_uprobe_multi_link_attach()
perf/core: Fix small negative period being ignored
perf: Really fix event_function_call() locking
perf: Optimize __pmu_ctx_sched_out()
perf: Add context time freeze
perf: Fix event_function_call() locking
perf: Extract a few helpers
perf: Optimize context reschedule for single PMU cases
...
Pull iommu updates from Joerg Roedel:
"Core changes:
- Allow ATS on VF when parent device is identity mapped
- Optimize unmap path on ARM io-pagetable implementation
- Use of_property_present()
ARM-SMMU changes:
- SMMUv2:
- Devicetree binding updates for Qualcomm MMU-500 implementations
- Extend workarounds for broken Qualcomm hypervisor to avoid
touching features that are not available (e.g. 16KiB page
support, reserved context banks)
- SMMUv3:
- Support for NVIDIA's custom virtual command queue hardware
- Fix Stage-2 stall configuration and extend tests to cover this
area
- A bunch of driver cleanups, including simplification of the
master rbtree code
- Minor cleanups and fixes across both drivers
Intel VT-d changes:
- Retire si_domain and convert to use static identity domain
- Batched IOTLB/dev-IOTLB invalidation
- Small code refactoring and cleanups
AMD-Vi changes:
- Cleanup and refactoring of io-pagetable code
- Add parameter to limit the used io-pagesizes
- Other cleanups and fixes"
* tag 'iommu-updates-v6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/iommu/linux: (77 commits)
dt-bindings: arm-smmu: Add compatible for QCS8300 SoC
iommu/amd: Test for PAGING domains before freeing a domain
iommu/amd: Fix argument order in amd_iommu_dev_flush_pasid_all()
iommu/amd: Add kernel parameters to limit V1 page-sizes
iommu/arm-smmu-v3: Reorganize struct arm_smmu_ctx_desc_cfg
iommu/arm-smmu-v3: Add types for each level of the CD table
iommu/arm-smmu-v3: Shrink the cdtab l1_desc array
iommu/arm-smmu-v3: Do not use devm for the cd table allocations
iommu/arm-smmu-v3: Remove strtab_base/cfg
iommu/arm-smmu-v3: Reorganize struct arm_smmu_strtab_cfg
iommu/arm-smmu-v3: Add types for each level of the 2 level stream table
iommu/arm-smmu-v3: Add arm_smmu_strtab_l1/2_idx()
iommu/arm-smmu-qcom: apply num_context_bank fixes for SDM630 / SDM660
iommu/arm-smmu-v3: Use the new rb tree helpers
dt-bindings: arm-smmu: document the support on SA8255p
iommu/tegra241-cmdqv: Do not allocate vcmdq until dma_set_mask_and_coherent
iommu/tegra241-cmdqv: Drop static at local variable
iommu/tegra241-cmdqv: Fix ioremap() error handling in probe()
iommu/amd: Do not set the D bit on AMD v2 table entries
iommu/amd: Correct the reported page sizes from the V1 table
...
Pull x86 APIC updates from Thomas Gleixner:
- Handle an allocation failure in the IO/APIC code gracefully instead
of crashing the machine.
- Remove support for APIC local destination mode on 64bit
Logical destination mode of the local APIC is used for systems with
up to 8 CPUs. It has an advantage over physical destination mode as
it allows to target multiple CPUs at once with IPIs. That advantage
was definitely worth it when systems with up to 8 CPUs were state of
the art for servers and workstations, but that's history.
In the recent past there were quite some reports of new laptops
failing to boot with logical destination mode, but they work fine
with physical destination mode. That's not a suprise because physical
destination mode is guaranteed to work as it's the only way to get a
CPU up and running via the INIT/INIT/STARTUP sequence. Some of the
affected systems were cured by BIOS updates, but not all OEMs provide
them.
As the number of CPUs keep increasing, logical destination mode
becomes less used and the benefit for small systems, like laptops, is
not really worth the trouble. So just remove logical destination mode
support for 64bit and be done with it.
- Code and comment cleanups in the APIC area.
* tag 'x86-apic-2024-09-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/irq: Fix comment on IRQ vector layout
x86/apic: Remove unused extern declarations
x86/apic: Remove logical destination mode for 64-bit
x86/apic: Remove unused inline function apic_set_eoi_cb()
x86/ioapic: Cleanup remaining coding style issues
x86/ioapic: Cleanup line breaks
x86/ioapic: Cleanup bracket usage
x86/ioapic: Cleanup comments
x86/ioapic: Move replace_pin_at_irq_node() to the call site
iommu/vt-d: Cleanup apic_printk()
x86/mpparse: Cleanup apic_printk()s
x86/ioapic: Cleanup guarded debug printk()s
x86/ioapic: Cleanup apic_printk()s
x86/apic: Cleanup apic_printk()s
x86/apic: Provide apic_printk() helpers
x86/ioapic: Use guard() for locking where applicable
x86/ioapic: Cleanup structs
x86/ioapic: Mark mp_alloc_timer_irq() __init
x86/ioapic: Handle allocation failures gracefully
Extracts IOTLB and Dev-IOTLB invalidation logic from cache tag flush
interfaces into dedicated helper functions. It prepares the codebase
for upcoming changes to support batched cache invalidations.
To enable direct use of qi_flush helpers in the new functions,
iommu->flush.flush_iotlb and quirk_extra_dev_tlb_flush() are opened up.
No functional changes are intended.
Co-developed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Tina Zhang <tina.zhang@intel.com>
Link: https://lore.kernel.org/r/20240815065221.50328-3-tina.zhang@intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Separate the logic for constructing IOTLB and device TLB invalidation
descriptors from the qi_flush interfaces. New helpers, qi_desc(), are
introduced to encapsulate this common functionality.
Moving descriptor composition code to new helpers enables its reuse in
the upcoming qi_batch interfaces.
No functional changes are intended.
Signed-off-by: Tina Zhang <tina.zhang@intel.com>
Link: https://lore.kernel.org/r/20240815065221.50328-2-tina.zhang@intel.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The caching mode of an IOMMU is irrelevant to the behavior of the device
TLB. Previously, commit <304b3bde24b5> ("iommu/vt-d: Remove caching mode
check before device TLB flush") removed this redundant check in the
domain unmap path.
Checking the caching mode before flushing the device TLB after a pasid
table entry is updated is unnecessary and can lead to inconsistent
behavior.
Extends this consistency by removing the caching mode check in the pasid
table update path.
Suggested-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20240820030208.20020-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
If qi_submit_sync() is invoked with 0 invalidation descriptors (for
instance, for DMA draining purposes), we can run into a bug where a
submitting thread fails to detect the completion of invalidation_wait.
Subsequently, this led to a soft lockup. Currently, there is no impact
by this bug on the existing users because no callers are submitting
invalidations with 0 descriptors. This fix will enable future users
(such as DMA drain) calling qi_submit_sync() with 0 count.
Suppose thread T1 invokes qi_submit_sync() with non-zero descriptors, while
concurrently, thread T2 calls qi_submit_sync() with zero descriptors. Both
threads then enter a while loop, waiting for their respective descriptors
to complete. T1 detects its completion (i.e., T1's invalidation_wait status
changes to QI_DONE by HW) and proceeds to call reclaim_free_desc() to
reclaim all descriptors, potentially including adjacent ones of other
threads that are also marked as QI_DONE.
During this time, while T2 is waiting to acquire the qi->q_lock, the IOMMU
hardware may complete the invalidation for T2, setting its status to
QI_DONE. However, if T1's execution of reclaim_free_desc() frees T2's
invalidation_wait descriptor and changes its status to QI_FREE, T2 will
not observe the QI_DONE status for its invalidation_wait and will
indefinitely remain stuck.
This soft lockup does not occur when only non-zero descriptors are
submitted.In such cases, invalidation descriptors are interspersed among
wait descriptors with the status QI_IN_USE, acting as barriers. These
barriers prevent the reclaim code from mistakenly freeing descriptors
belonging to other submitters.
Considered the following example timeline:
T1 T2
========================================
ID1
WD1
while(WD1!=QI_DONE)
unlock
lock
WD1=QI_DONE* WD2
while(WD2!=QI_DONE)
unlock
lock
WD1==QI_DONE?
ID1=QI_DONE WD2=DONE*
reclaim()
ID1=FREE
WD1=FREE
WD2=FREE
unlock
soft lockup! T2 never sees QI_DONE in WD2
Where:
ID = invalidation descriptor
WD = wait descriptor
* Written by hardware
The root of the problem is that the descriptor status QI_DONE flag is used
for two conflicting purposes:
1. signal a descriptor is ready for reclaim (to be freed)
2. signal by the hardware that a wait descriptor is complete
The solution (in this patch) is state separation by using QI_FREE flag
for #1.
Once a thread's invalidation descriptors are complete, their status would
be set to QI_FREE. The reclaim_free_desc() function would then only
free descriptors marked as QI_FREE instead of those marked as
QI_DONE. This change ensures that T2 (from the previous example) will
correctly observe the completion of its invalidation_wait (marked as
QI_DONE).
Signed-off-by: Sanjay K Kumar <sanjay.k.kumar@intel.com>
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20240728210059.1964602-1-jacob.jun.pan@linux.intel.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Software determines VT-d hardware support for passthrough translation by
inspecting the capability register. If passthrough translation is not
supported, the device is instructed to use DMA domain for its default
domain.
Add a global static identity domain with guaranteed attach semantics for
IOMMUs that support passthrough translation mode.
The global static identity domain is a dummy domain without corresponding
dmar_domain structure. Consequently, the device's info->domain will be
NULL with the identity domain is attached. Refactor the code accordingly.
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/20240809055431.36513-7-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The has_iotlb_device flag was used to indicate if a domain had attached
devices with ATS enabled. Domains without this flag didn't require device
TLB invalidation during unmap operations, optimizing performance by
avoiding unnecessary device iteration.
With the introduction of cache tags, this flag is no longer needed. The
code to iterate over attached devices was removed by commit 06792d0679
("iommu/vt-d: Cleanup use of iommu_flush_iotlb_psi()").
Remove has_iotlb_device to avoid unnecessary code.
Suggested-by: Jason Gunthorpe <jgg@nvidia.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/20240809055431.36513-5-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The iommu core defines the def_domain_type callback to query the iommu
driver about hardware capability and quirks. The iommu driver should
declare IOMMU_DOMAIN_DMA requirement for hardware lacking pass-through
capability.
Earlier VT-d hardware implementations did not support pass-through
translation mode. The iommu driver relied on a paging domain with all
physical system memory addresses identically mapped to the same IOVA
to simulate pass-through translation before the def_domain_type was
introduced and it has been kept until now. It's time to adjust it now
to make the Intel iommu driver follow the def_domain_type semantics.
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>
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Link: https://lore.kernel.org/r/20240809055431.36513-2-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
