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
Pull SoC driver updates from Arnd Bergmann:
"This is the first half of the driver changes:
- A treewide interface change to the "syscore" operations for power
management, as a preparation for future Tegra specific changes
- Reset controller updates with added drivers for LAN969x, eic770 and
RZ/G3S SoCs
- Protection of system controller registers on Renesas and Google
SoCs, to prevent trivially triggering a system crash from e.g.
debugfs access
- soc_device identification updates on Nvidia, Exynos and Mediatek
- debugfs support in the ST STM32 firewall driver
- Minor updates for SoC drivers on AMD/Xilinx, Renesas, Allwinner, TI
- Cleanups for memory controller support on Nvidia and Renesas"
* tag 'soc-drivers-6.19' of git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc: (114 commits)
memory: tegra186-emc: Fix missing put_bpmp
Documentation: reset: Remove reset_controller_add_lookup()
reset: fix BIT macro reference
reset: rzg2l-usbphy-ctrl: Fix a NULL vs IS_ERR() bug in probe
reset: th1520: Support reset controllers in more subsystems
reset: th1520: Prepare for supporting multiple controllers
dt-bindings: reset: thead,th1520-reset: Add controllers for more subsys
dt-bindings: reset: thead,th1520-reset: Remove non-VO-subsystem resets
reset: remove legacy reset lookup code
clk: davinci: psc: drop unused reset lookup
reset: rzg2l-usbphy-ctrl: Add support for RZ/G3S SoC
reset: rzg2l-usbphy-ctrl: Add support for USB PWRRDY
dt-bindings: reset: renesas,rzg2l-usbphy-ctrl: Document RZ/G3S support
reset: eswin: Add eic7700 reset driver
dt-bindings: reset: eswin: Documentation for eic7700 SoC
reset: sparx5: add LAN969x support
dt-bindings: reset: microchip: Add LAN969x support
soc: rockchip: grf: Add select correct PWM implementation on RK3368
soc/tegra: pmc: Add USB wake events for Tegra234
amba: tegra-ahb: Fix device leak on SMMU enable
...
VT-d second stage HW specifies both the maximum IOVA and the supported
table walk starting points. Weirdly there is HW that only supports a 4
level walk but has a maximum IOVA that only needs 3.
The current code miscalculates this and creates a wrongly sized page table
which ultimately fails the compatibility check for number of levels.
This is fixed by allowing the page table to be created with both a vasz
and top_level input. The vasz will set the aperture for the domain while
the top_level will set the page table geometry.
Add top_level to vtdss and correct the logic in VT-d to generate the right
top_level and vasz from mgaw and sagaw.
Fixes: d373449d8e ("iommu/vt-d: Use the generic iommu page table")
Reported-by: Calvin Owens <calvin@wbinvd.org>
Closes: https://lore.kernel.org/r/8f257d2651eb8a4358fcbd47b0145002e5f1d638.1764237717.git.calvin@wbinvd.org
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Tested-by: Calvin Owens <calvin@wbinvd.org>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Commit d373449d8e ("iommu/vt-d: Use the generic iommu page table")
changed the calculation of domain::aperture_end. Previously, it was
calculated as:
domain->domain.geometry.aperture_end =
__DOMAIN_MAX_ADDR(domain->gaw - 1);
where domain->gaw was limited to less than MGAW.
Currently, it is calculated purely based on the max level of the page
table that the hardware supports. This is incorrect as stated in Section
3.6 of the VT-d spec:
"Software using first-stage translation structures to translate an IO
Virtual Address (IOVA) must use canonical addresses. Additionally,
software must limit addresses to less than the minimum of MGAW and the
lower canonical address width implied by FSPM (i.e., 47-bit when FSPM
is 4-level and 56-bit when FSPM is 5-level)."
Restore the previous calculation method for domain::aperture_end to avoid
violating the spec. Incorrect aperture calculation causes GPU hangs
without generating VT-d faults on some Intel client platforms.
Fixes: d373449d8e ("iommu/vt-d: Use the generic iommu page table")
Reported-by: Chaitanya Kumar Borah <chaitanya.kumar.borah@intel.com>
Closes: https://lore.kernel.org/r/4f15cf3b-6fad-4cd8-87e5-6d86c0082673@intel.com
Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Suggested-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
INTEL_IOMMU_FLOPPY_WA workaround was introduced to create direct mappings
for first 16MB for floppy devices as the floppy drivers were not using
dma apis. We need not do this direct map if floppy driver is not
enabled.
INTEL_IOMMU_FLOPPY_WA is generally not a good idea. Iommu will be
mapping pages in this address range while kernel would also be
allocating from this range(mostly on memory stress). A misbehaving
device using this domain will have access to the pages that the
kernel might be actively using. We noticed this while running a test
that was trying to figure out if any pages used by kernel is in iommu
page tables.
This patch reduces the scope of the above issue by disabling the
workaround when floppy driver is not enabled. But we would still need to
fix the floppy driver to use dma apis so that we need not do direct map
without reserving the pages. Or the other option is to reserve this
memory range in firmware so that kernel will not use the pages.
Fixes: d850c2ee5f ("iommu/vt-d: Expose ISA direct mapping region via iommu_get_resv_regions")
Fixes: 49a0429e53 ("Intel IOMMU: Iommu floppy workaround")
Signed-off-by: Vineeth Pillai (Google) <vineeth@bitbyteword.org>
Link: https://lore.kernel.org/r/20251002161625.1155133-1-vineeth@bitbyteword.org
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Several drivers can benefit from registering per-instance data along
with the syscore operations. To achieve this, move the modifiable fields
out of the syscore_ops structure and into a separate struct syscore that
can be registered with the framework. Add a void * driver data field for
drivers to store contextual data that will be passed to the syscore ops.
Acked-by: Rafael J. Wysocki (Intel) <rafael@kernel.org>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Currently a incoherent walk domain cannot be attached to a coherent
capable iommu. Kevin says HW probably doesn't exist with such a mixture,
but making the driver support it makes logical sense anyhow.
When building the PASID entry the PWSNP (Page Walk Snoop) bit tells the HW
if it should issue snoops. If the page table is cache flushed because of
PT_FEAT_DMA_INCOHERENT then it is fine to set this bit to 0 even if the HW
supports 1.
Weaken the compatible check to permit a coherent instance to accept an
incoherent table and fix the PASID table construction to set PWSNP from
PT_FEAT_DMA_INCOHERENT.
SVA always sets PWSNP.
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Replace the VT-d iommu_domain implementation of the VT-d second stage and
first stage page tables with the iommupt VTDSS and x86_64
pagetables. x86_64 is shared with the AMD driver.
There are a couple notable things in VT-d:
- Like AMD the second stage format is not sign extended, unlike AMD it
cannot decode a full 64 bits. The first stage format is a normal sign
extended x86 page table
- The HW caps can indicate how many levels, how many address bits and what
leaf page sizes are supported in HW. As before the highest number of
levels that can translate the entire supported address width is used.
The supported page sizes are adjusted directly from the dedicated
first/second stage cap bits.
- VTD requires flushing 'write buffers'. This logic is left unchanged,
the write buffer flushes on any gather flush or through iotlb_sync_map.
- Like ARM, VTD has an optional non-coherent page table walker that
requires cache flushing. This is supported through PT_FEAT_DMA_INCOHERENT
the same as ARM, however x86 can't use the DMA API for flush, it must
call the arch function clflush_cache_range()
- The PT_FEAT_DYNAMIC_TOP can probably be supported on VT-d someday for the
second stage when it uses 128 bit atomic stores for the HW context
structures.
- PT_FEAT_VTDSS_FORCE_WRITEABLE is used to work around ERRATA_772415_SPR17
- A kernel command line parameter "sp_off" disables all page sizes except
4k
Remove all the unused iommu_domain page table code. The debugfs paths have
their own independent page table walker that is left alone for now.
This corrects a race with the non-coherent walker that the ARM
implementations have fixed:
CPU 0 CPU 1
pfn_to_dma_pte() pfn_to_dma_pte()
pte = &parent[offset];
if (!dma_pte_present(pte)) {
try_cmpxchg64(&pte->val)
pte = &parent[offset];
.. dma_pte_present(pte) ..
[...]
// iommu_map() completes
// Device does DMA
domain_flush_cache(pte)
The CPU 1 mapping operation shares a page table level with the CPU 0
mapping operation. CPU 0 installed a new page table level but has not
flushed it yet. CPU1 returns from iommu_map() and the device does DMA. The
non coherent walker fails to see the new table level installed by CPU 0
and fails the DMA with non-present.
The iommupt PT_FEAT_DMA_INCOHERENT implementation uses the ARM design of
storing a flag when CPU 0 completes the flush. If the flag is not set CPU
1 will also flush to ensure the HW can fully walk to the PTE being
installed.
Cc: Tina Zhang <tina.zhang@intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
The IOMMU core attaches each device to a default domain on probe(). Then,
every new "attach" operation has a fundamental meaning of two-fold:
- detach from its currently attached (old) domain
- attach to a given new domain
Modern IOMMU drivers following this pattern usually want to clean up the
things related to the old domain, so they call iommu_get_domain_for_dev()
to fetch the old domain.
Pass in the old domain pointer from the core to drivers, aligning with the
set_dev_pasid op that does so already.
Ensure all low-level attach fcuntions in the core can forward the correct
old domain pointer. Thus, rework those functions as well.
Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
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>
The register-based cache invalidation interface is in the process of being
replaced by the queued invalidation interface. The VT-d architecture
allows hardware implementations with a queued invalidation interface to
not implement the registers used for cache invalidation. Currently, the
debugfs interface dumps the Context Command Register unconditionally,
which is not reasonable.
Remove it to avoid potential access to non-present registers.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20250917025051.143853-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
The advanced fault logging has been removed from the specification since
v4.0. Linux doesn't implement advanced fault logging functionality, but
it currently dumps the advanced logging registers through debugfs. Remove
the dumping of these advanced fault logging registers through debugfs to
avoid potential access to non-present registers.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20250917024850.143801-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
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>
Bit 66 in the page group response descriptor used to be the LPIG (Last
Page in Group), but it was marked as Reserved since Specification 4.0.
Remove programming on this bit to make it consistent with the latest
specification.
Existing hardware all treats bit 66 of the page group response descriptor
as "ignored", therefore this change doesn't break any existing hardware.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20250901053943.1708490-1-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
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>
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>
Pull PCI updates from Bjorn Helgaas:
"Enumeration:
- Allow built-in drivers, not just modular drivers, to use async
initial probing (Lukas Wunner)
- Support Immediate Readiness even on devices with no PM Capability
(Sean Christopherson)
- Consolidate definition of PCIE_RESET_CONFIG_WAIT_MS (100ms), the
required delay between a reset and sending config requests to a
device (Niklas Cassel)
- Add pci_is_display() to check for "Display" base class and use it
in ALSA hda, vfio, vga_switcheroo, vt-d (Mario Limonciello)
- Allow 'isolated PCI functions' (multi-function devices without a
function 0) for LoongArch, similar to s390 and jailhouse (Huacai
Chen)
Power control:
- Add ability to enable optional slot clock for cases where the PCIe
host controller and the slot are supplied by different clocks
(Marek Vasut)
PCIe native device hotplug:
- Fix runtime PM ref imbalance on Hot-Plug Capable ports caused by
misinterpreting a config read failure after a device has been
removed (Lukas Wunner)
- Avoid creating a useless PCIe port service device for pciehp if the
slot is handled by the ACPI hotplug driver (Lukas Wunner)
- Ignore ACPI hotplug slots when calculating depth of pciehp hotplug
ports (Lukas Wunner)
Virtualization:
- Save VF resizable BAR state and restore it after reset (Michał
Winiarski)
- Allow IOV resources (VF BARs) to be resized (Michał Winiarski)
- Add pci_iov_vf_bar_set_size() so drivers can control VF BAR size
(Michał Winiarski)
Endpoint framework:
- Add RC-to-EP doorbell support using platform MSI controller,
including a test case (Frank Li)
- Allow BAR assignment via configfs so platforms have flexibility in
determining BAR usage (Jerome Brunet)
Native PCIe controller drivers:
- Convert amazon,al-alpine-v[23]-pcie, apm,xgene-pcie,
axis,artpec6-pcie, marvell,armada-3700-pcie, st,spear1340-pcie to
DT schema format (Rob Herring)
- Use dev_fwnode() instead of of_fwnode_handle() to remove OF
dependency in altera (fixes an unused variable), designware-host,
mediatek, mediatek-gen3, mobiveil, plda, xilinx, xilinx-dma,
xilinx-nwl (Jiri Slaby, Arnd Bergmann)
- Convert aardvark, altera, brcmstb, designware-host, iproc,
mediatek, mediatek-gen3, mobiveil, plda, rcar-host, vmd, xilinx,
xilinx-dma, xilinx-nwl from using pci_msi_create_irq_domain() to
using msi_create_parent_irq_domain() instead; this makes the
interrupt controller per-PCI device, allows dynamic allocation of
vectors after initialization, and allows support of IMS (Nam Cao)
APM X-Gene PCIe controller driver:
- Rewrite MSI handling to MSI CPU affinity, drop useless CPU hotplug
bits, use device-managed memory allocations, and clean things up
(Marc Zyngier)
- Probe xgene-msi as a standard platform driver rather than a
subsys_initcall (Marc Zyngier)
Broadcom STB PCIe controller driver:
- Add optional DT 'num-lanes' property and if present, use it to
override the Maximum Link Width advertised in Link Capabilities
(Jim Quinlan)
Cadence PCIe controller driver:
- Use PCIe Message routing types from the PCI core rather than
defining private ones (Hans Zhang)
Freescale i.MX6 PCIe controller driver:
- Add IMX8MQ_EP third 64-bit BAR in epc_features (Richard Zhu)
- Add IMX8MM_EP and IMX8MP_EP fixed 256-byte BAR 4 in epc_features
(Richard Zhu)
- Configure LUT for MSI/IOMMU in Endpoint mode so Root Complex can
trigger doorbel on Endpoint (Frank Li)
- Remove apps_reset (LTSSM_EN) from
imx_pcie_{assert,deassert}_core_reset(), which fixes a hotplug
regression on i.MX8MM (Richard Zhu)
- Delay Endpoint link start until configfs 'start' written (Richard
Zhu)
Intel VMD host bridge driver:
- Add Intel Panther Lake (PTL)-H/P/U Vendor ID (George D Sworo)
Qualcomm PCIe controller driver:
- Add DT binding and driver support for SA8255p, which supports ECAM
for Configuration Space access (Mayank Rana)
- Update DT binding and driver to describe PHYs and per-Root Port
resets in a Root Port stanza and deprecate describing them in the
host bridge; this makes it possible to support multiple Root Ports
in the future (Krishna Chaitanya Chundru)
- Add Qualcomm QCS615 to SM8150 DT binding (Ziyue Zhang)
- Add Qualcomm QCS8300 to SA8775p DT binding (Ziyue Zhang)
- Drop TBU and ref clocks from Qualcomm SM8150 and SC8180x DT
bindings (Konrad Dybcio)
- Document 'link_down' reset in Qualcomm SA8775P DT binding (Ziyue
Zhang)
- Add required PCIE_RESET_CONFIG_WAIT_MS delay after Link up IRQ
(Niklas Cassel)
Rockchip PCIe controller driver:
- Drop unused PCIe Message routing and code definitions (Hans Zhang)
- Remove several unused header includes (Hans Zhang)
- Use standard PCIe config register definitions instead of
rockchip-specific redefinitions (Geraldo Nascimento)
- Set Target Link Speed to 5.0 GT/s before retraining so we have a
chance to train at a higher speed (Geraldo Nascimento)
Rockchip DesignWare PCIe controller driver:
- Prevent race between link training and register update via DBI by
inhibiting link training after hot reset and link down (Wilfred
Mallawa)
- Add required PCIE_RESET_CONFIG_WAIT_MS delay after Link up IRQ
(Niklas Cassel)
Sophgo PCIe controller driver:
- Add DT binding and driver for Sophgo SG2044 PCIe controller driver
in Root Complex mode (Inochi Amaoto)
Synopsys DesignWare PCIe controller driver:
- Add required PCIE_RESET_CONFIG_WAIT_MS after waiting for Link up on
Ports that support > 5.0 GT/s. Slower Ports still rely on the
not-quite-correct PCIE_LINK_WAIT_SLEEP_MS 90ms default delay while
waiting for the Link (Niklas Cassel)"
* tag 'pci-v6.17-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/pci/pci: (116 commits)
dt-bindings: PCI: qcom,pcie-sa8775p: Document 'link_down' reset
dt-bindings: PCI: Remove 83xx-512x-pci.txt
dt-bindings: PCI: Convert amazon,al-alpine-v[23]-pcie to DT schema
dt-bindings: PCI: Convert marvell,armada-3700-pcie to DT schema
dt-bindings: PCI: Convert apm,xgene-pcie to DT schema
dt-bindings: PCI: Convert axis,artpec6-pcie to DT schema
dt-bindings: PCI: Convert st,spear1340-pcie to DT schema
PCI: Move is_pciehp check out of pciehp_is_native()
PCI: pciehp: Use is_pciehp instead of is_hotplug_bridge
PCI/portdrv: Use is_pciehp instead of is_hotplug_bridge
PCI/ACPI: Fix runtime PM ref imbalance on Hot-Plug Capable ports
selftests: pci_endpoint: Add doorbell test case
misc: pci_endpoint_test: Add doorbell test case
PCI: endpoint: pci-epf-test: Add doorbell test support
PCI: endpoint: Add pci_epf_align_inbound_addr() helper for inbound address alignment
PCI: endpoint: pci-ep-msi: Add checks for MSI parent and mutability
PCI: endpoint: Add RC-to-EP doorbell support using platform MSI controller
PCI: dwc: Add Sophgo SG2044 PCIe controller driver in Root Complex mode
PCI: vmd: Switch to msi_create_parent_irq_domain()
PCI: vmd: Convert to lock guards
...
Pull iommufd updates from Jason Gunthorpe:
"This broadly brings the assigned HW command queue support to iommufd.
This feature is used to improve SVA performance in VMs by avoiding
paravirtualization traps during SVA invalidations.
Along the way I think some of the core logic is in a much better state
to support future driver backed features.
Summary:
- IOMMU HW now has features to directly assign HW command queues to a
guest VM. In this mode the command queue operates on a limited set
of invalidation commands that are suitable for improving guest
invalidation performance and easy for the HW to virtualize.
This brings the generic infrastructure to allow IOMMU drivers to
expose such command queues through the iommufd uAPI, mmap the
doorbell pages, and get the guest physical range for the command
queue ring itself.
- An implementation for the NVIDIA SMMUv3 extension "cmdqv" is built
on the new iommufd command queue features. It works with the
existing SMMU driver support for cmdqv in guest VMs.
- Many precursor cleanups and improvements to support the above
cleanly, changes to the general ioctl and object helpers, driver
support for VDEVICE, and mmap pgoff cookie infrastructure.
- Sequence VDEVICE destruction to always happen before VFIO device
destruction. When using the above type features, and also in future
confidential compute, the internal virtual device representation
becomes linked to HW or CC TSM configuration and objects. If a VFIO
device is removed from iommufd those HW objects should also be
cleaned up to prevent a sort of UAF. This became important now that
we have HW backing the VDEVICE.
- Fix one syzkaller found error related to math overflows during iova
allocation"
* tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd: (57 commits)
iommu/arm-smmu-v3: Replace vsmmu_size/type with get_viommu_size
iommu/arm-smmu-v3: Do not bother impl_ops if IOMMU_VIOMMU_TYPE_ARM_SMMUV3
iommufd: Rename some shortterm-related identifiers
iommufd/selftest: Add coverage for vdevice tombstone
iommufd/selftest: Explicitly skip tests for inapplicable variant
iommufd/vdevice: Remove struct device reference from struct vdevice
iommufd: Destroy vdevice on idevice destroy
iommufd: Add a pre_destroy() op for objects
iommufd: Add iommufd_object_tombstone_user() helper
iommufd/viommu: Roll back to use iommufd_object_alloc() for vdevice
iommufd/selftest: Test reserved regions near ULONG_MAX
iommufd: Prevent ALIGN() overflow
iommu/tegra241-cmdqv: import IOMMUFD module namespace
iommufd: Do not allow _iommufd_object_alloc_ucmd if abort op is set
iommu/tegra241-cmdqv: Add IOMMU_VEVENTQ_TYPE_TEGRA241_CMDQV support
iommu/tegra241-cmdqv: Add user-space use support
iommu/tegra241-cmdqv: Do not statically map LVCMDQs
iommu/tegra241-cmdqv: Simplify deinit flow in tegra241_cmdqv_remove_vintf()
iommu/tegra241-cmdqv: Use request_threaded_irq
iommu/arm-smmu-v3-iommufd: Add hw_info to impl_ops
...
Pull kvm updates from Paolo Bonzini:
"ARM:
- Host driver for GICv5, the next generation interrupt controller for
arm64, including support for interrupt routing, MSIs, interrupt
translation and wired interrupts
- Use FEAT_GCIE_LEGACY on GICv5 systems to virtualize GICv3 VMs on
GICv5 hardware, leveraging the legacy VGIC interface
- Userspace control of the 'nASSGIcap' GICv3 feature, allowing
userspace to disable support for SGIs w/o an active state on
hardware that previously advertised it unconditionally
- Map supporting endpoints with cacheable memory attributes on
systems with FEAT_S2FWB and DIC where KVM no longer needs to
perform cache maintenance on the address range
- Nested support for FEAT_RAS and FEAT_DoubleFault2, allowing the
guest hypervisor to inject external aborts into an L2 VM and take
traps of masked external aborts to the hypervisor
- Convert more system register sanitization to the config-driven
implementation
- Fixes to the visibility of EL2 registers, namely making VGICv3
system registers accessible through the VGIC device instead of the
ONE_REG vCPU ioctls
- Various cleanups and minor fixes
LoongArch:
- Add stat information for in-kernel irqchip
- Add tracepoints for CPUCFG and CSR emulation exits
- Enhance in-kernel irqchip emulation
- Various cleanups
RISC-V:
- Enable ring-based dirty memory tracking
- Improve perf kvm stat to report interrupt events
- Delegate illegal instruction trap to VS-mode
- MMU improvements related to upcoming nested virtualization
s390x
- Fixes
x86:
- Add CONFIG_KVM_IOAPIC for x86 to allow disabling support for I/O
APIC, PIC, and PIT emulation at compile time
- Share device posted IRQ code between SVM and VMX and harden it
against bugs and runtime errors
- Use vcpu_idx, not vcpu_id, for GA log tag/metadata, to make lookups
O(1) instead of O(n)
- For MMIO stale data mitigation, track whether or not a vCPU has
access to (host) MMIO based on whether the page tables have MMIO
pfns mapped; using VFIO is prone to false negatives
- Rework the MSR interception code so that the SVM and VMX APIs are
more or less identical
- Recalculate all MSR intercepts from scratch on MSR filter changes,
instead of maintaining shadow bitmaps
- Advertise support for LKGS (Load Kernel GS base), a new instruction
that's loosely related to FRED, but is supported and enumerated
independently
- Fix a user-triggerable WARN that syzkaller found by setting the
vCPU in INIT_RECEIVED state (aka wait-for-SIPI), and then putting
the vCPU into VMX Root Mode (post-VMXON). Trying to detect every
possible path leading to architecturally forbidden states is hard
and even risks breaking userspace (if it goes from valid to valid
state but passes through invalid states), so just wait until
KVM_RUN to detect that the vCPU state isn't allowed
- Add KVM_X86_DISABLE_EXITS_APERFMPERF to allow disabling
interception of APERF/MPERF reads, so that a "properly" configured
VM can access APERF/MPERF. This has many caveats (APERF/MPERF
cannot be zeroed on vCPU creation or saved/restored on suspend and
resume, or preserved over thread migration let alone VM migration)
but can be useful whenever you're interested in letting Linux
guests see the effective physical CPU frequency in /proc/cpuinfo
- Reject KVM_SET_TSC_KHZ for vm file descriptors if vCPUs have been
created, as there's no known use case for changing the default
frequency for other VM types and it goes counter to the very reason
why the ioctl was added to the vm file descriptor. And also, there
would be no way to make it work for confidential VMs with a
"secure" TSC, so kill two birds with one stone
- Dynamically allocation the shadow MMU's hashed page list, and defer
allocating the hashed list until it's actually needed (the TDP MMU
doesn't use the list)
- Extract many of KVM's helpers for accessing architectural local
APIC state to common x86 so that they can be shared by guest-side
code for Secure AVIC
- Various cleanups and fixes
x86 (Intel):
- Preserve the host's DEBUGCTL.FREEZE_IN_SMM when running the guest.
Failure to honor FREEZE_IN_SMM can leak host state into guests
- Explicitly check vmcs12.GUEST_DEBUGCTL on nested VM-Enter to
prevent L1 from running L2 with features that KVM doesn't support,
e.g. BTF
x86 (AMD):
- WARN and reject loading kvm-amd.ko instead of panicking the kernel
if the nested SVM MSRPM offsets tracker can't handle an MSR (which
is pretty much a static condition and therefore should never
happen, but still)
- Fix a variety of flaws and bugs in the AVIC device posted IRQ code
- Inhibit AVIC if a vCPU's ID is too big (relative to what hardware
supports) instead of rejecting vCPU creation
- Extend enable_ipiv module param support to SVM, by simply leaving
IsRunning clear in the vCPU's physical ID table entry
- Disable IPI virtualization, via enable_ipiv, if the CPU is affected
by erratum #1235, to allow (safely) enabling AVIC on such CPUs
- Request GA Log interrupts if and only if the target vCPU is
blocking, i.e. only if KVM needs a notification in order to wake
the vCPU
- Intercept SPEC_CTRL on AMD if the MSR shouldn't exist according to
the vCPU's CPUID model
- Accept any SNP policy that is accepted by the firmware with respect
to SMT and single-socket restrictions. An incompatible policy
doesn't put the kernel at risk in any way, so there's no reason for
KVM to care
- Drop a superfluous WBINVD (on all CPUs!) when destroying a VM and
use WBNOINVD instead of WBINVD when possible for SEV cache
maintenance
- When reclaiming memory from an SEV guest, only do cache flushes on
CPUs that have ever run a vCPU for the guest, i.e. don't flush the
caches for CPUs that can't possibly have cache lines with dirty,
encrypted data
Generic:
- Rework irqbypass to track/match producers and consumers via an
xarray instead of a linked list. Using a linked list leads to
O(n^2) insertion times, which is hugely problematic for use cases
that create large numbers of VMs. Such use cases typically don't
actually use irqbypass, but eliminating the pointless registration
is a future problem to solve as it likely requires new uAPI
- Track irqbypass's "token" as "struct eventfd_ctx *" instead of a
"void *", to avoid making a simple concept unnecessarily difficult
to understand
- Decouple device posted IRQs from VFIO device assignment, as binding
a VM to a VFIO group is not a requirement for enabling device
posted IRQs
- Clean up and document/comment the irqfd assignment code
- Disallow binding multiple irqfds to an eventfd with a priority
waiter, i.e. ensure an eventfd is bound to at most one irqfd
through the entire host, and add a selftest to verify eventfd:irqfd
bindings are globally unique
- Add a tracepoint for KVM_SET_MEMORY_ATTRIBUTES to help debug issues
related to private <=> shared memory conversions
- Drop guest_memfd's .getattr() implementation as the VFS layer will
call generic_fillattr() if inode_operations.getattr is NULL
- Fix issues with dirty ring harvesting where KVM doesn't bound the
processing of entries in any way, which allows userspace to keep
KVM in a tight loop indefinitely
- Kill off kvm_arch_{start,end}_assignment() and x86's associated
tracking, now that KVM no longer uses assigned_device_count as a
heuristic for either irqbypass usage or MDS mitigation
Selftests:
- Fix a comment typo
- Verify KVM is loaded when getting any KVM module param so that
attempting to run a selftest without kvm.ko loaded results in a
SKIP message about KVM not being loaded/enabled (versus some random
parameter not existing)
- Skip tests that hit EACCES when attempting to access a file, and
print a "Root required?" help message. In most cases, the test just
needs to be run with elevated permissions"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (340 commits)
Documentation: KVM: Use unordered list for pre-init VGIC registers
RISC-V: KVM: Avoid re-acquiring memslot in kvm_riscv_gstage_map()
RISC-V: KVM: Use find_vma_intersection() to search for intersecting VMAs
RISC-V: perf/kvm: Add reporting of interrupt events
RISC-V: KVM: Enable ring-based dirty memory tracking
RISC-V: KVM: Fix inclusion of Smnpm in the guest ISA bitmap
RISC-V: KVM: Delegate illegal instruction fault to VS mode
RISC-V: KVM: Pass VMID as parameter to kvm_riscv_hfence_xyz() APIs
RISC-V: KVM: Factor-out g-stage page table management
RISC-V: KVM: Add vmid field to struct kvm_riscv_hfence
RISC-V: KVM: Introduce struct kvm_gstage_mapping
RISC-V: KVM: Factor-out MMU related declarations into separate headers
RISC-V: KVM: Use ncsr_xyz() in kvm_riscv_vcpu_trap_redirect()
RISC-V: KVM: Implement kvm_arch_flush_remote_tlbs_range()
RISC-V: KVM: Don't flush TLB when PTE is unchanged
RISC-V: KVM: Replace KVM_REQ_HFENCE_GVMA_VMID_ALL with KVM_REQ_TLB_FLUSH
RISC-V: KVM: Rename and move kvm_riscv_local_tlb_sanitize()
RISC-V: KVM: Drop the return value of kvm_riscv_vcpu_aia_init()
RISC-V: KVM: Check kvm_riscv_vcpu_alloc_vector_context() return value
KVM: arm64: selftests: Add FEAT_RAS EL2 registers to get-reg-list
...
Pull iommu updates from Will Deacon:
"Core:
- Remove the 'pgsize_bitmap' member from 'struct iommu_ops'
- Convert the x86 drivers over to msi_create_parent_irq_domain()
AMD-Vi:
- Add support for examining driver/device internals via debugfs
- Add support for "HATDis" to disable host translation when it is not
supported
- Add support for limiting the maximum host translation level based
on EFR[HATS]
Apple DART:
- Don't enable as built-in by default when ARCH_APPLE is selected
Arm SMMU:
- Devicetree bindings update for the Qualcomm SMMU in the "Milos" SoC
- Support for Qualcomm SM6115 MDSS parts
- Disable PRR on Qualcomm SM8250 as using these bits causes the
hypervisor to explode
Intel VT-d:
- Reorganize Intel VT-d to be ready for iommupt
- Optimize iotlb_sync_map for non-caching/non-RWBF modes
- Fix missed PASID in dev TLB invalidation in cache_tag_flush_all()
Mediatek:
- Fix build warnings when W=1
Samsung Exynos:
- Add support for reserved memory regions specified by the bootloader
TI OMAP:
- Use syscon_regmap_lookup_by_phandle_args() instead of parsing the
node manually
Misc:
- Cleanups and minor fixes across the board"
* tag 'iommu-updates-v6.17' of git://git.kernel.org/pub/scm/linux/kernel/git/iommu/linux: (48 commits)
iommu/vt-d: Fix UAF on sva unbind with pending IOPFs
iommu/vt-d: Make iotlb_sync_map a static property of dmar_domain
dt-bindings: arm-smmu: Remove sdm845-cheza specific entry
iommu/amd: Fix geometry.aperture_end for V2 tables
iommu/amd: Wrap debugfs ABI testing symbols snippets in literal code blocks
iommu/amd: Add documentation for AMD IOMMU debugfs support
iommu/amd: Add debugfs support to dump IRT Table
iommu/amd: Add debugfs support to dump device table
iommu/amd: Add support for device id user input
iommu/amd: Add debugfs support to dump IOMMU command buffer
iommu/amd: Add debugfs support to dump IOMMU Capability registers
iommu/amd: Add debugfs support to dump IOMMU MMIO registers
iommu/amd: Refactor AMD IOMMU debugfs initial setup
dt-bindings: arm-smmu: document the support on Milos
iommu/exynos: add support for reserved regions
iommu/arm-smmu: disable PRR on SM8250
iommu/arm-smmu-v3: Revert vmaster in the error path
iommu/io-pgtable-arm: Remove unused macro iopte_prot
iommu/arm-smmu-qcom: Add SM6115 MDSS compatible
iommu/qcom: Fix pgsize_bitmap
...
KVM IRQ changes for 6.17
- Rework irqbypass to track/match producers and consumers via an xarray
instead of a linked list. Using a linked list leads to O(n^2) insertion
times, which is hugely problematic for use cases that create large numbers
of VMs. Such use cases typically don't actually use irqbypass, but
eliminating the pointless registration is a future problem to solve as it
likely requires new uAPI.
- Track irqbypass's "token" as "struct eventfd_ctx *" instead of a "void *",
to avoid making a simple concept unnecessarily difficult to understand.
- Add CONFIG_KVM_IOAPIC for x86 to allow disabling support for I/O APIC, PIC,
and PIT emulation at compile time.
- Drop x86's irq_comm.c, and move a pile of IRQ related code into irq.c.
- Fix a variety of flaws and bugs in the AVIC device posted IRQ code.
- Inhibited AVIC if a vCPU's ID is too big (relative to what hardware
supports) instead of rejecting vCPU creation.
- Extend enable_ipiv module param support to SVM, by simply leaving IsRunning
clear in the vCPU's physical ID table entry.
- Disable IPI virtualization, via enable_ipiv, if the CPU is affected by
erratum #1235, to allow (safely) enabling AVIC on such CPUs.
- Dedup x86's device posted IRQ code, as the vast majority of functionality
can be shared verbatime between SVM and VMX.
- Harden the device posted IRQ code against bugs and runtime errors.
- Use vcpu_idx, not vcpu_id, for GA log tag/metadata, to make lookups O(1)
instead of O(n).
- Generate GA Log interrupts if and only if the target vCPU is blocking, i.e.
only if KVM needs a notification in order to wake the vCPU.
- Decouple device posted IRQs from VFIO device assignment, as binding a VM to
a VFIO group is not a requirement for enabling device posted IRQs.
- Clean up and document/comment the irqfd assignment code.
- Disallow binding multiple irqfds to an eventfd with a priority waiter, i.e.
ensure an eventfd is bound to at most one irqfd through the entire host,
and add a selftest to verify eventfd:irqfd bindings are globally unique.
* intel/vt-d:
iommu/vt-d: Fix UAF on sva unbind with pending IOPFs
iommu/vt-d: Make iotlb_sync_map a static property of dmar_domain
iommu/vt-d: Deduplicate cache_tag_flush_all by reusing flush_range
iommu/vt-d: Fix missing PASID in dev TLB flush with cache_tag_flush_all
iommu/vt-d: Split paging_domain_compatible()
iommu/vt-d: Split intel_iommu_enforce_cache_coherency()
iommu/vt-d: Create unique domain ops for each stage
iommu/vt-d: Split intel_iommu_domain_alloc_paging_flags()
iommu/vt-d: Do not wipe out the page table NID when devices detach
iommu/vt-d: Fold domain_exit() into intel_iommu_domain_free()
iommu/vt-d: Lift the __pa to domain_setup_first_level/intel_svm_set_dev_pasid()
iommu/vt-d: Optimize iotlb_sync_map for non-caching/non-RWBF modes
iommu/vt-d: Remove the CONFIG_X86 wrapping from iommu init hook
Commit 17fce9d233 ("iommu/vt-d: Put iopf enablement in domain attach
path") disables IOPF on device by removing the device from its IOMMU's
IOPF queue when the last IOPF-capable domain is detached from the device.
Unfortunately, it did this in a wrong place where there are still pending
IOPFs. As a result, a use-after-free error is potentially triggered and
eventually a kernel panic with a kernel trace similar to the following:
refcount_t: underflow; use-after-free.
WARNING: CPU: 3 PID: 313 at lib/refcount.c:28 refcount_warn_saturate+0xd8/0xe0
Workqueue: iopf_queue/dmar0-iopfq iommu_sva_handle_iopf
Call Trace:
<TASK>
iopf_free_group+0xe/0x20
process_one_work+0x197/0x3d0
worker_thread+0x23a/0x350
? rescuer_thread+0x4a0/0x4a0
kthread+0xf8/0x230
? finish_task_switch.isra.0+0x81/0x260
? kthreads_online_cpu+0x110/0x110
? kthreads_online_cpu+0x110/0x110
ret_from_fork+0x13b/0x170
? kthreads_online_cpu+0x110/0x110
ret_from_fork_asm+0x11/0x20
</TASK>
---[ end trace 0000000000000000 ]---
The intel_pasid_tear_down_entry() function is responsible for blocking
hardware from generating new page faults and flushing all in-flight
ones. Therefore, moving iopf_for_domain_remove() after this function
should resolve this.
Fixes: 17fce9d233 ("iommu/vt-d: Put iopf enablement in domain attach path")
Reported-by: Ethan Milon <ethan.milon@eviden.com>
Closes: https://lore.kernel.org/r/e8b37f3e-8539-40d4-8993-43a1f3ffe5aa@eviden.com
Suggested-by: Ethan Milon <ethan.milon@eviden.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20250723072045.1853328-1-baolu.lu@linux.intel.com
Signed-off-by: Will Deacon <will@kernel.org>
Commit 12724ce3fe ("iommu/vt-d: Optimize iotlb_sync_map for
non-caching/non-RWBF modes") dynamically set iotlb_sync_map. This causes
synchronization issues due to lack of locking on map and attach paths,
racing iommufd userspace operations.
Invalidation changes must precede device attachment to ensure all flushes
complete before hardware walks page tables, preventing coherence issues.
Make domain->iotlb_sync_map static, set once during domain allocation. If
an IOMMU requires iotlb_sync_map but the domain lacks it, attach is
rejected. This won't reduce domain sharing: RWBF and shadowing page table
caching are legacy uses with legacy hardware. Mixed configs (some IOMMUs
in caching mode, others not) are unlikely in real-world scenarios.
Fixes: 12724ce3fe ("iommu/vt-d: Optimize iotlb_sync_map for non-caching/non-RWBF modes")
Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20250721051657.1695788-1-baolu.lu@linux.intel.com
Signed-off-by: Will Deacon <will@kernel.org>
The function cache_tag_flush_all() was originally implemented with
incorrect device TLB invalidation logic that does not handle PASID, in
commit c4d27ffaa8 ("iommu/vt-d: Add cache tag invalidation helpers")
This causes regressions where full address space TLB invalidations occur
with a PASID attached, such as during transparent hugepage unmapping in
SVA configurations or when calling iommu_flush_iotlb_all(). In these
cases, the device receives a TLB invalidation that lacks PASID.
This incorrect logic was later extracted into
cache_tag_flush_devtlb_all(), in commit 3297d047cd ("iommu/vt-d:
Refactor IOTLB and Dev-IOTLB flush for batching")
The fix replaces the call to cache_tag_flush_devtlb_all() with
cache_tag_flush_devtlb_psi(), which properly handles PASID.
Fixes: 4f609dbff5 ("iommu/vt-d: Use cache helpers in arch_invalidate_secondary_tlbs")
Fixes: 4e589a5368 ("iommu/vt-d: Use cache_tag_flush_all() in flush_iotlb_all")
Signed-off-by: Ethan Milon <ethan.milon@eviden.com>
Link: https://lore.kernel.org/r/20250708214821.30967-1-ethan.milon@eviden.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20250714045028.958850-11-baolu.lu@linux.intel.com
Signed-off-by: Will Deacon <will@kernel.org>
Make First/Second stage specific functions that follow the same pattern in
intel_iommu_domain_alloc_first/second_stage() for computing
EOPNOTSUPP. This makes the code easier to understand as if we couldn't
create a domain with the parameters for this IOMMU instance then we
certainly are not compatible with it.
Check superpage support directly against the per-stage cap bits and the
pgsize_bitmap.
Add a note that the force_snooping is read without locking. The locking
needs to cover the compatible check and the add of the device to the list.
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/7-v3-dbbe6f7e7ae3+124ffe-vtd_prep_jgg@nvidia.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20250714045028.958850-10-baolu.lu@linux.intel.com
Signed-off-by: Will Deacon <will@kernel.org>
First Stage and Second Stage have very different ways to deny
no-snoop. The first stage uses the PGSNP bit which is global per-PASID so
enabling requires loading new PASID entries for all the attached devices.
Second stage uses a bit per PTE, so enabling just requires telling future
maps to set the bit.
Since we now have two domain ops we can have two functions that can
directly code their required actions instead of a bunch of logic dancing
around use_first_level.
Combine domain_set_force_snooping() into the new functions since they are
the only caller.
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/6-v3-dbbe6f7e7ae3+124ffe-vtd_prep_jgg@nvidia.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20250714045028.958850-9-baolu.lu@linux.intel.com
Signed-off-by: Will Deacon <will@kernel.org>
Use the domain ops pointer to tell what kind of domain it is instead of
the internal use_first_level indication. This also protects against
wrongly using a SVA/nested/IDENTITY/BLOCKED domain type in places they
should not be.
The only remaining uses of use_first_level outside the paging domain are in
paging_domain_compatible() and intel_iommu_enforce_cache_coherency().
Thus, remove the useless sets of use_first_level in
intel_svm_domain_alloc() and intel_iommu_domain_alloc_nested(). None of
the unique ops for these domain types ever reference it on their call
chains.
Add a WARN_ON() check in domain_context_mapping_one() as it only works
with second stage.
This is preparation for iommupt which will have different ops for each of
the stages.
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/5-v3-dbbe6f7e7ae3+124ffe-vtd_prep_jgg@nvidia.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20250714045028.958850-8-baolu.lu@linux.intel.com
Signed-off-by: Will Deacon <will@kernel.org>
Create stage specific functions that check the stage specific conditions
if each stage can be supported.
Have intel_iommu_domain_alloc_paging_flags() call both stages in sequence
until one does not return EOPNOTSUPP and prefer to use the first stage if
available and suitable for the requested flags.
Move second stage only operations like nested_parent and dirty_tracking
into the second stage function for clarity.
Move initialization of the iommu_domain members into paging_domain_alloc().
Drop initialization of domain->owner as the callers all do it.
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/4-v3-dbbe6f7e7ae3+124ffe-vtd_prep_jgg@nvidia.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20250714045028.958850-7-baolu.lu@linux.intel.com
Signed-off-by: Will Deacon <will@kernel.org>
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>
Split the vcpu_data structure that serves as a handoff from KVM to IOMMU
drivers into vendor specific structures. Overloading a single structure
makes the code hard to read and maintain, is *very* misleading as it
suggests that mixing vendors is actually supported, and bastardizing
Intel's posted interrupt descriptor address when AMD's IOMMU already has
its own structure is quite unnecessary.
Tested-by: Sairaj Kodilkar <sarunkod@amd.com>
Link: https://lore.kernel.org/r/20250611224604.313496-33-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
