DART has an additional global register to control which streams are
isolated. This register is a bit redundant since DART_TCR can already
be used to control isolation and is usually initialized to DART_STREAM_ALL
by the time we get control. Some DARTs (namely the one used for the audio
controller) however have some streams disabled initially. Make sure those
work by initializing DART_STREAMS_ENABLE during reset.
Reported-by: Martin Povišer <povik@protonmail.com>
Signed-off-by: Sven Peter <sven@svenpeter.dev>
Reviewed-by: Hector Martin <marcan@marcan.st>
Link: https://lore.kernel.org/r/20211019162253.45919-1-sven@svenpeter.dev
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The __domain_mapping() always removes the pages in the range from
'iov_pfn' to 'end_pfn', but the 'end_pfn' is always the last pfn
of the range that the caller wants to map.
This would introduce too many duplicated removing and leads the
map operation take too long, for example:
Map iova=0x100000,nr_pages=0x7d61800
iov_pfn: 0x100000, end_pfn: 0x7e617ff
iov_pfn: 0x140000, end_pfn: 0x7e617ff
iov_pfn: 0x180000, end_pfn: 0x7e617ff
iov_pfn: 0x1c0000, end_pfn: 0x7e617ff
iov_pfn: 0x200000, end_pfn: 0x7e617ff
...
it takes about 50ms in total.
We can reduce the cost by recalculate the 'end_pfn' and limit it
to the boundary of the end of this pte page.
Map iova=0x100000,nr_pages=0x7d61800
iov_pfn: 0x100000, end_pfn: 0x13ffff
iov_pfn: 0x140000, end_pfn: 0x17ffff
iov_pfn: 0x180000, end_pfn: 0x1bffff
iov_pfn: 0x1c0000, end_pfn: 0x1fffff
iov_pfn: 0x200000, end_pfn: 0x23ffff
...
it only need 9ms now.
This also removes a meaningless BUG_ON() in __domain_mapping().
Signed-off-by: Longpeng(Mike) <longpeng2@huawei.com>
Tested-by: Liujunjie <liujunjie23@huawei.com>
Link: https://lore.kernel.org/r/20211008000433.1115-1-longpeng2@huawei.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20211014053839.727419-10-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The IOMMU VT-d implementation uses the first level for GPA->HPA translation
by default. Although both the first level and the second level could handle
the DMA translation, they're different in some way. For example, the second
level translation has separate controls for the Access/Dirty page tracking.
With the first level translation, there's no such control. On the other
hand, the second level translation has the page-level control for forcing
snoop, but the first level only has global control with pasid granularity.
This uses the second level for GPA->HPA translation so that we can provide
a consistent hardware interface for use cases like dirty page tracking for
live migration.
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20210926114535.923263-1-baolu.lu@linux.intel.com
Link: https://lore.kernel.org/r/20211014053839.727419-6-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Pull asm-generic fixes from Arnd Bergmann:
"There is one build fix for Arm platforms that ended up impacting most
architectures because of the way the drivers/firmware Kconfig file is
wired up:
The CONFIG_QCOM_SCM dependency have caused a number of randconfig
regressions over time, and some still remain in v5.15-rc4. The fix we
agreed on in the end is to make this symbol selected by any driver
using it, and then building it even for non-Arm platforms with
CONFIG_COMPILE_TEST.
To make this work on all architectures, the drivers/firmware/Kconfig
file needs to be included for all architectures to make the symbol
itself visible.
In a separate discussion, we found that a sound driver patch that is
pending for v5.16 needs the same change to include this Kconfig file,
so the easiest solution seems to have my Kconfig rework included in
v5.15.
Finally, the branch also includes a small unrelated build fix for
NOMMU architectures"
Link: https://lore.kernel.org/all/20210928153508.101208f8@canb.auug.org.au/
Link: https://lore.kernel.org/all/20210928075216.4193128-1-arnd@kernel.org/
Link: https://lore.kernel.org/all/20211007151010.333516-1-arnd@kernel.org/
* tag 'asm-generic-fixes-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic:
asm-generic/io.h: give stub iounmap() on !MMU same prototype as elsewhere
qcom_scm: hide Kconfig symbol
firmware: include drivers/firmware/Kconfig unconditionally
Now that SCM can be a loadable module, we have to add another
dependency to avoid link failures when ipa or adreno-gpu are
built-in:
aarch64-linux-ld: drivers/net/ipa/ipa_main.o: in function `ipa_probe':
ipa_main.c:(.text+0xfc4): undefined reference to `qcom_scm_is_available'
ld.lld: error: undefined symbol: qcom_scm_is_available
>>> referenced by adreno_gpu.c
>>> gpu/drm/msm/adreno/adreno_gpu.o:(adreno_zap_shader_load) in archive drivers/built-in.a
This can happen when CONFIG_ARCH_QCOM is disabled and we don't select
QCOM_MDT_LOADER, but some other module selects QCOM_SCM. Ideally we'd
use a similar dependency here to what we have for QCOM_RPROC_COMMON,
but that causes dependency loops from other things selecting QCOM_SCM.
This appears to be an endless problem, so try something different this
time:
- CONFIG_QCOM_SCM becomes a hidden symbol that nothing 'depends on'
but that is simply selected by all of its users
- All the stubs in include/linux/qcom_scm.h can go away
- arm-smccc.h needs to provide a stub for __arm_smccc_smc() to
allow compile-testing QCOM_SCM on all architectures.
- To avoid a circular dependency chain involving RESET_CONTROLLER
and PINCTRL_SUNXI, drop the 'select RESET_CONTROLLER' statement.
According to my testing this still builds fine, and the QCOM
platform selects this symbol already.
Acked-by: Kalle Valo <kvalo@codeaurora.org>
Acked-by: Alex Elder <elder@linaro.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Replace uses of mem_encrypt_active() with calls to cc_platform_has() with
the CC_ATTR_MEM_ENCRYPT attribute.
Remove the implementation of mem_encrypt_active() across all arches.
For s390, since the default implementation of the cc_platform_has()
matches the s390 implementation of mem_encrypt_active(), cc_platform_has()
does not need to be implemented in s390 (the config option
ARCH_HAS_CC_PLATFORM is not set).
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20210928191009.32551-9-bp@alien8.de
Replace uses of sme_active() with the more generic cc_platform_has()
using CC_ATTR_HOST_MEM_ENCRYPT. If future support is added for other
memory encryption technologies, the use of CC_ATTR_HOST_MEM_ENCRYPT
can be updated, as required.
This also replaces two usages of sev_active() that are really geared
towards detecting if SME is active.
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20210928191009.32551-6-bp@alien8.de
This patch makes iommu/amd call report_iommu_fault() when an I/O page
fault occurs, which has two effects:
1) It allows device drivers to register a callback to be notified of
I/O page faults, via the iommu_set_fault_handler() API.
2) It triggers the io_page_fault tracepoint in report_iommu_fault()
when an I/O page fault occurs.
The latter point is the main aim of this patch, as it allows
rasdaemon-like daemons to be notified of I/O page faults, and to
possibly initiate corrective action in response.
A number of other IOMMU drivers already use report_iommu_fault(), and
I/O page faults on those IOMMUs therefore already trigger this
tracepoint -- but this isn't yet the case for AMD-Vi and Intel DMAR.
The AMD IOMMU specification suggests that the bit in an I/O page fault
event log entry that signals whether an I/O page fault was for a read
request or for a write request is only meaningful when the faulting
access was to a present page, but some testing on a Ryzen 3700X suggests
that this bit encodes the correct value even for I/O page faults to
non-present pages, and therefore, this patch passes the R/W information
up the stack even for I/O page faults to non-present pages.
Signed-off-by: Lennert Buytenhek <buytenh@arista.com>
Link: https://lore.kernel.org/r/YVLyBW97vZLpOaAp@wantstofly.org
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Pass the non-aligned size to __iommu_dma_map when using swiotlb bounce
buffers in iommu_dma_map_page, to account for min_align_mask.
To deal with granule alignment, __iommu_dma_map maps iova_align(size +
iova_off) bytes starting at phys - iova_off. If iommu_dma_map_page
passes aligned size when using swiotlb, then this becomes
iova_align(iova_align(orig_size) + iova_off). Normally iova_off will be
zero when using swiotlb. However, this is not the case for devices that
set min_align_mask. When iova_off is non-zero, __iommu_dma_map ends up
mapping an extra page at the end of the buffer. Beyond just being a
security issue, the extra page is not cleaned up by __iommu_dma_unmap.
This causes problems when the IOVA is reused, due to collisions in the
iommu driver. Just passing the original size is sufficient, since
__iommu_dma_map will take care of granule alignment.
Fixes: 1f221a0d0d ("swiotlb: respect min_align_mask")
Signed-off-by: David Stevens <stevensd@chromium.org>
Link: https://lore.kernel.org/r/20210929023300.335969-8-stevensd@google.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Add an argument to swiotlb_tbl_map_single that specifies the desired
alignment of the allocated buffer. This is used by dma-iommu to ensure
the buffer is aligned to the iova granule size when using swiotlb with
untrusted sub-granule mappings. This addresses an issue where adjacent
slots could be exposed to the untrusted device if IO_TLB_SIZE < iova
granule < PAGE_SIZE.
Signed-off-by: David Stevens <stevensd@chromium.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20210929023300.335969-7-stevensd@google.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Calling the iommu_dma_sync_*_for_cpu functions during unmap can cause
two copies out of the swiotlb buffer. Do the arch sync directly in
__iommu_dma_unmap_swiotlb instead to avoid this. This makes the call to
iommu_dma_sync_sg_for_cpu for untrusted devices in iommu_dma_unmap_sg no
longer necessary, so move that invocation later in the function.
Signed-off-by: David Stevens <stevensd@chromium.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/20210929023300.335969-4-stevensd@google.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
When calling arch_sync_dma, we need to pass it the memory that's
actually being used for dma. When using swiotlb bounce buffers, this is
the bounce buffer. Move arch_sync_dma into the __iommu_dma_map_swiotlb
helper, so it can use the bounce buffer address if necessary.
Now that iommu_dma_map_sg delegates to a function which takes care of
architectural syncing in the untrusted device case, the call to
iommu_dma_sync_sg_for_device can be moved so it only occurs for trusted
devices. Doing the sync for untrusted devices before mapping never
really worked, since it needs to be able to target swiotlb buffers.
This also moves the architectural sync to before the call to
__iommu_dma_map, to guarantee that untrusted devices can't see stale
data they shouldn't see.
Fixes: 82612d66d5 ("iommu: Allow the iommu/dma api to use bounce buffers")
Signed-off-by: David Stevens <stevensd@chromium.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/20210929023300.335969-3-stevensd@google.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The is_swiotlb_buffer function takes the physical address of the swiotlb
buffer, not the physical address of the original buffer. The sglist
contains the physical addresses of the original buffer, so for the
sync_sg functions to work properly when a bounce buffer might have been
used, we need to use iommu_iova_to_phys to look up the physical address.
This is what sync_single does, so call that function on each sglist
segment.
The previous code mostly worked because swiotlb does the transfer on map
and unmap. However, any callers which use DMA_ATTR_SKIP_CPU_SYNC with
sglists or which call sync_sg would not have had anything copied to the
bounce buffer.
Fixes: 82612d66d5 ("iommu: Allow the iommu/dma api to use bounce buffers")
Signed-off-by: David Stevens <stevensd@chromium.org>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20210929023300.335969-2-stevensd@google.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
clang-14 notices that a comparison is never true when
CONFIG_PHYS_ADDR_T_64BIT is disabled:
drivers/iommu/mtk_iommu.c:553:34: error: result of comparison of constant 5368709120 with expression of type 'phys_addr_t' (aka 'unsigned int') is always false [-Werror,-Wtautological-constant-out-of-range-compare]
if (dom->data->enable_4GB && pa >= MTK_IOMMU_4GB_MODE_REMAP_BASE)
~~ ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Add an explicit check for the type of the variable to skip the check
and the warning in that case.
Fixes: b4dad40e4f ("iommu/mediatek: Adjust the PA for the 4GB Mode")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Yong Wu <yong.wu@mediatek.com>
Link: https://lore.kernel.org/r/20210927121857.941160-1-arnd@kernel.org
Signed-off-by: Joerg Roedel <jroedel@suse.de>
sid2groups keeps track of which stream id combinations belong to a
iommu_group to assign those correctly to devices.
When a iommu_group is freed a stale pointer will however remain in
sid2groups. This prevents devices with the same stream id combination
to ever be attached again (see below).
Fix that by creating a shadow copy of the stream id configuration
when a group is allocated for the first time and clear the sid2group
entry when that group is freed.
# echo 1 >/sys/bus/pci/devices/0000\:03\:00.0/remove
pci 0000:03:00.0: Removing from iommu group 1
# echo 1 >/sys/bus/pci/rescan
[...]
pci 0000:03:00.0: BAR 0: assigned [mem 0x6a0000000-0x6a000ffff 64bit pref]
pci 0000:03:00.0: BAR 2: assigned [mem 0x6a0010000-0x6a001ffff 64bit pref]
pci 0000:03:00.0: BAR 6: assigned [mem 0x6c0100000-0x6c01007ff pref]
tg3 0000:03:00.0: Failed to add to iommu group 1: -2
[...]
Fixes: 46d1fb072e ("iommu/dart: Add DART iommu driver")
Reported-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Sven Peter <sven@svenpeter.dev>
Tested-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210924134502.15589-1-sven@svenpeter.dev
Signed-off-by: Joerg Roedel <jroedel@suse.de>
apple_dart_tlb_flush_{all,walk} expect to get a struct apple_dart_domain
but instead get a struct iommu_domain right now. This breaks those two
functions and can lead to kernel panics like the one below.
DART can only invalidate the entire TLB and apple_dart_iotlb_sync will
already flush everything. There's no need to do that again inside those
two functions. Let's just drop them.
pci 0000:03:00.0: Removing from iommu group 1
Unable to handle kernel paging request at virtual address 0000000100000023
[...]
Call trace:
_raw_spin_lock_irqsave+0x54/0xbc
apple_dart_hw_stream_command.constprop.0+0x2c/0x130
apple_dart_tlb_flush_all+0x48/0x90
free_io_pgtable_ops+0x40/0x70
apple_dart_domain_free+0x2c/0x44
iommu_group_release+0x68/0xac
kobject_cleanup+0x4c/0x1fc
kobject_cleanup+0x14c/0x1fc
kobject_put+0x64/0x84
iommu_group_remove_device+0x110/0x180
iommu_release_device+0x50/0xa0
[...]
Fixes: 46d1fb072e ("iommu/dart: Add DART iommu driver")
Reported-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Sven Peter <sven@svenpeter.dev>
Acked-by: Marc Zyngier <maz@kernel.org>
Tested-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20210921153934.35647-1-sven@svenpeter.dev
Signed-off-by: Joerg Roedel <jroedel@suse.de>
In preparation for FORTIFY_SOURCE performing compile-time and run-time
field bounds checking for memcpy(), memmove(), and memset(), avoid
intentionally writing across neighboring fields.
Use struct_group() in struct ivhd_entry around members ext and hidh, so
they can be referenced together. This will allow memcpy() and sizeof()
to more easily reason about sizes, improve readability, and avoid future
warnings about writing beyond the end of ext.
"pahole" shows no size nor member offset changes to struct ivhd_entry.
"objdump -d" shows no object code changes.
Cc: Will Deacon <will@kernel.org>
Cc: iommu@lists.linux-foundation.org
Acked-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Kees Cook <keescook@chromium.org>
Pull virtio updates from Michael Tsirkin:
- vduse driver ("vDPA Device in Userspace") supporting emulated virtio
block devices
- virtio-vsock support for end of record with SEQPACKET
- vdpa: mac and mq support for ifcvf and mlx5
- vdpa: management netlink for ifcvf
- virtio-i2c, gpio dt bindings
- misc fixes and cleanups
* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (39 commits)
Documentation: Add documentation for VDUSE
vduse: Introduce VDUSE - vDPA Device in Userspace
vduse: Implement an MMU-based software IOTLB
vdpa: Support transferring virtual addressing during DMA mapping
vdpa: factor out vhost_vdpa_pa_map() and vhost_vdpa_pa_unmap()
vdpa: Add an opaque pointer for vdpa_config_ops.dma_map()
vhost-iotlb: Add an opaque pointer for vhost IOTLB
vhost-vdpa: Handle the failure of vdpa_reset()
vdpa: Add reset callback in vdpa_config_ops
vdpa: Fix some coding style issues
file: Export receive_fd() to modules
eventfd: Export eventfd_wake_count to modules
iova: Export alloc_iova_fast() and free_iova_fast()
virtio-blk: remove unneeded "likely" statements
virtio-balloon: Use virtio_find_vqs() helper
vdpa: Make use of PFN_PHYS/PFN_UP/PFN_DOWN helper macro
vsock_test: update message bounds test for MSG_EOR
af_vsock: rename variables in receive loop
virtio/vsock: support MSG_EOR bit processing
vhost/vsock: support MSG_EOR bit processing
...
Pull iommu fixes from Joerg Roedel:
- Intel VT-d:
- PASID leakage in intel_svm_unbind_mm()
- Deadlock in intel_svm_drain_prq()
- AMD IOMMU: Fixes for an unhandled page-fault bug when AVIC is used
for a KVM guest.
- Make CONFIG_IOMMU_DEFAULT_DMA_LAZY architecture instead of IOMMU
driver dependent
* tag 'iommu-fixes-v5.15-rc0' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
iommu: Clarify default domain Kconfig
iommu/vt-d: Fix a deadlock in intel_svm_drain_prq()
iommu/vt-d: Fix PASID leak in intel_svm_unbind_mm()
iommu/amd: Remove iommu_init_ga()
iommu/amd: Relocate GAMSup check to early_enable_iommus
Although strictly it is the AMD and Intel drivers which have an existing
expectation of lazy behaviour by default, it ends up being rather
unintuitive to describe this literally in Kconfig. Express it instead as
an architecture dependency, to clarify that it is a valid config-time
decision. The end result is the same since virtio-iommu doesn't support
lazy mode and thus falls back to strict at runtime regardless.
The per-architecture disparity is a matter of historical expectations:
the AMD and Intel drivers have been lazy by default since 2008, and
changing that gets noticed by people asking where their I/O throughput
has gone. Conversely, Arm-based systems with their wider assortment of
IOMMU drivers mostly only support strict mode anyway; only the Arm SMMU
drivers have later grown support for passthrough and lazy mode, for
users who wanted to explicitly trade off isolation for performance.
These days, reducing the default level of isolation in a way which may
go unnoticed by users who expect otherwise hardly seems worth risking
for the sake of one line of Kconfig, so here's where we are.
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/69a0c6f17b000b54b8333ee42b3124c1d5a869e2.1631105737.git.robin.murphy@arm.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
pasid_mutex and dev->iommu->param->lock are held while unbinding mm is
flushing IO page fault workqueue and waiting for all page fault works to
finish. But an in-flight page fault work also need to hold the two locks
while unbinding mm are holding them and waiting for the work to finish.
This may cause an ABBA deadlock issue as shown below:
idxd 0000:00:0a.0: unbind PASID 2
======================================================
WARNING: possible circular locking dependency detected
5.14.0-rc7+ #549 Not tainted [ 186.615245] ----------
dsa_test/898 is trying to acquire lock:
ffff888100d854e8 (¶m->lock){+.+.}-{3:3}, at:
iopf_queue_flush_dev+0x29/0x60
but task is already holding lock:
ffffffff82b2f7c8 (pasid_mutex){+.+.}-{3:3}, at:
intel_svm_unbind+0x34/0x1e0
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #2 (pasid_mutex){+.+.}-{3:3}:
__mutex_lock+0x75/0x730
mutex_lock_nested+0x1b/0x20
intel_svm_page_response+0x8e/0x260
iommu_page_response+0x122/0x200
iopf_handle_group+0x1c2/0x240
process_one_work+0x2a5/0x5a0
worker_thread+0x55/0x400
kthread+0x13b/0x160
ret_from_fork+0x22/0x30
-> #1 (¶m->fault_param->lock){+.+.}-{3:3}:
__mutex_lock+0x75/0x730
mutex_lock_nested+0x1b/0x20
iommu_report_device_fault+0xc2/0x170
prq_event_thread+0x28a/0x580
irq_thread_fn+0x28/0x60
irq_thread+0xcf/0x180
kthread+0x13b/0x160
ret_from_fork+0x22/0x30
-> #0 (¶m->lock){+.+.}-{3:3}:
__lock_acquire+0x1134/0x1d60
lock_acquire+0xc6/0x2e0
__mutex_lock+0x75/0x730
mutex_lock_nested+0x1b/0x20
iopf_queue_flush_dev+0x29/0x60
intel_svm_drain_prq+0x127/0x210
intel_svm_unbind+0xc5/0x1e0
iommu_sva_unbind_device+0x62/0x80
idxd_cdev_release+0x15a/0x200 [idxd]
__fput+0x9c/0x250
____fput+0xe/0x10
task_work_run+0x64/0xa0
exit_to_user_mode_prepare+0x227/0x230
syscall_exit_to_user_mode+0x2c/0x60
do_syscall_64+0x48/0x90
entry_SYSCALL_64_after_hwframe+0x44/0xae
other info that might help us debug this:
Chain exists of:
¶m->lock --> ¶m->fault_param->lock --> pasid_mutex
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(pasid_mutex);
lock(¶m->fault_param->lock);
lock(pasid_mutex);
lock(¶m->lock);
*** DEADLOCK ***
2 locks held by dsa_test/898:
#0: ffff888100cc1cc0 (&group->mutex){+.+.}-{3:3}, at:
iommu_sva_unbind_device+0x53/0x80
#1: ffffffff82b2f7c8 (pasid_mutex){+.+.}-{3:3}, at:
intel_svm_unbind+0x34/0x1e0
stack backtrace:
CPU: 2 PID: 898 Comm: dsa_test Not tainted 5.14.0-rc7+ #549
Hardware name: Intel Corporation Kabylake Client platform/KBL S
DDR4 UD IMM CRB, BIOS KBLSE2R1.R00.X050.P01.1608011715 08/01/2016
Call Trace:
dump_stack_lvl+0x5b/0x74
dump_stack+0x10/0x12
print_circular_bug.cold+0x13d/0x142
check_noncircular+0xf1/0x110
__lock_acquire+0x1134/0x1d60
lock_acquire+0xc6/0x2e0
? iopf_queue_flush_dev+0x29/0x60
? pci_mmcfg_read+0xde/0x240
__mutex_lock+0x75/0x730
? iopf_queue_flush_dev+0x29/0x60
? pci_mmcfg_read+0xfd/0x240
? iopf_queue_flush_dev+0x29/0x60
mutex_lock_nested+0x1b/0x20
iopf_queue_flush_dev+0x29/0x60
intel_svm_drain_prq+0x127/0x210
? intel_pasid_tear_down_entry+0x22e/0x240
intel_svm_unbind+0xc5/0x1e0
iommu_sva_unbind_device+0x62/0x80
idxd_cdev_release+0x15a/0x200
pasid_mutex protects pasid and svm data mapping data. It's unnecessary
to hold pasid_mutex while flushing the workqueue. To fix the deadlock
issue, unlock pasid_pasid during flushing the workqueue to allow the works
to be handled.
Fixes: d5b9e4bfe0 ("iommu/vt-d: Report prq to io-pgfault framework")
Reported-and-tested-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Link: https://lore.kernel.org/r/20210826215918.4073446-1-fenghua.yu@intel.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20210828070622.2437559-3-baolu.lu@linux.intel.com
[joro: Removed timing information from kernel log messages]
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Currently, iommu_init_ga() checks and disables IOMMU VAPIC support
(i.e. AMD AVIC support in IOMMU) when GAMSup feature bit is not set.
However it forgets to clear IRQ_POSTING_CAP from the previously set
amd_iommu_irq_ops.capability.
This triggers an invalid page fault bug during guest VM warm reboot
if AVIC is enabled since the irq_remapping_cap(IRQ_POSTING_CAP) is
incorrectly set, and crash the system with the following kernel trace.
BUG: unable to handle page fault for address: 0000000000400dd8
RIP: 0010:amd_iommu_deactivate_guest_mode+0x19/0xbc
Call Trace:
svm_set_pi_irte_mode+0x8a/0xc0 [kvm_amd]
? kvm_make_all_cpus_request_except+0x50/0x70 [kvm]
kvm_request_apicv_update+0x10c/0x150 [kvm]
svm_toggle_avic_for_irq_window+0x52/0x90 [kvm_amd]
svm_enable_irq_window+0x26/0xa0 [kvm_amd]
vcpu_enter_guest+0xbbe/0x1560 [kvm]
? avic_vcpu_load+0xd5/0x120 [kvm_amd]
? kvm_arch_vcpu_load+0x76/0x240 [kvm]
? svm_get_segment_base+0xa/0x10 [kvm_amd]
kvm_arch_vcpu_ioctl_run+0x103/0x590 [kvm]
kvm_vcpu_ioctl+0x22a/0x5d0 [kvm]
__x64_sys_ioctl+0x84/0xc0
do_syscall_64+0x33/0x40
entry_SYSCALL_64_after_hwframe+0x44/0xae
Fixes by moving the initializing of AMD IOMMU interrupt remapping mode
(amd_iommu_guest_ir) earlier before setting up the
amd_iommu_irq_ops.capability with appropriate IRQ_POSTING_CAP flag.
[joro: Squashed the two patches and limited
check_features_on_all_iommus() to CONFIG_IRQ_REMAP
to fix a compile warning.]
Signed-off-by: Wei Huang <wei.huang2@amd.com>
Co-developed-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Link: https://lore.kernel.org/r/20210820202957.187572-2-suravee.suthikulpanit@amd.com
Link: https://lore.kernel.org/r/20210820202957.187572-3-suravee.suthikulpanit@amd.com
Fixes: 8bda0cfbdc ("iommu/amd: Detect and initialize guest vAPIC log")
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Pull iommu updates from Joerg Roedel:
- New DART IOMMU driver for Apple Silicon M1 chips
- Optimizations for iommu_[map/unmap] performance
- Selective TLB flush support for the AMD IOMMU driver to make it more
efficient on emulated IOMMUs
- Rework IOVA setup and default domain type setting to move more code
out of IOMMU drivers and to support runtime switching between certain
types of default domains
- VT-d Updates from Lu Baolu:
- Update the virtual command related registers
- Enable Intel IOMMU scalable mode by default
- Preset A/D bits for user space DMA usage
- Allow devices to have more than 32 outstanding PRs
- Various cleanups
- ARM SMMU Updates from Will Deacon:
SMMUv3:
- Minor optimisation to avoid zeroing struct members on CMD submission
- Increased use of batched commands to reduce submission latency
- Refactoring in preparation for ECMDQ support
SMMUv2:
- Fix races when probing devices with identical StreamIDs
- Optimise walk cache flushing for Qualcomm implementations
- Allow deep sleep states for some Qualcomm SoCs with shared clocks
- Various smaller optimizations, cleanups, and fixes
* tag 'iommu-updates-v5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (85 commits)
iommu/io-pgtable: Abstract iommu_iotlb_gather access
iommu/arm-smmu: Fix missing unlock on error in arm_smmu_device_group()
iommu/vt-d: Add present bit check in pasid entry setup helpers
iommu/vt-d: Use pasid_pte_is_present() helper function
iommu/vt-d: Drop the kernel doc annotation
iommu/vt-d: Allow devices to have more than 32 outstanding PRs
iommu/vt-d: Preset A/D bits for user space DMA usage
iommu/vt-d: Enable Intel IOMMU scalable mode by default
iommu/vt-d: Refactor Kconfig a bit
iommu/vt-d: Remove unnecessary oom message
iommu/vt-d: Update the virtual command related registers
iommu: Allow enabling non-strict mode dynamically
iommu: Merge strictness and domain type configs
iommu: Only log strictness for DMA domains
iommu: Expose DMA domain strictness via sysfs
iommu: Express DMA strictness via the domain type
iommu/vt-d: Prepare for multiple DMA domain types
iommu/arm-smmu: Prepare for multiple DMA domain types
iommu/amd: Prepare for multiple DMA domain types
iommu: Introduce explicit type for non-strict DMA domains
...
