Hook up IOMMU_OF_DECLARE() support in case CONFIG_IOMMU_DMA
is enabled. The only current supported case for 32-bit ARM
is disabled, however for 64-bit ARM usage of OF is required.
Signed-off-by: Magnus Damm <damm+renesas@opensource.se>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Add support for up to 8 contexts. Each context is mapped to one
domain. One domain is assigned one or more slave devices. Contexts
are allocated dynamically and slave devices are grouped together
based on which IPMMU device they are connected to. This makes slave
devices tied to the same IPMMU device share the same IOVA space.
Signed-off-by: Magnus Damm <damm+renesas@opensource.se>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Add root device handling to the IPMMU driver by allowing certain
DT compat strings to enable has_cache_leaf_nodes that in turn will
support both root devices with interrupts and leaf devices that
face the actual IPMMU consumer devices.
Signed-off-by: Magnus Damm <damm+renesas@opensource.se>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Introduce struct ipmmu_features to track various hardware
and software implementation changes inside the driver for
different kinds of IPMMU hardware. Add use_ns_alias_offset
as a first example of a feature to control if the secure
register bank offset should be used or not.
Signed-off-by: Magnus Damm <damm+renesas@opensource.se>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
The remaining difference between the ARM-specific and iommu-dma ops is
in the {add,remove}_device implementations, but even those have some
overlap and duplication. By stubbing out the few arm_iommu_*() calls,
we can get rid of the rest of the inline #ifdeffery to both simplify the
code and improve build coverage.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Now that the IPMMU instance pointer is the only thing remaining in the
private data structure, we no longer need the extra level of indirection
and can simply stash that directlty in the fwspec.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
We go through quite the merry dance in order to find masters behind the
same IPMMU instance, so that we can ensure they are grouped together.
None of which is really necessary, since the master's private data
already points to the particular IPMMU it is associated with, and that
IPMMU instance data is the perfect place to keep track of a per-instance
group directly.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
We have two implementations for ipmmu_ops->alloc depending on
CONFIG_IOMMU_DMA, the difference being whether they accept the
IOMMU_DOMAIN_DMA type or not. However, iommu_dma_get_cookie() is
guaranteed to return an error when !CONFIG_IOMMU_DMA, so if
ipmmu_domain_alloc_dma() was actually checking and handling the return
value correctly, it would behave the same as ipmmu_domain_alloc()
anyway.
Similarly for freeing; iommu_put_dma_cookie() is robust by design.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
In case of error, the function iommu_group_get() returns NULL pointer
not ERR_PTR(). The IS_ERR() test in the return value check should be
replaced with NULL test.
Fixes: 3ae4729202 ("iommu/ipmmu-vmsa: Add new IOMMU_DOMAIN_DMA ops")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
The function only sends the flush command to the IOMMU(s),
but does not wait for its completion when it returns. Fix
that.
Fixes: 601367d76b ('x86/amd-iommu: Remove iommu_flush_domain function')
Cc: stable@vger.kernel.org # >= 2.6.33
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Since IOVA allocation failure is not unusual case we need to flush
CPUs' rcache in hope we will succeed in next round.
However, it is useful to decide whether we need rcache flush step because
of two reasons:
- Not scalability. On large system with ~100 CPUs iterating and flushing
rcache for each CPU becomes serious bottleneck so we may want to defer it.
- free_cpu_cached_iovas() does not care about max PFN we are interested in.
Thus we may flush our rcaches and still get no new IOVA like in the
commonly used scenario:
if (dma_limit > DMA_BIT_MASK(32) && dev_is_pci(dev))
iova = alloc_iova_fast(iovad, iova_len, DMA_BIT_MASK(32) >> shift);
if (!iova)
iova = alloc_iova_fast(iovad, iova_len, dma_limit >> shift);
1. First alloc_iova_fast() call is limited to DMA_BIT_MASK(32) to get
PCI devices a SAC address
2. alloc_iova() fails due to full 32-bit space
3. rcaches contain PFNs out of 32-bit space so free_cpu_cached_iovas()
throws entries away for nothing and alloc_iova() fails again
4. Next alloc_iova_fast() call cannot take advantage of rcache since we
have just defeated caches. In this case we pick the slowest option
to proceed.
This patch reworks flushed_rcache local flag to be additional function
argument instead and control rcache flush step. Also, it updates all users
to do the flush as the last chance.
Signed-off-by: Tomasz Nowicki <Tomasz.Nowicki@caviumnetworks.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Tested-by: Nate Watterson <nwatters@codeaurora.org>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Exynos SYSMMU registers standard platform device with sysmmu_of_match
table, what means that this table is accessed every time a new platform
device is registered in a system. This might happen also after the boot,
so the table must not be attributed as initconst to avoid potential kernel
oops caused by access to freed memory.
Fixes: 6b21a5db36 ("iommu/exynos: Support for device tree")
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reviewed-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
When SME memory encryption is active it will rely on SWIOTLB to handle
DMA for devices that cannot support the addressing requirements of
having the encryption mask set in the physical address. The IOMMU
currently disables SWIOTLB if it is not running in passthrough mode.
This is not desired as non-PCI devices attempting DMA may fail. Update
the code to check if SME is active and not disable SWIOTLB.
Fixes: 2543a786aa ("iommu/amd: Allow the AMD IOMMU to work with memory encryption")
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Make use of the new alignment capability of
alloc_irq_index() to enforce IRQ index alignment
for MSI.
Reported-by: Thomas Gleixner <tglx@linutronix.de>
Fixes: 2b32450634 ('iommu/amd: Add routines to manage irq remapping tables')
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
For multi-MSI IRQ ranges the IRQ index needs to be aligned
to the power-of-two of the requested IRQ count. Extend the
alloc_irq_index() function to allow such an allocation.
Reported-by: Thomas Gleixner <tglx@linutronix.de>
Fixes: 2b32450634 ('iommu/amd: Add routines to manage irq remapping tables')
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Variable did_old is unsigned so checking whether it is
greater or equal to zero is not necessary.
Signed-off-by: Christos Gkekas <chris.gekas@gmail.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The notifier function will take the dmar_global_lock too, so
lockdep complains about inverse locking order when the
notifier is registered under the dmar_global_lock.
Reported-by: Jan Kiszka <jan.kiszka@siemens.com>
Fixes: 59ce0515cd ('iommu/vt-d: Update DRHD/RMRR/ATSR device scope caches when PCI hotplug happens')
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Now that the core API issues its own post-unmap TLB sync call, push that
operation out from the io-pgtable-arm-v7s internals into the users. For
now, we leave the invalidation implicit in the unmap operation, since
none of the current users would benefit much from any change to that.
Note that the conversion of msm_iommu is implicit, since that apparently
has no specific TLB sync operation anyway.
CC: Yong Wu <yong.wu@mediatek.com>
CC: Rob Clark <robdclark@gmail.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Now that the core API issues its own post-unmap TLB sync call, push that
operation out from the io-pgtable-arm internals into the users. For now,
we leave the invalidation implicit in the unmap operation, since none of
the current users would benefit much from any change to that.
CC: Magnus Damm <damm+renesas@opensource.se>
CC: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Anchor nodes are not reserved IOVAs in the way that copy_reserved_iova()
cares about - while the failure from reserve_iova() is benign since the
target domain will already have its own anchor, we still don't want to
be triggering spurious warnings.
Reported-by: kernel test robot <fengguang.wu@intel.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Fixes: bb68b2fbfb ('iommu/iova: Add rbtree anchor node')
Signed-off-by: Joerg Roedel <jroedel@suse.de>
When devices with different DMA masks are using the same domain, or for
PCI devices where we usually try a speculative 32-bit allocation first,
there is a fair possibility that the top PFN of the rcache stack at any
given time may be unsuitable for the lower limit, prompting a fallback
to allocating anew from the rbtree. Consequently, we may end up
artifically increasing pressure on the 32-bit IOVA space as unused IOVAs
accumulate lower down in the rcache stacks, while callers with 32-bit
masks also impose unnecessary rbtree overhead.
In such cases, let's try a bit harder to satisfy the allocation locally
first - scanning the whole stack should still be relatively inexpensive.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
When popping a pfn from an rcache, we are currently checking it directly
against limit_pfn for viability. Since this represents iova->pfn_lo, it
is technically possible for the corresponding iova->pfn_hi to be greater
than limit_pfn. Although we generally get away with it in practice since
limit_pfn is typically a power-of-two boundary and the IOVAs are
size-aligned, it's pretty trivial to make the iova_rcache_get() path
take the allocation size into account for complete safety.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
All put_iova_domain() should have to worry about is freeing memory - by
that point the domain must no longer be live, so the act of cleaning up
doesn't need to be concurrency-safe or maintain the rbtree in a
self-consistent state. There's no need to waste time with locking or
emptying the rcache magazines, and we can just use the postorder
traversal helper to clear out the remaining rbtree entries in-place.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The logic of __get_cached_rbnode() is a little obtuse, but then
__get_prev_node_of_cached_rbnode_or_last_node_and_update_limit_pfn()
wouldn't exactly roll off the tongue...
Now that we have the invariant that there is always a valid node to
start searching downwards from, everything gets a bit easier to follow
if we simplify that function to do what it says on the tin and return
the cached node (or anchor node as appropriate) directly. In turn, we
can then deduplicate the rb_prev() and limit_pfn logic into the main
loop itself, further reduce the amount of code under the lock, and
generally make the inner workings a bit less subtle.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Add a permanent dummy IOVA reservation to the rbtree, such that we can
always access the top of the address space instantly. The immediate
benefit is that we remove the overhead of the rb_last() traversal when
not using the cached node, but it also paves the way for further
simplifications.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Now that the cached node optimisation can apply to all allocations, the
couple of users which were playing tricks with dma_32bit_pfn in order to
benefit from it can stop doing so. Conversely, there is also no need for
all the other users to explicitly calculate a 'real' 32-bit PFN, when
init_iova_domain() can happily do that itself from the page granularity.
CC: Thierry Reding <thierry.reding@gmail.com>
CC: Jonathan Hunter <jonathanh@nvidia.com>
CC: David Airlie <airlied@linux.ie>
CC: Sudeep Dutt <sudeep.dutt@intel.com>
CC: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Tested-by: Zhen Lei <thunder.leizhen@huawei.com>
Tested-by: Nate Watterson <nwatters@codeaurora.org>
[rm: use iova_shift(), rewrote commit message]
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The cached node mechanism provides a significant performance benefit for
allocations using a 32-bit DMA mask, but in the case of non-PCI devices
or where the 32-bit space is full, the loss of this benefit can be
significant - on large systems there can be many thousands of entries in
the tree, such that walking all the way down to find free space every
time becomes increasingly awful.
Maintain a similar cached node for the whole IOVA space as a superset of
the 32-bit space so that performance can remain much more consistent.
Inspired by work by Zhen Lei <thunder.leizhen@huawei.com>.
Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Tested-by: Zhen Lei <thunder.leizhen@huawei.com>
Tested-by: Nate Watterson <nwatters@codeaurora.org>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The mask for calculating the padding size doesn't change, so there's no
need to recalculate it every loop iteration. Furthermore, Once we've
done that, it becomes clear that we don't actually need to calculate a
padding size at all - by flipping the arithmetic around, we can just
combine the upper limit, size, and mask directly to check against the
lower limit.
For an arm64 build, this alone knocks 20% off the object code size of
the entire alloc_iova() function!
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Tested-by: Zhen Lei <thunder.leizhen@huawei.com>
Tested-by: Nate Watterson <nwatters@codeaurora.org>
[rm: simplified more of the arithmetic, rewrote commit message]
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Checking the IOVA bounds separately before deciding which direction to
continue the search (if necessary) results in redundantly comparing both
pfns twice each. GCC can already determine that the final comparison op
is redundant and optimise it down to 3 in total, but we can go one
further with a little tweak of the ordering (which makes the intent of
the code that much cleaner as a bonus).
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Tested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Tested-by: Zhen Lei <thunder.leizhen@huawei.com>
Tested-by: Nate Watterson <nwatters@codeaurora.org>
[rm: rewrote commit message to clarify]
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
pr_err() messages should end with a new-line to avoid other messages
being concatenated. So replace '/n' with '\n'.
Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
Fixes: 45a01c4293 ('iommu/amd: Add function copy_dev_tables()')
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Fix the commit 81b3c25218 ("iommu/io-pgtable: Introduce explicit
coherency"). If there is no IO_PGTABLE_QUIRK_NO_DMA, we should call
dma_sync_single_for_device for cache synchronization.
Signed-off-by: Yong Wu <yong.wu@mediatek.com>
Fixes: 81b3c25218 ('iommu/io-pgtable: Introduce explicit coherency')
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
of_pci_iommu_init() tries to be clever and stop its alias walk at the
device represented by master_np, in case of weird PCI topologies where
the bridge to the IOMMU and the rest of the system is not at the root.
It turns out this is a bit short-sighted, since there are plenty of
other callers of pci_for_each_dma_alias() which would also need the same
behaviour in that situation, and the only platform so far with such a
topology (Cavium ThunderX2) already solves it more generally via a PCI
quirk. As this check is effectively redundant, and returning a boolean
value as an int is a bit broken anyway, let's just get rid of it.
Reported-by: Jean-Philippe Brucker <jean-philippe.brucker@arm.com>
Fixes: d87beb7492 ("iommu/of: Handle PCI aliases properly")
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Tested-by: Jean-Philippe Brucker <jean-philippe.brucker@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
If NO_DMA=y:
warning: (IPMMU_VMSA && ARM_SMMU && ARM_SMMU_V3 && QCOM_IOMMU) selects IOMMU_IO_PGTABLE_LPAE which has unmet direct dependencies (IOMMU_SUPPORT && HAS_DMA && (ARM || ARM64 || COMPILE_TEST && !GENERIC_ATOMIC64))
and
drivers/iommu/io-pgtable-arm.o: In function `__arm_lpae_sync_pte':
io-pgtable-arm.c:(.text+0x206): undefined reference to `bad_dma_ops'
drivers/iommu/io-pgtable-arm.o: In function `__arm_lpae_free_pages':
io-pgtable-arm.c:(.text+0x6a6): undefined reference to `bad_dma_ops'
drivers/iommu/io-pgtable-arm.o: In function `__arm_lpae_alloc_pages':
io-pgtable-arm.c:(.text+0x812): undefined reference to `bad_dma_ops'
io-pgtable-arm.c:(.text+0x81c): undefined reference to `bad_dma_ops'
io-pgtable-arm.c:(.text+0x862): undefined reference to `bad_dma_ops'
drivers/iommu/io-pgtable-arm.o: In function `arm_lpae_run_tests':
io-pgtable-arm.c:(.init.text+0x86): undefined reference to `alloc_io_pgtable_ops'
io-pgtable-arm.c:(.init.text+0x47c): undefined reference to `free_io_pgtable_ops'
drivers/iommu/qcom_iommu.o: In function `qcom_iommu_init_domain':
qcom_iommu.c:(.text+0x1ce): undefined reference to `alloc_io_pgtable_ops'
drivers/iommu/qcom_iommu.o: In function `qcom_iommu_domain_free':
qcom_iommu.c:(.text+0x754): undefined reference to `free_io_pgtable_ops'
QCOM_IOMMU selects IOMMU_IO_PGTABLE_LPAE, which bypasses its dependency
on HAS_DMA. Make QCOM_IOMMU depend on HAS_DMA to fix this.
Fixes: 0ae349a0f3 ("iommu/qcom: Add qcom_iommu")
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
add_device is a bit more suitable for establishing runtime PM links than
the xlate callback. This change also makes it possible to implement proper
cleanup - in remove_device callback.
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Building with gcc-4.6 results in this warning due to
dmar_table_print_dmar_entry being inlined as in newer compiler versions:
WARNING: vmlinux.o(.text+0x5c8bee): Section mismatch in reference from the function dmar_walk_remapping_entries() to the function .init.text:dmar_table_print_dmar_entry()
The function dmar_walk_remapping_entries() references
the function __init dmar_table_print_dmar_entry().
This is often because dmar_walk_remapping_entries lacks a __init
annotation or the annotation of dmar_table_print_dmar_entry is wrong.
This removes the __init annotation to avoid the warning. On compilers
that don't show the warning today, this should have no impact since the
function gets inlined anyway.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
parisc:allmodconfig, xtensa:allmodconfig, and possibly others generate
the following Kconfig warning.
warning: (IPMMU_VMSA && ARM_SMMU && ARM_SMMU_V3 && QCOM_IOMMU) selects
IOMMU_IO_PGTABLE_LPAE which has unmet direct dependencies (IOMMU_SUPPORT &&
HAS_DMA && (ARM || ARM64 || COMPILE_TEST && !GENERIC_ATOMIC64))
IOMMU_IO_PGTABLE_LPAE depends on (COMPILE_TEST && !GENERIC_ATOMIC64),
so any configuration option selecting it needs to have the same dependencies.
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
A client user instantiates and attaches to an iommu_domain to
program the OMAP IOMMU associated with the domain. The iommus
programmed by a client user are bound with the iommu_domain
through the user's device archdata. The OMAP IOMMU driver
currently supports only one IOMMU per IOMMU domain per user.
The OMAP IOMMU driver has been enhanced to support allowing
multiple IOMMUs to be programmed by a single client user. This
support is being added mainly to handle the DSP subsystems on
the DRA7xx SoCs, which have two MMUs within the same subsystem.
These MMUs provide translations for a processor core port and
an internal EDMA port. This support allows both the MMUs to
be programmed together, but with each one retaining it's own
internal state objects. The internal EDMA block is managed by
the software running on the DSPs, and this design provides
on-par functionality with previous generation OMAP DSPs where
the EDMA and the DSP core shared the same MMU.
The multiple iommus are expected to be provided through a
sentinel terminated array of omap_iommu_arch_data objects
through the client user's device archdata. The OMAP driver
core is enhanced to loop through the array of attached
iommus and program them for all common operations. The
sentinel-terminated logic is used so as to not change the
omap_iommu_arch_data structure.
NOTE:
1. The IOMMU group and IOMMU core registration is done only for
the DSP processor core MMU even though both MMUs are represented
by their own platform device and are probed individually. The
IOMMU device linking uses this registered MMU device. The struct
iommu_device for the second MMU is not used even though memory
for it is allocated.
2. The OMAP IOMMU debugfs code still continues to operate on
individual IOMMU objects.
Signed-off-by: Suman Anna <s-anna@ti.com>
[t-kristo@ti.com: ported support to 4.13 based kernel]
Signed-off-by: Tero Kristo <t-kristo@ti.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The OMAP IOMMU driver allows only a single device (eg: a rproc
device) to be attached per domain. The current attach detection
logic relies on a check for an attached iommu for the respective
client device. Change this logic to use the client device pointer
instead in preparation for supporting multiple iommu devices to be
bound to a single iommu domain, and thereby to a client device.
Signed-off-by: Suman Anna <s-anna@ti.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Slightly more changes than usual this time:
- KDump Kernel IOMMU take-over code for AMD IOMMU. The code now
tries to preserve the mappings of the kernel so that master
aborts for devices are avoided. Master aborts cause some
devices to fail in the kdump kernel, so this code makes the
dump more likely to succeed when AMD IOMMU is enabled.
- Common flush queue implementation for IOVA code users. The
code is still optional, but AMD and Intel IOMMU drivers had
their own implementation which is now unified.
- Finish support for iommu-groups. All drivers implement this
feature now so that IOMMU core code can rely on it.
- Finish support for 'struct iommu_device' in iommu drivers. All
drivers now use the interface.
- New functions in the IOMMU-API for explicit IO/TLB flushing.
This will help to reduce the number of IO/TLB flushes when
IOMMU drivers support this interface.
- Support for mt2712 in the Mediatek IOMMU driver
- New IOMMU driver for QCOM hardware
- System PM support for ARM-SMMU
- Shutdown method for ARM-SMMU-v3
- Some constification patches
- Various other small improvements and fixes
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v2
iQIcBAABAgAGBQJZtCFNAAoJECvwRC2XARrjZnQP/AxC/ezQpq82HbegF4sM/cVE
Ep7TeTqodEl75FS/6txe2wU0pwodqk/LB9ajfQZUbE1w8vKsNEqi5qf4ZYHGoxYI
5bWyjJBzKIlwENH5lsBpQNt6XLevrYmRsFy7F0tRYy+qPQq8k+js2i7/XkCL3q7L
3xklF847RRoITaTOhhaROx1pF23dSMEsS2XGuWHcZfjORtep4wcFKzd/2SvlCWCo
P2bRU7jBzfJuuGSA80gaiUbDmrULTUfYuZNp7njASzCgsDmagERtvDEpdoXPNNSp
u6s4LjU1Dp3fgr6g6cFRO7B6JUbWd619nwo9so/c/wZN54yEngBF9EyeeF3mv2O5
ZbM2mOW3RlZcjxFT/AC8G4cZwwP6MpCEQOdqknoqc6ZQwcDqwN0o9I4+po0wsiAU
89ijZZe9Mx0p9lNpihaBEB1erAUWPo5Obh62zo80W3h6x9WzkGQWM+PyFK2DYoaC
8biEZzcc21sLEHvXQkcEGJSKrihHr9sluOqvxmCw5QAkYIFAeZRoeH7JtZWjVCnr
T3XvaG1G1Aw6tS7ErxufdKawREAGki0Rm9i1baiH9sqNj5rllM01Y+PgU6E21Nbg
iZp9gJLjfwM4vhYLlovvQK5PRoOBsCkyCpEI4GJqjLeam5p/WN06CFFf0ifQofYr
qDPCVDkWHWV8nugFFKE7
=EVh9
-----END PGP SIGNATURE-----
Merge tag 'iommu-updates-v4.14' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu
Pull IOMMU updates from Joerg Roedel:
"Slightly more changes than usual this time:
- KDump Kernel IOMMU take-over code for AMD IOMMU. The code now tries
to preserve the mappings of the kernel so that master aborts for
devices are avoided. Master aborts cause some devices to fail in
the kdump kernel, so this code makes the dump more likely to
succeed when AMD IOMMU is enabled.
- common flush queue implementation for IOVA code users. The code is
still optional, but AMD and Intel IOMMU drivers had their own
implementation which is now unified.
- finish support for iommu-groups. All drivers implement this feature
now so that IOMMU core code can rely on it.
- finish support for 'struct iommu_device' in iommu drivers. All
drivers now use the interface.
- new functions in the IOMMU-API for explicit IO/TLB flushing. This
will help to reduce the number of IO/TLB flushes when IOMMU drivers
support this interface.
- support for mt2712 in the Mediatek IOMMU driver
- new IOMMU driver for QCOM hardware
- system PM support for ARM-SMMU
- shutdown method for ARM-SMMU-v3
- some constification patches
- various other small improvements and fixes"
* tag 'iommu-updates-v4.14' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (87 commits)
iommu/vt-d: Don't be too aggressive when clearing one context entry
iommu: Introduce Interface for IOMMU TLB Flushing
iommu/s390: Constify iommu_ops
iommu/vt-d: Avoid calling virt_to_phys() on null pointer
iommu/vt-d: IOMMU Page Request needs to check if address is canonical.
arm/tegra: Call bus_set_iommu() after iommu_device_register()
iommu/exynos: Constify iommu_ops
iommu/ipmmu-vmsa: Make ipmmu_gather_ops const
iommu/ipmmu-vmsa: Rereserving a free context before setting up a pagetable
iommu/amd: Rename a few flush functions
iommu/amd: Check if domain is NULL in get_domain() and return -EBUSY
iommu/mediatek: Fix a build warning of BIT(32) in ARM
iommu/mediatek: Fix a build fail of m4u_type
iommu: qcom: annotate PM functions as __maybe_unused
iommu/pamu: Fix PAMU boot crash
memory: mtk-smi: Degrade SMI init to module_init
iommu/mediatek: Enlarge the validate PA range for 4GB mode
iommu/mediatek: Disable iommu clock when system suspend
iommu/mediatek: Move pgtable allocation into domain_alloc
iommu/mediatek: Merge 2 M4U HWs into one iommu domain
...
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=9cLP
-----END PGP SIGNATURE-----
Merge tag 'pci-v4.14-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci
Pull PCI updates from Bjorn Helgaas:
- add enhanced Downstream Port Containment support, which prints more
details about Root Port Programmed I/O errors (Dongdong Liu)
- add Layerscape ls1088a and ls2088a support (Hou Zhiqiang)
- add MediaTek MT2712 and MT7622 support (Ryder Lee)
- add MediaTek MT2712 and MT7622 MSI support (Honghui Zhang)
- add Qualcom IPQ8074 support (Varadarajan Narayanan)
- add R-Car r8a7743/5 device tree support (Biju Das)
- add Rockchip per-lane PHY support for better power management (Shawn
Lin)
- fix IRQ mapping for hot-added devices by replacing the
pci_fixup_irqs() boot-time design with a host bridge hook called at
probe-time (Lorenzo Pieralisi, Matthew Minter)
- fix race when enabling two devices that results in upstream bridge
not being enabled correctly (Srinath Mannam)
- fix pciehp power fault infinite loop (Keith Busch)
- fix SHPC bridge MSI hotplug events by enabling bus mastering
(Aleksandr Bezzubikov)
- fix a VFIO issue by correcting PCIe capability sizes (Alex
Williamson)
- fix an INTD issue on Xilinx and possibly other drivers by unifying
INTx IRQ domain support (Paul Burton)
- avoid IOMMU stalls by marking AMD Stoney GPU ATS as broken (Joerg
Roedel)
- allow APM X-Gene device assignment to guests by adding an ACS quirk
(Feng Kan)
- fix driver crashes by disabling Extended Tags on Broadcom HT2100
(Extended Tags support is required for PCIe Receivers but not
Requesters, and we now enable them by default when Requesters support
them) (Sinan Kaya)
- fix MSIs for devices that use phantom RIDs for DMA by assuming MSIs
use the real Requester ID (not a phantom RID) (Robin Murphy)
- prevent assignment of Intel VMD children to guests (which may be
supported eventually, but isn't yet) by not associating an IOMMU with
them (Jon Derrick)
- fix Intel VMD suspend/resume by releasing IRQs on suspend (Scott
Bauer)
- fix a Function-Level Reset issue with Intel 750 NVMe by waiting
longer (up to 60sec instead of 1sec) for device to become ready
(Sinan Kaya)
- fix a Function-Level Reset issue on iProc Stingray by working around
hardware defects in the CRS implementation (Oza Pawandeep)
- fix an issue with Intel NVMe P3700 after an iProc reset by adding a
delay during shutdown (Oza Pawandeep)
- fix a Microsoft Hyper-V lockdep issue by polling instead of blocking
in compose_msi_msg() (Stephen Hemminger)
- fix a wireless LAN driver timeout by clearing DesignWare MSI
interrupt status after it is handled, not before (Faiz Abbas)
- fix DesignWare ATU enable checking (Jisheng Zhang)
- reduce Layerscape dependencies on the bootloader by doing more
initialization in the driver (Hou Zhiqiang)
- improve Intel VMD performance allowing allocation of more IRQ vectors
than present CPUs (Keith Busch)
- improve endpoint framework support for initial DMA mask, different
BAR sizes, configurable page sizes, MSI, test driver, etc (Kishon
Vijay Abraham I, Stan Drozd)
- rework CRS support to add periodic messages while we poll during
enumeration and after Function-Level Reset and prepare for possible
other uses of CRS (Sinan Kaya)
- clean up Root Port AER handling by removing unnecessary code and
moving error handler methods to struct pcie_port_service_driver
(Christoph Hellwig)
- clean up error handling paths in various drivers (Bjorn Andersson,
Fabio Estevam, Gustavo A. R. Silva, Harunobu Kurokawa, Jeffy Chen,
Lorenzo Pieralisi, Sergei Shtylyov)
- clean up SR-IOV resource handling by disabling VF decoding before
updating the corresponding resource structs (Gavin Shan)
- clean up DesignWare-based drivers by unifying quirks to update Class
Code and Interrupt Pin and related handling of write-protected
registers (Hou Zhiqiang)
- clean up by adding empty generic pcibios_align_resource() and
pcibios_fixup_bus() and removing empty arch-specific implementations
(Palmer Dabbelt)
- request exclusive reset control for several drivers to allow cleanup
elsewhere (Philipp Zabel)
- constify various structures (Arvind Yadav, Bhumika Goyal)
- convert from full_name() to %pOF (Rob Herring)
- remove unused variables from iProc, HiSi, Altera, Keystone (Shawn
Lin)
* tag 'pci-v4.14-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci: (170 commits)
PCI: xgene: Clean up whitespace
PCI: xgene: Define XGENE_PCI_EXP_CAP and use generic PCI_EXP_RTCTL offset
PCI: xgene: Fix platform_get_irq() error handling
PCI: xilinx-nwl: Fix platform_get_irq() error handling
PCI: rockchip: Fix platform_get_irq() error handling
PCI: altera: Fix platform_get_irq() error handling
PCI: spear13xx: Fix platform_get_irq() error handling
PCI: artpec6: Fix platform_get_irq() error handling
PCI: armada8k: Fix platform_get_irq() error handling
PCI: dra7xx: Fix platform_get_irq() error handling
PCI: exynos: Fix platform_get_irq() error handling
PCI: iproc: Clean up whitespace
PCI: iproc: Rename PCI_EXP_CAP to IPROC_PCI_EXP_CAP
PCI: iproc: Add 500ms delay during device shutdown
PCI: Fix typos and whitespace errors
PCI: Remove unused "res" variable from pci_resource_io()
PCI: Correct kernel-doc of pci_vpd_srdt_size(), pci_vpd_srdt_tag()
PCI/AER: Reformat AER register definitions
iommu/vt-d: Prevent VMD child devices from being remapping targets
x86/PCI: Use is_vmd() rather than relying on the domain number
...
Pull x86 mm changes from Ingo Molnar:
"PCID support, 5-level paging support, Secure Memory Encryption support
The main changes in this cycle are support for three new, complex
hardware features of x86 CPUs:
- Add 5-level paging support, which is a new hardware feature on
upcoming Intel CPUs allowing up to 128 PB of virtual address space
and 4 PB of physical RAM space - a 512-fold increase over the old
limits. (Supercomputers of the future forecasting hurricanes on an
ever warming planet can certainly make good use of more RAM.)
Many of the necessary changes went upstream in previous cycles,
v4.14 is the first kernel that can enable 5-level paging.
This feature is activated via CONFIG_X86_5LEVEL=y - disabled by
default.
(By Kirill A. Shutemov)
- Add 'encrypted memory' support, which is a new hardware feature on
upcoming AMD CPUs ('Secure Memory Encryption', SME) allowing system
RAM to be encrypted and decrypted (mostly) transparently by the
CPU, with a little help from the kernel to transition to/from
encrypted RAM. Such RAM should be more secure against various
attacks like RAM access via the memory bus and should make the
radio signature of memory bus traffic harder to intercept (and
decrypt) as well.
This feature is activated via CONFIG_AMD_MEM_ENCRYPT=y - disabled
by default.
(By Tom Lendacky)
- Enable PCID optimized TLB flushing on newer Intel CPUs: PCID is a
hardware feature that attaches an address space tag to TLB entries
and thus allows to skip TLB flushing in many cases, even if we
switch mm's.
(By Andy Lutomirski)
All three of these features were in the works for a long time, and
it's coincidence of the three independent development paths that they
are all enabled in v4.14 at once"
* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (65 commits)
x86/mm: Enable RCU based page table freeing (CONFIG_HAVE_RCU_TABLE_FREE=y)
x86/mm: Use pr_cont() in dump_pagetable()
x86/mm: Fix SME encryption stack ptr handling
kvm/x86: Avoid clearing the C-bit in rsvd_bits()
x86/CPU: Align CR3 defines
x86/mm, mm/hwpoison: Clear PRESENT bit for kernel 1:1 mappings of poison pages
acpi, x86/mm: Remove encryption mask from ACPI page protection type
x86/mm, kexec: Fix memory corruption with SME on successive kexecs
x86/mm/pkeys: Fix typo in Documentation/x86/protection-keys.txt
x86/mm/dump_pagetables: Speed up page tables dump for CONFIG_KASAN=y
x86/mm: Implement PCID based optimization: try to preserve old TLB entries using PCID
x86: Enable 5-level paging support via CONFIG_X86_5LEVEL=y
x86/mm: Allow userspace have mappings above 47-bit
x86/mm: Prepare to expose larger address space to userspace
x86/mpx: Do not allow MPX if we have mappings above 47-bit
x86/mm: Rename tasksize_32bit/64bit to task_size_32bit/64bit()
x86/xen: Redefine XEN_ELFNOTE_INIT_P2M using PUD_SIZE * PTRS_PER_PUD
x86/mm/dump_pagetables: Fix printout of p4d level
x86/mm/dump_pagetables: Generalize address normalization
x86/boot: Fix memremap() related build failure
...
Previously, we were invalidating context cache and IOTLB globally when
clearing one context entry. This is a tad too aggressive.
Invalidate the context cache and IOTLB for the interested device only.
Signed-off-by: Filippo Sironi <sironi@amazon.de>
Cc: David Woodhouse <dwmw@amazon.co.uk>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-kernel@vger.kernel.org
Acked-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Calls to mmu_notifier_invalidate_page() were replaced by calls to
mmu_notifier_invalidate_range() and are now bracketed by calls to
mmu_notifier_invalidate_range_start()/end()
Remove now useless invalidate_page callback.
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: iommu@lists.linux-foundation.org
Cc: Joerg Roedel <jroedel@suse.de>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Calls to mmu_notifier_invalidate_page() were replaced by calls to
mmu_notifier_invalidate_range() and are now bracketed by calls to
mmu_notifier_invalidate_range_start()/end()
Remove now useless invalidate_page callback.
Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Cc: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Cc: iommu@lists.linux-foundation.org
Cc: Joerg Roedel <jroedel@suse.de>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
VMD child devices must use the VMD endpoint's ID as the requester. Because
of this, there needs to be a way to link the parent VMD endpoint's IOMMU
group and associated mappings to the VMD child devices such that attaching
and detaching child devices modify the endpoint's mappings, while
preventing early detaching on a singular device removal or unbinding.
The reassignment of individual VMD child devices devices to VMs is outside
the scope of VMD, but may be implemented in the future. For now it is best
to prevent any such attempts.
Prevent VMD child devices from returning an IOMMU, which prevents it from
exposing an iommu_group sysfs directory and allowing subsequent binding by
userspace-access drivers such as VFIO.
Signed-off-by: Jon Derrick <jonathan.derrick@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
With the current IOMMU-API the hardware TLBs have to be
flushed in every iommu_ops->unmap() call-back.
For unmapping large amounts of address space, like it
happens when a KVM domain with assigned devices is
destroyed, this causes thousands of unnecessary TLB flushes
in the IOMMU hardware because the unmap call-back runs for
every unmapped physical page.
With the TLB Flush Interface and the new iommu_unmap_fast()
function introduced here the need to clean the hardware TLBs
is removed from the unmapping code-path. Users of
iommu_unmap_fast() have to explicitly call the TLB-Flush
functions to sync the page-table changes to the hardware.
Three functions for TLB-Flushes are introduced:
* iommu_flush_tlb_all() - Flushes all TLB entries
associated with that
domain. TLBs entries are
flushed when this function
returns.
* iommu_tlb_range_add() - This will add a given
range to the flush queue
for this domain.
* iommu_tlb_sync() - Flushes all queued ranges from
the hardware TLBs. Returns when
the flush is finished.
The semantic of this interface is intentionally similar to
the iommu_gather_ops from the io-pgtable code.
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
iommu_ops are not supposed to change at runtime.
Functions 'bus_set_iommu' working with const iommu_ops provided
by <linux/iommu.h>. So mark the non-const structs as const.
Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
Acked-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
