Commit 4b123757ee ("iommu/io-pgtable-arm: Make allocations
NUMA-aware") added a NUMA hint to page table allocation, but the pgtable
selftest doesn't provide an SMMU device parameter. Since dev_to_node
doesn't accept a NULL argument, add a special case for selftest.
Signed-off-by: Jean-Philippe Brucker <jean-philippe.brucker@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
We would generally expect pagetables to be read by the IOMMU more than
written by the CPU, so in NUMA systems it makes sense to locate them
close to the former and avoid cross-node pagetable walks if at all
possible. As it turns out, we already have a handle on the IOMMU device
for the sake of coherency management, so it's trivial to grab the
appropriate NUMA node when allocating new pagetable pages.
Note that we drop the semantics of alloc_pages_exact(), but that's fine
since they have never been necessary: the only time we're allocating
more than one page is for stage 2 top-level concatenation, but since
that is based on the number of IPA bits, the size is always some exact
power of two anyway.
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
We can use for_each_set_bit() to simplify code slightly in the
ARM io-pgtable self tests while unmapping.
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
It's not entirely unreasonable for io-pgtable-arm to be built for
configurations with 32-bit phys_addr_t, where the compiler rightly
raises a warning about the 36-bit shift. That particular code path
should never actually *run* on those systems, but we still want it
to compile cleanly, which is easily done by using an unambiguous u64
as the intermediate type instead.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Bring io-pgtable-arm in line with the ARMv8.2-LPA feature allowing
52-bit physical addresses when using the 64KB translation granule.
This will be supported by SMMUv3.1.
Tested-by: Nate Watterson <nwatters@codeaurora.org>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Unmap returns a size_t all throughout the IOMMU framework.
Make io-pgtable match this convention.
Moreover, there isn't a need to have a signed int return type
as we return 0 in case of failures.
Signed-off-by: Vivek Gautam <vivek.gautam@codeaurora.org>
Acked-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>
It may be an egregious error to attempt to use addresses outside the
range of the pagetable format, but that still doesn't mean we should
merrily wreak havoc by silently mapping/unmapping whatever truncated
portions of them might happen to correspond to real addresses.
Add some up-front checks to sanitise our inputs so that buggy callers
don't invite potential memory corruption.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
When writing a new table entry, we must ensure that the contents of the
table is made visible to the SMMU page table walker before the updated
table entry itself.
This is currently achieved using wmb(), which expands to an expensive and
unnecessary DSB instruction. Ideally, we'd just use cmpxchg64_release when
writing the table entry, but this doesn't have memory ordering semantics
on !SMP systems.
Instead, use dma_wmb(), which emits DMB OSHST. Strictly speaking, this
does more than we require (since it targets the outer-shareable domain),
but it's likely to be significantly faster than the DSB approach.
Reported-by: Linu Cherian <linu.cherian@cavium.com>
Suggested-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
For parallel I/O with multiple concurrent threads servicing the same
device (or devices, if several share a domain), serialising page table
updates becomes a massive bottleneck. On reflection, though, we don't
strictly need to do that - for valid IOMMU API usage, there are in fact
only two races that we need to guard against: multiple map requests for
different blocks within the same region, when the intermediate-level
table for that region does not yet exist; and multiple unmaps of
different parts of the same block entry. Both of those are fairly easily
solved by using a cmpxchg to install the new table, such that if we then
find that someone else's table got there first, we can simply free ours
and continue.
Make the requisite changes such that we can withstand being called
without the caller maintaining a lock. In theory, this opens up a few
corners in which wildly misbehaving callers making nonsensical
overlapping requests might lead to crashes instead of just unpredictable
results, but correct code really does not deserve to pay a significant
performance cost for the sake of masking bugs in theoretical broken code.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Once we remove the serialising spinlock, a potential race opens up for
non-coherent IOMMUs whereby a caller of .map() can be sure that cache
maintenance has been performed on their new PTE, but will have no
guarantee that such maintenance for table entries above it has actually
completed (e.g. if another CPU took an interrupt immediately after
writing the table entry, but before initiating the DMA sync).
Handling this race safely will add some potentially non-trivial overhead
to installing a table entry, which we would much rather avoid on
coherent systems where it will be unnecessary, and where we are stirivng
to minimise latency by removing the locking in the first place.
To that end, let's introduce an explicit notion of cache-coherency to
io-pgtable, such that we will be able to avoid penalising IOMMUs which
know enough to know when they are coherent.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
The current split_blk_unmap implementation suffers from some inscrutable
pointer trickery for creating the tables to replace the block entry, but
more than that it also suffers from hideous inefficiency. For example,
the most pathological case of unmapping a level 3 page from a level 1
block will allocate 513 lower-level tables to remap the entire block at
page granularity, when only 2 are actually needed (the rest can be
covered by level 2 block entries).
Also, we would like to be able to relax the spinlock requirement in
future, for which the roll-back-and-try-again logic for race resolution
would be pretty hideous under the current paradigm.
Both issues can be resolved most neatly by turning things sideways:
instead of repeatedly recursing into __arm_lpae_map() map to build up an
entire new sub-table depth-first, we can directly replace the block
entry with a next-level table of block/page entries, then repeat by
unmapping at the next level if necessary. With a little refactoring of
some helper functions, the code ends up not much bigger than before, but
considerably easier to follow and to adapt in future.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
The recursive nature of __arm_lpae_{map,unmap}() means that
ARM_LPAE_BLOCK_SIZE() is evaluated for every level, including those
where block mappings aren't possible. This in itself is harmless enough,
as we will only ever be called with valid sizes from the pgsize_bitmap,
and thus always recurse down past any imaginary block sizes. The only
problem is that most of those imaginary sizes overflow the type used for
the calculation, and thus trigger warnings under UBsan:
[ 63.020939] ================================================================================
[ 63.021284] UBSAN: Undefined behaviour in drivers/iommu/io-pgtable-arm.c:312:22
[ 63.021602] shift exponent 39 is too large for 32-bit type 'int'
[ 63.021909] CPU: 0 PID: 1119 Comm: lkvm Not tainted 4.7.0-rc3+ #819
[ 63.022163] Hardware name: FVP Base (DT)
[ 63.022345] Call trace:
[ 63.022629] [<ffffff900808f258>] dump_backtrace+0x0/0x3a8
[ 63.022975] [<ffffff900808f614>] show_stack+0x14/0x20
[ 63.023294] [<ffffff90086bc9dc>] dump_stack+0x104/0x148
[ 63.023609] [<ffffff9008713ce8>] ubsan_epilogue+0x18/0x68
[ 63.023956] [<ffffff9008714410>] __ubsan_handle_shift_out_of_bounds+0x18c/0x1bc
[ 63.024365] [<ffffff900890fcb0>] __arm_lpae_map+0x720/0xae0
[ 63.024732] [<ffffff9008910170>] arm_lpae_map+0x100/0x190
[ 63.025049] [<ffffff90089183d8>] arm_smmu_map+0x78/0xc8
[ 63.025390] [<ffffff9008906c18>] iommu_map+0x130/0x230
[ 63.025763] [<ffffff9008bf7564>] vfio_iommu_type1_attach_group+0x4bc/0xa00
[ 63.026156] [<ffffff9008bf3c78>] vfio_fops_unl_ioctl+0x320/0x580
[ 63.026515] [<ffffff9008377420>] do_vfs_ioctl+0x140/0xd28
[ 63.026858] [<ffffff9008378094>] SyS_ioctl+0x8c/0xa0
[ 63.027179] [<ffffff9008086e70>] el0_svc_naked+0x24/0x28
[ 63.027412] ================================================================================
Perform the shift in a 64-bit type to prevent the theoretical overflow
and keep the peace. As it turns out, this generates identical code for
32-bit ARM, and marginally shorter AArch64 code, so it's good all round.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Do a check for already installed leaf entry at the current level before
dereferencing it in order to avoid walking the page table down with
wrong pointer to the next level.
Signed-off-by: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>
CC: Will Deacon <will.deacon@arm.com>
CC: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Allow the creation of privileged mode mappings, for stage 1 only.
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Tested-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Jeremy Gebben <jgebben@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Check for iommu_gather_ops structures that are only stored in the tlb
field of an io_pgtable_cfg structure. The tlb field is of type
const struct iommu_gather_ops *, so iommu_gather_ops structures
having this property can be declared as const. Also, replace __initdata
with __initconst.
Acked-by: Julia Lawall <julia.lawall@lip6.fr>
Signed-off-by: Bhumika Goyal <bhumirks@gmail.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
We can use for_each_set_bit() to simplify the code slightly in the
ARM io-pgtable self tests.
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
The implementation of iova_to_phys for the long-descriptor ARM
io-pgtable code always masks with the granule size when inserting the
low virtual address bits into the physical address determined from the
page tables. In cases where the leaf entry is found before the final
level of table (i.e. due to a block mapping), this results in rounding
down to the bottom page of the block mapping. Consequently, the physical
address range batching in the vfio_unmap_unpin is defeated and we end
up taking the long way home.
This patch fixes the problem by masking the virtual address with the
appropriate mask for the level at which the leaf descriptor is located.
The short-descriptor code already gets this right, so no change is
needed there.
Cc: <stable@vger.kernel.org>
Reported-by: Robin Murphy <robin.murphy@arm.com>
Tested-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Teach the LPAE format to create Device mappings when asked.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Tested-by: Eric Auger <eric.auger@linaro.org>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
As the number of io-pgtable implementations grows beyond 1, it's time
to rationalise the quirks mechanism before things have a chance to
start getting really ugly and out-of-hand.
To that end:
- Indicate exactly which quirks each format can/does support.
- Fail creating a table if a caller wants unsupported quirks.
- Properly document where each quirk applies and why.
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Add some simple wrappers to avoid having the guts of the TLB operations
spilled all over the page table implementations, and to provide a point
to implement extra common functionality.
Acked-by: Will Deacon <will.deacon@arm.com>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Trying to build a kernel for ARC with both options CONFIG_COMPILE_TEST
and CONFIG_IOMMU_IO_PGTABLE_LPAE enabled (e.g. as a result of "make
allyesconfig") results in the following build failure:
| CC drivers/iommu/io-pgtable-arm.o
| linux/drivers/iommu/io-pgtable-arm.c: In
| function ‘__arm_lpae_alloc_pages’:
| linux/drivers/iommu/io-pgtable-arm.c:221:3:
| error: implicit declaration of function ‘dma_map_single’
| [-Werror=implicit-function-declaration]
| dma = dma_map_single(dev, pages, size, DMA_TO_DEVICE);
| ^
| linux/drivers/iommu/io-pgtable-arm.c:221:42:
| error: ‘DMA_TO_DEVICE’ undeclared (first use in this function)
| dma = dma_map_single(dev, pages, size, DMA_TO_DEVICE);
| ^
Since IOMMU_IO_PGTABLE_LPAE depends on DMA API, io-pgtable-arm.c should
include linux/dma-mapping.h. This fixes the reported failure.
Cc: Alexey Brodkin <abrodkin@synopsys.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Joerg Roedel <joro@8bytes.org>
Signed-off-by: Lada Trimasova <ltrimas@synopsys.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
When tearing down page tables, we return early for the final level
since we know that we won't have any table pointers to follow.
Unfortunately, this also means that we forget to free the final level,
so we end up leaking memory.
Fix the issue by always freeing the current level, but just don't bother
to iterate over the ptes if we're at the final level.
Cc: <stable@vger.kernel.org>
Reported-by: Zhang Bo <zhangbo_a@xiaomi.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
There is no need to keep a useful accessor for a public structure hidden
away in a private implementation. Move it out alongside the structure
definition so that other implementations may reuse it.
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
IOMMU hardware with range-based TLB maintenance commands can work
happily with the iova and size arguments passed via the tlb_add_flush
callback, but for IOMMUs which require separate commands per entry in
the range, it is not straightforward to infer the necessary granularity
when it comes to issuing the actual commands.
Add an additional argument indicating the granularity for the benefit
of drivers needing to know, and update the ARM LPAE code appropriately
(for non-leaf invalidations we currently just assume the worst-case
page granularity rather than walking the table to check).
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
In the case of corrupted page tables, or when an invalid size is given,
__arm_lpae_unmap() may recurse beyond the maximum number of levels.
Unfortunately the detection of this error condition only happens *after*
calculating a nonsense offset from something which might not be a valid
table pointer and dereferencing that to see if it is a valid PTE.
Make things a little more robust by checking the level is valid before
doing anything which depends on it being so.
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
In checking whether DMA addresses differ from physical addresses, using
dma_to_phys() is actually the wrong thing to do, since it may hide any
DMA offset, which is precisely one of the things we are checking for.
Simply casting between the two address types, whilst ugly, is in fact
the appropriate course of action. Further care (and ugliness) is also
necessary in the comparison to avoid truncation if phys_addr_t and
dma_addr_t differ in size.
We can also reject any device with a fixed DMA offset up-front at page
table creation, leaving the allocation-time check for the more subtle
cases like bounce buffering due to an incorrect DMA mask.
Furthermore, we can then fix the hackish KConfig dependency so that
architectures without a dma_to_phys() implementation may still
COMPILE_TEST (or even use!) the code. The true dependency is on the
DMA API, so use the appropriate symbol for that.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
[will: folded in selftest fix from Yong Wu]
Signed-off-by: Will Deacon <will.deacon@arm.com>
When installing a block mapping, we unconditionally overwrite a non-leaf
PTE if we find one. However, this can cause a problem if the following
sequence of events occur:
(1) iommu_map called for a 4k (i.e. PAGE_SIZE) mapping at some address
- We initialise the page table all the way down to a leaf entry
- No TLB maintenance is required, because we're going from invalid
to valid.
(2) iommu_unmap is called on the mapping installed in (1)
- We walk the page table to the final (leaf) entry and zero it
- We only changed a valid leaf entry, so we invalidate leaf-only
(3) iommu_map is called on the same address as (1), but this time for
a 2MB (i.e. BLOCK_SIZE) mapping)
- We walk the page table down to the penultimate level, where we
find a table entry
- We overwrite the table entry with a block mapping and return
without any TLB maintenance and without freeing the memory used
by the now-orphaned table.
This last step can lead to a walk-cache caching the overwritten table
entry, causing unexpected faults when the new mapping is accessed by a
device. One way to fix this would be to collapse the page table when
freeing the last page at a given level, but this would require expensive
iteration on every map call. Instead, this patch detects the case when
we are overwriting a table entry and explicitly unmaps the table first,
which takes care of both freeing and TLB invalidation.
Cc: <stable@vger.kernel.org>
Reported-by: Brian Starkey <brian.starkey@arm.com>
Tested-by: Brian Starkey <brian.starkey@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
With the users fully converted to DMA API operations, it's dead, Jim.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
With all current users now opted in to DMA API operations, make the
iommu_dev pointer mandatory, rendering the flush_pgtable callback
redundant for cache maintenance. However, since the DMA calls could be
nops in the case of a coherent IOMMU, we still need to ensure the page
table updates are fully synchronised against a subsequent page table
walk. In the unmap path, the TLB sync will usually need to do this
anyway, so just cement that requirement; in the map path which may
consist solely of cacheable memory writes (in the coherent case),
insert an appropriate barrier at the end of the operation, and obviate
the need to call flush_pgtable on every individual update for
synchronisation.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
[will: slight clarification to tlb_sync comment]
Signed-off-by: Will Deacon <will.deacon@arm.com>
Currently, users of the LPAE page table code are (ab)using dma_map_page()
as a means to flush page table updates for non-coherent IOMMUs. Since
from the CPU's point of view, creating IOMMU page tables *is* passing
DMA buffers to a device (the IOMMU's page table walker), there's little
reason not to use the DMA API correctly.
Allow IOMMU drivers to opt into DMA API operations for page table
allocation and updates by providing their appropriate device pointer.
The expectation is that an LPAE IOMMU should have a full view of system
memory, so use streaming mappings to avoid unnecessary pressure on
ZONE_DMA, and treat any DMA translation as a warning sign.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Although we set TCR.T1SZ to 0, the input address range covered by TTBR1
is actually calculated using T0SZ in this case on the ARM SMMU. This
could theoretically lead to speculative table walks through physical
address zero, leading to all sorts of fun and games if we have MMIO
regions down there.
This patch avoids the issue by setting EPD1 to disable walks through
the unused TTBR1 register.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Various build/boot bots have reported WARNs being triggered by the ARM
iopgtable LPAE self-tests on i386 machines.
This boils down to two instances of right-shifting a 32-bit unsigned
long (i.e. an iova) by more than the size of the type. On 32-bit ARM,
this happens to give us zero, hence my testing didn't catch this
earlier.
This patch fixes the issue by using DIV_ROUND_UP and explicit case to
to avoid the erroneous shifts.
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Reported-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
The quirk causes the Non-Secure bit to be set in all page table entries.
Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
This patch adds a series of basic self-consistency tests to the ARM LPAE
IO page table allocator that exercise corner cases in map/unmap, as well
as testing all valid configurations of pagesize, ias and stage.
Signed-off-by: Will Deacon <will.deacon@arm.com>
A number of IOMMUs found in ARM SoCs can walk architecture-compatible
page tables.
This patch adds a generic allocator for Stage-1 and Stage-2 v7/v8
long-descriptor page tables. 4k, 16k and 64k pages are supported, with
up to 4-levels of walk to cover a 48-bit address space.
Tested-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Jean-Philippe Brucker