| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
Calling arm_smmu_tlb_inv_range() with a size of zero, perhaps due to
an empty 'iommu_iotlb_gather' structure, should be a NOP. Elide the
CMD_SYNC when there is no invalidation to be performed.
Signed-off-by: Will Deacon <will@kernel.org>
|
|
There's really no need for this to be a bitfield, particularly as we
don't have bitwise addressing on arm64.
Signed-off-by: Will Deacon <will@kernel.org>
|
|
Detecting the ATS capability of the SMMU at probe time introduces a
spinlock into the ->unmap() fast path, even when ATS is not actually
in use. Furthermore, the ATC invalidation that exists is broken, as it
occurs before invalidation of the main SMMU TLB which leaves a window
where the ATC can be repopulated with stale entries.
Given that ATS is both a new feature and a specialist sport, disable it
for now whilst we fix it properly in subsequent patches. Since PRI
requires ATS, disable that too.
Cc: <stable@vger.kernel.org>
Fixes: 9ce27afc0830 ("iommu/arm-smmu-v3: Add support for PCI ATS")
Acked-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>
|
|
It turns out that we've always relied on some subtle ordering guarantees
when inserting commands into the SMMUv3 command queue. With the recent
changes to elide locking when possible, these guarantees become more
subtle and even more important.
Add a comment documented the barrier semantics of command insertion so
that we don't have to derive the behaviour from scratch each time it
comes up on the list.
Signed-off-by: Will Deacon <will@kernel.org>
|
|
Update the iommu_iotlb_gather structure passed to ->tlb_add_page() and
use this information to defer all TLB invalidation until ->iotlb_sync().
This drastically reduces contention on the command queue, since we can
insert our commands in batches rather than one-by-one.
Tested-by: Ganapatrao Kulkarni <gkulkarni@marvell.com>
Signed-off-by: Will Deacon <will@kernel.org>
|
|
The SMMU command queue is a bottleneck in large systems, thanks to the
spin_lock which serialises accesses from all CPUs to the single queue
supported by the hardware.
Attempt to improve this situation by moving to a new algorithm for
inserting commands into the queue, which is lock-free on the fast-path.
Tested-by: Ganapatrao Kulkarni <gkulkarni@marvell.com>
Signed-off-by: Will Deacon <will@kernel.org>
|
|
In preparation for rewriting the command queue insertion code to use a
new algorithm, rework many of our queue macro accessors and manipulation
functions so that they operate on the arm_smmu_ll_queue structure where
possible. This will allow us to call these helpers on local variables
without having to construct a full-blown arm_smmu_queue on the stack.
No functional change.
Tested-by: Ganapatrao Kulkarni <gkulkarni@marvell.com>
Signed-off-by: Will Deacon <will@kernel.org>
|
|
In preparation for rewriting the command queue insertion code to use a
new algorithm, introduce a new arm_smmu_ll_queue structure which contains
only the information necessary to perform queue arithmetic for a queue
and will later be extended so that we can perform complex atomic
manipulation on some of the fields.
No functional change.
Tested-by: Ganapatrao Kulkarni <gkulkarni@marvell.com>
Signed-off-by: Will Deacon <will@kernel.org>
|
|
The Q_OVF macro doesn't need to access the arm_smmu_queue structure, so
drop the unused macro argument.
No functional change.
Tested-by: Ganapatrao Kulkarni <gkulkarni@marvell.com>
Signed-off-by: Will Deacon <will@kernel.org>
|
|
In preparation for rewriting the command queue insertion code to use a
new algorithm, separate the software and hardware views of the prod and
cons indexes so that manipulating the software state doesn't
automatically update the hardware state at the same time.
No functional change.
Tested-by: Ganapatrao Kulkarni <gkulkarni@marvell.com>
Signed-off-by: Will Deacon <will@kernel.org>
|
|
With all the pieces in place, we can finally propagate the
iommu_iotlb_gather structure from the call to unmap() down to the IOMMU
drivers' implementation of ->tlb_add_page(). Currently everybody ignores
it, but the machinery is now there to defer invalidation.
Signed-off-by: Will Deacon <will@kernel.org>
|
|
Update the io-pgtable ->unmap() function to take an iommu_iotlb_gather
pointer as an argument, and update the callers as appropriate.
Signed-off-by: Will Deacon <will@kernel.org>
|
|
The ->tlb_sync() callback is no longer used, so it can be removed.
Signed-off-by: Will Deacon <will@kernel.org>
|
|
The ->tlb_add_flush() callback in the io-pgtable API now looks a bit
silly:
- It takes a size and a granule, which are always the same
- It takes a 'bool leaf', which is always true
- It only ever flushes a single page
With that in mind, replace it with an optional ->tlb_add_page() callback
that drops the useless parameters.
Signed-off-by: Will Deacon <will@kernel.org>
|
|
Now that all IOMMU drivers using the io-pgtable API implement the
->tlb_flush_walk() and ->tlb_flush_leaf() callbacks, we can use them in
the io-pgtable code instead of ->tlb_add_flush() immediately followed by
->tlb_sync().
Signed-off-by: Will Deacon <will@kernel.org>
|
|
Hook up ->tlb_flush_walk() and ->tlb_flush_leaf() in drivers using the
io-pgtable API so that we can start making use of them in the page-table
code. For now, they can just wrap the implementations of ->tlb_add_flush
and ->tlb_sync pending future optimisation in each driver.
Signed-off-by: Will Deacon <will@kernel.org>
|
|
In preparation for deferring TLB flushes to iommu_tlb_sync(), introduce
two new synchronous invalidation helpers to the io-pgtable API, which
allow the unmap() code to force invalidation in cases where it cannot be
deferred (e.g. when replacing a table with a block or when TLBI_ON_MAP
is set).
Signed-off-by: Will Deacon <will@kernel.org>
|
|
To allow IOMMU drivers to batch up TLB flushing operations and postpone
them until ->iotlb_sync() is called, extend the prototypes for the
->unmap() and ->iotlb_sync() IOMMU ops callbacks to take a pointer to
the current iommu_iotlb_gather structure.
All affected IOMMU drivers are updated, but there should be no
functional change since the extra parameter is ignored for now.
Signed-off-by: Will Deacon <will@kernel.org>
|
|
Introduce a helper function for drivers to use when updating an
iommu_iotlb_gather structure in response to an ->unmap() call, rather
than having to open-code the logic in every page-table implementation.
Signed-off-by: Will Deacon <will@kernel.org>
|
|
To permit batching of TLB flushes across multiple calls to the IOMMU
driver's ->unmap() implementation, introduce a new structure for
tracking the address range to be flushed and the granularity at which
the flushing is required.
This is hooked into the IOMMU API and its caller are updated to make use
of the new structure. Subsequent patches will plumb this into the IOMMU
drivers as well, but for now the gathering information is ignored.
Signed-off-by: Will Deacon <will@kernel.org>
|
|
In preparation for TLB flush gathering in the IOMMU API, rename the
iommu_gather_ops structure in io-pgtable to iommu_flush_ops, which
better describes its purpose and avoids the potential for confusion
between different levels of the API.
$ find linux/ -type f -name '*.[ch]' | xargs sed -i 's/gather_ops/flush_ops/g'
Signed-off-by: Will Deacon <will@kernel.org>
|
|
Commit b6b65ca20bc9 ("iommu/io-pgtable-arm: Add support for non-strict
mode") added an unconditional call to io_pgtable_tlb_sync() immediately
after the case where we replace a block entry with a table entry during
an unmap() call. This is redundant, since the IOMMU API will call
iommu_tlb_sync() on this path and the patch in question mentions this:
| To save having to reason about it too much, make sure the invalidation
| in arm_lpae_split_blk_unmap() just performs its own unconditional sync
| to minimise the window in which we're technically violating the break-
| before-make requirement on a live mapping. This might work out redundant
| with an outer-level sync for strict unmaps, but we'll never be splitting
| blocks on a DMA fastpath anyway.
However, this sync gets in the way of deferred TLB invalidation for leaf
entries and is at best a questionable, unproven hack. Remove it.
Signed-off-by: Will Deacon <will@kernel.org>
|
|
Commit add02cfdc9bc ("iommu: Introduce Interface for IOMMU TLB Flushing")
added three new TLB flushing operations to the IOMMU API so that the
underlying driver operations can be batched when unmapping large regions
of IO virtual address space.
However, the ->iotlb_range_add() callback has not been implemented by
any IOMMU drivers (amd_iommu.c implements it as an empty function, which
incurs the overhead of an indirect branch). Instead, drivers either flush
the entire IOTLB in the ->iotlb_sync() callback or perform the necessary
invalidation during ->unmap().
Attempting to implement ->iotlb_range_add() for arm-smmu-v3.c revealed
two major issues:
1. The page size used to map the region in the page-table is not known,
and so it is not generally possible to issue TLB flushes in the most
efficient manner.
2. The only mutable state passed to the callback is a pointer to the
iommu_domain, which can be accessed concurrently and therefore
requires expensive synchronisation to keep track of the outstanding
flushes.
Remove the callback entirely in preparation for extending ->unmap() and
->iotlb_sync() to update a token on the caller's stack.
Signed-off-by: Will Deacon <will@kernel.org>
|
|
|
|
The commit b3aa14f02254 ("iommu: remove the mapping_error dma_map_ops
method") incorrectly changed the checking from dma_ops_alloc_iova() in
map_sg() causes a crash under memory pressure as dma_ops_alloc_iova()
never return DMA_MAPPING_ERROR on failure but 0, so the error handling
is all wrong.
kernel BUG at drivers/iommu/iova.c:801!
Workqueue: kblockd blk_mq_run_work_fn
RIP: 0010:iova_magazine_free_pfns+0x7d/0xc0
Call Trace:
free_cpu_cached_iovas+0xbd/0x150
alloc_iova_fast+0x8c/0xba
dma_ops_alloc_iova.isra.6+0x65/0xa0
map_sg+0x8c/0x2a0
scsi_dma_map+0xc6/0x160
pqi_aio_submit_io+0x1f6/0x440 [smartpqi]
pqi_scsi_queue_command+0x90c/0xdd0 [smartpqi]
scsi_queue_rq+0x79c/0x1200
blk_mq_dispatch_rq_list+0x4dc/0xb70
blk_mq_sched_dispatch_requests+0x249/0x310
__blk_mq_run_hw_queue+0x128/0x200
blk_mq_run_work_fn+0x27/0x30
process_one_work+0x522/0xa10
worker_thread+0x63/0x5b0
kthread+0x1d2/0x1f0
ret_from_fork+0x22/0x40
Fixes: b3aa14f02254 ("iommu: remove the mapping_error dma_map_ops method")
Signed-off-by: Qian Cai <cai@lca.pw>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
The hexagon implementation pte_alloc_one(), pte_alloc_one_kernel(),
pte_free_kernel() and pte_free() is identical to the generic except of
lack of __GFP_ACCOUNT for the user PTEs allocation.
Switch hexagon to use generic version of these functions.
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
|
|
Now that examples are validated against the DT schema, an error with
required 'clocks' property missing is exposed:
Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.example.dt.yaml: \
pinctrl@40020000: gpio@0: 'clocks' is a required property
Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.example.dt.yaml: \
pinctrl@50020000: gpio@1000: 'clocks' is a required property
Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.example.dt.yaml: \
pinctrl@50020000: gpio@2000: 'clocks' is a required property
Add the missing 'clocks' properties to the examples to fix the errors.
Fixes: 2c9239c125f0 ("dt-bindings: pinctrl: Convert stm32 pinctrl bindings to json-schema")
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>
Cc: linux-gpio@vger.kernel.org
Cc: linux-stm32@st-md-mailman.stormreply.com
Acked-by: Alexandre TORGUE <alexandre.torgue@st.com>
Signed-off-by: Rob Herring <robh@kernel.org>
|
|
With the conversion to DT schema, the examples are now compiled with
dtc. The ad7124 binding example has the following warning:
Documentation/devicetree/bindings/iio/adc/adi,ad7124.example.dts:19.11-21: \
Warning (reg_format): /example-0/adc@0:reg: property has invalid length (4 bytes) (#address-cells == 1, #size-cells == 1)
There's a default #size-cells and #address-cells values of 1 for
examples. For examples needing different values such as this one on a
SPI bus, they need to provide a SPI bus parent node.
Fixes: 26ae15e62d3c ("Convert AD7124 bindings documentation to YAML format.")
Cc: Jonathan Cameron <jic23@kernel.org>
Cc: linux-iio@vger.kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
|
|
Now that examples are validated against the DT schema, a typo in
avia-hx711 example generates a warning:
Documentation/devicetree/bindings/iio/adc/avia-hx711.example.dt.yaml: weight: 'avdd-supply' is a required property
Fix the typo.
Fixes: 5150ec3fe125 ("avia-hx711.yaml: transform DT binding to YAML")
Cc: Andreas Klinger <ak@it-klinger.de>
Cc: Jonathan Cameron <jic23@kernel.org>
Cc: linux-iio@vger.kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
|
|
The schema examples are now validated against the schema itself. The
AST2500 pinctrl schema has a couple of errors:
Documentation/devicetree/bindings/pinctrl/aspeed,ast2500-pinctrl.example.dt.yaml: \
example-0: $nodename:0: 'example-0' does not match '^(bus|soc|axi|ahb|apb)(@[0-9a-f]+)?$'
Documentation/devicetree/bindings/pinctrl/aspeed,ast2500-pinctrl.example.dt.yaml: \
pinctrl: aspeed,external-nodes: [[1, 2]] is too short
Fixes: 0a617de16730 ("dt-bindings: pinctrl: aspeed: Convert AST2500 bindings to json-schema")
Cc: Andrew Jeffery <andrew@aj.id.au>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Joel Stanley <joel@jms.id.au>
Cc: linux-aspeed@lists.ozlabs.org
Cc: linux-gpio@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Acked-by: Andrew Jeffery <andrew@aj.id.au>
Signed-off-by: Rob Herring <robh@kernel.org>
|
|
The Aspeed pinctl schema have errors in the 'compatible' schema:
Documentation/devicetree/bindings/pinctrl/aspeed,ast2400-pinctrl.yaml: \
properties:compatible:enum: ['aspeed', 'ast2400-pinctrl', 'aspeed', 'g4-pinctrl'] has non-unique elements
Documentation/devicetree/bindings/pinctrl/aspeed,ast2500-pinctrl.yaml: \
properties:compatible:enum: ['aspeed', 'ast2500-pinctrl', 'aspeed', 'g5-pinctrl'] has non-unique elements
Flow style sequences have to be quoted if the vales contain ','. Fix
this by using the more common one line per entry formatting.
Fixes: 0a617de16730 ("dt-bindings: pinctrl: aspeed: Convert AST2500 bindings to json-schema")
Fixes: 07457937bb5c ("dt-bindings: pinctrl: aspeed: Convert AST2400 bindings to json-schema")
Cc: Andrew Jeffery <andrew@aj.id.au>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Joel Stanley <joel@jms.id.au>
Cc: linux-aspeed@lists.ozlabs.org
Cc: linux-gpio@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Acked-by: Andrew Jeffery <andrew@aj.id.au>
Signed-off-by: Rob Herring <robh@kernel.org>
|
|
Matching on the 'cpus' node was a bad choice because the schema is
incorrectly applied to non-RiscV cpus nodes. As we now have a common cpus
schema which checks the general structure, it is also redundant to do so
in the Risc-V CPU schema.
The downside is one could conceivably mix different architecture's cpu
nodes or have typos in the compatible string. The latter problem pretty
much exists for every schema.
Acked-by: Paul Walmsley <paul.walmsley@sifive.com>
Signed-off-by: Rob Herring <robh@kernel.org>
|
|
Properties which are child node definitions need to have an explict
type. Otherwise, a matching (DT) property can silently match when an
error is desired. Fix this up tree-wide. Once this is fixed, the
meta-schema will enforce this on any child node definitions.
Cc: Chen-Yu Tsai <wens@csie.org>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Brian Norris <computersforpeace@gmail.com>
Cc: Marek Vasut <marek.vasut@gmail.com>
Cc: Richard Weinberger <richard@nod.at>
Cc: Vignesh Raghavendra <vigneshr@ti.com>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>
Cc: linux-mtd@lists.infradead.org
Cc: linux-gpio@vger.kernel.org
Cc: linux-stm32@st-md-mailman.stormreply.com
Cc: linux-spi@vger.kernel.org
Acked-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Maxime Ripard <maxime.ripard@bootlin.com>
Acked-by: Mark Brown <broonie@kernel.org>
Acked-by: Alexandre TORGUE <alexandre.torgue@st.com>
Signed-off-by: Rob Herring <robh@kernel.org>
|
|
The recent fix for CR2 corruption introduced a new way to reliably corrupt
the saved CR2 value.
CR2 is saved early in the entry code in RDX, which is the third argument to
the fault handling functions. But it missed that between saving and
invoking the fault handler enter_from_user_mode() can be called. RDX is a
caller saved register so the invoked function can freely clobber it with
the obvious consequences.
The TRACE_IRQS_OFF call is safe as it calls through the thunk which
preserves RDX, but TRACE_IRQS_OFF_DEBUG is not because it also calls into
C-code outside of the thunk.
Store CR2 in R12 instead which is a callee saved register and move R12 to
RDX just before calling the fault handler.
Fixes: a0d14b8909de ("x86/mm, tracing: Fix CR2 corruption")
Reported-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1907201020540.1782@nanos.tec.linutronix.de
|
|
It's clearly documented that smp function calls cannot be invoked from
softirq handling context. Unfortunately nothing enforces that or emits a
warning.
A single function call can be invoked from softirq context only via
smp_call_function_single_async().
The only legit context is task context, so add a warning to that effect.
Reported-by: luferry <luferry@163.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20190718160601.GP3402@hirez.programming.kicks-ass.net
|
|
Updates KVM_CAP_PMU_EVENT_FILTER so it can also whitelist or blacklist
fixed counters.
Signed-off-by: Eric Hankland <ehankland@google.com>
[No need to check padding fields for zero. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
If a KVM guest is reset while running a nested guest, free_nested will
disable the shadow VMCS execution control in the vmcs01. However,
on the next KVM_RUN vmx_vcpu_run would nevertheless try to sync
the VMCS12 to the shadow VMCS which has since been freed.
This causes a vmptrld of a NULL pointer on my machime, but Jan reports
the host to hang altogether. Let's see how much this trivial patch fixes.
Reported-by: Jan Kiszka <jan.kiszka@siemens.com>
Cc: Liran Alon <liran.alon@oracle.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
This is useful for debugging, and is ratelimited nowadays.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
If a perf_event creation fails due to any reason of the host perf
subsystem, it has no chance to log the corresponding event for guest
which may cause abnormal sampling data in guest result. In debug mode,
this message helps to understand the state of vPMC and we may not
limit the number of occurrences but not in a spamming style.
Suggested-by: Joe Perches <joe@perches.com>
Signed-off-by: Like Xu <like.xu@linux.intel.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Use kvm_vcpu_wake_up() in kvm_s390_vcpu_wakeup().
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Inspired by commit 9cac38dd5d (KVM/s390: Set preempted flag during
vcpu wakeup and interrupt delivery), we want to also boost not just
lock holders but also vCPUs that are delivering interrupts. Most
smp_call_function_many calls are synchronous, so the IPI target vCPUs
are also good yield candidates. This patch introduces vcpu->ready to
boost vCPUs during wakeup and interrupt delivery time; unlike s390 we do
not reuse vcpu->preempted so that voluntarily preempted vCPUs are taken
into account by kvm_vcpu_on_spin, but vmx_vcpu_pi_put is not affected
(VT-d PI handles voluntary preemption separately, in pi_pre_block).
Testing on 80 HT 2 socket Xeon Skylake server, with 80 vCPUs VM 80GB RAM:
ebizzy -M
vanilla boosting improved
1VM 21443 23520 9%
2VM 2800 8000 180%
3VM 1800 3100 72%
Testing on my Haswell desktop 8 HT, with 8 vCPUs VM 8GB RAM, two VMs,
one running ebizzy -M, the other running 'stress --cpu 2':
w/ boosting + w/o pv sched yield(vanilla)
vanilla boosting improved
1570 4000 155%
w/ boosting + w/ pv sched yield(vanilla)
vanilla boosting improved
1844 5157 179%
w/o boosting, perf top in VM:
72.33% [kernel] [k] smp_call_function_many
4.22% [kernel] [k] call_function_i
3.71% [kernel] [k] async_page_fault
w/ boosting, perf top in VM:
38.43% [kernel] [k] smp_call_function_many
6.31% [kernel] [k] async_page_fault
6.13% libc-2.23.so [.] __memcpy_avx_unaligned
4.88% [kernel] [k] call_function_interrupt
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Marc Zyngier <maz@kernel.org>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
The code in vmx.c does not use "program_invocation_name", so there
is no need to "#define _GNU_SOURCE" here.
Signed-off-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
When CPU raise #NPF on guest data access and guest CR4.SMAP=1, it is
possible that CPU microcode implementing DecodeAssist will fail
to read bytes of instruction which caused #NPF. This is AMD errata
1096 and it happens because CPU microcode reading instruction bytes
incorrectly attempts to read code as implicit supervisor-mode data
accesses (that is, just like it would read e.g. a TSS), which are
susceptible to SMAP faults. The microcode reads CS:RIP and if it is
a user-mode address according to the page tables, the processor
gives up and returns no instruction bytes. In this case,
GuestIntrBytes field of the VMCB on a VMEXIT will incorrectly
return 0 instead of the correct guest instruction bytes.
Current KVM code attemps to detect and workaround this errata, but it
has multiple issues:
1) It mistakenly checks if guest CR4.SMAP=0 instead of guest CR4.SMAP=1,
which is required for encountering a SMAP fault.
2) It assumes SMAP faults can only occur when guest CPL==3.
However, in case guest CR4.SMEP=0, the guest can execute an instruction
which reside in a user-accessible page with CPL<3 priviledge. If this
instruction raise a #NPF on it's data access, then CPU DecodeAssist
microcode will still encounter a SMAP violation. Even though no sane
OS will do so (as it's an obvious priviledge escalation vulnerability),
we still need to handle this semanticly correct in KVM side.
Note that (2) *is* a useful optimization, because CR4.SMAP=1 is an easy
triggerable condition and guests usually enable SMAP together with SMEP.
If the vCPU has CR4.SMEP=1, the errata could indeed be encountered onlt
at guest CPL==3; otherwise, the CPU would raise a SMEP fault to guest
instead of #NPF. We keep this condition to avoid false positives in
the detection of the errata.
In addition, to avoid future confusion and improve code readbility,
include details of the errata in code and not just in commit message.
Fixes: 05d5a4863525 ("KVM: SVM: Workaround errata#1096 (insn_len maybe zero on SMAP violation)")
Cc: Singh Brijesh <brijesh.singh@amd.com>
Cc: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Liran Alon <liran.alon@oracle.com>
Reviewed-by: Brijesh Singh <brijesh.singh@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Dedicated instances are currently disturbed by unnecessary jitter due
to the emulated lapic timers firing on the same pCPUs where the
vCPUs reside. There is no hardware virtual timer on Intel for guest
like ARM, so both programming timer in guest and the emulated timer fires
incur vmexits. This patch tries to avoid vmexit when the emulated timer
fires, at least in dedicated instance scenario when nohz_full is enabled.
In that case, the emulated timers can be offload to the nearest busy
housekeeping cpus since APICv has been found for several years in server
processors. The guest timer interrupt can then be injected via posted interrupts,
which are delivered by the housekeeping cpu once the emulated timer fires.
The host should tuned so that vCPUs are placed on isolated physical
processors, and with several pCPUs surplus for busy housekeeping.
If disabled mwait/hlt/pause vmexits keep the vCPUs in non-root mode,
~3% redis performance benefit can be observed on Skylake server, and the
number of external interrupt vmexits drops substantially. Without patch
VM-EXIT Samples Samples% Time% Min Time Max Time Avg time
EXTERNAL_INTERRUPT 42916 49.43% 39.30% 0.47us 106.09us 0.71us ( +- 1.09% )
While with patch:
VM-EXIT Samples Samples% Time% Min Time Max Time Avg time
EXTERNAL_INTERRUPT 6871 9.29% 2.96% 0.44us 57.88us 0.72us ( +- 4.02% )
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
The gcc -fcf-protection=branch option is not compatible with
-mindirect-branch=thunk-extern. The latter is used when
CONFIG_RETPOLINE is selected, and this will fail to build with
a gcc which has -fcf-protection=branch enabled by default. Adding
-fcf-protection=none when building with retpoline enabled
prevents such build failures.
Signed-off-by: Seth Forshee <seth.forshee@canonical.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
|
|
- Some headers graduated from the blacklist
- hyperv_timer.h joined the header-test when CONFIG_X86=y
- nf_tables*.h joined the header-test when CONFIG_NF_TABLES is
enabled.
- The entry for nf_tables_offload.h was added to fix build error for
the combination of CONFIG_NF_TABLES=n and CONFIG_KERNEL_HEADER_TEST=y.
- The entry for iomap.h was added because this header is supposed to
be included only when CONFIG_BLOCK=y
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
|
|
This fell into disrepair a while ago, and the majority of hits to the
snapshots were from bots, so it's more trouble to keep running than it's worth.
Signed-off-by: Dave Jones <davej@codemonkey.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
Commit c5c27a0a5838 ("x86/stacktrace: Remove the pointless ULONG_MAX
marker") removes ULONG_MAX marker from user stack trace entries but
trace_user_stack_print() still uses the marker and it outputs unnecessary
"??".
For example:
less-1911 [001] d..2 34.758944: <user stack trace>
=> <00007f16f2295910>
=> ??
=> ??
=> ??
=> ??
=> ??
=> ??
=> ??
The user stack trace code zeroes the storage before saving the stack, so if
the trace is shorter than the maximum number of entries it can terminate
the print loop if a zero entry is detected.
Link: http://lkml.kernel.org/r/20190630085438.25545-1-devel@etsukata.com
Cc: stable@vger.kernel.org
Fixes: 4285f2fcef80 ("tracing: Remove the ULONG_MAX stack trace hackery")
Signed-off-by: Eiichi Tsukata <devel@etsukata.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
dma_map_sg() may use swiotlb buffer when the kernel command line includes
"swiotlb=force" or the dma_addr is out of dev->dma_mask range. After
DMA complete the memory moving from device to memory, then user call
dma_sync_sg_for_cpu() to sync with DMA buffer, and copy the original
virtual buffer to other space.
So dma_direct_sync_sg_for_cpu() should use swiotlb physical addr, not
the original physical addr from sg_phys(sg).
dma_direct_sync_sg_for_device() also has the same issue, correct it as
well.
Fixes: 55897af63091("dma-direct: merge swiotlb_dma_ops into the dma_direct code")
Signed-off-by: Fugang Duan <fugang.duan@nxp.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
|
Will Deacon
Linus Torvalds
Qian Cai
Mike Rapoport
Al Viro
Rob Herring
Thomas Gleixner
Peter Zijlstra
Eric Hankland
Paolo Bonzini
Like Xu
Wanpeng Li
Thomas Huth
Liran Alon
Seth Forshee
Masahiro Yamada
Dave Jones
Eiichi Tsukata
Fugang Duan