mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-12-29 17:25:38 +00:00
Merge 'origin/master' into perf-tools-next
To get the fixes in the perf-tools branch. Resolved a conflict due to RISC-V's syscall table change. Signed-off-by: Namhyung Kim <namhyung@kernel.org>
This commit is contained in:
Namhyung Kim
commit
aa5c90601b
12
.mailmap
12
.mailmap
@ -73,6 +73,8 @@ Andrey Ryabinin <ryabinin.a.a@gmail.com> <aryabinin@virtuozzo.com>
|
||||
Andrzej Hajda <andrzej.hajda@intel.com> <a.hajda@samsung.com>
|
||||
André Almeida <andrealmeid@igalia.com> <andrealmeid@collabora.com>
|
||||
Andy Adamson <andros@citi.umich.edu>
|
||||
Andy Chiu <andybnac@gmail.com> <andy.chiu@sifive.com>
|
||||
Andy Chiu <andybnac@gmail.com> <taochiu@synology.com>
|
||||
Andy Shevchenko <andy@kernel.org> <andy@smile.org.ua>
|
||||
Andy Shevchenko <andy@kernel.org> <ext-andriy.shevchenko@nokia.com>
|
||||
Anilkumar Kolli <quic_akolli@quicinc.com> <akolli@codeaurora.org>
|
||||
@ -197,7 +199,8 @@ Elliot Berman <quic_eberman@quicinc.com> <eberman@codeaurora.org>
|
||||
Enric Balletbo i Serra <eballetbo@kernel.org> <enric.balletbo@collabora.com>
|
||||
Enric Balletbo i Serra <eballetbo@kernel.org> <eballetbo@iseebcn.com>
|
||||
Erik Kaneda <erik.kaneda@intel.com> <erik.schmauss@intel.com>
|
||||
Eugen Hristev <eugen.hristev@collabora.com> <eugen.hristev@microchip.com>
|
||||
Eugen Hristev <eugen.hristev@linaro.org> <eugen.hristev@microchip.com>
|
||||
Eugen Hristev <eugen.hristev@linaro.org> <eugen.hristev@collabora.com>
|
||||
Evgeniy Polyakov <johnpol@2ka.mipt.ru>
|
||||
Ezequiel Garcia <ezequiel@vanguardiasur.com.ar> <ezequiel@collabora.com>
|
||||
Faith Ekstrand <faith.ekstrand@collabora.com> <jason@jlekstrand.net>
|
||||
@ -280,7 +283,7 @@ Jan Glauber <jan.glauber@gmail.com> <jglauber@cavium.com>
|
||||
Jan Kuliga <jtkuliga.kdev@gmail.com> <jankul@alatek.krakow.pl>
|
||||
Jarkko Sakkinen <jarkko@kernel.org> <jarkko.sakkinen@linux.intel.com>
|
||||
Jarkko Sakkinen <jarkko@kernel.org> <jarkko@profian.com>
|
||||
Jarkko Sakkinen <jarkko@kernel.org> <jarkko.sakkinen@tuni.fi>
|
||||
Jarkko Sakkinen <jarkko@kernel.org> <jarkko.sakkinen@parity.io>
|
||||
Jason Gunthorpe <jgg@ziepe.ca> <jgg@mellanox.com>
|
||||
Jason Gunthorpe <jgg@ziepe.ca> <jgg@nvidia.com>
|
||||
Jason Gunthorpe <jgg@ziepe.ca> <jgunthorpe@obsidianresearch.com>
|
||||
@ -304,6 +307,11 @@ Jens Axboe <axboe@kernel.dk> <axboe@fb.com>
|
||||
Jens Axboe <axboe@kernel.dk> <axboe@meta.com>
|
||||
Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
|
||||
Jernej Skrabec <jernej.skrabec@gmail.com> <jernej.skrabec@siol.net>
|
||||
Jesper Dangaard Brouer <hawk@kernel.org> <brouer@redhat.com>
|
||||
Jesper Dangaard Brouer <hawk@kernel.org> <hawk@comx.dk>
|
||||
Jesper Dangaard Brouer <hawk@kernel.org> <jbrouer@redhat.com>
|
||||
Jesper Dangaard Brouer <hawk@kernel.org> <jdb@comx.dk>
|
||||
Jesper Dangaard Brouer <hawk@kernel.org> <netoptimizer@brouer.com>
|
||||
Jessica Zhang <quic_jesszhan@quicinc.com> <jesszhan@codeaurora.org>
|
||||
Jilai Wang <quic_jilaiw@quicinc.com> <jilaiw@codeaurora.org>
|
||||
Jiri Kosina <jikos@kernel.org> <jikos@jikos.cz>
|
||||
|
||||
@ -223,7 +223,10 @@ are signed through the PKCS#7 message format to enforce some level of
|
||||
authorization of the policies (prohibiting an attacker from gaining
|
||||
unconstrained root, and deploying an "allow all" policy). These
|
||||
policies must be signed by a certificate that chains to the
|
||||
``SYSTEM_TRUSTED_KEYRING``. With openssl, the policy can be signed by::
|
||||
``SYSTEM_TRUSTED_KEYRING``, or to the secondary and/or platform keyrings if
|
||||
``CONFIG_IPE_POLICY_SIG_SECONDARY_KEYRING`` and/or
|
||||
``CONFIG_IPE_POLICY_SIG_PLATFORM_KEYRING`` are enabled, respectively.
|
||||
With openssl, the policy can be signed by::
|
||||
|
||||
openssl smime -sign \
|
||||
-in "$MY_POLICY" \
|
||||
@ -266,7 +269,7 @@ in the kernel. This file is write-only and accepts a PKCS#7 signed
|
||||
policy. Two checks will always be performed on this policy: First, the
|
||||
``policy_names`` must match with the updated version and the existing
|
||||
version. Second the updated policy must have a policy version greater than
|
||||
or equal to the currently-running version. This is to prevent rollback attacks.
|
||||
the currently-running version. This is to prevent rollback attacks.
|
||||
|
||||
The ``delete`` file is used to remove a policy that is no longer needed.
|
||||
This file is write-only and accepts a value of ``1`` to delete the policy.
|
||||
|
||||
@ -425,8 +425,8 @@ This governor exposes only one tunable:
|
||||
|
||||
``rate_limit_us``
|
||||
Minimum time (in microseconds) that has to pass between two consecutive
|
||||
runs of governor computations (default: 1000 times the scaling driver's
|
||||
transition latency).
|
||||
runs of governor computations (default: 1.5 times the scaling driver's
|
||||
transition latency or the maximum 2ms).
|
||||
|
||||
The purpose of this tunable is to reduce the scheduler context overhead
|
||||
of the governor which might be excessive without it.
|
||||
@ -474,17 +474,17 @@ This governor exposes the following tunables:
|
||||
This is how often the governor's worker routine should run, in
|
||||
microseconds.
|
||||
|
||||
Typically, it is set to values of the order of 10000 (10 ms). Its
|
||||
default value is equal to the value of ``cpuinfo_transition_latency``
|
||||
for each policy this governor is attached to (but since the unit here
|
||||
is greater by 1000, this means that the time represented by
|
||||
``sampling_rate`` is 1000 times greater than the transition latency by
|
||||
default).
|
||||
Typically, it is set to values of the order of 2000 (2 ms). Its
|
||||
default value is to add a 50% breathing room
|
||||
to ``cpuinfo_transition_latency`` on each policy this governor is
|
||||
attached to. The minimum is typically the length of two scheduler
|
||||
ticks.
|
||||
|
||||
If this tunable is per-policy, the following shell command sets the time
|
||||
represented by it to be 750 times as high as the transition latency::
|
||||
represented by it to be 1.5 times as high as the transition latency
|
||||
(the default)::
|
||||
|
||||
# echo `$(($(cat cpuinfo_transition_latency) * 750 / 1000)) > ondemand/sampling_rate
|
||||
# echo `$(($(cat cpuinfo_transition_latency) * 3 / 2)) > ondemand/sampling_rate
|
||||
|
||||
``up_threshold``
|
||||
If the estimated CPU load is above this value (in percent), the governor
|
||||
|
||||
@ -12,7 +12,10 @@ Pkeys Userspace (PKU) is a feature which can be found on:
|
||||
* Intel server CPUs, Skylake and later
|
||||
* Intel client CPUs, Tiger Lake (11th Gen Core) and later
|
||||
* Future AMD CPUs
|
||||
* arm64 CPUs implementing the Permission Overlay Extension (FEAT_S1POE)
|
||||
|
||||
x86_64
|
||||
======
|
||||
Pkeys work by dedicating 4 previously Reserved bits in each page table entry to
|
||||
a "protection key", giving 16 possible keys.
|
||||
|
||||
@ -28,6 +31,22 @@ register. The feature is only available in 64-bit mode, even though there is
|
||||
theoretically space in the PAE PTEs. These permissions are enforced on data
|
||||
access only and have no effect on instruction fetches.
|
||||
|
||||
arm64
|
||||
=====
|
||||
|
||||
Pkeys use 3 bits in each page table entry, to encode a "protection key index",
|
||||
giving 8 possible keys.
|
||||
|
||||
Protections for each key are defined with a per-CPU user-writable system
|
||||
register (POR_EL0). This is a 64-bit register encoding read, write and execute
|
||||
overlay permissions for each protection key index.
|
||||
|
||||
Being a CPU register, POR_EL0 is inherently thread-local, potentially giving
|
||||
each thread a different set of protections from every other thread.
|
||||
|
||||
Unlike x86_64, the protection key permissions also apply to instruction
|
||||
fetches.
|
||||
|
||||
Syscalls
|
||||
========
|
||||
|
||||
@ -38,11 +57,10 @@ There are 3 system calls which directly interact with pkeys::
|
||||
int pkey_mprotect(unsigned long start, size_t len,
|
||||
unsigned long prot, int pkey);
|
||||
|
||||
Before a pkey can be used, it must first be allocated with
|
||||
pkey_alloc(). An application calls the WRPKRU instruction
|
||||
directly in order to change access permissions to memory covered
|
||||
with a key. In this example WRPKRU is wrapped by a C function
|
||||
called pkey_set().
|
||||
Before a pkey can be used, it must first be allocated with pkey_alloc(). An
|
||||
application writes to the architecture specific CPU register directly in order
|
||||
to change access permissions to memory covered with a key. In this example
|
||||
this is wrapped by a C function called pkey_set().
|
||||
::
|
||||
|
||||
int real_prot = PROT_READ|PROT_WRITE;
|
||||
@ -64,9 +82,9 @@ is no longer in use::
|
||||
munmap(ptr, PAGE_SIZE);
|
||||
pkey_free(pkey);
|
||||
|
||||
.. note:: pkey_set() is a wrapper for the RDPKRU and WRPKRU instructions.
|
||||
An example implementation can be found in
|
||||
tools/testing/selftests/x86/protection_keys.c.
|
||||
.. note:: pkey_set() is a wrapper around writing to the CPU register.
|
||||
Example implementations can be found in
|
||||
tools/testing/selftests/mm/pkey-{arm64,powerpc,x86}.h
|
||||
|
||||
Behavior
|
||||
========
|
||||
@ -96,3 +114,7 @@ with a read()::
|
||||
The kernel will send a SIGSEGV in both cases, but si_code will be set
|
||||
to SEGV_PKERR when violating protection keys versus SEGV_ACCERR when
|
||||
the plain mprotect() permissions are violated.
|
||||
|
||||
Note that kernel accesses from a kthread (such as io_uring) will use a default
|
||||
value for the protection key register and so will not be consistent with
|
||||
userspace's value of the register or mprotect().
|
||||
|
||||
@ -63,6 +63,16 @@ properties:
|
||||
- const: sleep
|
||||
|
||||
power-domains:
|
||||
description: |
|
||||
The MediaTek DPI module is typically associated with one of the
|
||||
following multimedia power domains:
|
||||
POWER_DOMAIN_DISPLAY
|
||||
POWER_DOMAIN_VDOSYS
|
||||
POWER_DOMAIN_MM
|
||||
The specific power domain used varies depending on the SoC design.
|
||||
|
||||
It is recommended to explicitly add the appropriate power domain
|
||||
property to the DPI node in the device tree.
|
||||
maxItems: 1
|
||||
|
||||
port:
|
||||
@ -79,20 +89,6 @@ required:
|
||||
- clock-names
|
||||
- port
|
||||
|
||||
allOf:
|
||||
- if:
|
||||
not:
|
||||
properties:
|
||||
compatible:
|
||||
contains:
|
||||
enum:
|
||||
- mediatek,mt6795-dpi
|
||||
- mediatek,mt8173-dpi
|
||||
- mediatek,mt8186-dpi
|
||||
then:
|
||||
properties:
|
||||
power-domains: false
|
||||
|
||||
additionalProperties: false
|
||||
|
||||
examples:
|
||||
|
||||
@ -38,6 +38,7 @@ properties:
|
||||
description: A phandle and PM domain specifier as defined by bindings of
|
||||
the power controller specified by phandle. See
|
||||
Documentation/devicetree/bindings/power/power-domain.yaml for details.
|
||||
maxItems: 1
|
||||
|
||||
mediatek,gce-client-reg:
|
||||
description:
|
||||
@ -57,6 +58,9 @@ properties:
|
||||
clocks:
|
||||
items:
|
||||
- description: SPLIT Clock
|
||||
- description: Used for interfacing with the HDMI RX signal source.
|
||||
- description: Paired with receiving HDMI RX metadata.
|
||||
minItems: 1
|
||||
|
||||
required:
|
||||
- compatible
|
||||
@ -72,9 +76,24 @@ allOf:
|
||||
const: mediatek,mt8195-mdp3-split
|
||||
|
||||
then:
|
||||
properties:
|
||||
clocks:
|
||||
minItems: 3
|
||||
|
||||
required:
|
||||
- mediatek,gce-client-reg
|
||||
|
||||
- if:
|
||||
properties:
|
||||
compatible:
|
||||
contains:
|
||||
const: mediatek,mt8173-disp-split
|
||||
|
||||
then:
|
||||
properties:
|
||||
clocks:
|
||||
maxItems: 1
|
||||
|
||||
additionalProperties: false
|
||||
|
||||
examples:
|
||||
|
||||
@ -67,6 +67,10 @@ properties:
|
||||
A 2.5V to 3.3V supply for the external reference voltage. When omitted,
|
||||
the internal 2.5V reference is used.
|
||||
|
||||
refin-supply:
|
||||
description:
|
||||
A 2.5V to 3.3V supply for external reference voltage, for ad7380-4 only.
|
||||
|
||||
aina-supply:
|
||||
description:
|
||||
The common mode voltage supply for the AINA- pin on pseudo-differential
|
||||
@ -135,6 +139,23 @@ allOf:
|
||||
ainc-supply: false
|
||||
aind-supply: false
|
||||
|
||||
# ad7380-4 uses refin-supply as external reference.
|
||||
# All other chips from ad738x family use refio as optional external reference.
|
||||
# When refio-supply is omitted, internal reference is used.
|
||||
- if:
|
||||
properties:
|
||||
compatible:
|
||||
enum:
|
||||
- adi,ad7380-4
|
||||
then:
|
||||
properties:
|
||||
refio-supply: false
|
||||
required:
|
||||
- refin-supply
|
||||
else:
|
||||
properties:
|
||||
refin-supply: false
|
||||
|
||||
examples:
|
||||
- |
|
||||
#include <dt-bindings/interrupt-controller/irq.h>
|
||||
|
||||
@ -4,7 +4,7 @@
|
||||
$id: http://devicetree.org/schemas/iio/dac/adi,ad5686.yaml#
|
||||
$schema: http://devicetree.org/meta-schemas/core.yaml#
|
||||
|
||||
title: Analog Devices AD5360 and similar DACs
|
||||
title: Analog Devices AD5360 and similar SPI DACs
|
||||
|
||||
maintainers:
|
||||
- Michael Hennerich <michael.hennerich@analog.com>
|
||||
@ -12,41 +12,22 @@ maintainers:
|
||||
|
||||
properties:
|
||||
compatible:
|
||||
oneOf:
|
||||
- description: SPI devices
|
||||
enum:
|
||||
- adi,ad5310r
|
||||
- adi,ad5672r
|
||||
- adi,ad5674r
|
||||
- adi,ad5676
|
||||
- adi,ad5676r
|
||||
- adi,ad5679r
|
||||
- adi,ad5681r
|
||||
- adi,ad5682r
|
||||
- adi,ad5683
|
||||
- adi,ad5683r
|
||||
- adi,ad5684
|
||||
- adi,ad5684r
|
||||
- adi,ad5685r
|
||||
- adi,ad5686
|
||||
- adi,ad5686r
|
||||
- description: I2C devices
|
||||
enum:
|
||||
- adi,ad5311r
|
||||
- adi,ad5337r
|
||||
- adi,ad5338r
|
||||
- adi,ad5671r
|
||||
- adi,ad5675r
|
||||
- adi,ad5691r
|
||||
- adi,ad5692r
|
||||
- adi,ad5693
|
||||
- adi,ad5693r
|
||||
- adi,ad5694
|
||||
- adi,ad5694r
|
||||
- adi,ad5695r
|
||||
- adi,ad5696
|
||||
- adi,ad5696r
|
||||
|
||||
enum:
|
||||
- adi,ad5310r
|
||||
- adi,ad5672r
|
||||
- adi,ad5674r
|
||||
- adi,ad5676
|
||||
- adi,ad5676r
|
||||
- adi,ad5679r
|
||||
- adi,ad5681r
|
||||
- adi,ad5682r
|
||||
- adi,ad5683
|
||||
- adi,ad5683r
|
||||
- adi,ad5684
|
||||
- adi,ad5684r
|
||||
- adi,ad5685r
|
||||
- adi,ad5686
|
||||
- adi,ad5686r
|
||||
|
||||
reg:
|
||||
maxItems: 1
|
||||
|
||||
@ -4,7 +4,7 @@
|
||||
$id: http://devicetree.org/schemas/iio/dac/adi,ad5696.yaml#
|
||||
$schema: http://devicetree.org/meta-schemas/core.yaml#
|
||||
|
||||
title: Analog Devices AD5696 and similar multi-channel DACs
|
||||
title: Analog Devices AD5696 and similar I2C multi-channel DACs
|
||||
|
||||
maintainers:
|
||||
- Michael Auchter <michael.auchter@ni.com>
|
||||
@ -16,6 +16,7 @@ properties:
|
||||
compatible:
|
||||
enum:
|
||||
- adi,ad5311r
|
||||
- adi,ad5337r
|
||||
- adi,ad5338r
|
||||
- adi,ad5671r
|
||||
- adi,ad5675r
|
||||
|
||||
@ -26,6 +26,7 @@ properties:
|
||||
- brcm,asp-v2.1-mdio
|
||||
- brcm,asp-v2.2-mdio
|
||||
- brcm,unimac-mdio
|
||||
- brcm,bcm6846-mdio
|
||||
|
||||
reg:
|
||||
minItems: 1
|
||||
|
||||
@ -154,8 +154,6 @@ allOf:
|
||||
- qcom,sm8550-qmp-gen4x2-pcie-phy
|
||||
- qcom,sm8650-qmp-gen3x2-pcie-phy
|
||||
- qcom,sm8650-qmp-gen4x2-pcie-phy
|
||||
- qcom,x1e80100-qmp-gen3x2-pcie-phy
|
||||
- qcom,x1e80100-qmp-gen4x2-pcie-phy
|
||||
then:
|
||||
properties:
|
||||
clocks:
|
||||
@ -171,6 +169,8 @@ allOf:
|
||||
- qcom,sc8280xp-qmp-gen3x1-pcie-phy
|
||||
- qcom,sc8280xp-qmp-gen3x2-pcie-phy
|
||||
- qcom,sc8280xp-qmp-gen3x4-pcie-phy
|
||||
- qcom,x1e80100-qmp-gen3x2-pcie-phy
|
||||
- qcom,x1e80100-qmp-gen4x2-pcie-phy
|
||||
- qcom,x1e80100-qmp-gen4x4-pcie-phy
|
||||
then:
|
||||
properties:
|
||||
@ -201,6 +201,7 @@ allOf:
|
||||
- qcom,sm8550-qmp-gen4x2-pcie-phy
|
||||
- qcom,sm8650-qmp-gen4x2-pcie-phy
|
||||
- qcom,x1e80100-qmp-gen4x2-pcie-phy
|
||||
- qcom,x1e80100-qmp-gen4x4-pcie-phy
|
||||
then:
|
||||
properties:
|
||||
resets:
|
||||
|
||||
@ -102,21 +102,21 @@ properties:
|
||||
default: 2
|
||||
|
||||
interrupts:
|
||||
oneOf:
|
||||
- minItems: 1
|
||||
items:
|
||||
- description: TX interrupt
|
||||
- description: RX interrupt
|
||||
- items:
|
||||
- description: common/combined interrupt
|
||||
minItems: 1
|
||||
maxItems: 2
|
||||
|
||||
interrupt-names:
|
||||
oneOf:
|
||||
- minItems: 1
|
||||
- description: TX interrupt
|
||||
const: tx
|
||||
- description: RX interrupt
|
||||
const: rx
|
||||
- description: TX and RX interrupts
|
||||
items:
|
||||
- const: tx
|
||||
- const: rx
|
||||
- const: common
|
||||
- description: Common/combined interrupt
|
||||
const: common
|
||||
|
||||
fck_parent:
|
||||
$ref: /schemas/types.yaml#/definitions/string
|
||||
|
||||
@ -48,6 +48,10 @@ properties:
|
||||
- const: mclk_rx
|
||||
- const: hclk
|
||||
|
||||
port:
|
||||
$ref: audio-graph-port.yaml#
|
||||
unevaluatedProperties: false
|
||||
|
||||
resets:
|
||||
maxItems: 1
|
||||
|
||||
|
||||
@ -115,7 +115,7 @@ set up cache ready for use. The following script commands are available:
|
||||
|
||||
This mask can also be set through sysfs, eg::
|
||||
|
||||
echo 5 >/sys/modules/cachefiles/parameters/debug
|
||||
echo 5 > /sys/module/cachefiles/parameters/debug
|
||||
|
||||
|
||||
Starting the Cache
|
||||
|
||||
@ -208,7 +208,7 @@ The filesystem must arrange to `cancel
|
||||
such `reservations
|
||||
<https://lore.kernel.org/linux-xfs/20220817093627.GZ3600936@dread.disaster.area/>`_
|
||||
because writeback will not consume the reservation.
|
||||
The ``iomap_file_buffered_write_punch_delalloc`` can be called from a
|
||||
The ``iomap_write_delalloc_release`` can be called from a
|
||||
``->iomap_end`` function to find all the clean areas of the folios
|
||||
caching a fresh (``IOMAP_F_NEW``) delalloc mapping.
|
||||
It takes the ``invalidate_lock``.
|
||||
|
||||
@ -592,4 +592,3 @@ API Function Reference
|
||||
|
||||
.. kernel-doc:: include/linux/netfs.h
|
||||
.. kernel-doc:: fs/netfs/buffered_read.c
|
||||
.. kernel-doc:: fs/netfs/io.c
|
||||
|
||||
@ -41,13 +41,22 @@ supports only 1 SDO line.
|
||||
Reference voltage
|
||||
-----------------
|
||||
|
||||
2 possible reference voltage sources are supported:
|
||||
ad7380-4
|
||||
~~~~~~~~
|
||||
|
||||
ad7380-4 supports only an external reference voltage (2.5V to 3.3V). It must be
|
||||
declared in the device tree as ``refin-supply``.
|
||||
|
||||
All other devices from ad738x family
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
All other devices from ad738x support 2 possible reference voltage sources:
|
||||
|
||||
- Internal reference (2.5V)
|
||||
- External reference (2.5V to 3.3V)
|
||||
|
||||
The source is determined by the device tree. If ``refio-supply`` is present,
|
||||
then the external reference is used, else the internal reference is used.
|
||||
then it is used as external reference, else the internal reference is used.
|
||||
|
||||
Oversampling and resolution boost
|
||||
---------------------------------
|
||||
|
||||
@ -7,26 +7,26 @@ The DAMON subsystem covers the files that are listed in 'DATA ACCESS MONITOR'
|
||||
section of 'MAINTAINERS' file.
|
||||
|
||||
The mailing lists for the subsystem are damon@lists.linux.dev and
|
||||
linux-mm@kvack.org. Patches should be made against the mm-unstable `tree
|
||||
<https://git.kernel.org/akpm/mm/h/mm-unstable>` whenever possible and posted to
|
||||
the mailing lists.
|
||||
linux-mm@kvack.org. Patches should be made against the `mm-unstable tree
|
||||
<https://git.kernel.org/akpm/mm/h/mm-unstable>`_ whenever possible and posted
|
||||
to the mailing lists.
|
||||
|
||||
SCM Trees
|
||||
---------
|
||||
|
||||
There are multiple Linux trees for DAMON development. Patches under
|
||||
development or testing are queued in `damon/next
|
||||
<https://git.kernel.org/sj/h/damon/next>` by the DAMON maintainer.
|
||||
<https://git.kernel.org/sj/h/damon/next>`_ by the DAMON maintainer.
|
||||
Sufficiently reviewed patches will be queued in `mm-unstable
|
||||
<https://git.kernel.org/akpm/mm/h/mm-unstable>` by the memory management
|
||||
<https://git.kernel.org/akpm/mm/h/mm-unstable>`_ by the memory management
|
||||
subsystem maintainer. After more sufficient tests, the patches will be queued
|
||||
in `mm-stable <https://git.kernel.org/akpm/mm/h/mm-stable>` , and finally
|
||||
in `mm-stable <https://git.kernel.org/akpm/mm/h/mm-stable>`_, and finally
|
||||
pull-requested to the mainline by the memory management subsystem maintainer.
|
||||
|
||||
Note again the patches for mm-unstable `tree
|
||||
<https://git.kernel.org/akpm/mm/h/mm-unstable>` are queued by the memory
|
||||
Note again the patches for `mm-unstable tree
|
||||
<https://git.kernel.org/akpm/mm/h/mm-unstable>`_ are queued by the memory
|
||||
management subsystem maintainer. If the patches requires some patches in
|
||||
damon/next `tree <https://git.kernel.org/sj/h/damon/next>` which not yet merged
|
||||
`damon/next tree <https://git.kernel.org/sj/h/damon/next>`_ which not yet merged
|
||||
in mm-unstable, please make sure the requirement is clearly specified.
|
||||
|
||||
Submit checklist addendum
|
||||
@ -37,25 +37,25 @@ When making DAMON changes, you should do below.
|
||||
- Build changes related outputs including kernel and documents.
|
||||
- Ensure the builds introduce no new errors or warnings.
|
||||
- Run and ensure no new failures for DAMON `selftests
|
||||
<https://github.com/awslabs/damon-tests/blob/master/corr/run.sh#L49>` and
|
||||
<https://github.com/damonitor/damon-tests/blob/master/corr/run.sh#L49>`_ and
|
||||
`kunittests
|
||||
<https://github.com/awslabs/damon-tests/blob/master/corr/tests/kunit.sh>`.
|
||||
<https://github.com/damonitor/damon-tests/blob/master/corr/tests/kunit.sh>`_.
|
||||
|
||||
Further doing below and putting the results will be helpful.
|
||||
|
||||
- Run `damon-tests/corr
|
||||
<https://github.com/awslabs/damon-tests/tree/master/corr>` for normal
|
||||
<https://github.com/damonitor/damon-tests/tree/master/corr>`_ for normal
|
||||
changes.
|
||||
- Run `damon-tests/perf
|
||||
<https://github.com/awslabs/damon-tests/tree/master/perf>` for performance
|
||||
<https://github.com/damonitor/damon-tests/tree/master/perf>`_ for performance
|
||||
changes.
|
||||
|
||||
Key cycle dates
|
||||
---------------
|
||||
|
||||
Patches can be sent anytime. Key cycle dates of the `mm-unstable
|
||||
<https://git.kernel.org/akpm/mm/h/mm-unstable>` and `mm-stable
|
||||
<https://git.kernel.org/akpm/mm/h/mm-stable>` trees depend on the memory
|
||||
<https://git.kernel.org/akpm/mm/h/mm-unstable>`_ and `mm-stable
|
||||
<https://git.kernel.org/akpm/mm/h/mm-stable>`_ trees depend on the memory
|
||||
management subsystem maintainer.
|
||||
|
||||
Review cadence
|
||||
@ -72,13 +72,13 @@ Mailing tool
|
||||
Like many other Linux kernel subsystems, DAMON uses the mailing lists
|
||||
(damon@lists.linux.dev and linux-mm@kvack.org) as the major communication
|
||||
channel. There is a simple tool called `HacKerMaiL
|
||||
<https://github.com/damonitor/hackermail>` (``hkml``), which is for people who
|
||||
<https://github.com/damonitor/hackermail>`_ (``hkml``), which is for people who
|
||||
are not very familiar with the mailing lists based communication. The tool
|
||||
could be particularly helpful for DAMON community members since it is developed
|
||||
and maintained by DAMON maintainer. The tool is also officially announced to
|
||||
support DAMON and general Linux kernel development workflow.
|
||||
|
||||
In other words, `hkml <https://github.com/damonitor/hackermail>` is a mailing
|
||||
In other words, `hkml <https://github.com/damonitor/hackermail>`_ is a mailing
|
||||
tool for DAMON community, which DAMON maintainer is committed to support.
|
||||
Please feel free to try and report issues or feature requests for the tool to
|
||||
the maintainer.
|
||||
@ -98,8 +98,8 @@ slots, and attendees should reserve one of those at least 24 hours before the
|
||||
time slot, by reaching out to the maintainer.
|
||||
|
||||
Schedules and available reservation time slots are available at the Google `doc
|
||||
<https://docs.google.com/document/d/1v43Kcj3ly4CYqmAkMaZzLiM2GEnWfgdGbZAH3mi2vpM/edit?usp=sharing>`.
|
||||
<https://docs.google.com/document/d/1v43Kcj3ly4CYqmAkMaZzLiM2GEnWfgdGbZAH3mi2vpM/edit?usp=sharing>`_.
|
||||
There is also a public Google `calendar
|
||||
<https://calendar.google.com/calendar/u/0?cid=ZDIwOTA4YTMxNjc2MDQ3NTIyMmUzYTM5ZmQyM2U4NDA0ZGIwZjBiYmJlZGQxNDM0MmY4ZTRjOTE0NjdhZDRiY0Bncm91cC5jYWxlbmRhci5nb29nbGUuY29t>`
|
||||
<https://calendar.google.com/calendar/u/0?cid=ZDIwOTA4YTMxNjc2MDQ3NTIyMmUzYTM5ZmQyM2U4NDA0ZGIwZjBiYmJlZGQxNDM0MmY4ZTRjOTE0NjdhZDRiY0Bncm91cC5jYWxlbmRhci5nb29nbGUuY29t>`_
|
||||
that has the events. Anyone can subscribe it. DAMON maintainer will also
|
||||
provide periodic reminder to the mailing list (damon@lists.linux.dev).
|
||||
|
||||
@ -16,7 +16,7 @@ ii) transmit network traffic, or any other that needs raw
|
||||
|
||||
Howto can be found at:
|
||||
|
||||
https://sites.google.com/site/packetmmap/
|
||||
https://web.archive.org/web/20220404160947/https://sites.google.com/site/packetmmap/
|
||||
|
||||
Please send your comments to
|
||||
- Ulisses Alonso Camaró <uaca@i.hate.spam.alumni.uv.es>
|
||||
@ -166,7 +166,8 @@ As capture, each frame contains two parts::
|
||||
/* bind socket to eth0 */
|
||||
bind(this->socket, (struct sockaddr *)&my_addr, sizeof(struct sockaddr_ll));
|
||||
|
||||
A complete tutorial is available at: https://sites.google.com/site/packetmmap/
|
||||
A complete tutorial is available at:
|
||||
https://web.archive.org/web/20220404160947/https://sites.google.com/site/packetmmap/
|
||||
|
||||
By default, the user should put data at::
|
||||
|
||||
|
||||
@ -30,10 +30,13 @@ tree as a dedicated branch covering multiple subsystems.
|
||||
The main SoC tree is housed on git.kernel.org:
|
||||
https://git.kernel.org/pub/scm/linux/kernel/git/soc/soc.git/
|
||||
|
||||
Maintainers
|
||||
-----------
|
||||
|
||||
Clearly this is quite a wide range of topics, which no one person, or even
|
||||
small group of people are capable of maintaining. Instead, the SoC subsystem
|
||||
is comprised of many submaintainers, each taking care of individual platforms
|
||||
and driver subdirectories.
|
||||
is comprised of many submaintainers (platform maintainers), each taking care of
|
||||
individual platforms and driver subdirectories.
|
||||
In this regard, "platform" usually refers to a series of SoCs from a given
|
||||
vendor, for example, Nvidia's series of Tegra SoCs. Many submaintainers operate
|
||||
on a vendor level, responsible for multiple product lines. For several reasons,
|
||||
@ -43,14 +46,43 @@ MAINTAINERS file.
|
||||
|
||||
Most of these submaintainers have their own trees where they stage patches,
|
||||
sending pull requests to the main SoC tree. These trees are usually, but not
|
||||
always, listed in MAINTAINERS. The main SoC maintainers can be reached via the
|
||||
alias soc@kernel.org if there is no platform-specific maintainer, or if they
|
||||
are unresponsive.
|
||||
always, listed in MAINTAINERS.
|
||||
|
||||
What the SoC tree is not, however, is a location for architecture-specific code
|
||||
changes. Each architecture has its own maintainers that are responsible for
|
||||
architectural details, CPU errata and the like.
|
||||
|
||||
Submitting Patches for Given SoC
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
All typical platform related patches should be sent via SoC submaintainers
|
||||
(platform-specific maintainers). This includes also changes to per-platform or
|
||||
shared defconfigs (scripts/get_maintainer.pl might not provide correct
|
||||
addresses in such case).
|
||||
|
||||
Submitting Patches to the Main SoC Maintainers
|
||||
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
The main SoC maintainers can be reached via the alias soc@kernel.org only in
|
||||
following cases:
|
||||
|
||||
1. There are no platform-specific maintainers.
|
||||
|
||||
2. Platform-specific maintainers are unresponsive.
|
||||
|
||||
3. Introducing a completely new SoC platform. Such new SoC work should be sent
|
||||
first to common mailing lists, pointed out by scripts/get_maintainer.pl, for
|
||||
community review. After positive community review, work should be sent to
|
||||
soc@kernel.org in one patchset containing new arch/foo/Kconfig entry, DTS
|
||||
files, MAINTAINERS file entry and optionally initial drivers with their
|
||||
Devicetree bindings. The MAINTAINERS file entry should list new
|
||||
platform-specific maintainers, who are going to be responsible for handling
|
||||
patches for the platform from now on.
|
||||
|
||||
Note that the soc@kernel.org is usually not the place to discuss the patches,
|
||||
thus work sent to this address should be already considered as acceptable by
|
||||
the community.
|
||||
|
||||
Information for (new) Submaintainers
|
||||
------------------------------------
|
||||
|
||||
|
||||
@ -17,7 +17,7 @@ Architecture Level of support Constraints
|
||||
============= ================ ==============================================
|
||||
``arm64`` Maintained Little Endian only.
|
||||
``loongarch`` Maintained \-
|
||||
``riscv`` Maintained ``riscv64`` only.
|
||||
``riscv`` Maintained ``riscv64`` and LLVM/Clang only.
|
||||
``um`` Maintained \-
|
||||
``x86`` Maintained ``x86_64`` only.
|
||||
============= ================ ==============================================
|
||||
|
||||
@ -23,177 +23,166 @@ applications can additionally seal security critical data at runtime.
|
||||
A similar feature already exists in the XNU kernel with the
|
||||
VM_FLAGS_PERMANENT flag [1] and on OpenBSD with the mimmutable syscall [2].
|
||||
|
||||
User API
|
||||
========
|
||||
mseal()
|
||||
-----------
|
||||
The mseal() syscall has the following signature:
|
||||
SYSCALL
|
||||
=======
|
||||
mseal syscall signature
|
||||
-----------------------
|
||||
``int mseal(void \* addr, size_t len, unsigned long flags)``
|
||||
|
||||
``int mseal(void addr, size_t len, unsigned long flags)``
|
||||
**addr**/**len**: virtual memory address range.
|
||||
The address range set by **addr**/**len** must meet:
|
||||
- The start address must be in an allocated VMA.
|
||||
- The start address must be page aligned.
|
||||
- The end address (**addr** + **len**) must be in an allocated VMA.
|
||||
- no gap (unallocated memory) between start and end address.
|
||||
|
||||
**addr/len**: virtual memory address range.
|
||||
The ``len`` will be paged aligned implicitly by the kernel.
|
||||
|
||||
The address range set by ``addr``/``len`` must meet:
|
||||
- The start address must be in an allocated VMA.
|
||||
- The start address must be page aligned.
|
||||
- The end address (``addr`` + ``len``) must be in an allocated VMA.
|
||||
- no gap (unallocated memory) between start and end address.
|
||||
**flags**: reserved for future use.
|
||||
|
||||
The ``len`` will be paged aligned implicitly by the kernel.
|
||||
**Return values**:
|
||||
- **0**: Success.
|
||||
- **-EINVAL**:
|
||||
* Invalid input ``flags``.
|
||||
* The start address (``addr``) is not page aligned.
|
||||
* Address range (``addr`` + ``len``) overflow.
|
||||
- **-ENOMEM**:
|
||||
* The start address (``addr``) is not allocated.
|
||||
* The end address (``addr`` + ``len``) is not allocated.
|
||||
* A gap (unallocated memory) between start and end address.
|
||||
- **-EPERM**:
|
||||
* sealing is supported only on 64-bit CPUs, 32-bit is not supported.
|
||||
|
||||
**flags**: reserved for future use.
|
||||
**Note about error return**:
|
||||
- For above error cases, users can expect the given memory range is
|
||||
unmodified, i.e. no partial update.
|
||||
- There might be other internal errors/cases not listed here, e.g.
|
||||
error during merging/splitting VMAs, or the process reaching the maximum
|
||||
number of supported VMAs. In those cases, partial updates to the given
|
||||
memory range could happen. However, those cases should be rare.
|
||||
|
||||
**return values**:
|
||||
**Architecture support**:
|
||||
mseal only works on 64-bit CPUs, not 32-bit CPUs.
|
||||
|
||||
- ``0``: Success.
|
||||
**Idempotent**:
|
||||
users can call mseal multiple times. mseal on an already sealed memory
|
||||
is a no-action (not error).
|
||||
|
||||
- ``-EINVAL``:
|
||||
- Invalid input ``flags``.
|
||||
- The start address (``addr``) is not page aligned.
|
||||
- Address range (``addr`` + ``len``) overflow.
|
||||
**no munseal**
|
||||
Once mapping is sealed, it can't be unsealed. The kernel should never
|
||||
have munseal, this is consistent with other sealing feature, e.g.
|
||||
F_SEAL_SEAL for file.
|
||||
|
||||
- ``-ENOMEM``:
|
||||
- The start address (``addr``) is not allocated.
|
||||
- The end address (``addr`` + ``len``) is not allocated.
|
||||
- A gap (unallocated memory) between start and end address.
|
||||
Blocked mm syscall for sealed mapping
|
||||
-------------------------------------
|
||||
It might be important to note: **once the mapping is sealed, it will
|
||||
stay in the process's memory until the process terminates**.
|
||||
|
||||
- ``-EPERM``:
|
||||
- sealing is supported only on 64-bit CPUs, 32-bit is not supported.
|
||||
Example::
|
||||
|
||||
- For above error cases, users can expect the given memory range is
|
||||
unmodified, i.e. no partial update.
|
||||
*ptr = mmap(0, 4096, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
|
||||
rc = mseal(ptr, 4096, 0);
|
||||
/* munmap will fail */
|
||||
rc = munmap(ptr, 4096);
|
||||
assert(rc < 0);
|
||||
|
||||
- There might be other internal errors/cases not listed here, e.g.
|
||||
error during merging/splitting VMAs, or the process reaching the max
|
||||
number of supported VMAs. In those cases, partial updates to the given
|
||||
memory range could happen. However, those cases should be rare.
|
||||
Blocked mm syscall:
|
||||
- munmap
|
||||
- mmap
|
||||
- mremap
|
||||
- mprotect and pkey_mprotect
|
||||
- some destructive madvise behaviors: MADV_DONTNEED, MADV_FREE,
|
||||
MADV_DONTNEED_LOCKED, MADV_FREE, MADV_DONTFORK, MADV_WIPEONFORK
|
||||
|
||||
**Blocked operations after sealing**:
|
||||
Unmapping, moving to another location, and shrinking the size,
|
||||
via munmap() and mremap(), can leave an empty space, therefore
|
||||
can be replaced with a VMA with a new set of attributes.
|
||||
The first set of syscalls to block is munmap, mremap, mmap. They can
|
||||
either leave an empty space in the address space, therefore allowing
|
||||
replacement with a new mapping with new set of attributes, or can
|
||||
overwrite the existing mapping with another mapping.
|
||||
|
||||
Moving or expanding a different VMA into the current location,
|
||||
via mremap().
|
||||
mprotect and pkey_mprotect are blocked because they changes the
|
||||
protection bits (RWX) of the mapping.
|
||||
|
||||
Modifying a VMA via mmap(MAP_FIXED).
|
||||
Certain destructive madvise behaviors, specifically MADV_DONTNEED,
|
||||
MADV_FREE, MADV_DONTNEED_LOCKED, and MADV_WIPEONFORK, can introduce
|
||||
risks when applied to anonymous memory by threads lacking write
|
||||
permissions. Consequently, these operations are prohibited under such
|
||||
conditions. The aforementioned behaviors have the potential to modify
|
||||
region contents by discarding pages, effectively performing a memset(0)
|
||||
operation on the anonymous memory.
|
||||
|
||||
Size expansion, via mremap(), does not appear to pose any
|
||||
specific risks to sealed VMAs. It is included anyway because
|
||||
the use case is unclear. In any case, users can rely on
|
||||
merging to expand a sealed VMA.
|
||||
Kernel will return -EPERM for blocked syscalls.
|
||||
|
||||
mprotect() and pkey_mprotect().
|
||||
When blocked syscall return -EPERM due to sealing, the memory regions may
|
||||
or may not be changed, depends on the syscall being blocked:
|
||||
|
||||
Some destructive madvice() behaviors (e.g. MADV_DONTNEED)
|
||||
for anonymous memory, when users don't have write permission to the
|
||||
memory. Those behaviors can alter region contents by discarding pages,
|
||||
effectively a memset(0) for anonymous memory.
|
||||
- munmap: munmap is atomic. If one of VMAs in the given range is
|
||||
sealed, none of VMAs are updated.
|
||||
- mprotect, pkey_mprotect, madvise: partial update might happen, e.g.
|
||||
when mprotect over multiple VMAs, mprotect might update the beginning
|
||||
VMAs before reaching the sealed VMA and return -EPERM.
|
||||
- mmap and mremap: undefined behavior.
|
||||
|
||||
Kernel will return -EPERM for blocked operations.
|
||||
|
||||
For blocked operations, one can expect the given address is unmodified,
|
||||
i.e. no partial update. Note, this is different from existing mm
|
||||
system call behaviors, where partial updates are made till an error is
|
||||
found and returned to userspace. To give an example:
|
||||
|
||||
Assume following code sequence:
|
||||
|
||||
- ptr = mmap(null, 8192, PROT_NONE);
|
||||
- munmap(ptr + 4096, 4096);
|
||||
- ret1 = mprotect(ptr, 8192, PROT_READ);
|
||||
- mseal(ptr, 4096);
|
||||
- ret2 = mprotect(ptr, 8192, PROT_NONE);
|
||||
|
||||
ret1 will be -ENOMEM, the page from ptr is updated to PROT_READ.
|
||||
|
||||
ret2 will be -EPERM, the page remains to be PROT_READ.
|
||||
|
||||
**Note**:
|
||||
|
||||
- mseal() only works on 64-bit CPUs, not 32-bit CPU.
|
||||
|
||||
- users can call mseal() multiple times, mseal() on an already sealed memory
|
||||
is a no-action (not error).
|
||||
|
||||
- munseal() is not supported.
|
||||
|
||||
Use cases:
|
||||
==========
|
||||
Use cases
|
||||
=========
|
||||
- glibc:
|
||||
The dynamic linker, during loading ELF executables, can apply sealing to
|
||||
non-writable memory segments.
|
||||
mapping segments.
|
||||
|
||||
- Chrome browser: protect some security sensitive data-structures.
|
||||
- Chrome browser: protect some security sensitive data structures.
|
||||
|
||||
Notes on which memory to seal:
|
||||
==============================
|
||||
|
||||
It might be important to note that sealing changes the lifetime of a mapping,
|
||||
i.e. the sealed mapping won’t be unmapped till the process terminates or the
|
||||
exec system call is invoked. Applications can apply sealing to any virtual
|
||||
memory region from userspace, but it is crucial to thoroughly analyze the
|
||||
mapping's lifetime prior to apply the sealing.
|
||||
When not to use mseal
|
||||
=====================
|
||||
Applications can apply sealing to any virtual memory region from userspace,
|
||||
but it is *crucial to thoroughly analyze the mapping's lifetime* prior to
|
||||
apply the sealing. This is because the sealed mapping *won’t be unmapped*
|
||||
until the process terminates or the exec system call is invoked.
|
||||
|
||||
For example:
|
||||
- aio/shm
|
||||
aio/shm can call mmap and munmap on behalf of userspace, e.g.
|
||||
ksys_shmdt() in shm.c. The lifetimes of those mapping are not tied to
|
||||
the lifetime of the process. If those memories are sealed from userspace,
|
||||
then munmap will fail, causing leaks in VMA address space during the
|
||||
lifetime of the process.
|
||||
|
||||
- aio/shm
|
||||
- ptr allocated by malloc (heap)
|
||||
Don't use mseal on the memory ptr return from malloc().
|
||||
malloc() is implemented by allocator, e.g. by glibc. Heap manager might
|
||||
allocate a ptr from brk or mapping created by mmap.
|
||||
If an app calls mseal on a ptr returned from malloc(), this can affect
|
||||
the heap manager's ability to manage the mappings; the outcome is
|
||||
non-deterministic.
|
||||
|
||||
aio/shm can call mmap()/munmap() on behalf of userspace, e.g. ksys_shmdt() in
|
||||
shm.c. The lifetime of those mapping are not tied to the lifetime of the
|
||||
process. If those memories are sealed from userspace, then munmap() will fail,
|
||||
causing leaks in VMA address space during the lifetime of the process.
|
||||
Example::
|
||||
|
||||
- Brk (heap)
|
||||
ptr = malloc(size);
|
||||
/* don't call mseal on ptr return from malloc. */
|
||||
mseal(ptr, size);
|
||||
/* free will success, allocator can't shrink heap lower than ptr */
|
||||
free(ptr);
|
||||
|
||||
Currently, userspace applications can seal parts of the heap by calling
|
||||
malloc() and mseal().
|
||||
let's assume following calls from user space:
|
||||
mseal doesn't block
|
||||
===================
|
||||
In a nutshell, mseal blocks certain mm syscall from modifying some of VMA's
|
||||
attributes, such as protection bits (RWX). Sealed mappings doesn't mean the
|
||||
memory is immutable.
|
||||
|
||||
- ptr = malloc(size);
|
||||
- mprotect(ptr, size, RO);
|
||||
- mseal(ptr, size);
|
||||
- free(ptr);
|
||||
|
||||
Technically, before mseal() is added, the user can change the protection of
|
||||
the heap by calling mprotect(RO). As long as the user changes the protection
|
||||
back to RW before free(), the memory range can be reused.
|
||||
|
||||
Adding mseal() into the picture, however, the heap is then sealed partially,
|
||||
the user can still free it, but the memory remains to be RO. If the address
|
||||
is re-used by the heap manager for another malloc, the process might crash
|
||||
soon after. Therefore, it is important not to apply sealing to any memory
|
||||
that might get recycled.
|
||||
|
||||
Furthermore, even if the application never calls the free() for the ptr,
|
||||
the heap manager may invoke the brk system call to shrink the size of the
|
||||
heap. In the kernel, the brk-shrink will call munmap(). Consequently,
|
||||
depending on the location of the ptr, the outcome of brk-shrink is
|
||||
nondeterministic.
|
||||
|
||||
|
||||
Additional notes:
|
||||
=================
|
||||
As Jann Horn pointed out in [3], there are still a few ways to write
|
||||
to RO memory, which is, in a way, by design. Those cases are not covered
|
||||
by mseal(). If applications want to block such cases, sandbox tools (such as
|
||||
seccomp, LSM, etc) might be considered.
|
||||
to RO memory, which is, in a way, by design. And those could be blocked
|
||||
by different security measures.
|
||||
|
||||
Those cases are:
|
||||
|
||||
- Write to read-only memory through /proc/self/mem interface.
|
||||
- Write to read-only memory through ptrace (such as PTRACE_POKETEXT).
|
||||
- userfaultfd.
|
||||
- Write to read-only memory through /proc/self/mem interface (FOLL_FORCE).
|
||||
- Write to read-only memory through ptrace (such as PTRACE_POKETEXT).
|
||||
- userfaultfd.
|
||||
|
||||
The idea that inspired this patch comes from Stephen Röttger’s work in V8
|
||||
CFI [4]. Chrome browser in ChromeOS will be the first user of this API.
|
||||
|
||||
Reference:
|
||||
==========
|
||||
[1] https://github.com/apple-oss-distributions/xnu/blob/1031c584a5e37aff177559b9f69dbd3c8c3fd30a/osfmk/mach/vm_statistics.h#L274
|
||||
|
||||
[2] https://man.openbsd.org/mimmutable.2
|
||||
|
||||
[3] https://lore.kernel.org/lkml/CAG48ez3ShUYey+ZAFsU2i1RpQn0a5eOs2hzQ426FkcgnfUGLvA@mail.gmail.com
|
||||
|
||||
[4] https://docs.google.com/document/d/1O2jwK4dxI3nRcOJuPYkonhTkNQfbmwdvxQMyXgeaRHo/edit#heading=h.bvaojj9fu6hc
|
||||
Reference
|
||||
=========
|
||||
- [1] https://github.com/apple-oss-distributions/xnu/blob/1031c584a5e37aff177559b9f69dbd3c8c3fd30a/osfmk/mach/vm_statistics.h#L274
|
||||
- [2] https://man.openbsd.org/mimmutable.2
|
||||
- [3] https://lore.kernel.org/lkml/CAG48ez3ShUYey+ZAFsU2i1RpQn0a5eOs2hzQ426FkcgnfUGLvA@mail.gmail.com
|
||||
- [4] https://docs.google.com/document/d/1O2jwK4dxI3nRcOJuPYkonhTkNQfbmwdvxQMyXgeaRHo/edit#heading=h.bvaojj9fu6hc
|
||||
|
||||
@ -8098,13 +8098,15 @@ KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS By default, KVM emulates MONITOR/MWAIT (if
|
||||
KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT is
|
||||
disabled.
|
||||
|
||||
KVM_X86_QUIRK_SLOT_ZAP_ALL By default, KVM invalidates all SPTEs in
|
||||
fast way for memslot deletion when VM type
|
||||
is KVM_X86_DEFAULT_VM.
|
||||
When this quirk is disabled or when VM type
|
||||
is other than KVM_X86_DEFAULT_VM, KVM zaps
|
||||
only leaf SPTEs that are within the range of
|
||||
the memslot being deleted.
|
||||
KVM_X86_QUIRK_SLOT_ZAP_ALL By default, for KVM_X86_DEFAULT_VM VMs, KVM
|
||||
invalidates all SPTEs in all memslots and
|
||||
address spaces when a memslot is deleted or
|
||||
moved. When this quirk is disabled (or the
|
||||
VM type isn't KVM_X86_DEFAULT_VM), KVM only
|
||||
ensures the backing memory of the deleted
|
||||
or moved memslot isn't reachable, i.e KVM
|
||||
_may_ invalidate only SPTEs related to the
|
||||
memslot.
|
||||
=================================== ============================================
|
||||
|
||||
7.32 KVM_CAP_MAX_VCPU_ID
|
||||
|
||||
@ -136,7 +136,7 @@ For direct sp, we can easily avoid it since the spte of direct sp is fixed
|
||||
to gfn. For indirect sp, we disabled fast page fault for simplicity.
|
||||
|
||||
A solution for indirect sp could be to pin the gfn, for example via
|
||||
kvm_vcpu_gfn_to_pfn_atomic, before the cmpxchg. After the pinning:
|
||||
gfn_to_pfn_memslot_atomic, before the cmpxchg. After the pinning:
|
||||
|
||||
- We have held the refcount of pfn; that means the pfn can not be freed and
|
||||
be reused for another gfn.
|
||||
|
||||
183
MAINTAINERS
183
MAINTAINERS
@ -258,12 +258,6 @@ L: linux-acenic@sunsite.dk
|
||||
S: Maintained
|
||||
F: drivers/net/ethernet/alteon/acenic*
|
||||
|
||||
ACER ASPIRE 1 EMBEDDED CONTROLLER DRIVER
|
||||
M: Nikita Travkin <nikita@trvn.ru>
|
||||
S: Maintained
|
||||
F: Documentation/devicetree/bindings/platform/acer,aspire1-ec.yaml
|
||||
F: drivers/platform/arm64/acer-aspire1-ec.c
|
||||
|
||||
ACER ASPIRE ONE TEMPERATURE AND FAN DRIVER
|
||||
M: Peter Kaestle <peter@piie.net>
|
||||
L: platform-driver-x86@vger.kernel.org
|
||||
@ -888,7 +882,6 @@ F: drivers/staging/media/sunxi/cedrus/
|
||||
|
||||
ALPHA PORT
|
||||
M: Richard Henderson <richard.henderson@linaro.org>
|
||||
M: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
|
||||
M: Matt Turner <mattst88@gmail.com>
|
||||
L: linux-alpha@vger.kernel.org
|
||||
S: Odd Fixes
|
||||
@ -1761,8 +1754,8 @@ F: include/uapi/linux/if_arcnet.h
|
||||
ARM AND ARM64 SoC SUB-ARCHITECTURES (COMMON PARTS)
|
||||
M: Arnd Bergmann <arnd@arndb.de>
|
||||
M: Olof Johansson <olof@lixom.net>
|
||||
M: soc@kernel.org
|
||||
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
|
||||
L: soc@lists.linux.dev
|
||||
S: Maintained
|
||||
P: Documentation/process/maintainer-soc.rst
|
||||
C: irc://irc.libera.chat/armlinux
|
||||
@ -2263,12 +2256,6 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
|
||||
S: Maintained
|
||||
F: arch/arm/mach-ep93xx/ts72xx.c
|
||||
|
||||
ARM/CIRRUS LOGIC CLPS711X ARM ARCHITECTURE
|
||||
M: Alexander Shiyan <shc_work@mail.ru>
|
||||
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
|
||||
S: Odd Fixes
|
||||
N: clps711x
|
||||
|
||||
ARM/CIRRUS LOGIC EP93XX ARM ARCHITECTURE
|
||||
M: Hartley Sweeten <hsweeten@visionengravers.com>
|
||||
M: Alexander Sverdlin <alexander.sverdlin@gmail.com>
|
||||
@ -3815,14 +3802,6 @@ F: drivers/video/backlight/
|
||||
F: include/linux/backlight.h
|
||||
F: include/linux/pwm_backlight.h
|
||||
|
||||
BAIKAL-T1 PVT HARDWARE MONITOR DRIVER
|
||||
M: Serge Semin <fancer.lancer@gmail.com>
|
||||
L: linux-hwmon@vger.kernel.org
|
||||
S: Supported
|
||||
F: Documentation/devicetree/bindings/hwmon/baikal,bt1-pvt.yaml
|
||||
F: Documentation/hwmon/bt1-pvt.rst
|
||||
F: drivers/hwmon/bt1-pvt.[ch]
|
||||
|
||||
BARCO P50 GPIO DRIVER
|
||||
M: Santosh Kumar Yadav <santoshkumar.yadav@barco.com>
|
||||
M: Peter Korsgaard <peter.korsgaard@barco.com>
|
||||
@ -6476,7 +6455,6 @@ F: drivers/mtd/nand/raw/denali*
|
||||
|
||||
DESIGNWARE EDMA CORE IP DRIVER
|
||||
M: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
|
||||
R: Serge Semin <fancer.lancer@gmail.com>
|
||||
L: dmaengine@vger.kernel.org
|
||||
S: Maintained
|
||||
F: drivers/dma/dw-edma/
|
||||
@ -9745,6 +9723,7 @@ F: include/dt-bindings/gpio/
|
||||
F: include/linux/gpio.h
|
||||
F: include/linux/gpio/
|
||||
F: include/linux/of_gpio.h
|
||||
K: (devm_)?gpio_(request|free|direction|get|set)
|
||||
|
||||
GPIO UAPI
|
||||
M: Bartosz Golaszewski <brgl@bgdev.pl>
|
||||
@ -9759,14 +9738,6 @@ F: drivers/gpio/gpiolib-cdev.c
|
||||
F: include/uapi/linux/gpio.h
|
||||
F: tools/gpio/
|
||||
|
||||
GRE DEMULTIPLEXER DRIVER
|
||||
M: Dmitry Kozlov <xeb@mail.ru>
|
||||
L: netdev@vger.kernel.org
|
||||
S: Maintained
|
||||
F: include/net/gre.h
|
||||
F: net/ipv4/gre_demux.c
|
||||
F: net/ipv4/gre_offload.c
|
||||
|
||||
GRETH 10/100/1G Ethernet MAC device driver
|
||||
M: Andreas Larsson <andreas@gaisler.com>
|
||||
L: netdev@vger.kernel.org
|
||||
@ -11283,10 +11254,10 @@ F: security/integrity/
|
||||
F: security/integrity/ima/
|
||||
|
||||
INTEGRITY POLICY ENFORCEMENT (IPE)
|
||||
M: Fan Wu <wufan@linux.microsoft.com>
|
||||
M: Fan Wu <wufan@kernel.org>
|
||||
L: linux-security-module@vger.kernel.org
|
||||
S: Supported
|
||||
T: git https://github.com/microsoft/ipe.git
|
||||
T: git git://git.kernel.org/pub/scm/linux/kernel/git/wufan/ipe.git
|
||||
F: Documentation/admin-guide/LSM/ipe.rst
|
||||
F: Documentation/security/ipe.rst
|
||||
F: scripts/ipe/
|
||||
@ -11604,6 +11575,16 @@ F: drivers/crypto/intel/keembay/keembay-ocs-hcu-core.c
|
||||
F: drivers/crypto/intel/keembay/ocs-hcu.c
|
||||
F: drivers/crypto/intel/keembay/ocs-hcu.h
|
||||
|
||||
INTEL LA JOLLA COVE ADAPTER (LJCA) USB I/O EXPANDER DRIVERS
|
||||
M: Wentong Wu <wentong.wu@intel.com>
|
||||
M: Sakari Ailus <sakari.ailus@linux.intel.com>
|
||||
S: Maintained
|
||||
F: drivers/gpio/gpio-ljca.c
|
||||
F: drivers/i2c/busses/i2c-ljca.c
|
||||
F: drivers/spi/spi-ljca.c
|
||||
F: drivers/usb/misc/usb-ljca.c
|
||||
F: include/linux/usb/ljca.h
|
||||
|
||||
INTEL MANAGEMENT ENGINE (mei)
|
||||
M: Tomas Winkler <tomas.winkler@intel.com>
|
||||
L: linux-kernel@vger.kernel.org
|
||||
@ -12242,6 +12223,7 @@ R: Dmitry Vyukov <dvyukov@google.com>
|
||||
R: Vincenzo Frascino <vincenzo.frascino@arm.com>
|
||||
L: kasan-dev@googlegroups.com
|
||||
S: Maintained
|
||||
B: https://bugzilla.kernel.org/buglist.cgi?component=Sanitizers&product=Memory%20Management
|
||||
F: Documentation/dev-tools/kasan.rst
|
||||
F: arch/*/include/asm/*kasan.h
|
||||
F: arch/*/mm/kasan_init*
|
||||
@ -12265,6 +12247,7 @@ R: Dmitry Vyukov <dvyukov@google.com>
|
||||
R: Andrey Konovalov <andreyknvl@gmail.com>
|
||||
L: kasan-dev@googlegroups.com
|
||||
S: Maintained
|
||||
B: https://bugzilla.kernel.org/buglist.cgi?component=Sanitizers&product=Memory%20Management
|
||||
F: Documentation/dev-tools/kcov.rst
|
||||
F: include/linux/kcov.h
|
||||
F: include/uapi/linux/kcov.h
|
||||
@ -12947,12 +12930,6 @@ S: Maintained
|
||||
F: drivers/ata/pata_arasan_cf.c
|
||||
F: include/linux/pata_arasan_cf_data.h
|
||||
|
||||
LIBATA PATA DRIVERS
|
||||
R: Sergey Shtylyov <s.shtylyov@omp.ru>
|
||||
L: linux-ide@vger.kernel.org
|
||||
F: drivers/ata/ata_*.c
|
||||
F: drivers/ata/pata_*.c
|
||||
|
||||
LIBATA PATA FARADAY FTIDE010 AND GEMINI SATA BRIDGE DRIVERS
|
||||
M: Linus Walleij <linus.walleij@linaro.org>
|
||||
L: linux-ide@vger.kernel.org
|
||||
@ -12969,14 +12946,6 @@ F: drivers/ata/ahci_platform.c
|
||||
F: drivers/ata/libahci_platform.c
|
||||
F: include/linux/ahci_platform.h
|
||||
|
||||
LIBATA SATA AHCI SYNOPSYS DWC CONTROLLER DRIVER
|
||||
M: Serge Semin <fancer.lancer@gmail.com>
|
||||
L: linux-ide@vger.kernel.org
|
||||
S: Maintained
|
||||
F: Documentation/devicetree/bindings/ata/baikal,bt1-ahci.yaml
|
||||
F: Documentation/devicetree/bindings/ata/snps,dwc-ahci.yaml
|
||||
F: drivers/ata/ahci_dwc.c
|
||||
|
||||
LIBATA SATA PROMISE TX2/TX4 CONTROLLER DRIVER
|
||||
M: Mikael Pettersson <mikpelinux@gmail.com>
|
||||
L: linux-ide@vger.kernel.org
|
||||
@ -14173,8 +14142,7 @@ T: git git://linuxtv.org/media_tree.git
|
||||
F: drivers/media/platform/nxp/imx-pxp.[ch]
|
||||
|
||||
MEDIA DRIVERS FOR ASCOT2E
|
||||
M: Sergey Kozlov <serjk@netup.ru>
|
||||
M: Abylay Ospan <aospan@netup.ru>
|
||||
M: Abylay Ospan <aospan@amazon.com>
|
||||
L: linux-media@vger.kernel.org
|
||||
S: Supported
|
||||
W: https://linuxtv.org
|
||||
@ -14191,8 +14159,7 @@ T: git git://linuxtv.org/media_tree.git
|
||||
F: drivers/media/dvb-frontends/cxd2099*
|
||||
|
||||
MEDIA DRIVERS FOR CXD2841ER
|
||||
M: Sergey Kozlov <serjk@netup.ru>
|
||||
M: Abylay Ospan <aospan@netup.ru>
|
||||
M: Abylay Ospan <aospan@amazon.com>
|
||||
L: linux-media@vger.kernel.org
|
||||
S: Supported
|
||||
W: https://linuxtv.org
|
||||
@ -14245,7 +14212,7 @@ F: drivers/media/platform/nxp/imx7-media-csi.c
|
||||
F: drivers/media/platform/nxp/imx8mq-mipi-csi2.c
|
||||
|
||||
MEDIA DRIVERS FOR HELENE
|
||||
M: Abylay Ospan <aospan@netup.ru>
|
||||
M: Abylay Ospan <aospan@amazon.com>
|
||||
L: linux-media@vger.kernel.org
|
||||
S: Supported
|
||||
W: https://linuxtv.org
|
||||
@ -14254,8 +14221,7 @@ T: git git://linuxtv.org/media_tree.git
|
||||
F: drivers/media/dvb-frontends/helene*
|
||||
|
||||
MEDIA DRIVERS FOR HORUS3A
|
||||
M: Sergey Kozlov <serjk@netup.ru>
|
||||
M: Abylay Ospan <aospan@netup.ru>
|
||||
M: Abylay Ospan <aospan@amazon.com>
|
||||
L: linux-media@vger.kernel.org
|
||||
S: Supported
|
||||
W: https://linuxtv.org
|
||||
@ -14264,8 +14230,7 @@ T: git git://linuxtv.org/media_tree.git
|
||||
F: drivers/media/dvb-frontends/horus3a*
|
||||
|
||||
MEDIA DRIVERS FOR LNBH25
|
||||
M: Sergey Kozlov <serjk@netup.ru>
|
||||
M: Abylay Ospan <aospan@netup.ru>
|
||||
M: Abylay Ospan <aospan@amazon.com>
|
||||
L: linux-media@vger.kernel.org
|
||||
S: Supported
|
||||
W: https://linuxtv.org
|
||||
@ -14281,8 +14246,7 @@ T: git git://linuxtv.org/media_tree.git
|
||||
F: drivers/media/dvb-frontends/mxl5xx*
|
||||
|
||||
MEDIA DRIVERS FOR NETUP PCI UNIVERSAL DVB devices
|
||||
M: Sergey Kozlov <serjk@netup.ru>
|
||||
M: Abylay Ospan <aospan@netup.ru>
|
||||
M: Abylay Ospan <aospan@amazon.com>
|
||||
L: linux-media@vger.kernel.org
|
||||
S: Supported
|
||||
W: https://linuxtv.org
|
||||
@ -14907,9 +14871,10 @@ N: include/linux/page[-_]*
|
||||
|
||||
MEMORY MAPPING
|
||||
M: Andrew Morton <akpm@linux-foundation.org>
|
||||
R: Liam R. Howlett <Liam.Howlett@oracle.com>
|
||||
M: Liam R. Howlett <Liam.Howlett@oracle.com>
|
||||
M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
|
||||
R: Vlastimil Babka <vbabka@suse.cz>
|
||||
R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
|
||||
R: Jann Horn <jannh@google.com>
|
||||
L: linux-mm@kvack.org
|
||||
S: Maintained
|
||||
W: http://www.linux-mm.org
|
||||
@ -14932,13 +14897,6 @@ F: drivers/mtd/
|
||||
F: include/linux/mtd/
|
||||
F: include/uapi/mtd/
|
||||
|
||||
MEMSENSING MICROSYSTEMS MSA311 DRIVER
|
||||
M: Dmitry Rokosov <ddrokosov@sberdevices.ru>
|
||||
L: linux-iio@vger.kernel.org
|
||||
S: Maintained
|
||||
F: Documentation/devicetree/bindings/iio/accel/memsensing,msa311.yaml
|
||||
F: drivers/iio/accel/msa311.c
|
||||
|
||||
MEN A21 WATCHDOG DRIVER
|
||||
M: Johannes Thumshirn <morbidrsa@gmail.com>
|
||||
L: linux-watchdog@vger.kernel.org
|
||||
@ -15083,6 +15041,7 @@ F: drivers/spi/spi-at91-usart.c
|
||||
|
||||
MICROCHIP AUDIO ASOC DRIVERS
|
||||
M: Claudiu Beznea <claudiu.beznea@tuxon.dev>
|
||||
M: Andrei Simion <andrei.simion@microchip.com>
|
||||
L: linux-sound@vger.kernel.org
|
||||
S: Supported
|
||||
F: Documentation/devicetree/bindings/sound/atmel*
|
||||
@ -15191,6 +15150,7 @@ F: include/video/atmel_lcdc.h
|
||||
|
||||
MICROCHIP MCP16502 PMIC DRIVER
|
||||
M: Claudiu Beznea <claudiu.beznea@tuxon.dev>
|
||||
M: Andrei Simion <andrei.simion@microchip.com>
|
||||
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
|
||||
S: Supported
|
||||
F: Documentation/devicetree/bindings/regulator/microchip,mcp16502.yaml
|
||||
@ -15272,7 +15232,6 @@ F: drivers/tty/serial/8250/8250_pci1xxxx.c
|
||||
|
||||
MICROCHIP POLARFIRE FPGA DRIVERS
|
||||
M: Conor Dooley <conor.dooley@microchip.com>
|
||||
R: Vladimir Georgiev <v.georgiev@metrotek.ru>
|
||||
L: linux-fpga@vger.kernel.org
|
||||
S: Supported
|
||||
F: Documentation/devicetree/bindings/fpga/microchip,mpf-spi-fpga-mgr.yaml
|
||||
@ -15322,6 +15281,7 @@ F: drivers/spi/spi-atmel.*
|
||||
|
||||
MICROCHIP SSC DRIVER
|
||||
M: Claudiu Beznea <claudiu.beznea@tuxon.dev>
|
||||
M: Andrei Simion <andrei.simion@microchip.com>
|
||||
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
|
||||
S: Supported
|
||||
F: Documentation/devicetree/bindings/misc/atmel-ssc.txt
|
||||
@ -15527,17 +15487,6 @@ F: arch/mips/
|
||||
F: drivers/platform/mips/
|
||||
F: include/dt-bindings/mips/
|
||||
|
||||
MIPS BAIKAL-T1 PLATFORM
|
||||
M: Serge Semin <fancer.lancer@gmail.com>
|
||||
L: linux-mips@vger.kernel.org
|
||||
S: Supported
|
||||
F: Documentation/devicetree/bindings/bus/baikal,bt1-*.yaml
|
||||
F: Documentation/devicetree/bindings/clock/baikal,bt1-*.yaml
|
||||
F: drivers/bus/bt1-*.c
|
||||
F: drivers/clk/baikal-t1/
|
||||
F: drivers/memory/bt1-l2-ctl.c
|
||||
F: drivers/mtd/maps/physmap-bt1-rom.[ch]
|
||||
|
||||
MIPS BOSTON DEVELOPMENT BOARD
|
||||
M: Paul Burton <paulburton@kernel.org>
|
||||
L: linux-mips@vger.kernel.org
|
||||
@ -15550,7 +15499,6 @@ F: include/dt-bindings/clock/boston-clock.h
|
||||
|
||||
MIPS CORE DRIVERS
|
||||
M: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
|
||||
M: Serge Semin <fancer.lancer@gmail.com>
|
||||
L: linux-mips@vger.kernel.org
|
||||
S: Supported
|
||||
F: drivers/bus/mips_cdmm.c
|
||||
@ -16086,6 +16034,7 @@ F: include/uapi/linux/net_dropmon.h
|
||||
F: net/core/drop_monitor.c
|
||||
|
||||
NETWORKING DRIVERS
|
||||
M: Andrew Lunn <andrew+netdev@lunn.ch>
|
||||
M: "David S. Miller" <davem@davemloft.net>
|
||||
M: Eric Dumazet <edumazet@google.com>
|
||||
M: Jakub Kicinski <kuba@kernel.org>
|
||||
@ -16151,6 +16100,7 @@ M: "David S. Miller" <davem@davemloft.net>
|
||||
M: Eric Dumazet <edumazet@google.com>
|
||||
M: Jakub Kicinski <kuba@kernel.org>
|
||||
M: Paolo Abeni <pabeni@redhat.com>
|
||||
R: Simon Horman <horms@kernel.org>
|
||||
L: netdev@vger.kernel.org
|
||||
S: Maintained
|
||||
P: Documentation/process/maintainer-netdev.rst
|
||||
@ -16193,6 +16143,7 @@ F: include/uapi/linux/rtnetlink.h
|
||||
F: lib/net_utils.c
|
||||
F: lib/random32.c
|
||||
F: net/
|
||||
F: samples/pktgen/
|
||||
F: tools/net/
|
||||
F: tools/testing/selftests/net/
|
||||
X: Documentation/networking/mac80211-injection.rst
|
||||
@ -16517,12 +16468,6 @@ F: include/linux/ntb.h
|
||||
F: include/linux/ntb_transport.h
|
||||
F: tools/testing/selftests/ntb/
|
||||
|
||||
NTB IDT DRIVER
|
||||
M: Serge Semin <fancer.lancer@gmail.com>
|
||||
L: ntb@lists.linux.dev
|
||||
S: Supported
|
||||
F: drivers/ntb/hw/idt/
|
||||
|
||||
NTB INTEL DRIVER
|
||||
M: Dave Jiang <dave.jiang@intel.com>
|
||||
L: ntb@lists.linux.dev
|
||||
@ -18543,13 +18488,6 @@ F: drivers/pps/
|
||||
F: include/linux/pps*.h
|
||||
F: include/uapi/linux/pps.h
|
||||
|
||||
PPTP DRIVER
|
||||
M: Dmitry Kozlov <xeb@mail.ru>
|
||||
L: netdev@vger.kernel.org
|
||||
S: Maintained
|
||||
W: http://sourceforge.net/projects/accel-pptp
|
||||
F: drivers/net/ppp/pptp.c
|
||||
|
||||
PRESSURE STALL INFORMATION (PSI)
|
||||
M: Johannes Weiner <hannes@cmpxchg.org>
|
||||
M: Suren Baghdasaryan <surenb@google.com>
|
||||
@ -19523,6 +19461,14 @@ S: Maintained
|
||||
F: Documentation/tools/rtla/
|
||||
F: tools/tracing/rtla/
|
||||
|
||||
Real-time Linux (PREEMPT_RT)
|
||||
M: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
|
||||
M: Clark Williams <clrkwllms@kernel.org>
|
||||
M: Steven Rostedt <rostedt@goodmis.org>
|
||||
L: linux-rt-devel@lists.linux.dev
|
||||
S: Supported
|
||||
K: PREEMPT_RT
|
||||
|
||||
REALTEK AUDIO CODECS
|
||||
M: Oder Chiou <oder_chiou@realtek.com>
|
||||
S: Maintained
|
||||
@ -19632,15 +19578,6 @@ S: Supported
|
||||
F: Documentation/devicetree/bindings/i2c/renesas,iic-emev2.yaml
|
||||
F: drivers/i2c/busses/i2c-emev2.c
|
||||
|
||||
RENESAS ETHERNET AVB DRIVER
|
||||
R: Sergey Shtylyov <s.shtylyov@omp.ru>
|
||||
L: netdev@vger.kernel.org
|
||||
L: linux-renesas-soc@vger.kernel.org
|
||||
F: Documentation/devicetree/bindings/net/renesas,etheravb.yaml
|
||||
F: drivers/net/ethernet/renesas/Kconfig
|
||||
F: drivers/net/ethernet/renesas/Makefile
|
||||
F: drivers/net/ethernet/renesas/ravb*
|
||||
|
||||
RENESAS ETHERNET SWITCH DRIVER
|
||||
R: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
|
||||
L: netdev@vger.kernel.org
|
||||
@ -19690,14 +19627,6 @@ F: Documentation/devicetree/bindings/i2c/renesas,rmobile-iic.yaml
|
||||
F: drivers/i2c/busses/i2c-rcar.c
|
||||
F: drivers/i2c/busses/i2c-sh_mobile.c
|
||||
|
||||
RENESAS R-CAR SATA DRIVER
|
||||
R: Sergey Shtylyov <s.shtylyov@omp.ru>
|
||||
L: linux-ide@vger.kernel.org
|
||||
L: linux-renesas-soc@vger.kernel.org
|
||||
S: Supported
|
||||
F: Documentation/devicetree/bindings/ata/renesas,rcar-sata.yaml
|
||||
F: drivers/ata/sata_rcar.c
|
||||
|
||||
RENESAS R-CAR THERMAL DRIVERS
|
||||
M: Niklas Söderlund <niklas.soderlund@ragnatech.se>
|
||||
L: linux-renesas-soc@vger.kernel.org
|
||||
@ -19773,16 +19702,6 @@ S: Supported
|
||||
F: Documentation/devicetree/bindings/i2c/renesas,rzv2m.yaml
|
||||
F: drivers/i2c/busses/i2c-rzv2m.c
|
||||
|
||||
RENESAS SUPERH ETHERNET DRIVER
|
||||
R: Sergey Shtylyov <s.shtylyov@omp.ru>
|
||||
L: netdev@vger.kernel.org
|
||||
L: linux-renesas-soc@vger.kernel.org
|
||||
F: Documentation/devicetree/bindings/net/renesas,ether.yaml
|
||||
F: drivers/net/ethernet/renesas/Kconfig
|
||||
F: drivers/net/ethernet/renesas/Makefile
|
||||
F: drivers/net/ethernet/renesas/sh_eth*
|
||||
F: include/linux/sh_eth.h
|
||||
|
||||
RENESAS USB PHY DRIVER
|
||||
M: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
|
||||
L: linux-renesas-soc@vger.kernel.org
|
||||
@ -21777,8 +21696,8 @@ F: drivers/accessibility/speakup/
|
||||
SPEAR PLATFORM/CLOCK/PINCTRL SUPPORT
|
||||
M: Viresh Kumar <vireshk@kernel.org>
|
||||
M: Shiraz Hashim <shiraz.linux.kernel@gmail.com>
|
||||
M: soc@kernel.org
|
||||
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
|
||||
L: soc@lists.linux.dev
|
||||
S: Maintained
|
||||
W: http://www.st.com/spear
|
||||
F: arch/arm/boot/dts/st/spear*
|
||||
@ -22436,19 +22355,11 @@ F: drivers/tty/serial/8250/8250_lpss.c
|
||||
|
||||
SYNOPSYS DESIGNWARE APB GPIO DRIVER
|
||||
M: Hoan Tran <hoan@os.amperecomputing.com>
|
||||
M: Serge Semin <fancer.lancer@gmail.com>
|
||||
L: linux-gpio@vger.kernel.org
|
||||
S: Maintained
|
||||
F: Documentation/devicetree/bindings/gpio/snps,dw-apb-gpio.yaml
|
||||
F: drivers/gpio/gpio-dwapb.c
|
||||
|
||||
SYNOPSYS DESIGNWARE APB SSI DRIVER
|
||||
M: Serge Semin <fancer.lancer@gmail.com>
|
||||
L: linux-spi@vger.kernel.org
|
||||
S: Supported
|
||||
F: Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
|
||||
F: drivers/spi/spi-dw*
|
||||
|
||||
SYNOPSYS DESIGNWARE AXI DMAC DRIVER
|
||||
M: Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com>
|
||||
S: Maintained
|
||||
@ -23292,7 +23203,7 @@ F: Documentation/devicetree/bindings/iio/adc/ti,lmp92064.yaml
|
||||
F: drivers/iio/adc/ti-lmp92064.c
|
||||
|
||||
TI PCM3060 ASoC CODEC DRIVER
|
||||
M: Kirill Marinushkin <kmarinushkin@birdec.com>
|
||||
M: Kirill Marinushkin <k.marinushkin@gmail.com>
|
||||
L: linux-sound@vger.kernel.org
|
||||
S: Maintained
|
||||
F: Documentation/devicetree/bindings/sound/pcm3060.txt
|
||||
@ -23758,12 +23669,6 @@ L: linux-input@vger.kernel.org
|
||||
S: Maintained
|
||||
F: drivers/hid/hid-udraw-ps3.c
|
||||
|
||||
UFS FILESYSTEM
|
||||
M: Evgeniy Dushistov <dushistov@mail.ru>
|
||||
S: Maintained
|
||||
F: Documentation/admin-guide/ufs.rst
|
||||
F: fs/ufs/
|
||||
|
||||
UHID USERSPACE HID IO DRIVER
|
||||
M: David Rheinsberg <david@readahead.eu>
|
||||
L: linux-input@vger.kernel.org
|
||||
@ -24066,6 +23971,7 @@ USB RAW GADGET DRIVER
|
||||
R: Andrey Konovalov <andreyknvl@gmail.com>
|
||||
L: linux-usb@vger.kernel.org
|
||||
S: Maintained
|
||||
B: https://github.com/xairy/raw-gadget/issues
|
||||
F: Documentation/usb/raw-gadget.rst
|
||||
F: drivers/usb/gadget/legacy/raw_gadget.c
|
||||
F: include/uapi/linux/usb/raw_gadget.h
|
||||
@ -24737,9 +24643,10 @@ F: tools/testing/vsock/
|
||||
|
||||
VMA
|
||||
M: Andrew Morton <akpm@linux-foundation.org>
|
||||
R: Liam R. Howlett <Liam.Howlett@oracle.com>
|
||||
M: Liam R. Howlett <Liam.Howlett@oracle.com>
|
||||
M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
|
||||
R: Vlastimil Babka <vbabka@suse.cz>
|
||||
R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
|
||||
R: Jann Horn <jannh@google.com>
|
||||
L: linux-mm@kvack.org
|
||||
S: Maintained
|
||||
W: https://www.linux-mm.org
|
||||
|
||||
2
Makefile
2
Makefile
@ -2,7 +2,7 @@
|
||||
VERSION = 6
|
||||
PATCHLEVEL = 12
|
||||
SUBLEVEL = 0
|
||||
EXTRAVERSION = -rc3
|
||||
EXTRAVERSION = -rc6
|
||||
NAME = Baby Opossum Posse
|
||||
|
||||
# *DOCUMENTATION*
|
||||
|
||||
26
arch/Kconfig
26
arch/Kconfig
@ -838,7 +838,7 @@ config CFI_CLANG
|
||||
config CFI_ICALL_NORMALIZE_INTEGERS
|
||||
bool "Normalize CFI tags for integers"
|
||||
depends on CFI_CLANG
|
||||
depends on HAVE_CFI_ICALL_NORMALIZE_INTEGERS
|
||||
depends on HAVE_CFI_ICALL_NORMALIZE_INTEGERS_CLANG
|
||||
help
|
||||
This option normalizes the CFI tags for integer types so that all
|
||||
integer types of the same size and signedness receive the same CFI
|
||||
@ -851,21 +851,19 @@ config CFI_ICALL_NORMALIZE_INTEGERS
|
||||
|
||||
This option is necessary for using CFI with Rust. If unsure, say N.
|
||||
|
||||
config HAVE_CFI_ICALL_NORMALIZE_INTEGERS
|
||||
def_bool !GCOV_KERNEL && !KASAN
|
||||
depends on CFI_CLANG
|
||||
config HAVE_CFI_ICALL_NORMALIZE_INTEGERS_CLANG
|
||||
def_bool y
|
||||
depends on $(cc-option,-fsanitize=kcfi -fsanitize-cfi-icall-experimental-normalize-integers)
|
||||
help
|
||||
Is CFI_ICALL_NORMALIZE_INTEGERS supported with the set of compilers
|
||||
currently in use?
|
||||
# With GCOV/KASAN we need this fix: https://github.com/llvm/llvm-project/pull/104826
|
||||
depends on CLANG_VERSION >= 190103 || (!GCOV_KERNEL && !KASAN_GENERIC && !KASAN_SW_TAGS)
|
||||
|
||||
This option defaults to false if GCOV or KASAN is enabled, as there is
|
||||
an LLVM bug that makes normalized integers tags incompatible with
|
||||
KASAN and GCOV. Kconfig currently does not have the infrastructure to
|
||||
detect whether your rustc compiler contains the fix for this bug, so
|
||||
it is assumed that it doesn't. If your compiler has the fix, you can
|
||||
explicitly enable this option in your config file. The Kconfig logic
|
||||
needed to detect this will be added in a future kernel release.
|
||||
config HAVE_CFI_ICALL_NORMALIZE_INTEGERS_RUSTC
|
||||
def_bool y
|
||||
depends on HAVE_CFI_ICALL_NORMALIZE_INTEGERS_CLANG
|
||||
depends on RUSTC_VERSION >= 107900
|
||||
# With GCOV/KASAN we need this fix: https://github.com/rust-lang/rust/pull/129373
|
||||
depends on (RUSTC_LLVM_VERSION >= 190103 && RUSTC_VERSION >= 108200) || \
|
||||
(!GCOV_KERNEL && !KASAN_GENERIC && !KASAN_SW_TAGS)
|
||||
|
||||
config CFI_PERMISSIVE
|
||||
bool "Use CFI in permissive mode"
|
||||
|
||||
@ -77,7 +77,7 @@ &gpio {
|
||||
};
|
||||
|
||||
&hdmi {
|
||||
hpd-gpios = <&expgpio 1 GPIO_ACTIVE_LOW>;
|
||||
hpd-gpios = <&expgpio 0 GPIO_ACTIVE_LOW>;
|
||||
power-domains = <&power RPI_POWER_DOMAIN_HDMI>;
|
||||
status = "okay";
|
||||
};
|
||||
|
||||
@ -136,7 +136,7 @@ cp0_i2c0_pins: cp0-i2c0-pins {
|
||||
};
|
||||
|
||||
cp0_mdio_pins: cp0-mdio-pins {
|
||||
marvell,pins = "mpp40", "mpp41";
|
||||
marvell,pins = "mpp0", "mpp1";
|
||||
marvell,function = "ge";
|
||||
};
|
||||
|
||||
|
||||
@ -178,6 +178,7 @@ struct kvm_nvhe_init_params {
|
||||
unsigned long hcr_el2;
|
||||
unsigned long vttbr;
|
||||
unsigned long vtcr;
|
||||
unsigned long tmp;
|
||||
};
|
||||
|
||||
/*
|
||||
|
||||
@ -51,6 +51,7 @@
|
||||
#define KVM_REQ_RELOAD_PMU KVM_ARCH_REQ(5)
|
||||
#define KVM_REQ_SUSPEND KVM_ARCH_REQ(6)
|
||||
#define KVM_REQ_RESYNC_PMU_EL0 KVM_ARCH_REQ(7)
|
||||
#define KVM_REQ_NESTED_S2_UNMAP KVM_ARCH_REQ(8)
|
||||
|
||||
#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
|
||||
KVM_DIRTY_LOG_INITIALLY_SET)
|
||||
@ -211,6 +212,12 @@ struct kvm_s2_mmu {
|
||||
*/
|
||||
bool nested_stage2_enabled;
|
||||
|
||||
/*
|
||||
* true when this MMU needs to be unmapped before being used for a new
|
||||
* purpose.
|
||||
*/
|
||||
bool pending_unmap;
|
||||
|
||||
/*
|
||||
* 0: Nobody is currently using this, check vttbr for validity
|
||||
* >0: Somebody is actively using this.
|
||||
|
||||
@ -166,7 +166,8 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
|
||||
int create_hyp_stack(phys_addr_t phys_addr, unsigned long *haddr);
|
||||
void __init free_hyp_pgds(void);
|
||||
|
||||
void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size);
|
||||
void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
|
||||
u64 size, bool may_block);
|
||||
void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end);
|
||||
void kvm_stage2_wp_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end);
|
||||
|
||||
|
||||
@ -78,6 +78,8 @@ extern void kvm_s2_mmu_iterate_by_vmid(struct kvm *kvm, u16 vmid,
|
||||
extern void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu);
|
||||
extern void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu);
|
||||
|
||||
extern void check_nested_vcpu_requests(struct kvm_vcpu *vcpu);
|
||||
|
||||
struct kvm_s2_trans {
|
||||
phys_addr_t output;
|
||||
unsigned long block_size;
|
||||
@ -124,7 +126,7 @@ extern int kvm_s2_handle_perm_fault(struct kvm_vcpu *vcpu,
|
||||
struct kvm_s2_trans *trans);
|
||||
extern int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2);
|
||||
extern void kvm_nested_s2_wp(struct kvm *kvm);
|
||||
extern void kvm_nested_s2_unmap(struct kvm *kvm);
|
||||
extern void kvm_nested_s2_unmap(struct kvm *kvm, bool may_block);
|
||||
extern void kvm_nested_s2_flush(struct kvm *kvm);
|
||||
|
||||
unsigned long compute_tlb_inval_range(struct kvm_s2_mmu *mmu, u64 val);
|
||||
|
||||
@ -10,11 +10,9 @@
|
||||
#include <asm/insn.h>
|
||||
#include <asm/probes.h>
|
||||
|
||||
#define MAX_UINSN_BYTES AARCH64_INSN_SIZE
|
||||
|
||||
#define UPROBE_SWBP_INSN cpu_to_le32(BRK64_OPCODE_UPROBES)
|
||||
#define UPROBE_SWBP_INSN_SIZE AARCH64_INSN_SIZE
|
||||
#define UPROBE_XOL_SLOT_BYTES MAX_UINSN_BYTES
|
||||
#define UPROBE_XOL_SLOT_BYTES AARCH64_INSN_SIZE
|
||||
|
||||
typedef __le32 uprobe_opcode_t;
|
||||
|
||||
@ -23,8 +21,8 @@ struct arch_uprobe_task {
|
||||
|
||||
struct arch_uprobe {
|
||||
union {
|
||||
u8 insn[MAX_UINSN_BYTES];
|
||||
u8 ixol[MAX_UINSN_BYTES];
|
||||
__le32 insn;
|
||||
__le32 ixol;
|
||||
};
|
||||
struct arch_probe_insn api;
|
||||
bool simulate;
|
||||
|
||||
@ -146,6 +146,7 @@ int main(void)
|
||||
DEFINE(NVHE_INIT_HCR_EL2, offsetof(struct kvm_nvhe_init_params, hcr_el2));
|
||||
DEFINE(NVHE_INIT_VTTBR, offsetof(struct kvm_nvhe_init_params, vttbr));
|
||||
DEFINE(NVHE_INIT_VTCR, offsetof(struct kvm_nvhe_init_params, vtcr));
|
||||
DEFINE(NVHE_INIT_TMP, offsetof(struct kvm_nvhe_init_params, tmp));
|
||||
#endif
|
||||
#ifdef CONFIG_CPU_PM
|
||||
DEFINE(CPU_CTX_SP, offsetof(struct cpu_suspend_ctx, sp));
|
||||
|
||||
@ -99,10 +99,6 @@ arm_probe_decode_insn(probe_opcode_t insn, struct arch_probe_insn *api)
|
||||
aarch64_insn_is_blr(insn) ||
|
||||
aarch64_insn_is_ret(insn)) {
|
||||
api->handler = simulate_br_blr_ret;
|
||||
} else if (aarch64_insn_is_ldr_lit(insn)) {
|
||||
api->handler = simulate_ldr_literal;
|
||||
} else if (aarch64_insn_is_ldrsw_lit(insn)) {
|
||||
api->handler = simulate_ldrsw_literal;
|
||||
} else {
|
||||
/*
|
||||
* Instruction cannot be stepped out-of-line and we don't
|
||||
@ -140,6 +136,17 @@ arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi)
|
||||
probe_opcode_t insn = le32_to_cpu(*addr);
|
||||
probe_opcode_t *scan_end = NULL;
|
||||
unsigned long size = 0, offset = 0;
|
||||
struct arch_probe_insn *api = &asi->api;
|
||||
|
||||
if (aarch64_insn_is_ldr_lit(insn)) {
|
||||
api->handler = simulate_ldr_literal;
|
||||
decoded = INSN_GOOD_NO_SLOT;
|
||||
} else if (aarch64_insn_is_ldrsw_lit(insn)) {
|
||||
api->handler = simulate_ldrsw_literal;
|
||||
decoded = INSN_GOOD_NO_SLOT;
|
||||
} else {
|
||||
decoded = arm_probe_decode_insn(insn, &asi->api);
|
||||
}
|
||||
|
||||
/*
|
||||
* If there's a symbol defined in front of and near enough to
|
||||
@ -157,7 +164,6 @@ arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi)
|
||||
else
|
||||
scan_end = addr - MAX_ATOMIC_CONTEXT_SIZE;
|
||||
}
|
||||
decoded = arm_probe_decode_insn(insn, &asi->api);
|
||||
|
||||
if (decoded != INSN_REJECTED && scan_end)
|
||||
if (is_probed_address_atomic(addr - 1, scan_end))
|
||||
|
||||
@ -171,17 +171,15 @@ simulate_tbz_tbnz(u32 opcode, long addr, struct pt_regs *regs)
|
||||
void __kprobes
|
||||
simulate_ldr_literal(u32 opcode, long addr, struct pt_regs *regs)
|
||||
{
|
||||
u64 *load_addr;
|
||||
unsigned long load_addr;
|
||||
int xn = opcode & 0x1f;
|
||||
int disp;
|
||||
|
||||
disp = ldr_displacement(opcode);
|
||||
load_addr = (u64 *) (addr + disp);
|
||||
load_addr = addr + ldr_displacement(opcode);
|
||||
|
||||
if (opcode & (1 << 30)) /* x0-x30 */
|
||||
set_x_reg(regs, xn, *load_addr);
|
||||
set_x_reg(regs, xn, READ_ONCE(*(u64 *)load_addr));
|
||||
else /* w0-w30 */
|
||||
set_w_reg(regs, xn, *load_addr);
|
||||
set_w_reg(regs, xn, READ_ONCE(*(u32 *)load_addr));
|
||||
|
||||
instruction_pointer_set(regs, instruction_pointer(regs) + 4);
|
||||
}
|
||||
@ -189,14 +187,12 @@ simulate_ldr_literal(u32 opcode, long addr, struct pt_regs *regs)
|
||||
void __kprobes
|
||||
simulate_ldrsw_literal(u32 opcode, long addr, struct pt_regs *regs)
|
||||
{
|
||||
s32 *load_addr;
|
||||
unsigned long load_addr;
|
||||
int xn = opcode & 0x1f;
|
||||
int disp;
|
||||
|
||||
disp = ldr_displacement(opcode);
|
||||
load_addr = (s32 *) (addr + disp);
|
||||
load_addr = addr + ldr_displacement(opcode);
|
||||
|
||||
set_x_reg(regs, xn, *load_addr);
|
||||
set_x_reg(regs, xn, READ_ONCE(*(s32 *)load_addr));
|
||||
|
||||
instruction_pointer_set(regs, instruction_pointer(regs) + 4);
|
||||
}
|
||||
|
||||
@ -42,7 +42,7 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
|
||||
else if (!IS_ALIGNED(addr, AARCH64_INSN_SIZE))
|
||||
return -EINVAL;
|
||||
|
||||
insn = *(probe_opcode_t *)(&auprobe->insn[0]);
|
||||
insn = le32_to_cpu(auprobe->insn);
|
||||
|
||||
switch (arm_probe_decode_insn(insn, &auprobe->api)) {
|
||||
case INSN_REJECTED:
|
||||
@ -108,7 +108,7 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
|
||||
if (!auprobe->simulate)
|
||||
return false;
|
||||
|
||||
insn = *(probe_opcode_t *)(&auprobe->insn[0]);
|
||||
insn = le32_to_cpu(auprobe->insn);
|
||||
addr = instruction_pointer(regs);
|
||||
|
||||
if (auprobe->api.handler)
|
||||
|
||||
@ -412,6 +412,9 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
|
||||
|
||||
p->thread.cpu_context.x19 = (unsigned long)args->fn;
|
||||
p->thread.cpu_context.x20 = (unsigned long)args->fn_arg;
|
||||
|
||||
if (system_supports_poe())
|
||||
p->thread.por_el0 = POR_EL0_INIT;
|
||||
}
|
||||
p->thread.cpu_context.pc = (unsigned long)ret_from_fork;
|
||||
p->thread.cpu_context.sp = (unsigned long)childregs;
|
||||
|
||||
@ -19,6 +19,7 @@
|
||||
#include <linux/ratelimit.h>
|
||||
#include <linux/rseq.h>
|
||||
#include <linux/syscalls.h>
|
||||
#include <linux/pkeys.h>
|
||||
|
||||
#include <asm/daifflags.h>
|
||||
#include <asm/debug-monitors.h>
|
||||
@ -66,10 +67,63 @@ struct rt_sigframe_user_layout {
|
||||
unsigned long end_offset;
|
||||
};
|
||||
|
||||
/*
|
||||
* Holds any EL0-controlled state that influences unprivileged memory accesses.
|
||||
* This includes both accesses done in userspace and uaccess done in the kernel.
|
||||
*
|
||||
* This state needs to be carefully managed to ensure that it doesn't cause
|
||||
* uaccess to fail when setting up the signal frame, and the signal handler
|
||||
* itself also expects a well-defined state when entered.
|
||||
*/
|
||||
struct user_access_state {
|
||||
u64 por_el0;
|
||||
};
|
||||
|
||||
#define BASE_SIGFRAME_SIZE round_up(sizeof(struct rt_sigframe), 16)
|
||||
#define TERMINATOR_SIZE round_up(sizeof(struct _aarch64_ctx), 16)
|
||||
#define EXTRA_CONTEXT_SIZE round_up(sizeof(struct extra_context), 16)
|
||||
|
||||
/*
|
||||
* Save the user access state into ua_state and reset it to disable any
|
||||
* restrictions.
|
||||
*/
|
||||
static void save_reset_user_access_state(struct user_access_state *ua_state)
|
||||
{
|
||||
if (system_supports_poe()) {
|
||||
u64 por_enable_all = 0;
|
||||
|
||||
for (int pkey = 0; pkey < arch_max_pkey(); pkey++)
|
||||
por_enable_all |= POE_RXW << (pkey * POR_BITS_PER_PKEY);
|
||||
|
||||
ua_state->por_el0 = read_sysreg_s(SYS_POR_EL0);
|
||||
write_sysreg_s(por_enable_all, SYS_POR_EL0);
|
||||
/* Ensure that any subsequent uaccess observes the updated value */
|
||||
isb();
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Set the user access state for invoking the signal handler.
|
||||
*
|
||||
* No uaccess should be done after that function is called.
|
||||
*/
|
||||
static void set_handler_user_access_state(void)
|
||||
{
|
||||
if (system_supports_poe())
|
||||
write_sysreg_s(POR_EL0_INIT, SYS_POR_EL0);
|
||||
}
|
||||
|
||||
/*
|
||||
* Restore the user access state to the values saved in ua_state.
|
||||
*
|
||||
* No uaccess should be done after that function is called.
|
||||
*/
|
||||
static void restore_user_access_state(const struct user_access_state *ua_state)
|
||||
{
|
||||
if (system_supports_poe())
|
||||
write_sysreg_s(ua_state->por_el0, SYS_POR_EL0);
|
||||
}
|
||||
|
||||
static void init_user_layout(struct rt_sigframe_user_layout *user)
|
||||
{
|
||||
const size_t reserved_size =
|
||||
@ -261,18 +315,20 @@ static int restore_fpmr_context(struct user_ctxs *user)
|
||||
return err;
|
||||
}
|
||||
|
||||
static int preserve_poe_context(struct poe_context __user *ctx)
|
||||
static int preserve_poe_context(struct poe_context __user *ctx,
|
||||
const struct user_access_state *ua_state)
|
||||
{
|
||||
int err = 0;
|
||||
|
||||
__put_user_error(POE_MAGIC, &ctx->head.magic, err);
|
||||
__put_user_error(sizeof(*ctx), &ctx->head.size, err);
|
||||
__put_user_error(read_sysreg_s(SYS_POR_EL0), &ctx->por_el0, err);
|
||||
__put_user_error(ua_state->por_el0, &ctx->por_el0, err);
|
||||
|
||||
return err;
|
||||
}
|
||||
|
||||
static int restore_poe_context(struct user_ctxs *user)
|
||||
static int restore_poe_context(struct user_ctxs *user,
|
||||
struct user_access_state *ua_state)
|
||||
{
|
||||
u64 por_el0;
|
||||
int err = 0;
|
||||
@ -282,7 +338,7 @@ static int restore_poe_context(struct user_ctxs *user)
|
||||
|
||||
__get_user_error(por_el0, &(user->poe->por_el0), err);
|
||||
if (!err)
|
||||
write_sysreg_s(por_el0, SYS_POR_EL0);
|
||||
ua_state->por_el0 = por_el0;
|
||||
|
||||
return err;
|
||||
}
|
||||
@ -850,7 +906,8 @@ static int parse_user_sigframe(struct user_ctxs *user,
|
||||
}
|
||||
|
||||
static int restore_sigframe(struct pt_regs *regs,
|
||||
struct rt_sigframe __user *sf)
|
||||
struct rt_sigframe __user *sf,
|
||||
struct user_access_state *ua_state)
|
||||
{
|
||||
sigset_t set;
|
||||
int i, err;
|
||||
@ -899,7 +956,7 @@ static int restore_sigframe(struct pt_regs *regs,
|
||||
err = restore_zt_context(&user);
|
||||
|
||||
if (err == 0 && system_supports_poe() && user.poe)
|
||||
err = restore_poe_context(&user);
|
||||
err = restore_poe_context(&user, ua_state);
|
||||
|
||||
return err;
|
||||
}
|
||||
@ -908,6 +965,7 @@ SYSCALL_DEFINE0(rt_sigreturn)
|
||||
{
|
||||
struct pt_regs *regs = current_pt_regs();
|
||||
struct rt_sigframe __user *frame;
|
||||
struct user_access_state ua_state;
|
||||
|
||||
/* Always make any pending restarted system calls return -EINTR */
|
||||
current->restart_block.fn = do_no_restart_syscall;
|
||||
@ -924,12 +982,14 @@ SYSCALL_DEFINE0(rt_sigreturn)
|
||||
if (!access_ok(frame, sizeof (*frame)))
|
||||
goto badframe;
|
||||
|
||||
if (restore_sigframe(regs, frame))
|
||||
if (restore_sigframe(regs, frame, &ua_state))
|
||||
goto badframe;
|
||||
|
||||
if (restore_altstack(&frame->uc.uc_stack))
|
||||
goto badframe;
|
||||
|
||||
restore_user_access_state(&ua_state);
|
||||
|
||||
return regs->regs[0];
|
||||
|
||||
badframe:
|
||||
@ -1035,7 +1095,8 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user,
|
||||
}
|
||||
|
||||
static int setup_sigframe(struct rt_sigframe_user_layout *user,
|
||||
struct pt_regs *regs, sigset_t *set)
|
||||
struct pt_regs *regs, sigset_t *set,
|
||||
const struct user_access_state *ua_state)
|
||||
{
|
||||
int i, err = 0;
|
||||
struct rt_sigframe __user *sf = user->sigframe;
|
||||
@ -1097,10 +1158,9 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user,
|
||||
struct poe_context __user *poe_ctx =
|
||||
apply_user_offset(user, user->poe_offset);
|
||||
|
||||
err |= preserve_poe_context(poe_ctx);
|
||||
err |= preserve_poe_context(poe_ctx, ua_state);
|
||||
}
|
||||
|
||||
|
||||
/* ZA state if present */
|
||||
if (system_supports_sme() && err == 0 && user->za_offset) {
|
||||
struct za_context __user *za_ctx =
|
||||
@ -1237,9 +1297,6 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka,
|
||||
sme_smstop();
|
||||
}
|
||||
|
||||
if (system_supports_poe())
|
||||
write_sysreg_s(POR_EL0_INIT, SYS_POR_EL0);
|
||||
|
||||
if (ka->sa.sa_flags & SA_RESTORER)
|
||||
sigtramp = ka->sa.sa_restorer;
|
||||
else
|
||||
@ -1253,6 +1310,7 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
|
||||
{
|
||||
struct rt_sigframe_user_layout user;
|
||||
struct rt_sigframe __user *frame;
|
||||
struct user_access_state ua_state;
|
||||
int err = 0;
|
||||
|
||||
fpsimd_signal_preserve_current_state();
|
||||
@ -1260,13 +1318,14 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
|
||||
if (get_sigframe(&user, ksig, regs))
|
||||
return 1;
|
||||
|
||||
save_reset_user_access_state(&ua_state);
|
||||
frame = user.sigframe;
|
||||
|
||||
__put_user_error(0, &frame->uc.uc_flags, err);
|
||||
__put_user_error(NULL, &frame->uc.uc_link, err);
|
||||
|
||||
err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
|
||||
err |= setup_sigframe(&user, regs, set);
|
||||
err |= setup_sigframe(&user, regs, set, &ua_state);
|
||||
if (err == 0) {
|
||||
setup_return(regs, &ksig->ka, &user, usig);
|
||||
if (ksig->ka.sa.sa_flags & SA_SIGINFO) {
|
||||
@ -1276,6 +1335,11 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
|
||||
}
|
||||
}
|
||||
|
||||
if (err == 0)
|
||||
set_handler_user_access_state();
|
||||
else
|
||||
restore_user_access_state(&ua_state);
|
||||
|
||||
return err;
|
||||
}
|
||||
|
||||
|
||||
@ -997,6 +997,9 @@ static int kvm_vcpu_suspend(struct kvm_vcpu *vcpu)
|
||||
static int check_vcpu_requests(struct kvm_vcpu *vcpu)
|
||||
{
|
||||
if (kvm_request_pending(vcpu)) {
|
||||
if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu))
|
||||
return -EIO;
|
||||
|
||||
if (kvm_check_request(KVM_REQ_SLEEP, vcpu))
|
||||
kvm_vcpu_sleep(vcpu);
|
||||
|
||||
@ -1031,6 +1034,8 @@ static int check_vcpu_requests(struct kvm_vcpu *vcpu)
|
||||
|
||||
if (kvm_dirty_ring_check_request(vcpu))
|
||||
return 0;
|
||||
|
||||
check_nested_vcpu_requests(vcpu);
|
||||
}
|
||||
|
||||
return 1;
|
||||
|
||||
@ -24,28 +24,25 @@
|
||||
.align 11
|
||||
|
||||
SYM_CODE_START(__kvm_hyp_init)
|
||||
ventry __invalid // Synchronous EL2t
|
||||
ventry __invalid // IRQ EL2t
|
||||
ventry __invalid // FIQ EL2t
|
||||
ventry __invalid // Error EL2t
|
||||
ventry . // Synchronous EL2t
|
||||
ventry . // IRQ EL2t
|
||||
ventry . // FIQ EL2t
|
||||
ventry . // Error EL2t
|
||||
|
||||
ventry __invalid // Synchronous EL2h
|
||||
ventry __invalid // IRQ EL2h
|
||||
ventry __invalid // FIQ EL2h
|
||||
ventry __invalid // Error EL2h
|
||||
ventry . // Synchronous EL2h
|
||||
ventry . // IRQ EL2h
|
||||
ventry . // FIQ EL2h
|
||||
ventry . // Error EL2h
|
||||
|
||||
ventry __do_hyp_init // Synchronous 64-bit EL1
|
||||
ventry __invalid // IRQ 64-bit EL1
|
||||
ventry __invalid // FIQ 64-bit EL1
|
||||
ventry __invalid // Error 64-bit EL1
|
||||
ventry . // IRQ 64-bit EL1
|
||||
ventry . // FIQ 64-bit EL1
|
||||
ventry . // Error 64-bit EL1
|
||||
|
||||
ventry __invalid // Synchronous 32-bit EL1
|
||||
ventry __invalid // IRQ 32-bit EL1
|
||||
ventry __invalid // FIQ 32-bit EL1
|
||||
ventry __invalid // Error 32-bit EL1
|
||||
|
||||
__invalid:
|
||||
b .
|
||||
ventry . // Synchronous 32-bit EL1
|
||||
ventry . // IRQ 32-bit EL1
|
||||
ventry . // FIQ 32-bit EL1
|
||||
ventry . // Error 32-bit EL1
|
||||
|
||||
/*
|
||||
* Only uses x0..x3 so as to not clobber callee-saved SMCCC registers.
|
||||
@ -76,6 +73,13 @@ __do_hyp_init:
|
||||
eret
|
||||
SYM_CODE_END(__kvm_hyp_init)
|
||||
|
||||
SYM_CODE_START_LOCAL(__kvm_init_el2_state)
|
||||
/* Initialize EL2 CPU state to sane values. */
|
||||
init_el2_state // Clobbers x0..x2
|
||||
finalise_el2_state
|
||||
ret
|
||||
SYM_CODE_END(__kvm_init_el2_state)
|
||||
|
||||
/*
|
||||
* Initialize the hypervisor in EL2.
|
||||
*
|
||||
@ -102,9 +106,12 @@ SYM_CODE_START_LOCAL(___kvm_hyp_init)
|
||||
// TPIDR_EL2 is used to preserve x0 across the macro maze...
|
||||
isb
|
||||
msr tpidr_el2, x0
|
||||
init_el2_state
|
||||
finalise_el2_state
|
||||
str lr, [x0, #NVHE_INIT_TMP]
|
||||
|
||||
bl __kvm_init_el2_state
|
||||
|
||||
mrs x0, tpidr_el2
|
||||
ldr lr, [x0, #NVHE_INIT_TMP]
|
||||
|
||||
1:
|
||||
ldr x1, [x0, #NVHE_INIT_TPIDR_EL2]
|
||||
@ -199,9 +206,8 @@ SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu)
|
||||
|
||||
2: msr SPsel, #1 // We want to use SP_EL{1,2}
|
||||
|
||||
/* Initialize EL2 CPU state to sane values. */
|
||||
init_el2_state // Clobbers x0..x2
|
||||
finalise_el2_state
|
||||
bl __kvm_init_el2_state
|
||||
|
||||
__init_el2_nvhe_prepare_eret
|
||||
|
||||
/* Enable MMU, set vectors and stack. */
|
||||
|
||||
@ -317,7 +317,7 @@ int kvm_smccc_call_handler(struct kvm_vcpu *vcpu)
|
||||
* to the guest, and hide SSBS so that the
|
||||
* guest stays protected.
|
||||
*/
|
||||
if (cpus_have_final_cap(ARM64_SSBS))
|
||||
if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SSBS, IMP))
|
||||
break;
|
||||
fallthrough;
|
||||
case SPECTRE_UNAFFECTED:
|
||||
@ -428,7 +428,7 @@ int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
|
||||
* Convert the workaround level into an easy-to-compare number, where higher
|
||||
* values mean better protection.
|
||||
*/
|
||||
static int get_kernel_wa_level(u64 regid)
|
||||
static int get_kernel_wa_level(struct kvm_vcpu *vcpu, u64 regid)
|
||||
{
|
||||
switch (regid) {
|
||||
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
|
||||
@ -449,7 +449,7 @@ static int get_kernel_wa_level(u64 regid)
|
||||
* don't have any FW mitigation if SSBS is there at
|
||||
* all times.
|
||||
*/
|
||||
if (cpus_have_final_cap(ARM64_SSBS))
|
||||
if (kvm_has_feat(vcpu->kvm, ID_AA64PFR1_EL1, SSBS, IMP))
|
||||
return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL;
|
||||
fallthrough;
|
||||
case SPECTRE_UNAFFECTED:
|
||||
@ -486,7 +486,7 @@ int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
|
||||
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1:
|
||||
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2:
|
||||
case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3:
|
||||
val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
|
||||
val = get_kernel_wa_level(vcpu, reg->id) & KVM_REG_FEATURE_LEVEL_MASK;
|
||||
break;
|
||||
case KVM_REG_ARM_STD_BMAP:
|
||||
val = READ_ONCE(smccc_feat->std_bmap);
|
||||
@ -588,7 +588,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
|
||||
if (val & ~KVM_REG_FEATURE_LEVEL_MASK)
|
||||
return -EINVAL;
|
||||
|
||||
if (get_kernel_wa_level(reg->id) < val)
|
||||
if (get_kernel_wa_level(vcpu, reg->id) < val)
|
||||
return -EINVAL;
|
||||
|
||||
return 0;
|
||||
@ -624,7 +624,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
|
||||
* We can deal with NOT_AVAIL on NOT_REQUIRED, but not the
|
||||
* other way around.
|
||||
*/
|
||||
if (get_kernel_wa_level(reg->id) < wa_level)
|
||||
if (get_kernel_wa_level(vcpu, reg->id) < wa_level)
|
||||
return -EINVAL;
|
||||
|
||||
return 0;
|
||||
|
||||
@ -328,9 +328,10 @@ static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64
|
||||
may_block));
|
||||
}
|
||||
|
||||
void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size)
|
||||
void kvm_stage2_unmap_range(struct kvm_s2_mmu *mmu, phys_addr_t start,
|
||||
u64 size, bool may_block)
|
||||
{
|
||||
__unmap_stage2_range(mmu, start, size, true);
|
||||
__unmap_stage2_range(mmu, start, size, may_block);
|
||||
}
|
||||
|
||||
void kvm_stage2_flush_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, phys_addr_t end)
|
||||
@ -1015,7 +1016,7 @@ static void stage2_unmap_memslot(struct kvm *kvm,
|
||||
|
||||
if (!(vma->vm_flags & VM_PFNMAP)) {
|
||||
gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
|
||||
kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, vm_end - vm_start);
|
||||
kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, vm_end - vm_start, true);
|
||||
}
|
||||
hva = vm_end;
|
||||
} while (hva < reg_end);
|
||||
@ -1042,7 +1043,7 @@ void stage2_unmap_vm(struct kvm *kvm)
|
||||
kvm_for_each_memslot(memslot, bkt, slots)
|
||||
stage2_unmap_memslot(kvm, memslot);
|
||||
|
||||
kvm_nested_s2_unmap(kvm);
|
||||
kvm_nested_s2_unmap(kvm, true);
|
||||
|
||||
write_unlock(&kvm->mmu_lock);
|
||||
mmap_read_unlock(current->mm);
|
||||
@ -1912,7 +1913,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
|
||||
(range->end - range->start) << PAGE_SHIFT,
|
||||
range->may_block);
|
||||
|
||||
kvm_nested_s2_unmap(kvm);
|
||||
kvm_nested_s2_unmap(kvm, range->may_block);
|
||||
return false;
|
||||
}
|
||||
|
||||
@ -2179,8 +2180,8 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
|
||||
phys_addr_t size = slot->npages << PAGE_SHIFT;
|
||||
|
||||
write_lock(&kvm->mmu_lock);
|
||||
kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, size);
|
||||
kvm_nested_s2_unmap(kvm);
|
||||
kvm_stage2_unmap_range(&kvm->arch.mmu, gpa, size, true);
|
||||
kvm_nested_s2_unmap(kvm, true);
|
||||
write_unlock(&kvm->mmu_lock);
|
||||
}
|
||||
|
||||
|
||||
@ -632,9 +632,9 @@ static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu)
|
||||
/* Set the scene for the next search */
|
||||
kvm->arch.nested_mmus_next = (i + 1) % kvm->arch.nested_mmus_size;
|
||||
|
||||
/* Clear the old state */
|
||||
/* Make sure we don't forget to do the laundry */
|
||||
if (kvm_s2_mmu_valid(s2_mmu))
|
||||
kvm_stage2_unmap_range(s2_mmu, 0, kvm_phys_size(s2_mmu));
|
||||
s2_mmu->pending_unmap = true;
|
||||
|
||||
/*
|
||||
* The virtual VMID (modulo CnP) will be used as a key when matching
|
||||
@ -650,6 +650,16 @@ static struct kvm_s2_mmu *get_s2_mmu_nested(struct kvm_vcpu *vcpu)
|
||||
|
||||
out:
|
||||
atomic_inc(&s2_mmu->refcnt);
|
||||
|
||||
/*
|
||||
* Set the vCPU request to perform an unmap, even if the pending unmap
|
||||
* originates from another vCPU. This guarantees that the MMU has been
|
||||
* completely unmapped before any vCPU actually uses it, and allows
|
||||
* multiple vCPUs to lend a hand with completing the unmap.
|
||||
*/
|
||||
if (s2_mmu->pending_unmap)
|
||||
kvm_make_request(KVM_REQ_NESTED_S2_UNMAP, vcpu);
|
||||
|
||||
return s2_mmu;
|
||||
}
|
||||
|
||||
@ -663,6 +673,13 @@ void kvm_init_nested_s2_mmu(struct kvm_s2_mmu *mmu)
|
||||
|
||||
void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu)
|
||||
{
|
||||
/*
|
||||
* The vCPU kept its reference on the MMU after the last put, keep
|
||||
* rolling with it.
|
||||
*/
|
||||
if (vcpu->arch.hw_mmu)
|
||||
return;
|
||||
|
||||
if (is_hyp_ctxt(vcpu)) {
|
||||
vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu;
|
||||
} else {
|
||||
@ -674,10 +691,18 @@ void kvm_vcpu_load_hw_mmu(struct kvm_vcpu *vcpu)
|
||||
|
||||
void kvm_vcpu_put_hw_mmu(struct kvm_vcpu *vcpu)
|
||||
{
|
||||
if (kvm_is_nested_s2_mmu(vcpu->kvm, vcpu->arch.hw_mmu)) {
|
||||
/*
|
||||
* Keep a reference on the associated stage-2 MMU if the vCPU is
|
||||
* scheduling out and not in WFI emulation, suggesting it is likely to
|
||||
* reuse the MMU sometime soon.
|
||||
*/
|
||||
if (vcpu->scheduled_out && !vcpu_get_flag(vcpu, IN_WFI))
|
||||
return;
|
||||
|
||||
if (kvm_is_nested_s2_mmu(vcpu->kvm, vcpu->arch.hw_mmu))
|
||||
atomic_dec(&vcpu->arch.hw_mmu->refcnt);
|
||||
vcpu->arch.hw_mmu = NULL;
|
||||
}
|
||||
|
||||
vcpu->arch.hw_mmu = NULL;
|
||||
}
|
||||
|
||||
/*
|
||||
@ -730,7 +755,7 @@ void kvm_nested_s2_wp(struct kvm *kvm)
|
||||
}
|
||||
}
|
||||
|
||||
void kvm_nested_s2_unmap(struct kvm *kvm)
|
||||
void kvm_nested_s2_unmap(struct kvm *kvm, bool may_block)
|
||||
{
|
||||
int i;
|
||||
|
||||
@ -740,7 +765,7 @@ void kvm_nested_s2_unmap(struct kvm *kvm)
|
||||
struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i];
|
||||
|
||||
if (kvm_s2_mmu_valid(mmu))
|
||||
kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu));
|
||||
kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu), may_block);
|
||||
}
|
||||
}
|
||||
|
||||
@ -1184,3 +1209,17 @@ int kvm_init_nv_sysregs(struct kvm *kvm)
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
void check_nested_vcpu_requests(struct kvm_vcpu *vcpu)
|
||||
{
|
||||
if (kvm_check_request(KVM_REQ_NESTED_S2_UNMAP, vcpu)) {
|
||||
struct kvm_s2_mmu *mmu = vcpu->arch.hw_mmu;
|
||||
|
||||
write_lock(&vcpu->kvm->mmu_lock);
|
||||
if (mmu->pending_unmap) {
|
||||
kvm_stage2_unmap_range(mmu, 0, kvm_phys_size(mmu), true);
|
||||
mmu->pending_unmap = false;
|
||||
}
|
||||
write_unlock(&vcpu->kvm->mmu_lock);
|
||||
}
|
||||
}
|
||||
|
||||
@ -1527,6 +1527,14 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
|
||||
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE);
|
||||
|
||||
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_SME);
|
||||
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_RNDR_trap);
|
||||
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_NMI);
|
||||
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTE_frac);
|
||||
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_GCS);
|
||||
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_THE);
|
||||
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_MTEX);
|
||||
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_DF2);
|
||||
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_EL1_PFAR);
|
||||
break;
|
||||
case SYS_ID_AA64PFR2_EL1:
|
||||
/* We only expose FPMR */
|
||||
@ -1550,7 +1558,8 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu,
|
||||
val &= ~ID_AA64MMFR2_EL1_CCIDX_MASK;
|
||||
break;
|
||||
case SYS_ID_AA64MMFR3_EL1:
|
||||
val &= ID_AA64MMFR3_EL1_TCRX | ID_AA64MMFR3_EL1_S1POE;
|
||||
val &= ID_AA64MMFR3_EL1_TCRX | ID_AA64MMFR3_EL1_S1POE |
|
||||
ID_AA64MMFR3_EL1_S1PIE;
|
||||
break;
|
||||
case SYS_ID_MMFR4_EL1:
|
||||
val &= ~ARM64_FEATURE_MASK(ID_MMFR4_EL1_CCIDX);
|
||||
@ -1985,7 +1994,7 @@ static u64 reset_clidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
|
||||
* one cache line.
|
||||
*/
|
||||
if (kvm_has_mte(vcpu->kvm))
|
||||
clidr |= 2 << CLIDR_TTYPE_SHIFT(loc);
|
||||
clidr |= 2ULL << CLIDR_TTYPE_SHIFT(loc);
|
||||
|
||||
__vcpu_sys_reg(vcpu, r->reg) = clidr;
|
||||
|
||||
@ -2376,7 +2385,19 @@ static const struct sys_reg_desc sys_reg_descs[] = {
|
||||
ID_AA64PFR0_EL1_RAS |
|
||||
ID_AA64PFR0_EL1_AdvSIMD |
|
||||
ID_AA64PFR0_EL1_FP), },
|
||||
ID_SANITISED(ID_AA64PFR1_EL1),
|
||||
ID_WRITABLE(ID_AA64PFR1_EL1, ~(ID_AA64PFR1_EL1_PFAR |
|
||||
ID_AA64PFR1_EL1_DF2 |
|
||||
ID_AA64PFR1_EL1_MTEX |
|
||||
ID_AA64PFR1_EL1_THE |
|
||||
ID_AA64PFR1_EL1_GCS |
|
||||
ID_AA64PFR1_EL1_MTE_frac |
|
||||
ID_AA64PFR1_EL1_NMI |
|
||||
ID_AA64PFR1_EL1_RNDR_trap |
|
||||
ID_AA64PFR1_EL1_SME |
|
||||
ID_AA64PFR1_EL1_RES0 |
|
||||
ID_AA64PFR1_EL1_MPAM_frac |
|
||||
ID_AA64PFR1_EL1_RAS_frac |
|
||||
ID_AA64PFR1_EL1_MTE)),
|
||||
ID_WRITABLE(ID_AA64PFR2_EL1, ID_AA64PFR2_EL1_FPMR),
|
||||
ID_UNALLOCATED(4,3),
|
||||
ID_WRITABLE(ID_AA64ZFR0_EL1, ~ID_AA64ZFR0_EL1_RES0),
|
||||
@ -2390,7 +2411,21 @@ static const struct sys_reg_desc sys_reg_descs[] = {
|
||||
.get_user = get_id_reg,
|
||||
.set_user = set_id_aa64dfr0_el1,
|
||||
.reset = read_sanitised_id_aa64dfr0_el1,
|
||||
.val = ID_AA64DFR0_EL1_PMUVer_MASK |
|
||||
/*
|
||||
* Prior to FEAT_Debugv8.9, the architecture defines context-aware
|
||||
* breakpoints (CTX_CMPs) as the highest numbered breakpoints (BRPs).
|
||||
* KVM does not trap + emulate the breakpoint registers, and as such
|
||||
* cannot support a layout that misaligns with the underlying hardware.
|
||||
* While it may be possible to describe a subset that aligns with
|
||||
* hardware, just prevent changes to BRPs and CTX_CMPs altogether for
|
||||
* simplicity.
|
||||
*
|
||||
* See DDI0487K.a, section D2.8.3 Breakpoint types and linking
|
||||
* of breakpoints for more details.
|
||||
*/
|
||||
.val = ID_AA64DFR0_EL1_DoubleLock_MASK |
|
||||
ID_AA64DFR0_EL1_WRPs_MASK |
|
||||
ID_AA64DFR0_EL1_PMUVer_MASK |
|
||||
ID_AA64DFR0_EL1_DebugVer_MASK, },
|
||||
ID_SANITISED(ID_AA64DFR1_EL1),
|
||||
ID_UNALLOCATED(5,2),
|
||||
@ -2433,6 +2468,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
|
||||
ID_AA64MMFR2_EL1_NV |
|
||||
ID_AA64MMFR2_EL1_CCIDX)),
|
||||
ID_WRITABLE(ID_AA64MMFR3_EL1, (ID_AA64MMFR3_EL1_TCRX |
|
||||
ID_AA64MMFR3_EL1_S1PIE |
|
||||
ID_AA64MMFR3_EL1_S1POE)),
|
||||
ID_SANITISED(ID_AA64MMFR4_EL1),
|
||||
ID_UNALLOCATED(7,5),
|
||||
@ -2903,7 +2939,7 @@ static bool handle_alle1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
|
||||
* Drop all shadow S2s, resulting in S1/S2 TLBIs for each of the
|
||||
* corresponding VMIDs.
|
||||
*/
|
||||
kvm_nested_s2_unmap(vcpu->kvm);
|
||||
kvm_nested_s2_unmap(vcpu->kvm, true);
|
||||
|
||||
write_unlock(&vcpu->kvm->mmu_lock);
|
||||
|
||||
@ -2955,7 +2991,30 @@ union tlbi_info {
|
||||
static void s2_mmu_unmap_range(struct kvm_s2_mmu *mmu,
|
||||
const union tlbi_info *info)
|
||||
{
|
||||
kvm_stage2_unmap_range(mmu, info->range.start, info->range.size);
|
||||
/*
|
||||
* The unmap operation is allowed to drop the MMU lock and block, which
|
||||
* means that @mmu could be used for a different context than the one
|
||||
* currently being invalidated.
|
||||
*
|
||||
* This behavior is still safe, as:
|
||||
*
|
||||
* 1) The vCPU(s) that recycled the MMU are responsible for invalidating
|
||||
* the entire MMU before reusing it, which still honors the intent
|
||||
* of a TLBI.
|
||||
*
|
||||
* 2) Until the guest TLBI instruction is 'retired' (i.e. increment PC
|
||||
* and ERET to the guest), other vCPUs are allowed to use stale
|
||||
* translations.
|
||||
*
|
||||
* 3) Accidentally unmapping an unrelated MMU context is nonfatal, and
|
||||
* at worst may cause more aborts for shadow stage-2 fills.
|
||||
*
|
||||
* Dropping the MMU lock also implies that shadow stage-2 fills could
|
||||
* happen behind the back of the TLBI. This is still safe, though, as
|
||||
* the L1 needs to put its stage-2 in a consistent state before doing
|
||||
* the TLBI.
|
||||
*/
|
||||
kvm_stage2_unmap_range(mmu, info->range.start, info->range.size, true);
|
||||
}
|
||||
|
||||
static bool handle_vmalls12e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
|
||||
@ -3050,7 +3109,11 @@ static void s2_mmu_unmap_ipa(struct kvm_s2_mmu *mmu,
|
||||
max_size = compute_tlb_inval_range(mmu, info->ipa.addr);
|
||||
base_addr &= ~(max_size - 1);
|
||||
|
||||
kvm_stage2_unmap_range(mmu, base_addr, max_size);
|
||||
/*
|
||||
* See comment in s2_mmu_unmap_range() for why this is allowed to
|
||||
* reschedule.
|
||||
*/
|
||||
kvm_stage2_unmap_range(mmu, base_addr, max_size, true);
|
||||
}
|
||||
|
||||
static bool handle_ipas2e1is(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
|
||||
|
||||
@ -417,8 +417,28 @@ static void __kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
|
||||
kfree(vgic_cpu->private_irqs);
|
||||
vgic_cpu->private_irqs = NULL;
|
||||
|
||||
if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
|
||||
if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
|
||||
/*
|
||||
* If this vCPU is being destroyed because of a failed creation
|
||||
* then unregister the redistributor to avoid leaving behind a
|
||||
* dangling pointer to the vCPU struct.
|
||||
*
|
||||
* vCPUs that have been successfully created (i.e. added to
|
||||
* kvm->vcpu_array) get unregistered in kvm_vgic_destroy(), as
|
||||
* this function gets called while holding kvm->arch.config_lock
|
||||
* in the VM teardown path and would otherwise introduce a lock
|
||||
* inversion w.r.t. kvm->srcu.
|
||||
*
|
||||
* vCPUs that failed creation are torn down outside of the
|
||||
* kvm->arch.config_lock and do not get unregistered in
|
||||
* kvm_vgic_destroy(), meaning it is both safe and necessary to
|
||||
* do so here.
|
||||
*/
|
||||
if (kvm_get_vcpu_by_id(vcpu->kvm, vcpu->vcpu_id) != vcpu)
|
||||
vgic_unregister_redist_iodev(vcpu);
|
||||
|
||||
vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF;
|
||||
}
|
||||
}
|
||||
|
||||
void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu)
|
||||
@ -524,22 +544,31 @@ int kvm_vgic_map_resources(struct kvm *kvm)
|
||||
if (ret)
|
||||
goto out;
|
||||
|
||||
dist->ready = true;
|
||||
dist_base = dist->vgic_dist_base;
|
||||
mutex_unlock(&kvm->arch.config_lock);
|
||||
|
||||
ret = vgic_register_dist_iodev(kvm, dist_base, type);
|
||||
if (ret)
|
||||
if (ret) {
|
||||
kvm_err("Unable to register VGIC dist MMIO regions\n");
|
||||
goto out_slots;
|
||||
}
|
||||
|
||||
/*
|
||||
* kvm_io_bus_register_dev() guarantees all readers see the new MMIO
|
||||
* registration before returning through synchronize_srcu(), which also
|
||||
* implies a full memory barrier. As such, marking the distributor as
|
||||
* 'ready' here is guaranteed to be ordered after all vCPUs having seen
|
||||
* a completely configured distributor.
|
||||
*/
|
||||
dist->ready = true;
|
||||
goto out_slots;
|
||||
out:
|
||||
mutex_unlock(&kvm->arch.config_lock);
|
||||
out_slots:
|
||||
mutex_unlock(&kvm->slots_lock);
|
||||
|
||||
if (ret)
|
||||
kvm_vgic_destroy(kvm);
|
||||
kvm_vm_dead(kvm);
|
||||
|
||||
mutex_unlock(&kvm->slots_lock);
|
||||
|
||||
return ret;
|
||||
}
|
||||
|
||||
@ -236,7 +236,12 @@ static int vgic_set_common_attr(struct kvm_device *dev,
|
||||
|
||||
mutex_lock(&dev->kvm->arch.config_lock);
|
||||
|
||||
if (vgic_ready(dev->kvm) || dev->kvm->arch.vgic.nr_spis)
|
||||
/*
|
||||
* Either userspace has already configured NR_IRQS or
|
||||
* the vgic has already been initialized and vgic_init()
|
||||
* supplied a default amount of SPIs.
|
||||
*/
|
||||
if (dev->kvm->arch.vgic.nr_spis)
|
||||
ret = -EBUSY;
|
||||
else
|
||||
dev->kvm->arch.vgic.nr_spis =
|
||||
|
||||
@ -2220,7 +2220,11 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
|
||||
emit(A64_STR64I(A64_R(20), A64_SP, regs_off + 8), ctx);
|
||||
|
||||
if (flags & BPF_TRAMP_F_CALL_ORIG) {
|
||||
emit_a64_mov_i64(A64_R(0), (const u64)im, ctx);
|
||||
/* for the first pass, assume the worst case */
|
||||
if (!ctx->image)
|
||||
ctx->idx += 4;
|
||||
else
|
||||
emit_a64_mov_i64(A64_R(0), (const u64)im, ctx);
|
||||
emit_call((const u64)__bpf_tramp_enter, ctx);
|
||||
}
|
||||
|
||||
@ -2264,7 +2268,11 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
|
||||
|
||||
if (flags & BPF_TRAMP_F_CALL_ORIG) {
|
||||
im->ip_epilogue = ctx->ro_image + ctx->idx;
|
||||
emit_a64_mov_i64(A64_R(0), (const u64)im, ctx);
|
||||
/* for the first pass, assume the worst case */
|
||||
if (!ctx->image)
|
||||
ctx->idx += 4;
|
||||
else
|
||||
emit_a64_mov_i64(A64_R(0), (const u64)im, ctx);
|
||||
emit_call((const u64)__bpf_tramp_exit, ctx);
|
||||
}
|
||||
|
||||
|
||||
@ -26,6 +26,10 @@ struct loongson_board_info {
|
||||
|
||||
#define NR_WORDS DIV_ROUND_UP(NR_CPUS, BITS_PER_LONG)
|
||||
|
||||
/*
|
||||
* The "core" of cores_per_node and cores_per_package stands for a
|
||||
* logical core, which means in a SMT system it stands for a thread.
|
||||
*/
|
||||
struct loongson_system_configuration {
|
||||
int nr_cpus;
|
||||
int nr_nodes;
|
||||
|
||||
@ -16,7 +16,7 @@
|
||||
#define XRANGE_SHIFT (48)
|
||||
|
||||
/* Valid address length */
|
||||
#define XRANGE_SHADOW_SHIFT (PGDIR_SHIFT + PAGE_SHIFT - 3)
|
||||
#define XRANGE_SHADOW_SHIFT min(cpu_vabits, VA_BITS)
|
||||
/* Used for taking out the valid address */
|
||||
#define XRANGE_SHADOW_MASK GENMASK_ULL(XRANGE_SHADOW_SHIFT - 1, 0)
|
||||
/* One segment whole address space size */
|
||||
|
||||
@ -250,7 +250,7 @@
|
||||
#define CSR_ESTAT_IS_WIDTH 15
|
||||
#define CSR_ESTAT_IS (_ULCAST_(0x7fff) << CSR_ESTAT_IS_SHIFT)
|
||||
|
||||
#define LOONGARCH_CSR_ERA 0x6 /* ERA */
|
||||
#define LOONGARCH_CSR_ERA 0x6 /* Exception return address */
|
||||
|
||||
#define LOONGARCH_CSR_BADV 0x7 /* Bad virtual address */
|
||||
|
||||
|
||||
@ -10,6 +10,7 @@
|
||||
|
||||
#define __HAVE_ARCH_PMD_ALLOC_ONE
|
||||
#define __HAVE_ARCH_PUD_ALLOC_ONE
|
||||
#define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL
|
||||
#include <asm-generic/pgalloc.h>
|
||||
|
||||
static inline void pmd_populate_kernel(struct mm_struct *mm,
|
||||
@ -44,6 +45,16 @@ extern void pagetable_init(void);
|
||||
|
||||
extern pgd_t *pgd_alloc(struct mm_struct *mm);
|
||||
|
||||
static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
|
||||
{
|
||||
pte_t *pte = __pte_alloc_one_kernel(mm);
|
||||
|
||||
if (pte)
|
||||
kernel_pte_init(pte);
|
||||
|
||||
return pte;
|
||||
}
|
||||
|
||||
#define __pte_free_tlb(tlb, pte, address) \
|
||||
do { \
|
||||
pagetable_pte_dtor(page_ptdesc(pte)); \
|
||||
|
||||
@ -269,6 +269,7 @@ extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pm
|
||||
extern void pgd_init(void *addr);
|
||||
extern void pud_init(void *addr);
|
||||
extern void pmd_init(void *addr);
|
||||
extern void kernel_pte_init(void *addr);
|
||||
|
||||
/*
|
||||
* Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that
|
||||
@ -325,39 +326,17 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
|
||||
{
|
||||
WRITE_ONCE(*ptep, pteval);
|
||||
|
||||
if (pte_val(pteval) & _PAGE_GLOBAL) {
|
||||
pte_t *buddy = ptep_buddy(ptep);
|
||||
/*
|
||||
* Make sure the buddy is global too (if it's !none,
|
||||
* it better already be global)
|
||||
*/
|
||||
if (pte_none(ptep_get(buddy))) {
|
||||
#ifdef CONFIG_SMP
|
||||
/*
|
||||
* For SMP, multiple CPUs can race, so we need
|
||||
* to do this atomically.
|
||||
*/
|
||||
__asm__ __volatile__(
|
||||
__AMOR "$zero, %[global], %[buddy] \n"
|
||||
: [buddy] "+ZB" (buddy->pte)
|
||||
: [global] "r" (_PAGE_GLOBAL)
|
||||
: "memory");
|
||||
|
||||
DBAR(0b11000); /* o_wrw = 0b11000 */
|
||||
#else /* !CONFIG_SMP */
|
||||
WRITE_ONCE(*buddy, __pte(pte_val(ptep_get(buddy)) | _PAGE_GLOBAL));
|
||||
#endif /* CONFIG_SMP */
|
||||
}
|
||||
}
|
||||
if (pte_val(pteval) & _PAGE_GLOBAL)
|
||||
DBAR(0b11000); /* o_wrw = 0b11000 */
|
||||
#endif
|
||||
}
|
||||
|
||||
static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
|
||||
{
|
||||
/* Preserve global status for the pair */
|
||||
if (pte_val(ptep_get(ptep_buddy(ptep))) & _PAGE_GLOBAL)
|
||||
set_pte(ptep, __pte(_PAGE_GLOBAL));
|
||||
else
|
||||
set_pte(ptep, __pte(0));
|
||||
pte_t pte = ptep_get(ptep);
|
||||
pte_val(pte) &= _PAGE_GLOBAL;
|
||||
set_pte(ptep, pte);
|
||||
}
|
||||
|
||||
#define PGD_T_LOG2 (__builtin_ffs(sizeof(pgd_t)) - 1)
|
||||
|
||||
@ -293,13 +293,15 @@ unsigned long stack_top(void)
|
||||
{
|
||||
unsigned long top = TASK_SIZE & PAGE_MASK;
|
||||
|
||||
/* Space for the VDSO & data page */
|
||||
top -= PAGE_ALIGN(current->thread.vdso->size);
|
||||
top -= VVAR_SIZE;
|
||||
if (current->thread.vdso) {
|
||||
/* Space for the VDSO & data page */
|
||||
top -= PAGE_ALIGN(current->thread.vdso->size);
|
||||
top -= VVAR_SIZE;
|
||||
|
||||
/* Space to randomize the VDSO base */
|
||||
if (current->flags & PF_RANDOMIZE)
|
||||
top -= VDSO_RANDOMIZE_SIZE;
|
||||
/* Space to randomize the VDSO base */
|
||||
if (current->flags & PF_RANDOMIZE)
|
||||
top -= VDSO_RANDOMIZE_SIZE;
|
||||
}
|
||||
|
||||
return top;
|
||||
}
|
||||
|
||||
@ -55,6 +55,7 @@
|
||||
#define SMBIOS_FREQHIGH_OFFSET 0x17
|
||||
#define SMBIOS_FREQLOW_MASK 0xFF
|
||||
#define SMBIOS_CORE_PACKAGE_OFFSET 0x23
|
||||
#define SMBIOS_THREAD_PACKAGE_OFFSET 0x25
|
||||
#define LOONGSON_EFI_ENABLE (1 << 3)
|
||||
|
||||
unsigned long fw_arg0, fw_arg1, fw_arg2;
|
||||
@ -125,7 +126,7 @@ static void __init parse_cpu_table(const struct dmi_header *dm)
|
||||
cpu_clock_freq = freq_temp * 1000000;
|
||||
|
||||
loongson_sysconf.cpuname = (void *)dmi_string_parse(dm, dmi_data[16]);
|
||||
loongson_sysconf.cores_per_package = *(dmi_data + SMBIOS_CORE_PACKAGE_OFFSET);
|
||||
loongson_sysconf.cores_per_package = *(dmi_data + SMBIOS_THREAD_PACKAGE_OFFSET);
|
||||
|
||||
pr_info("CpuClock = %llu\n", cpu_clock_freq);
|
||||
}
|
||||
|
||||
@ -555,6 +555,9 @@ asmlinkage void noinstr do_ale(struct pt_regs *regs)
|
||||
#else
|
||||
unsigned int *pc;
|
||||
|
||||
if (regs->csr_prmd & CSR_PRMD_PIE)
|
||||
local_irq_enable();
|
||||
|
||||
perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, regs->csr_badvaddr);
|
||||
|
||||
/*
|
||||
@ -579,6 +582,8 @@ asmlinkage void noinstr do_ale(struct pt_regs *regs)
|
||||
die_if_kernel("Kernel ale access", regs);
|
||||
force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)regs->csr_badvaddr);
|
||||
out:
|
||||
if (regs->csr_prmd & CSR_PRMD_PIE)
|
||||
local_irq_disable();
|
||||
#endif
|
||||
irqentry_exit(regs, state);
|
||||
}
|
||||
|
||||
@ -34,7 +34,6 @@ static union {
|
||||
struct loongarch_vdso_data vdata;
|
||||
} loongarch_vdso_data __page_aligned_data;
|
||||
|
||||
static struct page *vdso_pages[] = { NULL };
|
||||
struct vdso_data *vdso_data = generic_vdso_data.data;
|
||||
struct vdso_pcpu_data *vdso_pdata = loongarch_vdso_data.vdata.pdata;
|
||||
struct vdso_rng_data *vdso_rng_data = &loongarch_vdso_data.vdata.rng_data;
|
||||
@ -85,10 +84,8 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
|
||||
|
||||
struct loongarch_vdso_info vdso_info = {
|
||||
.vdso = vdso_start,
|
||||
.size = PAGE_SIZE,
|
||||
.code_mapping = {
|
||||
.name = "[vdso]",
|
||||
.pages = vdso_pages,
|
||||
.mremap = vdso_mremap,
|
||||
},
|
||||
.data_mapping = {
|
||||
@ -103,11 +100,14 @@ static int __init init_vdso(void)
|
||||
unsigned long i, cpu, pfn;
|
||||
|
||||
BUG_ON(!PAGE_ALIGNED(vdso_info.vdso));
|
||||
BUG_ON(!PAGE_ALIGNED(vdso_info.size));
|
||||
|
||||
for_each_possible_cpu(cpu)
|
||||
vdso_pdata[cpu].node = cpu_to_node(cpu);
|
||||
|
||||
vdso_info.size = PAGE_ALIGN(vdso_end - vdso_start);
|
||||
vdso_info.code_mapping.pages =
|
||||
kcalloc(vdso_info.size / PAGE_SIZE, sizeof(struct page *), GFP_KERNEL);
|
||||
|
||||
pfn = __phys_to_pfn(__pa_symbol(vdso_info.vdso));
|
||||
for (i = 0; i < vdso_info.size / PAGE_SIZE; i++)
|
||||
vdso_info.code_mapping.pages[i] = pfn_to_page(pfn + i);
|
||||
|
||||
@ -161,10 +161,11 @@ static void _kvm_save_timer(struct kvm_vcpu *vcpu)
|
||||
if (kvm_vcpu_is_blocking(vcpu)) {
|
||||
|
||||
/*
|
||||
* HRTIMER_MODE_PINNED is suggested since vcpu may run in
|
||||
* the same physical cpu in next time
|
||||
* HRTIMER_MODE_PINNED_HARD is suggested since vcpu may run in
|
||||
* the same physical cpu in next time, and the timer should run
|
||||
* in hardirq context even in the PREEMPT_RT case.
|
||||
*/
|
||||
hrtimer_start(&vcpu->arch.swtimer, expire, HRTIMER_MODE_ABS_PINNED);
|
||||
hrtimer_start(&vcpu->arch.swtimer, expire, HRTIMER_MODE_ABS_PINNED_HARD);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@ -1457,7 +1457,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
|
||||
vcpu->arch.vpid = 0;
|
||||
vcpu->arch.flush_gpa = INVALID_GPA;
|
||||
|
||||
hrtimer_init(&vcpu->arch.swtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
|
||||
hrtimer_init(&vcpu->arch.swtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
|
||||
vcpu->arch.swtimer.function = kvm_swtimer_wakeup;
|
||||
|
||||
vcpu->arch.handle_exit = kvm_handle_exit;
|
||||
|
||||
@ -201,7 +201,9 @@ pte_t * __init populate_kernel_pte(unsigned long addr)
|
||||
pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
|
||||
if (!pte)
|
||||
panic("%s: Failed to allocate memory\n", __func__);
|
||||
|
||||
pmd_populate_kernel(&init_mm, pmd, pte);
|
||||
kernel_pte_init(pte);
|
||||
}
|
||||
|
||||
return pte_offset_kernel(pmd, addr);
|
||||
|
||||
@ -116,6 +116,26 @@ void pud_init(void *addr)
|
||||
EXPORT_SYMBOL_GPL(pud_init);
|
||||
#endif
|
||||
|
||||
void kernel_pte_init(void *addr)
|
||||
{
|
||||
unsigned long *p, *end;
|
||||
|
||||
p = (unsigned long *)addr;
|
||||
end = p + PTRS_PER_PTE;
|
||||
|
||||
do {
|
||||
p[0] = _PAGE_GLOBAL;
|
||||
p[1] = _PAGE_GLOBAL;
|
||||
p[2] = _PAGE_GLOBAL;
|
||||
p[3] = _PAGE_GLOBAL;
|
||||
p[4] = _PAGE_GLOBAL;
|
||||
p += 8;
|
||||
p[-3] = _PAGE_GLOBAL;
|
||||
p[-2] = _PAGE_GLOBAL;
|
||||
p[-1] = _PAGE_GLOBAL;
|
||||
} while (p != end);
|
||||
}
|
||||
|
||||
pmd_t mk_pmd(struct page *page, pgprot_t prot)
|
||||
{
|
||||
pmd_t pmd;
|
||||
|
||||
@ -102,3 +102,4 @@ unsigned long __cmpxchg_small(volatile void *ptr, unsigned long old,
|
||||
return old;
|
||||
}
|
||||
}
|
||||
EXPORT_SYMBOL(__cmpxchg_small);
|
||||
|
||||
@ -282,6 +282,7 @@ int __init opal_event_init(void)
|
||||
name, NULL);
|
||||
if (rc) {
|
||||
pr_warn("Error %d requesting OPAL irq %d\n", rc, (int)r->start);
|
||||
kfree(name);
|
||||
continue;
|
||||
}
|
||||
}
|
||||
|
||||
@ -177,7 +177,7 @@ config RISCV
|
||||
select HAVE_REGS_AND_STACK_ACCESS_API
|
||||
select HAVE_RETHOOK if !XIP_KERNEL
|
||||
select HAVE_RSEQ
|
||||
select HAVE_RUST if RUSTC_SUPPORTS_RISCV
|
||||
select HAVE_RUST if RUSTC_SUPPORTS_RISCV && CC_IS_CLANG
|
||||
select HAVE_SAMPLE_FTRACE_DIRECT
|
||||
select HAVE_SAMPLE_FTRACE_DIRECT_MULTI
|
||||
select HAVE_STACKPROTECTOR
|
||||
|
||||
@ -2,6 +2,12 @@ ifdef CONFIG_RELOCATABLE
|
||||
KBUILD_CFLAGS += -fno-pie
|
||||
endif
|
||||
|
||||
ifdef CONFIG_RISCV_ALTERNATIVE_EARLY
|
||||
ifdef CONFIG_FORTIFY_SOURCE
|
||||
KBUILD_CFLAGS += -D__NO_FORTIFY
|
||||
endif
|
||||
endif
|
||||
|
||||
obj-$(CONFIG_ERRATA_ANDES) += andes/
|
||||
obj-$(CONFIG_ERRATA_SIFIVE) += sifive/
|
||||
obj-$(CONFIG_ERRATA_THEAD) += thead/
|
||||
|
||||
@ -36,6 +36,11 @@ KASAN_SANITIZE_alternative.o := n
|
||||
KASAN_SANITIZE_cpufeature.o := n
|
||||
KASAN_SANITIZE_sbi_ecall.o := n
|
||||
endif
|
||||
ifdef CONFIG_FORTIFY_SOURCE
|
||||
CFLAGS_alternative.o += -D__NO_FORTIFY
|
||||
CFLAGS_cpufeature.o += -D__NO_FORTIFY
|
||||
CFLAGS_sbi_ecall.o += -D__NO_FORTIFY
|
||||
endif
|
||||
endif
|
||||
|
||||
extra-y += vmlinux.lds
|
||||
|
||||
@ -210,7 +210,7 @@ void __init __iomem *__acpi_map_table(unsigned long phys, unsigned long size)
|
||||
if (!size)
|
||||
return NULL;
|
||||
|
||||
return early_ioremap(phys, size);
|
||||
return early_memremap(phys, size);
|
||||
}
|
||||
|
||||
void __init __acpi_unmap_table(void __iomem *map, unsigned long size)
|
||||
@ -218,7 +218,7 @@ void __init __acpi_unmap_table(void __iomem *map, unsigned long size)
|
||||
if (!map || !size)
|
||||
return;
|
||||
|
||||
early_iounmap(map, size);
|
||||
early_memunmap(map, size);
|
||||
}
|
||||
|
||||
void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
|
||||
|
||||
@ -4,8 +4,6 @@
|
||||
* Copyright (C) 2017 SiFive
|
||||
*/
|
||||
|
||||
#define GENERATING_ASM_OFFSETS
|
||||
|
||||
#include <linux/kbuild.h>
|
||||
#include <linux/mm.h>
|
||||
#include <linux/sched.h>
|
||||
|
||||
@ -80,8 +80,7 @@ int populate_cache_leaves(unsigned int cpu)
|
||||
{
|
||||
struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
|
||||
struct cacheinfo *this_leaf = this_cpu_ci->info_list;
|
||||
struct device_node *np = of_cpu_device_node_get(cpu);
|
||||
struct device_node *prev = NULL;
|
||||
struct device_node *np, *prev;
|
||||
int levels = 1, level = 1;
|
||||
|
||||
if (!acpi_disabled) {
|
||||
@ -105,6 +104,10 @@ int populate_cache_leaves(unsigned int cpu)
|
||||
return 0;
|
||||
}
|
||||
|
||||
np = of_cpu_device_node_get(cpu);
|
||||
if (!np)
|
||||
return -ENOENT;
|
||||
|
||||
if (of_property_read_bool(np, "cache-size"))
|
||||
ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level);
|
||||
if (of_property_read_bool(np, "i-cache-size"))
|
||||
|
||||
@ -58,7 +58,7 @@ void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu)
|
||||
if (cpu_ops->cpu_is_stopped)
|
||||
ret = cpu_ops->cpu_is_stopped(cpu);
|
||||
if (ret)
|
||||
pr_warn("CPU%d may not have stopped: %d\n", cpu, ret);
|
||||
pr_warn("CPU%u may not have stopped: %d\n", cpu, ret);
|
||||
}
|
||||
|
||||
/*
|
||||
|
||||
@ -64,7 +64,7 @@ extra_header_fields:
|
||||
.long efi_header_end - _start // SizeOfHeaders
|
||||
.long 0 // CheckSum
|
||||
.short IMAGE_SUBSYSTEM_EFI_APPLICATION // Subsystem
|
||||
.short 0 // DllCharacteristics
|
||||
.short IMAGE_DLL_CHARACTERISTICS_NX_COMPAT // DllCharacteristics
|
||||
.quad 0 // SizeOfStackReserve
|
||||
.quad 0 // SizeOfStackCommit
|
||||
.quad 0 // SizeOfHeapReserve
|
||||
|
||||
@ -16,8 +16,12 @@ KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO), $(KBUILD_CFLAGS))
|
||||
KBUILD_CFLAGS += -mcmodel=medany
|
||||
|
||||
CFLAGS_cmdline_early.o += -D__NO_FORTIFY
|
||||
CFLAGS_lib-fdt_ro.o += -D__NO_FORTIFY
|
||||
CFLAGS_fdt_early.o += -D__NO_FORTIFY
|
||||
# lib/string.c already defines __NO_FORTIFY
|
||||
CFLAGS_ctype.o += -D__NO_FORTIFY
|
||||
CFLAGS_lib-fdt.o += -D__NO_FORTIFY
|
||||
CFLAGS_lib-fdt_ro.o += -D__NO_FORTIFY
|
||||
CFLAGS_archrandom_early.o += -D__NO_FORTIFY
|
||||
|
||||
$(obj)/%.pi.o: OBJCOPYFLAGS := --prefix-symbols=__pi_ \
|
||||
--remove-section=.note.gnu.property \
|
||||
|
||||
@ -136,8 +136,6 @@
|
||||
#define REG_PTR(insn, pos, regs) \
|
||||
(ulong *)((ulong)(regs) + REG_OFFSET(insn, pos))
|
||||
|
||||
#define GET_RM(insn) (((insn) >> 12) & 7)
|
||||
|
||||
#define GET_RS1(insn, regs) (*REG_PTR(insn, SH_RS1, regs))
|
||||
#define GET_RS2(insn, regs) (*REG_PTR(insn, SH_RS2, regs))
|
||||
#define GET_RS1S(insn, regs) (*REG_PTR(RVC_RS1S(insn), 0, regs))
|
||||
|
||||
@ -18,6 +18,7 @@ obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o
|
||||
|
||||
ccflags-y := -fno-stack-protector
|
||||
ccflags-y += -DDISABLE_BRANCH_PROFILING
|
||||
ccflags-y += -fno-builtin
|
||||
|
||||
ifneq ($(c-gettimeofday-y),)
|
||||
CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y)
|
||||
|
||||
@ -55,7 +55,7 @@ struct imsic {
|
||||
/* IMSIC SW-file */
|
||||
struct imsic_mrif *swfile;
|
||||
phys_addr_t swfile_pa;
|
||||
spinlock_t swfile_extirq_lock;
|
||||
raw_spinlock_t swfile_extirq_lock;
|
||||
};
|
||||
|
||||
#define imsic_vs_csr_read(__c) \
|
||||
@ -622,7 +622,7 @@ static void imsic_swfile_extirq_update(struct kvm_vcpu *vcpu)
|
||||
* interruptions between reading topei and updating pending status.
|
||||
*/
|
||||
|
||||
spin_lock_irqsave(&imsic->swfile_extirq_lock, flags);
|
||||
raw_spin_lock_irqsave(&imsic->swfile_extirq_lock, flags);
|
||||
|
||||
if (imsic_mrif_atomic_read(mrif, &mrif->eidelivery) &&
|
||||
imsic_mrif_topei(mrif, imsic->nr_eix, imsic->nr_msis))
|
||||
@ -630,7 +630,7 @@ static void imsic_swfile_extirq_update(struct kvm_vcpu *vcpu)
|
||||
else
|
||||
kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_EXT);
|
||||
|
||||
spin_unlock_irqrestore(&imsic->swfile_extirq_lock, flags);
|
||||
raw_spin_unlock_irqrestore(&imsic->swfile_extirq_lock, flags);
|
||||
}
|
||||
|
||||
static void imsic_swfile_read(struct kvm_vcpu *vcpu, bool clear,
|
||||
@ -1051,7 +1051,7 @@ int kvm_riscv_vcpu_aia_imsic_init(struct kvm_vcpu *vcpu)
|
||||
}
|
||||
imsic->swfile = page_to_virt(swfile_page);
|
||||
imsic->swfile_pa = page_to_phys(swfile_page);
|
||||
spin_lock_init(&imsic->swfile_extirq_lock);
|
||||
raw_spin_lock_init(&imsic->swfile_extirq_lock);
|
||||
|
||||
/* Setup IO device */
|
||||
kvm_iodevice_init(&imsic->iodev, &imsic_iodoev_ops);
|
||||
|
||||
@ -18,6 +18,7 @@
|
||||
#define RV_MAX_REG_ARGS 8
|
||||
#define RV_FENTRY_NINSNS 2
|
||||
#define RV_FENTRY_NBYTES (RV_FENTRY_NINSNS * 4)
|
||||
#define RV_KCFI_NINSNS (IS_ENABLED(CONFIG_CFI_CLANG) ? 1 : 0)
|
||||
/* imm that allows emit_imm to emit max count insns */
|
||||
#define RV_MAX_COUNT_IMM 0x7FFF7FF7FF7FF7FF
|
||||
|
||||
@ -271,7 +272,8 @@ static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx)
|
||||
if (!is_tail_call)
|
||||
emit_addiw(RV_REG_A0, RV_REG_A5, 0, ctx);
|
||||
emit_jalr(RV_REG_ZERO, is_tail_call ? RV_REG_T3 : RV_REG_RA,
|
||||
is_tail_call ? (RV_FENTRY_NINSNS + 1) * 4 : 0, /* skip reserved nops and TCC init */
|
||||
/* kcfi, fentry and TCC init insns will be skipped on tailcall */
|
||||
is_tail_call ? (RV_KCFI_NINSNS + RV_FENTRY_NINSNS + 1) * 4 : 0,
|
||||
ctx);
|
||||
}
|
||||
|
||||
@ -548,8 +550,8 @@ static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64,
|
||||
rv_lr_w(r0, 0, rd, 0, 0), ctx);
|
||||
jmp_offset = ninsns_rvoff(8);
|
||||
emit(rv_bne(RV_REG_T2, r0, jmp_offset >> 1), ctx);
|
||||
emit(is64 ? rv_sc_d(RV_REG_T3, rs, rd, 0, 0) :
|
||||
rv_sc_w(RV_REG_T3, rs, rd, 0, 0), ctx);
|
||||
emit(is64 ? rv_sc_d(RV_REG_T3, rs, rd, 0, 1) :
|
||||
rv_sc_w(RV_REG_T3, rs, rd, 0, 1), ctx);
|
||||
jmp_offset = ninsns_rvoff(-6);
|
||||
emit(rv_bne(RV_REG_T3, 0, jmp_offset >> 1), ctx);
|
||||
emit(rv_fence(0x3, 0x3), ctx);
|
||||
|
||||
@ -50,7 +50,6 @@ CONFIG_NUMA=y
|
||||
CONFIG_HZ_100=y
|
||||
CONFIG_CERT_STORE=y
|
||||
CONFIG_EXPOLINE=y
|
||||
# CONFIG_EXPOLINE_EXTERN is not set
|
||||
CONFIG_EXPOLINE_AUTO=y
|
||||
CONFIG_CHSC_SCH=y
|
||||
CONFIG_VFIO_CCW=m
|
||||
@ -95,6 +94,7 @@ CONFIG_BINFMT_MISC=m
|
||||
CONFIG_ZSWAP=y
|
||||
CONFIG_ZSWAP_ZPOOL_DEFAULT_ZBUD=y
|
||||
CONFIG_ZSMALLOC_STAT=y
|
||||
CONFIG_SLAB_BUCKETS=y
|
||||
CONFIG_SLUB_STATS=y
|
||||
# CONFIG_COMPAT_BRK is not set
|
||||
CONFIG_MEMORY_HOTPLUG=y
|
||||
@ -426,6 +426,13 @@ CONFIG_DEVTMPFS_SAFE=y
|
||||
# CONFIG_FW_LOADER is not set
|
||||
CONFIG_CONNECTOR=y
|
||||
CONFIG_ZRAM=y
|
||||
CONFIG_ZRAM_BACKEND_LZ4=y
|
||||
CONFIG_ZRAM_BACKEND_LZ4HC=y
|
||||
CONFIG_ZRAM_BACKEND_ZSTD=y
|
||||
CONFIG_ZRAM_BACKEND_DEFLATE=y
|
||||
CONFIG_ZRAM_BACKEND_842=y
|
||||
CONFIG_ZRAM_BACKEND_LZO=y
|
||||
CONFIG_ZRAM_DEF_COMP_DEFLATE=y
|
||||
CONFIG_BLK_DEV_LOOP=m
|
||||
CONFIG_BLK_DEV_DRBD=m
|
||||
CONFIG_BLK_DEV_NBD=m
|
||||
@ -486,6 +493,7 @@ CONFIG_DM_UEVENT=y
|
||||
CONFIG_DM_FLAKEY=m
|
||||
CONFIG_DM_VERITY=m
|
||||
CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y
|
||||
CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG_PLATFORM_KEYRING=y
|
||||
CONFIG_DM_SWITCH=m
|
||||
CONFIG_DM_INTEGRITY=m
|
||||
CONFIG_DM_VDO=m
|
||||
@ -535,6 +543,7 @@ CONFIG_NLMON=m
|
||||
CONFIG_MLX4_EN=m
|
||||
CONFIG_MLX5_CORE=m
|
||||
CONFIG_MLX5_CORE_EN=y
|
||||
# CONFIG_NET_VENDOR_META is not set
|
||||
# CONFIG_NET_VENDOR_MICREL is not set
|
||||
# CONFIG_NET_VENDOR_MICROCHIP is not set
|
||||
# CONFIG_NET_VENDOR_MICROSEMI is not set
|
||||
@ -695,6 +704,7 @@ CONFIG_NFSD=m
|
||||
CONFIG_NFSD_V3_ACL=y
|
||||
CONFIG_NFSD_V4=y
|
||||
CONFIG_NFSD_V4_SECURITY_LABEL=y
|
||||
# CONFIG_NFSD_LEGACY_CLIENT_TRACKING is not set
|
||||
CONFIG_CIFS=m
|
||||
CONFIG_CIFS_UPCALL=y
|
||||
CONFIG_CIFS_XATTR=y
|
||||
@ -740,7 +750,6 @@ CONFIG_CRYPTO_DH=m
|
||||
CONFIG_CRYPTO_ECDH=m
|
||||
CONFIG_CRYPTO_ECDSA=m
|
||||
CONFIG_CRYPTO_ECRDSA=m
|
||||
CONFIG_CRYPTO_SM2=m
|
||||
CONFIG_CRYPTO_CURVE25519=m
|
||||
CONFIG_CRYPTO_AES_TI=m
|
||||
CONFIG_CRYPTO_ANUBIS=m
|
||||
|
||||
@ -48,7 +48,6 @@ CONFIG_NUMA=y
|
||||
CONFIG_HZ_100=y
|
||||
CONFIG_CERT_STORE=y
|
||||
CONFIG_EXPOLINE=y
|
||||
# CONFIG_EXPOLINE_EXTERN is not set
|
||||
CONFIG_EXPOLINE_AUTO=y
|
||||
CONFIG_CHSC_SCH=y
|
||||
CONFIG_VFIO_CCW=m
|
||||
@ -89,6 +88,7 @@ CONFIG_BINFMT_MISC=m
|
||||
CONFIG_ZSWAP=y
|
||||
CONFIG_ZSWAP_ZPOOL_DEFAULT_ZBUD=y
|
||||
CONFIG_ZSMALLOC_STAT=y
|
||||
CONFIG_SLAB_BUCKETS=y
|
||||
# CONFIG_COMPAT_BRK is not set
|
||||
CONFIG_MEMORY_HOTPLUG=y
|
||||
CONFIG_MEMORY_HOTREMOVE=y
|
||||
@ -416,6 +416,13 @@ CONFIG_DEVTMPFS_SAFE=y
|
||||
# CONFIG_FW_LOADER is not set
|
||||
CONFIG_CONNECTOR=y
|
||||
CONFIG_ZRAM=y
|
||||
CONFIG_ZRAM_BACKEND_LZ4=y
|
||||
CONFIG_ZRAM_BACKEND_LZ4HC=y
|
||||
CONFIG_ZRAM_BACKEND_ZSTD=y
|
||||
CONFIG_ZRAM_BACKEND_DEFLATE=y
|
||||
CONFIG_ZRAM_BACKEND_842=y
|
||||
CONFIG_ZRAM_BACKEND_LZO=y
|
||||
CONFIG_ZRAM_DEF_COMP_DEFLATE=y
|
||||
CONFIG_BLK_DEV_LOOP=m
|
||||
CONFIG_BLK_DEV_DRBD=m
|
||||
CONFIG_BLK_DEV_NBD=m
|
||||
@ -476,6 +483,7 @@ CONFIG_DM_UEVENT=y
|
||||
CONFIG_DM_FLAKEY=m
|
||||
CONFIG_DM_VERITY=m
|
||||
CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y
|
||||
CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG_PLATFORM_KEYRING=y
|
||||
CONFIG_DM_SWITCH=m
|
||||
CONFIG_DM_INTEGRITY=m
|
||||
CONFIG_DM_VDO=m
|
||||
@ -525,6 +533,7 @@ CONFIG_NLMON=m
|
||||
CONFIG_MLX4_EN=m
|
||||
CONFIG_MLX5_CORE=m
|
||||
CONFIG_MLX5_CORE_EN=y
|
||||
# CONFIG_NET_VENDOR_META is not set
|
||||
# CONFIG_NET_VENDOR_MICREL is not set
|
||||
# CONFIG_NET_VENDOR_MICROCHIP is not set
|
||||
# CONFIG_NET_VENDOR_MICROSEMI is not set
|
||||
@ -682,6 +691,7 @@ CONFIG_NFSD=m
|
||||
CONFIG_NFSD_V3_ACL=y
|
||||
CONFIG_NFSD_V4=y
|
||||
CONFIG_NFSD_V4_SECURITY_LABEL=y
|
||||
# CONFIG_NFSD_LEGACY_CLIENT_TRACKING is not set
|
||||
CONFIG_CIFS=m
|
||||
CONFIG_CIFS_UPCALL=y
|
||||
CONFIG_CIFS_XATTR=y
|
||||
@ -726,7 +736,6 @@ CONFIG_CRYPTO_DH=m
|
||||
CONFIG_CRYPTO_ECDH=m
|
||||
CONFIG_CRYPTO_ECDSA=m
|
||||
CONFIG_CRYPTO_ECRDSA=m
|
||||
CONFIG_CRYPTO_SM2=m
|
||||
CONFIG_CRYPTO_CURVE25519=m
|
||||
CONFIG_CRYPTO_AES_TI=m
|
||||
CONFIG_CRYPTO_ANUBIS=m
|
||||
@ -767,6 +776,7 @@ CONFIG_CRYPTO_LZ4=m
|
||||
CONFIG_CRYPTO_LZ4HC=m
|
||||
CONFIG_CRYPTO_ZSTD=m
|
||||
CONFIG_CRYPTO_ANSI_CPRNG=m
|
||||
CONFIG_CRYPTO_JITTERENTROPY_OSR=1
|
||||
CONFIG_CRYPTO_USER_API_HASH=m
|
||||
CONFIG_CRYPTO_USER_API_SKCIPHER=m
|
||||
CONFIG_CRYPTO_USER_API_RNG=m
|
||||
|
||||
@ -49,6 +49,7 @@ CONFIG_ZFCP=y
|
||||
# CONFIG_HVC_IUCV is not set
|
||||
# CONFIG_HW_RANDOM_S390 is not set
|
||||
# CONFIG_HMC_DRV is not set
|
||||
# CONFIG_S390_UV_UAPI is not set
|
||||
# CONFIG_S390_TAPE is not set
|
||||
# CONFIG_VMCP is not set
|
||||
# CONFIG_MONWRITER is not set
|
||||
|
||||
@ -49,6 +49,7 @@ struct perf_sf_sde_regs {
|
||||
};
|
||||
|
||||
#define perf_arch_fetch_caller_regs(regs, __ip) do { \
|
||||
(regs)->psw.mask = 0; \
|
||||
(regs)->psw.addr = (__ip); \
|
||||
(regs)->gprs[15] = (unsigned long)__builtin_frame_address(0) - \
|
||||
offsetof(struct stack_frame, back_chain); \
|
||||
|
||||
@ -77,7 +77,7 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu)
|
||||
vcpu->stat.instruction_diagnose_258++;
|
||||
if (vcpu->run->s.regs.gprs[rx] & 7)
|
||||
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
|
||||
rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], rx, &parm, sizeof(parm));
|
||||
rc = read_guest_real(vcpu, vcpu->run->s.regs.gprs[rx], &parm, sizeof(parm));
|
||||
if (rc)
|
||||
return kvm_s390_inject_prog_cond(vcpu, rc);
|
||||
if (parm.parm_version != 2 || parm.parm_len < 5 || parm.code != 0x258)
|
||||
|
||||
@ -828,6 +828,8 @@ static int access_guest_page(struct kvm *kvm, enum gacc_mode mode, gpa_t gpa,
|
||||
const gfn_t gfn = gpa_to_gfn(gpa);
|
||||
int rc;
|
||||
|
||||
if (!gfn_to_memslot(kvm, gfn))
|
||||
return PGM_ADDRESSING;
|
||||
if (mode == GACC_STORE)
|
||||
rc = kvm_write_guest_page(kvm, gfn, data, offset, len);
|
||||
else
|
||||
@ -985,6 +987,8 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
|
||||
gra += fragment_len;
|
||||
data += fragment_len;
|
||||
}
|
||||
if (rc > 0)
|
||||
vcpu->arch.pgm.code = rc;
|
||||
return rc;
|
||||
}
|
||||
|
||||
|
||||
@ -405,11 +405,12 @@ int read_guest_abs(struct kvm_vcpu *vcpu, unsigned long gpa, void *data,
|
||||
* @len: number of bytes to copy
|
||||
*
|
||||
* Copy @len bytes from @data (kernel space) to @gra (guest real address).
|
||||
* It is up to the caller to ensure that the entire guest memory range is
|
||||
* valid memory before calling this function.
|
||||
* Guest low address and key protection are not checked.
|
||||
*
|
||||
* Returns zero on success or -EFAULT on error.
|
||||
* Returns zero on success, -EFAULT when copying from @data failed, or
|
||||
* PGM_ADRESSING in case @gra is outside a memslot. In this case, pgm check info
|
||||
* is also stored to allow injecting into the guest (if applicable) using
|
||||
* kvm_s390_inject_prog_cond().
|
||||
*
|
||||
* If an error occurs data may have been copied partially to guest memory.
|
||||
*/
|
||||
@ -428,11 +429,12 @@ int write_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data,
|
||||
* @len: number of bytes to copy
|
||||
*
|
||||
* Copy @len bytes from @gra (guest real address) to @data (kernel space).
|
||||
* It is up to the caller to ensure that the entire guest memory range is
|
||||
* valid memory before calling this function.
|
||||
* Guest key protection is not checked.
|
||||
*
|
||||
* Returns zero on success or -EFAULT on error.
|
||||
* Returns zero on success, -EFAULT when copying to @data failed, or
|
||||
* PGM_ADRESSING in case @gra is outside a memslot. In this case, pgm check info
|
||||
* is also stored to allow injecting into the guest (if applicable) using
|
||||
* kvm_s390_inject_prog_cond().
|
||||
*
|
||||
* If an error occurs data may have been copied partially to kernel space.
|
||||
*/
|
||||
|
||||
@ -280,18 +280,19 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf)
|
||||
goto no_pdev;
|
||||
|
||||
switch (ccdf->pec) {
|
||||
case 0x003a: /* Service Action or Error Recovery Successful */
|
||||
case 0x002a: /* Error event concerns FMB */
|
||||
case 0x002b:
|
||||
case 0x002c:
|
||||
break;
|
||||
case 0x0040: /* Service Action or Error Recovery Failed */
|
||||
case 0x003b:
|
||||
zpci_event_io_failure(pdev, pci_channel_io_perm_failure);
|
||||
break;
|
||||
default: /* PCI function left in the error state attempt to recover */
|
||||
ers_res = zpci_event_attempt_error_recovery(pdev);
|
||||
if (ers_res != PCI_ERS_RESULT_RECOVERED)
|
||||
zpci_event_io_failure(pdev, pci_channel_io_perm_failure);
|
||||
break;
|
||||
default:
|
||||
/*
|
||||
* Mark as frozen not permanently failed because the device
|
||||
* could be subsequently recovered by the platform.
|
||||
*/
|
||||
zpci_event_io_failure(pdev, pci_channel_io_frozen);
|
||||
break;
|
||||
}
|
||||
pci_dev_put(pdev);
|
||||
no_pdev:
|
||||
|
||||
@ -2257,6 +2257,7 @@ config RANDOMIZE_MEMORY_PHYSICAL_PADDING
|
||||
config ADDRESS_MASKING
|
||||
bool "Linear Address Masking support"
|
||||
depends on X86_64
|
||||
depends on COMPILE_TEST || !CPU_MITIGATIONS # wait for LASS
|
||||
help
|
||||
Linear Address Masking (LAM) modifies the checking that is applied
|
||||
to 64-bit linear addresses, allowing software to use of the
|
||||
|
||||
@ -9,6 +9,8 @@
|
||||
#include <asm/unwind_hints.h>
|
||||
#include <asm/segment.h>
|
||||
#include <asm/cache.h>
|
||||
#include <asm/cpufeatures.h>
|
||||
#include <asm/nospec-branch.h>
|
||||
|
||||
#include "calling.h"
|
||||
|
||||
@ -19,6 +21,9 @@ SYM_FUNC_START(entry_ibpb)
|
||||
movl $PRED_CMD_IBPB, %eax
|
||||
xorl %edx, %edx
|
||||
wrmsr
|
||||
|
||||
/* Make sure IBPB clears return stack preductions too. */
|
||||
FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_BUG_IBPB_NO_RET
|
||||
RET
|
||||
SYM_FUNC_END(entry_ibpb)
|
||||
/* For KVM */
|
||||
|
||||
@ -871,6 +871,8 @@ SYM_FUNC_START(entry_SYSENTER_32)
|
||||
|
||||
/* Now ready to switch the cr3 */
|
||||
SWITCH_TO_USER_CR3 scratch_reg=%eax
|
||||
/* Clobbers ZF */
|
||||
CLEAR_CPU_BUFFERS
|
||||
|
||||
/*
|
||||
* Restore all flags except IF. (We restore IF separately because
|
||||
@ -881,7 +883,6 @@ SYM_FUNC_START(entry_SYSENTER_32)
|
||||
BUG_IF_WRONG_CR3 no_user_check=1
|
||||
popfl
|
||||
popl %eax
|
||||
CLEAR_CPU_BUFFERS
|
||||
|
||||
/*
|
||||
* Return back to the vDSO, which will pop ecx and edx.
|
||||
@ -1144,7 +1145,6 @@ SYM_CODE_START(asm_exc_nmi)
|
||||
|
||||
/* Not on SYSENTER stack. */
|
||||
call exc_nmi
|
||||
CLEAR_CPU_BUFFERS
|
||||
jmp .Lnmi_return
|
||||
|
||||
.Lnmi_from_sysenter_stack:
|
||||
@ -1165,6 +1165,7 @@ SYM_CODE_START(asm_exc_nmi)
|
||||
|
||||
CHECK_AND_APPLY_ESPFIX
|
||||
RESTORE_ALL_NMI cr3_reg=%edi pop=4
|
||||
CLEAR_CPU_BUFFERS
|
||||
jmp .Lirq_return
|
||||
|
||||
#ifdef CONFIG_X86_ESPFIX32
|
||||
@ -1206,6 +1207,7 @@ SYM_CODE_START(asm_exc_nmi)
|
||||
* 1 - orig_ax
|
||||
*/
|
||||
lss (1+5+6)*4(%esp), %esp # back to espfix stack
|
||||
CLEAR_CPU_BUFFERS
|
||||
jmp .Lirq_return
|
||||
#endif
|
||||
SYM_CODE_END(asm_exc_nmi)
|
||||
|
||||
@ -116,7 +116,10 @@ static inline bool amd_gart_present(void)
|
||||
|
||||
#define amd_nb_num(x) 0
|
||||
#define amd_nb_has_feature(x) false
|
||||
#define node_to_amd_nb(x) NULL
|
||||
static inline struct amd_northbridge *node_to_amd_nb(int node)
|
||||
{
|
||||
return NULL;
|
||||
}
|
||||
#define amd_gart_present(x) false
|
||||
|
||||
#endif
|
||||
|
||||
@ -215,7 +215,7 @@
|
||||
#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* Disable Speculative Store Bypass. */
|
||||
#define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* AMD SSBD implementation via LS_CFG MSR */
|
||||
#define X86_FEATURE_IBRS ( 7*32+25) /* "ibrs" Indirect Branch Restricted Speculation */
|
||||
#define X86_FEATURE_IBPB ( 7*32+26) /* "ibpb" Indirect Branch Prediction Barrier */
|
||||
#define X86_FEATURE_IBPB ( 7*32+26) /* "ibpb" Indirect Branch Prediction Barrier without a guaranteed RSB flush */
|
||||
#define X86_FEATURE_STIBP ( 7*32+27) /* "stibp" Single Thread Indirect Branch Predictors */
|
||||
#define X86_FEATURE_ZEN ( 7*32+28) /* Generic flag for all Zen and newer */
|
||||
#define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* L1TF workaround PTE inversion */
|
||||
@ -348,6 +348,7 @@
|
||||
#define X86_FEATURE_CPPC (13*32+27) /* "cppc" Collaborative Processor Performance Control */
|
||||
#define X86_FEATURE_AMD_PSFD (13*32+28) /* Predictive Store Forwarding Disable */
|
||||
#define X86_FEATURE_BTC_NO (13*32+29) /* Not vulnerable to Branch Type Confusion */
|
||||
#define X86_FEATURE_AMD_IBPB_RET (13*32+30) /* IBPB clears return address predictor */
|
||||
#define X86_FEATURE_BRS (13*32+31) /* "brs" Branch Sampling available */
|
||||
|
||||
/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
|
||||
@ -523,4 +524,5 @@
|
||||
#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* "div0" AMD DIV0 speculation bug */
|
||||
#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */
|
||||
#define X86_BUG_BHI X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */
|
||||
#define X86_BUG_IBPB_NO_RET X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */
|
||||
#endif /* _ASM_X86_CPUFEATURES_H */
|
||||
|
||||
@ -323,7 +323,16 @@
|
||||
* Note: Only the memory operand variant of VERW clears the CPU buffers.
|
||||
*/
|
||||
.macro CLEAR_CPU_BUFFERS
|
||||
ALTERNATIVE "", __stringify(verw _ASM_RIP(mds_verw_sel)), X86_FEATURE_CLEAR_CPU_BUF
|
||||
#ifdef CONFIG_X86_64
|
||||
ALTERNATIVE "", "verw mds_verw_sel(%rip)", X86_FEATURE_CLEAR_CPU_BUF
|
||||
#else
|
||||
/*
|
||||
* In 32bit mode, the memory operand must be a %cs reference. The data
|
||||
* segments may not be usable (vm86 mode), and the stack segment may not
|
||||
* be flat (ESPFIX32).
|
||||
*/
|
||||
ALTERNATIVE "", "verw %cs:mds_verw_sel", X86_FEATURE_CLEAR_CPU_BUF
|
||||
#endif
|
||||
.endm
|
||||
|
||||
#ifdef CONFIG_X86_64
|
||||
|
||||
@ -6,7 +6,7 @@
|
||||
typeof(sym) __ret; \
|
||||
asm_inline("mov %1,%0\n1:\n" \
|
||||
".pushsection runtime_ptr_" #sym ",\"a\"\n\t" \
|
||||
".long 1b - %c2 - .\n\t" \
|
||||
".long 1b - %c2 - .\n" \
|
||||
".popsection" \
|
||||
:"=r" (__ret) \
|
||||
:"i" ((unsigned long)0x0123456789abcdefull), \
|
||||
@ -20,7 +20,7 @@
|
||||
typeof(0u+(val)) __ret = (val); \
|
||||
asm_inline("shrl $12,%k0\n1:\n" \
|
||||
".pushsection runtime_shift_" #sym ",\"a\"\n\t" \
|
||||
".long 1b - 1 - .\n\t" \
|
||||
".long 1b - 1 - .\n" \
|
||||
".popsection" \
|
||||
:"+r" (__ret)); \
|
||||
__ret; })
|
||||
|
||||
@ -12,6 +12,13 @@
|
||||
#include <asm/cpufeatures.h>
|
||||
#include <asm/page.h>
|
||||
#include <asm/percpu.h>
|
||||
#include <asm/runtime-const.h>
|
||||
|
||||
/*
|
||||
* Virtual variable: there's no actual backing store for this,
|
||||
* it can purely be used as 'runtime_const_ptr(USER_PTR_MAX)'
|
||||
*/
|
||||
extern unsigned long USER_PTR_MAX;
|
||||
|
||||
#ifdef CONFIG_ADDRESS_MASKING
|
||||
/*
|
||||
@ -46,19 +53,24 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm,
|
||||
|
||||
#endif
|
||||
|
||||
/*
|
||||
* The virtual address space space is logically divided into a kernel
|
||||
* half and a user half. When cast to a signed type, user pointers
|
||||
* are positive and kernel pointers are negative.
|
||||
*/
|
||||
#define valid_user_address(x) ((__force long)(x) >= 0)
|
||||
#define valid_user_address(x) \
|
||||
((__force unsigned long)(x) <= runtime_const_ptr(USER_PTR_MAX))
|
||||
|
||||
/*
|
||||
* Masking the user address is an alternative to a conditional
|
||||
* user_access_begin that can avoid the fencing. This only works
|
||||
* for dense accesses starting at the address.
|
||||
*/
|
||||
#define mask_user_address(x) ((typeof(x))((long)(x)|((long)(x)>>63)))
|
||||
static inline void __user *mask_user_address(const void __user *ptr)
|
||||
{
|
||||
unsigned long mask;
|
||||
asm("cmp %1,%0\n\t"
|
||||
"sbb %0,%0"
|
||||
:"=r" (mask)
|
||||
:"r" (ptr),
|
||||
"0" (runtime_const_ptr(USER_PTR_MAX)));
|
||||
return (__force void __user *)(mask | (__force unsigned long)ptr);
|
||||
}
|
||||
#define masked_user_access_begin(x) ({ \
|
||||
__auto_type __masked_ptr = (x); \
|
||||
__masked_ptr = mask_user_address(__masked_ptr); \
|
||||
@ -69,23 +81,16 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm,
|
||||
* arbitrary values in those bits rather then masking them off.
|
||||
*
|
||||
* Enforce two rules:
|
||||
* 1. 'ptr' must be in the user half of the address space
|
||||
* 1. 'ptr' must be in the user part of the address space
|
||||
* 2. 'ptr+size' must not overflow into kernel addresses
|
||||
*
|
||||
* Note that addresses around the sign change are not valid addresses,
|
||||
* and will GP-fault even with LAM enabled if the sign bit is set (see
|
||||
* "CR3.LAM_SUP" that can narrow the canonicality check if we ever
|
||||
* enable it, but not remove it entirely).
|
||||
*
|
||||
* So the "overflow into kernel addresses" does not imply some sudden
|
||||
* exact boundary at the sign bit, and we can allow a lot of slop on the
|
||||
* size check.
|
||||
* Note that we always have at least one guard page between the
|
||||
* max user address and the non-canonical gap, allowing us to
|
||||
* ignore small sizes entirely.
|
||||
*
|
||||
* In fact, we could probably remove the size check entirely, since
|
||||
* any kernel accesses will be in increasing address order starting
|
||||
* at 'ptr', and even if the end might be in kernel space, we'll
|
||||
* hit the GP faults for non-canonical accesses before we ever get
|
||||
* there.
|
||||
* at 'ptr'.
|
||||
*
|
||||
* That's a separate optimization, for now just handle the small
|
||||
* constant case.
|
||||
|
||||
@ -44,6 +44,7 @@
|
||||
#define PCI_DEVICE_ID_AMD_19H_M70H_DF_F4 0x14f4
|
||||
#define PCI_DEVICE_ID_AMD_19H_M78H_DF_F4 0x12fc
|
||||
#define PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4 0x12c4
|
||||
#define PCI_DEVICE_ID_AMD_1AH_M20H_DF_F4 0x16fc
|
||||
#define PCI_DEVICE_ID_AMD_1AH_M60H_DF_F4 0x124c
|
||||
#define PCI_DEVICE_ID_AMD_1AH_M70H_DF_F4 0x12bc
|
||||
#define PCI_DEVICE_ID_AMD_MI200_DF_F4 0x14d4
|
||||
@ -127,6 +128,7 @@ static const struct pci_device_id amd_nb_link_ids[] = {
|
||||
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F4) },
|
||||
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) },
|
||||
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4) },
|
||||
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_DF_F4) },
|
||||
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M60H_DF_F4) },
|
||||
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M70H_DF_F4) },
|
||||
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F4) },
|
||||
|
||||
@ -440,7 +440,19 @@ static int lapic_timer_shutdown(struct clock_event_device *evt)
|
||||
v = apic_read(APIC_LVTT);
|
||||
v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
|
||||
apic_write(APIC_LVTT, v);
|
||||
apic_write(APIC_TMICT, 0);
|
||||
|
||||
/*
|
||||
* Setting APIC_LVT_MASKED (above) should be enough to tell
|
||||
* the hardware that this timer will never fire. But AMD
|
||||
* erratum 411 and some Intel CPU behavior circa 2024 say
|
||||
* otherwise. Time for belt and suspenders programming: mask
|
||||
* the timer _and_ zero the counter registers:
|
||||
*/
|
||||
if (v & APIC_LVT_TIMER_TSCDEADLINE)
|
||||
wrmsrl(MSR_IA32_TSC_DEADLINE, 0);
|
||||
else
|
||||
apic_write(APIC_TMICT, 0);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
||||
@ -1202,5 +1202,6 @@ void amd_check_microcode(void)
|
||||
if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
|
||||
return;
|
||||
|
||||
on_each_cpu(zenbleed_check_cpu, NULL, 1);
|
||||
if (cpu_feature_enabled(X86_FEATURE_ZEN2))
|
||||
on_each_cpu(zenbleed_check_cpu, NULL, 1);
|
||||
}
|
||||
|
||||
@ -1115,8 +1115,25 @@ static void __init retbleed_select_mitigation(void)
|
||||
|
||||
case RETBLEED_MITIGATION_IBPB:
|
||||
setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB);
|
||||
|
||||
/*
|
||||
* IBPB on entry already obviates the need for
|
||||
* software-based untraining so clear those in case some
|
||||
* other mitigation like SRSO has selected them.
|
||||
*/
|
||||
setup_clear_cpu_cap(X86_FEATURE_UNRET);
|
||||
setup_clear_cpu_cap(X86_FEATURE_RETHUNK);
|
||||
|
||||
setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
|
||||
mitigate_smt = true;
|
||||
|
||||
/*
|
||||
* There is no need for RSB filling: entry_ibpb() ensures
|
||||
* all predictions, including the RSB, are invalidated,
|
||||
* regardless of IBPB implementation.
|
||||
*/
|
||||
setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT);
|
||||
|
||||
break;
|
||||
|
||||
case RETBLEED_MITIGATION_STUFF:
|
||||
@ -2627,6 +2644,14 @@ static void __init srso_select_mitigation(void)
|
||||
if (has_microcode) {
|
||||
setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB);
|
||||
srso_mitigation = SRSO_MITIGATION_IBPB;
|
||||
|
||||
/*
|
||||
* IBPB on entry already obviates the need for
|
||||
* software-based untraining so clear those in case some
|
||||
* other mitigation like Retbleed has selected them.
|
||||
*/
|
||||
setup_clear_cpu_cap(X86_FEATURE_UNRET);
|
||||
setup_clear_cpu_cap(X86_FEATURE_RETHUNK);
|
||||
}
|
||||
} else {
|
||||
pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n");
|
||||
@ -2638,6 +2663,13 @@ static void __init srso_select_mitigation(void)
|
||||
if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) {
|
||||
setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
|
||||
srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT;
|
||||
|
||||
/*
|
||||
* There is no need for RSB filling: entry_ibpb() ensures
|
||||
* all predictions, including the RSB, are invalidated,
|
||||
* regardless of IBPB implementation.
|
||||
*/
|
||||
setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT);
|
||||
}
|
||||
} else {
|
||||
pr_err("WARNING: kernel not compiled with MITIGATION_SRSO.\n");
|
||||
|
||||
@ -69,6 +69,7 @@
|
||||
#include <asm/sev.h>
|
||||
#include <asm/tdx.h>
|
||||
#include <asm/posted_intr.h>
|
||||
#include <asm/runtime-const.h>
|
||||
|
||||
#include "cpu.h"
|
||||
|
||||
@ -1443,6 +1444,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
|
||||
boot_cpu_has(X86_FEATURE_HYPERVISOR)))
|
||||
setup_force_cpu_bug(X86_BUG_BHI);
|
||||
|
||||
if (cpu_has(c, X86_FEATURE_AMD_IBPB) && !cpu_has(c, X86_FEATURE_AMD_IBPB_RET))
|
||||
setup_force_cpu_bug(X86_BUG_IBPB_NO_RET);
|
||||
|
||||
if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
|
||||
return;
|
||||
|
||||
@ -2386,6 +2390,15 @@ void __init arch_cpu_finalize_init(void)
|
||||
alternative_instructions();
|
||||
|
||||
if (IS_ENABLED(CONFIG_X86_64)) {
|
||||
unsigned long USER_PTR_MAX = TASK_SIZE_MAX-1;
|
||||
|
||||
/*
|
||||
* Enable this when LAM is gated on LASS support
|
||||
if (cpu_feature_enabled(X86_FEATURE_LAM))
|
||||
USER_PTR_MAX = (1ul << 63) - PAGE_SIZE - 1;
|
||||
*/
|
||||
runtime_const_init(ptr, USER_PTR_MAX);
|
||||
|
||||
/*
|
||||
* Make sure the first 2MB area is not mapped by huge pages
|
||||
* There are typically fixed size MTRRs in there and overlapping
|
||||
|
||||
@ -584,7 +584,7 @@ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_
|
||||
native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->new_rev, dummy);
|
||||
}
|
||||
|
||||
static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size);
|
||||
static enum ucode_state _load_microcode_amd(u8 family, const u8 *data, size_t size);
|
||||
|
||||
static int __init save_microcode_in_initrd(void)
|
||||
{
|
||||
@ -605,7 +605,7 @@ static int __init save_microcode_in_initrd(void)
|
||||
if (!desc.mc)
|
||||
return -EINVAL;
|
||||
|
||||
ret = load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size);
|
||||
ret = _load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size);
|
||||
if (ret > UCODE_UPDATED)
|
||||
return -EINVAL;
|
||||
|
||||
@ -613,16 +613,19 @@ static int __init save_microcode_in_initrd(void)
|
||||
}
|
||||
early_initcall(save_microcode_in_initrd);
|
||||
|
||||
static inline bool patch_cpus_equivalent(struct ucode_patch *p, struct ucode_patch *n)
|
||||
static inline bool patch_cpus_equivalent(struct ucode_patch *p,
|
||||
struct ucode_patch *n,
|
||||
bool ignore_stepping)
|
||||
{
|
||||
/* Zen and newer hardcode the f/m/s in the patch ID */
|
||||
if (x86_family(bsp_cpuid_1_eax) >= 0x17) {
|
||||
union cpuid_1_eax p_cid = ucode_rev_to_cpuid(p->patch_id);
|
||||
union cpuid_1_eax n_cid = ucode_rev_to_cpuid(n->patch_id);
|
||||
|
||||
/* Zap stepping */
|
||||
p_cid.stepping = 0;
|
||||
n_cid.stepping = 0;
|
||||
if (ignore_stepping) {
|
||||
p_cid.stepping = 0;
|
||||
n_cid.stepping = 0;
|
||||
}
|
||||
|
||||
return p_cid.full == n_cid.full;
|
||||
} else {
|
||||
@ -644,13 +647,13 @@ static struct ucode_patch *cache_find_patch(struct ucode_cpu_info *uci, u16 equi
|
||||
WARN_ON_ONCE(!n.patch_id);
|
||||
|
||||
list_for_each_entry(p, µcode_cache, plist)
|
||||
if (patch_cpus_equivalent(p, &n))
|
||||
if (patch_cpus_equivalent(p, &n, false))
|
||||
return p;
|
||||
|
||||
return NULL;
|
||||
}
|
||||
|
||||
static inline bool patch_newer(struct ucode_patch *p, struct ucode_patch *n)
|
||||
static inline int patch_newer(struct ucode_patch *p, struct ucode_patch *n)
|
||||
{
|
||||
/* Zen and newer hardcode the f/m/s in the patch ID */
|
||||
if (x86_family(bsp_cpuid_1_eax) >= 0x17) {
|
||||
@ -659,6 +662,9 @@ static inline bool patch_newer(struct ucode_patch *p, struct ucode_patch *n)
|
||||
zp.ucode_rev = p->patch_id;
|
||||
zn.ucode_rev = n->patch_id;
|
||||
|
||||
if (zn.stepping != zp.stepping)
|
||||
return -1;
|
||||
|
||||
return zn.rev > zp.rev;
|
||||
} else {
|
||||
return n->patch_id > p->patch_id;
|
||||
@ -668,10 +674,14 @@ static inline bool patch_newer(struct ucode_patch *p, struct ucode_patch *n)
|
||||
static void update_cache(struct ucode_patch *new_patch)
|
||||
{
|
||||
struct ucode_patch *p;
|
||||
int ret;
|
||||
|
||||
list_for_each_entry(p, µcode_cache, plist) {
|
||||
if (patch_cpus_equivalent(p, new_patch)) {
|
||||
if (!patch_newer(p, new_patch)) {
|
||||
if (patch_cpus_equivalent(p, new_patch, true)) {
|
||||
ret = patch_newer(p, new_patch);
|
||||
if (ret < 0)
|
||||
continue;
|
||||
else if (!ret) {
|
||||
/* we already have the latest patch */
|
||||
kfree(new_patch->data);
|
||||
kfree(new_patch);
|
||||
@ -944,6 +954,20 @@ static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
|
||||
return UCODE_OK;
|
||||
}
|
||||
|
||||
static enum ucode_state _load_microcode_amd(u8 family, const u8 *data, size_t size)
|
||||
{
|
||||
enum ucode_state ret;
|
||||
|
||||
/* free old equiv table */
|
||||
free_equiv_cpu_table();
|
||||
|
||||
ret = __load_microcode_amd(family, data, size);
|
||||
if (ret != UCODE_OK)
|
||||
cleanup();
|
||||
|
||||
return ret;
|
||||
}
|
||||
|
||||
static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size)
|
||||
{
|
||||
struct cpuinfo_x86 *c;
|
||||
@ -951,14 +975,9 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz
|
||||
struct ucode_patch *p;
|
||||
enum ucode_state ret;
|
||||
|
||||
/* free old equiv table */
|
||||
free_equiv_cpu_table();
|
||||
|
||||
ret = __load_microcode_amd(family, data, size);
|
||||
if (ret != UCODE_OK) {
|
||||
cleanup();
|
||||
ret = _load_microcode_amd(family, data, size);
|
||||
if (ret != UCODE_OK)
|
||||
return ret;
|
||||
}
|
||||
|
||||
for_each_node(nid) {
|
||||
cpu = cpumask_first(cpumask_of_node(nid));
|
||||
|
||||
@ -207,7 +207,7 @@ static inline bool rdt_get_mb_table(struct rdt_resource *r)
|
||||
return false;
|
||||
}
|
||||
|
||||
static bool __get_mem_config_intel(struct rdt_resource *r)
|
||||
static __init bool __get_mem_config_intel(struct rdt_resource *r)
|
||||
{
|
||||
struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
|
||||
union cpuid_0x10_3_eax eax;
|
||||
@ -241,7 +241,7 @@ static bool __get_mem_config_intel(struct rdt_resource *r)
|
||||
return true;
|
||||
}
|
||||
|
||||
static bool __rdt_get_mem_config_amd(struct rdt_resource *r)
|
||||
static __init bool __rdt_get_mem_config_amd(struct rdt_resource *r)
|
||||
{
|
||||
struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
|
||||
u32 eax, ebx, ecx, edx, subleaf;
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue
Block a user