2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-25 05:34:00 +08:00

KVM/arm64 updates for v5.14.

- Add MTE support in guests, complete with tag save/restore interface
 - Reduce the impact of CMOs by moving them in the page-table code
 - Allow device block mappings at stage-2
 - Reduce the footprint of the vmemmap in protected mode
 - Support the vGIC on dumb systems such as the Apple M1
 - Add selftest infrastructure to support multiple configuration
   and apply that to PMU/non-PMU setups
 - Add selftests for the debug architecture
 - The usual crop of PMU fixes
 -----BEGIN PGP SIGNATURE-----
 
 iQJDBAABCgAtFiEEn9UcU+C1Yxj9lZw9I9DQutE9ekMFAmDV2bEPHG1hekBrZXJu
 ZWwub3JnAAoJECPQ0LrRPXpDEr8P/ivwROx5NwGcHGmU5RfUCT3aFqhtVHHwD/lu
 jPcgoO61kz9TelOu6QRaVuK+mVHxcq3iP4R8nPq/QCkUlEXTmK2xkyhXhGXSYpH4
 6jM8+BbC3eG7iAxx6H0UM4JTl4Riwat6ZZtXpWEWs9TKqOHOQYFpMkxSttwVZ1CZ
 SjbtFvXLEdzKn6PzUWnKdBNMV/mHsdAtohZit9oJOc4ttc8072XxETQ4TFQ+MSvA
 j9zY9QPmWzgcZnotqRRu9sbTGO2vxtXuUtY3sjdD8+C9OgSe9qvpnNjymcmfwaMu
 1fBkfh65oaO4ItJBdGOUOoEcFqwN5imPiI7CB/O+ZYkO9sBCuTUPSQwPkyiwXb9r
 bUkTaQw2nZiNWsqR1x07fQ2sGYbMp5mnmgmqiV4MUWkLmFp9LZATCWYTTn24cBNS
 6SjVP6/8S0r3EhLnYjH0Pn1we5PooU1EF6RlCAd3ewYoo+9fPnwjNYwIWH5i5wB7
 +tnei44NACAw9cfbos+BYQQ/dY15OSFzLzIMomlabB7OpXOdDg3H6tJnPbFwWwXb
 9nF8XdHqxeDVVVrDCAx1BSodSXm9xqgnQM2RDGTUnpVcAfqAr3MXX6VsyKQDzj8T
 QXF9qOVCBAABv6BXAvSQ6mvMJZDUVbUPEPhf7kXzF46JsRd6A7wWoU/OnMGHQ/w7
 wjvH8HVy
 =fWBV
 -----END PGP SIGNATURE-----

Merge tag 'kvmarm-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD

KVM/arm64 updates for v5.14.

- Add MTE support in guests, complete with tag save/restore interface
- Reduce the impact of CMOs by moving them in the page-table code
- Allow device block mappings at stage-2
- Reduce the footprint of the vmemmap in protected mode
- Support the vGIC on dumb systems such as the Apple M1
- Add selftest infrastructure to support multiple configuration
  and apply that to PMU/non-PMU setups
- Add selftests for the debug architecture
- The usual crop of PMU fixes
This commit is contained in:
Paolo Bonzini 2021-06-25 11:24:24 -04:00
commit b8917b4ae4
816 changed files with 9392 additions and 4425 deletions

View File

@ -1458,11 +1458,22 @@ unprivileged_bpf_disabled
=========================
Writing 1 to this entry will disable unprivileged calls to ``bpf()``;
once disabled, calling ``bpf()`` without ``CAP_SYS_ADMIN`` will return
``-EPERM``.
once disabled, calling ``bpf()`` without ``CAP_SYS_ADMIN`` or ``CAP_BPF``
will return ``-EPERM``. Once set to 1, this can't be cleared from the
running kernel anymore.
Once set, this can't be cleared.
Writing 2 to this entry will also disable unprivileged calls to ``bpf()``,
however, an admin can still change this setting later on, if needed, by
writing 0 or 1 to this entry.
If ``BPF_UNPRIV_DEFAULT_OFF`` is enabled in the kernel config, then this
entry will default to 2 instead of 0.
= =============================================================
0 Unprivileged calls to ``bpf()`` are enabled
1 Unprivileged calls to ``bpf()`` are disabled without recovery
2 Unprivileged calls to ``bpf()`` are disabled
= =============================================================
watchdog
========

View File

@ -60,7 +60,6 @@ properties:
maxItems: 2
idt,xtal-load-femtofarads:
$ref: /schemas/types.yaml#/definitions/uint32
minimum: 9000
maximum: 22760
description: Optional load capacitor for XTAL1 and XTAL2
@ -84,7 +83,6 @@ patternProperties:
enum: [ 1800000, 2500000, 3300000 ]
idt,slew-percent:
description: The Slew rate control for CMOS single-ended.
$ref: /schemas/types.yaml#/definitions/uint32
enum: [ 80, 85, 90, 100 ]
required:

View File

@ -46,6 +46,13 @@ properties:
description: |
I2C bus timeout in microseconds
fsl,i2c-erratum-a004447:
$ref: /schemas/types.yaml#/definitions/flag
description: |
Indicates the presence of QorIQ erratum A-004447, which
says that the standard i2c recovery scheme mechanism does
not work and an alternate implementation is needed.
required:
- compatible
- reg

View File

@ -102,7 +102,6 @@ patternProperties:
st,adc-channel-names:
description: List of single-ended channel names.
$ref: /schemas/types.yaml#/definitions/string-array
st,filter-order:
description: |

View File

@ -38,6 +38,5 @@ properties:
Duration in seconds which the key should be kept pressed for device to
reset automatically. Device with key pressed reset feature can specify
this property.
$ref: /schemas/types.yaml#/definitions/uint32
additionalProperties: true

View File

@ -92,7 +92,6 @@ properties:
this interconnect to send RPMh commands.
qcom,bcm-voter-names:
$ref: /schemas/types.yaml#/definitions/string-array
description: |
Names for each of the qcom,bcm-voters specified.

View File

@ -4,8 +4,8 @@ This controller is present on BCM6318, BCM6328, BCM6362 and BCM63268.
In these SoCs it's possible to control LEDs both as GPIOs or by hardware.
However, on some devices there are Serial LEDs (LEDs connected to a 74x164
controller), which can either be controlled by software (exporting the 74x164
as spi-gpio. See Documentation/devicetree/bindings/gpio/gpio-74x164.txt), or
by hardware using this driver.
as spi-gpio. See Documentation/devicetree/bindings/gpio/fairchild,74hc595.yaml),
or by hardware using this driver.
Some of these Serial LEDs are hardware controlled (e.g. ethernet LEDs) and
exporting the 74x164 as spi-gpio prevents those LEDs to be hardware
controlled, so the only chance to keep them working is by using this driver.

View File

@ -3,7 +3,7 @@ LEDs connected to Broadcom BCM6358 controller
This controller is present on BCM6358 and BCM6368.
In these SoCs there are Serial LEDs (LEDs connected to a 74x164 controller),
which can either be controlled by software (exporting the 74x164 as spi-gpio.
See Documentation/devicetree/bindings/gpio/gpio-74x164.txt), or
See Documentation/devicetree/bindings/gpio/fairchild,74hc595.yaml), or
by hardware using this driver.
Required properties:

View File

@ -99,32 +99,26 @@ properties:
Indicates that the channel acts as primary among the bonded channels.
port:
type: object
$ref: /schemas/graph.yaml#/properties/port
unevaluatedProperties: false
description:
Child port node corresponding to the data input, in accordance with the
video interface bindings defined in
Documentation/devicetree/bindings/media/video-interfaces.txt.
The port node must contain at least one endpoint.
Child port node corresponding to the data input. The port node must
contain at least one endpoint.
properties:
endpoint:
type: object
$ref: /schemas/graph.yaml#/$defs/endpoint-base
unevaluatedProperties: false
properties:
remote-endpoint:
description:
A phandle to the remote tuner endpoint subnode in remote node
port.
sync-active:
$ref: /schemas/types.yaml#/definitions/uint32
enum: [0, 1]
description:
Indicates sync signal polarity, 0/1 for low/high respectively.
This property maps to SYNCAC bit in the hardware manual. The
default is 1 (active high).
additionalProperties: false
required:
- compatible
- reg

View File

@ -105,7 +105,6 @@ properties:
- description: Whether the IPA clock is enabled (if valid)
qcom,smem-state-names:
$ref: /schemas/types.yaml#/definitions/string-array
description: The names of the state bits used for SMP2P output
items:
- const: ipa-clock-enabled-valid

View File

@ -10,7 +10,7 @@ allOf:
- $ref: ethernet-controller.yaml#
maintainers:
- Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
- Sergei Shtylyov <sergei.shtylyov@gmail.com>
properties:
compatible:

View File

@ -9,7 +9,6 @@ Required properties:
"mediatek,mt8173-efuse" or "mediatek,efuse": for MT8173
"mediatek,mt8192-efuse", "mediatek,efuse": for MT8192
"mediatek,mt8516-efuse", "mediatek,efuse": for MT8516
"mediatek,mt8192-efuse", "mediatek,efuse": for MT8192
- reg: Should contain registers location and length
= Data cells =

View File

@ -118,7 +118,7 @@ patternProperties:
description:
Specifies the Spread Spectrum Clocking mode used. It can be NO_SSC,
EXTERNAL_SSC or INTERNAL_SSC.
Refer include/dt-bindings/phy/phy-cadence-torrent.h for the constants to be used.
Refer include/dt-bindings/phy/phy-cadence.h for the constants to be used.
$ref: /schemas/types.yaml#/definitions/uint32
enum: [0, 1, 2]
default: 0

View File

@ -20,7 +20,7 @@ properties:
maxItems: 1
phys:
$ref: /schemas/types.yaml#/definitions/phandle
maxItems: 1
description: phandle to the USB phy
monitored-battery:

View File

@ -49,7 +49,7 @@ properties:
maxItems: 1
memory-region:
$ref: /schemas/types.yaml#/definitions/phandle
maxItems: 1
description:
phandle to a node describing reserved memory (System RAM memory)
The M core can't access all the DDR memory space on some platform,

View File

@ -72,7 +72,7 @@ examples:
mux-controls = <&mux>;
spi-flash@0 {
flash@0 {
compatible = "jedec,spi-nor";
reg = <0>;
spi-max-frequency = <40000000>;

View File

@ -123,6 +123,8 @@ are in ``drivers/usb/common/common.c``.
In addition, some functions useful for creating debugging output are
defined in ``drivers/usb/common/debug.c``.
.. _usb_header:
Host-Side Data Types and Macros
===============================

View File

@ -109,6 +109,16 @@ auxiliary vector.
scv 0 syscalls will always behave as PPC_FEATURE2_HTM_NOSC.
ptrace
------
When ptracing system calls (PTRACE_SYSCALL), the pt_regs.trap value contains
the system call type that can be used to distinguish between sc and scv 0
system calls, and the different register conventions can be accounted for.
If the value of (pt_regs.trap & 0xfff0) is 0xc00 then the system call was
performed with the sc instruction, if it is 0x3000 then the system call was
performed with the scv 0 instruction.
vsyscall
========

View File

@ -250,14 +250,14 @@ Users can read via ``ioctl(SECCOMP_IOCTL_NOTIF_RECV)`` (or ``poll()``) on a
seccomp notification fd to receive a ``struct seccomp_notif``, which contains
five members: the input length of the structure, a unique-per-filter ``id``,
the ``pid`` of the task which triggered this request (which may be 0 if the
task is in a pid ns not visible from the listener's pid namespace), a ``flags``
member which for now only has ``SECCOMP_NOTIF_FLAG_SIGNALED``, representing
whether or not the notification is a result of a non-fatal signal, and the
``data`` passed to seccomp. Userspace can then make a decision based on this
information about what to do, and ``ioctl(SECCOMP_IOCTL_NOTIF_SEND)`` a
response, indicating what should be returned to userspace. The ``id`` member of
``struct seccomp_notif_resp`` should be the same ``id`` as in ``struct
seccomp_notif``.
task is in a pid ns not visible from the listener's pid namespace). The
notification also contains the ``data`` passed to seccomp, and a filters flag.
The structure should be zeroed out prior to calling the ioctl.
Userspace can then make a decision based on this information about what to do,
and ``ioctl(SECCOMP_IOCTL_NOTIF_SEND)`` a response, indicating what should be
returned to userspace. The ``id`` member of ``struct seccomp_notif_resp`` should
be the same ``id`` as in ``struct seccomp_notif``.
It is worth noting that ``struct seccomp_data`` contains the values of register
arguments to the syscall, but does not contain pointers to memory. The task's

View File

@ -5039,6 +5039,42 @@ see KVM_XEN_VCPU_SET_ATTR above.
The KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST type may not be used
with the KVM_XEN_VCPU_GET_ATTR ioctl.
4.130 KVM_ARM_MTE_COPY_TAGS
---------------------------
:Capability: KVM_CAP_ARM_MTE
:Architectures: arm64
:Type: vm ioctl
:Parameters: struct kvm_arm_copy_mte_tags
:Returns: number of bytes copied, < 0 on error (-EINVAL for incorrect
arguments, -EFAULT if memory cannot be accessed).
::
struct kvm_arm_copy_mte_tags {
__u64 guest_ipa;
__u64 length;
void __user *addr;
__u64 flags;
__u64 reserved[2];
};
Copies Memory Tagging Extension (MTE) tags to/from guest tag memory. The
``guest_ipa`` and ``length`` fields must be ``PAGE_SIZE`` aligned. The ``addr``
field must point to a buffer which the tags will be copied to or from.
``flags`` specifies the direction of copy, either ``KVM_ARM_TAGS_TO_GUEST`` or
``KVM_ARM_TAGS_FROM_GUEST``.
The size of the buffer to store the tags is ``(length / 16)`` bytes
(granules in MTE are 16 bytes long). Each byte contains a single tag
value. This matches the format of ``PTRACE_PEEKMTETAGS`` and
``PTRACE_POKEMTETAGS``.
If an error occurs before any data is copied then a negative error code is
returned. If some tags have been copied before an error occurs then the number
of bytes successfully copied is returned. If the call completes successfully
then ``length`` is returned.
4.131 KVM_GET_SREGS2
------------------
@ -6622,6 +6658,29 @@ that are valid (ie: if KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES is
set in the 'flags' field then both 'insn_size' and 'insn_bytes' have valid data
in them.)
7.28 KVM_CAP_ARM_MTE
--------------------
:Architectures: arm64
:Parameters: none
This capability indicates that KVM (and the hardware) supports exposing the
Memory Tagging Extensions (MTE) to the guest. It must also be enabled by the
VMM before creating any VCPUs to allow the guest access. Note that MTE is only
available to a guest running in AArch64 mode and enabling this capability will
cause attempts to create AArch32 VCPUs to fail.
When enabled the guest is able to access tags associated with any memory given
to the guest. KVM will ensure that the tags are maintained during swap or
hibernation of the host; however the VMM needs to manually save/restore the
tags as appropriate if the VM is migrated.
When this capability is enabled all memory in memslots must be mapped as
not-shareable (no MAP_SHARED), attempts to create a memslot with a
MAP_SHARED mmap will result in an -EINVAL return.
When enabled the VMM may make use of the ``KVM_ARM_MTE_COPY_TAGS`` ioctl to
perform a bulk copy of tags to/from the guest.
8. Other capabilities.
======================

View File

@ -1618,8 +1618,8 @@ F: Documentation/devicetree/bindings/sound/amlogic*
F: sound/soc/meson/
ARM/Amlogic Meson SoC support
M: Neil Armstrong <narmstrong@baylibre.com>
M: Kevin Hilman <khilman@baylibre.com>
R: Neil Armstrong <narmstrong@baylibre.com>
R: Jerome Brunet <jbrunet@baylibre.com>
R: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@ -4138,6 +4138,14 @@ S: Odd Fixes
F: Documentation/devicetree/bindings/arm/cavium-thunder2.txt
F: arch/arm64/boot/dts/cavium/thunder2-99xx*
CBS/ETF/TAPRIO QDISCS
M: Vinicius Costa Gomes <vinicius.gomes@intel.com>
S: Maintained
L: netdev@vger.kernel.org
F: net/sched/sch_cbs.c
F: net/sched/sch_etf.c
F: net/sched/sch_taprio.c
CC2520 IEEE-802.15.4 RADIO DRIVER
M: Varka Bhadram <varkabhadram@gmail.com>
L: linux-wpan@vger.kernel.org
@ -5569,7 +5577,6 @@ F: drivers/soc/fsl/dpio
DPAA2 ETHERNET DRIVER
M: Ioana Ciornei <ioana.ciornei@nxp.com>
M: Ioana Radulescu <ruxandra.radulescu@nxp.com>
L: netdev@vger.kernel.org
S: Maintained
F: Documentation/networking/device_drivers/ethernet/freescale/dpaa2/ethernet-driver.rst
@ -9986,6 +9993,8 @@ F: arch/arm64/include/asm/kvm*
F: arch/arm64/include/uapi/asm/kvm*
F: arch/arm64/kvm/
F: include/kvm/arm_*
F: tools/testing/selftests/kvm/*/aarch64/
F: tools/testing/selftests/kvm/aarch64/
KERNEL VIRTUAL MACHINE FOR MIPS (KVM/mips)
M: Huacai Chen <chenhuacai@kernel.org>
@ -12180,6 +12189,7 @@ F: drivers/platform/surface/surfacepro3_button.c
MICROSOFT SURFACE SYSTEM AGGREGATOR SUBSYSTEM
M: Maximilian Luz <luzmaximilian@gmail.com>
L: platform-driver-x86@vger.kernel.org
S: Maintained
W: https://github.com/linux-surface/surface-aggregator-module
C: irc://chat.freenode.net/##linux-surface
@ -12680,9 +12690,9 @@ F: drivers/rtc/rtc-ntxec.c
F: include/linux/mfd/ntxec.h
NETRONOME ETHERNET DRIVERS
M: Simon Horman <simon.horman@netronome.com>
M: Simon Horman <simon.horman@corigine.com>
R: Jakub Kicinski <kuba@kernel.org>
L: oss-drivers@netronome.com
L: oss-drivers@corigine.com
S: Maintained
F: drivers/net/ethernet/netronome/
@ -12709,7 +12719,6 @@ M: "David S. Miller" <davem@davemloft.net>
M: Jakub Kicinski <kuba@kernel.org>
L: netdev@vger.kernel.org
S: Maintained
W: http://www.linuxfoundation.org/en/Net
Q: https://patchwork.kernel.org/project/netdevbpf/list/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
@ -12754,7 +12763,6 @@ M: "David S. Miller" <davem@davemloft.net>
M: Jakub Kicinski <kuba@kernel.org>
L: netdev@vger.kernel.org
S: Maintained
W: http://www.linuxfoundation.org/en/Net
Q: https://patchwork.kernel.org/project/netdevbpf/list/
B: mailto:netdev@vger.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
@ -12896,8 +12904,10 @@ F: include/uapi/linux/nexthop.h
F: net/ipv4/nexthop.c
NFC SUBSYSTEM
M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com>
L: linux-nfc@lists.01.org (moderated for non-subscribers)
L: netdev@vger.kernel.org
S: Orphan
S: Maintained
F: Documentation/devicetree/bindings/net/nfc/
F: drivers/nfc/
F: include/linux/platform_data/nfcmrvl.h
@ -13205,7 +13215,6 @@ F: Documentation/devicetree/bindings/sound/tfa9879.txt
F: sound/soc/codecs/tfa9879*
NXP-NCI NFC DRIVER
M: Clément Perrochaud <clement.perrochaud@effinnov.com>
R: Charles Gorand <charles.gorand@effinnov.com>
L: linux-nfc@lists.01.org (moderated for non-subscribers)
S: Supported
@ -14317,10 +14326,12 @@ PER-CPU MEMORY ALLOCATOR
M: Dennis Zhou <dennis@kernel.org>
M: Tejun Heo <tj@kernel.org>
M: Christoph Lameter <cl@linux.com>
L: linux-mm@kvack.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/dennis/percpu.git
F: arch/*/include/asm/percpu.h
F: include/linux/percpu*.h
F: lib/percpu*.c
F: mm/percpu*.c
PER-TASK DELAY ACCOUNTING
@ -14734,7 +14745,6 @@ W: https://wireless.wiki.kernel.org/en/users/Drivers/p54
F: drivers/net/wireless/intersil/prism54/
PROC FILESYSTEM
R: Alexey Dobriyan <adobriyan@gmail.com>
L: linux-kernel@vger.kernel.org
L: linux-fsdevel@vger.kernel.org
S: Maintained
@ -15945,6 +15955,7 @@ S390 IUCV NETWORK LAYER
M: Julian Wiedmann <jwi@linux.ibm.com>
M: Karsten Graul <kgraul@linux.ibm.com>
L: linux-s390@vger.kernel.org
L: netdev@vger.kernel.org
S: Supported
W: http://www.ibm.com/developerworks/linux/linux390/
F: drivers/s390/net/*iucv*
@ -15955,6 +15966,7 @@ S390 NETWORK DRIVERS
M: Julian Wiedmann <jwi@linux.ibm.com>
M: Karsten Graul <kgraul@linux.ibm.com>
L: linux-s390@vger.kernel.org
L: netdev@vger.kernel.org
S: Supported
W: http://www.ibm.com/developerworks/linux/linux390/
F: drivers/s390/net/
@ -17304,6 +17316,12 @@ L: linux-i2c@vger.kernel.org
S: Maintained
F: drivers/i2c/busses/i2c-stm32*
ST STM32 SPI DRIVER
M: Alain Volmat <alain.volmat@foss.st.com>
L: linux-spi@vger.kernel.org
S: Maintained
F: drivers/spi/spi-stm32.c
ST STPDDC60 DRIVER
M: Daniel Nilsson <daniel.nilsson@flex.com>
L: linux-hwmon@vger.kernel.org
@ -17662,7 +17680,6 @@ R: Mika Westerberg <mika.westerberg@linux.intel.com>
L: linux-i2c@vger.kernel.org
S: Maintained
F: drivers/i2c/busses/i2c-designware-*
F: include/linux/platform_data/i2c-designware.h
SYNOPSYS DESIGNWARE MMC/SD/SDIO DRIVER
M: Jaehoon Chung <jh80.chung@samsung.com>
@ -19998,6 +20015,7 @@ F: arch/x86/xen/*swiotlb*
F: drivers/xen/*swiotlb*
XFS FILESYSTEM
C: irc://irc.oftc.net/xfs
M: Darrick J. Wong <djwong@kernel.org>
M: linux-xfs@vger.kernel.org
L: linux-xfs@vger.kernel.org

View File

@ -2,7 +2,7 @@
VERSION = 5
PATCHLEVEL = 13
SUBLEVEL = 0
EXTRAVERSION = -rc2
EXTRAVERSION = -rc4
NAME = Frozen Wasteland
# *DOCUMENTATION*
@ -928,6 +928,11 @@ CC_FLAGS_LTO += -fvisibility=hidden
# Limit inlining across translation units to reduce binary size
KBUILD_LDFLAGS += -mllvm -import-instr-limit=5
# Check for frame size exceeding threshold during prolog/epilog insertion.
ifneq ($(CONFIG_FRAME_WARN),0)
KBUILD_LDFLAGS += -plugin-opt=-warn-stack-size=$(CONFIG_FRAME_WARN)
endif
endif
ifdef CONFIG_LTO

View File

@ -482,7 +482,7 @@
550 common process_madvise sys_process_madvise
551 common epoll_pwait2 sys_epoll_pwait2
552 common mount_setattr sys_mount_setattr
553 common quotactl_path sys_quotactl_path
# 553 reserved for quotactl_path
554 common landlock_create_ruleset sys_landlock_create_ruleset
555 common landlock_add_rule sys_landlock_add_rule
556 common landlock_restrict_self sys_landlock_restrict_self

View File

@ -10,6 +10,7 @@ config ARCH_WPCM450
bool "Support for WPCM450 BMC (Hermon)"
depends on ARCH_MULTI_V5
select CPU_ARM926T
select WPCM450_AIC
select NPCM7XX_TIMER
help
General support for WPCM450 BMC (Hermon).

View File

@ -121,8 +121,13 @@ static int cplds_probe(struct platform_device *pdev)
return fpga->irq;
base_irq = platform_get_irq(pdev, 1);
if (base_irq < 0)
if (base_irq < 0) {
base_irq = 0;
} else {
ret = devm_irq_alloc_descs(&pdev->dev, base_irq, base_irq, CPLDS_NB_IRQ, 0);
if (ret < 0)
return ret;
}
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
fpga->base = devm_ioremap_resource(&pdev->dev, res);

View File

@ -456,7 +456,7 @@
440 common process_madvise sys_process_madvise
441 common epoll_pwait2 sys_epoll_pwait2
442 common mount_setattr sys_mount_setattr
443 common quotactl_path sys_quotactl_path
# 443 reserved for quotactl_path
444 common landlock_create_ruleset sys_landlock_create_ruleset
445 common landlock_add_rule sys_landlock_add_rule
446 common landlock_restrict_self sys_landlock_restrict_self

View File

@ -1,6 +1,5 @@
# SPDX-License-Identifier: GPL-2.0-only
obj-y += kernel/ mm/
obj-$(CONFIG_NET) += net/
obj-y += kernel/ mm/ net/
obj-$(CONFIG_KVM) += kvm/
obj-$(CONFIG_XEN) += xen/
obj-$(CONFIG_CRYPTO) += crypto/

View File

@ -14,7 +14,6 @@
ports {
port@0 {
reg = <0>;
csi20_in: endpoint {
clock-lanes = <0>;
data-lanes = <1 2>;
@ -29,7 +28,6 @@
ports {
port@0 {
reg = <0>;
csi40_in: endpoint {
clock-lanes = <0>;
data-lanes = <1 2>;

View File

@ -2573,6 +2573,10 @@
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
};
port@1 {
#address-cells = <1>;
#size-cells = <0>;
@ -2628,6 +2632,10 @@
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
};
port@1 {
#address-cells = <1>;
#size-cells = <0>;

View File

@ -2419,6 +2419,10 @@
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
};
port@1 {
#address-cells = <1>;
#size-cells = <0>;
@ -2474,6 +2478,10 @@
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
};
port@1 {
#address-cells = <1>;
#size-cells = <0>;

View File

@ -33,7 +33,7 @@
status = "okay";
ports {
port {
port@0 {
csi40_in: endpoint {
clock-lanes = <0>;
data-lanes = <1 2>;

View File

@ -1823,6 +1823,10 @@
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
};
port@1 {
#address-cells = <1>;
#size-cells = <0>;

View File

@ -2709,6 +2709,10 @@
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
};
port@1 {
#address-cells = <1>;
#size-cells = <0>;
@ -2764,6 +2768,10 @@
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
};
port@1 {
#address-cells = <1>;
#size-cells = <0>;

View File

@ -192,6 +192,10 @@
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
};
port@1 {
#address-cells = <1>;
#size-cells = <0>;

View File

@ -3097,6 +3097,10 @@
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
};
port@1 {
#address-cells = <1>;
#size-cells = <0>;
@ -3152,6 +3156,10 @@
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
};
port@1 {
#address-cells = <1>;
#size-cells = <0>;
@ -3191,6 +3199,10 @@
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
};
port@1 {
#address-cells = <1>;
#size-cells = <0>;

View File

@ -2761,6 +2761,10 @@
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
};
port@1 {
#address-cells = <1>;
#size-cells = <0>;
@ -2816,6 +2820,10 @@
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
};
port@1 {
#address-cells = <1>;
#size-cells = <0>;

View File

@ -2499,6 +2499,10 @@
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
};
port@1 {
#address-cells = <1>;
#size-cells = <0>;
@ -2554,6 +2558,10 @@
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
};
port@1 {
#address-cells = <1>;
#size-cells = <0>;

View File

@ -2575,6 +2575,10 @@
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
};
port@1 {
#address-cells = <1>;
#size-cells = <0>;
@ -2630,6 +2634,10 @@
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
};
port@1 {
#address-cells = <1>;
#size-cells = <0>;

View File

@ -1106,6 +1106,10 @@
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
};
port@1 {
#address-cells = <1>;
#size-cells = <0>;

View File

@ -1439,6 +1439,10 @@
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
};
port@1 {
#address-cells = <1>;
#size-cells = <0>;
@ -1478,6 +1482,10 @@
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
};
port@1 {
#address-cells = <1>;
#size-cells = <0>;

View File

@ -298,8 +298,6 @@
ports {
port@0 {
reg = <0>;
csi40_in: endpoint {
clock-lanes = <0>;
data-lanes = <1 2>;

View File

@ -1970,6 +1970,10 @@
#address-cells = <1>;
#size-cells = <0>;
port@0 {
reg = <0>;
};
port@1 {
#address-cells = <1>;
#size-cells = <0>;

View File

@ -349,7 +349,6 @@
ports {
port@0 {
reg = <0>;
csi20_in: endpoint {
clock-lanes = <0>;
data-lanes = <1>;
@ -364,8 +363,6 @@
ports {
port@0 {
reg = <0>;
csi40_in: endpoint {
clock-lanes = <0>;
data-lanes = <1 2 3 4>;

View File

@ -197,11 +197,6 @@ alternative_endif
#define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...) \
alternative_insn insn1, insn2, cap, IS_ENABLED(cfg)
.macro user_alt, label, oldinstr, newinstr, cond
9999: alternative_insn "\oldinstr", "\newinstr", \cond
_asm_extable 9999b, \label
.endm
#endif /* __ASSEMBLY__ */
/*

View File

@ -124,7 +124,8 @@ static inline u32 gic_read_rpr(void)
#define gic_read_lpir(c) readq_relaxed(c)
#define gic_write_lpir(v, c) writeq_relaxed(v, c)
#define gic_flush_dcache_to_poc(a,l) __flush_dcache_area((a), (l))
#define gic_flush_dcache_to_poc(a,l) \
dcache_clean_inval_poc((unsigned long)(a), (unsigned long)(a)+(l))
#define gits_read_baser(c) readq_relaxed(c)
#define gits_write_baser(v, c) writeq_relaxed(v, c)

View File

@ -130,15 +130,27 @@ alternative_endif
.endm
/*
* Emit an entry into the exception table
* Create an exception table entry for `insn`, which will branch to `fixup`
* when an unhandled fault is taken.
*/
.macro _asm_extable, from, to
.macro _asm_extable, insn, fixup
.pushsection __ex_table, "a"
.align 3
.long (\from - .), (\to - .)
.long (\insn - .), (\fixup - .)
.popsection
.endm
/*
* Create an exception table entry for `insn` if `fixup` is provided. Otherwise
* do nothing.
*/
.macro _cond_extable, insn, fixup
.ifnc \fixup,
_asm_extable \insn, \fixup
.endif
.endm
#define USER(l, x...) \
9999: x; \
_asm_extable 9999b, l
@ -375,51 +387,53 @@ alternative_cb_end
bfi \tcr, \tmp0, \pos, #3
.endm
/*
* Macro to perform a data cache maintenance for the interval
* [kaddr, kaddr + size)
*
* op: operation passed to dc instruction
* domain: domain used in dsb instruciton
* kaddr: starting virtual address of the region
* size: size of the region
* Corrupts: kaddr, size, tmp1, tmp2
*/
.macro __dcache_op_workaround_clean_cache, op, kaddr
.macro __dcache_op_workaround_clean_cache, op, addr
alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE
dc \op, \kaddr
dc \op, \addr
alternative_else
dc civac, \kaddr
dc civac, \addr
alternative_endif
.endm
.macro dcache_by_line_op op, domain, kaddr, size, tmp1, tmp2
/*
* Macro to perform a data cache maintenance for the interval
* [start, end)
*
* op: operation passed to dc instruction
* domain: domain used in dsb instruciton
* start: starting virtual address of the region
* end: end virtual address of the region
* fixup: optional label to branch to on user fault
* Corrupts: start, end, tmp1, tmp2
*/
.macro dcache_by_line_op op, domain, start, end, tmp1, tmp2, fixup
dcache_line_size \tmp1, \tmp2
add \size, \kaddr, \size
sub \tmp2, \tmp1, #1
bic \kaddr, \kaddr, \tmp2
9998:
bic \start, \start, \tmp2
.Ldcache_op\@:
.ifc \op, cvau
__dcache_op_workaround_clean_cache \op, \kaddr
__dcache_op_workaround_clean_cache \op, \start
.else
.ifc \op, cvac
__dcache_op_workaround_clean_cache \op, \kaddr
__dcache_op_workaround_clean_cache \op, \start
.else
.ifc \op, cvap
sys 3, c7, c12, 1, \kaddr // dc cvap
sys 3, c7, c12, 1, \start // dc cvap
.else
.ifc \op, cvadp
sys 3, c7, c13, 1, \kaddr // dc cvadp
sys 3, c7, c13, 1, \start // dc cvadp
.else
dc \op, \kaddr
dc \op, \start
.endif
.endif
.endif
.endif
add \kaddr, \kaddr, \tmp1
cmp \kaddr, \size
b.lo 9998b
add \start, \start, \tmp1
cmp \start, \end
b.lo .Ldcache_op\@
dsb \domain
_cond_extable .Ldcache_op\@, \fixup
.endm
/*
@ -427,20 +441,22 @@ alternative_endif
* [start, end)
*
* start, end: virtual addresses describing the region
* label: A label to branch to on user fault.
* fixup: optional label to branch to on user fault
* Corrupts: tmp1, tmp2
*/
.macro invalidate_icache_by_line start, end, tmp1, tmp2, label
.macro invalidate_icache_by_line start, end, tmp1, tmp2, fixup
icache_line_size \tmp1, \tmp2
sub \tmp2, \tmp1, #1
bic \tmp2, \start, \tmp2
9997:
USER(\label, ic ivau, \tmp2) // invalidate I line PoU
.Licache_op\@:
ic ivau, \tmp2 // invalidate I line PoU
add \tmp2, \tmp2, \tmp1
cmp \tmp2, \end
b.lo 9997b
b.lo .Licache_op\@
dsb ish
isb
_cond_extable .Licache_op\@, \fixup
.endm
/*

View File

@ -74,7 +74,7 @@ static inline unsigned long array_index_mask_nospec(unsigned long idx,
* This insanity brought to you by speculative system register reads,
* out-of-order memory accesses, sequence locks and Thomas Gleixner.
*
* http://lists.infradead.org/pipermail/linux-arm-kernel/2019-February/631195.html
* https://lore.kernel.org/r/alpine.DEB.2.21.1902081950260.1662@nanos.tec.linutronix.de/
*/
#define arch_counter_enforce_ordering(val) do { \
u64 tmp, _val = (val); \

View File

@ -30,45 +30,58 @@
* the implementation assumes non-aliasing VIPT D-cache and (aliasing)
* VIPT I-cache.
*
* flush_icache_range(start, end)
* All functions below apply to the interval [start, end)
* - start - virtual start address (inclusive)
* - end - virtual end address (exclusive)
*
* Ensure coherency between the I-cache and the D-cache in the
* region described by start, end.
* - start - virtual start address
* - end - virtual end address
* caches_clean_inval_pou(start, end)
*
* invalidate_icache_range(start, end)
* Ensure coherency between the I-cache and the D-cache region to
* the Point of Unification.
*
* Invalidate the I-cache in the region described by start, end.
* - start - virtual start address
* - end - virtual end address
* caches_clean_inval_user_pou(start, end)
*
* __flush_cache_user_range(start, end)
* Ensure coherency between the I-cache and the D-cache region to
* the Point of Unification.
* Use only if the region might access user memory.
*
* Ensure coherency between the I-cache and the D-cache in the
* region described by start, end.
* - start - virtual start address
* - end - virtual end address
* icache_inval_pou(start, end)
*
* __flush_dcache_area(kaddr, size)
* Invalidate I-cache region to the Point of Unification.
*
* Ensure that the data held in page is written back.
* - kaddr - page address
* - size - region size
* dcache_clean_inval_poc(start, end)
*
* Clean and invalidate D-cache region to the Point of Coherency.
*
* dcache_inval_poc(start, end)
*
* Invalidate D-cache region to the Point of Coherency.
*
* dcache_clean_poc(start, end)
*
* Clean D-cache region to the Point of Coherency.
*
* dcache_clean_pop(start, end)
*
* Clean D-cache region to the Point of Persistence.
*
* dcache_clean_pou(start, end)
*
* Clean D-cache region to the Point of Unification.
*/
extern void __flush_icache_range(unsigned long start, unsigned long end);
extern int invalidate_icache_range(unsigned long start, unsigned long end);
extern void __flush_dcache_area(void *addr, size_t len);
extern void __inval_dcache_area(void *addr, size_t len);
extern void __clean_dcache_area_poc(void *addr, size_t len);
extern void __clean_dcache_area_pop(void *addr, size_t len);
extern void __clean_dcache_area_pou(void *addr, size_t len);
extern long __flush_cache_user_range(unsigned long start, unsigned long end);
extern void sync_icache_aliases(void *kaddr, unsigned long len);
extern void caches_clean_inval_pou(unsigned long start, unsigned long end);
extern void icache_inval_pou(unsigned long start, unsigned long end);
extern void dcache_clean_inval_poc(unsigned long start, unsigned long end);
extern void dcache_inval_poc(unsigned long start, unsigned long end);
extern void dcache_clean_poc(unsigned long start, unsigned long end);
extern void dcache_clean_pop(unsigned long start, unsigned long end);
extern void dcache_clean_pou(unsigned long start, unsigned long end);
extern long caches_clean_inval_user_pou(unsigned long start, unsigned long end);
extern void sync_icache_aliases(unsigned long start, unsigned long end);
static inline void flush_icache_range(unsigned long start, unsigned long end)
{
__flush_icache_range(start, end);
caches_clean_inval_pou(start, end);
/*
* IPI all online CPUs so that they undergo a context synchronization
@ -122,7 +135,7 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *,
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
extern void flush_dcache_page(struct page *);
static __always_inline void __flush_icache_all(void)
static __always_inline void icache_inval_all_pou(void)
{
if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC))
return;

View File

@ -137,7 +137,7 @@ void efi_virtmap_unload(void);
static inline void efi_capsule_flush_cache_range(void *addr, int size)
{
__flush_dcache_area(addr, size);
dcache_clean_inval_poc((unsigned long)addr, (unsigned long)addr + size);
}
#endif /* _ASM_EFI_H */

View File

@ -12,7 +12,8 @@
#include <asm/types.h>
/* Hyp Configuration Register (HCR) bits */
#define HCR_ATA (UL(1) << 56)
#define HCR_ATA_SHIFT 56
#define HCR_ATA (UL(1) << HCR_ATA_SHIFT)
#define HCR_FWB (UL(1) << 46)
#define HCR_API (UL(1) << 41)
#define HCR_APK (UL(1) << 40)

View File

@ -84,6 +84,9 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu)
if (cpus_have_const_cap(ARM64_MISMATCHED_CACHE_TYPE) ||
vcpu_el1_is_32bit(vcpu))
vcpu->arch.hcr_el2 |= HCR_TID2;
if (kvm_has_mte(vcpu->kvm))
vcpu->arch.hcr_el2 |= HCR_ATA;
}
static inline unsigned long *vcpu_hcr(struct kvm_vcpu *vcpu)

View File

@ -46,6 +46,7 @@
#define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(2)
#define KVM_REQ_RECORD_STEAL KVM_ARCH_REQ(3)
#define KVM_REQ_RELOAD_GICv4 KVM_ARCH_REQ(4)
#define KVM_REQ_RELOAD_PMU KVM_ARCH_REQ(5)
#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
KVM_DIRTY_LOG_INITIALLY_SET)
@ -132,6 +133,9 @@ struct kvm_arch {
u8 pfr0_csv2;
u8 pfr0_csv3;
/* Memory Tagging Extension enabled for the guest */
bool mte_enabled;
};
struct kvm_vcpu_fault_info {
@ -206,6 +210,12 @@ enum vcpu_sysreg {
CNTP_CVAL_EL0,
CNTP_CTL_EL0,
/* Memory Tagging Extension registers */
RGSR_EL1, /* Random Allocation Tag Seed Register */
GCR_EL1, /* Tag Control Register */
TFSR_EL1, /* Tag Fault Status Register (EL1) */
TFSRE0_EL1, /* Tag Fault Status Register (EL0) */
/* 32bit specific registers. Keep them at the end of the range */
DACR32_EL2, /* Domain Access Control Register */
IFSR32_EL2, /* Instruction Fault Status Register */
@ -716,6 +726,9 @@ int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
struct kvm_device_attr *attr);
long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm,
struct kvm_arm_copy_mte_tags *copy_tags);
/* Guest/host FPSIMD coordination helpers */
int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu);
@ -764,6 +777,7 @@ bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);
#define kvm_arm_vcpu_sve_finalized(vcpu) \
((vcpu)->arch.flags & KVM_ARM64_VCPU_SVE_FINALIZED)
#define kvm_has_mte(kvm) (system_supports_mte() && (kvm)->arch.mte_enabled)
#define kvm_vcpu_has_pmu(vcpu) \
(test_bit(KVM_ARM_VCPU_PMU_V3, (vcpu)->arch.features))

View File

@ -180,17 +180,16 @@ static inline void *__kvm_vector_slot2addr(void *base,
struct kvm;
#define kvm_flush_dcache_to_poc(a,l) __flush_dcache_area((a), (l))
#define kvm_flush_dcache_to_poc(a,l) \
dcache_clean_inval_poc((unsigned long)(a), (unsigned long)(a)+(l))
static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
{
return (vcpu_read_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;
}
static inline void __clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size)
static inline void __clean_dcache_guest_page(void *va, size_t size)
{
void *va = page_address(pfn_to_page(pfn));
/*
* With FWB, we ensure that the guest always accesses memory using
* cacheable attributes, and we don't have to clean to PoC when
@ -203,18 +202,14 @@ static inline void __clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size)
kvm_flush_dcache_to_poc(va, size);
}
static inline void __invalidate_icache_guest_page(kvm_pfn_t pfn,
unsigned long size)
static inline void __invalidate_icache_guest_page(void *va, size_t size)
{
if (icache_is_aliasing()) {
/* any kind of VIPT cache */
__flush_icache_all();
icache_inval_all_pou();
} else if (is_kernel_in_hyp_mode() || !icache_is_vpipt()) {
/* PIPT or VPIPT at EL2 (see comment in __kvm_tlb_flush_vmid_ipa) */
void *va = page_address(pfn_to_page(pfn));
invalidate_icache_range((unsigned long)va,
(unsigned long)va + size);
icache_inval_pou((unsigned long)va, (unsigned long)va + size);
}
}

View File

@ -0,0 +1,66 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2020-2021 ARM Ltd.
*/
#ifndef __ASM_KVM_MTE_H
#define __ASM_KVM_MTE_H
#ifdef __ASSEMBLY__
#include <asm/sysreg.h>
#ifdef CONFIG_ARM64_MTE
.macro mte_switch_to_guest g_ctxt, h_ctxt, reg1
alternative_if_not ARM64_MTE
b .L__skip_switch\@
alternative_else_nop_endif
mrs \reg1, hcr_el2
tbz \reg1, #(HCR_ATA_SHIFT), .L__skip_switch\@
mrs_s \reg1, SYS_RGSR_EL1
str \reg1, [\h_ctxt, #CPU_RGSR_EL1]
mrs_s \reg1, SYS_GCR_EL1
str \reg1, [\h_ctxt, #CPU_GCR_EL1]
ldr \reg1, [\g_ctxt, #CPU_RGSR_EL1]
msr_s SYS_RGSR_EL1, \reg1
ldr \reg1, [\g_ctxt, #CPU_GCR_EL1]
msr_s SYS_GCR_EL1, \reg1
.L__skip_switch\@:
.endm
.macro mte_switch_to_hyp g_ctxt, h_ctxt, reg1
alternative_if_not ARM64_MTE
b .L__skip_switch\@
alternative_else_nop_endif
mrs \reg1, hcr_el2
tbz \reg1, #(HCR_ATA_SHIFT), .L__skip_switch\@
mrs_s \reg1, SYS_RGSR_EL1
str \reg1, [\g_ctxt, #CPU_RGSR_EL1]
mrs_s \reg1, SYS_GCR_EL1
str \reg1, [\g_ctxt, #CPU_GCR_EL1]
ldr \reg1, [\h_ctxt, #CPU_RGSR_EL1]
msr_s SYS_RGSR_EL1, \reg1
ldr \reg1, [\h_ctxt, #CPU_GCR_EL1]
msr_s SYS_GCR_EL1, \reg1
isb
.L__skip_switch\@:
.endm
#else /* !CONFIG_ARM64_MTE */
.macro mte_switch_to_guest g_ctxt, h_ctxt, reg1
.endm
.macro mte_switch_to_hyp g_ctxt, h_ctxt, reg1
.endm
#endif /* CONFIG_ARM64_MTE */
#endif /* __ASSEMBLY__ */
#endif /* __ASM_KVM_MTE_H */

View File

@ -27,23 +27,29 @@ typedef u64 kvm_pte_t;
/**
* struct kvm_pgtable_mm_ops - Memory management callbacks.
* @zalloc_page: Allocate a single zeroed memory page. The @arg parameter
* can be used by the walker to pass a memcache. The
* initial refcount of the page is 1.
* @zalloc_pages_exact: Allocate an exact number of zeroed memory pages. The
* @size parameter is in bytes, and is rounded-up to the
* next page boundary. The resulting allocation is
* physically contiguous.
* @free_pages_exact: Free an exact number of memory pages previously
* allocated by zalloc_pages_exact.
* @get_page: Increment the refcount on a page.
* @put_page: Decrement the refcount on a page. When the refcount
* reaches 0 the page is automatically freed.
* @page_count: Return the refcount of a page.
* @phys_to_virt: Convert a physical address into a virtual address mapped
* in the current context.
* @virt_to_phys: Convert a virtual address mapped in the current context
* into a physical address.
* @zalloc_page: Allocate a single zeroed memory page.
* The @arg parameter can be used by the walker
* to pass a memcache. The initial refcount of
* the page is 1.
* @zalloc_pages_exact: Allocate an exact number of zeroed memory pages.
* The @size parameter is in bytes, and is rounded
* up to the next page boundary. The resulting
* allocation is physically contiguous.
* @free_pages_exact: Free an exact number of memory pages previously
* allocated by zalloc_pages_exact.
* @get_page: Increment the refcount on a page.
* @put_page: Decrement the refcount on a page. When the
* refcount reaches 0 the page is automatically
* freed.
* @page_count: Return the refcount of a page.
* @phys_to_virt: Convert a physical address into a virtual
* address mapped in the current context.
* @virt_to_phys: Convert a virtual address mapped in the current
* context into a physical address.
* @dcache_clean_inval_poc: Clean and invalidate the data cache to the PoC
* for the specified memory address range.
* @icache_inval_pou: Invalidate the instruction cache to the PoU
* for the specified memory address range.
*/
struct kvm_pgtable_mm_ops {
void* (*zalloc_page)(void *arg);
@ -54,6 +60,8 @@ struct kvm_pgtable_mm_ops {
int (*page_count)(void *addr);
void* (*phys_to_virt)(phys_addr_t phys);
phys_addr_t (*virt_to_phys)(void *addr);
void (*dcache_clean_inval_poc)(void *addr, size_t size);
void (*icache_inval_pou)(void *addr, size_t size);
};
/**

View File

@ -7,6 +7,7 @@
#define MTE_GRANULE_SIZE UL(16)
#define MTE_GRANULE_MASK (~(MTE_GRANULE_SIZE - 1))
#define MTE_GRANULES_PER_PAGE (PAGE_SIZE / MTE_GRANULE_SIZE)
#define MTE_TAG_SHIFT 56
#define MTE_TAG_SIZE 4
#define MTE_TAG_MASK GENMASK((MTE_TAG_SHIFT + (MTE_TAG_SIZE - 1)), MTE_TAG_SHIFT)

View File

@ -37,7 +37,7 @@ void mte_free_tag_storage(char *storage);
/* track which pages have valid allocation tags */
#define PG_mte_tagged PG_arch_2
void mte_sync_tags(pte_t *ptep, pte_t pte);
void mte_sync_tags(pte_t old_pte, pte_t pte);
void mte_copy_page_tags(void *kto, const void *kfrom);
void mte_thread_init_user(void);
void mte_thread_switch(struct task_struct *next);
@ -53,7 +53,7 @@ int mte_ptrace_copy_tags(struct task_struct *child, long request,
/* unused if !CONFIG_ARM64_MTE, silence the compiler */
#define PG_mte_tagged 0
static inline void mte_sync_tags(pte_t *ptep, pte_t pte)
static inline void mte_sync_tags(pte_t old_pte, pte_t pte)
{
}
static inline void mte_copy_page_tags(void *kto, const void *kfrom)

View File

@ -314,9 +314,25 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte))
__sync_icache_dcache(pte);
if (system_supports_mte() &&
pte_present(pte) && pte_tagged(pte) && !pte_special(pte))
mte_sync_tags(ptep, pte);
/*
* If the PTE would provide user space access to the tags associated
* with it then ensure that the MTE tags are synchronised. Although
* pte_access_permitted() returns false for exec only mappings, they
* don't expose tags (instruction fetches don't check tags).
*/
if (system_supports_mte() && pte_access_permitted(pte, false) &&
!pte_special(pte)) {
pte_t old_pte = READ_ONCE(*ptep);
/*
* We only need to synchronise if the new PTE has tags enabled
* or if swapping in (in which case another mapping may have
* set tags in the past even if this PTE isn't tagged).
* (!pte_none() && !pte_present()) is an open coded version of
* is_swap_pte()
*/
if (pte_tagged(pte) || (!pte_none(old_pte) && !pte_present(old_pte)))
mte_sync_tags(old_pte, pte);
}
__check_racy_pte_update(mm, ptep, pte);

View File

@ -651,7 +651,8 @@
#define INIT_SCTLR_EL2_MMU_ON \
(SCTLR_ELx_M | SCTLR_ELx_C | SCTLR_ELx_SA | SCTLR_ELx_I | \
SCTLR_ELx_IESB | SCTLR_ELx_WXN | ENDIAN_SET_EL2 | SCTLR_EL2_RES1)
SCTLR_ELx_IESB | SCTLR_ELx_WXN | ENDIAN_SET_EL2 | \
SCTLR_ELx_ITFSB | SCTLR_EL2_RES1)
#define INIT_SCTLR_EL2_MMU_OFF \
(SCTLR_EL2_RES1 | ENDIAN_SET_EL2)

View File

@ -893,8 +893,7 @@ __SYSCALL(__NR_process_madvise, sys_process_madvise)
__SYSCALL(__NR_epoll_pwait2, compat_sys_epoll_pwait2)
#define __NR_mount_setattr 442
__SYSCALL(__NR_mount_setattr, sys_mount_setattr)
#define __NR_quotactl_path 443
__SYSCALL(__NR_quotactl_path, sys_quotactl_path)
/* 443 is reserved for quotactl_path */
#define __NR_landlock_create_ruleset 444
__SYSCALL(__NR_landlock_create_ruleset, sys_landlock_create_ruleset)
#define __NR_landlock_add_rule 445

View File

@ -184,6 +184,17 @@ struct kvm_vcpu_events {
__u32 reserved[12];
};
struct kvm_arm_copy_mte_tags {
__u64 guest_ipa;
__u64 length;
void __user *addr;
__u64 flags;
__u64 reserved[2];
};
#define KVM_ARM_TAGS_TO_GUEST 0
#define KVM_ARM_TAGS_FROM_GUEST 1
/* If you need to interpret the index values, here is the key: */
#define KVM_REG_ARM_COPROC_MASK 0x000000000FFF0000
#define KVM_REG_ARM_COPROC_SHIFT 16

View File

@ -181,7 +181,7 @@ static void __nocfi __apply_alternatives(struct alt_region *region, bool is_modu
*/
if (!is_module) {
dsb(ish);
__flush_icache_all();
icache_inval_all_pou();
isb();
/* Ignore ARM64_CB bit from feature mask */

View File

@ -111,6 +111,8 @@ int main(void)
DEFINE(VCPU_WORKAROUND_FLAGS, offsetof(struct kvm_vcpu, arch.workaround_flags));
DEFINE(VCPU_HCR_EL2, offsetof(struct kvm_vcpu, arch.hcr_el2));
DEFINE(CPU_USER_PT_REGS, offsetof(struct kvm_cpu_context, regs));
DEFINE(CPU_RGSR_EL1, offsetof(struct kvm_cpu_context, sys_regs[RGSR_EL1]));
DEFINE(CPU_GCR_EL1, offsetof(struct kvm_cpu_context, sys_regs[GCR_EL1]));
DEFINE(CPU_APIAKEYLO_EL1, offsetof(struct kvm_cpu_context, sys_regs[APIAKEYLO_EL1]));
DEFINE(CPU_APIBKEYLO_EL1, offsetof(struct kvm_cpu_context, sys_regs[APIBKEYLO_EL1]));
DEFINE(CPU_APDAKEYLO_EL1, offsetof(struct kvm_cpu_context, sys_regs[APDAKEYLO_EL1]));

View File

@ -28,7 +28,8 @@ SYM_CODE_START(efi_enter_kernel)
* stale icache entries from before relocation.
*/
ldr w1, =kernel_size
bl __clean_dcache_area_poc
add x1, x0, x1
bl dcache_clean_poc
ic ialluis
/*
@ -36,8 +37,8 @@ SYM_CODE_START(efi_enter_kernel)
* so that we can safely disable the MMU and caches.
*/
adr x0, 0f
ldr w1, 3f
bl __clean_dcache_area_poc
adr x1, 3f
bl dcache_clean_poc
0:
/* Turn off Dcache and MMU */
mrs x0, CurrentEL
@ -64,5 +65,5 @@ SYM_CODE_START(efi_enter_kernel)
mov x2, xzr
mov x3, xzr
br x19
3:
SYM_CODE_END(efi_enter_kernel)
3: .long . - 0b

View File

@ -117,8 +117,8 @@ SYM_CODE_START_LOCAL(preserve_boot_args)
dmb sy // needed before dc ivac with
// MMU off
mov x1, #0x20 // 4 x 8 bytes
b __inval_dcache_area // tail call
add x1, x0, #0x20 // 4 x 8 bytes
b dcache_inval_poc // tail call
SYM_CODE_END(preserve_boot_args)
/*
@ -268,8 +268,7 @@ SYM_FUNC_START_LOCAL(__create_page_tables)
*/
adrp x0, init_pg_dir
adrp x1, init_pg_end
sub x1, x1, x0
bl __inval_dcache_area
bl dcache_inval_poc
/*
* Clear the init page tables.
@ -382,13 +381,11 @@ SYM_FUNC_START_LOCAL(__create_page_tables)
adrp x0, idmap_pg_dir
adrp x1, idmap_pg_end
sub x1, x1, x0
bl __inval_dcache_area
bl dcache_inval_poc
adrp x0, init_pg_dir
adrp x1, init_pg_end
sub x1, x1, x0
bl __inval_dcache_area
bl dcache_inval_poc
ret x28
SYM_FUNC_END(__create_page_tables)

View File

@ -45,7 +45,7 @@
* Because this code has to be copied to a 'safe' page, it can't call out to
* other functions by PC-relative address. Also remember that it may be
* mid-way through over-writing other functions. For this reason it contains
* code from flush_icache_range() and uses the copy_page() macro.
* code from caches_clean_inval_pou() and uses the copy_page() macro.
*
* This 'safe' page is mapped via ttbr0, and executed from there. This function
* switches to a copy of the linear map in ttbr1, performs the restore, then
@ -87,11 +87,12 @@ SYM_CODE_START(swsusp_arch_suspend_exit)
copy_page x0, x1, x2, x3, x4, x5, x6, x7, x8, x9
add x1, x10, #PAGE_SIZE
/* Clean the copied page to PoU - based on flush_icache_range() */
/* Clean the copied page to PoU - based on caches_clean_inval_pou() */
raw_dcache_line_size x2, x3
sub x3, x2, #1
bic x4, x10, x3
2: dc cvau, x4 /* clean D line / unified line */
2: /* clean D line / unified line */
alternative_insn "dc cvau, x4", "dc civac, x4", ARM64_WORKAROUND_CLEAN_CACHE
add x4, x4, x2
cmp x4, x1
b.lo 2b

View File

@ -210,7 +210,7 @@ static int create_safe_exec_page(void *src_start, size_t length,
return -ENOMEM;
memcpy(page, src_start, length);
__flush_icache_range((unsigned long)page, (unsigned long)page + length);
caches_clean_inval_pou((unsigned long)page, (unsigned long)page + length);
rc = trans_pgd_idmap_page(&trans_info, &trans_ttbr0, &t0sz, page);
if (rc)
return rc;
@ -240,8 +240,6 @@ static int create_safe_exec_page(void *src_start, size_t length,
return 0;
}
#define dcache_clean_range(start, end) __flush_dcache_area(start, (end - start))
#ifdef CONFIG_ARM64_MTE
static DEFINE_XARRAY(mte_pages);
@ -383,13 +381,18 @@ int swsusp_arch_suspend(void)
ret = swsusp_save();
} else {
/* Clean kernel core startup/idle code to PoC*/
dcache_clean_range(__mmuoff_data_start, __mmuoff_data_end);
dcache_clean_range(__idmap_text_start, __idmap_text_end);
dcache_clean_inval_poc((unsigned long)__mmuoff_data_start,
(unsigned long)__mmuoff_data_end);
dcache_clean_inval_poc((unsigned long)__idmap_text_start,
(unsigned long)__idmap_text_end);
/* Clean kvm setup code to PoC? */
if (el2_reset_needed()) {
dcache_clean_range(__hyp_idmap_text_start, __hyp_idmap_text_end);
dcache_clean_range(__hyp_text_start, __hyp_text_end);
dcache_clean_inval_poc(
(unsigned long)__hyp_idmap_text_start,
(unsigned long)__hyp_idmap_text_end);
dcache_clean_inval_poc((unsigned long)__hyp_text_start,
(unsigned long)__hyp_text_end);
}
swsusp_mte_restore_tags();
@ -474,7 +477,8 @@ int swsusp_arch_resume(void)
* The hibernate exit text contains a set of el2 vectors, that will
* be executed at el2 with the mmu off in order to reload hyp-stub.
*/
__flush_dcache_area(hibernate_exit, exit_size);
dcache_clean_inval_poc((unsigned long)hibernate_exit,
(unsigned long)hibernate_exit + exit_size);
/*
* KASLR will cause the el2 vectors to be in a different location in

View File

@ -237,7 +237,8 @@ asmlinkage void __init init_feature_override(void)
for (i = 0; i < ARRAY_SIZE(regs); i++) {
if (regs[i]->override)
__flush_dcache_area(regs[i]->override,
dcache_clean_inval_poc((unsigned long)regs[i]->override,
(unsigned long)regs[i]->override +
sizeof(*regs[i]->override));
}
}

View File

@ -35,7 +35,7 @@ __efistub_strnlen = __pi_strnlen;
__efistub_strcmp = __pi_strcmp;
__efistub_strncmp = __pi_strncmp;
__efistub_strrchr = __pi_strrchr;
__efistub___clean_dcache_area_poc = __pi___clean_dcache_area_poc;
__efistub_dcache_clean_poc = __pi_dcache_clean_poc;
#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
__efistub___memcpy = __pi_memcpy;

View File

@ -198,7 +198,7 @@ int __kprobes aarch64_insn_patch_text_nosync(void *addr, u32 insn)
ret = aarch64_insn_write(tp, insn);
if (ret == 0)
__flush_icache_range((uintptr_t)tp,
caches_clean_inval_pou((uintptr_t)tp,
(uintptr_t)tp + AARCH64_INSN_SIZE);
return ret;

View File

@ -72,7 +72,9 @@ u64 __init kaslr_early_init(void)
* we end up running with module randomization disabled.
*/
module_alloc_base = (u64)_etext - MODULES_VSIZE;
__flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base));
dcache_clean_inval_poc((unsigned long)&module_alloc_base,
(unsigned long)&module_alloc_base +
sizeof(module_alloc_base));
/*
* Try to map the FDT early. If this fails, we simply bail,
@ -170,8 +172,12 @@ u64 __init kaslr_early_init(void)
module_alloc_base += (module_range * (seed & ((1 << 21) - 1))) >> 21;
module_alloc_base &= PAGE_MASK;
__flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base));
__flush_dcache_area(&memstart_offset_seed, sizeof(memstart_offset_seed));
dcache_clean_inval_poc((unsigned long)&module_alloc_base,
(unsigned long)&module_alloc_base +
sizeof(module_alloc_base));
dcache_clean_inval_poc((unsigned long)&memstart_offset_seed,
(unsigned long)&memstart_offset_seed +
sizeof(memstart_offset_seed));
return offset;
}

View File

@ -68,10 +68,16 @@ int machine_kexec_post_load(struct kimage *kimage)
kimage->arch.kern_reloc = __pa(reloc_code);
kexec_image_info(kimage);
/* Flush the reloc_code in preparation for its execution. */
__flush_dcache_area(reloc_code, arm64_relocate_new_kernel_size);
flush_icache_range((uintptr_t)reloc_code, (uintptr_t)reloc_code +
arm64_relocate_new_kernel_size);
/*
* For execution with the MMU off, reloc_code needs to be cleaned to the
* PoC and invalidated from the I-cache.
*/
dcache_clean_inval_poc((unsigned long)reloc_code,
(unsigned long)reloc_code +
arm64_relocate_new_kernel_size);
icache_inval_pou((uintptr_t)reloc_code,
(uintptr_t)reloc_code +
arm64_relocate_new_kernel_size);
return 0;
}
@ -102,16 +108,18 @@ static void kexec_list_flush(struct kimage *kimage)
for (entry = &kimage->head; ; entry++) {
unsigned int flag;
void *addr;
unsigned long addr;
/* flush the list entries. */
__flush_dcache_area(entry, sizeof(kimage_entry_t));
dcache_clean_inval_poc((unsigned long)entry,
(unsigned long)entry +
sizeof(kimage_entry_t));
flag = *entry & IND_FLAGS;
if (flag == IND_DONE)
break;
addr = phys_to_virt(*entry & PAGE_MASK);
addr = (unsigned long)phys_to_virt(*entry & PAGE_MASK);
switch (flag) {
case IND_INDIRECTION:
@ -120,7 +128,7 @@ static void kexec_list_flush(struct kimage *kimage)
break;
case IND_SOURCE:
/* flush the source pages. */
__flush_dcache_area(addr, PAGE_SIZE);
dcache_clean_inval_poc(addr, addr + PAGE_SIZE);
break;
case IND_DESTINATION:
break;
@ -147,8 +155,10 @@ static void kexec_segment_flush(const struct kimage *kimage)
kimage->segment[i].memsz,
kimage->segment[i].memsz / PAGE_SIZE);
__flush_dcache_area(phys_to_virt(kimage->segment[i].mem),
kimage->segment[i].memsz);
dcache_clean_inval_poc(
(unsigned long)phys_to_virt(kimage->segment[i].mem),
(unsigned long)phys_to_virt(kimage->segment[i].mem) +
kimage->segment[i].memsz);
}
}

View File

@ -32,10 +32,9 @@ DEFINE_STATIC_KEY_FALSE(mte_async_mode);
EXPORT_SYMBOL_GPL(mte_async_mode);
#endif
static void mte_sync_page_tags(struct page *page, pte_t *ptep, bool check_swap)
static void mte_sync_page_tags(struct page *page, pte_t old_pte,
bool check_swap, bool pte_is_tagged)
{
pte_t old_pte = READ_ONCE(*ptep);
if (check_swap && is_swap_pte(old_pte)) {
swp_entry_t entry = pte_to_swp_entry(old_pte);
@ -43,6 +42,9 @@ static void mte_sync_page_tags(struct page *page, pte_t *ptep, bool check_swap)
return;
}
if (!pte_is_tagged)
return;
page_kasan_tag_reset(page);
/*
* We need smp_wmb() in between setting the flags and clearing the
@ -55,16 +57,22 @@ static void mte_sync_page_tags(struct page *page, pte_t *ptep, bool check_swap)
mte_clear_page_tags(page_address(page));
}
void mte_sync_tags(pte_t *ptep, pte_t pte)
void mte_sync_tags(pte_t old_pte, pte_t pte)
{
struct page *page = pte_page(pte);
long i, nr_pages = compound_nr(page);
bool check_swap = nr_pages == 1;
bool pte_is_tagged = pte_tagged(pte);
/* Early out if there's nothing to do */
if (!check_swap && !pte_is_tagged)
return;
/* if PG_mte_tagged is set, tags have already been initialised */
for (i = 0; i < nr_pages; i++, page++) {
if (!test_and_set_bit(PG_mte_tagged, &page->flags))
mte_sync_page_tags(page, ptep, check_swap);
mte_sync_page_tags(page, old_pte, check_swap,
pte_is_tagged);
}
}

View File

@ -21,7 +21,7 @@ void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
memcpy(dst, src, len);
/* flush caches (dcache/icache) */
sync_icache_aliases(dst, len);
sync_icache_aliases((unsigned long)dst, (unsigned long)dst + len);
kunmap_atomic(xol_page_kaddr);
}

View File

@ -122,7 +122,9 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
secondary_data.task = idle;
secondary_data.stack = task_stack_page(idle) + THREAD_SIZE;
update_cpu_boot_status(CPU_MMU_OFF);
__flush_dcache_area(&secondary_data, sizeof(secondary_data));
dcache_clean_inval_poc((unsigned long)&secondary_data,
(unsigned long)&secondary_data +
sizeof(secondary_data));
/* Now bring the CPU into our world */
ret = boot_secondary(cpu, idle);
@ -143,7 +145,9 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
pr_crit("CPU%u: failed to come online\n", cpu);
secondary_data.task = NULL;
secondary_data.stack = NULL;
__flush_dcache_area(&secondary_data, sizeof(secondary_data));
dcache_clean_inval_poc((unsigned long)&secondary_data,
(unsigned long)&secondary_data +
sizeof(secondary_data));
status = READ_ONCE(secondary_data.status);
if (status == CPU_MMU_OFF)
status = READ_ONCE(__early_cpu_boot_status);

View File

@ -36,7 +36,7 @@ static void write_pen_release(u64 val)
unsigned long size = sizeof(secondary_holding_pen_release);
secondary_holding_pen_release = val;
__flush_dcache_area(start, size);
dcache_clean_inval_poc((unsigned long)start, (unsigned long)start + size);
}
@ -90,8 +90,9 @@ static int smp_spin_table_cpu_prepare(unsigned int cpu)
* the boot protocol.
*/
writeq_relaxed(pa_holding_pen, release_addr);
__flush_dcache_area((__force void *)release_addr,
sizeof(*release_addr));
dcache_clean_inval_poc((__force unsigned long)release_addr,
(__force unsigned long)release_addr +
sizeof(*release_addr));
/*
* Send an event to wake up the secondary CPU.

View File

@ -41,7 +41,7 @@ __do_compat_cache_op(unsigned long start, unsigned long end)
dsb(ish);
}
ret = __flush_cache_user_range(start, start + chunk);
ret = caches_clean_inval_user_pou(start, start + chunk);
if (ret)
return ret;

View File

@ -9,6 +9,7 @@
#include <linux/kvm_host.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/irqdomain.h>
#include <linux/uaccess.h>
#include <clocksource/arm_arch_timer.h>
@ -973,6 +974,135 @@ static int kvm_timer_dying_cpu(unsigned int cpu)
return 0;
}
static int timer_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu)
{
if (vcpu)
irqd_set_forwarded_to_vcpu(d);
else
irqd_clr_forwarded_to_vcpu(d);
return 0;
}
static int timer_irq_set_irqchip_state(struct irq_data *d,
enum irqchip_irq_state which, bool val)
{
if (which != IRQCHIP_STATE_ACTIVE || !irqd_is_forwarded_to_vcpu(d))
return irq_chip_set_parent_state(d, which, val);
if (val)
irq_chip_mask_parent(d);
else
irq_chip_unmask_parent(d);
return 0;
}
static void timer_irq_eoi(struct irq_data *d)
{
if (!irqd_is_forwarded_to_vcpu(d))
irq_chip_eoi_parent(d);
}
static void timer_irq_ack(struct irq_data *d)
{
d = d->parent_data;
if (d->chip->irq_ack)
d->chip->irq_ack(d);
}
static struct irq_chip timer_chip = {
.name = "KVM",
.irq_ack = timer_irq_ack,
.irq_mask = irq_chip_mask_parent,
.irq_unmask = irq_chip_unmask_parent,
.irq_eoi = timer_irq_eoi,
.irq_set_type = irq_chip_set_type_parent,
.irq_set_vcpu_affinity = timer_irq_set_vcpu_affinity,
.irq_set_irqchip_state = timer_irq_set_irqchip_state,
};
static int timer_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
unsigned int nr_irqs, void *arg)
{
irq_hw_number_t hwirq = (uintptr_t)arg;
return irq_domain_set_hwirq_and_chip(domain, virq, hwirq,
&timer_chip, NULL);
}
static void timer_irq_domain_free(struct irq_domain *domain, unsigned int virq,
unsigned int nr_irqs)
{
}
static const struct irq_domain_ops timer_domain_ops = {
.alloc = timer_irq_domain_alloc,
.free = timer_irq_domain_free,
};
static struct irq_ops arch_timer_irq_ops = {
.get_input_level = kvm_arch_timer_get_input_level,
};
static void kvm_irq_fixup_flags(unsigned int virq, u32 *flags)
{
*flags = irq_get_trigger_type(virq);
if (*flags != IRQF_TRIGGER_HIGH && *flags != IRQF_TRIGGER_LOW) {
kvm_err("Invalid trigger for timer IRQ%d, assuming level low\n",
virq);
*flags = IRQF_TRIGGER_LOW;
}
}
static int kvm_irq_init(struct arch_timer_kvm_info *info)
{
struct irq_domain *domain = NULL;
if (info->virtual_irq <= 0) {
kvm_err("kvm_arch_timer: invalid virtual timer IRQ: %d\n",
info->virtual_irq);
return -ENODEV;
}
host_vtimer_irq = info->virtual_irq;
kvm_irq_fixup_flags(host_vtimer_irq, &host_vtimer_irq_flags);
if (kvm_vgic_global_state.no_hw_deactivation) {
struct fwnode_handle *fwnode;
struct irq_data *data;
fwnode = irq_domain_alloc_named_fwnode("kvm-timer");
if (!fwnode)
return -ENOMEM;
/* Assume both vtimer and ptimer in the same parent */
data = irq_get_irq_data(host_vtimer_irq);
domain = irq_domain_create_hierarchy(data->domain, 0,
NR_KVM_TIMERS, fwnode,
&timer_domain_ops, NULL);
if (!domain) {
irq_domain_free_fwnode(fwnode);
return -ENOMEM;
}
arch_timer_irq_ops.flags |= VGIC_IRQ_SW_RESAMPLE;
WARN_ON(irq_domain_push_irq(domain, host_vtimer_irq,
(void *)TIMER_VTIMER));
}
if (info->physical_irq > 0) {
host_ptimer_irq = info->physical_irq;
kvm_irq_fixup_flags(host_ptimer_irq, &host_ptimer_irq_flags);
if (domain)
WARN_ON(irq_domain_push_irq(domain, host_ptimer_irq,
(void *)TIMER_PTIMER));
}
return 0;
}
int kvm_timer_hyp_init(bool has_gic)
{
struct arch_timer_kvm_info *info;
@ -986,23 +1116,12 @@ int kvm_timer_hyp_init(bool has_gic)
return -ENODEV;
}
err = kvm_irq_init(info);
if (err)
return err;
/* First, do the virtual EL1 timer irq */
if (info->virtual_irq <= 0) {
kvm_err("kvm_arch_timer: invalid virtual timer IRQ: %d\n",
info->virtual_irq);
return -ENODEV;
}
host_vtimer_irq = info->virtual_irq;
host_vtimer_irq_flags = irq_get_trigger_type(host_vtimer_irq);
if (host_vtimer_irq_flags != IRQF_TRIGGER_HIGH &&
host_vtimer_irq_flags != IRQF_TRIGGER_LOW) {
kvm_err("Invalid trigger for vtimer IRQ%d, assuming level low\n",
host_vtimer_irq);
host_vtimer_irq_flags = IRQF_TRIGGER_LOW;
}
err = request_percpu_irq(host_vtimer_irq, kvm_arch_timer_handler,
"kvm guest vtimer", kvm_get_running_vcpus());
if (err) {
@ -1027,15 +1146,6 @@ int kvm_timer_hyp_init(bool has_gic)
/* Now let's do the physical EL1 timer irq */
if (info->physical_irq > 0) {
host_ptimer_irq = info->physical_irq;
host_ptimer_irq_flags = irq_get_trigger_type(host_ptimer_irq);
if (host_ptimer_irq_flags != IRQF_TRIGGER_HIGH &&
host_ptimer_irq_flags != IRQF_TRIGGER_LOW) {
kvm_err("Invalid trigger for ptimer IRQ%d, assuming level low\n",
host_ptimer_irq);
host_ptimer_irq_flags = IRQF_TRIGGER_LOW;
}
err = request_percpu_irq(host_ptimer_irq, kvm_arch_timer_handler,
"kvm guest ptimer", kvm_get_running_vcpus());
if (err) {
@ -1143,7 +1253,7 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu)
ret = kvm_vgic_map_phys_irq(vcpu,
map.direct_vtimer->host_timer_irq,
map.direct_vtimer->irq.irq,
kvm_arch_timer_get_input_level);
&arch_timer_irq_ops);
if (ret)
return ret;
@ -1151,7 +1261,7 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu)
ret = kvm_vgic_map_phys_irq(vcpu,
map.direct_ptimer->host_timer_irq,
map.direct_ptimer->irq.irq,
kvm_arch_timer_get_input_level);
&arch_timer_irq_ops);
}
if (ret)

View File

@ -93,6 +93,12 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
r = 0;
kvm->arch.return_nisv_io_abort_to_user = true;
break;
case KVM_CAP_ARM_MTE:
if (!system_supports_mte() || kvm->created_vcpus)
return -EINVAL;
r = 0;
kvm->arch.mte_enabled = true;
break;
default:
r = -EINVAL;
break;
@ -237,6 +243,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
*/
r = 1;
break;
case KVM_CAP_ARM_MTE:
r = system_supports_mte();
break;
case KVM_CAP_STEAL_TIME:
r = kvm_arm_pvtime_supported();
break;
@ -689,6 +698,10 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu)
vgic_v4_load(vcpu);
preempt_enable();
}
if (kvm_check_request(KVM_REQ_RELOAD_PMU, vcpu))
kvm_pmu_handle_pmcr(vcpu,
__vcpu_sys_reg(vcpu, PMCR_EL0));
}
}
@ -1078,7 +1091,7 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
stage2_unmap_vm(vcpu->kvm);
else
__flush_icache_all();
icache_inval_all_pou();
}
vcpu_reset_hcr(vcpu);
@ -1350,6 +1363,13 @@ long kvm_arch_vm_ioctl(struct file *filp,
return 0;
}
case KVM_ARM_MTE_COPY_TAGS: {
struct kvm_arm_copy_mte_tags copy_tags;
if (copy_from_user(&copy_tags, argp, sizeof(copy_tags)))
return -EFAULT;
return kvm_vm_ioctl_mte_copy_tags(kvm, &copy_tags);
}
default:
return -EINVAL;
}

View File

@ -1015,3 +1015,89 @@ int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
return ret;
}
long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm,
struct kvm_arm_copy_mte_tags *copy_tags)
{
gpa_t guest_ipa = copy_tags->guest_ipa;
size_t length = copy_tags->length;
void __user *tags = copy_tags->addr;
gpa_t gfn;
bool write = !(copy_tags->flags & KVM_ARM_TAGS_FROM_GUEST);
int ret = 0;
if (!kvm_has_mte(kvm))
return -EINVAL;
if (copy_tags->reserved[0] || copy_tags->reserved[1])
return -EINVAL;
if (copy_tags->flags & ~KVM_ARM_TAGS_FROM_GUEST)
return -EINVAL;
if (length & ~PAGE_MASK || guest_ipa & ~PAGE_MASK)
return -EINVAL;
gfn = gpa_to_gfn(guest_ipa);
mutex_lock(&kvm->slots_lock);
while (length > 0) {
kvm_pfn_t pfn = gfn_to_pfn_prot(kvm, gfn, write, NULL);
void *maddr;
unsigned long num_tags;
struct page *page;
if (is_error_noslot_pfn(pfn)) {
ret = -EFAULT;
goto out;
}
page = pfn_to_online_page(pfn);
if (!page) {
/* Reject ZONE_DEVICE memory */
ret = -EFAULT;
goto out;
}
maddr = page_address(page);
if (!write) {
if (test_bit(PG_mte_tagged, &page->flags))
num_tags = mte_copy_tags_to_user(tags, maddr,
MTE_GRANULES_PER_PAGE);
else
/* No tags in memory, so write zeros */
num_tags = MTE_GRANULES_PER_PAGE -
clear_user(tags, MTE_GRANULES_PER_PAGE);
kvm_release_pfn_clean(pfn);
} else {
num_tags = mte_copy_tags_from_user(maddr, tags,
MTE_GRANULES_PER_PAGE);
/*
* Set the flag after checking the write
* completed fully
*/
if (num_tags == MTE_GRANULES_PER_PAGE)
set_bit(PG_mte_tagged, &page->flags);
kvm_release_pfn_dirty(pfn);
}
if (num_tags != MTE_GRANULES_PER_PAGE) {
ret = -EFAULT;
goto out;
}
gfn++;
tags += num_tags;
length -= PAGE_SIZE;
}
out:
mutex_unlock(&kvm->slots_lock);
/* If some data has been copied report the number of bytes copied */
if (length != copy_tags->length)
return copy_tags->length - length;
return ret;
}

View File

@ -13,6 +13,7 @@
#include <asm/kvm_arm.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_mmu.h>
#include <asm/kvm_mte.h>
#include <asm/kvm_ptrauth.h>
.text
@ -51,6 +52,9 @@ alternative_else_nop_endif
add x29, x0, #VCPU_CONTEXT
// mte_switch_to_guest(g_ctxt, h_ctxt, tmp1)
mte_switch_to_guest x29, x1, x2
// Macro ptrauth_switch_to_guest format:
// ptrauth_switch_to_guest(guest cxt, tmp1, tmp2, tmp3)
// The below macro to restore guest keys is not implemented in C code
@ -142,6 +146,9 @@ SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL)
// when this feature is enabled for kernel code.
ptrauth_switch_to_hyp x1, x2, x3, x4, x5
// mte_switch_to_hyp(g_ctxt, h_ctxt, reg1)
mte_switch_to_hyp x1, x2, x3
// Restore hyp's sp_el0
restore_sp_el0 x2, x3

View File

@ -112,7 +112,8 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode,
new |= (old & PSR_C_BIT);
new |= (old & PSR_V_BIT);
// TODO: TCO (if/when ARMv8.5-MemTag is exposed to guests)
if (kvm_has_mte(vcpu->kvm))
new |= PSR_TCO_BIT;
new |= (old & PSR_DIT_BIT);

View File

@ -76,6 +76,7 @@ el1_trap:
b __guest_exit
el1_irq:
el1_fiq:
get_vcpu_ptr x1, x0
mov x0, #ARM_EXCEPTION_IRQ
b __guest_exit
@ -131,7 +132,6 @@ SYM_CODE_END(\label)
invalid_vector el2t_error_invalid
invalid_vector el2h_irq_invalid
invalid_vector el2h_fiq_invalid
invalid_vector el1_fiq_invalid
.ltorg
@ -179,12 +179,12 @@ SYM_CODE_START(__kvm_hyp_vector)
valid_vect el1_sync // Synchronous 64-bit EL1
valid_vect el1_irq // IRQ 64-bit EL1
invalid_vect el1_fiq_invalid // FIQ 64-bit EL1
valid_vect el1_fiq // FIQ 64-bit EL1
valid_vect el1_error // Error 64-bit EL1
valid_vect el1_sync // Synchronous 32-bit EL1
valid_vect el1_irq // IRQ 32-bit EL1
invalid_vect el1_fiq_invalid // FIQ 32-bit EL1
valid_vect el1_fiq // FIQ 32-bit EL1
valid_vect el1_error // Error 32-bit EL1
SYM_CODE_END(__kvm_hyp_vector)

View File

@ -14,6 +14,7 @@
#include <asm/kvm_asm.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_hyp.h>
#include <asm/kvm_mmu.h>
static inline void __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
{
@ -26,6 +27,16 @@ static inline void __sysreg_save_user_state(struct kvm_cpu_context *ctxt)
ctxt_sys_reg(ctxt, TPIDRRO_EL0) = read_sysreg(tpidrro_el0);
}
static inline bool ctxt_has_mte(struct kvm_cpu_context *ctxt)
{
struct kvm_vcpu *vcpu = ctxt->__hyp_running_vcpu;
if (!vcpu)
vcpu = container_of(ctxt, struct kvm_vcpu, arch.ctxt);
return kvm_has_mte(kern_hyp_va(vcpu->kvm));
}
static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
{
ctxt_sys_reg(ctxt, CSSELR_EL1) = read_sysreg(csselr_el1);
@ -46,6 +57,11 @@ static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt)
ctxt_sys_reg(ctxt, PAR_EL1) = read_sysreg_par();
ctxt_sys_reg(ctxt, TPIDR_EL1) = read_sysreg(tpidr_el1);
if (ctxt_has_mte(ctxt)) {
ctxt_sys_reg(ctxt, TFSR_EL1) = read_sysreg_el1(SYS_TFSR);
ctxt_sys_reg(ctxt, TFSRE0_EL1) = read_sysreg_s(SYS_TFSRE0_EL1);
}
ctxt_sys_reg(ctxt, SP_EL1) = read_sysreg(sp_el1);
ctxt_sys_reg(ctxt, ELR_EL1) = read_sysreg_el1(SYS_ELR);
ctxt_sys_reg(ctxt, SPSR_EL1) = read_sysreg_el1(SYS_SPSR);
@ -107,6 +123,11 @@ static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt)
write_sysreg(ctxt_sys_reg(ctxt, PAR_EL1), par_el1);
write_sysreg(ctxt_sys_reg(ctxt, TPIDR_EL1), tpidr_el1);
if (ctxt_has_mte(ctxt)) {
write_sysreg_el1(ctxt_sys_reg(ctxt, TFSR_EL1), SYS_TFSR);
write_sysreg_s(ctxt_sys_reg(ctxt, TFSRE0_EL1), SYS_TFSRE0_EL1);
}
if (!has_vhe() &&
cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT) &&
ctxt->__hyp_running_vcpu) {

View File

@ -7,7 +7,7 @@
#include <nvhe/memory.h>
#include <nvhe/spinlock.h>
#define HYP_NO_ORDER UINT_MAX
#define HYP_NO_ORDER USHRT_MAX
struct hyp_pool {
/*
@ -19,48 +19,13 @@ struct hyp_pool {
struct list_head free_area[MAX_ORDER];
phys_addr_t range_start;
phys_addr_t range_end;
unsigned int max_order;
unsigned short max_order;
};
static inline void hyp_page_ref_inc(struct hyp_page *p)
{
struct hyp_pool *pool = hyp_page_to_pool(p);
hyp_spin_lock(&pool->lock);
p->refcount++;
hyp_spin_unlock(&pool->lock);
}
static inline int hyp_page_ref_dec_and_test(struct hyp_page *p)
{
struct hyp_pool *pool = hyp_page_to_pool(p);
int ret;
hyp_spin_lock(&pool->lock);
p->refcount--;
ret = (p->refcount == 0);
hyp_spin_unlock(&pool->lock);
return ret;
}
static inline void hyp_set_page_refcounted(struct hyp_page *p)
{
struct hyp_pool *pool = hyp_page_to_pool(p);
hyp_spin_lock(&pool->lock);
if (p->refcount) {
hyp_spin_unlock(&pool->lock);
BUG();
}
p->refcount = 1;
hyp_spin_unlock(&pool->lock);
}
/* Allocation */
void *hyp_alloc_pages(struct hyp_pool *pool, unsigned int order);
void hyp_get_page(void *addr);
void hyp_put_page(void *addr);
void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order);
void hyp_get_page(struct hyp_pool *pool, void *addr);
void hyp_put_page(struct hyp_pool *pool, void *addr);
/* Used pages cannot be freed */
int hyp_pool_init(struct hyp_pool *pool, u64 pfn, unsigned int nr_pages,

View File

@ -23,7 +23,7 @@ extern struct host_kvm host_kvm;
int __pkvm_prot_finalize(void);
int __pkvm_mark_hyp(phys_addr_t start, phys_addr_t end);
int kvm_host_prepare_stage2(void *mem_pgt_pool, void *dev_pgt_pool);
int kvm_host_prepare_stage2(void *pgt_pool_base);
void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt);
static __always_inline void __load_host_stage2(void)

View File

@ -7,12 +7,9 @@
#include <linux/types.h>
struct hyp_pool;
struct hyp_page {
unsigned int refcount;
unsigned int order;
struct hyp_pool *pool;
struct list_head node;
unsigned short refcount;
unsigned short order;
};
extern u64 __hyp_vmemmap;

View File

@ -78,19 +78,20 @@ static inline unsigned long hyp_s1_pgtable_pages(void)
return res;
}
static inline unsigned long host_s2_mem_pgtable_pages(void)
static inline unsigned long host_s2_pgtable_pages(void)
{
unsigned long res;
/*
* Include an extra 16 pages to safely upper-bound the worst case of
* concatenated pgds.
*/
return __hyp_pgtable_total_pages() + 16;
}
res = __hyp_pgtable_total_pages() + 16;
static inline unsigned long host_s2_dev_pgtable_pages(void)
{
/* Allow 1 GiB for MMIO mappings */
return __hyp_pgtable_max_pages(SZ_1G >> PAGE_SHIFT);
res += __hyp_pgtable_max_pages(SZ_1G >> PAGE_SHIFT);
return res;
}
#endif /* __KVM_HYP_MM_H */

View File

@ -7,7 +7,7 @@
#include <asm/assembler.h>
#include <asm/alternative.h>
SYM_FUNC_START_PI(__flush_dcache_area)
SYM_FUNC_START_PI(dcache_clean_inval_poc)
dcache_by_line_op civac, sy, x0, x1, x2, x3
ret
SYM_FUNC_END_PI(__flush_dcache_area)
SYM_FUNC_END_PI(dcache_clean_inval_poc)

View File

@ -23,8 +23,7 @@
extern unsigned long hyp_nr_cpus;
struct host_kvm host_kvm;
static struct hyp_pool host_s2_mem;
static struct hyp_pool host_s2_dev;
static struct hyp_pool host_s2_pool;
/*
* Copies of the host's CPU features registers holding sanitized values.
@ -36,7 +35,7 @@ static const u8 pkvm_hyp_id = 1;
static void *host_s2_zalloc_pages_exact(size_t size)
{
return hyp_alloc_pages(&host_s2_mem, get_order(size));
return hyp_alloc_pages(&host_s2_pool, get_order(size));
}
static void *host_s2_zalloc_page(void *pool)
@ -44,20 +43,24 @@ static void *host_s2_zalloc_page(void *pool)
return hyp_alloc_pages(pool, 0);
}
static int prepare_s2_pools(void *mem_pgt_pool, void *dev_pgt_pool)
static void host_s2_get_page(void *addr)
{
hyp_get_page(&host_s2_pool, addr);
}
static void host_s2_put_page(void *addr)
{
hyp_put_page(&host_s2_pool, addr);
}
static int prepare_s2_pool(void *pgt_pool_base)
{
unsigned long nr_pages, pfn;
int ret;
pfn = hyp_virt_to_pfn(mem_pgt_pool);
nr_pages = host_s2_mem_pgtable_pages();
ret = hyp_pool_init(&host_s2_mem, pfn, nr_pages, 0);
if (ret)
return ret;
pfn = hyp_virt_to_pfn(dev_pgt_pool);
nr_pages = host_s2_dev_pgtable_pages();
ret = hyp_pool_init(&host_s2_dev, pfn, nr_pages, 0);
pfn = hyp_virt_to_pfn(pgt_pool_base);
nr_pages = host_s2_pgtable_pages();
ret = hyp_pool_init(&host_s2_pool, pfn, nr_pages, 0);
if (ret)
return ret;
@ -67,8 +70,8 @@ static int prepare_s2_pools(void *mem_pgt_pool, void *dev_pgt_pool)
.phys_to_virt = hyp_phys_to_virt,
.virt_to_phys = hyp_virt_to_phys,
.page_count = hyp_page_count,
.get_page = hyp_get_page,
.put_page = hyp_put_page,
.get_page = host_s2_get_page,
.put_page = host_s2_put_page,
};
return 0;
@ -86,7 +89,7 @@ static void prepare_host_vtcr(void)
id_aa64mmfr1_el1_sys_val, phys_shift);
}
int kvm_host_prepare_stage2(void *mem_pgt_pool, void *dev_pgt_pool)
int kvm_host_prepare_stage2(void *pgt_pool_base)
{
struct kvm_s2_mmu *mmu = &host_kvm.arch.mmu;
int ret;
@ -94,7 +97,7 @@ int kvm_host_prepare_stage2(void *mem_pgt_pool, void *dev_pgt_pool)
prepare_host_vtcr();
hyp_spin_lock_init(&host_kvm.lock);
ret = prepare_s2_pools(mem_pgt_pool, dev_pgt_pool);
ret = prepare_s2_pool(pgt_pool_base);
if (ret)
return ret;
@ -199,11 +202,10 @@ static bool range_is_memory(u64 start, u64 end)
}
static inline int __host_stage2_idmap(u64 start, u64 end,
enum kvm_pgtable_prot prot,
struct hyp_pool *pool)
enum kvm_pgtable_prot prot)
{
return kvm_pgtable_stage2_map(&host_kvm.pgt, start, end - start, start,
prot, pool);
prot, &host_s2_pool);
}
static int host_stage2_idmap(u64 addr)
@ -211,7 +213,6 @@ static int host_stage2_idmap(u64 addr)
enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_W;
struct kvm_mem_range range;
bool is_memory = find_mem_range(addr, &range);
struct hyp_pool *pool = is_memory ? &host_s2_mem : &host_s2_dev;
int ret;
if (is_memory)
@ -222,22 +223,21 @@ static int host_stage2_idmap(u64 addr)
if (ret)
goto unlock;
ret = __host_stage2_idmap(range.start, range.end, prot, pool);
if (is_memory || ret != -ENOMEM)
ret = __host_stage2_idmap(range.start, range.end, prot);
if (ret != -ENOMEM)
goto unlock;
/*
* host_s2_mem has been provided with enough pages to cover all of
* memory with page granularity, so we should never hit the ENOMEM case.
* However, it is difficult to know how much of the MMIO range we will
* need to cover upfront, so we may need to 'recycle' the pages if we
* run out.
* The pool has been provided with enough pages to cover all of memory
* with page granularity, but it is difficult to know how much of the
* MMIO range we will need to cover upfront, so we may need to 'recycle'
* the pages if we run out.
*/
ret = host_stage2_unmap_dev_all();
if (ret)
goto unlock;
ret = __host_stage2_idmap(range.start, range.end, prot, pool);
ret = __host_stage2_idmap(range.start, range.end, prot);
unlock:
hyp_spin_unlock(&host_kvm.lock);
@ -258,7 +258,7 @@ int __pkvm_mark_hyp(phys_addr_t start, phys_addr_t end)
hyp_spin_lock(&host_kvm.lock);
ret = kvm_pgtable_stage2_set_owner(&host_kvm.pgt, start, end - start,
&host_s2_mem, pkvm_hyp_id);
&host_s2_pool, pkvm_hyp_id);
hyp_spin_unlock(&host_kvm.lock);
return ret != -EAGAIN ? ret : 0;

View File

@ -32,7 +32,7 @@ u64 __hyp_vmemmap;
*/
static struct hyp_page *__find_buddy_nocheck(struct hyp_pool *pool,
struct hyp_page *p,
unsigned int order)
unsigned short order)
{
phys_addr_t addr = hyp_page_to_phys(p);
@ -51,21 +51,49 @@ static struct hyp_page *__find_buddy_nocheck(struct hyp_pool *pool,
/* Find a buddy page currently available for allocation */
static struct hyp_page *__find_buddy_avail(struct hyp_pool *pool,
struct hyp_page *p,
unsigned int order)
unsigned short order)
{
struct hyp_page *buddy = __find_buddy_nocheck(pool, p, order);
if (!buddy || buddy->order != order || list_empty(&buddy->node))
if (!buddy || buddy->order != order || buddy->refcount)
return NULL;
return buddy;
}
/*
* Pages that are available for allocation are tracked in free-lists, so we use
* the pages themselves to store the list nodes to avoid wasting space. As the
* allocator always returns zeroed pages (which are zeroed on the hyp_put_page()
* path to optimize allocation speed), we also need to clean-up the list node in
* each page when we take it out of the list.
*/
static inline void page_remove_from_list(struct hyp_page *p)
{
struct list_head *node = hyp_page_to_virt(p);
__list_del_entry(node);
memset(node, 0, sizeof(*node));
}
static inline void page_add_to_list(struct hyp_page *p, struct list_head *head)
{
struct list_head *node = hyp_page_to_virt(p);
INIT_LIST_HEAD(node);
list_add_tail(node, head);
}
static inline struct hyp_page *node_to_page(struct list_head *node)
{
return hyp_virt_to_page(node);
}
static void __hyp_attach_page(struct hyp_pool *pool,
struct hyp_page *p)
{
unsigned int order = p->order;
unsigned short order = p->order;
struct hyp_page *buddy;
memset(hyp_page_to_virt(p), 0, PAGE_SIZE << p->order);
@ -83,32 +111,23 @@ static void __hyp_attach_page(struct hyp_pool *pool,
break;
/* Take the buddy out of its list, and coallesce with @p */
list_del_init(&buddy->node);
page_remove_from_list(buddy);
buddy->order = HYP_NO_ORDER;
p = min(p, buddy);
}
/* Mark the new head, and insert it */
p->order = order;
list_add_tail(&p->node, &pool->free_area[order]);
}
static void hyp_attach_page(struct hyp_page *p)
{
struct hyp_pool *pool = hyp_page_to_pool(p);
hyp_spin_lock(&pool->lock);
__hyp_attach_page(pool, p);
hyp_spin_unlock(&pool->lock);
page_add_to_list(p, &pool->free_area[order]);
}
static struct hyp_page *__hyp_extract_page(struct hyp_pool *pool,
struct hyp_page *p,
unsigned int order)
unsigned short order)
{
struct hyp_page *buddy;
list_del_init(&p->node);
page_remove_from_list(p);
while (p->order > order) {
/*
* The buddy of order n - 1 currently has HYP_NO_ORDER as it
@ -119,30 +138,64 @@ static struct hyp_page *__hyp_extract_page(struct hyp_pool *pool,
p->order--;
buddy = __find_buddy_nocheck(pool, p, p->order);
buddy->order = p->order;
list_add_tail(&buddy->node, &pool->free_area[buddy->order]);
page_add_to_list(buddy, &pool->free_area[buddy->order]);
}
return p;
}
void hyp_put_page(void *addr)
static inline void hyp_page_ref_inc(struct hyp_page *p)
{
struct hyp_page *p = hyp_virt_to_page(addr);
BUG_ON(p->refcount == USHRT_MAX);
p->refcount++;
}
static inline int hyp_page_ref_dec_and_test(struct hyp_page *p)
{
p->refcount--;
return (p->refcount == 0);
}
static inline void hyp_set_page_refcounted(struct hyp_page *p)
{
BUG_ON(p->refcount);
p->refcount = 1;
}
static void __hyp_put_page(struct hyp_pool *pool, struct hyp_page *p)
{
if (hyp_page_ref_dec_and_test(p))
hyp_attach_page(p);
__hyp_attach_page(pool, p);
}
void hyp_get_page(void *addr)
/*
* Changes to the buddy tree and page refcounts must be done with the hyp_pool
* lock held. If a refcount change requires an update to the buddy tree (e.g.
* hyp_put_page()), both operations must be done within the same critical
* section to guarantee transient states (e.g. a page with null refcount but
* not yet attached to a free list) can't be observed by well-behaved readers.
*/
void hyp_put_page(struct hyp_pool *pool, void *addr)
{
struct hyp_page *p = hyp_virt_to_page(addr);
hyp_page_ref_inc(p);
hyp_spin_lock(&pool->lock);
__hyp_put_page(pool, p);
hyp_spin_unlock(&pool->lock);
}
void *hyp_alloc_pages(struct hyp_pool *pool, unsigned int order)
void hyp_get_page(struct hyp_pool *pool, void *addr)
{
unsigned int i = order;
struct hyp_page *p = hyp_virt_to_page(addr);
hyp_spin_lock(&pool->lock);
hyp_page_ref_inc(p);
hyp_spin_unlock(&pool->lock);
}
void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order)
{
unsigned short i = order;
struct hyp_page *p;
hyp_spin_lock(&pool->lock);
@ -156,11 +209,11 @@ void *hyp_alloc_pages(struct hyp_pool *pool, unsigned int order)
}
/* Extract it from the tree at the right order */
p = list_first_entry(&pool->free_area[i], struct hyp_page, node);
p = node_to_page(pool->free_area[i].next);
p = __hyp_extract_page(pool, p, order);
hyp_spin_unlock(&pool->lock);
hyp_set_page_refcounted(p);
hyp_spin_unlock(&pool->lock);
return hyp_page_to_virt(p);
}
@ -181,15 +234,14 @@ int hyp_pool_init(struct hyp_pool *pool, u64 pfn, unsigned int nr_pages,
/* Init the vmemmap portion */
p = hyp_phys_to_page(phys);
memset(p, 0, sizeof(*p) * nr_pages);
for (i = 0; i < nr_pages; i++) {
p[i].pool = pool;
INIT_LIST_HEAD(&p[i].node);
p[i].order = 0;
hyp_set_page_refcounted(&p[i]);
}
/* Attach the unused pages to the buddy tree */
for (i = reserved_pages; i < nr_pages; i++)
__hyp_attach_page(pool, &p[i]);
__hyp_put_page(pool, &p[i]);
return 0;
}

View File

@ -24,8 +24,7 @@ unsigned long hyp_nr_cpus;
static void *vmemmap_base;
static void *hyp_pgt_base;
static void *host_s2_mem_pgt_base;
static void *host_s2_dev_pgt_base;
static void *host_s2_pgt_base;
static struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops;
static int divide_memory_pool(void *virt, unsigned long size)
@ -45,14 +44,9 @@ static int divide_memory_pool(void *virt, unsigned long size)
if (!hyp_pgt_base)
return -ENOMEM;
nr_pages = host_s2_mem_pgtable_pages();
host_s2_mem_pgt_base = hyp_early_alloc_contig(nr_pages);
if (!host_s2_mem_pgt_base)
return -ENOMEM;
nr_pages = host_s2_dev_pgtable_pages();
host_s2_dev_pgt_base = hyp_early_alloc_contig(nr_pages);
if (!host_s2_dev_pgt_base)
nr_pages = host_s2_pgtable_pages();
host_s2_pgt_base = hyp_early_alloc_contig(nr_pages);
if (!host_s2_pgt_base)
return -ENOMEM;
return 0;
@ -134,7 +128,8 @@ static void update_nvhe_init_params(void)
for (i = 0; i < hyp_nr_cpus; i++) {
params = per_cpu_ptr(&kvm_init_params, i);
params->pgd_pa = __hyp_pa(pkvm_pgtable.pgd);
__flush_dcache_area(params, sizeof(*params));
dcache_clean_inval_poc((unsigned long)params,
(unsigned long)params + sizeof(*params));
}
}
@ -143,6 +138,16 @@ static void *hyp_zalloc_hyp_page(void *arg)
return hyp_alloc_pages(&hpool, 0);
}
static void hpool_get_page(void *addr)
{
hyp_get_page(&hpool, addr);
}
static void hpool_put_page(void *addr)
{
hyp_put_page(&hpool, addr);
}
void __noreturn __pkvm_init_finalise(void)
{
struct kvm_host_data *host_data = this_cpu_ptr(&kvm_host_data);
@ -158,7 +163,7 @@ void __noreturn __pkvm_init_finalise(void)
if (ret)
goto out;
ret = kvm_host_prepare_stage2(host_s2_mem_pgt_base, host_s2_dev_pgt_base);
ret = kvm_host_prepare_stage2(host_s2_pgt_base);
if (ret)
goto out;
@ -166,8 +171,8 @@ void __noreturn __pkvm_init_finalise(void)
.zalloc_page = hyp_zalloc_hyp_page,
.phys_to_virt = hyp_phys_to_virt,
.virt_to_phys = hyp_virt_to_phys,
.get_page = hyp_get_page,
.put_page = hyp_put_page,
.get_page = hpool_get_page,
.put_page = hpool_put_page,
};
pkvm_pgtable.mm_ops = &pkvm_pgtable_mm_ops;

View File

@ -104,7 +104,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
* you should be running with VHE enabled.
*/
if (icache_is_vpipt())
__flush_icache_all();
icache_inval_all_pou();
__tlb_switch_to_host(&cxt);
}

View File

@ -577,12 +577,24 @@ static void stage2_put_pte(kvm_pte_t *ptep, struct kvm_s2_mmu *mmu, u64 addr,
mm_ops->put_page(ptep);
}
static bool stage2_pte_cacheable(struct kvm_pgtable *pgt, kvm_pte_t pte)
{
u64 memattr = pte & KVM_PTE_LEAF_ATTR_LO_S2_MEMATTR;
return memattr == KVM_S2_MEMATTR(pgt, NORMAL);
}
static bool stage2_pte_executable(kvm_pte_t pte)
{
return !(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN);
}
static int stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level,
kvm_pte_t *ptep,
struct stage2_map_data *data)
{
kvm_pte_t new, old = *ptep;
u64 granule = kvm_granule_size(level), phys = data->phys;
struct kvm_pgtable *pgt = data->mmu->pgt;
struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops;
if (!kvm_block_mapping_supported(addr, end, phys, level))
@ -606,6 +618,14 @@ static int stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level,
stage2_put_pte(ptep, data->mmu, addr, level, mm_ops);
}
/* Perform CMOs before installation of the guest stage-2 PTE */
if (mm_ops->dcache_clean_inval_poc && stage2_pte_cacheable(pgt, new))
mm_ops->dcache_clean_inval_poc(kvm_pte_follow(new, mm_ops),
granule);
if (mm_ops->icache_inval_pou && stage2_pte_executable(new))
mm_ops->icache_inval_pou(kvm_pte_follow(new, mm_ops), granule);
smp_store_release(ptep, new);
if (stage2_pte_is_counted(new))
mm_ops->get_page(ptep);
@ -798,12 +818,6 @@ int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size,
return ret;
}
static bool stage2_pte_cacheable(struct kvm_pgtable *pgt, kvm_pte_t pte)
{
u64 memattr = pte & KVM_PTE_LEAF_ATTR_LO_S2_MEMATTR;
return memattr == KVM_S2_MEMATTR(pgt, NORMAL);
}
static int stage2_unmap_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
enum kvm_pgtable_walk_flags flag,
void * const arg)
@ -839,8 +853,11 @@ static int stage2_unmap_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
stage2_put_pte(ptep, mmu, addr, level, mm_ops);
if (need_flush) {
__flush_dcache_area(kvm_pte_follow(pte, mm_ops),
kvm_granule_size(level));
kvm_pte_t *pte_follow = kvm_pte_follow(pte, mm_ops);
dcache_clean_inval_poc((unsigned long)pte_follow,
(unsigned long)pte_follow +
kvm_granule_size(level));
}
if (childp)
@ -861,10 +878,11 @@ int kvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size)
}
struct stage2_attr_data {
kvm_pte_t attr_set;
kvm_pte_t attr_clr;
kvm_pte_t pte;
u32 level;
kvm_pte_t attr_set;
kvm_pte_t attr_clr;
kvm_pte_t pte;
u32 level;
struct kvm_pgtable_mm_ops *mm_ops;
};
static int stage2_attr_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
@ -873,6 +891,7 @@ static int stage2_attr_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
{
kvm_pte_t pte = *ptep;
struct stage2_attr_data *data = arg;
struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops;
if (!kvm_pte_valid(pte))
return 0;
@ -887,8 +906,17 @@ static int stage2_attr_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
* but worst-case the access flag update gets lost and will be
* set on the next access instead.
*/
if (data->pte != pte)
if (data->pte != pte) {
/*
* Invalidate instruction cache before updating the guest
* stage-2 PTE if we are going to add executable permission.
*/
if (mm_ops->icache_inval_pou &&
stage2_pte_executable(pte) && !stage2_pte_executable(*ptep))
mm_ops->icache_inval_pou(kvm_pte_follow(pte, mm_ops),
kvm_granule_size(level));
WRITE_ONCE(*ptep, pte);
}
return 0;
}
@ -903,6 +931,7 @@ static int stage2_update_leaf_attrs(struct kvm_pgtable *pgt, u64 addr,
struct stage2_attr_data data = {
.attr_set = attr_set & attr_mask,
.attr_clr = attr_clr & attr_mask,
.mm_ops = pgt->mm_ops,
};
struct kvm_pgtable_walker walker = {
.cb = stage2_attr_walker,
@ -988,11 +1017,15 @@ static int stage2_flush_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
struct kvm_pgtable *pgt = arg;
struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops;
kvm_pte_t pte = *ptep;
kvm_pte_t *pte_follow;
if (!kvm_pte_valid(pte) || !stage2_pte_cacheable(pgt, pte))
return 0;
__flush_dcache_area(kvm_pte_follow(pte, mm_ops), kvm_granule_size(level));
pte_follow = kvm_pte_follow(pte, mm_ops);
dcache_clean_inval_poc((unsigned long)pte_follow,
(unsigned long)pte_follow +
kvm_granule_size(level));
return 0;
}

View File

@ -71,8 +71,7 @@ void __init kvm_hyp_reserve(void)
}
hyp_mem_pages += hyp_s1_pgtable_pages();
hyp_mem_pages += host_s2_mem_pgtable_pages();
hyp_mem_pages += host_s2_dev_pgtable_pages();
hyp_mem_pages += host_s2_pgtable_pages();
/*
* The hyp_vmemmap needs to be backed by pages, but these pages

View File

@ -126,6 +126,16 @@ static void *kvm_host_va(phys_addr_t phys)
return __va(phys);
}
static void clean_dcache_guest_page(void *va, size_t size)
{
__clean_dcache_guest_page(va, size);
}
static void invalidate_icache_guest_page(void *va, size_t size)
{
__invalidate_icache_guest_page(va, size);
}
/*
* Unmapping vs dcache management:
*
@ -432,6 +442,8 @@ static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = {
.page_count = kvm_host_page_count,
.phys_to_virt = kvm_host_va,
.virt_to_phys = kvm_host_pa,
.dcache_clean_inval_poc = clean_dcache_guest_page,
.icache_inval_pou = invalidate_icache_guest_page,
};
/**
@ -693,16 +705,6 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
}
static void clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size)
{
__clean_dcache_guest_page(pfn, size);
}
static void invalidate_icache_guest_page(kvm_pfn_t pfn, unsigned long size)
{
__invalidate_icache_guest_page(pfn, size);
}
static void kvm_send_hwpoison_signal(unsigned long address, short lsb)
{
send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb, current);
@ -822,6 +824,74 @@ transparent_hugepage_adjust(struct kvm_memory_slot *memslot,
return PAGE_SIZE;
}
static int get_vma_page_shift(struct vm_area_struct *vma, unsigned long hva)
{
unsigned long pa;
if (is_vm_hugetlb_page(vma) && !(vma->vm_flags & VM_PFNMAP))
return huge_page_shift(hstate_vma(vma));
if (!(vma->vm_flags & VM_PFNMAP))
return PAGE_SHIFT;
VM_BUG_ON(is_vm_hugetlb_page(vma));
pa = (vma->vm_pgoff << PAGE_SHIFT) + (hva - vma->vm_start);
#ifndef __PAGETABLE_PMD_FOLDED
if ((hva & (PUD_SIZE - 1)) == (pa & (PUD_SIZE - 1)) &&
ALIGN_DOWN(hva, PUD_SIZE) >= vma->vm_start &&
ALIGN(hva, PUD_SIZE) <= vma->vm_end)
return PUD_SHIFT;
#endif
if ((hva & (PMD_SIZE - 1)) == (pa & (PMD_SIZE - 1)) &&
ALIGN_DOWN(hva, PMD_SIZE) >= vma->vm_start &&
ALIGN(hva, PMD_SIZE) <= vma->vm_end)
return PMD_SHIFT;
return PAGE_SHIFT;
}
/*
* The page will be mapped in stage 2 as Normal Cacheable, so the VM will be
* able to see the page's tags and therefore they must be initialised first. If
* PG_mte_tagged is set, tags have already been initialised.
*
* The race in the test/set of the PG_mte_tagged flag is handled by:
* - preventing VM_SHARED mappings in a memslot with MTE preventing two VMs
* racing to santise the same page
* - mmap_lock protects between a VM faulting a page in and the VMM performing
* an mprotect() to add VM_MTE
*/
static int sanitise_mte_tags(struct kvm *kvm, kvm_pfn_t pfn,
unsigned long size)
{
unsigned long i, nr_pages = size >> PAGE_SHIFT;
struct page *page;
if (!kvm_has_mte(kvm))
return 0;
/*
* pfn_to_online_page() is used to reject ZONE_DEVICE pages
* that may not support tags.
*/
page = pfn_to_online_page(pfn);
if (!page)
return -EFAULT;
for (i = 0; i < nr_pages; i++, page++) {
if (!test_bit(PG_mte_tagged, &page->flags)) {
mte_clear_page_tags(page_address(page));
set_bit(PG_mte_tagged, &page->flags);
}
}
return 0;
}
static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
struct kvm_memory_slot *memslot, unsigned long hva,
unsigned long fault_status)
@ -830,6 +900,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
bool write_fault, writable, force_pte = false;
bool exec_fault;
bool device = false;
bool shared;
unsigned long mmu_seq;
struct kvm *kvm = vcpu->kvm;
struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
@ -853,7 +924,10 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
return -EFAULT;
}
/* Let's check if we will get back a huge page backed by hugetlbfs */
/*
* Let's check if we will get back a huge page backed by hugetlbfs, or
* get block mapping for device MMIO region.
*/
mmap_read_lock(current->mm);
vma = find_vma_intersection(current->mm, hva, hva + 1);
if (unlikely(!vma)) {
@ -862,17 +936,19 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
return -EFAULT;
}
if (is_vm_hugetlb_page(vma))
vma_shift = huge_page_shift(hstate_vma(vma));
else
vma_shift = PAGE_SHIFT;
if (logging_active ||
(vma->vm_flags & VM_PFNMAP)) {
/*
* logging_active is guaranteed to never be true for VM_PFNMAP
* memslots.
*/
if (logging_active) {
force_pte = true;
vma_shift = PAGE_SHIFT;
} else {
vma_shift = get_vma_page_shift(vma, hva);
}
shared = (vma->vm_flags & VM_PFNMAP);
switch (vma_shift) {
#ifndef __PAGETABLE_PMD_FOLDED
case PUD_SHIFT:
@ -943,8 +1019,17 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
return -EFAULT;
if (kvm_is_device_pfn(pfn)) {
/*
* If the page was identified as device early by looking at
* the VMA flags, vma_pagesize is already representing the
* largest quantity we can map. If instead it was mapped
* via gfn_to_pfn_prot(), vma_pagesize is set to PAGE_SIZE
* and must not be upgraded.
*
* In both cases, we don't let transparent_hugepage_adjust()
* change things at the last minute.
*/
device = true;
force_pte = true;
} else if (logging_active && !write_fault) {
/*
* Only actually map the page as writable if this was a write
@ -965,19 +1050,25 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
* If we are not forced to use page mapping, check if we are
* backed by a THP and thus use block mapping if possible.
*/
if (vma_pagesize == PAGE_SIZE && !force_pte)
if (vma_pagesize == PAGE_SIZE && !(force_pte || device))
vma_pagesize = transparent_hugepage_adjust(memslot, hva,
&pfn, &fault_ipa);
if (fault_status != FSC_PERM && !device && kvm_has_mte(kvm)) {
/* Check the VMM hasn't introduced a new VM_SHARED VMA */
if (!shared)
ret = sanitise_mte_tags(kvm, pfn, vma_pagesize);
else
ret = -EFAULT;
if (ret)
goto out_unlock;
}
if (writable)
prot |= KVM_PGTABLE_PROT_W;
if (fault_status != FSC_PERM && !device)
clean_dcache_guest_page(pfn, vma_pagesize);
if (exec_fault) {
if (exec_fault)
prot |= KVM_PGTABLE_PROT_X;
invalidate_icache_guest_page(pfn, vma_pagesize);
}
if (device)
prot |= KVM_PGTABLE_PROT_DEVICE;
@ -1168,19 +1259,22 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
{
kvm_pfn_t pfn = pte_pfn(range->pte);
int ret;
if (!kvm->arch.mmu.pgt)
return false;
WARN_ON(range->end - range->start != 1);
/*
* We've moved a page around, probably through CoW, so let's treat it
* just like a translation fault and clean the cache to the PoC.
*/
clean_dcache_guest_page(pfn, PAGE_SIZE);
ret = sanitise_mte_tags(kvm, pfn, PAGE_SIZE);
if (ret)
return false;
/*
* We've moved a page around, probably through CoW, so let's treat
* it just like a translation fault and the map handler will clean
* the cache to the PoC.
*
* The MMU notifiers will have unmapped a huge PMD before calling
* ->change_pte() (which in turn calls kvm_set_spte_gfn()) and
* therefore we never need to clear out a huge PMD through this
@ -1346,7 +1440,6 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
{
hva_t hva = mem->userspace_addr;
hva_t reg_end = hva + mem->memory_size;
bool writable = !(mem->flags & KVM_MEM_READONLY);
int ret = 0;
if (change != KVM_MR_CREATE && change != KVM_MR_MOVE &&
@ -1363,8 +1456,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
mmap_read_lock(current->mm);
/*
* A memory region could potentially cover multiple VMAs, and any holes
* between them, so iterate over all of them to find out if we can map
* any of them right now.
* between them, so iterate over all of them.
*
* +--------------------------------------------+
* +---------------+----------------+ +----------------+
@ -1375,51 +1467,29 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
*/
do {
struct vm_area_struct *vma;
hva_t vm_start, vm_end;
vma = find_vma_intersection(current->mm, hva, reg_end);
if (!vma)
break;
/*
* Take the intersection of this VMA with the memory region
* VM_SHARED mappings are not allowed with MTE to avoid races
* when updating the PG_mte_tagged page flag, see
* sanitise_mte_tags for more details.
*/
vm_start = max(hva, vma->vm_start);
vm_end = min(reg_end, vma->vm_end);
if (kvm_has_mte(kvm) && vma->vm_flags & VM_SHARED)
return -EINVAL;
if (vma->vm_flags & VM_PFNMAP) {
gpa_t gpa = mem->guest_phys_addr +
(vm_start - mem->userspace_addr);
phys_addr_t pa;
pa = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT;
pa += vm_start - vma->vm_start;
/* IO region dirty page logging not allowed */
if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) {
ret = -EINVAL;
goto out;
}
ret = kvm_phys_addr_ioremap(kvm, gpa, pa,
vm_end - vm_start,
writable);
if (ret)
break;
}
}
hva = vm_end;
hva = min(reg_end, vma->vm_end);
} while (hva < reg_end);
if (change == KVM_MR_FLAGS_ONLY)
goto out;
spin_lock(&kvm->mmu_lock);
if (ret)
unmap_stage2_range(&kvm->arch.mmu, mem->guest_phys_addr, mem->memory_size);
else if (!cpus_have_final_cap(ARM64_HAS_STAGE2_FWB))
stage2_flush_memslot(kvm, memslot);
spin_unlock(&kvm->mmu_lock);
out:
mmap_read_unlock(current->mm);
return ret;
}

View File

@ -578,6 +578,7 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0);
if (val & ARMV8_PMU_PMCR_P) {
mask &= ~BIT(ARMV8_PMU_CYCLE_IDX);
for_each_set_bit(i, &mask, 32)
kvm_pmu_set_counter_value(vcpu, i, 0);
}
@ -850,6 +851,9 @@ int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
return -EINVAL;
}
/* One-off reload of the PMU on first run */
kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
return 0;
}

View File

@ -176,6 +176,10 @@ static bool vcpu_allowed_register_width(struct kvm_vcpu *vcpu)
if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1) && is32bit)
return false;
/* MTE is incompatible with AArch32 */
if (kvm_has_mte(vcpu->kvm) && is32bit)
return false;
/* Check that the vcpus are either all 32bit or all 64bit */
kvm_for_each_vcpu(i, tmp, vcpu->kvm) {
if (vcpu_has_feature(tmp, KVM_ARM_VCPU_EL1_32BIT) != is32bit)

View File

@ -1047,6 +1047,13 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu,
break;
case SYS_ID_AA64PFR1_EL1:
val &= ~FEATURE(ID_AA64PFR1_MTE);
if (kvm_has_mte(vcpu->kvm)) {
u64 pfr, mte;
pfr = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1);
mte = cpuid_feature_extract_unsigned_field(pfr, ID_AA64PFR1_MTE_SHIFT);
val |= FIELD_PREP(FEATURE(ID_AA64PFR1_MTE), mte);
}
break;
case SYS_ID_AA64ISAR1_EL1:
if (!vcpu_has_ptrauth(vcpu))
@ -1302,6 +1309,23 @@ static bool access_ccsidr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
return true;
}
static unsigned int mte_visibility(const struct kvm_vcpu *vcpu,
const struct sys_reg_desc *rd)
{
if (kvm_has_mte(vcpu->kvm))
return 0;
return REG_HIDDEN;
}
#define MTE_REG(name) { \
SYS_DESC(SYS_##name), \
.access = undef_access, \
.reset = reset_unknown, \
.reg = name, \
.visibility = mte_visibility, \
}
/* sys_reg_desc initialiser for known cpufeature ID registers */
#define ID_SANITISED(name) { \
SYS_DESC(SYS_##name), \
@ -1470,8 +1494,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
{ SYS_DESC(SYS_ACTLR_EL1), access_actlr, reset_actlr, ACTLR_EL1 },
{ SYS_DESC(SYS_CPACR_EL1), NULL, reset_val, CPACR_EL1, 0 },
{ SYS_DESC(SYS_RGSR_EL1), undef_access },
{ SYS_DESC(SYS_GCR_EL1), undef_access },
MTE_REG(RGSR_EL1),
MTE_REG(GCR_EL1),
{ SYS_DESC(SYS_ZCR_EL1), NULL, reset_val, ZCR_EL1, 0, .visibility = sve_visibility },
{ SYS_DESC(SYS_TRFCR_EL1), undef_access },
@ -1498,8 +1522,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
{ SYS_DESC(SYS_ERXMISC0_EL1), trap_raz_wi },
{ SYS_DESC(SYS_ERXMISC1_EL1), trap_raz_wi },
{ SYS_DESC(SYS_TFSR_EL1), undef_access },
{ SYS_DESC(SYS_TFSRE0_EL1), undef_access },
MTE_REG(TFSR_EL1),
MTE_REG(TFSRE0_EL1),
{ SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 },
{ SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 },

View File

@ -482,6 +482,16 @@ static irqreturn_t vgic_maintenance_handler(int irq, void *data)
return IRQ_HANDLED;
}
static struct gic_kvm_info *gic_kvm_info;
void __init vgic_set_kvm_info(const struct gic_kvm_info *info)
{
BUG_ON(gic_kvm_info != NULL);
gic_kvm_info = kmalloc(sizeof(*info), GFP_KERNEL);
if (gic_kvm_info)
*gic_kvm_info = *info;
}
/**
* kvm_vgic_init_cpu_hardware - initialize the GIC VE hardware
*
@ -509,18 +519,29 @@ void kvm_vgic_init_cpu_hardware(void)
*/
int kvm_vgic_hyp_init(void)
{
const struct gic_kvm_info *gic_kvm_info;
bool has_mask;
int ret;
gic_kvm_info = gic_get_kvm_info();
if (!gic_kvm_info)
return -ENODEV;
if (!gic_kvm_info->maint_irq) {
has_mask = !gic_kvm_info->no_maint_irq_mask;
if (has_mask && !gic_kvm_info->maint_irq) {
kvm_err("No vgic maintenance irq\n");
return -ENXIO;
}
/*
* If we get one of these oddball non-GICs, taint the kernel,
* as we have no idea of how they *really* behave.
*/
if (gic_kvm_info->no_hw_deactivation) {
kvm_info("Non-architectural vgic, tainting kernel\n");
add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
kvm_vgic_global_state.no_hw_deactivation = true;
}
switch (gic_kvm_info->type) {
case GIC_V2:
ret = vgic_v2_probe(gic_kvm_info);
@ -536,10 +557,17 @@ int kvm_vgic_hyp_init(void)
ret = -ENODEV;
}
kvm_vgic_global_state.maint_irq = gic_kvm_info->maint_irq;
kfree(gic_kvm_info);
gic_kvm_info = NULL;
if (ret)
return ret;
kvm_vgic_global_state.maint_irq = gic_kvm_info->maint_irq;
if (!has_mask)
return 0;
ret = request_percpu_irq(kvm_vgic_global_state.maint_irq,
vgic_maintenance_handler,
"vgic", kvm_get_running_vcpus());

Some files were not shown because too many files have changed in this diff Show More