mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2025-04-12 06:49:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

ASoC: tas2764: Random patches from the Asahi Linux

Browse Source 
Merge series from broonie@kernel.org:

This is a random subset of the patches for the tas2764 driver that I
found in the Asahi Linux tree which seemed to be clear fixes and
improvements which apply easily to mainline without much effort, there's
a bunch more work on the driver that should also be applicable.

I've only build tested this.
This commit is contained in:
Mark Brown 2025-02-17 13:38:46 +00:00
commit 0770b7cc09
No known key found for this signature in database
GPG Key ID: 24D68B725D5487D0
592 changed files with 6835 additions and 3964 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.mailmap
View File

@ -376,6 +376,7 @@ Juha Yrjola <juha.yrjola@solidboot.com>
Julien Thierry <julien.thierry.kdev@gmail.com> <julien.thierry@arm.com>
Iskren Chernev <me@iskren.info> <iskren.chernev@gmail.com>
Kalle Valo <kvalo@kernel.org> <kvalo@codeaurora.org>
Kalle Valo <kvalo@kernel.org> <quic_kvalo@quicinc.com>
Kalyan Thota <quic_kalyant@quicinc.com> <kalyan_t@codeaurora.org>
Karthikeyan Periyasamy <quic_periyasa@quicinc.com> <periyasa@codeaurora.org>
Kathiravan T <quic_kathirav@quicinc.com> <kathirav@codeaurora.org>

6
CREDITS
View File

@ -2515,11 +2515,9 @@ D: SLS distribution
D: Initial implementation of VC's, pty's and select()
N: Pavel Machek
E: pavel@ucw.cz
E: pavel@kernel.org
P: 4096R/92DFCE96 4FA7 9EEF FCD4 C44F C585 B8C7 C060 2241 92DF CE96
D: Softcursor for vga, hypertech cdrom support, vcsa bugfix, nbd,
D: sun4/330 port, capabilities for elf, speedup for rm on ext2, USB,
D: work on suspend-to-ram/disk, killing duplicates from ioctl32,
D: NBD, Sun4/330 port, USB, work on suspend-to-ram/disk,
D: Altera SoCFPGA and Nokia N900 support.
S: Czech Republic

2
Documentation/arch/arm64/gcs.rst
View File

@ -37,7 +37,7 @@ intended to be exhaustive.
shadow stacks rather than GCS.
* Support for GCS is reported to userspace via HWCAP_GCS in the aux vector
AT_HWCAP2 entry.
AT_HWCAP entry.
* GCS is enabled per thread. While there is support for disabling GCS
at runtime this should be done with great care.

3
Documentation/devicetree/bindings/clock/qcom,gpucc.yaml
View File

@ -8,6 +8,7 @@ title: Qualcomm Graphics Clock & Reset Controller
maintainers:
- Taniya Das <quic_tdas@quicinc.com>
- Imran Shaik <quic_imrashai@quicinc.com>
description: |
Qualcomm graphics clock control module provides the clocks, resets and power
@ -23,10 +24,12 @@ description: |
include/dt-bindings/clock/qcom,gpucc-sm8150.h
include/dt-bindings/clock/qcom,gpucc-sm8250.h
include/dt-bindings/clock/qcom,gpucc-sm8350.h
include/dt-bindings/clock/qcom,qcs8300-gpucc.h
properties:
compatible:
enum:
- qcom,qcs8300-gpucc
- qcom,sdm845-gpucc
- qcom,sa8775p-gpucc
- qcom,sc7180-gpucc

6
Documentation/devicetree/bindings/clock/qcom,sa8775p-camcc.yaml
View File

@ -8,16 +8,20 @@ title: Qualcomm Camera Clock & Reset Controller on SA8775P
maintainers:
- Taniya Das <quic_tdas@quicinc.com>
- Imran Shaik <quic_imrashai@quicinc.com>
description: |
Qualcomm camera clock control module provides the clocks, resets and power
domains on SA8775p.
See also: include/dt-bindings/clock/qcom,sa8775p-camcc.h
See also:
include/dt-bindings/clock/qcom,qcs8300-camcc.h
include/dt-bindings/clock/qcom,sa8775p-camcc.h
properties:
compatible:
enum:
- qcom,qcs8300-camcc
- qcom,sa8775p-camcc
clocks:

1
Documentation/devicetree/bindings/clock/qcom,sa8775p-videocc.yaml
View File

@ -18,6 +18,7 @@ description: |
properties:
compatible:
enum:
- qcom,qcs8300-videocc
- qcom,sa8775p-videocc
clocks:

29
Documentation/devicetree/bindings/display/panel/powertip,hx8238a.yaml Normal file
View File

@ -0,0 +1,29 @@
# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
%YAML 1.2
---
$id: http://devicetree.org/schemas/display/panel/powertip,hx8238a.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: Powertip Electronic Technology Co. 320 x 240 LCD panel
maintainers:
- Lukasz Majewski <lukma@denx.de>
allOf:
- $ref: panel-dpi.yaml#
properties:
compatible:
items:
- const: powertip,hx8238a
- {} # panel-dpi, but not listed here to avoid false select
height-mm: true
panel-timing: true
port: true
power-supply: true
width-mm: true
additionalProperties: false
...

29
Documentation/devicetree/bindings/display/panel/powertip,st7272.yaml Normal file
View File

@ -0,0 +1,29 @@
# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
%YAML 1.2
---
$id: http://devicetree.org/schemas/display/panel/powertip,st7272.yaml#
$schema: http://devicetree.org/meta-schemas/core.yaml#
title: Powertip Electronic Technology Co. 320 x 240 LCD panel
maintainers:
- Lukasz Majewski <lukma@denx.de>
allOf:
- $ref: panel-dpi.yaml#
properties:
compatible:
items:
- const: powertip,st7272
- {} # panel-dpi, but not listed here to avoid false select
height-mm: true
panel-timing: true
port: true
power-supply: true
width-mm: true
additionalProperties: false
...

2
Documentation/devicetree/bindings/display/ti/ti,am65x-dss.yaml
View File

@ -23,7 +23,7 @@ properties:
compatible:
enum:
- ti,am625-dss
- ti,am62a7,dss
- ti,am62a7-dss
- ti,am65x-dss
reg:

5
Documentation/devicetree/bindings/interrupt-controller/microchip,lan966x-oic.yaml
View File

@ -14,9 +14,8 @@ allOf:
description: |
The Microchip LAN966x outband interrupt controller (OIC) maps the internal
interrupt sources of the LAN966x device to an external interrupt.
When the LAN966x device is used as a PCI device, the external interrupt is
routed to the PCI interrupt.
interrupt sources of the LAN966x device to a PCI interrupt when the LAN966x
device is used as a PCI device.
properties:
compatible:

1
Documentation/devicetree/bindings/net/wireless/qcom,ath10k.yaml
View File

@ -7,7 +7,6 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
title: Qualcomm Technologies ath10k wireless devices
maintainers:
- Kalle Valo <kvalo@kernel.org>
- Jeff Johnson <jjohnson@kernel.org>
description:

1
Documentation/devicetree/bindings/net/wireless/qcom,ath11k-pci.yaml
View File

@ -8,7 +8,6 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
title: Qualcomm Technologies ath11k wireless devices (PCIe)
maintainers:
- Kalle Valo <kvalo@kernel.org>
- Jeff Johnson <jjohnson@kernel.org>
description: |

1
Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml
View File

@ -8,7 +8,6 @@ $schema: http://devicetree.org/meta-schemas/core.yaml#
title: Qualcomm Technologies ath11k wireless devices
maintainers:
- Kalle Valo <kvalo@kernel.org>
- Jeff Johnson <jjohnson@kernel.org>
description: |

1
Documentation/devicetree/bindings/net/wireless/qcom,ath12k-wsi.yaml
View File

@ -9,7 +9,6 @@ title: Qualcomm Technologies ath12k wireless devices (PCIe) with WSI interface
maintainers:
- Jeff Johnson <jjohnson@kernel.org>
- Kalle Valo <kvalo@kernel.org>
description: |
Qualcomm Technologies IEEE 802.11be PCIe devices with WSI interface.

1
Documentation/devicetree/bindings/net/wireless/qcom,ath12k.yaml
View File

@ -9,7 +9,6 @@ title: Qualcomm Technologies ath12k wireless devices (PCIe)
maintainers:
- Jeff Johnson <quic_jjohnson@quicinc.com>
- Kalle Valo <kvalo@kernel.org>
description:
Qualcomm Technologies IEEE 802.11be PCIe devices.

1
Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml
View File

@ -36,6 +36,7 @@ properties:
- qcom,qcs404-qfprom
- qcom,qcs615-qfprom
- qcom,qcs8300-qfprom
- qcom,sar2130p-qfprom
- qcom,sc7180-qfprom
- qcom,sc7280-qfprom
- qcom,sc8280xp-qfprom

2
Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.yaml
View File

@ -22,7 +22,7 @@ description:
Each sub-node is identified using the node's name, with valid values listed
for each of the pmics below.
For mp5496, s1, s2
For mp5496, s1, s2, l2, l5
For pm2250, s1, s2, s3, s4, l1, l2, l3, l4, l5, l6, l7, l8, l9, l10, l11,
l12, l13, l14, l15, l16, l17, l18, l19, l20, l21, l22

6
Documentation/driver-api/infrastructure.rst
View File

@ -41,6 +41,12 @@ Device Drivers Base
.. kernel-doc:: drivers/base/class.c
:export:
.. kernel-doc:: include/linux/device/faux.h
:internal:
.. kernel-doc:: drivers/base/faux.c
:export:
.. kernel-doc:: drivers/base/node.c
:internal:

98
Documentation/filesystems/bcachefs/SubmittingPatches.rst Normal file
View File

@ -0,0 +1,98 @@
Submitting patches to bcachefs:
===============================
Patches must be tested before being submitted, either with the xfstests suite
[0], or the full bcachefs test suite in ktest [1], depending on what's being
touched. Note that ktest wraps xfstests and will be an easier method to running
it for most users; it includes single-command wrappers for all the mainstream
in-kernel local filesystems.
Patches will undergo more testing after being merged (including
lockdep/kasan/preempt/etc. variants), these are not generally required to be
run by the submitter - but do put some thought into what you're changing and
which tests might be relevant, e.g. are you dealing with tricky memory layout
work? kasan, are you doing locking work? then lockdep; and ktest includes
single-command variants for the debug build types you'll most likely need.
The exception to this rule is incomplete WIP/RFC patches: if you're working on
something nontrivial, it's encouraged to send out a WIP patch to let people
know what you're doing and make sure you're on the right track. Just make sure
it includes a brief note as to what's done and what's incomplete, to avoid
confusion.
Rigorous checkpatch.pl adherence is not required (many of its warnings are
considered out of date), but try not to deviate too much without reason.
Focus on writing code that reads well and is organized well; code should be
aesthetically pleasing.
CI:
===
Instead of running your tests locally, when running the full test suite it's
prefereable to let a server farm do it in parallel, and then have the results
in a nice test dashboard (which can tell you which failures are new, and
presents results in a git log view, avoiding the need for most bisecting).
That exists [2], and community members may request an account. If you work for
a big tech company, you'll need to help out with server costs to get access -
but the CI is not restricted to running bcachefs tests: it runs any ktest test
(which generally makes it easy to wrap other tests that can run in qemu).
Other things to think about:
============================
- How will we debug this code? Is there sufficient introspection to diagnose
when something starts acting wonky on a user machine?
We don't necessarily need every single field of every data structure visible
with introspection, but having the important fields of all the core data
types wired up makes debugging drastically easier - a bit of thoughtful
foresight greatly reduces the need to have people build custom kernels with
debug patches.
More broadly, think about all the debug tooling that might be needed.
- Does it make the codebase more or less of a mess? Can we also try to do some
organizing, too?
- Do new tests need to be written? New assertions? How do we know and verify
that the code is correct, and what happens if something goes wrong?
We don't yet have automated code coverage analysis or easy fault injection -
but for now, pretend we did and ask what they might tell us.
Assertions are hugely important, given that we don't yet have a systems
language that can do ergonomic embedded correctness proofs. Hitting an assert
in testing is much better than wandering off into undefined behaviour la-la
land - use them. Use them judiciously, and not as a replacement for proper
error handling, but use them.
- Does it need to be performance tested? Should we add new peformance counters?
bcachefs has a set of persistent runtime counters which can be viewed with
the 'bcachefs fs top' command; this should give users a basic idea of what
their filesystem is currently doing. If you're doing a new feature or looking
at old code, think if anything should be added.
- If it's a new on disk format feature - have upgrades and downgrades been
tested? (Automated tests exists but aren't in the CI, due to the hassle of
disk image management; coordinate to have them run.)
Mailing list, IRC:
==================
Patches should hit the list [3], but much discussion and code review happens on
IRC as well [4]; many people appreciate the more conversational approach and
quicker feedback.
Additionally, we have a lively user community doing excellent QA work, which
exists primarily on IRC. Please make use of that resource; user feedback is
important for any nontrivial feature, and documenting it in commit messages
would be a good idea.
[0]: git://git.kernel.org/pub/scm/fs/xfs/xfstests-dev.git
[1]: https://evilpiepirate.org/git/ktest.git/
[2]: https://evilpiepirate.org/~testdashboard/ci/
[3]: linux-bcachefs@vger.kernel.org
[4]: irc.oftc.net#bcache, #bcachefs-dev

1
Documentation/filesystems/bcachefs/index.rst
View File

@ -9,4 +9,5 @@ bcachefs Documentation
:numbered:
CodingStyle
SubmittingPatches
errorcodes

3
Documentation/netlink/specs/ethtool.yaml
View File

@ -1524,7 +1524,8 @@ attribute-sets:
nested-attributes: bitset
-
name: hwtstamp-flags
type: u32
type: nest
nested-attributes: bitset
operations:
enum-model: directional

4
Documentation/networking/iso15765-2.rst
View File

@ -369,8 +369,8 @@ to their default.
addr.can_family = AF_CAN;
addr.can_ifindex = if_nametoindex("can0");
addr.tp.tx_id = 0x18DA42F1 | CAN_EFF_FLAG;
addr.tp.rx_id = 0x18DAF142 | CAN_EFF_FLAG;
addr.can_addr.tp.tx_id = 0x18DA42F1 | CAN_EFF_FLAG;
addr.can_addr.tp.rx_id = 0x18DAF142 | CAN_EFF_FLAG;
ret = bind(s, (struct sockaddr *)&addr, sizeof(addr));
if (ret < 0)

2
Documentation/virt/kvm/api.rst
View File

@ -1419,7 +1419,7 @@ fetch) is injected in the guest.
S390:
^^^^^
Returns -EINVAL if the VM has the KVM_VM_S390_UCONTROL flag set.
Returns -EINVAL or -EEXIST if the VM has the KVM_VM_S390_UCONTROL flag set.
Returns -EINVAL if called on a protected VM.
4.36 KVM_SET_TSS_ADDR

85
MAINTAINERS
View File

@ -2209,7 +2209,6 @@ F: sound/soc/codecs/cs42l84.*
F: sound/soc/codecs/ssm3515.c
ARM/APPLE MACHINE SUPPORT
M: Hector Martin <marcan@marcan.st>
M: Sven Peter <sven@svenpeter.dev>
R: Alyssa Rosenzweig <alyssa@rosenzweig.io>
L: asahi@lists.linux.dev
@ -3655,7 +3654,6 @@ F: Documentation/devicetree/bindings/phy/phy-ath79-usb.txt
F: drivers/phy/qualcomm/phy-ath79-usb.c
ATHEROS ATH GENERIC UTILITIES
M: Kalle Valo <kvalo@kernel.org>
M: Jeff Johnson <jjohnson@kernel.org>
L: linux-wireless@vger.kernel.org
S: Supported
@ -3860,13 +3858,6 @@ W: https://ez.analog.com/linux-software-drivers
F: Documentation/devicetree/bindings/pwm/adi,axi-pwmgen.yaml
F: drivers/pwm/pwm-axi-pwmgen.c
AXXIA I2C CONTROLLER
M: Krzysztof Adamski <krzysztof.adamski@nokia.com>
L: linux-i2c@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/i2c/i2c-axxia.txt
F: drivers/i2c/busses/i2c-axxia.c
AZ6007 DVB DRIVER
M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-media@vger.kernel.org
@ -3955,6 +3946,7 @@ M: Kent Overstreet <kent.overstreet@linux.dev>
L: linux-bcachefs@vger.kernel.org
S: Supported
C: irc://irc.oftc.net/bcache
P: Documentation/filesystems/bcachefs/SubmittingPatches.rst
T: git https://evilpiepirate.org/git/bcachefs.git
F: fs/bcachefs/
F: Documentation/filesystems/bcachefs/
@ -7116,8 +7108,10 @@ F: rust/kernel/device.rs
F: rust/kernel/device_id.rs
F: rust/kernel/devres.rs
F: rust/kernel/driver.rs
F: rust/kernel/faux.rs
F: rust/kernel/platform.rs
F: samples/rust/rust_driver_platform.rs
F: samples/rust/rust_driver_faux.rs
DRIVERS FOR OMAP ADAPTIVE VOLTAGE SCALING (AVS)
M: Nishanth Menon <nm@ti.com>
@ -9418,7 +9412,7 @@ F: fs/freevxfs/
FREEZER
M: "Rafael J. Wysocki" <rafael@kernel.org>
M: Pavel Machek <pavel@ucw.cz>
M: Pavel Machek <pavel@kernel.org>
L: linux-pm@vger.kernel.org
S: Supported
F: Documentation/power/freezing-of-tasks.rst
@ -9878,7 +9872,7 @@ S: Maintained
F: drivers/staging/gpib/
GPIO ACPI SUPPORT
M: Mika Westerberg <mika.westerberg@linux.intel.com>
M: Mika Westerberg <westeri@kernel.org>
M: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
L: linux-gpio@vger.kernel.org
L: linux-acpi@vger.kernel.org
@ -10253,7 +10247,7 @@ F: drivers/video/fbdev/hgafb.c
HIBERNATION (aka Software Suspend, aka swsusp)
M: "Rafael J. Wysocki" <rafael@kernel.org>
M: Pavel Machek <pavel@ucw.cz>
M: Pavel Machek <pavel@kernel.org>
L: linux-pm@vger.kernel.org
S: Supported
B: https://bugzilla.kernel.org
@ -10822,7 +10816,7 @@ S: Odd Fixes
F: drivers/tty/hvc/
I2C ACPI SUPPORT
M: Mika Westerberg <mika.westerberg@linux.intel.com>
M: Mika Westerberg <westeri@kernel.org>
L: linux-i2c@vger.kernel.org
L: linux-acpi@vger.kernel.org
S: Maintained
@ -13124,8 +13118,8 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/har
F: scripts/leaking_addresses.pl
LED SUBSYSTEM
M: Pavel Machek <pavel@ucw.cz>
M: Lee Jones <lee@kernel.org>
M: Pavel Machek <pavel@kernel.org>
L: linux-leds@vger.kernel.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/lee/leds.git
@ -16438,7 +16432,7 @@ X: drivers/net/can/
X: drivers/net/wireless/
NETWORKING DRIVERS (WIRELESS)
M: Kalle Valo <kvalo@kernel.org>
M: Johannes Berg <johannes@sipsolutions.net>
L: linux-wireless@vger.kernel.org
S: Maintained
W: https://wireless.wiki.kernel.org/
@ -16462,6 +16456,22 @@ F: include/net/dsa.h
F: net/dsa/
F: tools/testing/selftests/drivers/net/dsa/
NETWORKING [ETHTOOL]
M: Andrew Lunn <andrew@lunn.ch>
M: Jakub Kicinski <kuba@kernel.org>
F: Documentation/netlink/specs/ethtool.yaml
F: Documentation/networking/ethtool-netlink.rst
F: include/linux/ethtool*
F: include/uapi/linux/ethtool*
F: net/ethtool/
F: tools/testing/selftests/drivers/net/*/ethtool*
NETWORKING [ETHTOOL CABLE TEST]
M: Andrew Lunn <andrew@lunn.ch>
F: net/ethtool/cabletest.c
F: tools/testing/selftests/drivers/net/*/ethtool*
K: cable_test
NETWORKING [GENERAL]
M: "David S. Miller" <davem@davemloft.net>
M: Eric Dumazet <edumazet@google.com>
@ -16493,6 +16503,7 @@ F: include/linux/netdev*
F: include/linux/netlink.h
F: include/linux/netpoll.h
F: include/linux/rtnetlink.h
F: include/linux/sctp.h
F: include/linux/seq_file_net.h
F: include/linux/skbuff*
F: include/net/
@ -16509,6 +16520,7 @@ F: include/uapi/linux/netdev*
F: include/uapi/linux/netlink.h
F: include/uapi/linux/netlink_diag.h
F: include/uapi/linux/rtnetlink.h
F: include/uapi/linux/sctp.h
F: lib/net_utils.c
F: lib/random32.c
F: net/
@ -16621,6 +16633,7 @@ F: tools/testing/selftests/net/mptcp/
NETWORKING [TCP]
M: Eric Dumazet <edumazet@google.com>
M: Neal Cardwell <ncardwell@google.com>
R: Kuniyuki Iwashima <kuniyu@amazon.com>
L: netdev@vger.kernel.org
S: Maintained
F: Documentation/networking/net_cachelines/tcp_sock.rst
@ -16648,6 +16661,31 @@ F: include/net/tls.h
F: include/uapi/linux/tls.h
F: net/tls/*
NETWORKING [SOCKETS]
M: Eric Dumazet <edumazet@google.com>
M: Kuniyuki Iwashima <kuniyu@amazon.com>
M: Paolo Abeni <pabeni@redhat.com>
M: Willem de Bruijn <willemb@google.com>
S: Maintained
F: include/linux/sock_diag.h
F: include/linux/socket.h
F: include/linux/sockptr.h
F: include/net/sock.h
F: include/net/sock_reuseport.h
F: include/uapi/linux/socket.h
F: net/core/*sock*
F: net/core/scm.c
F: net/socket.c
NETWORKING [UNIX SOCKETS]
M: Kuniyuki Iwashima <kuniyu@amazon.com>
S: Maintained
F: include/net/af_unix.h
F: include/net/netns/unix.h
F: include/uapi/linux/unix_diag.h
F: net/unix/
F: tools/testing/selftests/net/af_unix/
NETXEN (1/10) GbE SUPPORT
M: Manish Chopra <manishc@marvell.com>
M: Rahul Verma <rahulv@marvell.com>
@ -16781,7 +16819,7 @@ F: include/linux/tick.h
F: kernel/time/tick*.*
NOKIA N900 CAMERA SUPPORT (ET8EK8 SENSOR, AD5820 FOCUS)
M: Pavel Machek <pavel@ucw.cz>
M: Pavel Machek <pavel@kernel.org>
M: Sakari Ailus <sakari.ailus@iki.fi>
L: linux-media@vger.kernel.org
S: Maintained
@ -17713,6 +17751,7 @@ L: netdev@vger.kernel.org
L: dev@openvswitch.org
S: Maintained
W: http://openvswitch.org
F: Documentation/networking/openvswitch.rst
F: include/uapi/linux/openvswitch.h
F: net/openvswitch/
F: tools/testing/selftests/net/openvswitch/
@ -19313,7 +19352,6 @@ Q: http://patchwork.linuxtv.org/project/linux-media/list/
F: drivers/media/tuners/qt1010*
QUALCOMM ATH12K WIRELESS DRIVER
M: Kalle Valo <kvalo@kernel.org>
M: Jeff Johnson <jjohnson@kernel.org>
L: ath12k@lists.infradead.org
S: Supported
@ -19323,7 +19361,6 @@ F: drivers/net/wireless/ath/ath12k/
N: ath12k
QUALCOMM ATHEROS ATH10K WIRELESS DRIVER
M: Kalle Valo <kvalo@kernel.org>
M: Jeff Johnson <jjohnson@kernel.org>
L: ath10k@lists.infradead.org
S: Supported
@ -19333,7 +19370,6 @@ F: drivers/net/wireless/ath/ath10k/
N: ath10k
QUALCOMM ATHEROS ATH11K WIRELESS DRIVER
M: Kalle Valo <kvalo@kernel.org>
M: Jeff Johnson <jjohnson@kernel.org>
L: ath11k@lists.infradead.org
S: Supported
@ -19468,6 +19504,15 @@ L: dmaengine@vger.kernel.org
S: Supported
F: drivers/dma/qcom/hidma*
QUALCOMM I2C QCOM GENI DRIVER
M: Mukesh Kumar Savaliya <quic_msavaliy@quicinc.com>
M: Viken Dadhaniya <quic_vdadhani@quicinc.com>
L: linux-i2c@vger.kernel.org
L: linux-arm-msm@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/i2c/qcom,i2c-geni-qcom.yaml
F: drivers/i2c/busses/i2c-qcom-geni.c
QUALCOMM I2C CCI DRIVER
M: Loic Poulain <loic.poulain@linaro.org>
M: Robert Foss <rfoss@kernel.org>
@ -22807,7 +22852,7 @@ F: drivers/sh/
SUSPEND TO RAM
M: "Rafael J. Wysocki" <rafael@kernel.org>
M: Len Brown <len.brown@intel.com>
M: Pavel Machek <pavel@ucw.cz>
M: Pavel Machek <pavel@kernel.org>
L: linux-pm@vger.kernel.org
S: Supported
B: https://bugzilla.kernel.org

15
Makefile
View File

@ -2,7 +2,7 @@
VERSION = 6
PATCHLEVEL = 14
SUBLEVEL = 0
EXTRAVERSION = -rc1
EXTRAVERSION = -rc3
NAME = Baby Opossum Posse
# *DOCUMENTATION*
@ -1120,8 +1120,8 @@ LDFLAGS_vmlinux += --orphan-handling=$(CONFIG_LD_ORPHAN_WARN_LEVEL)
endif
# Align the bit size of userspace programs with the kernel
KBUILD_USERCFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CFLAGS))
KBUILD_USERLDFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CFLAGS))
KBUILD_USERCFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS))
KBUILD_USERLDFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS))
# make the checker run with the right architecture
CHECKFLAGS += --arch=$(ARCH)
@ -1421,18 +1421,13 @@ ifneq ($(wildcard $(resolve_btfids_O)),)
$(Q)$(MAKE) -sC $(srctree)/tools/bpf/resolve_btfids O=$(resolve_btfids_O) clean
endif
# Clear a bunch of variables before executing the submake
ifeq ($(quiet),silent_)
tools_silent=s
endif
tools/: FORCE
$(Q)mkdir -p $(objtree)/tools
$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(tools_silent) $(filter --j% -j,$(MAKEFLAGS))" O=$(abspath $(objtree)) subdir=tools -C $(srctree)/tools/
$(Q)$(MAKE) LDFLAGS= O=$(abspath $(objtree)) subdir=tools -C $(srctree)/tools/
tools/%: FORCE
$(Q)mkdir -p $(objtree)/tools
$(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(tools_silent) $(filter --j% -j,$(MAKEFLAGS))" O=$(abspath $(objtree)) subdir=tools -C $(srctree)/tools/ $*
$(Q)$(MAKE) LDFLAGS= O=$(abspath $(objtree)) subdir=tools -C $(srctree)/tools/ $*
# ---------------------------------------------------------------------------
# Kernel selftest

6
arch/alpha/include/asm/elf.h
View File

@ -74,7 +74,7 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
/*
* This is used to ensure we don't load something for the wrong architecture.
*/
#define elf_check_arch(x) ((x)->e_machine == EM_ALPHA)
#define elf_check_arch(x) (((x)->e_machine == EM_ALPHA) && !((x)->e_flags & EF_ALPHA_32BIT))
/*
* These are used to set parameters in the core dumps.
@ -137,10 +137,6 @@ extern int dump_elf_task(elf_greg_t *dest, struct task_struct *task);
: amask (AMASK_CIX) ? "ev6" : "ev67"); \
})
#define SET_PERSONALITY(EX) \
set_personality(((EX).e_flags & EF_ALPHA_32BIT) \
? PER_LINUX_32BIT : PER_LINUX)
extern int alpha_l1i_cacheshape;
extern int alpha_l1d_cacheshape;
extern int alpha_l2_cacheshape;

2
arch/alpha/include/asm/hwrpb.h
View File

@ -135,7 +135,7 @@ struct crb_struct {
/* virtual->physical map */
unsigned long map_entries;
unsigned long map_pages;
struct vf_map_struct map[1];
struct vf_map_struct map[];
};
struct memclust_struct {

2
arch/alpha/include/asm/pgtable.h
View File

@ -360,7 +360,7 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
extern void paging_init(void);
/* We have our own get_unmapped_area to cope with ADDR_LIMIT_32BIT. */
/* We have our own get_unmapped_area */
#define HAVE_ARCH_UNMAPPED_AREA
#endif /* _ALPHA_PGTABLE_H */

8
arch/alpha/include/asm/processor.h
View File

@ -8,23 +8,19 @@
#ifndef __ASM_ALPHA_PROCESSOR_H
#define __ASM_ALPHA_PROCESSOR_H
#include <linux/personality.h> /* for ADDR_LIMIT_32BIT */
/*
* We have a 42-bit user address space: 4TB user VM...
*/
#define TASK_SIZE (0x40000000000UL)
#define STACK_TOP \
(current->personality & ADDR_LIMIT_32BIT ? 0x80000000 : 0x00120000000UL)
#define STACK_TOP (0x00120000000UL)
#define STACK_TOP_MAX 0x00120000000UL
/* This decides where the kernel will search for a free chunk of vm
* space during mmap's.
*/
#define TASK_UNMAPPED_BASE \
((current->personality & ADDR_LIMIT_32BIT) ? 0x40000000 : TASK_SIZE / 2)
#define TASK_UNMAPPED_BASE (TASK_SIZE / 2)
/* This is dead. Everything has been moved to thread_info. */
struct thread_struct { };

2
arch/alpha/include/uapi/asm/ptrace.h
View File

@ -42,6 +42,8 @@ struct pt_regs {
unsigned long trap_a0;
unsigned long trap_a1;
unsigned long trap_a2;
/* This makes the stack 16-byte aligned as GCC expects */
unsigned long __pad0;
/* These are saved by PAL-code: */
unsigned long ps;
unsigned long pc;

4
arch/alpha/kernel/asm-offsets.c
View File

@ -19,9 +19,13 @@ static void __used foo(void)
DEFINE(TI_STATUS, offsetof(struct thread_info, status));
BLANK();
DEFINE(SP_OFF, offsetof(struct pt_regs, ps));
DEFINE(SIZEOF_PT_REGS, sizeof(struct pt_regs));
BLANK();
DEFINE(SWITCH_STACK_SIZE, sizeof(struct switch_stack));
BLANK();
DEFINE(HAE_CACHE, offsetof(struct alpha_machine_vector, hae_cache));
DEFINE(HAE_REG, offsetof(struct alpha_machine_vector, hae_register));
}

24
arch/alpha/kernel/entry.S
View File

@ -15,10 +15,6 @@
.set noat
.cfi_sections .debug_frame
/* Stack offsets. */
#define SP_OFF 184
#define SWITCH_STACK_SIZE 64
.macro CFI_START_OSF_FRAME func
.align 4
.globl \func
@ -198,8 +194,8 @@ CFI_END_OSF_FRAME entArith
CFI_START_OSF_FRAME entMM
SAVE_ALL
/* save $9 - $15 so the inline exception code can manipulate them. */
subq $sp, 56, $sp
.cfi_adjust_cfa_offset 56
subq $sp, 64, $sp
.cfi_adjust_cfa_offset 64
stq $9, 0($sp)
stq $10, 8($sp)
stq $11, 16($sp)
@ -214,7 +210,7 @@ CFI_START_OSF_FRAME entMM
.cfi_rel_offset $13, 32
.cfi_rel_offset $14, 40
.cfi_rel_offset $15, 48
addq $sp, 56, $19
addq $sp, 64, $19
/* handle the fault */
lda $8, 0x3fff
bic $sp, $8, $8
@ -227,7 +223,7 @@ CFI_START_OSF_FRAME entMM
ldq $13, 32($sp)
ldq $14, 40($sp)
ldq $15, 48($sp)
addq $sp, 56, $sp
addq $sp, 64, $sp
.cfi_restore $9
.cfi_restore $10
.cfi_restore $11
@ -235,7 +231,7 @@ CFI_START_OSF_FRAME entMM
.cfi_restore $13
.cfi_restore $14
.cfi_restore $15
.cfi_adjust_cfa_offset -56
.cfi_adjust_cfa_offset -64
/* finish up the syscall as normal. */
br ret_from_sys_call
CFI_END_OSF_FRAME entMM
@ -382,8 +378,8 @@ entUnaUser:
.cfi_restore $0
.cfi_adjust_cfa_offset -256
SAVE_ALL /* setup normal kernel stack */
lda $sp, -56($sp)
.cfi_adjust_cfa_offset 56
lda $sp, -64($sp)
.cfi_adjust_cfa_offset 64
stq $9, 0($sp)
stq $10, 8($sp)
stq $11, 16($sp)
@ -399,7 +395,7 @@ entUnaUser:
.cfi_rel_offset $14, 40
.cfi_rel_offset $15, 48
lda $8, 0x3fff
addq $sp, 56, $19
addq $sp, 64, $19
bic $sp, $8, $8
jsr $26, do_entUnaUser
ldq $9, 0($sp)
@ -409,7 +405,7 @@ entUnaUser:
ldq $13, 32($sp)
ldq $14, 40($sp)
ldq $15, 48($sp)
lda $sp, 56($sp)
lda $sp, 64($sp)
.cfi_restore $9
.cfi_restore $10
.cfi_restore $11
@ -417,7 +413,7 @@ entUnaUser:
.cfi_restore $13
.cfi_restore $14
.cfi_restore $15
.cfi_adjust_cfa_offset -56
.cfi_adjust_cfa_offset -64
br ret_from_sys_call
CFI_END_OSF_FRAME entUna

11
arch/alpha/kernel/osf_sys.c
View File

@ -1210,8 +1210,7 @@ SYSCALL_DEFINE1(old_adjtimex, struct timex32 __user *, txc_p)
return ret;
}
/* Get an address range which is currently unmapped. Similar to the
generic version except that we know how to honor ADDR_LIMIT_32BIT. */
/* Get an address range which is currently unmapped. */
static unsigned long
arch_get_unmapped_area_1(unsigned long addr, unsigned long len,
@ -1230,13 +1229,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
unsigned long len, unsigned long pgoff,
unsigned long flags, vm_flags_t vm_flags)
{
unsigned long limit;
/* "32 bit" actually means 31 bit, since pointers sign extend. */
if (current->personality & ADDR_LIMIT_32BIT)
limit = 0x80000000;
else
limit = TASK_SIZE;
unsigned long limit = TASK_SIZE;
if (len > limit)
return -ENOMEM;

3
arch/alpha/kernel/pci_iommu.c
View File

@ -13,6 +13,7 @@
#include <linux/log2.h>
#include <linux/dma-map-ops.h>
#include <linux/iommu-helper.h>
#include <linux/string_choices.h>
#include <asm/io.h>
#include <asm/hwrpb.h>
@ -212,7 +213,7 @@ static int pci_dac_dma_supported(struct pci_dev *dev, u64 mask)
/* If both conditions above are met, we are fine. */
DBGA("pci_dac_dma_supported %s from %ps\n",
ok ? "yes" : "no", __builtin_return_address(0));
str_yes_no(ok), __builtin_return_address(0));
return ok;
}

2
arch/alpha/kernel/traps.c
View File

@ -649,7 +649,7 @@ s_reg_to_mem (unsigned long s_reg)
static int unauser_reg_offsets[32] = {
R(r0), R(r1), R(r2), R(r3), R(r4), R(r5), R(r6), R(r7), R(r8),
/* r9 ... r15 are stored in front of regs. */
-56, -48, -40, -32, -24, -16, -8,
-64, -56, -48, -40, -32, -24, -16, /* padding at -8 */
R(r16), R(r17), R(r18),
R(r19), R(r20), R(r21), R(r22), R(r23), R(r24), R(r25), R(r26),
R(r27), R(r28), R(gp),

4
arch/alpha/mm/fault.c
View File

@ -78,8 +78,8 @@ __load_new_mm_context(struct mm_struct *next_mm)
/* Macro for exception fixup code to access integer registers. */
#define dpf_reg(r) \
(((unsigned long *)regs)[(r) <= 8 ? (r) : (r) <= 15 ? (r)-16 : \
(r) <= 18 ? (r)+10 : (r)-10])
(((unsigned long *)regs)[(r) <= 8 ? (r) : (r) <= 15 ? (r)-17 : \
(r) <= 18 ? (r)+11 : (r)-10])
asmlinkage void
do_page_fault(unsigned long address, unsigned long mmcsr,

1
arch/arm64/Kconfig
View File

@ -225,7 +225,6 @@ config ARM64
select HAVE_FUNCTION_ERROR_INJECTION
select HAVE_FUNCTION_GRAPH_FREGS
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_FUNCTION_GRAPH_RETVAL
select HAVE_GCC_PLUGINS
select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && \
HW_PERF_EVENTS && HAVE_PERF_EVENTS_NMI

4
arch/arm64/Makefile
View File

@ -48,7 +48,11 @@ KBUILD_CFLAGS += $(CC_FLAGS_NO_FPU) \
KBUILD_CFLAGS += $(call cc-disable-warning, psabi)
KBUILD_AFLAGS += $(compat_vdso)
ifeq ($(call test-ge, $(CONFIG_RUSTC_VERSION), 108500),y)
KBUILD_RUSTFLAGS += --target=aarch64-unknown-none-softfloat
else
KBUILD_RUSTFLAGS += --target=aarch64-unknown-none -Ctarget-feature="-neon"
endif
KBUILD_CFLAGS += $(call cc-option,-mabi=lp64)
KBUILD_AFLAGS += $(call cc-option,-mabi=lp64)

42
arch/arm64/include/asm/kvm_emulate.h
View File

@ -605,48 +605,6 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu)
__cpacr_to_cptr_set(clr, set));\
} while (0)
static __always_inline void kvm_write_cptr_el2(u64 val)
{
if (has_vhe() || has_hvhe())
write_sysreg(val, cpacr_el1);
else
write_sysreg(val, cptr_el2);
}
/* Resets the value of cptr_el2 when returning to the host. */
static __always_inline void __kvm_reset_cptr_el2(struct kvm *kvm)
{
u64 val;
if (has_vhe()) {
val = (CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN);
if (cpus_have_final_cap(ARM64_SME))
val |= CPACR_EL1_SMEN_EL1EN;
} else if (has_hvhe()) {
val = CPACR_EL1_FPEN;
if (!kvm_has_sve(kvm) || !guest_owns_fp_regs())
val |= CPACR_EL1_ZEN;
if (cpus_have_final_cap(ARM64_SME))
val |= CPACR_EL1_SMEN;
} else {
val = CPTR_NVHE_EL2_RES1;
if (kvm_has_sve(kvm) && guest_owns_fp_regs())
val |= CPTR_EL2_TZ;
if (!cpus_have_final_cap(ARM64_SME))
val |= CPTR_EL2_TSM;
}
kvm_write_cptr_el2(val);
}
#ifdef __KVM_NVHE_HYPERVISOR__
#define kvm_reset_cptr_el2(v) __kvm_reset_cptr_el2(kern_hyp_va((v)->kvm))
#else
#define kvm_reset_cptr_el2(v) __kvm_reset_cptr_el2((v)->kvm)
#endif
/*
* Returns a 'sanitised' view of CPTR_EL2, translating from nVHE to the VHE
* format if E2H isn't set.

22
arch/arm64/include/asm/kvm_host.h
View File

@ -100,7 +100,7 @@ static inline void push_hyp_memcache(struct kvm_hyp_memcache *mc,
static inline void *pop_hyp_memcache(struct kvm_hyp_memcache *mc,
void *(*to_va)(phys_addr_t phys))
{
phys_addr_t *p = to_va(mc->head);
phys_addr_t *p = to_va(mc->head & PAGE_MASK);
if (!mc->nr_pages)
return NULL;
@ -615,8 +615,6 @@ struct cpu_sve_state {
struct kvm_host_data {
#define KVM_HOST_DATA_FLAG_HAS_SPE 0
#define KVM_HOST_DATA_FLAG_HAS_TRBE 1
#define KVM_HOST_DATA_FLAG_HOST_SVE_ENABLED 2
#define KVM_HOST_DATA_FLAG_HOST_SME_ENABLED 3
#define KVM_HOST_DATA_FLAG_TRBE_ENABLED 4
#define KVM_HOST_DATA_FLAG_EL1_TRACING_CONFIGURED 5
unsigned long flags;
@ -624,23 +622,13 @@ struct kvm_host_data {
struct kvm_cpu_context host_ctxt;
/*
* All pointers in this union are hyp VA.
* Hyp VA.
* sve_state is only used in pKVM and if system_supports_sve().
*/
union {
struct user_fpsimd_state *fpsimd_state;
struct cpu_sve_state *sve_state;
};
struct cpu_sve_state *sve_state;
union {
/* HYP VA pointer to the host storage for FPMR */
u64 *fpmr_ptr;
/*
* Used by pKVM only, as it needs to provide storage
* for the host
*/
u64 fpmr;
};
/* Used by pKVM only. */
u64 fpmr;
/* Ownership of the FP regs */
enum {

12
arch/arm64/kernel/cacheinfo.c
View File

@ -101,16 +101,18 @@ int populate_cache_leaves(unsigned int cpu)
unsigned int level, idx;
enum cache_type type;
struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
struct cacheinfo *this_leaf = this_cpu_ci->info_list;
struct cacheinfo *infos = this_cpu_ci->info_list;
for (idx = 0, level = 1; level <= this_cpu_ci->num_levels &&
idx < this_cpu_ci->num_leaves; idx++, level++) {
idx < this_cpu_ci->num_leaves; level++) {
type = get_cache_type(level);
if (type == CACHE_TYPE_SEPARATE) {
ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level);
ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level);
if (idx + 1 >= this_cpu_ci->num_leaves)
break;
ci_leaf_init(&infos[idx++], CACHE_TYPE_DATA, level);
ci_leaf_init(&infos[idx++], CACHE_TYPE_INST, level);
} else {
ci_leaf_init(this_leaf++, type, level);
ci_leaf_init(&infos[idx++], type, level);
}
}
return 0;

5
arch/arm64/kernel/cpufeature.c
View File

@ -3091,6 +3091,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
HWCAP_CAP(ID_AA64ISAR0_EL1, TS, FLAGM, CAP_HWCAP, KERNEL_HWCAP_FLAGM),
HWCAP_CAP(ID_AA64ISAR0_EL1, TS, FLAGM2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2),
HWCAP_CAP(ID_AA64ISAR0_EL1, RNDR, IMP, CAP_HWCAP, KERNEL_HWCAP_RNG),
HWCAP_CAP(ID_AA64ISAR3_EL1, FPRCVT, IMP, CAP_HWCAP, KERNEL_HWCAP_FPRCVT),
HWCAP_CAP(ID_AA64PFR0_EL1, FP, IMP, CAP_HWCAP, KERNEL_HWCAP_FP),
HWCAP_CAP(ID_AA64PFR0_EL1, FP, FP16, CAP_HWCAP, KERNEL_HWCAP_FPHP),
HWCAP_CAP(ID_AA64PFR0_EL1, AdvSIMD, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMD),
@ -3180,8 +3181,6 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
HWCAP_CAP(ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA),
HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4),
HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2),
HWCAP_CAP(ID_AA64SMFR0_EL1, SF8MM8, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8MM8),
HWCAP_CAP(ID_AA64SMFR0_EL1, SF8MM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8MM4),
HWCAP_CAP(ID_AA64SMFR0_EL1, SBitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SBITPERM),
HWCAP_CAP(ID_AA64SMFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_AES),
HWCAP_CAP(ID_AA64SMFR0_EL1, SFEXPA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SFEXPA),
@ -3192,6 +3191,8 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
HWCAP_CAP(ID_AA64FPFR0_EL1, F8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_F8FMA),
HWCAP_CAP(ID_AA64FPFR0_EL1, F8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_F8DP4),
HWCAP_CAP(ID_AA64FPFR0_EL1, F8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_F8DP2),
HWCAP_CAP(ID_AA64FPFR0_EL1, F8MM8, IMP, CAP_HWCAP, KERNEL_HWCAP_F8MM8),
HWCAP_CAP(ID_AA64FPFR0_EL1, F8MM4, IMP, CAP_HWCAP, KERNEL_HWCAP_F8MM4),
HWCAP_CAP(ID_AA64FPFR0_EL1, F8E4M3, IMP, CAP_HWCAP, KERNEL_HWCAP_F8E4M3),
HWCAP_CAP(ID_AA64FPFR0_EL1, F8E5M2, IMP, CAP_HWCAP, KERNEL_HWCAP_F8E5M2),
#ifdef CONFIG_ARM64_POE

25
arch/arm64/kernel/fpsimd.c
View File

@ -1694,31 +1694,6 @@ void fpsimd_signal_preserve_current_state(void)
sve_to_fpsimd(current);
}
/*
* Called by KVM when entering the guest.
*/
void fpsimd_kvm_prepare(void)
{
if (!system_supports_sve())
return;
/*
* KVM does not save host SVE state since we can only enter
* the guest from a syscall so the ABI means that only the
* non-saved SVE state needs to be saved. If we have left
* SVE enabled for performance reasons then update the task
* state to be FPSIMD only.
*/
get_cpu_fpsimd_context();
if (test_and_clear_thread_flag(TIF_SVE)) {
sve_to_fpsimd(current);
current->thread.fp_type = FP_STATE_FPSIMD;
}
put_cpu_fpsimd_context();
}
/*
* Associate current's FPSIMD context with this cpu
* The caller must have ownership of the cpu FPSIMD context before calling

22
arch/arm64/kernel/topology.c
View File

@ -194,12 +194,19 @@ static void amu_fie_setup(const struct cpumask *cpus)
int cpu;
/* We are already set since the last insmod of cpufreq driver */
if (unlikely(cpumask_subset(cpus, amu_fie_cpus)))
if (cpumask_available(amu_fie_cpus) &&
unlikely(cpumask_subset(cpus, amu_fie_cpus)))
return;
for_each_cpu(cpu, cpus) {
for_each_cpu(cpu, cpus)
if (!freq_counters_valid(cpu))
return;
if (!cpumask_available(amu_fie_cpus) &&
!zalloc_cpumask_var(&amu_fie_cpus, GFP_KERNEL)) {
WARN_ONCE(1, "Failed to allocate FIE cpumask for CPUs[%*pbl]\n",
cpumask_pr_args(cpus));
return;
}
cpumask_or(amu_fie_cpus, amu_fie_cpus, cpus);
@ -237,17 +244,8 @@ static struct notifier_block init_amu_fie_notifier = {
static int __init init_amu_fie(void)
{
int ret;
if (!zalloc_cpumask_var(&amu_fie_cpus, GFP_KERNEL))
return -ENOMEM;
ret = cpufreq_register_notifier(&init_amu_fie_notifier,
return cpufreq_register_notifier(&init_amu_fie_notifier,
CPUFREQ_POLICY_NOTIFIER);
if (ret)
free_cpumask_var(amu_fie_cpus);
return ret;
}
core_initcall(init_amu_fie);

1
arch/arm64/kernel/vdso/vdso.lds.S
View File

@ -41,6 +41,7 @@ SECTIONS
*/
/DISCARD/ : {
*(.note.GNU-stack .note.gnu.property)
*(.ARM.attributes)
}
.note : { *(.note.*) } :text :note

1
arch/arm64/kernel/vmlinux.lds.S
View File

@ -162,6 +162,7 @@ SECTIONS
/DISCARD/ : {
*(.interp .dynamic)
*(.dynsym .dynstr .hash .gnu.hash)
*(.ARM.attributes)
}
. = KIMAGE_VADDR;

65
arch/arm64/kvm/arch_timer.c
View File

@ -447,21 +447,19 @@ static void kvm_timer_update_status(struct arch_timer_context *ctx, bool level)
static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level,
struct arch_timer_context *timer_ctx)
{
int ret;
kvm_timer_update_status(timer_ctx, new_level);
timer_ctx->irq.level = new_level;
trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_irq(timer_ctx),
timer_ctx->irq.level);
if (!userspace_irqchip(vcpu->kvm)) {
ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu,
timer_irq(timer_ctx),
timer_ctx->irq.level,
timer_ctx);
WARN_ON(ret);
}
if (userspace_irqchip(vcpu->kvm))
return;
kvm_vgic_inject_irq(vcpu->kvm, vcpu,
timer_irq(timer_ctx),
timer_ctx->irq.level,
timer_ctx);
}
/* Only called for a fully emulated timer */
@ -471,10 +469,8 @@ static void timer_emulate(struct arch_timer_context *ctx)
trace_kvm_timer_emulate(ctx, should_fire);
if (should_fire != ctx->irq.level) {
if (should_fire != ctx->irq.level)
kvm_timer_update_irq(ctx->vcpu, should_fire, ctx);
return;
}
kvm_timer_update_status(ctx, should_fire);
@ -761,21 +757,6 @@ static void kvm_timer_vcpu_load_nested_switch(struct kvm_vcpu *vcpu,
timer_irq(map->direct_ptimer),
&arch_timer_irq_ops);
WARN_ON_ONCE(ret);
/*
* The virtual offset behaviour is "interesting", as it
* always applies when HCR_EL2.E2H==0, but only when
* accessed from EL1 when HCR_EL2.E2H==1. So make sure we
* track E2H when putting the HV timer in "direct" mode.
*/
if (map->direct_vtimer == vcpu_hvtimer(vcpu)) {
struct arch_timer_offset *offs = &map->direct_vtimer->offset;
if (vcpu_el2_e2h_is_set(vcpu))
offs->vcpu_offset = NULL;
else
offs->vcpu_offset = &__vcpu_sys_reg(vcpu, CNTVOFF_EL2);
}
}
}
@ -976,31 +957,21 @@ void kvm_timer_sync_nested(struct kvm_vcpu *vcpu)
* which allows trapping of the timer registers even with NV2.
* Still, this is still worse than FEAT_NV on its own. Meh.
*/
if (!vcpu_el2_e2h_is_set(vcpu)) {
if (cpus_have_final_cap(ARM64_HAS_ECV))
return;
/*
* A non-VHE guest hypervisor doesn't have any direct access
* to its timers: the EL2 registers trap (and the HW is
* fully emulated), while the EL0 registers access memory
* despite the access being notionally direct. Boo.
*
* We update the hardware timer registers with the
* latest value written by the guest to the VNCR page
* and let the hardware take care of the rest.
*/
write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTV_CTL_EL0), SYS_CNTV_CTL);
write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTV_CVAL_EL0), SYS_CNTV_CVAL);
write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTP_CTL_EL0), SYS_CNTP_CTL);
write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTP_CVAL_EL0), SYS_CNTP_CVAL);
} else {
if (!cpus_have_final_cap(ARM64_HAS_ECV)) {
/*
* For a VHE guest hypervisor, the EL2 state is directly
* stored in the host EL1 timers, while the emulated EL0
* stored in the host EL1 timers, while the emulated EL1
* state is stored in the VNCR page. The latter could have
* been updated behind our back, and we must reset the
* emulation of the timers.
*
* A non-VHE guest hypervisor doesn't have any direct access
* to its timers: the EL2 registers trap despite being
* notionally direct (we use the EL1 HW, as for VHE), while
* the EL1 registers access memory.
*
* In both cases, process the emulated timers on each guest
* exit. Boo.
*/
struct timer_map map;
get_timer_map(vcpu, &map);

28
arch/arm64/kvm/arm.c
View File

@ -2290,6 +2290,19 @@ static int __init init_subsystems(void)
break;
case -ENODEV:
case -ENXIO:
/*
* No VGIC? No pKVM for you.
*
* Protected mode assumes that VGICv3 is present, so no point
* in trying to hobble along if vgic initialization fails.
*/
if (is_protected_kvm_enabled())
goto out;
/*
* Otherwise, userspace could choose to implement a GIC for its
* guest on non-cooperative hardware.
*/
vgic_present = false;
err = 0;
break;
@ -2400,6 +2413,13 @@ static void kvm_hyp_init_symbols(void)
kvm_nvhe_sym(id_aa64smfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64SMFR0_EL1);
kvm_nvhe_sym(__icache_flags) = __icache_flags;
kvm_nvhe_sym(kvm_arm_vmid_bits) = kvm_arm_vmid_bits;
/*
* Flush entire BSS since part of its data containing init symbols is read
* while the MMU is off.
*/
kvm_flush_dcache_to_poc(kvm_ksym_ref(__hyp_bss_start),
kvm_ksym_ref(__hyp_bss_end) - kvm_ksym_ref(__hyp_bss_start));
}
static int __init kvm_hyp_init_protection(u32 hyp_va_bits)
@ -2461,14 +2481,6 @@ static void finalize_init_hyp_mode(void)
per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state =
kern_hyp_va(sve_state);
}
} else {
for_each_possible_cpu(cpu) {
struct user_fpsimd_state *fpsimd_state;
fpsimd_state = &per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->host_ctxt.fp_regs;
per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->fpsimd_state =
kern_hyp_va(fpsimd_state);
}
}
}

107
arch/arm64/kvm/fpsimd.c
View File

@ -54,50 +54,18 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu)
if (!system_supports_fpsimd())
return;
fpsimd_kvm_prepare();
/*
* We will check TIF_FOREIGN_FPSTATE just before entering the
* guest in kvm_arch_vcpu_ctxflush_fp() and override this to
* FP_STATE_FREE if the flag set.
* Ensure that any host FPSIMD/SVE/SME state is saved and unbound such
* that the host kernel is responsible for restoring this state upon
* return to userspace, and the hyp code doesn't need to save anything.
*
* When the host may use SME, fpsimd_save_and_flush_cpu_state() ensures
* that PSTATE.{SM,ZA} == {0,0}.
*/
*host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED;
*host_data_ptr(fpsimd_state) = kern_hyp_va(&current->thread.uw.fpsimd_state);
*host_data_ptr(fpmr_ptr) = kern_hyp_va(&current->thread.uw.fpmr);
fpsimd_save_and_flush_cpu_state();
*host_data_ptr(fp_owner) = FP_STATE_FREE;
host_data_clear_flag(HOST_SVE_ENABLED);
if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN)
host_data_set_flag(HOST_SVE_ENABLED);
if (system_supports_sme()) {
host_data_clear_flag(HOST_SME_ENABLED);
if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN)
host_data_set_flag(HOST_SME_ENABLED);
/*
* If PSTATE.SM is enabled then save any pending FP
* state and disable PSTATE.SM. If we leave PSTATE.SM
* enabled and the guest does not enable SME via
* CPACR_EL1.SMEN then operations that should be valid
* may generate SME traps from EL1 to EL1 which we
* can't intercept and which would confuse the guest.
*
* Do the same for PSTATE.ZA in the case where there
* is state in the registers which has not already
* been saved, this is very unlikely to happen.
*/
if (read_sysreg_s(SYS_SVCR) & (SVCR_SM_MASK | SVCR_ZA_MASK)) {
*host_data_ptr(fp_owner) = FP_STATE_FREE;
fpsimd_save_and_flush_cpu_state();
}
}
/*
* If normal guests gain SME support, maintain this behavior for pKVM
* guests, which don't support SME.
*/
WARN_ON(is_protected_kvm_enabled() && system_supports_sme() &&
read_sysreg_s(SYS_SVCR));
WARN_ON_ONCE(system_supports_sme() && read_sysreg_s(SYS_SVCR));
}
/*
@ -162,52 +130,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
local_irq_save(flags);
/*
* If we have VHE then the Hyp code will reset CPACR_EL1 to
* the default value and we need to reenable SME.
*/
if (has_vhe() && system_supports_sme()) {
/* Also restore EL0 state seen on entry */
if (host_data_test_flag(HOST_SME_ENABLED))
sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_SMEN);
else
sysreg_clear_set(CPACR_EL1,
CPACR_EL1_SMEN_EL0EN,
CPACR_EL1_SMEN_EL1EN);
isb();
}
if (guest_owns_fp_regs()) {
if (vcpu_has_sve(vcpu)) {
u64 zcr = read_sysreg_el1(SYS_ZCR);
/*
* If the vCPU is in the hyp context then ZCR_EL1 is
* loaded with its vEL2 counterpart.
*/
__vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)) = zcr;
/*
* Restore the VL that was saved when bound to the CPU,
* which is the maximum VL for the guest. Because the
* layout of the data when saving the sve state depends
* on the VL, we need to use a consistent (i.e., the
* maximum) VL.
* Note that this means that at guest exit ZCR_EL1 is
* not necessarily the same as on guest entry.
*
* ZCR_EL2 holds the guest hypervisor's VL when running
* a nested guest, which could be smaller than the
* max for the vCPU. Similar to above, we first need to
* switch to a VL consistent with the layout of the
* vCPU's SVE state. KVM support for NV implies VHE, so
* using the ZCR_EL1 alias is safe.
*/
if (!has_vhe() || (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)))
sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1,
SYS_ZCR_EL1);
}
/*
* Flush (save and invalidate) the fpsimd/sve state so that if
* the host tries to use fpsimd/sve, it's not using stale data
@ -219,18 +142,6 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu)
* when needed.
*/
fpsimd_save_and_flush_cpu_state();
} else if (has_vhe() && system_supports_sve()) {
/*
* The FPSIMD/SVE state in the CPU has not been touched, and we
* have SVE (and VHE): CPACR_EL1 (alias CPTR_EL2) has been
* reset by kvm_reset_cptr_el2() in the Hyp code, disabling SVE
* for EL0. To avoid spurious traps, restore the trap state
* seen by kvm_arch_vcpu_load_fp():
*/
if (host_data_test_flag(HOST_SVE_ENABLED))
sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_ZEN_EL0EN);
else
sysreg_clear_set(CPACR_EL1, CPACR_EL1_ZEN_EL0EN, 0);
}
local_irq_restore(flags);

5
arch/arm64/kvm/hyp/entry.S
View File

@ -44,6 +44,11 @@ alternative_if ARM64_HAS_RAS_EXTN
alternative_else_nop_endif
mrs x1, isr_el1
cbz x1, 1f
// Ensure that __guest_enter() always provides a context
// synchronization event so that callers don't need ISBs for anything
// that would usually be synchonized by the ERET.
isb
mov x0, #ARM_EXCEPTION_IRQ
ret

148
arch/arm64/kvm/hyp/include/hyp/switch.h
View File

@ -326,7 +326,7 @@ static inline bool __populate_fault_info(struct kvm_vcpu *vcpu)
return __get_fault_info(vcpu->arch.fault.esr_el2, &vcpu->arch.fault);
}
static bool kvm_hyp_handle_mops(struct kvm_vcpu *vcpu, u64 *exit_code)
static inline bool kvm_hyp_handle_mops(struct kvm_vcpu *vcpu, u64 *exit_code)
{
*vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
arm64_mops_reset_regs(vcpu_gp_regs(vcpu), vcpu->arch.fault.esr_el2);
@ -375,7 +375,87 @@ static inline void __hyp_sve_save_host(void)
true);
}
static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu);
static inline void fpsimd_lazy_switch_to_guest(struct kvm_vcpu *vcpu)
{
u64 zcr_el1, zcr_el2;
if (!guest_owns_fp_regs())
return;
if (vcpu_has_sve(vcpu)) {
/* A guest hypervisor may restrict the effective max VL. */
if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))
zcr_el2 = __vcpu_sys_reg(vcpu, ZCR_EL2);
else
zcr_el2 = vcpu_sve_max_vq(vcpu) - 1;
write_sysreg_el2(zcr_el2, SYS_ZCR);
zcr_el1 = __vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu));
write_sysreg_el1(zcr_el1, SYS_ZCR);
}
}
static inline void fpsimd_lazy_switch_to_host(struct kvm_vcpu *vcpu)
{
u64 zcr_el1, zcr_el2;
if (!guest_owns_fp_regs())
return;
/*
* When the guest owns the FP regs, we know that guest+hyp traps for
* any FPSIMD/SVE/SME features exposed to the guest have been disabled
* by either fpsimd_lazy_switch_to_guest() or kvm_hyp_handle_fpsimd()
* prior to __guest_entry(). As __guest_entry() guarantees a context
* synchronization event, we don't need an ISB here to avoid taking
* traps for anything that was exposed to the guest.
*/
if (vcpu_has_sve(vcpu)) {
zcr_el1 = read_sysreg_el1(SYS_ZCR);
__vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)) = zcr_el1;
/*
* The guest's state is always saved using the guest's max VL.
* Ensure that the host has the guest's max VL active such that
* the host can save the guest's state lazily, but don't
* artificially restrict the host to the guest's max VL.
*/
if (has_vhe()) {
zcr_el2 = vcpu_sve_max_vq(vcpu) - 1;
write_sysreg_el2(zcr_el2, SYS_ZCR);
} else {
zcr_el2 = sve_vq_from_vl(kvm_host_sve_max_vl) - 1;
write_sysreg_el2(zcr_el2, SYS_ZCR);
zcr_el1 = vcpu_sve_max_vq(vcpu) - 1;
write_sysreg_el1(zcr_el1, SYS_ZCR);
}
}
}
static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
{
/*
* Non-protected kvm relies on the host restoring its sve state.
* Protected kvm restores the host's sve state as not to reveal that
* fpsimd was used by a guest nor leak upper sve bits.
*/
if (system_supports_sve()) {
__hyp_sve_save_host();
/* Re-enable SVE traps if not supported for the guest vcpu. */
if (!vcpu_has_sve(vcpu))
cpacr_clear_set(CPACR_EL1_ZEN, 0);
} else {
__fpsimd_save_state(host_data_ptr(host_ctxt.fp_regs));
}
if (kvm_has_fpmr(kern_hyp_va(vcpu->kvm)))
*host_data_ptr(fpmr) = read_sysreg_s(SYS_FPMR);
}
/*
* We trap the first access to the FP/SIMD to save the host context and
@ -383,7 +463,7 @@ static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu);
* If FP/SIMD is not implemented, handle the trap and inject an undefined
* instruction exception to the guest. Similarly for trapped SVE accesses.
*/
static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
static inline bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
{
bool sve_guest;
u8 esr_ec;
@ -425,7 +505,7 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
isb();
/* Write out the host state if it's in the registers */
if (host_owns_fp_regs())
if (is_protected_kvm_enabled() && host_owns_fp_regs())
kvm_hyp_save_fpsimd_host(vcpu);
/* Restore the guest state */
@ -501,9 +581,22 @@ static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu)
return true;
}
/* Open-coded version of timer_get_offset() to allow for kern_hyp_va() */
static inline u64 hyp_timer_get_offset(struct arch_timer_context *ctxt)
{
u64 offset = 0;
if (ctxt->offset.vm_offset)
offset += *kern_hyp_va(ctxt->offset.vm_offset);
if (ctxt->offset.vcpu_offset)
offset += *kern_hyp_va(ctxt->offset.vcpu_offset);
return offset;
}
static inline u64 compute_counter_value(struct arch_timer_context *ctxt)
{
return arch_timer_read_cntpct_el0() - timer_get_offset(ctxt);
return arch_timer_read_cntpct_el0() - hyp_timer_get_offset(ctxt);
}
static bool kvm_handle_cntxct(struct kvm_vcpu *vcpu)
@ -587,7 +680,7 @@ static bool handle_ampere1_tcr(struct kvm_vcpu *vcpu)
return true;
}
static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code)
static inline bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code)
{
if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
handle_tx2_tvm(vcpu))
@ -607,7 +700,7 @@ static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code)
return false;
}
static bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code)
static inline bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code)
{
if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
__vgic_v3_perform_cpuif_access(vcpu) == 1)
@ -616,19 +709,18 @@ static bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code)
return false;
}
static bool kvm_hyp_handle_memory_fault(struct kvm_vcpu *vcpu, u64 *exit_code)
static inline bool kvm_hyp_handle_memory_fault(struct kvm_vcpu *vcpu,
u64 *exit_code)
{
if (!__populate_fault_info(vcpu))
return true;
return false;
}
static bool kvm_hyp_handle_iabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
__alias(kvm_hyp_handle_memory_fault);
static bool kvm_hyp_handle_watchpt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
__alias(kvm_hyp_handle_memory_fault);
#define kvm_hyp_handle_iabt_low kvm_hyp_handle_memory_fault
#define kvm_hyp_handle_watchpt_low kvm_hyp_handle_memory_fault
static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
static inline bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
{
if (kvm_hyp_handle_memory_fault(vcpu, exit_code))
return true;
@ -658,23 +750,16 @@ static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
typedef bool (*exit_handler_fn)(struct kvm_vcpu *, u64 *);
static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu);
static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code);
/*
* Allow the hypervisor to handle the exit with an exit handler if it has one.
*
* Returns true if the hypervisor handled the exit, and control should go back
* to the guest, or false if it hasn't.
*/
static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code,
const exit_handler_fn *handlers)
{
const exit_handler_fn *handlers = kvm_get_exit_handler_array(vcpu);
exit_handler_fn fn;
fn = handlers[kvm_vcpu_trap_get_class(vcpu)];
exit_handler_fn fn = handlers[kvm_vcpu_trap_get_class(vcpu)];
if (fn)
return fn(vcpu, exit_code);
@ -704,20 +789,9 @@ static inline void synchronize_vcpu_pstate(struct kvm_vcpu *vcpu, u64 *exit_code
* the guest, false when we should restore the host state and return to the
* main run loop.
*/
static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
static inline bool __fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code,
const exit_handler_fn *handlers)
{
/*
* Save PSTATE early so that we can evaluate the vcpu mode
* early on.
*/
synchronize_vcpu_pstate(vcpu, exit_code);
/*
* Check whether we want to repaint the state one way or
* another.
*/
early_exit_filter(vcpu, exit_code);
if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ)
vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR);
@ -747,7 +821,7 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
goto exit;
/* Check if there's an exit handler and allow it to handle the exit. */
if (kvm_hyp_handle_exit(vcpu, exit_code))
if (kvm_hyp_handle_exit(vcpu, exit_code, handlers))
goto guest;
exit:
/* Return to the host kernel and handle the exit */

39
arch/arm64/kvm/hyp/nvhe/hyp-main.c
View File

@ -5,6 +5,7 @@
*/
#include <hyp/adjust_pc.h>
#include <hyp/switch.h>
#include <asm/pgtable-types.h>
#include <asm/kvm_asm.h>
@ -83,7 +84,7 @@ static void fpsimd_sve_sync(struct kvm_vcpu *vcpu)
if (system_supports_sve())
__hyp_sve_restore_host();
else
__fpsimd_restore_state(*host_data_ptr(fpsimd_state));
__fpsimd_restore_state(host_data_ptr(host_ctxt.fp_regs));
if (has_fpmr)
write_sysreg_s(*host_data_ptr(fpmr), SYS_FPMR);
@ -91,11 +92,34 @@ static void fpsimd_sve_sync(struct kvm_vcpu *vcpu)
*host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED;
}
static void flush_debug_state(struct pkvm_hyp_vcpu *hyp_vcpu)
{
struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
hyp_vcpu->vcpu.arch.debug_owner = host_vcpu->arch.debug_owner;
if (kvm_guest_owns_debug_regs(&hyp_vcpu->vcpu))
hyp_vcpu->vcpu.arch.vcpu_debug_state = host_vcpu->arch.vcpu_debug_state;
else if (kvm_host_owns_debug_regs(&hyp_vcpu->vcpu))
hyp_vcpu->vcpu.arch.external_debug_state = host_vcpu->arch.external_debug_state;
}
static void sync_debug_state(struct pkvm_hyp_vcpu *hyp_vcpu)
{
struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
if (kvm_guest_owns_debug_regs(&hyp_vcpu->vcpu))
host_vcpu->arch.vcpu_debug_state = hyp_vcpu->vcpu.arch.vcpu_debug_state;
else if (kvm_host_owns_debug_regs(&hyp_vcpu->vcpu))
host_vcpu->arch.external_debug_state = hyp_vcpu->vcpu.arch.external_debug_state;
}
static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
{
struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu;
fpsimd_sve_flush();
flush_debug_state(hyp_vcpu);
hyp_vcpu->vcpu.arch.ctxt = host_vcpu->arch.ctxt;
@ -123,6 +147,7 @@ static void sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)
unsigned int i;
fpsimd_sve_sync(&hyp_vcpu->vcpu);
sync_debug_state(hyp_vcpu);
host_vcpu->arch.ctxt = hyp_vcpu->vcpu.arch.ctxt;
@ -200,8 +225,12 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt)
sync_hyp_vcpu(hyp_vcpu);
} else {
struct kvm_vcpu *vcpu = kern_hyp_va(host_vcpu);
/* The host is fully trusted, run its vCPU directly. */
ret = __kvm_vcpu_run(kern_hyp_va(host_vcpu));
fpsimd_lazy_switch_to_guest(vcpu);
ret = __kvm_vcpu_run(vcpu);
fpsimd_lazy_switch_to_host(vcpu);
}
out:
cpu_reg(host_ctxt, 1) = ret;
@ -651,12 +680,6 @@ void handle_trap(struct kvm_cpu_context *host_ctxt)
case ESR_ELx_EC_SMC64:
handle_host_smc(host_ctxt);
break;
case ESR_ELx_EC_SVE:
cpacr_clear_set(0, CPACR_EL1_ZEN);
isb();
sve_cond_update_zcr_vq(sve_vq_from_vl(kvm_host_sve_max_vl) - 1,
SYS_ZCR_EL2);
break;
case ESR_ELx_EC_IABT_LOW:
case ESR_ELx_EC_DABT_LOW:
handle_host_mem_abort(host_ctxt);

76
arch/arm64/kvm/hyp/nvhe/mem_protect.c
View File

@ -943,10 +943,10 @@ static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ip
ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level);
if (ret)
return ret;
if (level != KVM_PGTABLE_LAST_LEVEL)
return -E2BIG;
if (!kvm_pte_valid(pte))
return -ENOENT;
if (level != KVM_PGTABLE_LAST_LEVEL)
return -E2BIG;
state = guest_get_page_state(pte, ipa);
if (state != PKVM_PAGE_SHARED_BORROWED)
@ -998,44 +998,57 @@ unlock:
return ret;
}
int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot)
static void assert_host_shared_guest(struct pkvm_hyp_vm *vm, u64 ipa)
{
struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
u64 ipa = hyp_pfn_to_phys(gfn);
u64 phys;
int ret;
if (prot & ~KVM_PGTABLE_PROT_RWX)
return -EINVAL;
if (!IS_ENABLED(CONFIG_NVHE_EL2_DEBUG))
return;
host_lock_component();
guest_lock_component(vm);
ret = __check_host_shared_guest(vm, &phys, ipa);
if (!ret)
ret = kvm_pgtable_stage2_relax_perms(&vm->pgt, ipa, prot, 0);
guest_unlock_component(vm);
host_unlock_component();
WARN_ON(ret && ret != -ENOENT);
}
int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot)
{
struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
u64 ipa = hyp_pfn_to_phys(gfn);
int ret;
if (pkvm_hyp_vm_is_protected(vm))
return -EPERM;
if (prot & ~KVM_PGTABLE_PROT_RWX)
return -EINVAL;
assert_host_shared_guest(vm, ipa);
guest_lock_component(vm);
ret = kvm_pgtable_stage2_relax_perms(&vm->pgt, ipa, prot, 0);
guest_unlock_component(vm);
return ret;
}
int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *vm)
{
u64 ipa = hyp_pfn_to_phys(gfn);
u64 phys;
int ret;
host_lock_component();
if (pkvm_hyp_vm_is_protected(vm))
return -EPERM;
assert_host_shared_guest(vm, ipa);
guest_lock_component(vm);
ret = __check_host_shared_guest(vm, &phys, ipa);
if (!ret)
ret = kvm_pgtable_stage2_wrprotect(&vm->pgt, ipa, PAGE_SIZE);
ret = kvm_pgtable_stage2_wrprotect(&vm->pgt, ipa, PAGE_SIZE);
guest_unlock_component(vm);
host_unlock_component();
return ret;
}
@ -1043,18 +1056,15 @@ int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *vm)
int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm)
{
u64 ipa = hyp_pfn_to_phys(gfn);
u64 phys;
int ret;
host_lock_component();
if (pkvm_hyp_vm_is_protected(vm))
return -EPERM;
assert_host_shared_guest(vm, ipa);
guest_lock_component(vm);
ret = __check_host_shared_guest(vm, &phys, ipa);
if (!ret)
ret = kvm_pgtable_stage2_test_clear_young(&vm->pgt, ipa, PAGE_SIZE, mkold);
ret = kvm_pgtable_stage2_test_clear_young(&vm->pgt, ipa, PAGE_SIZE, mkold);
guest_unlock_component(vm);
host_unlock_component();
return ret;
}
@ -1063,18 +1073,14 @@ int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu)
{
struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu);
u64 ipa = hyp_pfn_to_phys(gfn);
u64 phys;
int ret;
host_lock_component();
if (pkvm_hyp_vm_is_protected(vm))
return -EPERM;
assert_host_shared_guest(vm, ipa);
guest_lock_component(vm);
ret = __check_host_shared_guest(vm, &phys, ipa);
if (!ret)
kvm_pgtable_stage2_mkyoung(&vm->pgt, ipa, 0);
kvm_pgtable_stage2_mkyoung(&vm->pgt, ipa, 0);
guest_unlock_component(vm);
host_unlock_component();
return ret;
return 0;
}

89
arch/arm64/kvm/hyp/nvhe/switch.c
View File

@ -39,6 +39,9 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
{
u64 val = CPTR_EL2_TAM; /* Same bit irrespective of E2H */
if (!guest_owns_fp_regs())
__activate_traps_fpsimd32(vcpu);
if (has_hvhe()) {
val |= CPACR_EL1_TTA;
@ -47,6 +50,8 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
if (vcpu_has_sve(vcpu))
val |= CPACR_EL1_ZEN;
}
write_sysreg(val, cpacr_el1);
} else {
val |= CPTR_EL2_TTA | CPTR_NVHE_EL2_RES1;
@ -61,12 +66,32 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
if (!guest_owns_fp_regs())
val |= CPTR_EL2_TFP;
write_sysreg(val, cptr_el2);
}
}
if (!guest_owns_fp_regs())
__activate_traps_fpsimd32(vcpu);
static void __deactivate_cptr_traps(struct kvm_vcpu *vcpu)
{
if (has_hvhe()) {
u64 val = CPACR_EL1_FPEN;
kvm_write_cptr_el2(val);
if (cpus_have_final_cap(ARM64_SVE))
val |= CPACR_EL1_ZEN;
if (cpus_have_final_cap(ARM64_SME))
val |= CPACR_EL1_SMEN;
write_sysreg(val, cpacr_el1);
} else {
u64 val = CPTR_NVHE_EL2_RES1;
if (!cpus_have_final_cap(ARM64_SVE))
val |= CPTR_EL2_TZ;
if (!cpus_have_final_cap(ARM64_SME))
val |= CPTR_EL2_TSM;
write_sysreg(val, cptr_el2);
}
}
static void __activate_traps(struct kvm_vcpu *vcpu)
@ -119,7 +144,7 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2);
kvm_reset_cptr_el2(vcpu);
__deactivate_cptr_traps(vcpu);
write_sysreg(__kvm_hyp_host_vector, vbar_el2);
}
@ -192,34 +217,6 @@ static bool kvm_handle_pvm_sys64(struct kvm_vcpu *vcpu, u64 *exit_code)
kvm_handle_pvm_sysreg(vcpu, exit_code));
}
static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
{
/*
* Non-protected kvm relies on the host restoring its sve state.
* Protected kvm restores the host's sve state as not to reveal that
* fpsimd was used by a guest nor leak upper sve bits.
*/
if (unlikely(is_protected_kvm_enabled() && system_supports_sve())) {
__hyp_sve_save_host();
/* Re-enable SVE traps if not supported for the guest vcpu. */
if (!vcpu_has_sve(vcpu))
cpacr_clear_set(CPACR_EL1_ZEN, 0);
} else {
__fpsimd_save_state(*host_data_ptr(fpsimd_state));
}
if (kvm_has_fpmr(kern_hyp_va(vcpu->kvm))) {
u64 val = read_sysreg_s(SYS_FPMR);
if (unlikely(is_protected_kvm_enabled()))
*host_data_ptr(fpmr) = val;
else
**host_data_ptr(fpmr_ptr) = val;
}
}
static const exit_handler_fn hyp_exit_handlers[] = {
[0 ... ESR_ELx_EC_MAX] = NULL,
[ESR_ELx_EC_CP15_32] = kvm_hyp_handle_cp15_32,
@ -251,19 +248,21 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)
return hyp_exit_handlers;
}
/*
* Some guests (e.g., protected VMs) are not be allowed to run in AArch32.
* The ARMv8 architecture does not give the hypervisor a mechanism to prevent a
* guest from dropping to AArch32 EL0 if implemented by the CPU. If the
* hypervisor spots a guest in such a state ensure it is handled, and don't
* trust the host to spot or fix it. The check below is based on the one in
* kvm_arch_vcpu_ioctl_run().
*
* Returns false if the guest ran in AArch32 when it shouldn't have, and
* thus should exit to the host, or true if a the guest run loop can continue.
*/
static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
{
const exit_handler_fn *handlers = kvm_get_exit_handler_array(vcpu);
synchronize_vcpu_pstate(vcpu, exit_code);
/*
* Some guests (e.g., protected VMs) are not be allowed to run in
* AArch32. The ARMv8 architecture does not give the hypervisor a
* mechanism to prevent a guest from dropping to AArch32 EL0 if
* implemented by the CPU. If the hypervisor spots a guest in such a
* state ensure it is handled, and don't trust the host to spot or fix
* it. The check below is based on the one in
* kvm_arch_vcpu_ioctl_run().
*/
if (unlikely(vcpu_is_protected(vcpu) && vcpu_mode_is_32bit(vcpu))) {
/*
* As we have caught the guest red-handed, decide that it isn't
@ -276,6 +275,8 @@ static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
*exit_code &= BIT(ARM_EXIT_WITH_SERROR_BIT);
*exit_code |= ARM_EXCEPTION_IL;
}
return __fixup_guest_exit(vcpu, exit_code, handlers);
}
/* Switch to the guest for legacy non-VHE systems */

33
arch/arm64/kvm/hyp/vhe/switch.c
View File

@ -136,6 +136,16 @@ write:
write_sysreg(val, cpacr_el1);
}
static void __deactivate_cptr_traps(struct kvm_vcpu *vcpu)
{
u64 val = CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN;
if (cpus_have_final_cap(ARM64_SME))
val |= CPACR_EL1_SMEN_EL1EN;
write_sysreg(val, cpacr_el1);
}
static void __activate_traps(struct kvm_vcpu *vcpu)
{
u64 val;
@ -207,7 +217,7 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
*/
asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
kvm_reset_cptr_el2(vcpu);
__deactivate_cptr_traps(vcpu);
if (!arm64_kernel_unmapped_at_el0())
host_vectors = __this_cpu_read(this_cpu_vector);
@ -413,14 +423,6 @@ static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code)
return true;
}
static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
{
__fpsimd_save_state(*host_data_ptr(fpsimd_state));
if (kvm_has_fpmr(vcpu->kvm))
**host_data_ptr(fpmr_ptr) = read_sysreg_s(SYS_FPMR);
}
static bool kvm_hyp_handle_tlbi_el2(struct kvm_vcpu *vcpu, u64 *exit_code)
{
int ret = -EINVAL;
@ -538,13 +540,10 @@ static const exit_handler_fn hyp_exit_handlers[] = {
[ESR_ELx_EC_MOPS] = kvm_hyp_handle_mops,
};
static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)
static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
{
return hyp_exit_handlers;
}
synchronize_vcpu_pstate(vcpu, exit_code);
static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
{
/*
* If we were in HYP context on entry, adjust the PSTATE view
* so that the usual helpers work correctly.
@ -564,6 +563,8 @@ static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
*vcpu_cpsr(vcpu) &= ~(PSR_MODE_MASK | PSR_MODE32_BIT);
*vcpu_cpsr(vcpu) |= mode;
}
return __fixup_guest_exit(vcpu, exit_code, hyp_exit_handlers);
}
/* Switch to the guest for VHE systems running in EL2 */
@ -578,6 +579,8 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
sysreg_save_host_state_vhe(host_ctxt);
fpsimd_lazy_switch_to_guest(vcpu);
/*
* Note that ARM erratum 1165522 requires us to configure both stage 1
* and stage 2 translation for the guest context before we clear
@ -602,6 +605,8 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
__deactivate_traps(vcpu);
fpsimd_lazy_switch_to_host(vcpu);
sysreg_restore_host_state_vhe(host_ctxt);
if (guest_owns_fp_regs())

9
arch/arm64/kvm/nested.c
View File

@ -67,26 +67,27 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu)
if (!tmp)
return -ENOMEM;
swap(kvm->arch.nested_mmus, tmp);
/*
* If we went through a realocation, adjust the MMU back-pointers in
* the previously initialised kvm_pgtable structures.
*/
if (kvm->arch.nested_mmus != tmp)
for (int i = 0; i < kvm->arch.nested_mmus_size; i++)
tmp[i].pgt->mmu = &tmp[i];
kvm->arch.nested_mmus[i].pgt->mmu = &kvm->arch.nested_mmus[i];
for (int i = kvm->arch.nested_mmus_size; !ret && i < num_mmus; i++)
ret = init_nested_s2_mmu(kvm, &tmp[i]);
ret = init_nested_s2_mmu(kvm, &kvm->arch.nested_mmus[i]);
if (ret) {
for (int i = kvm->arch.nested_mmus_size; i < num_mmus; i++)
kvm_free_stage2_pgd(&tmp[i]);
kvm_free_stage2_pgd(&kvm->arch.nested_mmus[i]);
return ret;
}
kvm->arch.nested_mmus_size = num_mmus;
kvm->arch.nested_mmus = tmp;
return 0;
}

16
arch/arm64/kvm/sys_regs.c
View File

@ -1452,6 +1452,16 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu,
return true;
}
static bool access_hv_timer(struct kvm_vcpu *vcpu,
struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
if (!vcpu_el2_e2h_is_set(vcpu))
return undef_access(vcpu, p, r);
return access_arch_timer(vcpu, p, r);
}
static s64 kvm_arm64_ftr_safe_value(u32 id, const struct arm64_ftr_bits *ftrp,
s64 new, s64 cur)
{
@ -3103,9 +3113,9 @@ static const struct sys_reg_desc sys_reg_descs[] = {
EL2_REG(CNTHP_CTL_EL2, access_arch_timer, reset_val, 0),
EL2_REG(CNTHP_CVAL_EL2, access_arch_timer, reset_val, 0),
{ SYS_DESC(SYS_CNTHV_TVAL_EL2), access_arch_timer },
EL2_REG(CNTHV_CTL_EL2, access_arch_timer, reset_val, 0),
EL2_REG(CNTHV_CVAL_EL2, access_arch_timer, reset_val, 0),
{ SYS_DESC(SYS_CNTHV_TVAL_EL2), access_hv_timer },
EL2_REG(CNTHV_CTL_EL2, access_hv_timer, reset_val, 0),
EL2_REG(CNTHV_CVAL_EL2, access_hv_timer, reset_val, 0),
{ SYS_DESC(SYS_CNTKCTL_EL12), access_cntkctl_el12 },

74
arch/arm64/kvm/vgic/vgic-init.c
View File

@ -34,9 +34,9 @@
*
* CPU Interface:
*
* - kvm_vgic_vcpu_init(): initialization of static data that
* doesn't depend on any sizing information or emulation type. No
* allocation is allowed there.
* - kvm_vgic_vcpu_init(): initialization of static data that doesn't depend
* on any sizing information. Private interrupts are allocated if not
* already allocated at vgic-creation time.
*/
/* EARLY INIT */
@ -58,6 +58,8 @@ void kvm_vgic_early_init(struct kvm *kvm)
/* CREATION */
static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type);
/**
* kvm_vgic_create: triggered by the instantiation of the VGIC device by
* user space, either through the legacy KVM_CREATE_IRQCHIP ioctl (v2 only)
@ -112,6 +114,22 @@ int kvm_vgic_create(struct kvm *kvm, u32 type)
goto out_unlock;
}
kvm_for_each_vcpu(i, vcpu, kvm) {
ret = vgic_allocate_private_irqs_locked(vcpu, type);
if (ret)
break;
}
if (ret) {
kvm_for_each_vcpu(i, vcpu, kvm) {
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
kfree(vgic_cpu->private_irqs);
vgic_cpu->private_irqs = NULL;
}
goto out_unlock;
}
kvm->arch.vgic.in_kernel = true;
kvm->arch.vgic.vgic_model = type;
@ -180,7 +198,7 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
return 0;
}
static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu)
static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
int i;
@ -218,17 +236,28 @@ static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu)
/* PPIs */
irq->config = VGIC_CONFIG_LEVEL;
}
switch (type) {
case KVM_DEV_TYPE_ARM_VGIC_V3:
irq->group = 1;
irq->mpidr = kvm_vcpu_get_mpidr_aff(vcpu);
break;
case KVM_DEV_TYPE_ARM_VGIC_V2:
irq->group = 0;
irq->targets = BIT(vcpu->vcpu_id);
break;
}
}
return 0;
}
static int vgic_allocate_private_irqs(struct kvm_vcpu *vcpu)
static int vgic_allocate_private_irqs(struct kvm_vcpu *vcpu, u32 type)
{
int ret;
mutex_lock(&vcpu->kvm->arch.config_lock);
ret = vgic_allocate_private_irqs_locked(vcpu);
ret = vgic_allocate_private_irqs_locked(vcpu, type);
mutex_unlock(&vcpu->kvm->arch.config_lock);
return ret;
@ -258,7 +287,7 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
if (!irqchip_in_kernel(vcpu->kvm))
return 0;
ret = vgic_allocate_private_irqs(vcpu);
ret = vgic_allocate_private_irqs(vcpu, dist->vgic_model);
if (ret)
return ret;
@ -295,7 +324,7 @@ int vgic_init(struct kvm *kvm)
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct kvm_vcpu *vcpu;
int ret = 0, i;
int ret = 0;
unsigned long idx;
lockdep_assert_held(&kvm->arch.config_lock);
@ -315,35 +344,6 @@ int vgic_init(struct kvm *kvm)
if (ret)
goto out;
/* Initialize groups on CPUs created before the VGIC type was known */
kvm_for_each_vcpu(idx, vcpu, kvm) {
ret = vgic_allocate_private_irqs_locked(vcpu);
if (ret)
goto out;
for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) {
struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, i);
switch (dist->vgic_model) {
case KVM_DEV_TYPE_ARM_VGIC_V3:
irq->group = 1;
irq->mpidr = kvm_vcpu_get_mpidr_aff(vcpu);
break;
case KVM_DEV_TYPE_ARM_VGIC_V2:
irq->group = 0;
irq->targets = 1U << idx;
break;
default:
ret = -EINVAL;
}
vgic_put_irq(kvm, irq);
if (ret)
goto out;
}
}
/*
* If we have GICv4.1 enabled, unconditionally request enable the
* v4 support so that we get HW-accelerated vSGIs. Otherwise, only

7
arch/arm64/mm/trans_pgd.c
View File

@ -162,6 +162,13 @@ static int copy_p4d(struct trans_pgd_info *info, pgd_t *dst_pgdp,
unsigned long next;
unsigned long addr = start;
if (pgd_none(READ_ONCE(*dst_pgdp))) {
dst_p4dp = trans_alloc(info);
if (!dst_p4dp)
return -ENOMEM;
pgd_populate(NULL, dst_pgdp, dst_p4dp);
}
dst_p4dp = p4d_offset(dst_pgdp, start);
src_p4dp = p4d_offset(src_pgdp, start);
do {

21
arch/loongarch/include/asm/cpu-info.h
View File

@ -76,27 +76,6 @@ extern const char *__cpu_full_name[];
#define cpu_family_string() __cpu_family[raw_smp_processor_id()]
#define cpu_full_name_string() __cpu_full_name[raw_smp_processor_id()]
struct seq_file;
struct notifier_block;
extern int register_proc_cpuinfo_notifier(struct notifier_block *nb);
extern int proc_cpuinfo_notifier_call_chain(unsigned long val, void *v);
#define proc_cpuinfo_notifier(fn, pri) \
({ \
static struct notifier_block fn##_nb = { \
.notifier_call = fn, \
.priority = pri \
}; \
\
register_proc_cpuinfo_notifier(&fn##_nb); \
})
struct proc_cpuinfo_notifier_args {
struct seq_file *m;
unsigned long n;
};
static inline bool cpus_are_siblings(int cpua, int cpub)
{
struct cpuinfo_loongarch *infoa = &cpu_data[cpua];

2
arch/loongarch/include/asm/smp.h
View File

@ -77,6 +77,8 @@ extern int __cpu_logical_map[NR_CPUS];
#define SMP_IRQ_WORK BIT(ACTION_IRQ_WORK)
#define SMP_CLEAR_VECTOR BIT(ACTION_CLEAR_VECTOR)
struct seq_file;
struct secondary_data {
unsigned long stack;
unsigned long thread_info;

28
arch/loongarch/kernel/genex.S
View File

@ -18,16 +18,19 @@
.align 5
SYM_FUNC_START(__arch_cpu_idle)
/* start of rollback region */
LONG_L t0, tp, TI_FLAGS
nop
andi t0, t0, _TIF_NEED_RESCHED
bnez t0, 1f
nop
nop
nop
/* start of idle interrupt region */
ori t0, zero, CSR_CRMD_IE
/* idle instruction needs irq enabled */
csrxchg t0, t0, LOONGARCH_CSR_CRMD
/*
* If an interrupt lands here; between enabling interrupts above and
* going idle on the next instruction, we must *NOT* go idle since the
* interrupt could have set TIF_NEED_RESCHED or caused an timer to need
* reprogramming. Fall through -- see handle_vint() below -- and have
* the idle loop take care of things.
*/
idle 0
/* end of rollback region */
/* end of idle interrupt region */
1: jr ra
SYM_FUNC_END(__arch_cpu_idle)
@ -35,11 +38,10 @@ SYM_CODE_START(handle_vint)
UNWIND_HINT_UNDEFINED
BACKUP_T0T1
SAVE_ALL
la_abs t1, __arch_cpu_idle
la_abs t1, 1b
LONG_L t0, sp, PT_ERA
/* 32 byte rollback region */
ori t0, t0, 0x1f
xori t0, t0, 0x1f
/* 3 instructions idle interrupt region */
ori t0, t0, 0b1100
bne t0, t1, 1f
LONG_S t0, sp, PT_ERA
1: move a0, sp

3
arch/loongarch/kernel/idle.c
View File

@ -11,7 +11,6 @@
void __cpuidle arch_cpu_idle(void)
{
raw_local_irq_enable();
__arch_cpu_idle(); /* idle instruction needs irq enabled */
__arch_cpu_idle();
raw_local_irq_disable();
}

29
arch/loongarch/kernel/proc.c
View File

@ -13,28 +13,12 @@
#include <asm/processor.h>
#include <asm/time.h>
/*
* No lock; only written during early bootup by CPU 0.
*/
static RAW_NOTIFIER_HEAD(proc_cpuinfo_chain);
int __ref register_proc_cpuinfo_notifier(struct notifier_block *nb)
{
return raw_notifier_chain_register(&proc_cpuinfo_chain, nb);
}
int proc_cpuinfo_notifier_call_chain(unsigned long val, void *v)
{
return raw_notifier_call_chain(&proc_cpuinfo_chain, val, v);
}
static int show_cpuinfo(struct seq_file *m, void *v)
{
unsigned long n = (unsigned long) v - 1;
unsigned int isa = cpu_data[n].isa_level;
unsigned int version = cpu_data[n].processor_id & 0xff;
unsigned int fp_version = cpu_data[n].fpu_vers;
struct proc_cpuinfo_notifier_args proc_cpuinfo_notifier_args;
#ifdef CONFIG_SMP
if (!cpu_online(n))
@ -91,20 +75,13 @@ static int show_cpuinfo(struct seq_file *m, void *v)
if (cpu_has_lbt_mips) seq_printf(m, " lbt_mips");
seq_printf(m, "\n");
seq_printf(m, "Hardware Watchpoint\t: %s",
cpu_has_watch ? "yes, " : "no\n");
seq_printf(m, "Hardware Watchpoint\t: %s", str_yes_no(cpu_has_watch));
if (cpu_has_watch) {
seq_printf(m, "iwatch count: %d, dwatch count: %d\n",
seq_printf(m, ", iwatch count: %d, dwatch count: %d",
cpu_data[n].watch_ireg_count, cpu_data[n].watch_dreg_count);
}
proc_cpuinfo_notifier_args.m = m;
proc_cpuinfo_notifier_args.n = n;
raw_notifier_call_chain(&proc_cpuinfo_chain, 0,
&proc_cpuinfo_notifier_args);
seq_printf(m, "\n");
seq_printf(m, "\n\n");
return 0;
}

6
arch/loongarch/kernel/reset.c
View File

@ -33,7 +33,7 @@ void machine_halt(void)
console_flush_on_panic(CONSOLE_FLUSH_PENDING);
while (true) {
__arch_cpu_idle();
__asm__ __volatile__("idle 0" : : : "memory");
}
}
@ -53,7 +53,7 @@ void machine_power_off(void)
#endif
while (true) {
__arch_cpu_idle();
__asm__ __volatile__("idle 0" : : : "memory");
}
}
@ -74,6 +74,6 @@ void machine_restart(char *command)
acpi_reboot();
while (true) {
__arch_cpu_idle();
__asm__ __volatile__("idle 0" : : : "memory");
}
}

4
arch/loongarch/kvm/main.c
View File

@ -303,9 +303,9 @@ int kvm_arch_enable_virtualization_cpu(void)
* TOE=0: Trap on Exception.
* TIT=0: Trap on Timer.
*/
if (env & CSR_GCFG_GCIP_ALL)
if (env & CSR_GCFG_GCIP_SECURE)
gcfg |= CSR_GCFG_GCI_SECURE;
if (env & CSR_GCFG_MATC_ROOT)
if (env & CSR_GCFG_MATP_ROOT)
gcfg |= CSR_GCFG_MATC_ROOT;
write_csr_gcfg(gcfg);

2
arch/loongarch/kvm/switch.S
View File

@ -85,7 +85,7 @@
* Guest CRMD comes from separate GCSR_CRMD register
*/
ori t0, zero, CSR_PRMD_PIE
csrxchg t0, t0, LOONGARCH_CSR_PRMD
csrwr t0, LOONGARCH_CSR_PRMD
/* Set PVM bit to setup ertn to guest context */
ori t0, zero, CSR_GSTAT_PVM

3
arch/loongarch/kvm/vcpu.c
View File

@ -1548,9 +1548,6 @@ static int _kvm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
/* Restore timer state regardless */
kvm_restore_timer(vcpu);
/* Control guest page CCA attribute */
change_csr_gcfg(CSR_GCFG_MATC_MASK, CSR_GCFG_MATC_ROOT);
kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
/* Restore hardware PMU CSRs */

2
arch/loongarch/lib/csum.c
View File

@ -25,7 +25,7 @@ unsigned int __no_sanitize_address do_csum(const unsigned char *buff, int len)
const u64 *ptr;
u64 data, sum64 = 0;
if (unlikely(len == 0))
if (unlikely(len <= 0))
return 0;
offset = (unsigned long)buff & 7;

3
arch/loongarch/mm/pageattr.c
View File

@ -3,6 +3,7 @@
* Copyright (C) 2024 Loongson Technology Corporation Limited
*/
#include <linux/memblock.h>
#include <linux/pagewalk.h>
#include <linux/pgtable.h>
#include <asm/set_memory.h>
@ -167,7 +168,7 @@ bool kernel_page_present(struct page *page)
unsigned long addr = (unsigned long)page_address(page);
if (addr < vm_map_base)
return true;
return memblock_is_memory(__pa(addr));
pgd = pgd_offset_k(addr);
if (pgd_none(pgdp_get(pgd)))

4
arch/mips/include/asm/ptrace.h
View File

@ -27,8 +27,8 @@
*/
struct pt_regs {
#ifdef CONFIG_32BIT
/* Pad bytes for argument save space on the stack. */
unsigned long pad0[8];
/* Saved syscall stack arguments; entries 0-3 unused. */
unsigned long args[8];
#endif
/* Saved main processor registers. */

32
arch/mips/include/asm/syscall.h
View File

@ -57,37 +57,21 @@ static inline void mips_syscall_update_nr(struct task_struct *task,
static inline void mips_get_syscall_arg(unsigned long *arg,
struct task_struct *task, struct pt_regs *regs, unsigned int n)
{
unsigned long usp __maybe_unused = regs->regs[29];
#ifdef CONFIG_32BIT
switch (n) {
case 0: case 1: case 2: case 3:
*arg = regs->regs[4 + n];
return;
#ifdef CONFIG_32BIT
case 4: case 5: case 6: case 7:
get_user(*arg, (int *)usp + n);
*arg = regs->args[n];
return;
#endif
#ifdef CONFIG_64BIT
case 4: case 5: case 6: case 7:
#ifdef CONFIG_MIPS32_O32
if (test_tsk_thread_flag(task, TIF_32BIT_REGS))
get_user(*arg, (int *)usp + n);
else
#endif
*arg = regs->regs[4 + n];
return;
#endif
default:
BUG();
}
unreachable();
#else
*arg = regs->regs[4 + n];
if ((IS_ENABLED(CONFIG_MIPS32_O32) &&
test_tsk_thread_flag(task, TIF_32BIT_REGS)))
*arg = (unsigned int)*arg;
#endif
}
static inline long syscall_get_error(struct task_struct *task,

6
arch/mips/kernel/asm-offsets.c
View File

@ -27,6 +27,12 @@ void output_ptreg_defines(void);
void output_ptreg_defines(void)
{
COMMENT("MIPS pt_regs offsets.");
#ifdef CONFIG_32BIT
OFFSET(PT_ARG4, pt_regs, args[4]);
OFFSET(PT_ARG5, pt_regs, args[5]);
OFFSET(PT_ARG6, pt_regs, args[6]);
OFFSET(PT_ARG7, pt_regs, args[7]);
#endif
OFFSET(PT_R0, pt_regs, regs[0]);
OFFSET(PT_R1, pt_regs, regs[1]);
OFFSET(PT_R2, pt_regs, regs[2]);

8
arch/mips/kernel/scall32-o32.S
View File

@ -64,10 +64,10 @@ load_a6: user_lw(t7, 24(t0)) # argument #7 from usp
load_a7: user_lw(t8, 28(t0)) # argument #8 from usp
loads_done:
sw t5, 16(sp) # argument #5 to ksp
sw t6, 20(sp) # argument #6 to ksp
sw t7, 24(sp) # argument #7 to ksp
sw t8, 28(sp) # argument #8 to ksp
sw t5, PT_ARG4(sp) # argument #5 to ksp
sw t6, PT_ARG5(sp) # argument #6 to ksp
sw t7, PT_ARG6(sp) # argument #7 to ksp
sw t8, PT_ARG7(sp) # argument #8 to ksp
.set pop
.section __ex_table,"a"

2
arch/powerpc/sysdev/fsl_msi.c
View File

@ -75,7 +75,7 @@ static void fsl_msi_print_chip(struct irq_data *irqd, struct seq_file *p)
srs = (hwirq >> msi_data->srs_shift) & MSI_SRS_MASK;
cascade_virq = msi_data->cascade_array[srs]->virq;
seq_printf(p, " fsl-msi-%d", cascade_virq);
seq_printf(p, "fsl-msi-%d", cascade_virq);
}

1
arch/s390/configs/debug_defconfig
View File

@ -740,7 +740,6 @@ CONFIG_IMA=y
CONFIG_IMA_DEFAULT_HASH_SHA256=y
CONFIG_IMA_WRITE_POLICY=y
CONFIG_IMA_APPRAISE=y
CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor"
CONFIG_BUG_ON_DATA_CORRUPTION=y
CONFIG_CRYPTO_USER=m
# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set

1
arch/s390/configs/defconfig
View File

@ -725,7 +725,6 @@ CONFIG_IMA=y
CONFIG_IMA_DEFAULT_HASH_SHA256=y
CONFIG_IMA_WRITE_POLICY=y
CONFIG_IMA_APPRAISE=y
CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor"
CONFIG_BUG_ON_DATA_CORRUPTION=y
CONFIG_CRYPTO_FIPS=y
CONFIG_CRYPTO_USER=m

1
arch/s390/configs/zfcpdump_defconfig
View File

@ -62,7 +62,6 @@ CONFIG_ZFCP=y
# CONFIG_INOTIFY_USER is not set
# CONFIG_MISC_FILESYSTEMS is not set
# CONFIG_NETWORK_FILESYSTEMS is not set
CONFIG_LSM="yama,loadpin,safesetid,integrity"
# CONFIG_ZLIB_DFLTCC is not set
CONFIG_XZ_DEC_MICROLZMA=y
CONFIG_PRINTK_TIME=y

6
arch/s390/include/asm/bitops.h
View File

@ -53,7 +53,11 @@ static __always_inline bool arch_test_bit(unsigned long nr, const volatile unsig
unsigned long mask;
int cc;
if (__builtin_constant_p(nr)) {
/*
* With CONFIG_PROFILE_ALL_BRANCHES enabled gcc fails to
* handle __builtin_constant_p() in some cases.
*/
if (!IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && __builtin_constant_p(nr)) {
addr = (const volatile unsigned char *)ptr;
addr += (nr ^ (BITS_PER_LONG - BITS_PER_BYTE)) / BITS_PER_BYTE;
mask = 1UL << (nr & (BITS_PER_BYTE - 1));

20
arch/s390/include/asm/gmap.h
View File

@ -23,7 +23,6 @@
/**
* struct gmap_struct - guest address space
* @list: list head for the mm->context gmap list
* @crst_list: list of all crst tables used in the guest address space
* @mm: pointer to the parent mm_struct
* @guest_to_host: radix tree with guest to host address translation
* @host_to_guest: radix tree with pointer to segment table entries
@ -35,7 +34,6 @@
* @guest_handle: protected virtual machine handle for the ultravisor
* @host_to_rmap: radix tree with gmap_rmap lists
* @children: list of shadow gmap structures
* @pt_list: list of all page tables used in the shadow guest address space
* @shadow_lock: spinlock to protect the shadow gmap list
* @parent: pointer to the parent gmap for shadow guest address spaces
* @orig_asce: ASCE for which the shadow page table has been created
@ -45,7 +43,6 @@
*/
struct gmap {
struct list_head list;
struct list_head crst_list;
struct mm_struct *mm;
struct radix_tree_root guest_to_host;
struct radix_tree_root host_to_guest;
@ -61,7 +58,6 @@ struct gmap {
/* Additional data for shadow guest address spaces */
struct radix_tree_root host_to_rmap;
struct list_head children;
struct list_head pt_list;
spinlock_t shadow_lock;
struct gmap *parent;
unsigned long orig_asce;
@ -106,23 +102,21 @@ struct gmap *gmap_create(struct mm_struct *mm, unsigned long limit);
void gmap_remove(struct gmap *gmap);
struct gmap *gmap_get(struct gmap *gmap);
void gmap_put(struct gmap *gmap);
void gmap_free(struct gmap *gmap);
struct gmap *gmap_alloc(unsigned long limit);
int gmap_map_segment(struct gmap *gmap, unsigned long from,
unsigned long to, unsigned long len);
int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len);
unsigned long __gmap_translate(struct gmap *, unsigned long gaddr);
unsigned long gmap_translate(struct gmap *, unsigned long gaddr);
int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr);
int gmap_fault(struct gmap *, unsigned long gaddr, unsigned int fault_flags);
void gmap_discard(struct gmap *, unsigned long from, unsigned long to);
void __gmap_zap(struct gmap *, unsigned long gaddr);
void gmap_unlink(struct mm_struct *, unsigned long *table, unsigned long vmaddr);
int gmap_read_table(struct gmap *gmap, unsigned long gaddr, unsigned long *val);
struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce,
int edat_level);
int gmap_shadow_valid(struct gmap *sg, unsigned long asce, int edat_level);
void gmap_unshadow(struct gmap *sg);
int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t,
int fake);
int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t,
@ -131,24 +125,22 @@ int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt,
int fake);
int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt,
int fake);
int gmap_shadow_pgt_lookup(struct gmap *sg, unsigned long saddr,
unsigned long *pgt, int *dat_protection, int *fake);
int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte);
void gmap_register_pte_notifier(struct gmap_notifier *);
void gmap_unregister_pte_notifier(struct gmap_notifier *);
int gmap_mprotect_notify(struct gmap *, unsigned long start,
unsigned long len, int prot);
int gmap_protect_one(struct gmap *gmap, unsigned long gaddr, int prot, unsigned long bits);
void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4],
unsigned long gaddr, unsigned long vmaddr);
int s390_disable_cow_sharing(void);
void s390_unlist_old_asce(struct gmap *gmap);
int s390_replace_asce(struct gmap *gmap);
void s390_uv_destroy_pfns(unsigned long count, unsigned long *pfns);
int __s390_uv_destroy_range(struct mm_struct *mm, unsigned long start,
unsigned long end, bool interruptible);
int kvm_s390_wiggle_split_folio(struct mm_struct *mm, struct folio *folio, bool split);
unsigned long *gmap_table_walk(struct gmap *gmap, unsigned long gaddr, int level);
/**
* s390_uv_destroy_range - Destroy a range of pages in the given mm.

6
arch/s390/include/asm/kvm_host.h
View File

@ -30,6 +30,8 @@
#define KVM_S390_ESCA_CPU_SLOTS 248
#define KVM_MAX_VCPUS 255
#define KVM_INTERNAL_MEM_SLOTS 1
/*
* These seem to be used for allocating ->chip in the routing table, which we
* don't use. 1 is as small as we can get to reduce the needed memory. If we
@ -931,12 +933,14 @@ struct sie_page2 {
u8 reserved928[0x1000 - 0x928]; /* 0x0928 */
};
struct vsie_page;
struct kvm_s390_vsie {
struct mutex mutex;
struct radix_tree_root addr_to_page;
int page_count;
int next;
struct page *pages[KVM_MAX_VCPUS];
struct vsie_page *pages[KVM_MAX_VCPUS];
};
struct kvm_s390_gisa_iam {

21
arch/s390/include/asm/pgtable.h
View File

@ -420,9 +420,10 @@ void setup_protection_map(void);
#define PGSTE_HC_BIT 0x0020000000000000UL
#define PGSTE_GR_BIT 0x0004000000000000UL
#define PGSTE_GC_BIT 0x0002000000000000UL
#define PGSTE_UC_BIT 0x0000800000000000UL /* user dirty (migration) */
#define PGSTE_IN_BIT 0x0000400000000000UL /* IPTE notify bit */
#define PGSTE_VSIE_BIT 0x0000200000000000UL /* ref'd in a shadow table */
#define PGSTE_ST2_MASK 0x0000ffff00000000UL
#define PGSTE_UC_BIT 0x0000000000008000UL /* user dirty (migration) */
#define PGSTE_IN_BIT 0x0000000000004000UL /* IPTE notify bit */
#define PGSTE_VSIE_BIT 0x0000000000002000UL /* ref'd in a shadow table */
/* Guest Page State used for virtualization */
#define _PGSTE_GPS_ZERO 0x0000000080000000UL
@ -2007,4 +2008,18 @@ extern void s390_reset_cmma(struct mm_struct *mm);
#define pmd_pgtable(pmd) \
((pgtable_t)__va(pmd_val(pmd) & -sizeof(pte_t)*PTRS_PER_PTE))
static inline unsigned long gmap_pgste_get_pgt_addr(unsigned long *pgt)
{
unsigned long *pgstes, res;
pgstes = pgt + _PAGE_ENTRIES;
res = (pgstes[0] & PGSTE_ST2_MASK) << 16;
res |= pgstes[1] & PGSTE_ST2_MASK;
res |= (pgstes[2] & PGSTE_ST2_MASK) >> 16;
res |= (pgstes[3] & PGSTE_ST2_MASK) >> 32;
return res;
}
#endif /* _S390_PAGE_H */

6
arch/s390/include/asm/uv.h
View File

@ -628,12 +628,12 @@ static inline int is_prot_virt_host(void)
}
int uv_pin_shared(unsigned long paddr);
int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb);
int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr);
int uv_destroy_folio(struct folio *folio);
int uv_destroy_pte(pte_t pte);
int uv_convert_from_secure_pte(pte_t pte);
int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr);
int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb);
int uv_convert_from_secure(unsigned long paddr);
int uv_convert_from_secure_folio(struct folio *folio);
void setup_uv(void);

292
arch/s390/kernel/uv.c
View File

@ -19,19 +19,6 @@
#include <asm/sections.h>
#include <asm/uv.h>
#if !IS_ENABLED(CONFIG_KVM)
unsigned long __gmap_translate(struct gmap *gmap, unsigned long gaddr)
{
return 0;
}
int gmap_fault(struct gmap *gmap, unsigned long gaddr,
unsigned int fault_flags)
{
return 0;
}
#endif
/* the bootdata_preserved fields come from ones in arch/s390/boot/uv.c */
int __bootdata_preserved(prot_virt_guest);
EXPORT_SYMBOL(prot_virt_guest);
@ -159,6 +146,7 @@ int uv_destroy_folio(struct folio *folio)
folio_put(folio);
return rc;
}
EXPORT_SYMBOL(uv_destroy_folio);
/*
* The present PTE still indirectly holds a folio reference through the mapping.
@ -175,7 +163,7 @@ int uv_destroy_pte(pte_t pte)
*
* @paddr: Absolute host address of page to be exported
*/
static int uv_convert_from_secure(unsigned long paddr)
int uv_convert_from_secure(unsigned long paddr)
{
struct uv_cb_cfs uvcb = {
.header.cmd = UVC_CMD_CONV_FROM_SEC_STOR,
@ -187,11 +175,12 @@ static int uv_convert_from_secure(unsigned long paddr)
return -EINVAL;
return 0;
}
EXPORT_SYMBOL_GPL(uv_convert_from_secure);
/*
* The caller must already hold a reference to the folio.
*/
static int uv_convert_from_secure_folio(struct folio *folio)
int uv_convert_from_secure_folio(struct folio *folio)
{
int rc;
@ -206,6 +195,7 @@ static int uv_convert_from_secure_folio(struct folio *folio)
folio_put(folio);
return rc;
}
EXPORT_SYMBOL_GPL(uv_convert_from_secure_folio);
/*
* The present PTE still indirectly holds a folio reference through the mapping.
@ -237,13 +227,33 @@ static int expected_folio_refs(struct folio *folio)
return res;
}
static int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb)
/**
* make_folio_secure() - make a folio secure
* @folio: the folio to make secure
* @uvcb: the uvcb that describes the UVC to be used
*
* The folio @folio will be made secure if possible, @uvcb will be passed
* as-is to the UVC.
*
* Return: 0 on success;
* -EBUSY if the folio is in writeback or has too many references;
* -E2BIG if the folio is large;
* -EAGAIN if the UVC needs to be attempted again;
* -ENXIO if the address is not mapped;
* -EINVAL if the UVC failed for other reasons.
*
* Context: The caller must hold exactly one extra reference on the folio
* (it's the same logic as split_folio())
*/
int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb)
{
int expected, cc = 0;
if (folio_test_large(folio))
return -E2BIG;
if (folio_test_writeback(folio))
return -EAGAIN;
expected = expected_folio_refs(folio);
return -EBUSY;
expected = expected_folio_refs(folio) + 1;
if (!folio_ref_freeze(folio, expected))
return -EBUSY;
set_bit(PG_arch_1, &folio->flags);
@ -267,251 +277,7 @@ static int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb)
return -EAGAIN;
return uvcb->rc == 0x10a ? -ENXIO : -EINVAL;
}
/**
* should_export_before_import - Determine whether an export is needed
* before an import-like operation
* @uvcb: the Ultravisor control block of the UVC to be performed
* @mm: the mm of the process
*
* Returns whether an export is needed before every import-like operation.
* This is needed for shared pages, which don't trigger a secure storage
* exception when accessed from a different guest.
*
* Although considered as one, the Unpin Page UVC is not an actual import,
* so it is not affected.
*
* No export is needed also when there is only one protected VM, because the
* page cannot belong to the wrong VM in that case (there is no "other VM"
* it can belong to).
*
* Return: true if an export is needed before every import, otherwise false.
*/
static bool should_export_before_import(struct uv_cb_header *uvcb, struct mm_struct *mm)
{
/*
* The misc feature indicates, among other things, that importing a
* shared page from a different protected VM will automatically also
* transfer its ownership.
*/
if (uv_has_feature(BIT_UV_FEAT_MISC))
return false;
if (uvcb->cmd == UVC_CMD_UNPIN_PAGE_SHARED)
return false;
return atomic_read(&mm->context.protected_count) > 1;
}
/*
* Drain LRU caches: the local one on first invocation and the ones of all
* CPUs on successive invocations. Returns "true" on the first invocation.
*/
static bool drain_lru(bool *drain_lru_called)
{
/*
* If we have tried a local drain and the folio refcount
* still does not match our expected safe value, try with a
* system wide drain. This is needed if the pagevecs holding
* the page are on a different CPU.
*/
if (*drain_lru_called) {
lru_add_drain_all();
/* We give up here, don't retry immediately. */
return false;
}
/*
* We are here if the folio refcount does not match the
* expected safe value. The main culprits are usually
* pagevecs. With lru_add_drain() we drain the pagevecs
* on the local CPU so that hopefully the refcount will
* reach the expected safe value.
*/
lru_add_drain();
*drain_lru_called = true;
/* The caller should try again immediately */
return true;
}
/*
* Requests the Ultravisor to make a page accessible to a guest.
* If it's brought in the first time, it will be cleared. If
* it has been exported before, it will be decrypted and integrity
* checked.
*/
int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb)
{
struct vm_area_struct *vma;
bool drain_lru_called = false;
spinlock_t *ptelock;
unsigned long uaddr;
struct folio *folio;
pte_t *ptep;
int rc;
again:
rc = -EFAULT;
mmap_read_lock(gmap->mm);
uaddr = __gmap_translate(gmap, gaddr);
if (IS_ERR_VALUE(uaddr))
goto out;
vma = vma_lookup(gmap->mm, uaddr);
if (!vma)
goto out;
/*
* Secure pages cannot be huge and userspace should not combine both.
* In case userspace does it anyway this will result in an -EFAULT for
* the unpack. The guest is thus never reaching secure mode. If
* userspace is playing dirty tricky with mapping huge pages later
* on this will result in a segmentation fault.
*/
if (is_vm_hugetlb_page(vma))
goto out;
rc = -ENXIO;
ptep = get_locked_pte(gmap->mm, uaddr, &ptelock);
if (!ptep)
goto out;
if (pte_present(*ptep) && !(pte_val(*ptep) & _PAGE_INVALID) && pte_write(*ptep)) {
folio = page_folio(pte_page(*ptep));
rc = -EAGAIN;
if (folio_test_large(folio)) {
rc = -E2BIG;
} else if (folio_trylock(folio)) {
if (should_export_before_import(uvcb, gmap->mm))
uv_convert_from_secure(PFN_PHYS(folio_pfn(folio)));
rc = make_folio_secure(folio, uvcb);
folio_unlock(folio);
}
/*
* Once we drop the PTL, the folio may get unmapped and
* freed immediately. We need a temporary reference.
*/
if (rc == -EAGAIN || rc == -E2BIG)
folio_get(folio);
}
pte_unmap_unlock(ptep, ptelock);
out:
mmap_read_unlock(gmap->mm);
switch (rc) {
case -E2BIG:
folio_lock(folio);
rc = split_folio(folio);
folio_unlock(folio);
folio_put(folio);
switch (rc) {
case 0:
/* Splitting succeeded, try again immediately. */
goto again;
case -EAGAIN:
/* Additional folio references. */
if (drain_lru(&drain_lru_called))
goto again;
return -EAGAIN;
case -EBUSY:
/* Unexpected race. */
return -EAGAIN;
}
WARN_ON_ONCE(1);
return -ENXIO;
case -EAGAIN:
/*
* If we are here because the UVC returned busy or partial
* completion, this is just a useless check, but it is safe.
*/
folio_wait_writeback(folio);
folio_put(folio);
return -EAGAIN;
case -EBUSY:
/* Additional folio references. */
if (drain_lru(&drain_lru_called))
goto again;
return -EAGAIN;
case -ENXIO:
if (gmap_fault(gmap, gaddr, FAULT_FLAG_WRITE))
return -EFAULT;
return -EAGAIN;
}
return rc;
}
EXPORT_SYMBOL_GPL(gmap_make_secure);
int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr)
{
struct uv_cb_cts uvcb = {
.header.cmd = UVC_CMD_CONV_TO_SEC_STOR,
.header.len = sizeof(uvcb),
.guest_handle = gmap->guest_handle,
.gaddr = gaddr,
};
return gmap_make_secure(gmap, gaddr, &uvcb);
}
EXPORT_SYMBOL_GPL(gmap_convert_to_secure);
/**
* gmap_destroy_page - Destroy a guest page.
* @gmap: the gmap of the guest
* @gaddr: the guest address to destroy
*
* An attempt will be made to destroy the given guest page. If the attempt
* fails, an attempt is made to export the page. If both attempts fail, an
* appropriate error is returned.
*/
int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr)
{
struct vm_area_struct *vma;
struct folio_walk fw;
unsigned long uaddr;
struct folio *folio;
int rc;
rc = -EFAULT;
mmap_read_lock(gmap->mm);
uaddr = __gmap_translate(gmap, gaddr);
if (IS_ERR_VALUE(uaddr))
goto out;
vma = vma_lookup(gmap->mm, uaddr);
if (!vma)
goto out;
/*
* Huge pages should not be able to become secure
*/
if (is_vm_hugetlb_page(vma))
goto out;
rc = 0;
folio = folio_walk_start(&fw, vma, uaddr, 0);
if (!folio)
goto out;
/*
* See gmap_make_secure(): large folios cannot be secure. Small
* folio implies FW_LEVEL_PTE.
*/
if (folio_test_large(folio) || !pte_write(fw.pte))
goto out_walk_end;
rc = uv_destroy_folio(folio);
/*
* Fault handlers can race; it is possible that two CPUs will fault
* on the same secure page. One CPU can destroy the page, reboot,
* re-enter secure mode and import it, while the second CPU was
* stuck at the beginning of the handler. At some point the second
* CPU will be able to progress, and it will not be able to destroy
* the page. In that case we do not want to terminate the process,
* we instead try to export the page.
*/
if (rc)
rc = uv_convert_from_secure_folio(folio);
out_walk_end:
folio_walk_end(&fw, vma);
out:
mmap_read_unlock(gmap->mm);
return rc;
}
EXPORT_SYMBOL_GPL(gmap_destroy_page);
EXPORT_SYMBOL_GPL(make_folio_secure);
/*
* To be called with the folio locked or with an extra reference! This will

2
arch/s390/kvm/Makefile
View File

@ -8,7 +8,7 @@ include $(srctree)/virt/kvm/Makefile.kvm
ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
kvm-y += kvm-s390.o intercept.o interrupt.o priv.o sigp.o
kvm-y += diag.o gaccess.o guestdbg.o vsie.o pv.o
kvm-y += diag.o gaccess.o guestdbg.o vsie.o pv.o gmap.o gmap-vsie.o
kvm-$(CONFIG_VFIO_PCI_ZDEV_KVM) += pci.o
obj-$(CONFIG_KVM) += kvm.o

44
arch/s390/kvm/gaccess.c
View File

@ -16,6 +16,7 @@
#include <asm/gmap.h>
#include <asm/dat-bits.h>
#include "kvm-s390.h"
#include "gmap.h"
#include "gaccess.h"
/*
@ -1392,6 +1393,44 @@ shadow_pgt:
return 0;
}
/**
* shadow_pgt_lookup() - find a shadow page table
* @sg: pointer to the shadow guest address space structure
* @saddr: the address in the shadow aguest address space
* @pgt: parent gmap address of the page table to get shadowed
* @dat_protection: if the pgtable is marked as protected by dat
* @fake: pgt references contiguous guest memory block, not a pgtable
*
* Returns 0 if the shadow page table was found and -EAGAIN if the page
* table was not found.
*
* Called with sg->mm->mmap_lock in read.
*/
static int shadow_pgt_lookup(struct gmap *sg, unsigned long saddr, unsigned long *pgt,
int *dat_protection, int *fake)
{
unsigned long pt_index;
unsigned long *table;
struct page *page;
int rc;
spin_lock(&sg->guest_table_lock);
table = gmap_table_walk(sg, saddr, 1); /* get segment pointer */
if (table && !(*table & _SEGMENT_ENTRY_INVALID)) {
/* Shadow page tables are full pages (pte+pgste) */
page = pfn_to_page(*table >> PAGE_SHIFT);
pt_index = gmap_pgste_get_pgt_addr(page_to_virt(page));
*pgt = pt_index & ~GMAP_SHADOW_FAKE_TABLE;
*dat_protection = !!(*table & _SEGMENT_ENTRY_PROTECT);
*fake = !!(pt_index & GMAP_SHADOW_FAKE_TABLE);
rc = 0;
} else {
rc = -EAGAIN;
}
spin_unlock(&sg->guest_table_lock);
return rc;
}
/**
* kvm_s390_shadow_fault - handle fault on a shadow page table
* @vcpu: virtual cpu
@ -1415,6 +1454,9 @@ int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg,
int dat_protection, fake;
int rc;
if (KVM_BUG_ON(!gmap_is_shadow(sg), vcpu->kvm))
return -EFAULT;
mmap_read_lock(sg->mm);
/*
* We don't want any guest-2 tables to change - so the parent
@ -1423,7 +1465,7 @@ int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg,
*/
ipte_lock(vcpu->kvm);
rc = gmap_shadow_pgt_lookup(sg, saddr, &pgt, &dat_protection, &fake);
rc = shadow_pgt_lookup(sg, saddr, &pgt, &dat_protection, &fake);
if (rc)
rc = kvm_s390_shadow_tables(sg, saddr, &pgt, &dat_protection,
&fake);

142
arch/s390/kvm/gmap-vsie.c Normal file
View File

@ -0,0 +1,142 @@
// SPDX-License-Identifier: GPL-2.0
/*
* Guest memory management for KVM/s390 nested VMs.
*
* Copyright IBM Corp. 2008, 2020, 2024
*
* Author(s): Claudio Imbrenda <imbrenda@linux.ibm.com>
* Martin Schwidefsky <schwidefsky@de.ibm.com>
* David Hildenbrand <david@redhat.com>
* Janosch Frank <frankja@linux.vnet.ibm.com>
*/
#include <linux/compiler.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/pgtable.h>
#include <linux/pagemap.h>
#include <linux/mman.h>
#include <asm/lowcore.h>
#include <asm/gmap.h>
#include <asm/uv.h>
#include "kvm-s390.h"
#include "gmap.h"
/**
* gmap_find_shadow - find a specific asce in the list of shadow tables
* @parent: pointer to the parent gmap
* @asce: ASCE for which the shadow table is created
* @edat_level: edat level to be used for the shadow translation
*
* Returns the pointer to a gmap if a shadow table with the given asce is
* already available, ERR_PTR(-EAGAIN) if another one is just being created,
* otherwise NULL
*
* Context: Called with parent->shadow_lock held
*/
static struct gmap *gmap_find_shadow(struct gmap *parent, unsigned long asce, int edat_level)
{
struct gmap *sg;
lockdep_assert_held(&parent->shadow_lock);
list_for_each_entry(sg, &parent->children, list) {
if (!gmap_shadow_valid(sg, asce, edat_level))
continue;
if (!sg->initialized)
return ERR_PTR(-EAGAIN);
refcount_inc(&sg->ref_count);
return sg;
}
return NULL;
}
/**
* gmap_shadow - create/find a shadow guest address space
* @parent: pointer to the parent gmap
* @asce: ASCE for which the shadow table is created
* @edat_level: edat level to be used for the shadow translation
*
* The pages of the top level page table referred by the asce parameter
* will be set to read-only and marked in the PGSTEs of the kvm process.
* The shadow table will be removed automatically on any change to the
* PTE mapping for the source table.
*
* Returns a guest address space structure, ERR_PTR(-ENOMEM) if out of memory,
* ERR_PTR(-EAGAIN) if the caller has to retry and ERR_PTR(-EFAULT) if the
* parent gmap table could not be protected.
*/
struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, int edat_level)
{
struct gmap *sg, *new;
unsigned long limit;
int rc;
if (KVM_BUG_ON(parent->mm->context.allow_gmap_hpage_1m, (struct kvm *)parent->private) ||
KVM_BUG_ON(gmap_is_shadow(parent), (struct kvm *)parent->private))
return ERR_PTR(-EFAULT);
spin_lock(&parent->shadow_lock);
sg = gmap_find_shadow(parent, asce, edat_level);
spin_unlock(&parent->shadow_lock);
if (sg)
return sg;
/* Create a new shadow gmap */
limit = -1UL >> (33 - (((asce & _ASCE_TYPE_MASK) >> 2) * 11));
if (asce & _ASCE_REAL_SPACE)
limit = -1UL;
new = gmap_alloc(limit);
if (!new)
return ERR_PTR(-ENOMEM);
new->mm = parent->mm;
new->parent = gmap_get(parent);
new->private = parent->private;
new->orig_asce = asce;
new->edat_level = edat_level;
new->initialized = false;
spin_lock(&parent->shadow_lock);
/* Recheck if another CPU created the same shadow */
sg = gmap_find_shadow(parent, asce, edat_level);
if (sg) {
spin_unlock(&parent->shadow_lock);
gmap_free(new);
return sg;
}
if (asce & _ASCE_REAL_SPACE) {
/* only allow one real-space gmap shadow */
list_for_each_entry(sg, &parent->children, list) {
if (sg->orig_asce & _ASCE_REAL_SPACE) {
spin_lock(&sg->guest_table_lock);
gmap_unshadow(sg);
spin_unlock(&sg->guest_table_lock);
list_del(&sg->list);
gmap_put(sg);
break;
}
}
}
refcount_set(&new->ref_count, 2);
list_add(&new->list, &parent->children);
if (asce & _ASCE_REAL_SPACE) {
/* nothing to protect, return right away */
new->initialized = true;
spin_unlock(&parent->shadow_lock);
return new;
}
spin_unlock(&parent->shadow_lock);
/* protect after insertion, so it will get properly invalidated */
mmap_read_lock(parent->mm);
rc = __kvm_s390_mprotect_many(parent, asce & _ASCE_ORIGIN,
((asce & _ASCE_TABLE_LENGTH) + 1),
PROT_READ, GMAP_NOTIFY_SHADOW);
mmap_read_unlock(parent->mm);
spin_lock(&parent->shadow_lock);
new->initialized = true;
if (rc) {
list_del(&new->list);
gmap_free(new);
new = ERR_PTR(rc);
}
spin_unlock(&parent->shadow_lock);
return new;
}

212
arch/s390/kvm/gmap.c Normal file
View File

@ -0,0 +1,212 @@
// SPDX-License-Identifier: GPL-2.0
/*
* Guest memory management for KVM/s390
*
* Copyright IBM Corp. 2008, 2020, 2024
*
* Author(s): Claudio Imbrenda <imbrenda@linux.ibm.com>
* Martin Schwidefsky <schwidefsky@de.ibm.com>
* David Hildenbrand <david@redhat.com>
* Janosch Frank <frankja@linux.vnet.ibm.com>
*/
#include <linux/compiler.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/pgtable.h>
#include <linux/pagemap.h>
#include <asm/lowcore.h>
#include <asm/gmap.h>
#include <asm/uv.h>
#include "gmap.h"
/**
* should_export_before_import - Determine whether an export is needed
* before an import-like operation
* @uvcb: the Ultravisor control block of the UVC to be performed
* @mm: the mm of the process
*
* Returns whether an export is needed before every import-like operation.
* This is needed for shared pages, which don't trigger a secure storage
* exception when accessed from a different guest.
*
* Although considered as one, the Unpin Page UVC is not an actual import,
* so it is not affected.
*
* No export is needed also when there is only one protected VM, because the
* page cannot belong to the wrong VM in that case (there is no "other VM"
* it can belong to).
*
* Return: true if an export is needed before every import, otherwise false.
*/
static bool should_export_before_import(struct uv_cb_header *uvcb, struct mm_struct *mm)
{
/*
* The misc feature indicates, among other things, that importing a
* shared page from a different protected VM will automatically also
* transfer its ownership.
*/
if (uv_has_feature(BIT_UV_FEAT_MISC))
return false;
if (uvcb->cmd == UVC_CMD_UNPIN_PAGE_SHARED)
return false;
return atomic_read(&mm->context.protected_count) > 1;
}
static int __gmap_make_secure(struct gmap *gmap, struct page *page, void *uvcb)
{
struct folio *folio = page_folio(page);
int rc;
/*
* Secure pages cannot be huge and userspace should not combine both.
* In case userspace does it anyway this will result in an -EFAULT for
* the unpack. The guest is thus never reaching secure mode.
* If userspace plays dirty tricks and decides to map huge pages at a
* later point in time, it will receive a segmentation fault or
* KVM_RUN will return -EFAULT.
*/
if (folio_test_hugetlb(folio))
return -EFAULT;
if (folio_test_large(folio)) {
mmap_read_unlock(gmap->mm);
rc = kvm_s390_wiggle_split_folio(gmap->mm, folio, true);
mmap_read_lock(gmap->mm);
if (rc)
return rc;
folio = page_folio(page);
}
if (!folio_trylock(folio))
return -EAGAIN;
if (should_export_before_import(uvcb, gmap->mm))
uv_convert_from_secure(folio_to_phys(folio));
rc = make_folio_secure(folio, uvcb);
folio_unlock(folio);
/*
* In theory a race is possible and the folio might have become
* large again before the folio_trylock() above. In that case, no
* action is performed and -EAGAIN is returned; the callers will
* have to try again later.
* In most cases this implies running the VM again, getting the same
* exception again, and make another attempt in this function.
* This is expected to happen extremely rarely.
*/
if (rc == -E2BIG)
return -EAGAIN;
/* The folio has too many references, try to shake some off */
if (rc == -EBUSY) {
mmap_read_unlock(gmap->mm);
kvm_s390_wiggle_split_folio(gmap->mm, folio, false);
mmap_read_lock(gmap->mm);
return -EAGAIN;
}
return rc;
}
/**
* gmap_make_secure() - make one guest page secure
* @gmap: the guest gmap
* @gaddr: the guest address that needs to be made secure
* @uvcb: the UVCB specifying which operation needs to be performed
*
* Context: needs to be called with kvm->srcu held.
* Return: 0 on success, < 0 in case of error (see __gmap_make_secure()).
*/
int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb)
{
struct kvm *kvm = gmap->private;
struct page *page;
int rc = 0;
lockdep_assert_held(&kvm->srcu);
page = gfn_to_page(kvm, gpa_to_gfn(gaddr));
mmap_read_lock(gmap->mm);
if (page)
rc = __gmap_make_secure(gmap, page, uvcb);
kvm_release_page_clean(page);
mmap_read_unlock(gmap->mm);
return rc;
}
int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr)
{
struct uv_cb_cts uvcb = {
.header.cmd = UVC_CMD_CONV_TO_SEC_STOR,
.header.len = sizeof(uvcb),
.guest_handle = gmap->guest_handle,
.gaddr = gaddr,
};
return gmap_make_secure(gmap, gaddr, &uvcb);
}
/**
* __gmap_destroy_page() - Destroy a guest page.
* @gmap: the gmap of the guest
* @page: the page to destroy
*
* An attempt will be made to destroy the given guest page. If the attempt
* fails, an attempt is made to export the page. If both attempts fail, an
* appropriate error is returned.
*
* Context: must be called holding the mm lock for gmap->mm
*/
static int __gmap_destroy_page(struct gmap *gmap, struct page *page)
{
struct folio *folio = page_folio(page);
int rc;
/*
* See gmap_make_secure(): large folios cannot be secure. Small
* folio implies FW_LEVEL_PTE.
*/
if (folio_test_large(folio))
return -EFAULT;
rc = uv_destroy_folio(folio);
/*
* Fault handlers can race; it is possible that two CPUs will fault
* on the same secure page. One CPU can destroy the page, reboot,
* re-enter secure mode and import it, while the second CPU was
* stuck at the beginning of the handler. At some point the second
* CPU will be able to progress, and it will not be able to destroy
* the page. In that case we do not want to terminate the process,
* we instead try to export the page.
*/
if (rc)
rc = uv_convert_from_secure_folio(folio);
return rc;
}
/**
* gmap_destroy_page() - Destroy a guest page.
* @gmap: the gmap of the guest
* @gaddr: the guest address to destroy
*
* An attempt will be made to destroy the given guest page. If the attempt
* fails, an attempt is made to export the page. If both attempts fail, an
* appropriate error is returned.
*
* Context: may sleep.
*/
int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr)
{
struct page *page;
int rc = 0;
mmap_read_lock(gmap->mm);
page = gfn_to_page(gmap->private, gpa_to_gfn(gaddr));
if (page)
rc = __gmap_destroy_page(gmap, page);
kvm_release_page_clean(page);
mmap_read_unlock(gmap->mm);
return rc;
}

39
arch/s390/kvm/gmap.h Normal file
View File

@ -0,0 +1,39 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
* KVM guest address space mapping code
*
* Copyright IBM Corp. 2007, 2016, 2025
* Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
* Claudio Imbrenda <imbrenda@linux.ibm.com>
*/
#ifndef ARCH_KVM_S390_GMAP_H
#define ARCH_KVM_S390_GMAP_H
#define GMAP_SHADOW_FAKE_TABLE 1ULL
int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb);
int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr);
int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr);
struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, int edat_level);
/**
* gmap_shadow_valid - check if a shadow guest address space matches the
* given properties and is still valid
* @sg: pointer to the shadow guest address space structure
* @asce: ASCE for which the shadow table is requested
* @edat_level: edat level to be used for the shadow translation
*
* Returns 1 if the gmap shadow is still valid and matches the given
* properties, the caller can continue using it. Returns 0 otherwise, the
* caller has to request a new shadow gmap in this case.
*
*/
static inline int gmap_shadow_valid(struct gmap *sg, unsigned long asce, int edat_level)
{
if (sg->removed)
return 0;
return sg->orig_asce == asce && sg->edat_level == edat_level;
}
#endif

7
arch/s390/kvm/intercept.c
View File

@ -21,6 +21,7 @@
#include "gaccess.h"
#include "trace.h"
#include "trace-s390.h"
#include "gmap.h"
u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu)
{
@ -367,7 +368,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
reg2, &srcaddr, GACC_FETCH, 0);
if (rc)
return kvm_s390_inject_prog_cond(vcpu, rc);
rc = gmap_fault(vcpu->arch.gmap, srcaddr, 0);
rc = kvm_s390_handle_dat_fault(vcpu, srcaddr, 0);
if (rc != 0)
return rc;
@ -376,7 +377,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu)
reg1, &dstaddr, GACC_STORE, 0);
if (rc)
return kvm_s390_inject_prog_cond(vcpu, rc);
rc = gmap_fault(vcpu->arch.gmap, dstaddr, FAULT_FLAG_WRITE);
rc = kvm_s390_handle_dat_fault(vcpu, dstaddr, FOLL_WRITE);
if (rc != 0)
return rc;
@ -549,7 +550,7 @@ static int handle_pv_uvc(struct kvm_vcpu *vcpu)
* If the unpin did not succeed, the guest will exit again for the UVC
* and we will retry the unpin.
*/
if (rc == -EINVAL)
if (rc == -EINVAL || rc == -ENXIO)
return 0;
/*
* If we got -EAGAIN here, we simply return it. It will eventually

19
arch/s390/kvm/interrupt.c
View File

@ -2893,7 +2893,8 @@ int kvm_set_routing_entry(struct kvm *kvm,
struct kvm_kernel_irq_routing_entry *e,
const struct kvm_irq_routing_entry *ue)
{
u64 uaddr;
u64 uaddr_s, uaddr_i;
int idx;
switch (ue->type) {
/* we store the userspace addresses instead of the guest addresses */
@ -2901,14 +2902,16 @@ int kvm_set_routing_entry(struct kvm *kvm,
if (kvm_is_ucontrol(kvm))
return -EINVAL;
e->set = set_adapter_int;
uaddr = gmap_translate(kvm->arch.gmap, ue->u.adapter.summary_addr);
if (uaddr == -EFAULT)
idx = srcu_read_lock(&kvm->srcu);
uaddr_s = gpa_to_hva(kvm, ue->u.adapter.summary_addr);
uaddr_i = gpa_to_hva(kvm, ue->u.adapter.ind_addr);
srcu_read_unlock(&kvm->srcu, idx);
if (kvm_is_error_hva(uaddr_s) || kvm_is_error_hva(uaddr_i))
return -EFAULT;
e->adapter.summary_addr = uaddr;
uaddr = gmap_translate(kvm->arch.gmap, ue->u.adapter.ind_addr);
if (uaddr == -EFAULT)
return -EFAULT;
e->adapter.ind_addr = uaddr;
e->adapter.summary_addr = uaddr_s;
e->adapter.ind_addr = uaddr_i;
e->adapter.summary_offset = ue->u.adapter.summary_offset;
e->adapter.ind_offset = ue->u.adapter.ind_offset;
e->adapter.adapter_id = ue->u.adapter.adapter_id;

237
arch/s390/kvm/kvm-s390.c
View File

@ -50,6 +50,7 @@
#include "kvm-s390.h"
#include "gaccess.h"
#include "pci.h"
#include "gmap.h"
#define CREATE_TRACE_POINTS
#include "trace.h"
@ -3428,8 +3429,20 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
VM_EVENT(kvm, 3, "vm created with type %lu", type);
if (type & KVM_VM_S390_UCONTROL) {
struct kvm_userspace_memory_region2 fake_memslot = {
.slot = KVM_S390_UCONTROL_MEMSLOT,
.guest_phys_addr = 0,
.userspace_addr = 0,
.memory_size = ALIGN_DOWN(TASK_SIZE, _SEGMENT_SIZE),
.flags = 0,
};
kvm->arch.gmap = NULL;
kvm->arch.mem_limit = KVM_S390_NO_MEM_LIMIT;
/* one flat fake memslot covering the whole address-space */
mutex_lock(&kvm->slots_lock);
KVM_BUG_ON(kvm_set_internal_memslot(kvm, &fake_memslot), kvm);
mutex_unlock(&kvm->slots_lock);
} else {
if (sclp.hamax == U64_MAX)
kvm->arch.mem_limit = TASK_SIZE_MAX;
@ -4498,6 +4511,75 @@ static bool ibs_enabled(struct kvm_vcpu *vcpu)
return kvm_s390_test_cpuflags(vcpu, CPUSTAT_IBS);
}
static int __kvm_s390_fixup_fault_sync(struct gmap *gmap, gpa_t gaddr, unsigned int flags)
{
struct kvm *kvm = gmap->private;
gfn_t gfn = gpa_to_gfn(gaddr);
bool unlocked;
hva_t vmaddr;
gpa_t tmp;
int rc;
if (kvm_is_ucontrol(kvm)) {
tmp = __gmap_translate(gmap, gaddr);
gfn = gpa_to_gfn(tmp);
}
vmaddr = gfn_to_hva(kvm, gfn);
rc = fixup_user_fault(gmap->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked);
if (!rc)
rc = __gmap_link(gmap, gaddr, vmaddr);
return rc;
}
/**
* __kvm_s390_mprotect_many() - Apply specified protection to guest pages
* @gmap: the gmap of the guest
* @gpa: the starting guest address
* @npages: how many pages to protect
* @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
* @bits: pgste notification bits to set
*
* Returns: 0 in case of success, < 0 in case of error - see gmap_protect_one()
*
* Context: kvm->srcu and gmap->mm need to be held in read mode
*/
int __kvm_s390_mprotect_many(struct gmap *gmap, gpa_t gpa, u8 npages, unsigned int prot,
unsigned long bits)
{
unsigned int fault_flag = (prot & PROT_WRITE) ? FAULT_FLAG_WRITE : 0;
gpa_t end = gpa + npages * PAGE_SIZE;
int rc;
for (; gpa < end; gpa = ALIGN(gpa + 1, rc)) {
rc = gmap_protect_one(gmap, gpa, prot, bits);
if (rc == -EAGAIN) {
__kvm_s390_fixup_fault_sync(gmap, gpa, fault_flag);
rc = gmap_protect_one(gmap, gpa, prot, bits);
}
if (rc < 0)
return rc;
}
return 0;
}
static int kvm_s390_mprotect_notify_prefix(struct kvm_vcpu *vcpu)
{
gpa_t gaddr = kvm_s390_get_prefix(vcpu);
int idx, rc;
idx = srcu_read_lock(&vcpu->kvm->srcu);
mmap_read_lock(vcpu->arch.gmap->mm);
rc = __kvm_s390_mprotect_many(vcpu->arch.gmap, gaddr, 2, PROT_WRITE, GMAP_NOTIFY_MPROT);
mmap_read_unlock(vcpu->arch.gmap->mm);
srcu_read_unlock(&vcpu->kvm->srcu, idx);
return rc;
}
static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
{
retry:
@ -4513,9 +4595,8 @@ retry:
*/
if (kvm_check_request(KVM_REQ_REFRESH_GUEST_PREFIX, vcpu)) {
int rc;
rc = gmap_mprotect_notify(vcpu->arch.gmap,
kvm_s390_get_prefix(vcpu),
PAGE_SIZE * 2, PROT_WRITE);
rc = kvm_s390_mprotect_notify_prefix(vcpu);
if (rc) {
kvm_make_request(KVM_REQ_REFRESH_GUEST_PREFIX, vcpu);
return rc;
@ -4766,11 +4847,111 @@ static int vcpu_post_run_addressing_exception(struct kvm_vcpu *vcpu)
return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
}
static void kvm_s390_assert_primary_as(struct kvm_vcpu *vcpu)
{
KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm,
"Unexpected program interrupt 0x%x, TEID 0x%016lx",
current->thread.gmap_int_code, current->thread.gmap_teid.val);
}
/*
* __kvm_s390_handle_dat_fault() - handle a dat fault for the gmap of a vcpu
* @vcpu: the vCPU whose gmap is to be fixed up
* @gfn: the guest frame number used for memslots (including fake memslots)
* @gaddr: the gmap address, does not have to match @gfn for ucontrol gmaps
* @flags: FOLL_* flags
*
* Return: 0 on success, < 0 in case of error.
* Context: The mm lock must not be held before calling. May sleep.
*/
int __kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr, unsigned int flags)
{
struct kvm_memory_slot *slot;
unsigned int fault_flags;
bool writable, unlocked;
unsigned long vmaddr;
struct page *page;
kvm_pfn_t pfn;
int rc;
slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
return vcpu_post_run_addressing_exception(vcpu);
fault_flags = flags & FOLL_WRITE ? FAULT_FLAG_WRITE : 0;
if (vcpu->arch.gmap->pfault_enabled)
flags |= FOLL_NOWAIT;
vmaddr = __gfn_to_hva_memslot(slot, gfn);
try_again:
pfn = __kvm_faultin_pfn(slot, gfn, flags, &writable, &page);
/* Access outside memory, inject addressing exception */
if (is_noslot_pfn(pfn))
return vcpu_post_run_addressing_exception(vcpu);
/* Signal pending: try again */
if (pfn == KVM_PFN_ERR_SIGPENDING)
return -EAGAIN;
/* Needs I/O, try to setup async pfault (only possible with FOLL_NOWAIT) */
if (pfn == KVM_PFN_ERR_NEEDS_IO) {
trace_kvm_s390_major_guest_pfault(vcpu);
if (kvm_arch_setup_async_pf(vcpu))
return 0;
vcpu->stat.pfault_sync++;
/* Could not setup async pfault, try again synchronously */
flags &= ~FOLL_NOWAIT;
goto try_again;
}
/* Any other error */
if (is_error_pfn(pfn))
return -EFAULT;
/* Success */
mmap_read_lock(vcpu->arch.gmap->mm);
/* Mark the userspace PTEs as young and/or dirty, to avoid page fault loops */
rc = fixup_user_fault(vcpu->arch.gmap->mm, vmaddr, fault_flags, &unlocked);
if (!rc)
rc = __gmap_link(vcpu->arch.gmap, gaddr, vmaddr);
scoped_guard(spinlock, &vcpu->kvm->mmu_lock) {
kvm_release_faultin_page(vcpu->kvm, page, false, writable);
}
mmap_read_unlock(vcpu->arch.gmap->mm);
return rc;
}
static int vcpu_dat_fault_handler(struct kvm_vcpu *vcpu, unsigned long gaddr, unsigned int flags)
{
unsigned long gaddr_tmp;
gfn_t gfn;
gfn = gpa_to_gfn(gaddr);
if (kvm_is_ucontrol(vcpu->kvm)) {
/*
* This translates the per-vCPU guest address into a
* fake guest address, which can then be used with the
* fake memslots that are identity mapping userspace.
* This allows ucontrol VMs to use the normal fault
* resolution path, like normal VMs.
*/
mmap_read_lock(vcpu->arch.gmap->mm);
gaddr_tmp = __gmap_translate(vcpu->arch.gmap, gaddr);
mmap_read_unlock(vcpu->arch.gmap->mm);
if (gaddr_tmp == -EFAULT) {
vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL;
vcpu->run->s390_ucontrol.trans_exc_code = gaddr;
vcpu->run->s390_ucontrol.pgm_code = PGM_SEGMENT_TRANSLATION;
return -EREMOTE;
}
gfn = gpa_to_gfn(gaddr_tmp);
}
return __kvm_s390_handle_dat_fault(vcpu, gfn, gaddr, flags);
}
static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
{
unsigned int flags = 0;
unsigned long gaddr;
int rc = 0;
gaddr = current->thread.gmap_teid.addr * PAGE_SIZE;
if (kvm_s390_cur_gmap_fault_is_write())
@ -4781,9 +4962,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
vcpu->stat.exit_null++;
break;
case PGM_NON_SECURE_STORAGE_ACCESS:
KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm,
"Unexpected program interrupt 0x%x, TEID 0x%016lx",
current->thread.gmap_int_code, current->thread.gmap_teid.val);
kvm_s390_assert_primary_as(vcpu);
/*
* This is normal operation; a page belonging to a protected
* guest has not been imported yet. Try to import the page into
@ -4794,9 +4973,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
break;
case PGM_SECURE_STORAGE_ACCESS:
case PGM_SECURE_STORAGE_VIOLATION:
KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm,
"Unexpected program interrupt 0x%x, TEID 0x%016lx",
current->thread.gmap_int_code, current->thread.gmap_teid.val);
kvm_s390_assert_primary_as(vcpu);
/*
* This can happen after a reboot with asynchronous teardown;
* the new guest (normal or protected) will run on top of the
@ -4825,40 +5002,15 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
case PGM_REGION_FIRST_TRANS:
case PGM_REGION_SECOND_TRANS:
case PGM_REGION_THIRD_TRANS:
KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm,
"Unexpected program interrupt 0x%x, TEID 0x%016lx",
current->thread.gmap_int_code, current->thread.gmap_teid.val);
if (vcpu->arch.gmap->pfault_enabled) {
rc = gmap_fault(vcpu->arch.gmap, gaddr, flags | FAULT_FLAG_RETRY_NOWAIT);
if (rc == -EFAULT)
return vcpu_post_run_addressing_exception(vcpu);
if (rc == -EAGAIN) {
trace_kvm_s390_major_guest_pfault(vcpu);
if (kvm_arch_setup_async_pf(vcpu))
return 0;
vcpu->stat.pfault_sync++;
} else {
return rc;
}
}
rc = gmap_fault(vcpu->arch.gmap, gaddr, flags);
if (rc == -EFAULT) {
if (kvm_is_ucontrol(vcpu->kvm)) {
vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL;
vcpu->run->s390_ucontrol.trans_exc_code = gaddr;
vcpu->run->s390_ucontrol.pgm_code = 0x10;
return -EREMOTE;
}
return vcpu_post_run_addressing_exception(vcpu);
}
break;
kvm_s390_assert_primary_as(vcpu);
return vcpu_dat_fault_handler(vcpu, gaddr, flags);
default:
KVM_BUG(1, vcpu->kvm, "Unexpected program interrupt 0x%x, TEID 0x%016lx",
current->thread.gmap_int_code, current->thread.gmap_teid.val);
send_sig(SIGSEGV, current, 0);
break;
}
return rc;
return 0;
}
static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
@ -5737,7 +5889,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
}
#endif
case KVM_S390_VCPU_FAULT: {
r = gmap_fault(vcpu->arch.gmap, arg, 0);
idx = srcu_read_lock(&vcpu->kvm->srcu);
r = vcpu_dat_fault_handler(vcpu, arg, 0);
srcu_read_unlock(&vcpu->kvm->srcu, idx);
break;
}
case KVM_ENABLE_CAP:
@ -5853,7 +6007,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
{
gpa_t size;
if (kvm_is_ucontrol(kvm))
if (kvm_is_ucontrol(kvm) && new->id < KVM_USER_MEM_SLOTS)
return -EINVAL;
/* When we are protected, we should not change the memory slots */
@ -5905,6 +6059,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
{
int rc = 0;
if (kvm_is_ucontrol(kvm))
return;
switch (change) {
case KVM_MR_DELETE:
rc = gmap_unmap_segment(kvm->arch.gmap, old->base_gfn * PAGE_SIZE,

19
arch/s390/kvm/kvm-s390.h
View File

@ -20,6 +20,8 @@
#include <asm/processor.h>
#include <asm/sclp.h>
#define KVM_S390_UCONTROL_MEMSLOT (KVM_USER_MEM_SLOTS + 0)
static inline void kvm_s390_fpu_store(struct kvm_run *run)
{
fpu_stfpc(&run->s.regs.fpc);
@ -279,6 +281,15 @@ static inline u32 kvm_s390_get_gisa_desc(struct kvm *kvm)
return gd;
}
static inline hva_t gpa_to_hva(struct kvm *kvm, gpa_t gpa)
{
hva_t hva = gfn_to_hva(kvm, gpa_to_gfn(gpa));
if (!kvm_is_error_hva(hva))
hva |= offset_in_page(gpa);
return hva;
}
/* implemented in pv.c */
int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc);
int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc);
@ -408,6 +419,14 @@ void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu);
void kvm_s390_set_cpu_timer(struct kvm_vcpu *vcpu, __u64 cputm);
__u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu);
int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rc, u16 *rrc);
int __kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr, unsigned int flags);
int __kvm_s390_mprotect_many(struct gmap *gmap, gpa_t gpa, u8 npages, unsigned int prot,
unsigned long bits);
static inline int kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gpa_t gaddr, unsigned int flags)
{
return __kvm_s390_handle_dat_fault(vcpu, gpa_to_gfn(gaddr), gaddr, flags);
}
/* implemented in diag.c */
int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);

21
arch/s390/kvm/pv.c
View File

@ -17,6 +17,7 @@
#include <linux/sched/mm.h>
#include <linux/mmu_notifier.h>
#include "kvm-s390.h"
#include "gmap.h"
bool kvm_s390_pv_is_protected(struct kvm *kvm)
{
@ -638,10 +639,28 @@ static int unpack_one(struct kvm *kvm, unsigned long addr, u64 tweak,
.tweak[1] = offset,
};
int ret = gmap_make_secure(kvm->arch.gmap, addr, &uvcb);
unsigned long vmaddr;
bool unlocked;
*rc = uvcb.header.rc;
*rrc = uvcb.header.rrc;
if (ret == -ENXIO) {
mmap_read_lock(kvm->mm);
vmaddr = gfn_to_hva(kvm, gpa_to_gfn(addr));
if (kvm_is_error_hva(vmaddr)) {
ret = -EFAULT;
} else {
ret = fixup_user_fault(kvm->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked);
if (!ret)
ret = __gmap_link(kvm->arch.gmap, addr, vmaddr);
}
mmap_read_unlock(kvm->mm);
if (!ret)
return -EAGAIN;
return ret;
}
if (ret && ret != -EAGAIN)
KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: failed addr %llx with rc %x rrc %x",
uvcb.gaddr, *rc, *rrc);
@ -660,6 +679,8 @@ int kvm_s390_pv_unpack(struct kvm *kvm, unsigned long addr, unsigned long size,
KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: start addr %lx size %lx",
addr, size);
guard(srcu)(&kvm->srcu);
while (offset < size) {
ret = unpack_one(kvm, addr, tweak, offset, rc, rrc);
if (ret == -EAGAIN) {

106
arch/s390/kvm/vsie.c
View File

@ -13,6 +13,7 @@
#include <linux/bitmap.h>
#include <linux/sched/signal.h>
#include <linux/io.h>
#include <linux/mman.h>
#include <asm/gmap.h>
#include <asm/mmu_context.h>
@ -22,6 +23,11 @@
#include <asm/facility.h>
#include "kvm-s390.h"
#include "gaccess.h"
#include "gmap.h"
enum vsie_page_flags {
VSIE_PAGE_IN_USE = 0,
};
struct vsie_page {
struct kvm_s390_sie_block scb_s; /* 0x0000 */
@ -46,7 +52,18 @@ struct vsie_page {
gpa_t gvrd_gpa; /* 0x0240 */
gpa_t riccbd_gpa; /* 0x0248 */
gpa_t sdnx_gpa; /* 0x0250 */
__u8 reserved[0x0700 - 0x0258]; /* 0x0258 */
/*
* guest address of the original SCB. Remains set for free vsie
* pages, so we can properly look them up in our addr_to_page
* radix tree.
*/
gpa_t scb_gpa; /* 0x0258 */
/*
* Flags: must be set/cleared atomically after the vsie page can be
* looked up by other CPUs.
*/
unsigned long flags; /* 0x0260 */
__u8 reserved[0x0700 - 0x0268]; /* 0x0268 */
struct kvm_s390_crypto_cb crycb; /* 0x0700 */
__u8 fac[S390_ARCH_FAC_LIST_SIZE_BYTE]; /* 0x0800 */
};
@ -584,7 +601,6 @@ void kvm_s390_vsie_gmap_notifier(struct gmap *gmap, unsigned long start,
struct kvm *kvm = gmap->private;
struct vsie_page *cur;
unsigned long prefix;
struct page *page;
int i;
if (!gmap_is_shadow(gmap))
@ -594,10 +610,9 @@ void kvm_s390_vsie_gmap_notifier(struct gmap *gmap, unsigned long start,
* therefore we can safely reference them all the time.
*/
for (i = 0; i < kvm->arch.vsie.page_count; i++) {
page = READ_ONCE(kvm->arch.vsie.pages[i]);
if (!page)
cur = READ_ONCE(kvm->arch.vsie.pages[i]);
if (!cur)
continue;
cur = page_to_virt(page);
if (READ_ONCE(cur->gmap) != gmap)
continue;
prefix = cur->scb_s.prefix << GUEST_PREFIX_SHIFT;
@ -1345,6 +1360,20 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
return rc;
}
/* Try getting a given vsie page, returning "true" on success. */
static inline bool try_get_vsie_page(struct vsie_page *vsie_page)
{
if (test_bit(VSIE_PAGE_IN_USE, &vsie_page->flags))
return false;
return !test_and_set_bit(VSIE_PAGE_IN_USE, &vsie_page->flags);
}
/* Put a vsie page acquired through get_vsie_page / try_get_vsie_page. */
static void put_vsie_page(struct vsie_page *vsie_page)
{
clear_bit(VSIE_PAGE_IN_USE, &vsie_page->flags);
}
/*
* Get or create a vsie page for a scb address.
*
@ -1355,16 +1384,21 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
static struct vsie_page *get_vsie_page(struct kvm *kvm, unsigned long addr)
{
struct vsie_page *vsie_page;
struct page *page;
int nr_vcpus;
rcu_read_lock();
page = radix_tree_lookup(&kvm->arch.vsie.addr_to_page, addr >> 9);
vsie_page = radix_tree_lookup(&kvm->arch.vsie.addr_to_page, addr >> 9);
rcu_read_unlock();
if (page) {
if (page_ref_inc_return(page) == 2)
return page_to_virt(page);
page_ref_dec(page);
if (vsie_page) {
if (try_get_vsie_page(vsie_page)) {
if (vsie_page->scb_gpa == addr)
return vsie_page;
/*
* We raced with someone reusing + putting this vsie
* page before we grabbed it.
*/
put_vsie_page(vsie_page);
}
}
/*
@ -1375,36 +1409,40 @@ static struct vsie_page *get_vsie_page(struct kvm *kvm, unsigned long addr)
mutex_lock(&kvm->arch.vsie.mutex);
if (kvm->arch.vsie.page_count < nr_vcpus) {
page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO | GFP_DMA);
if (!page) {
vsie_page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO | GFP_DMA);
if (!vsie_page) {
mutex_unlock(&kvm->arch.vsie.mutex);
return ERR_PTR(-ENOMEM);
}
page_ref_inc(page);
kvm->arch.vsie.pages[kvm->arch.vsie.page_count] = page;
__set_bit(VSIE_PAGE_IN_USE, &vsie_page->flags);
kvm->arch.vsie.pages[kvm->arch.vsie.page_count] = vsie_page;
kvm->arch.vsie.page_count++;
} else {
/* reuse an existing entry that belongs to nobody */
while (true) {
page = kvm->arch.vsie.pages[kvm->arch.vsie.next];
if (page_ref_inc_return(page) == 2)
vsie_page = kvm->arch.vsie.pages[kvm->arch.vsie.next];
if (try_get_vsie_page(vsie_page))
break;
page_ref_dec(page);
kvm->arch.vsie.next++;
kvm->arch.vsie.next %= nr_vcpus;
}
radix_tree_delete(&kvm->arch.vsie.addr_to_page, page->index >> 9);
if (vsie_page->scb_gpa != ULONG_MAX)
radix_tree_delete(&kvm->arch.vsie.addr_to_page,
vsie_page->scb_gpa >> 9);
}
page->index = addr;
/* double use of the same address */
if (radix_tree_insert(&kvm->arch.vsie.addr_to_page, addr >> 9, page)) {
page_ref_dec(page);
/* Mark it as invalid until it resides in the tree. */
vsie_page->scb_gpa = ULONG_MAX;
/* Double use of the same address or allocation failure. */
if (radix_tree_insert(&kvm->arch.vsie.addr_to_page, addr >> 9,
vsie_page)) {
put_vsie_page(vsie_page);
mutex_unlock(&kvm->arch.vsie.mutex);
return NULL;
}
vsie_page->scb_gpa = addr;
mutex_unlock(&kvm->arch.vsie.mutex);
vsie_page = page_to_virt(page);
memset(&vsie_page->scb_s, 0, sizeof(struct kvm_s390_sie_block));
release_gmap_shadow(vsie_page);
vsie_page->fault_addr = 0;
@ -1412,14 +1450,6 @@ static struct vsie_page *get_vsie_page(struct kvm *kvm, unsigned long addr)
return vsie_page;
}
/* put a vsie page acquired via get_vsie_page */
static void put_vsie_page(struct kvm *kvm, struct vsie_page *vsie_page)
{
struct page *page = pfn_to_page(__pa(vsie_page) >> PAGE_SHIFT);
page_ref_dec(page);
}
int kvm_s390_handle_vsie(struct kvm_vcpu *vcpu)
{
struct vsie_page *vsie_page;
@ -1470,7 +1500,7 @@ out_unshadow:
out_unpin_scb:
unpin_scb(vcpu, vsie_page, scb_addr);
out_put:
put_vsie_page(vcpu->kvm, vsie_page);
put_vsie_page(vsie_page);
return rc < 0 ? rc : 0;
}
@ -1486,18 +1516,18 @@ void kvm_s390_vsie_init(struct kvm *kvm)
void kvm_s390_vsie_destroy(struct kvm *kvm)
{
struct vsie_page *vsie_page;
struct page *page;
int i;
mutex_lock(&kvm->arch.vsie.mutex);
for (i = 0; i < kvm->arch.vsie.page_count; i++) {
page = kvm->arch.vsie.pages[i];
vsie_page = kvm->arch.vsie.pages[i];
kvm->arch.vsie.pages[i] = NULL;
vsie_page = page_to_virt(page);
release_gmap_shadow(vsie_page);
/* free the radix tree entry */
radix_tree_delete(&kvm->arch.vsie.addr_to_page, page->index >> 9);
__free_page(page);
if (vsie_page->scb_gpa != ULONG_MAX)
radix_tree_delete(&kvm->arch.vsie.addr_to_page,
vsie_page->scb_gpa >> 9);
free_page((unsigned long)vsie_page);
}
kvm->arch.vsie.page_count = 0;
mutex_unlock(&kvm->arch.vsie.mutex);

681
arch/s390/mm/gmap.c
View File

File diff suppressed because it is too large Load Diff

2
arch/s390/mm/pgalloc.c
View File

@ -176,8 +176,6 @@ unsigned long *page_table_alloc(struct mm_struct *mm)
}
table = ptdesc_to_virt(ptdesc);
__arch_set_page_dat(table, 1);
/* pt_list is used by gmap only */
INIT_LIST_HEAD(&ptdesc->pt_list);
memset64((u64 *)table, _PAGE_INVALID, PTRS_PER_PTE);
memset64((u64 *)table + PTRS_PER_PTE, 0, PTRS_PER_PTE);
return table;

20
arch/s390/pci/pci_bus.c
View File

@ -331,6 +331,17 @@ error:
return rc;
}
static bool zpci_bus_is_isolated_vf(struct zpci_bus *zbus, struct zpci_dev *zdev)
{
struct pci_dev *pdev;
pdev = zpci_iov_find_parent_pf(zbus, zdev);
if (!pdev)
return true;
pci_dev_put(pdev);
return false;
}
int zpci_bus_device_register(struct zpci_dev *zdev, struct pci_ops *ops)
{
bool topo_is_tid = zdev->tid_avail;
@ -345,6 +356,15 @@ int zpci_bus_device_register(struct zpci_dev *zdev, struct pci_ops *ops)
topo = topo_is_tid ? zdev->tid : zdev->pchid;
zbus = zpci_bus_get(topo, topo_is_tid);
/*
* An isolated VF gets its own domain/bus even if there exists
* a matching domain/bus already
*/
if (zbus && zpci_bus_is_isolated_vf(zbus, zdev)) {
zpci_bus_put(zbus);
zbus = NULL;
}
if (!zbus) {
zbus = zpci_bus_alloc(topo, topo_is_tid);
if (!zbus)

56
arch/s390/pci/pci_iov.c
View File

@ -60,18 +60,35 @@ static int zpci_iov_link_virtfn(struct pci_dev *pdev, struct pci_dev *virtfn, in
return 0;
}
int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn)
/**
* zpci_iov_find_parent_pf - Find the parent PF, if any, of the given function
* @zbus: The bus that the PCI function is on, or would be added on
* @zdev: The PCI function
*
* Finds the parent PF, if it exists and is configured, of the given PCI function
* and increments its refcount. Th PF is searched for on the provided bus so the
* caller has to ensure that this is the correct bus to search. This function may
* be used before adding the PCI function to a zbus.
*
* Return: Pointer to the struct pci_dev of the parent PF or NULL if it not
* found. If the function is not a VF or has no RequesterID information,
* NULL is returned as well.
*/
struct pci_dev *zpci_iov_find_parent_pf(struct zpci_bus *zbus, struct zpci_dev *zdev)
{
int i, cand_devfn;
struct zpci_dev *zdev;
int i, vfid, devfn, cand_devfn;
struct pci_dev *pdev;
int vfid = vfn - 1; /* Linux' vfid's start at 0 vfn at 1*/
int rc = 0;
if (!zbus->multifunction)
return 0;
/* If the parent PF for the given VF is also configured in the
return NULL;
/* Non-VFs and VFs without RID available don't have a parent */
if (!zdev->vfn || !zdev->rid_available)
return NULL;
/* Linux vfid starts at 0 vfn at 1 */
vfid = zdev->vfn - 1;
devfn = zdev->rid & ZPCI_RID_MASK_DEVFN;
/*
* If the parent PF for the given VF is also configured in the
* instance, it must be on the same zbus.
* We can then identify the parent PF by checking what
* devfn the VF would have if it belonged to that PF using the PF's
@ -85,15 +102,26 @@ int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn
if (!pdev)
continue;
cand_devfn = pci_iov_virtfn_devfn(pdev, vfid);
if (cand_devfn == virtfn->devfn) {
rc = zpci_iov_link_virtfn(pdev, virtfn, vfid);
/* balance pci_get_slot() */
pci_dev_put(pdev);
break;
}
if (cand_devfn == devfn)
return pdev;
/* balance pci_get_slot() */
pci_dev_put(pdev);
}
}
return NULL;
}
int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn)
{
struct zpci_dev *zdev = to_zpci(virtfn);
struct pci_dev *pdev_pf;
int rc = 0;
pdev_pf = zpci_iov_find_parent_pf(zbus, zdev);
if (pdev_pf) {
/* Linux' vfids start at 0 while zdev->vfn starts at 1 */
rc = zpci_iov_link_virtfn(pdev_pf, virtfn, zdev->vfn - 1);
pci_dev_put(pdev_pf);
}
return rc;
}

7
arch/s390/pci/pci_iov.h
View File

@ -19,6 +19,8 @@ void zpci_iov_map_resources(struct pci_dev *pdev);
int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn);
struct pci_dev *zpci_iov_find_parent_pf(struct zpci_bus *zbus, struct zpci_dev *zdev);
#else /* CONFIG_PCI_IOV */
static inline void zpci_iov_remove_virtfn(struct pci_dev *pdev, int vfn) {}
@ -28,5 +30,10 @@ static inline int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *v
{
return 0;
}
static inline struct pci_dev *zpci_iov_find_parent_pf(struct zpci_bus *zbus, struct zpci_dev *zdev)
{
return NULL;
}
#endif /* CONFIG_PCI_IOV */
#endif /* __S390_PCI_IOV_h */

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